linux-kernel - Re: [PATCH v2 0/5] iommu/vt-d: Ensure memory ordering in context & root entry updates

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: <aV1C5tG_SRMe1yvL@mitya-t14-2025>
Date: Tue, 6 Jan 2026 18:14:14 +0100
From: Dmytro Maluka <dmaluka@...omium.org>
To: Jason Gunthorpe <jgg@...pe.ca>
Cc: David Woodhouse <dwmw2@...radead.org>,
	Lu Baolu <baolu.lu@...ux.intel.com>, iommu@...ts.linux.dev,
	Joerg Roedel <joro@...tes.org>, Will Deacon <will@...nel.org>,
	Robin Murphy <robin.murphy@....com>, linux-kernel@...r.kernel.org,
	"Vineeth Pillai (Google)" <vineeth@...byteword.org>,
	Aashish Sharma <aashish@...hishsharma.net>,
	Grzegorz Jaszczyk <jaszczyk@...omium.org>,
	Chuanxiao Dong <chuanxiao.dong@...el.com>,
	Kevin Tian <kevin.tian@...el.com>
Subject: Re: [PATCH v2 0/5] iommu/vt-d: Ensure memory ordering in context &
 root entry updates

On Tue, Jan 06, 2026 at 12:45:18PM -0400, Jason Gunthorpe wrote:
> On Tue, Jan 06, 2026 at 04:50:11PM +0100, Dmytro Maluka wrote:
> > So we'd better make sure that if it happens before the barrier (i.e.
> > when the device is not supposed to do DMA), the compiler (and thus
> > the CPU) doesn't set the present bit, so it stays non-present, so
> > the IOMMU will block this unexpected/malicious DMA?
> 
> It is true that any write to the dword containing the present bit
> (only!) should probably use WRITE_ONCE.

Yeah, I agree that for other dwords within an entry it isn't necessary.

So, when it comes to the actual code, it's not like the Intel IOMMU
driver has lots of WRITE_ONCE spread all over the code. It's only in
pasid_set_bits() and pasid_clear_entry(). Though, since pasid_set_bits()
is used for setting any bits, as a result, WRITE_ONCE is also done for
dwords that don't need it, but that doesn't hurt either.