From: Thierry Reding <thierry.reding@kernel.org>
To: Thierry Reding <thierry.reding@kernel.org>,
Jon Hunter <jonathanh@nvidia.com>,
Mikko Perttunen <mperttunen@nvidia.com>
Cc: Sumit Gupta <sumitg@nvidia.com>,
devicetree@vger.kernel.org, linux-tegra@vger.kernel.org
Subject: [PATCH 1/3] arm64: tegra: Fix address translation on Tegra264
Date: Fri, 30 Oct 2026 15:10:59 +0100 [thread overview]
Message-ID: <20261030141101.845044-1-thierry.reding@kernel.org> (raw)
From: Thierry Reding <treding@nvidia.com>
The TOP chiplet has a region of memory at the local offset 0x20000000.
This region is currently unused, so remapping the non-prefetchable, 32
bit PCI region through that region works fine. However, subsequent
changes will need to make the actual hardware within this region
available, which then causes an address translation conflict.
Fix this by moving the interim translation address (note that this is
purely used for address translation in the operating system and never
used by the driver code) to an unused region of the chiplet's address
space.
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
arch/arm64/boot/dts/nvidia/tegra264.dtsi | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/arm64/boot/dts/nvidia/tegra264.dtsi b/arch/arm64/boot/dts/nvidia/tegra264.dtsi
index 5ab34cd09a3d..ddcc6d3ac9f0 100644
--- a/arch/arm64/boot/dts/nvidia/tegra264.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra264.dtsi
@@ -3420,9 +3420,9 @@ bus@8100000000 {
#address-cells = <2>;
#size-cells = <2>;
- ranges = <0x00 0x00000000 0x81 0x00000000 0x00 0x20000000>, /* MMIO (512 MiB) */
- <0x00 0x20000000 0x00 0x20000000 0x00 0x20000000>, /* non-prefetchable memory (32-bit, 512 MiB) */
- <0x00 0x40000000 0x81 0x40000000 0x00 0x20000000>, /* MMIO (512 MiB) */
+ ranges = <0x00 0x00000000 0x81 0x00000000 0x00 0x18000000>, /* MMIO (384 MiB) */
+ <0x00 0x18000000 0x00 0x20000000 0x00 0x08000000>, /* non-prefetchable memory (32-bit, 128 MiB) */
+ <0x00 0x20000000 0x81 0x20000000 0x00 0x30000000>, /* MMIO (768 MiB) */
<0xa8 0x80000000 0xa8 0x80000000 0x57 0x80000000>; /* I/O, ECAM, prefetchable memory (64-bit) */
smmu1: iommu@5000000 {
@@ -3582,7 +3582,7 @@ pci@c000000 {
dma-coherent;
ranges = <0x81000000 0x00 0x84000000 0xd0 0x84000000 0x00 0x00200000>, /* I/O */
- <0x82000000 0x00 0x20000000 0x00 0x20000000 0x00 0x08000000>, /* non-prefetchable memory (128 MiB) */
+ <0x82000000 0x00 0x20000000 0x00 0x18000000 0x00 0x08000000>, /* non-prefetchable memory (128 MiB) */
<0xc3000000 0xd0 0xc0000000 0xd0 0xc0000000 0x07 0xc0000000>; /* prefetchable memory */
bus-range = <0x0 0xff>;
--
2.55.0
next reply other threads:[~2026-10-30 14:11 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-30 14:10 Thierry Reding [this message]
2026-10-30 14:11 ` [PATCH 2/3] arm64: tegra: Fix memory size unit in comment Thierry Reding
2026-10-30 14:11 ` [PATCH 3/3] arm64: tegra: Remove PCI ranges from VISION chiplet Thierry Reding
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=20261030141101.845044-1-thierry.reding@kernel.org \
--to=thierry.reding@kernel.org \
--cc=devicetree@vger.kernel.org \
--cc=jonathanh@nvidia.com \
--cc=linux-tegra@vger.kernel.org \
--cc=mperttunen@nvidia.com \
--cc=sumitg@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