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: <CALnjE+qgYP50ONksYbF2uT1iLSPQ=jvOhsh72uFDoTXGTemJ2g@mail.gmail.com>
Date:	Tue, 22 Jan 2013 14:30:30 -0800
From:	Pravin Shelar <pshelar@...ira.com>
To:	Eric Dumazet <eric.dumazet@...il.com>
Cc:	David Miller <davem@...emloft.net>, netdev@...r.kernel.org,
	Jesse Gross <jesse@...ira.com>
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.
>
> If so, just revert my GSO patch.
>
> This is plain stupid to cook GSO packets and then linearize them, adding
> an extra copy and a point of failure, as allocating a 128K skb->head
> will probably fail very easily.
>
OK.
This overhead can be avoided with GRE segmentation offload. I will
send that series soon.

> Now, tcp_sendmsg() cooked skb are fine, and this patch assumes they are
> not.
>
> This patch is absolutely wrong.
>
>
--
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