linux-kernel - Re: [PATCH v4 2/5] iommu/vt-d: Remove the pasid present check in prq_event

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: <68ecfa4b-e1a8-4569-932a-cd450391ccfa@intel.com>
Date: Tue, 29 Oct 2024 13:11:52 +0800
From: Yi Liu <yi.l.liu@...el.com>
To: Baolu Lu <baolu.lu@...ux.intel.com>, Joel Granados
	<joel.granados@...nel.org>, David Woodhouse <dwmw2@...radead.org>, "Joerg
 Roedel" <joro@...tes.org>, Will Deacon <will@...nel.org>, Robin Murphy
	<robin.murphy@....com>, Jason Gunthorpe <jgg@...pe.ca>, Kevin Tian
	<kevin.tian@...el.com>, Klaus Jensen <its@...elevant.dk>
CC: <linux-kernel@...r.kernel.org>, <iommu@...ts.linux.dev>, Klaus Jensen
	<k.jensen@...sung.com>
Subject: Re: [PATCH v4 2/5] iommu/vt-d: Remove the pasid present check in
 prq_event_thread

On 2024/10/28 16:23, Baolu Lu wrote:
> On 2024/10/28 15:50, Yi Liu wrote:
>> On 2024/10/16 05:08, Joel Granados wrote:
>>> From: Klaus Jensen <k.jensen@...sung.com>
>>>
>>> PASID is not strictly needed when handling a PRQ event; remove the check
>>> for the pasid present bit in the request. This change was not included
>>> in the creation of prq.c to emphasize the change in capability checks
>>> when handing PRQ events.
>>>
>>> Signed-off-by: Klaus Jensen <k.jensen@...sung.com>
>>> Reviewed-by: Kevin Tian <kevin.tian@...el.com>
>>> Signed-off-by: Joel Granados <joel.granados@...nel.org>
>>
>> looks like the PRQ draining is missed for the PRI usage. When a pasid
>> entry is destroyed, it might need to add helper similar to the
>> intel_drain_pasid_prq() to drain PRQ for the non-pasid usage.
> 
> Perhaps we can move intel_drain_pasid_prq() into
> intel_pasid_tear_down_entry(), indicating that once a translation is
> removed from the pasid and PRI is enabled on the device, the page
> requests for the pasid should be flushed.
> 

yes, something like the below patch but no flag to opt-out the PRQ drain.

https://lore.kernel.org/linux-iommu/20241018055402.23277-3-yi.l.liu@intel.com/

-- 
Regards,
Yi Liu