netdev - Re: [PATCH V3 03/10] PCI/TPH: Add pci=notph to prevent use of TPH

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: <4304146d-9bcd-422f-b4dd-79b4a74329cb@amd.com>
Date: Wed, 24 Jul 2024 15:08:58 -0500
From: Wei Huang <wei.huang2@....com>
To: Bjorn Helgaas <helgaas@...nel.org>,
 Alejandro Lucero Palau <alucerop@....com>
Cc: linux-pci@...r.kernel.org, linux-kernel@...r.kernel.org,
 linux-doc@...r.kernel.org, netdev@...r.kernel.org,
 Jonathan.Cameron@...wei.com, corbet@....net, davem@...emloft.net,
 edumazet@...gle.com, kuba@...nel.org, pabeni@...hat.com,
 alex.williamson@...hat.com, gospo@...adcom.com, michael.chan@...adcom.com,
 ajit.khaparde@...adcom.com, somnath.kotur@...adcom.com,
 andrew.gospodarek@...adcom.com, manoj.panicker2@....com,
 Eric.VanTassell@....com, vadim.fedorenko@...ux.dev, horms@...nel.org,
 bagasdotme@...il.com, bhelgaas@...gle.com
Subject: Re: [PATCH V3 03/10] PCI/TPH: Add pci=notph to prevent use of TPH



On 7/24/24 10:36, Bjorn Helgaas wrote:
> On Wed, Jul 24, 2024 at 03:45:34PM +0100, Alejandro Lucero Palau wrote:
>> On 7/17/24 21:55, Wei Huang wrote:
>>> TLP headers with incorrect steering tags (e.g. caused by buggy driver)
>>> can potentially cause issues when the system hardware consumes the tags.
>>> Provide a kernel option, with related helper functions, to completely
>>> prevent TPH from being enabled.
>>
>> Maybe rephrase it for including a potential buggy device, including the cpu.
>>
>> Also, what about handling this with a no-tph-allow device list instead of a
>> generic binary option for the whole system?
>>
>> Foreseeing some buggy or poor-performance implementations, or specific use
>> cases where it could be counterproductive, maybe supporting both options.
> 
> Makes sense if/when we need it.  IMO no point in adding an empty list
> of known-broken devices.

We can add quirks.c, or something similar later, after TPH support is
enabled.