linux-kernel - Re: [PATCH v2 14/18] iommu/arm-smmu-v3: Support domains with shared CDs

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] [day] [month] [year] [list]

Date:   Tue, 11 Jul 2023 10:53:53 -0300
From:   Jason Gunthorpe <jgg@...dia.com>
To:     "Zhang, Tina" <tina.zhang@...el.com>
Cc:     Michael Shavit <mshavit@...gle.com>, Will Deacon <will@...nel.org>,
        Robin Murphy <robin.murphy@....com>,
        Joerg Roedel <joro@...tes.org>,
        "jean-philippe@...aro.org" <jean-philippe@...aro.org>,
        "nicolinc@...dia.com" <nicolinc@...dia.com>,
        "baolu.lu@...ux.intel.com" <baolu.lu@...ux.intel.com>,
        "linux-arm-kernel@...ts.infradead.org" 
        <linux-arm-kernel@...ts.infradead.org>,
        "iommu@...ts.linux.dev" <iommu@...ts.linux.dev>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v2 14/18] iommu/arm-smmu-v3: Support domains with shared
 CDs

On Tue, Jul 11, 2023 at 12:26:56AM +0000, Zhang, Tina wrote:

> The motivation is mainly to for performance optimization for vIOMMU,
> though it could also benefit native world.
> 
> Currently, in invalidate_range() callback implemented by VT-d
> driver, due to lacking sva_domain knowledge (i.e.,
> intel_invalidate_range() doesn't know which IOMMUs' IOTLB should be
> invalidated), intel_invalidate_range() just performs IOMMU IOTLB per
> device and that leads to superfluous IOTLB invalidations. 

You get the sva_domain from container_of on the notifier

The sva_domain has a list of all the devices and iommu's that it is
connected to

The driver optimizes the invalidations based on the list.

The core code de-duplicates the sva domain so there is usually only
one.

If someone creates two SVA domains then the driver is less optimal, oh
well.

The driver should not look inside the mm_struct and certainly should
never try to get a "SVA domain" from it.

Jason