From: Catalin Marinas <catalin.marinas@arm.com>
To: Jason Gunthorpe <jgg@nvidia.com>
Cc: Piotr Jaroszynski <pjaroszynski@nvidia.com>,
Ryan Roberts <ryan.roberts@arm.com>,
Will Deacon <will@kernel.org>,
linux-arm-kernel@lists.infradead.org, linux-mm@kvack.org,
Alistair Popple <apopple@nvidia.com>,
John Hubbard <jhubbard@nvidia.com>, Zi Yan <ziy@nvidia.com>,
Breno Leitao <leitao@debian.org>,
stable@vger.kernel.org
Subject: Re: [PATCH] arm64: contpte: fix set_access_flags() no-op check for SMMU/ATS faults
Date: Wed, 4 Mar 2026 17:25:10 +0000 [thread overview]
Message-ID: <aahq9i7XNYOBG49y@arm.com> (raw)
In-Reply-To: <20260304153949.GP972761@nvidia.com>
On Wed, Mar 04, 2026 at 11:39:49AM -0400, Jason Gunthorpe wrote:
> On Wed, Mar 04, 2026 at 03:01:51PM +0000, Catalin Marinas wrote:
> > Good point. For the AF bit, the hardware is not allowed to cache it in
> > the TLB, so we can't get an AF fault for an unrelated VA nearby.
>
> The way we have read the spec is there is no restriction on what PTE
> the HW accesses when it encounters a CONT group.
Trying to find some rule in the Arm ARM, it only says that hardware
AF/DBM only happens to a single entry but it is not specific about which
in a contiguous range.
So yeah, it's better not to assume anything. If it helps software, we
could tighten the architecture but I think the benefit is marginal.
--
Catalin
next prev parent reply other threads:[~2026-03-04 17:25 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-03 6:37 Piotr Jaroszynski
2026-03-03 7:19 ` James Houghton
2026-03-03 12:45 ` Jason Gunthorpe
2026-03-03 21:40 ` Piotr Jaroszynski
2026-03-03 8:38 ` Ryan Roberts
2026-03-03 18:40 ` Piotr Jaroszynski
2026-03-03 19:12 ` Jason Gunthorpe
2026-03-04 12:20 ` Ryan Roberts
2026-03-04 13:44 ` Jason Gunthorpe
2026-03-04 11:17 ` Catalin Marinas
2026-03-04 13:43 ` Jason Gunthorpe
2026-03-04 15:01 ` Catalin Marinas
2026-03-04 15:39 ` Jason Gunthorpe
2026-03-04 17:16 ` Piotr Jaroszynski
2026-03-04 17:25 ` Catalin Marinas [this message]
2026-03-04 17:37 ` Breno Leitao
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=aahq9i7XNYOBG49y@arm.com \
--to=catalin.marinas@arm.com \
--cc=apopple@nvidia.com \
--cc=jgg@nvidia.com \
--cc=jhubbard@nvidia.com \
--cc=leitao@debian.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-mm@kvack.org \
--cc=pjaroszynski@nvidia.com \
--cc=ryan.roberts@arm.com \
--cc=stable@vger.kernel.org \
--cc=will@kernel.org \
--cc=ziy@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox