netdev - Re: [PATCH 2/2] IP_GRE: Linearize skb before csum.

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: <CAEP_g=_AebncQ6_tHDA0rN=ya4tAqpN2i8FuQ1hqa8mOgj_AJA@mail.gmail.com>
Date:	Tue, 22 Jan 2013 14:38:03 -0800
From:	Jesse Gross <jesse@...ira.com>
To:	Eric Dumazet <eric.dumazet@...il.com>
Cc:	David Miller <davem@...emloft.net>, pshelar@...ira.com,
	netdev@...r.kernel.org
Subject: Re: [PATCH 2/2] IP_GRE: Linearize skb before csum.

On Tue, Jan 22, 2013 at 2:15 PM, Eric Dumazet <eric.dumazet@...il.com> wrote:
> On Tue, 2013-01-22 at 17:08 -0500, David Miller wrote:
>> From: Eric Dumazet <eric.dumazet@...il.com>
>> Date: Tue, 22 Jan 2013 14:03:19 -0800
>>
>> > An application changing data provided on a sendfile() or vmsplice() cant
>> > really expect data integrity being respected, even if checksum are done
>> > by the NIC (TSO)
>> >
>> > So if data integrity is not respected, just send a bogus TX checksum.
>>
>> I disagree.
>>
>> As a quality of implementation decision, we should always compute
>> correct checksums, ragardless of whether the page contents can be
>> modified asynchronously during the packet transmit.
>
> The retransmits will compute the correct checksums.
>
> For a very unlikely operation from the user, we want to disable GSO on
> GRE.

We're currently enforcing this assumption in the rest of the network
stack - it's why we mask out scatter/gather capability in the NIC if
it isn't capable of checksumming the packet.

Packets with asynchronous changes may come from VMs, so it isn't
necessarily reasonable to tell people that they need to disable
offloads with certain use cases.

As Pravin said, pushing down the GSO to the lowest layer is the best
way to solve the problem.  However, I would argue that the current
behavior is not correct.
--
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