linux-kernel - Re: [PATCH] intel-iommu: Manage iommu

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: <1321733519.15493.81.camel@shinybook.infradead.org>
Date:	Sat, 19 Nov 2011 20:11:59 +0000
From:	David Woodhouse <dwmw2@...radead.org>
To:	Chris Wright <chrisw@...s-sol.org>
Cc:	Alex Williamson <alex.williamson@...hat.com>,
	rajesh.sankaran@...el.com, iommu@...ts.linux-foundation.org,
	linux-pci@...r.kernel.org, linux-kernel@...r.kernel.org,
	ddutile@...hat.com
Subject: Re: [PATCH] intel-iommu: Manage iommu_coherency globally

On Sat, 2011-11-19 at 11:17 -0800, Chris Wright wrote:
> > Hm, it seems I lied to you about this. The non-coherent mode isn't just
> > a historical mistake; it's configurable by the BIOS, and we actually
> > encourage people to use the non-coherent mode because it makes the
> > hardware page-walk faster — so reduces the latency for IOTLB misses.
> 
> Interesting because for the workloads I've tested it's the exact opposite.
> Tested w/ BIOS enabling and disabling coherency, and w/ non-coherent
> access and streaming DMA (i.e. bare metal NIC bw testing)...the IOMMU
> added smth like 10% when non-coherent vs. coherent. 

Right. I specifically said "latency for IOTLB misses". That is the main
reason we apparently advise BIOS authors to use non-coherent mode.

(Of course, the fact that we're letting the BIOS control this at all
means that we obviously haven't learned *any* lessons from the last few
years of pain with VT-d enabling and BIOS bugs. It should have been
under OS control. But that's a separate, stunningly depressing, issue.)

Of course, The *overall* performance sucks rocks if we are in
non-coherent mode. The bare-metal NIC bandwidth testing is the obvious
test case for it, and thanks for providing ballpark numbers for that.
They perfectly back up the qualitative remarks I made to Rajesh
yesterday on exactly this topic.

-- 
dwmw2

Download attachment "smime.p7s" of type "application/x-pkcs7-signature" (5818 bytes)