netdev - Re: inbound connection problems when "netlink: test for all flags of the NLM_F

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20110118184730.GD4202@del.dom.local>
Date:	Tue, 18 Jan 2011 19:47:30 +0100
From:	Jarek Poplawski <jarkao2@...il.com>
To:	Jan Engelhardt <jengelh@...ozas.de>
Cc:	Alessandro Suardi <alessandro.suardi@...il.com>,
	jamal <hadi@...erus.ca>, David Miller <davem@...emloft.net>,
	pablo@...filter.org, arthur.marsh@...ernode.on.net,
	eric.dumazet@...il.com, netdev@...r.kernel.org
Subject: Re: inbound connection problems when "netlink: test for all flags
 of the NLM_F_DUMP composite" commit applied

On Tue, Jan 18, 2011 at 07:28:52PM +0100, Jarek Poplawski wrote:
> On Tue, Jan 18, 2011 at 07:24:40PM +0100, Jan Engelhardt wrote:
> > 
> > On Tuesday 2011-01-18 19:10, Alessandro Suardi wrote:
> > >On Tue, Jan 18, 2011 at 6:23 PM, Jarek Poplawski <jarkao2@...il.com> wrote:
> > >>
> > >> NLM_F_DUMP flags should be applied to GET requests only, eg. rtnetlink
> > >> tests message type to verify this. Since genetlink can't do the same
> > >> use "practical" test for ops->dumpit (assuming NEW request won't be
> > >> mixed with GET).
> ...
> > >2.6.37-git18 + netlink revert + this patch
> > > - fixes Avahi
> > > - breaks acpid
> > >Starting acpi daemon: RTNETLINK1 answers: Operation not supported
> > >acpid: error talking to the kernel via netlink
> > 
> > Deducing from that, it is a GET-like request that was sent by acpid, 
> > and the message type is one that has both a dumpit and a doit function.
> > So if EOPNOTSUPP now occurs on all message types that have both dumpit 
> > and doit, you should have broken a lot more than just acpid.
> 
> Right, we need something better here.

On the other hand, until there is something better, we might try to
fix it at least for "normal" dumpit cases?

Alessandro, could you try (with the netlink revert)?

Thanks,
Jarek P.

---
diff -Nurp a/net/netlink/genetlink.c b/net/netlink/genetlink.c
--- a/net/netlink/genetlink.c	2011-01-18 16:58:16.000000000 +0100
+++ b/net/netlink/genetlink.c	2011-01-18 19:36:25.000000000 +0100
@@ -519,15 +519,14 @@ static int genl_rcv_msg(struct sk_buff *
 	    security_netlink_recv(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	if (nlh->nlmsg_flags & NLM_F_DUMP) {
-		if (ops->dumpit == NULL)
-			return -EOPNOTSUPP;
-
-		genl_unlock();
-		err = netlink_dump_start(net->genl_sock, skb, nlh,
-					 ops->dumpit, ops->done);
-		genl_lock();
-		return err;
+	if (ops->dumpit) {
+		if (nlh->nlmsg_flags & NLM_F_DUMP) {
+			genl_unlock();
+			err = netlink_dump_start(net->genl_sock, skb, nlh,
+						 ops->dumpit, ops->done);
+			genl_lock();
+			return err;
+		}
 	}
 
 	if (ops->doit == NULL)
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html