From: Jason Gunthorpe <jgg@ziepe.ca>
To: Daniel Drake <dan@reactivated.net>
Cc: "Joerg Roedel (AMD)" <joro@8bytes.org>,
Will Deacon <will@kernel.org>,
Robin Murphy <robin.murphy@arm.com>,
Rob Herring <robh@kernel.org>,
Krzysztof Kozlowski <krzk+dt@kernel.org>,
Conor Dooley <conor+dt@kernel.org>,
Florian Fainelli <florian.fainelli@broadcom.com>,
Broadcom internal kernel review list
<bcm-kernel-feedback-list@broadcom.com>,
iommu@lists.linux.dev, linux-kernel@vger.kernel.org,
devicetree@vger.kernel.org, linux-rpi-kernel@lists.infradead.org,
linux-arm-kernel@lists.infradead.org,
nick.hollinghurst@raspberrypi.com
Subject: Re: [PATCH 5/6] iommu: Add Broadcom BCM2712 IOMMU driver
Date: Sat, 18 Jul 2026 11:32:33 -0300 [thread overview]
Message-ID: <20260718143233.GE701389@ziepe.ca> (raw)
In-Reply-To: <57f5675c-8bcd-4022-978b-9f7933bb0032@reactivated.net>
On Sat, Jul 18, 2026 at 09:39:48AM +0100, Daniel Drake wrote:
> I don't think I can use that because this setup uses an IOVA aperture at
> base 0xA00000000, whereas generic_pt assumes it is managing a 0-indexed
> virtual address space. So the driver has to intercept every incoming IOVA
> and translate for the aperture, see how map_pages calls:
When you say aperture here you mean we place an IOPTE at VA 0 but the
dma_addr_t for that has to be adjusted to 0xA00000000 ?
I wonder if DT can do this with dma-ranges or something, we have many
other conditions where the dma_addr_t and the internal physical have
offsets..
> I was wondering about making iommupt understand apertures and
> translate accordingly, but I imagine you would want to keep that
> kind of thing out of the generic fast path?
We already have pt_full_va_prefix() which isn't strictly an offset but
it it probably matches what this HW does.
You can implement it in the broadcom format and return the prefix value.
So long as the vasz fits within those trailing 0s. That's basically
free and has no runtime cost on other formats.
Jason
next prev parent reply other threads:[~2026-07-18 14:32 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-12 21:18 [PATCH 0/6] Add support for Broadcom BCM2712 IOMMU driver (Raspberry Pi 5) Daniel Drake
2026-07-12 21:18 ` [PATCH 1/6] generic_pt: allow missing sw bit in DMA_INCOHERENT case Daniel Drake
2026-07-12 22:00 ` Jason Gunthorpe
2026-07-12 21:18 ` [PATCH 2/6] iommupt: allow full-table contiguous leaves in unit tests Daniel Drake
2026-07-12 22:02 ` Jason Gunthorpe
2026-07-12 21:18 ` [PATCH 3/6] dt-bindings: iommu: Add Broadcom BCM2712 IOMMU Daniel Drake
2026-07-13 9:16 ` Krzysztof Kozlowski
2026-07-12 21:18 ` [PATCH 4/6] iommu/generic_pt: Add Broadcom BCM2712 page table format Daniel Drake
2026-07-12 22:05 ` Jason Gunthorpe
2026-07-13 10:02 ` Nick Hollinghurst
2026-07-13 12:00 ` Jason Gunthorpe
2026-07-12 21:18 ` [PATCH 5/6] iommu: Add Broadcom BCM2712 IOMMU driver Daniel Drake
2026-07-12 22:11 ` Jason Gunthorpe
2026-07-18 8:39 ` Daniel Drake
2026-07-18 14:32 ` Jason Gunthorpe [this message]
2026-07-12 21:18 ` [PATCH 6/6] arm64: dts: broadcom: bcm2712: Add GPU IOMMU and IOMMU cache nodes Daniel Drake
2026-07-13 9:17 ` Krzysztof Kozlowski
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=20260718143233.GE701389@ziepe.ca \
--to=jgg@ziepe.ca \
--cc=bcm-kernel-feedback-list@broadcom.com \
--cc=conor+dt@kernel.org \
--cc=dan@reactivated.net \
--cc=devicetree@vger.kernel.org \
--cc=florian.fainelli@broadcom.com \
--cc=iommu@lists.linux.dev \
--cc=joro@8bytes.org \
--cc=krzk+dt@kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rpi-kernel@lists.infradead.org \
--cc=nick.hollinghurst@raspberrypi.com \
--cc=robh@kernel.org \
--cc=robin.murphy@arm.com \
--cc=will@kernel.org \
/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