netlink: change return-value logic of netlink_broadcast()

Currently, netlink_broadcast() reports errors to the caller if no
messages at all were delivered:

1) If, at least, one message has been delivered correctly, returns 0.
2) Otherwise, if no messages at all were delivered due to skb_clone()
   failure, return -ENOBUFS.
3) Otherwise, if there are no listeners, return -ESRCH.

With this patch, the caller knows if the delivery of any of the
messages to the listeners have failed:

1) If it fails to deliver any message (for whatever reason), return
   -ENOBUFS.
2) Otherwise, if all messages were delivered OK, returns 0.
3) Otherwise, if no listeners, return -ESRCH.

In the current ctnetlink code and in Netfilter in general, we can add
reliable logging and connection tracking event delivery by dropping the
packets whose events were not successfully delivered over Netlink. Of
course, this option would be settable via /proc as this approach reduces
performance (in terms of filtered connections per seconds by a stateful
firewall) but providing reliable logging and event delivery (for
conntrackd) in return.

This patch also changes some clients of netlink_broadcast() that
may report ENOBUFS errors via printk. This error handling is not
of any help. Instead, the userspace daemons that are listening to
those netlink messages should resync themselves with the kernel-side
if they hit ENOBUFS.

BTW, netlink_broadcast() clients include those that call
cn_netlink_send(), nlmsg_multicast() and genlmsg_multicast() since they
internally call netlink_broadcast() and return its error value.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 13 insertions, 16 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 9eb895c7a2a9..6ee69c27f806 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -950,6 +950,7 @@ struct netlink_broadcast_data {
         u32 pid;
         u32 group;
         int failure;
+        int delivery_failure;
         int congested;
         int delivered;
         gfp_t allocation;
@@ -999,6 +1000,7 @@ static inline int do_one_broadcast(struct sock *sk,
                 p->skb2 = NULL;
         } else if ((val = netlink_broadcast_deliver(sk, p->skb2)) < 0) {
                 netlink_overrun(sk);
+                p->delivery_failure = 1;
         } else {
                 p->congested |= val;
                 p->delivered = 1;
@@ -1025,6 +1027,7 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid,
         info.pid = pid;
         info.group = group;
         info.failure = 0;
+        info.delivery_failure = 0;
         info.congested = 0;
         info.delivered = 0;
         info.allocation = allocation;
@@ -1045,13 +1048,14 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid,
         if (info.skb2)
                 kfree_skb(info.skb2);
 
+        if (info.delivery_failure || info.failure)
+                return -ENOBUFS;
+
         if (info.delivered) {
                 if (info.congested && (allocation & __GFP_WAIT))
                         yield();
                 return 0;
         }
-        if (info.failure)
-                return -ENOBUFS;
         return -ESRCH;
 }
 EXPORT_SYMBOL(netlink_broadcast);
diff --git a/net/wimax/op-msg.c b/net/wimax/op-msg.c
index cb3b4ad53683..5d149c1b5f0d 100644
--- a/net/wimax/op-msg.c
+++ b/net/wimax/op-msg.c
@@ -258,7 +258,6 @@ EXPORT_SYMBOL_GPL(wimax_msg_len);
  */
 int wimax_msg_send(struct wimax_dev *wimax_dev, struct sk_buff *skb)
 {
-        int result;
         struct device *dev = wimax_dev->net_dev->dev.parent;
         void *msg = skb->data;
         size_t size = skb->len;
@@ -266,11 +265,9 @@ int wimax_msg_send(struct wimax_dev *wimax_dev, struct sk_buff *skb)
 
         d_printf(1, dev, "CTX: wimax msg, %zu bytes\n", size);
         d_dump(2, dev, msg, size);
-        result = genlmsg_multicast(skb, 0, wimax_gnl_mcg.id, GFP_KERNEL);
-        d_printf(1, dev, "CTX: genl multicast result %d\n", result);
-        if (result == -ESRCH)   /* Nobody connected, ignore it */
-                result = 0;     /* btw, the skb is freed already */
-        return result;
+        genlmsg_multicast(skb, 0, wimax_gnl_mcg.id, GFP_KERNEL);
+        d_printf(1, dev, "CTX: genl multicast done\n");
+        return 0;
 }
 EXPORT_SYMBOL_GPL(wimax_msg_send);
 
diff --git a/net/wimax/stack.c b/net/wimax/stack.c
index 3869c0327882..a0ee76b52510 100644
--- a/net/wimax/stack.c
+++ b/net/wimax/stack.c
@@ -163,16 +163,12 @@ int wimax_gnl_re_state_change_send(
         struct device *dev = wimax_dev_to_dev(wimax_dev);
         d_fnstart(3, dev, "(wimax_dev %p report_skb %p)\n",
                   wimax_dev, report_skb);
-        if (report_skb == NULL)
+        if (report_skb == NULL) {
+                result = -ENOMEM;
                 goto out;
-        genlmsg_end(report_skb, header);
-        result = genlmsg_multicast(report_skb, 0, wimax_gnl_mcg.id, GFP_KERNEL);
-        if (result == -ESRCH)   /* Nobody connected, ignore it */
-                result = 0;     /* btw, the skb is freed already */
-        if (result < 0) {
-                dev_err(dev, "RE_STCH: Error sending: %d\n", result);
-                nlmsg_free(report_skb);
         }
+        genlmsg_end(report_skb, header);
+        genlmsg_multicast(report_skb, 0, wimax_gnl_mcg.id, GFP_KERNEL);
 out:
         d_fnend(3, dev, "(wimax_dev %p report_skb %p) = %d\n",
                 wimax_dev, report_skb, result);