ipoe: flush sessions left by a previous instance with a single command

On startup accel-pppd is expected to drop everything a previous instance
left behind in the kernel. For sessions it did so by dumping them with
IPOE_CMD_GET and sending one IPOE_CMD_DELETE per ifindex. That dump was
written for the session backup code removed in 1972a7e5c and was never
adapted to its new, destructive role:

 - it was issued on the socket subscribed to the packet multicast group,
   so it competed with the notifications that the still attached stale
   rx handlers keep generating; on a loaded box the receive buffer
   overruns and rtnl_dump_filter() gives up with ENOBUFS,
 - its return value was discarded, so such a failure was silent,
 - it ran before the interfaces were detached, which is what produces
   those notifications in the first place,
 - it was skipped entirely when the multicast group could not be
   resolved, again with nothing but a warning about packet handling,
 - and every session cost a socket, a round trip, a grace period and a
   full unregister_netdev().

Whatever it missed stays in the kernel forever: the daemon has no record
of those sessions, so nothing ever deletes them, and every subscriber
later assigned one of their addresses is refused with EEXIST by
IPOE_CMD_MODIFY.

Add IPOE_CMD_FLUSH, which unlinks all sessions in one go, waits for a
single grace period and unregisters the devices with
unregister_netdevice_many(), and use it instead. The old path is kept as
a fallback for a module predating the command, which is reported as
EOPNOTSUPP, and now checks its return value and uses a private socket.

Reorder init() so the interfaces are detached before the multicast group
is joined, and so the flush also runs when only the group lookup failed.

2 files changed, 55 insertions, 0 deletions

diff --git a/drivers/ipoe/ipoe.c b/drivers/ipoe/ipoe.c
index 73926994..8f1c852b 100644
--- a/drivers/ipoe/ipoe.c
+++ b/drivers/ipoe/ipoe.c
@@ -1420,6 +1420,52 @@ out_unlock:
 	return ret;
 }
 
+static int ipoe_nl_cmd_flush(struct sk_buff *skb, struct genl_info *info)
+{
+	struct ipoe_session *ses;
+	LIST_HEAD(list);
+	LIST_HEAD(kill_list);
+
+	down(&ipoe_wlock);
+
+	list_splice_init(&ipoe_list2, &list);
+
+	list_for_each_entry(ses, &list, entry2) {
+		if (ses->peer_addr)
+			list_del_rcu(&ses->entry);
+		if (ses->u.hwaddr_u)
+			list_del_rcu(&ses->entry3);
+	}
+
+	up(&ipoe_wlock);
+
+	if (list_empty(&list))
+		return 0;
+
+	/* a single grace period covers the whole batch */
+	synchronize_rcu();
+
+	list_for_each_entry(ses, &list, entry2) {
+		while (atomic_read(&ses->refs))
+			schedule_timeout_uninterruptible(1);
+
+		if (ses->link_dev) {
+			dev_put(ses->link_dev);
+			ses->link_dev = NULL;
+		}
+	}
+
+	rtnl_lock();
+	list_for_each_entry(ses, &list, entry2)
+		unregister_netdevice_queue(ses->dev, &kill_list);
+	unregister_netdevice_many(&kill_list);
+	rtnl_unlock();
+
+	/* the sessions are freed by now, do not touch 'list' again */
+
+	return 0;
+}
+
 static int ipoe_nl_cmd_modify(struct sk_buff *skb, struct genl_info *info)
 {
 	int ret = -EINVAL, r = 0;
@@ -1896,6 +1942,14 @@ static const struct genl_ops ipoe_nl_ops[] = {
 		.policy = ipoe_nl_policy,
 #endif
 	},
+	{
+		.cmd = IPOE_CMD_FLUSH,
+		.doit = ipoe_nl_cmd_flush,
+		.flags = GENL_ADMIN_PERM,
+#if LINUX_VERSION_CODE < KERNEL_VERSION(5,2,0)
+		.policy = ipoe_nl_policy,
+#endif
+	},
 };
 
 #if LINUX_VERSION_CODE < KERNEL_VERSION(3,13,0) && RHEL_MAJOR < 7
diff --git a/drivers/ipoe/ipoe.h b/drivers/ipoe/ipoe.h
index 4097e2da..2d041c50 100644
--- a/drivers/ipoe/ipoe.h
+++ b/drivers/ipoe/ipoe.h
@@ -16,6 +16,7 @@ enum {
 	IPOE_CMD_DEL_EXCLUDE,
 	IPOE_CMD_ADD_NET,
 	IPOE_CMD_DEL_NET,
+	IPOE_CMD_FLUSH,
 	__IPOE_CMD_MAX,
 };