From: "Michał Kopeć" <michal@nozomi.space>
To: AngeloGioacchino Del Regno
<angelogioacchino.delregno@collabora.com>,
Matthias Brugger <matthias.bgg@gmail.com>
Cc: "Rob Herring" <robh@kernel.org>,
"Krzysztof Kozlowski" <krzk+dt@kernel.org>,
"Conor Dooley" <conor+dt@kernel.org>,
"Fei Shao" <fshao@chromium.org>,
devicetree@vger.kernel.org, linux-mediatek@lists.infradead.org,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org,
"Michał Kopeć" <michal@nozomi.space>
Subject: [PATCH 1/3] arm64: dts: mediatek: mt8188-geralt: Reserve SCP dual-core memory region
Date: Sat, 3 Oct 2026 21:31:06 +0200 [thread overview]
Message-ID: <20261003193108.789939-2-michal@nozomi.space> (raw)
In-Reply-To: <20261003193108.789939-1-michal@nozomi.space>
The trusted firmware on MT8188 protects 0x70000000-0x79ffffff (the SCP
core1 DRAM region) in the EMI MPU. Only the application processor and
the SCP may access it; accesses from other bus masters, including the
GPU, are silently dropped on write and return zeros on read.
The region is not reserved in the device tree, so Linux hands it out as
ordinary memory. Under memory pressure, GPU buffers and GPU page tables
end up there, which causes silent loss of GPU writes, translation
faults on page-table entries that are valid from the CPU's point of
view, and the GPU resets that follow.
Reserve the region, as the ChromeOS device tree does. No driver uses
it, so describe it as a plain no-map reservation.
Fixes: 5e6af7f54189 ("arm64: dts: mediatek: Introduce MT8188 Geralt platform based Ciri")
Signed-off-by: Michał Kopeć <michal@nozomi.space>
---
arch/arm64/boot/dts/mediatek/mt8188-geralt.dtsi | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/arch/arm64/boot/dts/mediatek/mt8188-geralt.dtsi b/arch/arm64/boot/dts/mediatek/mt8188-geralt.dtsi
index 801eee735afe6..d8edbde6ee4ac 100644
--- a/arch/arm64/boot/dts/mediatek/mt8188-geralt.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8188-geralt.dtsi
@@ -197,6 +197,11 @@ adsp_dma_mem: memory@61000000 {
reg = <0 0x61000000 0 0x100000>;
no-map;
};
+
+ scp_dual_mem: memory@70000000 {
+ reg = <0 0x70000000 0 0xa000000>;
+ no-map;
+ };
};
};
--
2.55.0
next prev parent reply other threads:[~2026-10-03 19:31 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-03 19:31 [PATCH 0/3] arm64: dts: mediatek: mt8188: SCP memory, thermal and touchpad fixes Michał Kopeć
2026-10-03 19:31 ` Michał Kopeć [this message]
2026-10-03 19:31 ` [PATCH 2/3] arm64: dts: mediatek: mt8188: Add power allocator parameters to CPU zones Michał Kopeć
2026-10-03 19:31 ` [PATCH 3/3] arm64: dts: mediatek: mt8188-geralt: Add the detachable base touchpad Michał Kopeć
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=20261003193108.789939-2-michal@nozomi.space \
--to=michal@nozomi.space \
--cc=angelogioacchino.delregno@collabora.com \
--cc=conor+dt@kernel.org \
--cc=devicetree@vger.kernel.org \
--cc=fshao@chromium.org \
--cc=krzk+dt@kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mediatek@lists.infradead.org \
--cc=matthias.bgg@gmail.com \
--cc=robh@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