linux-kernel - Re: [PATCH] iommufd: Enforce IOMMU_RESV_SW_MSI upon hwpt

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 for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <ZqvIQFsgUGjqqjmF@Asurada-Nvidia>
Date: Thu, 1 Aug 2024 10:39:12 -0700
From: Nicolin Chen <nicolinc@...dia.com>
To: Jason Gunthorpe <jgg@...dia.com>
CC: "Tian, Kevin" <kevin.tian@...el.com>, "Liu, Yi L" <yi.l.liu@...el.com>,
	"iommu@...ts.linux.dev" <iommu@...ts.linux.dev>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] iommufd: Enforce IOMMU_RESV_SW_MSI upon hwpt_paging
 allocation

On Thu, Aug 01, 2024 at 10:28:48AM -0300, Jason Gunthorpe wrote:
> On Wed, Jul 31, 2024 at 11:23:24AM -0700, Nicolin Chen wrote:
> > > If we really want to go this route I wonder whether a per-IOMMU
> > > get_resv_regions() API should first exist then there is a clear definition
> > > what types are per-IOMMU and what are not.
> > 
> > Probably it'd be necessary.
> 
> But domains can cross IOMMU's as well, it is not per-iommu you are
> after but hardwired per-IOMMU driver type.
> 
> What was the issue with trying to fix this on the nesting attach side?

No, seems that we all agreed on enforcing IOVAs to the parent 
HWPT, so we will Just go on the nesting attach side.

Thanks
Nicolin