* [PATCH 3/5] dt-bindings: clock: qcom: Add Maili global clock controller
From: Taniya Das @ 2026-06-18 17:21 UTC (permalink / raw)
To: Bjorn Andersson, Michael Turquette, Stephen Boyd, Brian Masney,
Rob Herring, Krzysztof Kozlowski, Conor Dooley, Taniya Das,
Vivek Aknurwar
Cc: Ajit Pandey, Imran Shaik, Jagadeesh Kona, linux-arm-msm,
linux-clk, devicetree, linux-kernel
In-Reply-To: <20260618-maili_initial_clock-v1-0-d6ede0352113@oss.qualcomm.com>
Add device tree bindings for the global clock controller on the
Qualcomm Maili SoC by extending the Qualcomm Hawi GCC bindings
since Maili is identical to Hawi and has few additional clocks.
Signed-off-by: Taniya Das <taniya.das@oss.qualcomm.com>
---
Documentation/devicetree/bindings/clock/qcom,hawi-gcc.yaml | 4 +++-
include/dt-bindings/clock/qcom,hawi-gcc.h | 10 ++++++++++
2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/clock/qcom,hawi-gcc.yaml b/Documentation/devicetree/bindings/clock/qcom,hawi-gcc.yaml
index 4f428c0f7286e83683a65cbe60b2cfeff67f5b8b..f0e8c6144697100588d68bc7c4f1d9822dba4cc2 100644
--- a/Documentation/devicetree/bindings/clock/qcom,hawi-gcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,hawi-gcc.yaml
@@ -17,7 +17,9 @@ description: |
properties:
compatible:
- const: qcom,hawi-gcc
+ enum:
+ - qcom,hawi-gcc
+ - qcom,maili-gcc
clocks:
items:
diff --git a/include/dt-bindings/clock/qcom,hawi-gcc.h b/include/dt-bindings/clock/qcom,hawi-gcc.h
index 6cd7fa0884f535efce90b60997662ca90cfb9b7e..9e0e382af3112b980997f0c7e223720517f12b02 100644
--- a/include/dt-bindings/clock/qcom,hawi-gcc.h
+++ b/include/dt-bindings/clock/qcom,hawi-gcc.h
@@ -196,6 +196,16 @@
#define GCC_VIDEO_AXI0C_CLK 186
#define GCC_VIDEO_XO_CLK 187
+/* Maili has below additional clocks on top of Hawi */
+#define GCC_QUPV3_WRAP5_CORE_2X_CLK 188
+#define GCC_QUPV3_WRAP5_CORE_CLK 189
+#define GCC_QUPV3_WRAP5_QSPI_REF_CLK 190
+#define GCC_QUPV3_WRAP5_QSPI_REF_CLK_SRC 191
+#define GCC_QUPV3_WRAP5_S0_CLK 192
+#define GCC_QUPV3_WRAP5_S0_CLK_SRC 193
+#define GCC_QUPV3_WRAP_5_M_AHB_CLK 194
+#define GCC_QUPV3_WRAP_5_S_AHB_CLK 195
+
/* GCC power domains */
#define GCC_PCIE_0_GDSC 0
#define GCC_PCIE_0_PHY_GDSC 1
--
2.34.1
^ permalink raw reply related
* [PATCH 2/5] dt-bindings: clock: qcom: Add Maili TCSR clock controller
From: Taniya Das @ 2026-06-18 17:21 UTC (permalink / raw)
To: Bjorn Andersson, Michael Turquette, Stephen Boyd, Brian Masney,
Rob Herring, Krzysztof Kozlowski, Conor Dooley, Taniya Das,
Vivek Aknurwar
Cc: Ajit Pandey, Imran Shaik, Jagadeesh Kona, linux-arm-msm,
linux-clk, devicetree, linux-kernel
In-Reply-To: <20260618-maili_initial_clock-v1-0-d6ede0352113@oss.qualcomm.com>
Add bindings documentation for TCSR clock controller on the
Qualcomm Maili SoC.
Maili is a derivative of the Hawi SoC and the tcsr clock controller
is identical to that of Hawi. Therefore Maili uses the fallback
compatible to reuse the Hawi tcsrcc driver.
Signed-off-by: Taniya Das <taniya.das@oss.qualcomm.com>
---
.../bindings/clock/qcom,sm8550-tcsr.yaml | 34 +++++++++++++---------
1 file changed, 20 insertions(+), 14 deletions(-)
diff --git a/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml b/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml
index 08824f84897358f2f7eac58e282a507c0489b5bd..15bdf055db3c012ea98217a0e7ca729ef41071a3 100644
--- a/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,sm8550-tcsr.yaml
@@ -25,20 +25,26 @@ description: |
properties:
compatible:
- items:
- - enum:
- - qcom,eliza-tcsr
- - qcom,glymur-tcsr
- - qcom,hawi-tcsrcc
- - qcom,kaanapali-tcsr
- - qcom,milos-tcsr
- - qcom,nord-tcsrcc
- - qcom,sar2130p-tcsr
- - qcom,sm8550-tcsr
- - qcom,sm8650-tcsr
- - qcom,sm8750-tcsr
- - qcom,x1e80100-tcsr
- - const: syscon
+ oneOf:
+ - items:
+ - enum:
+ - qcom,eliza-tcsr
+ - qcom,glymur-tcsr
+ - qcom,hawi-tcsrcc
+ - qcom,kaanapali-tcsr
+ - qcom,milos-tcsr
+ - qcom,nord-tcsrcc
+ - qcom,sar2130p-tcsr
+ - qcom,sm8550-tcsr
+ - qcom,sm8650-tcsr
+ - qcom,sm8750-tcsr
+ - qcom,x1e80100-tcsr
+ - const: syscon
+ - items:
+ - enum:
+ - qcom,maili-tcsrcc
+ - const: qcom,hawi-tcsrcc
+ - const: syscon
clocks:
items:
--
2.34.1
^ permalink raw reply related
* [PATCH 1/5] dt-bindings: clock: qcom-rpmhcc: Add RPMH clock controller for Maili
From: Taniya Das @ 2026-06-18 17:21 UTC (permalink / raw)
To: Bjorn Andersson, Michael Turquette, Stephen Boyd, Brian Masney,
Rob Herring, Krzysztof Kozlowski, Conor Dooley, Taniya Das,
Vivek Aknurwar
Cc: Ajit Pandey, Imran Shaik, Jagadeesh Kona, linux-arm-msm,
linux-clk, devicetree, linux-kernel
In-Reply-To: <20260618-maili_initial_clock-v1-0-d6ede0352113@oss.qualcomm.com>
Document the RPMH clock controller for the Qualcomm Maili SoC.
Maili SoC is a derivative of the Hawi SoC and the rpmh clock controller
is identical to that of Hawi. Therefore Maili uses the fallback
compatible to reuse the Hawi rpmhcc driver.
Signed-off-by: Taniya Das <taniya.das@oss.qualcomm.com>
---
.../devicetree/bindings/clock/qcom,rpmhcc.yaml | 65 ++++++++++++----------
1 file changed, 35 insertions(+), 30 deletions(-)
diff --git a/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml b/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml
index d344b33860429527246484560823074f52a9159d..2b446aca5207c9cc2922635b0539f2d2f926ea0a 100644
--- a/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml
@@ -16,36 +16,41 @@ description: |
properties:
compatible:
- enum:
- - qcom,eliza-rpmh-clk
- - qcom,glymur-rpmh-clk
- - qcom,hawi-rpmh-clk
- - qcom,kaanapali-rpmh-clk
- - qcom,milos-rpmh-clk
- - qcom,nord-rpmh-clk
- - qcom,qcs615-rpmh-clk
- - qcom,qdu1000-rpmh-clk
- - qcom,sa8775p-rpmh-clk
- - qcom,sar2130p-rpmh-clk
- - qcom,sc7180-rpmh-clk
- - qcom,sc7280-rpmh-clk
- - qcom,sc8180x-rpmh-clk
- - qcom,sc8280xp-rpmh-clk
- - qcom,sdm670-rpmh-clk
- - qcom,sdm845-rpmh-clk
- - qcom,sdx55-rpmh-clk
- - qcom,sdx65-rpmh-clk
- - qcom,sdx75-rpmh-clk
- - qcom,sm4450-rpmh-clk
- - qcom,sm6350-rpmh-clk
- - qcom,sm8150-rpmh-clk
- - qcom,sm8250-rpmh-clk
- - qcom,sm8350-rpmh-clk
- - qcom,sm8450-rpmh-clk
- - qcom,sm8550-rpmh-clk
- - qcom,sm8650-rpmh-clk
- - qcom,sm8750-rpmh-clk
- - qcom,x1e80100-rpmh-clk
+ oneOf:
+ - enum:
+ - qcom,eliza-rpmh-clk
+ - qcom,glymur-rpmh-clk
+ - qcom,hawi-rpmh-clk
+ - qcom,kaanapali-rpmh-clk
+ - qcom,milos-rpmh-clk
+ - qcom,nord-rpmh-clk
+ - qcom,qcs615-rpmh-clk
+ - qcom,qdu1000-rpmh-clk
+ - qcom,sa8775p-rpmh-clk
+ - qcom,sar2130p-rpmh-clk
+ - qcom,sc7180-rpmh-clk
+ - qcom,sc7280-rpmh-clk
+ - qcom,sc8180x-rpmh-clk
+ - qcom,sc8280xp-rpmh-clk
+ - qcom,sdm670-rpmh-clk
+ - qcom,sdm845-rpmh-clk
+ - qcom,sdx55-rpmh-clk
+ - qcom,sdx65-rpmh-clk
+ - qcom,sdx75-rpmh-clk
+ - qcom,sm4450-rpmh-clk
+ - qcom,sm6350-rpmh-clk
+ - qcom,sm8150-rpmh-clk
+ - qcom,sm8250-rpmh-clk
+ - qcom,sm8350-rpmh-clk
+ - qcom,sm8450-rpmh-clk
+ - qcom,sm8550-rpmh-clk
+ - qcom,sm8650-rpmh-clk
+ - qcom,sm8750-rpmh-clk
+ - qcom,x1e80100-rpmh-clk
+ - items:
+ - enum:
+ - qcom,maili-rpmh-clk
+ - const: qcom,hawi-rpmh-clk
clocks:
maxItems: 1
--
2.34.1
^ permalink raw reply related
* [PATCH 0/5] clk: qcom: Introduce initial clock controllers for Maili SoC
From: Taniya Das @ 2026-06-18 17:21 UTC (permalink / raw)
To: Bjorn Andersson, Michael Turquette, Stephen Boyd, Brian Masney,
Rob Herring, Krzysztof Kozlowski, Conor Dooley, Taniya Das,
Vivek Aknurwar
Cc: Ajit Pandey, Imran Shaik, Jagadeesh Kona, linux-arm-msm,
linux-clk, devicetree, linux-kernel
Introduce the initial set of clock controller bindings and driver
support for the upcoming Qualcomm Maili SoC.
Maili is a new mobile SoC from Qualcomm. It is a derivative of the
Hawi SoC and shares most of its clock topology. Where the hardware is
identical, Maili reuses the existing Hawi drivers via fallback
compatible strings. Where Maili diverges — specifically in the Global
Clock Controller (GCC), which carries an additional QUPv3 wrapper
(WRAP5) — the Hawi GCC driver is extended to handle both SoCs.
The series covers the following clock controllers:
- RPMH clock controller: identical to Hawi; uses qcom,hawi-rpmh-clk
as fallback.
- TCSR clock controller: identical to Hawi; uses qcom,hawi-tcsrcc
as fallback.
- Global Clock Controller (GCC): extends the Hawi GCC driver with
eight additional QUPV3 WRAP5 clocks present only on Maili.
- CPUCP mailbox controller: software-compatible with X1E80100; uses
qcom,x1e80100-cpucp-mbox as fallback.
The devicetree for Maili will be upstreamed later.
---
Taniya Das (5):
dt-bindings: clock: qcom-rpmhcc: Add RPMH clock controller for Maili
dt-bindings: clock: qcom: Add Maili TCSR clock controller
dt-bindings: clock: qcom: Add Maili global clock controller
clk: qcom: gcc-hawi: Add support for global clock controller on Maili
dt-bindings: mailbox: qcom: Document Maili CPUCP mailbox controller
.../devicetree/bindings/clock/qcom,hawi-gcc.yaml | 4 +-
.../devicetree/bindings/clock/qcom,rpmhcc.yaml | 65 +++----
.../bindings/clock/qcom,sm8550-tcsr.yaml | 34 ++--
.../bindings/mailbox/qcom,cpucp-mbox.yaml | 1 +
drivers/clk/qcom/gcc-hawi.c | 200 +++++++++++++++++++++
include/dt-bindings/clock/qcom,hawi-gcc.h | 10 ++
6 files changed, 269 insertions(+), 45 deletions(-)
---
base-commit: 4fa3f5fabb30bf00d7475d5a33459ea83d639bf9
change-id: 20260617-maili_initial_clock-c7e2b4530d80
Best regards,
--
Taniya Das <taniya.das@oss.qualcomm.com>
^ permalink raw reply
* Re: [PATCH v2 1/2] of: property: Fix of_fwnode_get_reference_args() with negative index
From: Rob Herring (Arm) @ 2026-06-18 17:09 UTC (permalink / raw)
To: Alban Bedel
Cc: Greg Kroah-Hartman, Rafael J. Wysocki, Tommaso Merciai,
Saravana Kannan, Andy Shevchenko, Danilo Krummrich, devicetree,
linux-kernel, Krzysztof Kozlowski, Sakari Ailus, Zijun Hu,
Daniel Scally, Heikki Krogerus, driver-core
In-Reply-To: <20260618152035.1600436-1-alban.bedel@lht.dlh.de>
On Thu, 18 Jun 2026 17:20:34 +0200, Alban Bedel wrote:
> fwnode_property_get_reference_args() should return -ENOENT when an out
> of bound index is passed. An issue arised with the OF backend because
> the OF API use signed indexes while the fwnode API use unsigned ones.
> When an index value greater the INT_MAX was passed to the OF backend
> it got casted to a negative value and it returned -EINVAL instead of
> -ENOENT. This patch add a check to of_fwnode_get_reference_args() to
> catch negative index before they are passed to the OF API and return
> -ENOENT right away.
>
> This issue appeared when the following pattern was used in the LED
> subsystem:
>
> index = fwnode_property_match_string(fwnode, "led-names", name)
> led_node = fwnode_find_reference(fwnode, "leds", index);
>
> Unlike the same pattern with the OF API, this pattern implicitly cast
> the signed return value of fwnode_property_match_string() to an
> unsigned index leading to the above issue with the OF backend. It can
> be argued that the return value of fwnode_property_match_string()
> should be checked separately, but I think there is value in supporting
> such simple and straight to the point patterns.
>
> Link: https://lore.kernel.org/linux-leds/aimVRwJPhlGxsIUj@tom-desktop/T/#mc43cbf7e0599991b56dd0d9680714d28d145fbc8
> Cc: Tommaso Merciai <tommaso.merciai.xr@bp.renesas.com>
> Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
> Signed-off-by: Alban Bedel <alban.bedel@lht.dlh.de>
> ---
> v2: Fixed comment block to follow linux coding style.
> ---
> drivers/of/property.c | 8 ++++++++
> 1 file changed, 8 insertions(+)
>
Applied, thanks!
^ permalink raw reply
* [PATCH 10/10] RFC: rust: driver: support map-like syntax for ID table
From: Gary Guo @ 2026-06-18 17:03 UTC (permalink / raw)
To: Greg Kroah-Hartman, Rafael J. Wysocki, Danilo Krummrich,
Miguel Ojeda, Boqun Feng, Björn Roy Baron, Benno Lossin,
Andreas Hindborg, Alice Ryhl, Trevor Gross, Daniel Almeida,
Tamir Duberstein, Alexandre Courbot, Onur Özkan,
FUJITA Tomonori, David Airlie, Simona Vetter, Bjorn Helgaas,
Krzysztof Wilczyński, Abdiel Janulgue, Robin Murphy,
Dave Ertman, Ira Weiny, Leon Romanovsky, Len Brown, Igor Korotin,
Rob Herring, Saravana Kannan, Viresh Kumar, Michal Wilczynski,
Drew Fustini, Guo Ren, Fu Wei, Uwe Kleine-König
Cc: driver-core, rust-for-linux, linux-kernel, netdev, nova-gpu,
dri-devel, linux-pci, linux-acpi, devicetree, linux-pm,
linux-riscv, linux-pwm, Gary Guo
In-Reply-To: <20260618-id_info-v1-0-96af1e559ef9@garyguo.net>
The device ID table and its associated info is really just a map. Add a
syntax to `module_device_table` macro that reflects that.
Signed-off-by: Gary Guo <gary@garyguo.net>
---
rust/kernel/device_id.rs | 11 +++++++++++
samples/rust/rust_driver_pci.rs | 7 +++----
2 files changed, 14 insertions(+), 4 deletions(-)
diff --git a/rust/kernel/device_id.rs b/rust/kernel/device_id.rs
index 26618bcda276..7c61cdcc9427 100644
--- a/rust/kernel/device_id.rs
+++ b/rust/kernel/device_id.rs
@@ -183,6 +183,17 @@ macro_rules! module_device_table {
$table_type: literal, $device_id_ty: ty,
$table_name: ident, $id_info_type: ty,
[$(($id: expr, $info:expr $(,)?)),* $(,)?]
+ ) => {
+ $crate::module_device_table!(
+ $table_type, $device_id_ty, $table_name, $id_info_type,
+ {$($id=>$info,)*}
+ );
+ };
+
+ (
+ $table_type: literal, $device_id_ty: ty,
+ $table_name: ident, $id_info_type: ty,
+ {$($id: expr => $info:expr),* $(,)?}
) => {
#[export_name =
concat!("__mod_device_table__", line!(),
diff --git a/samples/rust/rust_driver_pci.rs b/samples/rust/rust_driver_pci.rs
index 2282191e6292..652819dff082 100644
--- a/samples/rust/rust_driver_pci.rs
+++ b/samples/rust/rust_driver_pci.rs
@@ -75,10 +75,9 @@ struct SampleDriverData<'bound> {
kernel::pci_device_table!(
PCI_TABLE,
<SampleDriver as pci::Driver>::IdInfo,
- [(
- pci::DeviceId::from_id(pci::Vendor::REDHAT, 0x5),
- TestIndex::NO_EVENTFD
- )]
+ {
+ pci::DeviceId::from_id(pci::Vendor::REDHAT, 0x5) => TestIndex::NO_EVENTFD,
+ }
);
impl SampleDriverData<'_> {
--
2.54.0
^ permalink raw reply related
* [PATCH 09/10] rust: driver: remove duplicate ID table
From: Gary Guo @ 2026-06-18 17:03 UTC (permalink / raw)
To: Greg Kroah-Hartman, Rafael J. Wysocki, Danilo Krummrich,
Miguel Ojeda, Boqun Feng, Björn Roy Baron, Benno Lossin,
Andreas Hindborg, Alice Ryhl, Trevor Gross, Daniel Almeida,
Tamir Duberstein, Alexandre Courbot, Onur Özkan,
FUJITA Tomonori, David Airlie, Simona Vetter, Bjorn Helgaas,
Krzysztof Wilczyński, Abdiel Janulgue, Robin Murphy,
Dave Ertman, Ira Weiny, Leon Romanovsky, Len Brown, Igor Korotin,
Rob Herring, Saravana Kannan, Viresh Kumar, Michal Wilczynski,
Drew Fustini, Guo Ren, Fu Wei, Uwe Kleine-König
Cc: driver-core, rust-for-linux, linux-kernel, netdev, nova-gpu,
dri-devel, linux-pci, linux-acpi, devicetree, linux-pm,
linux-riscv, linux-pwm, Gary Guo
In-Reply-To: <20260618-id_info-v1-0-96af1e559ef9@garyguo.net>
Previously, `IdArray` contains both device ID table and info table so we
keep a separate copy for MODULE_DEVICE_TABLE for hotplug (which needs to be
just the device ID table). With the info being changed to be carried via
pointers, `IdArray` is now layout compatible with raw ID table and hence
there is no longer a need to keep the distinction.
Deduplicate the code, and remove the redundant copy for hotplug purpose by
just giving the `IdArray` instance a proper symbol name.
Signed-off-by: Gary Guo <gary@garyguo.net>
---
rust/kernel/device_id.rs | 76 +++++++++++++++++-------------------------------
1 file changed, 27 insertions(+), 49 deletions(-)
diff --git a/rust/kernel/device_id.rs b/rust/kernel/device_id.rs
index 59453588df0e..26618bcda276 100644
--- a/rust/kernel/device_id.rs
+++ b/rust/kernel/device_id.rs
@@ -86,28 +86,23 @@ unsafe fn info_unchecked_opt<U>(&self) -> Option<&'static U> {
}
}
-/// A zero-terminated device id array.
+/// A zero-terminated device id array, followed by context data.
#[repr(C)]
-pub struct RawIdArray<T: RawDeviceId, const N: usize> {
+pub struct IdArray<T: RawDeviceId, U: 'static, const N: usize> {
// This is `MaybeUninit<T::RawType>` so any bytes inside it can carry provenance in CTFE.
// If this were `T::RawType`, integer fields would not be able to contain pointers.
ids: [MaybeUninit<T::RawType>; N],
sentinel: MaybeUninit<T::RawType>,
+ phantom: PhantomData<&'static U>,
}
-impl<T: RawDeviceId, const N: usize> RawIdArray<T, N> {
- #[doc(hidden)]
- pub const fn size(&self) -> usize {
- core::mem::size_of::<Self>()
- }
-}
+// SAFETY: device ID is plain data plus a `&'static U` and can thus be sent between threads safely
+// if `&U` can.
+unsafe impl<T: RawDeviceId, U: Sync + 'static, const N: usize> Send for IdArray<T, U, N> {}
-/// A zero-terminated device id array, followed by context data.
-#[repr(C)]
-pub struct IdArray<T: RawDeviceId, U: 'static, const N: usize> {
- raw_ids: RawIdArray<T, N>,
- phantom: PhantomData<&'static U>,
-}
+// SAFETY: device ID is plain data plus a `&'static U` and can thus be shared between threads safely
+// if `&U` can.
+unsafe impl<T: RawDeviceId, U: Sync + 'static, const N: usize> Sync for IdArray<T, U, N> {}
impl<T: RawDeviceId + RawDeviceIdIndex, U: 'static, const N: usize> IdArray<T, U, N> {
/// Creates a new instance of the array.
@@ -137,22 +132,13 @@ impl<T: RawDeviceId + RawDeviceIdIndex, U: 'static, const N: usize> IdArray<T, U
core::mem::forget(ids);
Self {
- raw_ids: RawIdArray {
- ids: raw_ids,
- sentinel: MaybeUninit::zeroed(),
- },
+ ids: raw_ids,
+ sentinel: MaybeUninit::zeroed(),
phantom: PhantomData,
}
}
}
-impl<T: RawDeviceId, U: 'static, const N: usize> IdArray<T, U, N> {
- /// Reference to the contained [`RawIdArray`].
- pub const fn raw_ids(&self) -> &RawIdArray<T, N> {
- &self.raw_ids
- }
-}
-
impl<T: RawDeviceId, const N: usize> IdArray<T, (), N> {
/// Creates a new instance of the array without writing index values.
///
@@ -164,10 +150,8 @@ impl<T: RawDeviceId, const N: usize> IdArray<T, (), N> {
core::mem::forget(ids);
Self {
- raw_ids: RawIdArray {
- ids: raw_ids,
- sentinel: MaybeUninit::zeroed(),
- },
+ ids: raw_ids,
+ sentinel: MaybeUninit::zeroed(),
phantom: PhantomData,
}
}
@@ -200,13 +184,17 @@ macro_rules! module_device_table {
$table_name: ident, $id_info_type: ty,
[$(($id: expr, $info:expr $(,)?)),* $(,)?]
) => {
- const $table_name: $crate::device_id::IdArray<
+ #[export_name =
+ concat!("__mod_device_table__", line!(),
+ "__kmod_", module_path!(),
+ "__", $table_type,
+ "__", stringify!($table_name))
+ ]
+ static $table_name: $crate::device_id::IdArray<
$device_id_ty,
$id_info_type,
{ <[$device_id_ty]>::len(&[$($id,)*]) },
> = $crate::device_id::IdArray::new([$(($id, &$info),)*]);
-
- $crate::module_device_table!($table_type, $table_name);
};
// Case for no ID info.
@@ -215,26 +203,16 @@ macro_rules! module_device_table {
$table_name: ident, @none,
[$($id: expr),* $(,)?]
) => {
- const $table_name: $crate::device_id::IdArray<
+ #[export_name =
+ concat!("__mod_device_table__", line!(),
+ "__kmod_", module_path!(),
+ "__", $table_type,
+ "__", stringify!($table_name))
+ ]
+ static $table_name: $crate::device_id::IdArray<
$device_id_ty,
(),
{ <[$device_id_ty]>::len(&[$($id,)*]) },
> = $crate::device_id::IdArray::new_without_index([$($id),*]);
-
- $crate::module_device_table!($table_type, $table_name);
- };
-
- ($table_type: literal, $table_name:ident) => {
- const _: () = {
- #[rustfmt::skip]
- #[export_name =
- concat!("__mod_device_table__", line!(),
- "__kmod_", module_path!(),
- "__", $table_type,
- "__", stringify!($table_name))
- ]
- static TABLE: [::core::mem::MaybeUninit<u8>; $table_name.raw_ids().size()] =
- unsafe { ::core::mem::transmute_copy($table_name.raw_ids()) };
- };
};
}
--
2.54.0
^ permalink raw reply related
* [PATCH 08/10] rust: driver: remove open-coded matching logic
From: Gary Guo @ 2026-06-18 17:03 UTC (permalink / raw)
To: Greg Kroah-Hartman, Rafael J. Wysocki, Danilo Krummrich,
Miguel Ojeda, Boqun Feng, Björn Roy Baron, Benno Lossin,
Andreas Hindborg, Alice Ryhl, Trevor Gross, Daniel Almeida,
Tamir Duberstein, Alexandre Courbot, Onur Özkan,
FUJITA Tomonori, David Airlie, Simona Vetter, Bjorn Helgaas,
Krzysztof Wilczyński, Abdiel Janulgue, Robin Murphy,
Dave Ertman, Ira Weiny, Leon Romanovsky, Len Brown, Igor Korotin,
Rob Herring, Saravana Kannan, Viresh Kumar, Michal Wilczynski,
Drew Fustini, Guo Ren, Fu Wei, Uwe Kleine-König
Cc: driver-core, rust-for-linux, linux-kernel, netdev, nova-gpu,
dri-devel, linux-pci, linux-acpi, devicetree, linux-pm,
linux-riscv, linux-pwm, Gary Guo
In-Reply-To: <20260618-id_info-v1-0-96af1e559ef9@garyguo.net>
With device ID info now including pointers instead of indices, the
open-coded ACPI/OF matching is no longer needed and can be replaced with
`device_get_match_data`.
Signed-off-by: Gary Guo <gary@garyguo.net>
---
rust/kernel/driver.rs | 114 ++++--------------------------------------------
rust/kernel/i2c.rs | 6 ++-
rust/kernel/platform.rs | 3 +-
3 files changed, 15 insertions(+), 108 deletions(-)
diff --git a/rust/kernel/driver.rs b/rust/kernel/driver.rs
index 824899d76fed..a881f5ef99ec 100644
--- a/rust/kernel/driver.rs
+++ b/rust/kernel/driver.rs
@@ -107,7 +107,6 @@
use crate::{
acpi,
device,
- device_id::RawDeviceIdIndex,
of,
prelude::*,
types::Opaque,
@@ -325,117 +324,22 @@ pub trait Adapter {
/// The [`acpi::IdTable`] of the corresponding driver
fn acpi_id_table() -> Option<acpi::IdTable<Self::IdInfo>>;
- /// Returns the driver's private data from the matching entry in the [`acpi::IdTable`], if any.
- ///
- /// If this returns `None`, it means there is no match with an entry in the [`acpi::IdTable`].
- fn acpi_id_info(dev: &device::Device) -> Option<&'static Self::IdInfo> {
- #[cfg(not(CONFIG_ACPI))]
- {
- let _ = dev;
- None
- }
-
- #[cfg(CONFIG_ACPI)]
- {
- let table = Self::acpi_id_table()?;
-
- // SAFETY:
- // - `table` has static lifetime, hence it's valid for read,
- // - `dev` is guaranteed to be valid while it's alive, and so is `dev.as_raw()`.
- let raw_id = unsafe { bindings::acpi_match_device(table.as_ptr(), dev.as_raw()) };
-
- if raw_id.is_null() {
- None
- } else {
- // SAFETY: `DeviceId` is a `#[repr(transparent)]` wrapper of `struct acpi_device_id`
- // and does not add additional invariants, so it's safe to transmute.
- let id = unsafe { &*raw_id.cast::<acpi::DeviceId>() };
-
- // SAFETY: `id` comes from `table` which is of type `IdArray<_, Self::IdInfo>`.
- Some(unsafe { id.info_unchecked::<Self::IdInfo>() })
- }
- }
- }
-
/// The [`of::IdTable`] of the corresponding driver.
fn of_id_table() -> Option<of::IdTable<Self::IdInfo>>;
- /// Returns the driver's private data from the matching entry in the [`of::IdTable`], if any.
- ///
- /// If this returns `None`, it means there is no match with an entry in the [`of::IdTable`].
- fn of_id_info(dev: &device::Device) -> Option<&'static Self::IdInfo> {
- let table = Self::of_id_table()?;
-
- #[cfg(not(any(CONFIG_OF, CONFIG_ACPI)))]
- {
- let _ = (dev, table);
- }
-
- #[cfg(CONFIG_OF)]
- {
- // SAFETY:
- // - `table` has static lifetime, hence it's valid for read,
- // - `dev` is guaranteed to be valid while it's alive, and so is `dev.as_raw()`.
- let raw_id = unsafe { bindings::of_match_device(table.as_ptr(), dev.as_raw()) };
-
- if !raw_id.is_null() {
- // SAFETY: `DeviceId` is a `#[repr(transparent)]` wrapper of `struct of_device_id`
- // and does not add additional invariants, so it's safe to transmute.
- let id = unsafe { &*raw_id.cast::<of::DeviceId>() };
-
- // SAFETY: `id` comes from `table` which is of type `IdArray<_, Self::IdInfo>`.
- return Some(unsafe { id.info_unchecked::<Self::IdInfo>() });
- }
- }
-
- #[cfg(CONFIG_ACPI)]
- {
- use core::ptr;
- use device::property::FwNode;
-
- let mut raw_id = ptr::null();
-
- let fwnode = dev.fwnode().map_or(ptr::null_mut(), FwNode::as_raw);
-
- // SAFETY: `fwnode` is a pointer to a valid `fwnode_handle`. A null pointer will be
- // passed through the function.
- let adev = unsafe { bindings::to_acpi_device_node(fwnode) };
-
- // SAFETY:
- // - `adev` is a valid pointer to `acpi_device` or is null. It is guaranteed to be
- // valid as long as `dev` is alive.
- // - `table` has static lifetime, hence it's valid for read.
- if unsafe { acpi_of_match_device(adev, table.as_ptr(), &raw mut raw_id) } {
- // SAFETY:
- // - the function returns true, therefore `raw_id` has been set to a pointer to a
- // valid `of_device_id`.
- // - `DeviceId` is a `#[repr(transparent)]` wrapper of `struct of_device_id`
- // and does not add additional invariants, so it's safe to transmute.
- let id = unsafe { &*raw_id.cast::<of::DeviceId>() };
-
- // SAFETY: `id` comes from `table` which is of type `IdArray<_, Self::IdInfo>`.
- return Some(unsafe { id.info_unchecked::<Self::IdInfo>() });
- }
- }
-
- None
- }
-
/// Returns the driver's private data from the matching entry of any of the ID tables, if any.
///
/// If this returns `None`, it means that there is no match in any of the ID tables directly
/// associated with a [`device::Device`].
- fn id_info(dev: &device::Device) -> Option<&'static Self::IdInfo> {
- let id = Self::acpi_id_info(dev);
- if id.is_some() {
- return id;
- }
-
- let id = Self::of_id_info(dev);
- if id.is_some() {
- return id;
- }
+ ///
+ /// # Safety
+ ///
+ /// The caller must ensure that the `dev` matched data is of type `Self::IdInfo`.
+ unsafe fn id_info(dev: &device::Device) -> Option<&'static Self::IdInfo> {
+ // SAFETY: `dev` is guaranteed to be valid while it's alive, and so is `dev.as_raw()`.
+ let data = unsafe { bindings::device_get_match_data(dev.as_raw()) };
- None
+ // SAFETY: Per safety requirement, `data` is of type `Self::IdInfo`.
+ unsafe { data.cast::<Self::IdInfo>().as_ref() }
}
}
diff --git a/rust/kernel/i2c.rs b/rust/kernel/i2c.rs
index 9e551c7e8e41..07680fd2f3fc 100644
--- a/rust/kernel/i2c.rs
+++ b/rust/kernel/i2c.rs
@@ -149,8 +149,10 @@ extern "C" fn probe_callback(idev: *mut bindings::i2c_client) -> kernel::ffi::c_
// INVARIANT: `idev` is valid for the duration of `probe_callback()`.
let idev = unsafe { &*idev.cast::<I2cClient<device::CoreInternal<'_>>>() };
- let info =
- Self::i2c_id_info(idev).or_else(|| <Self as driver::Adapter>::id_info(idev.as_ref()));
+ let info = Self::i2c_id_info(idev).or_else(|| {
+ // SAFETY: `idev` matched data is of type `Self::IdInfo`.
+ unsafe { <Self as driver::Adapter>::id_info(idev.as_ref()) }
+ });
from_result(|| {
let data = T::probe(idev, info);
diff --git a/rust/kernel/platform.rs b/rust/kernel/platform.rs
index 210a815925ce..e12e88113ca5 100644
--- a/rust/kernel/platform.rs
+++ b/rust/kernel/platform.rs
@@ -100,7 +100,8 @@ extern "C" fn probe_callback(pdev: *mut bindings::platform_device) -> kernel::ff
//
// INVARIANT: `pdev` is valid for the duration of `probe_callback()`.
let pdev = unsafe { &*pdev.cast::<Device<device::CoreInternal<'_>>>() };
- let info = <Self as driver::Adapter>::id_info(pdev.as_ref());
+ // SAFETY: `pdev` matched data is of type `Self::IdInfo`.
+ let info = unsafe { <Self as driver::Adapter>::id_info(pdev.as_ref()) };
from_result(|| {
let data = T::probe(pdev, info);
--
2.54.0
^ permalink raw reply related
* [PATCH 07/10] rust: driver: store pointers in `DeviceId`
From: Gary Guo @ 2026-06-18 17:03 UTC (permalink / raw)
To: Greg Kroah-Hartman, Rafael J. Wysocki, Danilo Krummrich,
Miguel Ojeda, Boqun Feng, Björn Roy Baron, Benno Lossin,
Andreas Hindborg, Alice Ryhl, Trevor Gross, Daniel Almeida,
Tamir Duberstein, Alexandre Courbot, Onur Özkan,
FUJITA Tomonori, David Airlie, Simona Vetter, Bjorn Helgaas,
Krzysztof Wilczyński, Abdiel Janulgue, Robin Murphy,
Dave Ertman, Ira Weiny, Leon Romanovsky, Len Brown, Igor Korotin,
Rob Herring, Saravana Kannan, Viresh Kumar, Michal Wilczynski,
Drew Fustini, Guo Ren, Fu Wei, Uwe Kleine-König
Cc: driver-core, rust-for-linux, linux-kernel, netdev, nova-gpu,
dri-devel, linux-pci, linux-acpi, devicetree, linux-pm,
linux-riscv, linux-pwm, Gary Guo
In-Reply-To: <20260618-id_info-v1-0-96af1e559ef9@garyguo.net>
The common practice in C drivers is to store pointers into `driver_data`
field of device IDs. The Rust code is however currently storing indices
into the fields and then carry a side table that maps the index to
pointers.
It is much simpler to just have `DeviceId` carry the pointer like C code
does. However, just doing so naively would cause a "pointers cannot be cast
to integers during const eval" error, as kernel_ulong_t does not have
provenance while pointers do, and Rust forbids `expose_provenance` during
consteval.
Work around this limitation by wrapping raw IDs in `MaybeUninit`.
`MaybeUninit` is allowed to host arbitrary bytes with or without
provenance, so we can just then use `unsafe` to store a pointer with
provenance there. This has the same effect as changing the C-side
definition to use `void*` instead of `kernel_ulong_t`, but without actually
changing the C side.
Signed-off-by: Gary Guo <gary@garyguo.net>
---
rust/kernel/acpi.rs | 4 ---
rust/kernel/auxiliary.rs | 8 ++---
rust/kernel/device_id.rs | 88 +++++++++++++++++++++++++++++-------------------
rust/kernel/driver.rs | 14 ++++----
rust/kernel/i2c.rs | 7 ++--
rust/kernel/of.rs | 4 ---
rust/kernel/pci.rs | 11 +++---
rust/kernel/usb.rs | 7 ++--
8 files changed, 73 insertions(+), 70 deletions(-)
diff --git a/rust/kernel/acpi.rs b/rust/kernel/acpi.rs
index 315f2f2af446..ea2ce61ee393 100644
--- a/rust/kernel/acpi.rs
+++ b/rust/kernel/acpi.rs
@@ -25,10 +25,6 @@ unsafe impl RawDeviceId for DeviceId {
// SAFETY: `DRIVER_DATA_OFFSET` is the offset to the `driver_data` field.
unsafe impl RawDeviceIdIndex for DeviceId {
const DRIVER_DATA_OFFSET: usize = core::mem::offset_of!(bindings::acpi_device_id, driver_data);
-
- fn index(&self) -> usize {
- self.0.driver_data
- }
}
impl DeviceId {
diff --git a/rust/kernel/auxiliary.rs b/rust/kernel/auxiliary.rs
index 59787c9bff26..aa13d8866a19 100644
--- a/rust/kernel/auxiliary.rs
+++ b/rust/kernel/auxiliary.rs
@@ -93,7 +93,9 @@ extern "C" fn probe_callback(
// SAFETY: `DeviceId` is a `#[repr(transparent)`] wrapper of `struct auxiliary_device_id`
// and does not add additional invariants, so it's safe to transmute.
let id = unsafe { &*id.cast::<DeviceId>() };
- let info = T::ID_TABLE.info(id.index());
+
+ // SAFETY: `id` comes from `T::ID_TABLE` which is of type `IdArray<_, T::IdInfo>`.
+ let info = unsafe { id.info_unchecked::<T::IdInfo>() };
from_result(|| {
let data = T::probe(adev, info);
@@ -169,10 +171,6 @@ unsafe impl RawDeviceId for DeviceId {
unsafe impl RawDeviceIdIndex for DeviceId {
const DRIVER_DATA_OFFSET: usize =
core::mem::offset_of!(bindings::auxiliary_device_id, driver_data);
-
- fn index(&self) -> usize {
- self.0.driver_data
- }
}
/// IdTable type for auxiliary drivers.
diff --git a/rust/kernel/device_id.rs b/rust/kernel/device_id.rs
index 84852a2d9ad7..59453588df0e 100644
--- a/rust/kernel/device_id.rs
+++ b/rust/kernel/device_id.rs
@@ -5,7 +5,10 @@
//! Each bus / subsystem that matches device and driver through a bus / subsystem specific ID is
//! expected to implement [`RawDeviceId`].
-use core::mem::MaybeUninit;
+use core::{
+ marker::PhantomData,
+ mem::MaybeUninit, //
+};
/// Marker trait to indicate a Rust device ID type represents a corresponding C device ID type.
///
@@ -47,15 +50,48 @@ pub unsafe trait RawDeviceIdIndex: RawDeviceId {
/// The offset (in bytes) to the context/data field in the raw device ID.
const DRIVER_DATA_OFFSET: usize;
- /// The index stored at `DRIVER_DATA_OFFSET` of the implementor of the [`RawDeviceIdIndex`]
- /// trait.
- fn index(&self) -> usize;
+ /// Obtain the data pointer stored inside the device ID.
+ ///
+ /// # Safety
+ ///
+ /// `&Self` must be stored inside a `IdArray<Self, U>`.
+ unsafe fn info_unchecked<U>(&self) -> &'static U {
+ // SAFETY: By safety requirement of the trait, this is `self.driver_data as *const U` and by
+ // the safety requirement of the function, this is stored in `IdArray<Self, U>` so is
+ // convertible to `&'static U`.
+ unsafe {
+ core::ptr::from_ref(self)
+ .byte_add(Self::DRIVER_DATA_OFFSET)
+ .cast::<&U>()
+ .read()
+ }
+ }
+
+ /// Obtain the data pointer stored inside the device ID.
+ ///
+ /// # Safety
+ ///
+ /// `&Self` must be stored inside a `IdArray<Self, U>`, or has NULL (or 0) as driver data.
+ unsafe fn info_unchecked_opt<U>(&self) -> Option<&'static U> {
+ // SAFETY: By safety requirement of the trait, this is `self.driver_data as *const U` and by
+ // the safety requirement of the function, if this is stored in `IdArray<Self, U>`, this is
+ // convertible to `Option<&'static U>`. Otherwise it is NULL which is `None` as
+ // `Option<&U>`.
+ unsafe {
+ core::ptr::from_ref(self)
+ .byte_add(Self::DRIVER_DATA_OFFSET)
+ .cast::<Option<&U>>()
+ .read()
+ }
+ }
}
/// A zero-terminated device id array.
#[repr(C)]
pub struct RawIdArray<T: RawDeviceId, const N: usize> {
- ids: [T::RawType; N],
+ // This is `MaybeUninit<T::RawType>` so any bytes inside it can carry provenance in CTFE.
+ // If this were `T::RawType`, integer fields would not be able to contain pointers.
+ ids: [MaybeUninit<T::RawType>; N],
sentinel: MaybeUninit<T::RawType>,
}
@@ -68,18 +104,17 @@ pub const fn size(&self) -> usize {
/// A zero-terminated device id array, followed by context data.
#[repr(C)]
-pub struct IdArray<T: RawDeviceId, U, const N: usize> {
+pub struct IdArray<T: RawDeviceId, U: 'static, const N: usize> {
raw_ids: RawIdArray<T, N>,
- id_infos: [U; N],
+ phantom: PhantomData<&'static U>,
}
-impl<T: RawDeviceId + RawDeviceIdIndex, U, const N: usize> IdArray<T, U, N> {
+impl<T: RawDeviceId + RawDeviceIdIndex, U: 'static, const N: usize> IdArray<T, U, N> {
/// Creates a new instance of the array.
///
/// The contents are derived from the given identifiers and context information.
- pub const fn new(ids: [(T, U); N]) -> Self {
+ pub const fn new(ids: [(T, &'static U); N]) -> Self {
let mut raw_ids = [const { MaybeUninit::<T::RawType>::uninit() }; N];
- let mut infos = [const { MaybeUninit::uninit() }; N];
let mut i = 0usize;
while i < N {
@@ -87,18 +122,15 @@ impl<T: RawDeviceId + RawDeviceIdIndex, U, const N: usize> IdArray<T, U, N> {
// layout-wise compatible with `RawType`.
raw_ids[i] = unsafe { core::mem::transmute_copy(&ids[i].0) };
// SAFETY: by the safety requirement of `RawDeviceIdIndex`, this would be effectively
- // `raw_ids[i].driver_data = i;`.
+ // `raw_ids[i].driver_data = ids[i].1;`.
unsafe {
raw_ids[i]
.as_mut_ptr()
.byte_add(T::DRIVER_DATA_OFFSET)
- .cast::<usize>()
- .write(i);
+ .cast::<&U>()
+ .write(ids[i].1);
}
- // SAFETY: this is effectively a move: `infos[i] = ids[i].1`. We make a copy here but
- // later forget `ids`.
- infos[i] = MaybeUninit::new(unsafe { core::ptr::read(&ids[i].1) });
i += 1;
}
@@ -106,20 +138,15 @@ impl<T: RawDeviceId + RawDeviceIdIndex, U, const N: usize> IdArray<T, U, N> {
Self {
raw_ids: RawIdArray {
- // SAFETY: this is effectively `array_assume_init`, which is unstable, so we use
- // `transmute_copy` instead. We have initialized all elements of `raw_ids` so this
- // `array_assume_init` is safe.
- ids: unsafe { core::mem::transmute_copy(&raw_ids) },
+ ids: raw_ids,
sentinel: MaybeUninit::zeroed(),
},
- // SAFETY: We have initialized all elements of `infos` so this `array_assume_init` is
- // safe.
- id_infos: unsafe { core::mem::transmute_copy(&infos) },
+ phantom: PhantomData,
}
}
}
-impl<T: RawDeviceId, U, const N: usize> IdArray<T, U, N> {
+impl<T: RawDeviceId, U: 'static, const N: usize> IdArray<T, U, N> {
/// Reference to the contained [`RawIdArray`].
pub const fn raw_ids(&self) -> &RawIdArray<T, N> {
&self.raw_ids
@@ -133,7 +160,7 @@ impl<T: RawDeviceId, const N: usize> IdArray<T, (), N> {
/// If the device implements [`RawDeviceIdIndex`], consider using [`IdArray::new`] instead.
pub const fn new_without_index(ids: [T; N]) -> Self {
// SAFETY: `T` is layout-wise compatible with `T::RawType`, so is the array of them.
- let raw_ids: [T::RawType; N] = unsafe { core::mem::transmute_copy(&ids) };
+ let raw_ids: [MaybeUninit<T::RawType>; N] = unsafe { core::mem::transmute_copy(&ids) };
core::mem::forget(ids);
Self {
@@ -141,7 +168,7 @@ impl<T: RawDeviceId, const N: usize> IdArray<T, (), N> {
ids: raw_ids,
sentinel: MaybeUninit::zeroed(),
},
- id_infos: [(); N],
+ phantom: PhantomData,
}
}
}
@@ -155,9 +182,6 @@ impl<T: RawDeviceId, const N: usize> IdArray<T, (), N> {
pub trait IdTable<T: RawDeviceId, U> {
/// Obtain the pointer to the ID table.
fn as_ptr(&self) -> *const T::RawType;
-
- /// Obtain the pointer to the driver-specific information from an index.
- fn info(&self, index: usize) -> &U;
}
impl<T: RawDeviceId, U, const N: usize> IdTable<T, U> for IdArray<T, U, N> {
@@ -166,10 +190,6 @@ fn as_ptr(&self) -> *const T::RawType {
// to access the sentinel.
core::ptr::from_ref(self).cast()
}
-
- fn info(&self, index: usize) -> &U {
- &self.id_infos[index]
- }
}
/// Create device table alias for modpost.
@@ -184,7 +204,7 @@ macro_rules! module_device_table {
$device_id_ty,
$id_info_type,
{ <[$device_id_ty]>::len(&[$($id,)*]) },
- > = $crate::device_id::IdArray::new([$(($id, $info),)*]);
+ > = $crate::device_id::IdArray::new([$(($id, &$info),)*]);
$crate::module_device_table!($table_type, $table_name);
};
diff --git a/rust/kernel/driver.rs b/rust/kernel/driver.rs
index bf5ba0d27553..824899d76fed 100644
--- a/rust/kernel/driver.rs
+++ b/rust/kernel/driver.rs
@@ -107,6 +107,7 @@
use crate::{
acpi,
device,
+ device_id::RawDeviceIdIndex,
of,
prelude::*,
types::Opaque,
@@ -350,7 +351,8 @@ fn acpi_id_info(dev: &device::Device) -> Option<&'static Self::IdInfo> {
// and does not add additional invariants, so it's safe to transmute.
let id = unsafe { &*raw_id.cast::<acpi::DeviceId>() };
- Some(table.info(<acpi::DeviceId as crate::device_id::RawDeviceIdIndex>::index(id)))
+ // SAFETY: `id` comes from `table` which is of type `IdArray<_, Self::IdInfo>`.
+ Some(unsafe { id.info_unchecked::<Self::IdInfo>() })
}
}
}
@@ -381,9 +383,8 @@ fn of_id_info(dev: &device::Device) -> Option<&'static Self::IdInfo> {
// and does not add additional invariants, so it's safe to transmute.
let id = unsafe { &*raw_id.cast::<of::DeviceId>() };
- return Some(table.info(
- <of::DeviceId as crate::device_id::RawDeviceIdIndex>::index(id),
- ));
+ // SAFETY: `id` comes from `table` which is of type `IdArray<_, Self::IdInfo>`.
+ return Some(unsafe { id.info_unchecked::<Self::IdInfo>() });
}
}
@@ -412,9 +413,8 @@ fn of_id_info(dev: &device::Device) -> Option<&'static Self::IdInfo> {
// and does not add additional invariants, so it's safe to transmute.
let id = unsafe { &*raw_id.cast::<of::DeviceId>() };
- return Some(table.info(
- <of::DeviceId as crate::device_id::RawDeviceIdIndex>::index(id),
- ));
+ // SAFETY: `id` comes from `table` which is of type `IdArray<_, Self::IdInfo>`.
+ return Some(unsafe { id.info_unchecked::<Self::IdInfo>() });
}
}
diff --git a/rust/kernel/i2c.rs b/rust/kernel/i2c.rs
index 55c89ba3a82a..9e551c7e8e41 100644
--- a/rust/kernel/i2c.rs
+++ b/rust/kernel/i2c.rs
@@ -65,10 +65,6 @@ unsafe impl RawDeviceId for DeviceId {
// SAFETY: `DRIVER_DATA_OFFSET` is the offset to the `driver_data` field.
unsafe impl RawDeviceIdIndex for DeviceId {
const DRIVER_DATA_OFFSET: usize = core::mem::offset_of!(bindings::i2c_device_id, driver_data);
-
- fn index(&self) -> usize {
- self.0.driver_data
- }
}
/// IdTable type for I2C
@@ -212,7 +208,8 @@ fn i2c_id_info(dev: &I2cClient) -> Option<&'static <Self as driver::Adapter>::Id
// does not add additional invariants, so it's safe to transmute.
let id = unsafe { &*raw_id.cast::<DeviceId>() };
- Some(table.info(<DeviceId as RawDeviceIdIndex>::index(id)))
+ // SAFETY: `id` comes from `table` which is of type `IdArray<_, Self::IdInfo>`.
+ Some(unsafe { id.info_unchecked::<T::IdInfo>() })
}
}
diff --git a/rust/kernel/of.rs b/rust/kernel/of.rs
index 35aa6d36d309..d0318f62afd7 100644
--- a/rust/kernel/of.rs
+++ b/rust/kernel/of.rs
@@ -25,10 +25,6 @@ unsafe impl RawDeviceId for DeviceId {
// SAFETY: `DRIVER_DATA_OFFSET` is the offset to the `data` field.
unsafe impl RawDeviceIdIndex for DeviceId {
const DRIVER_DATA_OFFSET: usize = core::mem::offset_of!(bindings::of_device_id, data);
-
- fn index(&self) -> usize {
- self.0.data as usize
- }
}
impl DeviceId {
diff --git a/rust/kernel/pci.rs b/rust/kernel/pci.rs
index a3dd48f76353..a630c7fc6a85 100644
--- a/rust/kernel/pci.rs
+++ b/rust/kernel/pci.rs
@@ -110,10 +110,13 @@ extern "C" fn probe_callback(
// SAFETY: `DeviceId` is a `#[repr(transparent)]` wrapper of `struct pci_device_id` and
// does not add additional invariants, so it's safe to transmute.
let id = unsafe { &*id.cast::<DeviceId>() };
- let info = T::ID_TABLE.info(id.index());
+
+ // SAFETY: `id` comes from `T::ID_TABLE` which is of type `IdArray<_, T::IdInfo>` or
+ // `pci_device_id_any` which has 0 as driver_data.
+ let info = unsafe { id.info_unchecked_opt::<T::IdInfo>() };
from_result(|| {
- let data = T::probe(pdev, Some(info));
+ let data = T::probe(pdev, info);
pdev.as_ref().set_drvdata(data)?;
Ok(0)
@@ -233,10 +236,6 @@ unsafe impl RawDeviceId for DeviceId {
// SAFETY: `DRIVER_DATA_OFFSET` is the offset to the `driver_data` field.
unsafe impl RawDeviceIdIndex for DeviceId {
const DRIVER_DATA_OFFSET: usize = core::mem::offset_of!(bindings::pci_device_id, driver_data);
-
- fn index(&self) -> usize {
- self.0.driver_data
- }
}
/// `IdTable` type for PCI.
diff --git a/rust/kernel/usb.rs b/rust/kernel/usb.rs
index 500b5e0ba4ea..8aeff5011755 100644
--- a/rust/kernel/usb.rs
+++ b/rust/kernel/usb.rs
@@ -89,7 +89,8 @@ extern "C" fn probe_callback(
// does not add additional invariants, so it's safe to transmute.
let id = unsafe { &*id.cast::<DeviceId>() };
- let info = T::ID_TABLE.info(id.index());
+ // SAFETY: `id` comes from `T::ID_TABLE` which is of type `IdArray<_, T::IdInfo>`.
+ let info = unsafe { id.info_unchecked::<T::IdInfo>() };
let data = T::probe(intf, id, info);
let dev: &device::Device<device::CoreInternal<'_>> = intf.as_ref();
@@ -242,10 +243,6 @@ unsafe impl RawDeviceId for DeviceId {
// SAFETY: `DRIVER_DATA_OFFSET` is the offset to the `driver_info` field.
unsafe impl RawDeviceIdIndex for DeviceId {
const DRIVER_DATA_OFFSET: usize = core::mem::offset_of!(bindings::usb_device_id, driver_info);
-
- fn index(&self) -> usize {
- self.0.driver_info
- }
}
/// [`IdTable`](kernel::device_id::IdTable) type for USB.
--
2.54.0
^ permalink raw reply related
* [PATCH 06/10] rust: driver: remove `$module_table_name` from `module_device_table`
From: Gary Guo @ 2026-06-18 17:03 UTC (permalink / raw)
To: Greg Kroah-Hartman, Rafael J. Wysocki, Danilo Krummrich,
Miguel Ojeda, Boqun Feng, Björn Roy Baron, Benno Lossin,
Andreas Hindborg, Alice Ryhl, Trevor Gross, Daniel Almeida,
Tamir Duberstein, Alexandre Courbot, Onur Özkan,
FUJITA Tomonori, David Airlie, Simona Vetter, Bjorn Helgaas,
Krzysztof Wilczyński, Abdiel Janulgue, Robin Murphy,
Dave Ertman, Ira Weiny, Leon Romanovsky, Len Brown, Igor Korotin,
Rob Herring, Saravana Kannan, Viresh Kumar, Michal Wilczynski,
Drew Fustini, Guo Ren, Fu Wei, Uwe Kleine-König
Cc: driver-core, rust-for-linux, linux-kernel, netdev, nova-gpu,
dri-devel, linux-pci, linux-acpi, devicetree, linux-pm,
linux-riscv, linux-pwm, Gary Guo
In-Reply-To: <20260618-id_info-v1-0-96af1e559ef9@garyguo.net>
Wrap the generated code in a `const _: ()` block to avoid symbol conflict.
This removes the need of creating a new identifier.
Signed-off-by: Gary Guo <gary@garyguo.net>
---
drivers/cpufreq/rcpufreq_dt.rs | 1 -
drivers/gpu/drm/nova/driver.rs | 1 -
drivers/gpu/drm/tyr/driver.rs | 1 -
drivers/gpu/nova-core/driver.rs | 1 -
drivers/pwm/pwm_th1520.rs | 1 -
rust/kernel/device_id.rs | 30 ++++++++++++++++--------------
rust/kernel/i2c.rs | 3 ---
rust/kernel/net/phy.rs | 2 +-
rust/kernel/pci.rs | 1 -
rust/kernel/platform.rs | 2 --
rust/kernel/usb.rs | 1 -
samples/rust/rust_debugfs.rs | 1 -
samples/rust/rust_dma.rs | 1 -
samples/rust/rust_driver_auxiliary.rs | 2 --
samples/rust/rust_driver_i2c.rs | 3 ---
samples/rust/rust_driver_pci.rs | 1 -
samples/rust/rust_driver_platform.rs | 2 --
samples/rust/rust_driver_usb.rs | 1 -
samples/rust/rust_i2c_client.rs | 2 --
samples/rust/rust_soc.rs | 2 --
20 files changed, 17 insertions(+), 42 deletions(-)
diff --git a/drivers/cpufreq/rcpufreq_dt.rs b/drivers/cpufreq/rcpufreq_dt.rs
index 10106fa13095..145daa12072f 100644
--- a/drivers/cpufreq/rcpufreq_dt.rs
+++ b/drivers/cpufreq/rcpufreq_dt.rs
@@ -194,7 +194,6 @@ fn register_em(policy: &mut cpufreq::Policy) {
kernel::of_device_table!(
OF_TABLE,
- MODULE_OF_TABLE,
<CPUFreqDTDriver as platform::Driver>::IdInfo,
[(of::DeviceId::new(c"operating-points-v2"), ())]
);
diff --git a/drivers/gpu/drm/nova/driver.rs b/drivers/gpu/drm/nova/driver.rs
index 48933d86ddda..43f15cdfeb09 100644
--- a/drivers/gpu/drm/nova/driver.rs
+++ b/drivers/gpu/drm/nova/driver.rs
@@ -43,7 +43,6 @@ pub(crate) struct NovaData {
kernel::auxiliary_device_table!(
AUX_TABLE,
- MODULE_AUX_TABLE,
<NovaDriver as auxiliary::Driver>::IdInfo,
[(
auxiliary::DeviceId::new(NOVA_CORE_MODULE_NAME, AUXILIARY_NAME),
diff --git a/drivers/gpu/drm/tyr/driver.rs b/drivers/gpu/drm/tyr/driver.rs
index d063bc664cc1..218e9af899c7 100644
--- a/drivers/gpu/drm/tyr/driver.rs
+++ b/drivers/gpu/drm/tyr/driver.rs
@@ -87,7 +87,6 @@ fn issue_soft_reset(dev: &Device, iomem: &IoMem<'_>) -> Result {
kernel::of_device_table!(
OF_TABLE,
- MODULE_OF_TABLE,
<TyrPlatformDriver as platform::Driver>::IdInfo,
[
(of::DeviceId::new(c"rockchip,rk3588-mali"), ()),
diff --git a/drivers/gpu/nova-core/driver.rs b/drivers/gpu/nova-core/driver.rs
index 5a5f0b63e0f3..0c53b7239ac9 100644
--- a/drivers/gpu/nova-core/driver.rs
+++ b/drivers/gpu/nova-core/driver.rs
@@ -40,7 +40,6 @@ pub(crate) struct NovaCore<'bound> {
kernel::pci_device_table!(
PCI_TABLE,
- MODULE_PCI_TABLE,
<NovaCoreDriver as pci::Driver>::IdInfo,
[
// Modern NVIDIA GPUs will show up as either VGA or 3D controllers.
diff --git a/drivers/pwm/pwm_th1520.rs b/drivers/pwm/pwm_th1520.rs
index 3e3fa51ccef9..1df752330e8f 100644
--- a/drivers/pwm/pwm_th1520.rs
+++ b/drivers/pwm/pwm_th1520.rs
@@ -303,7 +303,6 @@ fn drop(self: Pin<&mut Self>) {
kernel::of_device_table!(
OF_TABLE,
- MODULE_OF_TABLE,
<Th1520PwmPlatformDriver as platform::Driver>::IdInfo,
[(of::DeviceId::new(c"thead,th1520-pwm"), ())]
);
diff --git a/rust/kernel/device_id.rs b/rust/kernel/device_id.rs
index 0239f89d5f69..84852a2d9ad7 100644
--- a/rust/kernel/device_id.rs
+++ b/rust/kernel/device_id.rs
@@ -177,7 +177,7 @@ fn info(&self, index: usize) -> &U {
macro_rules! module_device_table {
(
$table_type: literal, $device_id_ty: ty,
- $table_name: ident, $module_table_name: ident, $id_info_type: ty,
+ $table_name: ident, $id_info_type: ty,
[$(($id: expr, $info:expr $(,)?)),* $(,)?]
) => {
const $table_name: $crate::device_id::IdArray<
@@ -186,13 +186,13 @@ macro_rules! module_device_table {
{ <[$device_id_ty]>::len(&[$($id,)*]) },
> = $crate::device_id::IdArray::new([$(($id, $info),)*]);
- $crate::module_device_table!($table_type, $module_table_name, $table_name);
+ $crate::module_device_table!($table_type, $table_name);
};
// Case for no ID info.
(
$table_type: literal, $device_id_ty: ty,
- $table_name: ident, $module_table_name: ident, @none,
+ $table_name: ident, @none,
[$($id: expr),* $(,)?]
) => {
const $table_name: $crate::device_id::IdArray<
@@ -201,18 +201,20 @@ macro_rules! module_device_table {
{ <[$device_id_ty]>::len(&[$($id,)*]) },
> = $crate::device_id::IdArray::new_without_index([$($id),*]);
- $crate::module_device_table!($table_type, $module_table_name, $table_name);
+ $crate::module_device_table!($table_type, $table_name);
};
- ($table_type: literal, $module_table_name: ident, $table_name:ident) => {
- #[rustfmt::skip]
- #[export_name =
- concat!("__mod_device_table__", line!(),
- "__kmod_", module_path!(),
- "__", $table_type,
- "__", stringify!($table_name))
- ]
- static $module_table_name: [::core::mem::MaybeUninit<u8>; $table_name.raw_ids().size()] =
- unsafe { ::core::mem::transmute_copy($table_name.raw_ids()) };
+ ($table_type: literal, $table_name:ident) => {
+ const _: () = {
+ #[rustfmt::skip]
+ #[export_name =
+ concat!("__mod_device_table__", line!(),
+ "__kmod_", module_path!(),
+ "__", $table_type,
+ "__", stringify!($table_name))
+ ]
+ static TABLE: [::core::mem::MaybeUninit<u8>; $table_name.raw_ids().size()] =
+ unsafe { ::core::mem::transmute_copy($table_name.raw_ids()) };
+ };
};
}
diff --git a/rust/kernel/i2c.rs b/rust/kernel/i2c.rs
index a7d9b88ae616..55c89ba3a82a 100644
--- a/rust/kernel/i2c.rs
+++ b/rust/kernel/i2c.rs
@@ -261,7 +261,6 @@ macro_rules! module_i2c_driver {
///
/// kernel::acpi_device_table!(
/// ACPI_TABLE,
-/// MODULE_ACPI_TABLE,
/// <MyDriver as i2c::Driver>::IdInfo,
/// [
/// (acpi::DeviceId::new(c"LNUXBEEF"), ())
@@ -270,7 +269,6 @@ macro_rules! module_i2c_driver {
///
/// kernel::i2c_device_table!(
/// I2C_TABLE,
-/// MODULE_I2C_TABLE,
/// <MyDriver as i2c::Driver>::IdInfo,
/// [
/// (i2c::DeviceId::new(c"rust_driver_i2c"), ())
@@ -279,7 +277,6 @@ macro_rules! module_i2c_driver {
///
/// kernel::of_device_table!(
/// OF_TABLE,
-/// MODULE_OF_TABLE,
/// <MyDriver as i2c::Driver>::IdInfo,
/// [
/// (of::DeviceId::new(c"test,device"), ())
diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs
index 166572861e61..1e86b901c391 100644
--- a/rust/kernel/net/phy.rs
+++ b/rust/kernel/net/phy.rs
@@ -811,7 +811,7 @@ macro_rules! module_phy_driver {
(@device_table [$($dev:expr),+]) => {
$crate::module_device_table!(
"mdio", $crate::net::phy::DeviceId,
- phydev, TABLE, @none, [$($dev),+]
+ TABLE, @none, [$($dev),+]
);
};
diff --git a/rust/kernel/pci.rs b/rust/kernel/pci.rs
index 34e07a53244d..a3dd48f76353 100644
--- a/rust/kernel/pci.rs
+++ b/rust/kernel/pci.rs
@@ -261,7 +261,6 @@ macro_rules! pci_device_table {
///
/// kernel::pci_device_table!(
/// PCI_TABLE,
-/// MODULE_PCI_TABLE,
/// <MyDriver as pci::Driver>::IdInfo,
/// [
/// (
diff --git a/rust/kernel/platform.rs b/rust/kernel/platform.rs
index 9b362e0495d3..210a815925ce 100644
--- a/rust/kernel/platform.rs
+++ b/rust/kernel/platform.rs
@@ -176,7 +176,6 @@ macro_rules! module_platform_driver {
///
/// kernel::of_device_table!(
/// OF_TABLE,
-/// MODULE_OF_TABLE,
/// <MyDriver as platform::Driver>::IdInfo,
/// [
/// (of::DeviceId::new(c"test,device"), ())
@@ -185,7 +184,6 @@ macro_rules! module_platform_driver {
///
/// kernel::acpi_device_table!(
/// ACPI_TABLE,
-/// MODULE_ACPI_TABLE,
/// <MyDriver as platform::Driver>::IdInfo,
/// [
/// (acpi::DeviceId::new(c"LNUXBEEF"), ())
diff --git a/rust/kernel/usb.rs b/rust/kernel/usb.rs
index 154919ee1e19..500b5e0ba4ea 100644
--- a/rust/kernel/usb.rs
+++ b/rust/kernel/usb.rs
@@ -271,7 +271,6 @@ macro_rules! usb_device_table {
///
/// kernel::usb_device_table!(
/// USB_TABLE,
-/// MODULE_USB_TABLE,
/// <MyDriver as usb::Driver>::IdInfo,
/// [
/// (usb::DeviceId::from_id(0x1234, 0x5678), ()),
diff --git a/samples/rust/rust_debugfs.rs b/samples/rust/rust_debugfs.rs
index 1f59e08aaa4b..181fd98ae5b6 100644
--- a/samples/rust/rust_debugfs.rs
+++ b/samples/rust/rust_debugfs.rs
@@ -110,7 +110,6 @@ fn from_str(s: &str) -> Result<Self> {
kernel::acpi_device_table!(
ACPI_TABLE,
- MODULE_ACPI_TABLE,
<RustDebugFs as platform::Driver>::IdInfo,
[(acpi::DeviceId::new(c"LNUXBEEF"), ())]
);
diff --git a/samples/rust/rust_dma.rs b/samples/rust/rust_dma.rs
index 9beb37275e0d..80c309ce07e9 100644
--- a/samples/rust/rust_dma.rs
+++ b/samples/rust/rust_dma.rs
@@ -51,7 +51,6 @@ unsafe impl kernel::transmute::FromBytes for MyStruct {}
kernel::pci_device_table!(
PCI_TABLE,
- MODULE_PCI_TABLE,
<DmaSampleDriver as pci::Driver>::IdInfo,
[(pci::DeviceId::from_id(pci::Vendor::REDHAT, 0x5), ())]
);
diff --git a/samples/rust/rust_driver_auxiliary.rs b/samples/rust/rust_driver_auxiliary.rs
index 73c63afc046a..704567a072ba 100644
--- a/samples/rust/rust_driver_auxiliary.rs
+++ b/samples/rust/rust_driver_auxiliary.rs
@@ -24,7 +24,6 @@
kernel::auxiliary_device_table!(
AUX_TABLE,
- MODULE_AUX_TABLE,
<AuxiliaryDriver as auxiliary::Driver>::IdInfo,
[(auxiliary::DeviceId::new(MODULE_NAME, AUXILIARY_NAME), ())]
);
@@ -66,7 +65,6 @@ struct ParentData<'bound> {
kernel::pci_device_table!(
PCI_TABLE,
- MODULE_PCI_TABLE,
<ParentDriver as pci::Driver>::IdInfo,
[(pci::DeviceId::from_id(pci::Vendor::REDHAT, 0x5), ())]
);
diff --git a/samples/rust/rust_driver_i2c.rs b/samples/rust/rust_driver_i2c.rs
index ead8263a7d48..a0df0c6097c4 100644
--- a/samples/rust/rust_driver_i2c.rs
+++ b/samples/rust/rust_driver_i2c.rs
@@ -14,21 +14,18 @@
kernel::acpi_device_table! {
ACPI_TABLE,
- MODULE_ACPI_TABLE,
<SampleDriver as i2c::Driver>::IdInfo,
[(acpi::DeviceId::new(c"LNUXBEEF"), 0)]
}
kernel::i2c_device_table! {
I2C_TABLE,
- MODULE_I2C_TABLE,
<SampleDriver as i2c::Driver>::IdInfo,
[(i2c::DeviceId::new(c"rust_driver_i2c"), 0)]
}
kernel::of_device_table! {
OF_TABLE,
- MODULE_OF_TABLE,
<SampleDriver as i2c::Driver>::IdInfo,
[(of::DeviceId::new(c"test,rust_driver_i2c"), 0)]
}
diff --git a/samples/rust/rust_driver_pci.rs b/samples/rust/rust_driver_pci.rs
index 5547dd704a1b..2282191e6292 100644
--- a/samples/rust/rust_driver_pci.rs
+++ b/samples/rust/rust_driver_pci.rs
@@ -74,7 +74,6 @@ struct SampleDriverData<'bound> {
kernel::pci_device_table!(
PCI_TABLE,
- MODULE_PCI_TABLE,
<SampleDriver as pci::Driver>::IdInfo,
[(
pci::DeviceId::from_id(pci::Vendor::REDHAT, 0x5),
diff --git a/samples/rust/rust_driver_platform.rs b/samples/rust/rust_driver_platform.rs
index ec0d6cac4f57..710145b3605a 100644
--- a/samples/rust/rust_driver_platform.rs
+++ b/samples/rust/rust_driver_platform.rs
@@ -87,14 +87,12 @@ struct SampleDriver {
kernel::of_device_table!(
OF_TABLE,
- MODULE_OF_TABLE,
<SampleDriver as platform::Driver>::IdInfo,
[(of::DeviceId::new(c"test,rust-device"), Info(42))]
);
kernel::acpi_device_table!(
ACPI_TABLE,
- MODULE_ACPI_TABLE,
<SampleDriver as platform::Driver>::IdInfo,
[(acpi::DeviceId::new(c"LNUXBEEF"), Info(0))]
);
diff --git a/samples/rust/rust_driver_usb.rs b/samples/rust/rust_driver_usb.rs
index 02bd5085f9bc..284042c5969b 100644
--- a/samples/rust/rust_driver_usb.rs
+++ b/samples/rust/rust_driver_usb.rs
@@ -19,7 +19,6 @@ struct SampleDriver {
kernel::usb_device_table!(
USB_TABLE,
- MODULE_USB_TABLE,
<SampleDriver as usb::Driver>::IdInfo,
[(usb::DeviceId::from_id(0x1234, 0x5678), ()),]
);
diff --git a/samples/rust/rust_i2c_client.rs b/samples/rust/rust_i2c_client.rs
index 2d876f4e3ee0..c8a23875ef5b 100644
--- a/samples/rust/rust_i2c_client.rs
+++ b/samples/rust/rust_i2c_client.rs
@@ -87,14 +87,12 @@ struct SampleDriver {
kernel::of_device_table!(
OF_TABLE,
- MODULE_OF_TABLE,
<SampleDriver as platform::Driver>::IdInfo,
[(of::DeviceId::new(c"test,rust-device"), ())]
);
kernel::acpi_device_table!(
ACPI_TABLE,
- MODULE_ACPI_TABLE,
<SampleDriver as platform::Driver>::IdInfo,
[(acpi::DeviceId::new(c"LNUXBEEF"), ())]
);
diff --git a/samples/rust/rust_soc.rs b/samples/rust/rust_soc.rs
index 808d58200eb6..f5e5f2f9adf7 100644
--- a/samples/rust/rust_soc.rs
+++ b/samples/rust/rust_soc.rs
@@ -23,14 +23,12 @@ struct SampleSocDriver {
kernel::of_device_table!(
OF_TABLE,
- MODULE_OF_TABLE,
<SampleSocDriver as platform::Driver>::IdInfo,
[(of::DeviceId::new(c"test,rust-device"), ())]
);
kernel::acpi_device_table!(
ACPI_TABLE,
- MODULE_ACPI_TABLE,
<SampleSocDriver as platform::Driver>::IdInfo,
[(acpi::DeviceId::new(c"LNUXBEEF"), ())]
);
--
2.54.0
^ permalink raw reply related
* [PATCH 05/10] rust: driver: centralize device ID handling
From: Gary Guo @ 2026-06-18 17:03 UTC (permalink / raw)
To: Greg Kroah-Hartman, Rafael J. Wysocki, Danilo Krummrich,
Miguel Ojeda, Boqun Feng, Björn Roy Baron, Benno Lossin,
Andreas Hindborg, Alice Ryhl, Trevor Gross, Daniel Almeida,
Tamir Duberstein, Alexandre Courbot, Onur Özkan,
FUJITA Tomonori, David Airlie, Simona Vetter, Bjorn Helgaas,
Krzysztof Wilczyński, Abdiel Janulgue, Robin Murphy,
Dave Ertman, Ira Weiny, Leon Romanovsky, Len Brown, Igor Korotin,
Rob Herring, Saravana Kannan, Viresh Kumar, Michal Wilczynski,
Drew Fustini, Guo Ren, Fu Wei, Uwe Kleine-König
Cc: driver-core, rust-for-linux, linux-kernel, netdev, nova-gpu,
dri-devel, linux-pci, linux-acpi, devicetree, linux-pm,
linux-riscv, linux-pwm, Gary Guo
In-Reply-To: <20260618-id_info-v1-0-96af1e559ef9@garyguo.net>
Move the `IdArray` creation from individual buses to be handled by shared
code in `device_id.rs`.
Signed-off-by: Gary Guo <gary@garyguo.net>
---
rust/kernel/acpi.rs | 10 ++--------
rust/kernel/auxiliary.rs | 10 ++--------
rust/kernel/device_id.rs | 31 ++++++++++++++++++++++++++++++-
rust/kernel/i2c.rs | 10 ++--------
rust/kernel/net/phy.rs | 10 ++++------
rust/kernel/of.rs | 10 ++--------
rust/kernel/pci.rs | 10 ++--------
rust/kernel/usb.rs | 10 ++--------
8 files changed, 46 insertions(+), 55 deletions(-)
diff --git a/rust/kernel/acpi.rs b/rust/kernel/acpi.rs
index 9b8efa623130..315f2f2af446 100644
--- a/rust/kernel/acpi.rs
+++ b/rust/kernel/acpi.rs
@@ -53,13 +53,7 @@ pub const fn new(id: &'static CStr) -> Self {
/// Create an ACPI `IdTable` with an "alias" for modpost.
#[macro_export]
macro_rules! acpi_device_table {
- ($table_name:ident, $module_table_name:ident, $id_info_type: ty, $table_data: expr) => {
- const $table_name: $crate::device_id::IdArray<
- $crate::acpi::DeviceId,
- $id_info_type,
- { $table_data.len() },
- > = $crate::device_id::IdArray::new($table_data);
-
- $crate::module_device_table!("acpi", $module_table_name, $table_name);
+ ($($tt:tt)*) => {
+ $crate::module_device_table!("acpi", $crate::acpi::DeviceId, $($tt)*);
};
}
diff --git a/rust/kernel/auxiliary.rs b/rust/kernel/auxiliary.rs
index c42928d5a239..59787c9bff26 100644
--- a/rust/kernel/auxiliary.rs
+++ b/rust/kernel/auxiliary.rs
@@ -181,14 +181,8 @@ fn index(&self) -> usize {
/// Create a auxiliary `IdTable` with its alias for modpost.
#[macro_export]
macro_rules! auxiliary_device_table {
- ($table_name:ident, $module_table_name:ident, $id_info_type: ty, $table_data: expr) => {
- const $table_name: $crate::device_id::IdArray<
- $crate::auxiliary::DeviceId,
- $id_info_type,
- { $table_data.len() },
- > = $crate::device_id::IdArray::new($table_data);
-
- $crate::module_device_table!("auxiliary", $module_table_name, $table_name);
+ ($($tt:tt)*) => {
+ $crate::module_device_table!("auxiliary", $crate::auxiliary::DeviceId, $($tt)*);
};
}
diff --git a/rust/kernel/device_id.rs b/rust/kernel/device_id.rs
index eeef3f5e7b63..0239f89d5f69 100644
--- a/rust/kernel/device_id.rs
+++ b/rust/kernel/device_id.rs
@@ -175,7 +175,36 @@ fn info(&self, index: usize) -> &U {
/// Create device table alias for modpost.
#[macro_export]
macro_rules! module_device_table {
- ($table_type: literal, $module_table_name:ident, $table_name:ident) => {
+ (
+ $table_type: literal, $device_id_ty: ty,
+ $table_name: ident, $module_table_name: ident, $id_info_type: ty,
+ [$(($id: expr, $info:expr $(,)?)),* $(,)?]
+ ) => {
+ const $table_name: $crate::device_id::IdArray<
+ $device_id_ty,
+ $id_info_type,
+ { <[$device_id_ty]>::len(&[$($id,)*]) },
+ > = $crate::device_id::IdArray::new([$(($id, $info),)*]);
+
+ $crate::module_device_table!($table_type, $module_table_name, $table_name);
+ };
+
+ // Case for no ID info.
+ (
+ $table_type: literal, $device_id_ty: ty,
+ $table_name: ident, $module_table_name: ident, @none,
+ [$($id: expr),* $(,)?]
+ ) => {
+ const $table_name: $crate::device_id::IdArray<
+ $device_id_ty,
+ (),
+ { <[$device_id_ty]>::len(&[$($id,)*]) },
+ > = $crate::device_id::IdArray::new_without_index([$($id),*]);
+
+ $crate::module_device_table!($table_type, $module_table_name, $table_name);
+ };
+
+ ($table_type: literal, $module_table_name: ident, $table_name:ident) => {
#[rustfmt::skip]
#[export_name =
concat!("__mod_device_table__", line!(),
diff --git a/rust/kernel/i2c.rs b/rust/kernel/i2c.rs
index 7655d61daac8..a7d9b88ae616 100644
--- a/rust/kernel/i2c.rs
+++ b/rust/kernel/i2c.rs
@@ -77,14 +77,8 @@ fn index(&self) -> usize {
/// Create a I2C `IdTable` with its alias for modpost.
#[macro_export]
macro_rules! i2c_device_table {
- ($table_name:ident, $module_table_name:ident, $id_info_type: ty, $table_data: expr) => {
- const $table_name: $crate::device_id::IdArray<
- $crate::i2c::DeviceId,
- $id_info_type,
- { $table_data.len() },
- > = $crate::device_id::IdArray::new($table_data);
-
- $crate::module_device_table!("i2c", $module_table_name, $table_name);
+ ($($tt:tt)*) => {
+ $crate::module_device_table!("i2c", $crate::i2c::DeviceId, $($tt)*);
};
}
diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs
index 965ecca7d55f..166572861e61 100644
--- a/rust/kernel/net/phy.rs
+++ b/rust/kernel/net/phy.rs
@@ -809,12 +809,10 @@ macro_rules! module_phy_driver {
};
(@device_table [$($dev:expr),+]) => {
- const N: usize = $crate::module_phy_driver!(@count_devices $($dev),+);
-
- const TABLE: $crate::device_id::IdArray<$crate::net::phy::DeviceId, (), N> =
- $crate::device_id::IdArray::new_without_index([ $($dev),+, ]);
-
- $crate::module_device_table!("mdio", phydev, TABLE);
+ $crate::module_device_table!(
+ "mdio", $crate::net::phy::DeviceId,
+ phydev, TABLE, @none, [$($dev),+]
+ );
};
(drivers: [$($driver:ident),+ $(,)?], device_table: [$($dev:expr),+ $(,)?], $($f:tt)*) => {
diff --git a/rust/kernel/of.rs b/rust/kernel/of.rs
index 58b20c367f99..35aa6d36d309 100644
--- a/rust/kernel/of.rs
+++ b/rust/kernel/of.rs
@@ -53,13 +53,7 @@ pub const fn new(compatible: &'static CStr) -> Self {
/// Create an OF `IdTable` with an "alias" for modpost.
#[macro_export]
macro_rules! of_device_table {
- ($table_name:ident, $module_table_name:ident, $id_info_type: ty, $table_data: expr) => {
- const $table_name: $crate::device_id::IdArray<
- $crate::of::DeviceId,
- $id_info_type,
- { $table_data.len() },
- > = $crate::device_id::IdArray::new($table_data);
-
- $crate::module_device_table!("of", $module_table_name, $table_name);
+ ($($tt:tt)*) => {
+ $crate::module_device_table!("of", $crate::of::DeviceId, $($tt)*);
};
}
diff --git a/rust/kernel/pci.rs b/rust/kernel/pci.rs
index 0e055e4df99e..34e07a53244d 100644
--- a/rust/kernel/pci.rs
+++ b/rust/kernel/pci.rs
@@ -245,14 +245,8 @@ fn index(&self) -> usize {
/// Create a PCI `IdTable` with its alias for modpost.
#[macro_export]
macro_rules! pci_device_table {
- ($table_name:ident, $module_table_name:ident, $id_info_type: ty, $table_data: expr) => {
- const $table_name: $crate::device_id::IdArray<
- $crate::pci::DeviceId,
- $id_info_type,
- { $table_data.len() },
- > = $crate::device_id::IdArray::new($table_data);
-
- $crate::module_device_table!("pci", $module_table_name, $table_name);
+ ($($tt:tt)*) => {
+ $crate::module_device_table!("pci", $crate::pci::DeviceId, $($tt)*);
};
}
diff --git a/rust/kernel/usb.rs b/rust/kernel/usb.rs
index 7aff0c82d0af..154919ee1e19 100644
--- a/rust/kernel/usb.rs
+++ b/rust/kernel/usb.rs
@@ -254,14 +254,8 @@ fn index(&self) -> usize {
/// Create a USB `IdTable` with its alias for modpost.
#[macro_export]
macro_rules! usb_device_table {
- ($table_name:ident, $module_table_name:ident, $id_info_type: ty, $table_data: expr) => {
- const $table_name: $crate::device_id::IdArray<
- $crate::usb::DeviceId,
- $id_info_type,
- { $table_data.len() },
- > = $crate::device_id::IdArray::new($table_data);
-
- $crate::module_device_table!("usb", $module_table_name, $table_name);
+ ($($tt:tt)*) => {
+ $crate::module_device_table!("usb", $crate::usb::DeviceId, $($tt)*);
};
}
--
2.54.0
^ permalink raw reply related
* [PATCH 04/10] rust: net/phy: remove expansion from doc
From: Gary Guo @ 2026-06-18 17:03 UTC (permalink / raw)
To: Greg Kroah-Hartman, Rafael J. Wysocki, Danilo Krummrich,
Miguel Ojeda, Boqun Feng, Björn Roy Baron, Benno Lossin,
Andreas Hindborg, Alice Ryhl, Trevor Gross, Daniel Almeida,
Tamir Duberstein, Alexandre Courbot, Onur Özkan,
FUJITA Tomonori, David Airlie, Simona Vetter, Bjorn Helgaas,
Krzysztof Wilczyński, Abdiel Janulgue, Robin Murphy,
Dave Ertman, Ira Weiny, Leon Romanovsky, Len Brown, Igor Korotin,
Rob Herring, Saravana Kannan, Viresh Kumar, Michal Wilczynski,
Drew Fustini, Guo Ren, Fu Wei, Uwe Kleine-König
Cc: driver-core, rust-for-linux, linux-kernel, netdev, nova-gpu,
dri-devel, linux-pci, linux-acpi, devicetree, linux-pm,
linux-riscv, linux-pwm, Gary Guo
In-Reply-To: <20260618-id_info-v1-0-96af1e559ef9@garyguo.net>
The expansion serves little purpose and it can easily diverge.
Signed-off-by: Gary Guo <gary@garyguo.net>
---
rust/kernel/net/phy.rs | 56 --------------------------------------------------
1 file changed, 56 deletions(-)
diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs
index 2868e3a9e02c..965ecca7d55f 100644
--- a/rust/kernel/net/phy.rs
+++ b/rust/kernel/net/phy.rs
@@ -800,62 +800,6 @@ const fn as_int(&self) -> u32 {
/// }
/// # }
/// ```
-///
-/// This expands to the following code:
-///
-/// ```ignore
-/// use kernel::net::phy::{self, DeviceId};
-/// use kernel::prelude::*;
-///
-/// struct Module {
-/// _reg: ::kernel::net::phy::Registration,
-/// }
-///
-/// module! {
-/// type: Module,
-/// name: "rust_sample_phy",
-/// authors: ["Rust for Linux Contributors"],
-/// description: "Rust sample PHYs driver",
-/// license: "GPL",
-/// }
-///
-/// struct PhySample;
-///
-/// #[vtable]
-/// impl phy::Driver for PhySample {
-/// const NAME: &'static CStr = c"PhySample";
-/// const PHY_DEVICE_ID: phy::DeviceId = phy::DeviceId::new_with_exact_mask(0x00000001);
-/// }
-///
-/// const _: () = {
-/// static mut DRIVERS: [::kernel::net::phy::DriverVTable; 1] =
-/// [::kernel::net::phy::create_phy_driver::<PhySample>()];
-///
-/// impl ::kernel::Module for Module {
-/// fn init(module: &'static ::kernel::ThisModule) -> Result<Self> {
-/// let drivers = unsafe { &mut DRIVERS };
-/// let mut reg = ::kernel::net::phy::Registration::register(
-/// module,
-/// ::core::pin::Pin::static_mut(drivers),
-/// )?;
-/// Ok(Module { _reg: reg })
-/// }
-/// }
-/// };
-///
-/// const N: usize = 1;
-///
-/// const TABLE: ::kernel::device_id::IdArray<::kernel::net::phy::DeviceId, (), N> =
-/// ::kernel::device_id::IdArray::new_without_index([
-/// ::kernel::net::phy::DeviceId(
-/// ::kernel::bindings::mdio_device_id {
-/// phy_id: 0x00000001,
-/// phy_id_mask: 0xffffffff,
-/// }),
-/// ]);
-///
-/// ::kernel::module_device_table!("mdio", phydev, TABLE);
-/// ```
#[macro_export]
macro_rules! module_phy_driver {
(@replace_expr $_t:tt $sub:expr) => {$sub};
--
2.54.0
^ permalink raw reply related
* [PATCH 03/10] rust: pci: use `Option<&IdInfo>` for device ID info
From: Gary Guo @ 2026-06-18 17:03 UTC (permalink / raw)
To: Greg Kroah-Hartman, Rafael J. Wysocki, Danilo Krummrich,
Miguel Ojeda, Boqun Feng, Björn Roy Baron, Benno Lossin,
Andreas Hindborg, Alice Ryhl, Trevor Gross, Daniel Almeida,
Tamir Duberstein, Alexandre Courbot, Onur Özkan,
FUJITA Tomonori, David Airlie, Simona Vetter, Bjorn Helgaas,
Krzysztof Wilczyński, Abdiel Janulgue, Robin Murphy,
Dave Ertman, Ira Weiny, Leon Romanovsky, Len Brown, Igor Korotin,
Rob Herring, Saravana Kannan, Viresh Kumar, Michal Wilczynski,
Drew Fustini, Guo Ren, Fu Wei, Uwe Kleine-König
Cc: driver-core, rust-for-linux, linux-kernel, netdev, nova-gpu,
dri-devel, linux-pci, linux-acpi, devicetree, linux-pm,
linux-riscv, linux-pwm, Gary Guo
In-Reply-To: <20260618-id_info-v1-0-96af1e559ef9@garyguo.net>
It is possible that `pci_device_id_any` will be passed to the driver, e.g.
`driver_override` is used on the device. Therefore, the driver must be able
to handle the case where `driver_data` is 0. Thus, update the `probe`
functions to get `Option`.
The current code cannot tell if the info does not exist or is the first
entry; however this will be achievable once the code is updated to use a
`&'static IdInfo` pointer instead of indices.
Signed-off-by: Gary Guo <gary@garyguo.net>
---
drivers/gpu/nova-core/driver.rs | 2 +-
rust/kernel/pci.rs | 6 +++---
samples/rust/rust_dma.rs | 2 +-
samples/rust/rust_driver_auxiliary.rs | 2 +-
samples/rust/rust_driver_pci.rs | 3 ++-
5 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/nova-core/driver.rs b/drivers/gpu/nova-core/driver.rs
index 5738d4ac521b..5a5f0b63e0f3 100644
--- a/drivers/gpu/nova-core/driver.rs
+++ b/drivers/gpu/nova-core/driver.rs
@@ -70,7 +70,7 @@ impl pci::Driver for NovaCoreDriver {
fn probe<'bound>(
pdev: &'bound pci::Device<Core<'_>>,
- _info: &'bound Self::IdInfo,
+ _info: Option<&'bound Self::IdInfo>,
) -> impl PinInit<Self::Data<'bound>, Error> + 'bound {
pin_init::pin_init_scope(move || {
dev_dbg!(pdev, "Probe Nova Core GPU driver.\n");
diff --git a/rust/kernel/pci.rs b/rust/kernel/pci.rs
index 5071cae6543f..0e055e4df99e 100644
--- a/rust/kernel/pci.rs
+++ b/rust/kernel/pci.rs
@@ -113,7 +113,7 @@ extern "C" fn probe_callback(
let info = T::ID_TABLE.info(id.index());
from_result(|| {
- let data = T::probe(pdev, info);
+ let data = T::probe(pdev, Some(info));
pdev.as_ref().set_drvdata(data)?;
Ok(0)
@@ -284,7 +284,7 @@ macro_rules! pci_device_table {
///
/// fn probe<'bound>(
/// _pdev: &'bound pci::Device<Core<'_>>,
-/// _id_info: &'bound Self::IdInfo,
+/// _id_info: Option<&'bound Self::IdInfo>,
/// ) -> impl PinInit<Self::Data<'bound>, Error> + 'bound {
/// Err(ENODEV)
/// }
@@ -313,7 +313,7 @@ pub trait Driver {
/// attempt to initialize the device here.
fn probe<'bound>(
dev: &'bound Device<device::Core<'_>>,
- id_info: &'bound Self::IdInfo,
+ id_info: Option<&'bound Self::IdInfo>,
) -> impl PinInit<Self::Data<'bound>, Error> + 'bound;
/// PCI driver unbind.
diff --git a/samples/rust/rust_dma.rs b/samples/rust/rust_dma.rs
index 5046b4628d0e..9beb37275e0d 100644
--- a/samples/rust/rust_dma.rs
+++ b/samples/rust/rust_dma.rs
@@ -63,7 +63,7 @@ impl pci::Driver for DmaSampleDriver {
fn probe<'bound>(
pdev: &'bound pci::Device<Core<'_>>,
- _info: &'bound Self::IdInfo,
+ _info: Option<&'bound Self::IdInfo>,
) -> impl PinInit<Self, Error> + 'bound {
pin_init::pin_init_scope(move || {
dev_info!(pdev, "Probe DMA test driver.\n");
diff --git a/samples/rust/rust_driver_auxiliary.rs b/samples/rust/rust_driver_auxiliary.rs
index 2c1351040e45..73c63afc046a 100644
--- a/samples/rust/rust_driver_auxiliary.rs
+++ b/samples/rust/rust_driver_auxiliary.rs
@@ -79,7 +79,7 @@ impl pci::Driver for ParentDriver {
fn probe<'bound>(
pdev: &'bound pci::Device<Core<'_>>,
- _info: &'bound Self::IdInfo,
+ _info: Option<&'bound Self::IdInfo>,
) -> impl PinInit<Self::Data<'bound>, Error> + 'bound {
Ok(ParentData {
// SAFETY: `ParentData` is the driver's private data, which is dropped when the
diff --git a/samples/rust/rust_driver_pci.rs b/samples/rust/rust_driver_pci.rs
index 1aa8197d8698..5547dd704a1b 100644
--- a/samples/rust/rust_driver_pci.rs
+++ b/samples/rust/rust_driver_pci.rs
@@ -144,7 +144,7 @@ impl pci::Driver for SampleDriver {
fn probe<'bound>(
pdev: &'bound pci::Device<Core<'_>>,
- info: &'bound Self::IdInfo,
+ info: Option<&'bound Self::IdInfo>,
) -> impl PinInit<Self::Data<'bound>, Error> + 'bound {
let vendor = pdev.vendor_id();
dev_dbg!(
@@ -153,6 +153,7 @@ fn probe<'bound>(
vendor,
pdev.device_id()
);
+ let info = info.ok_or(ENODEV)?;
pdev.enable_device_mem()?;
pdev.set_master();
--
2.54.0
^ permalink raw reply related
* [PATCH 01/10] rust: driver: remove `IdTable::id`
From: Gary Guo @ 2026-06-18 17:03 UTC (permalink / raw)
To: Greg Kroah-Hartman, Rafael J. Wysocki, Danilo Krummrich,
Miguel Ojeda, Boqun Feng, Björn Roy Baron, Benno Lossin,
Andreas Hindborg, Alice Ryhl, Trevor Gross, Daniel Almeida,
Tamir Duberstein, Alexandre Courbot, Onur Özkan,
FUJITA Tomonori, David Airlie, Simona Vetter, Bjorn Helgaas,
Krzysztof Wilczyński, Abdiel Janulgue, Robin Murphy,
Dave Ertman, Ira Weiny, Leon Romanovsky, Len Brown, Igor Korotin,
Rob Herring, Saravana Kannan, Viresh Kumar, Michal Wilczynski,
Drew Fustini, Guo Ren, Fu Wei, Uwe Kleine-König
Cc: driver-core, rust-for-linux, linux-kernel, netdev, nova-gpu,
dri-devel, linux-pci, linux-acpi, devicetree, linux-pm,
linux-riscv, linux-pwm, Gary Guo
In-Reply-To: <20260618-id_info-v1-0-96af1e559ef9@garyguo.net>
This is unused.
Signed-off-by: Gary Guo <gary@garyguo.net>
---
rust/kernel/device_id.rs | 7 -------
1 file changed, 7 deletions(-)
diff --git a/rust/kernel/device_id.rs b/rust/kernel/device_id.rs
index 8e9721446014..fbf6d8e6afb9 100644
--- a/rust/kernel/device_id.rs
+++ b/rust/kernel/device_id.rs
@@ -166,9 +166,6 @@ pub trait IdTable<T: RawDeviceId, U> {
/// Obtain the pointer to the ID table.
fn as_ptr(&self) -> *const T::RawType;
- /// Obtain the pointer to the bus specific device ID from an index.
- fn id(&self, index: usize) -> &T::RawType;
-
/// Obtain the pointer to the driver-specific information from an index.
fn info(&self, index: usize) -> &U;
}
@@ -180,10 +177,6 @@ fn as_ptr(&self) -> *const T::RawType {
core::ptr::from_ref(self).cast()
}
- fn id(&self, index: usize) -> &T::RawType {
- &self.raw_ids.ids[index]
- }
-
fn info(&self, index: usize) -> &U {
&self.id_infos[index]
}
--
2.54.0
^ permalink raw reply related
* [PATCH 02/10] rust: driver: simplify `IdArray::new_without_index`
From: Gary Guo @ 2026-06-18 17:03 UTC (permalink / raw)
To: Greg Kroah-Hartman, Rafael J. Wysocki, Danilo Krummrich,
Miguel Ojeda, Boqun Feng, Björn Roy Baron, Benno Lossin,
Andreas Hindborg, Alice Ryhl, Trevor Gross, Daniel Almeida,
Tamir Duberstein, Alexandre Courbot, Onur Özkan,
FUJITA Tomonori, David Airlie, Simona Vetter, Bjorn Helgaas,
Krzysztof Wilczyński, Abdiel Janulgue, Robin Murphy,
Dave Ertman, Ira Weiny, Leon Romanovsky, Len Brown, Igor Korotin,
Rob Herring, Saravana Kannan, Viresh Kumar, Michal Wilczynski,
Drew Fustini, Guo Ren, Fu Wei, Uwe Kleine-König
Cc: driver-core, rust-for-linux, linux-kernel, netdev, nova-gpu,
dri-devel, linux-pci, linux-acpi, devicetree, linux-pm,
linux-riscv, linux-pwm, Gary Guo
In-Reply-To: <20260618-id_info-v1-0-96af1e559ef9@garyguo.net>
This method can very easily construct the `IdArray` on its own without
delegating to `Self::build`. Doing so also simplifies the phy device table
macro because it does not need to construct tuples anymore.
This also allows simplification of `new` and `build` which removes the
`unsafe`.
Signed-off-by: Gary Guo <gary@garyguo.net>
---
rust/kernel/device_id.rs | 64 ++++++++++++++++++++----------------------------
rust/kernel/net/phy.rs | 2 +-
2 files changed, 28 insertions(+), 38 deletions(-)
diff --git a/rust/kernel/device_id.rs b/rust/kernel/device_id.rs
index fbf6d8e6afb9..eeef3f5e7b63 100644
--- a/rust/kernel/device_id.rs
+++ b/rust/kernel/device_id.rs
@@ -73,19 +73,11 @@ pub struct IdArray<T: RawDeviceId, U, const N: usize> {
id_infos: [U; N],
}
-impl<T: RawDeviceId, U, const N: usize> IdArray<T, U, N> {
+impl<T: RawDeviceId + RawDeviceIdIndex, U, const N: usize> IdArray<T, U, N> {
/// Creates a new instance of the array.
///
/// The contents are derived from the given identifiers and context information.
- ///
- /// # Safety
- ///
- /// `data_offset` as `None` is always safe.
- /// If `data_offset` is `Some(data_offset)`, then:
- /// - `data_offset` must be the correct offset (in bytes) to the context/data field
- /// (e.g., the `driver_data` field) within the raw device ID structure.
- /// - The field at `data_offset` must be correctly sized to hold a `usize`.
- const unsafe fn build(ids: [(T, U); N], data_offset: Option<usize>) -> Self {
+ pub const fn new(ids: [(T, U); N]) -> Self {
let mut raw_ids = [const { MaybeUninit::<T::RawType>::uninit() }; N];
let mut infos = [const { MaybeUninit::uninit() }; N];
@@ -94,16 +86,14 @@ impl<T: RawDeviceId, U, const N: usize> IdArray<T, U, N> {
// SAFETY: by the safety requirement of `RawDeviceId`, we're guaranteed that `T` is
// layout-wise compatible with `RawType`.
raw_ids[i] = unsafe { core::mem::transmute_copy(&ids[i].0) };
- if let Some(data_offset) = data_offset {
- // SAFETY: by the safety requirement of this function, this would be effectively
- // `raw_ids[i].driver_data = i;`.
- unsafe {
- raw_ids[i]
- .as_mut_ptr()
- .byte_add(data_offset)
- .cast::<usize>()
- .write(i);
- }
+ // SAFETY: by the safety requirement of `RawDeviceIdIndex`, this would be effectively
+ // `raw_ids[i].driver_data = i;`.
+ unsafe {
+ raw_ids[i]
+ .as_mut_ptr()
+ .byte_add(T::DRIVER_DATA_OFFSET)
+ .cast::<usize>()
+ .write(i);
}
// SAFETY: this is effectively a move: `infos[i] = ids[i].1`. We make a copy here but
@@ -127,32 +117,32 @@ impl<T: RawDeviceId, U, const N: usize> IdArray<T, U, N> {
id_infos: unsafe { core::mem::transmute_copy(&infos) },
}
}
+}
- /// Creates a new instance of the array without writing index values.
- ///
- /// The contents are derived from the given identifiers and context information.
- /// If the device implements [`RawDeviceIdIndex`], consider using [`IdArray::new`] instead.
- pub const fn new_without_index(ids: [(T, U); N]) -> Self {
- // SAFETY: Calling `Self::build` with `offset = None` is always safe,
- // because no raw memory writes are performed in this case.
- unsafe { Self::build(ids, None) }
- }
-
+impl<T: RawDeviceId, U, const N: usize> IdArray<T, U, N> {
/// Reference to the contained [`RawIdArray`].
pub const fn raw_ids(&self) -> &RawIdArray<T, N> {
&self.raw_ids
}
}
-impl<T: RawDeviceId + RawDeviceIdIndex, U, const N: usize> IdArray<T, U, N> {
- /// Creates a new instance of the array.
+impl<T: RawDeviceId, const N: usize> IdArray<T, (), N> {
+ /// Creates a new instance of the array without writing index values.
///
/// The contents are derived from the given identifiers and context information.
- pub const fn new(ids: [(T, U); N]) -> Self {
- // SAFETY: by the safety requirement of `RawDeviceIdIndex`,
- // `T::DRIVER_DATA_OFFSET` is guaranteed to be the correct offset (in bytes) to
- // a field within `T::RawType`.
- unsafe { Self::build(ids, Some(T::DRIVER_DATA_OFFSET)) }
+ /// If the device implements [`RawDeviceIdIndex`], consider using [`IdArray::new`] instead.
+ pub const fn new_without_index(ids: [T; N]) -> Self {
+ // SAFETY: `T` is layout-wise compatible with `T::RawType`, so is the array of them.
+ let raw_ids: [T::RawType; N] = unsafe { core::mem::transmute_copy(&ids) };
+ core::mem::forget(ids);
+
+ Self {
+ raw_ids: RawIdArray {
+ ids: raw_ids,
+ sentinel: MaybeUninit::zeroed(),
+ },
+ id_infos: [(); N],
+ }
}
}
diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs
index 3ca99db5cccf..2868e3a9e02c 100644
--- a/rust/kernel/net/phy.rs
+++ b/rust/kernel/net/phy.rs
@@ -868,7 +868,7 @@ macro_rules! module_phy_driver {
const N: usize = $crate::module_phy_driver!(@count_devices $($dev),+);
const TABLE: $crate::device_id::IdArray<$crate::net::phy::DeviceId, (), N> =
- $crate::device_id::IdArray::new_without_index([ $(($dev,())),+, ]);
+ $crate::device_id::IdArray::new_without_index([ $($dev),+, ]);
$crate::module_device_table!("mdio", phydev, TABLE);
};
--
2.54.0
^ permalink raw reply related
* [PATCH 00/10] rust: driver: use pointers instead of indices for ID info
From: Gary Guo @ 2026-06-18 17:03 UTC (permalink / raw)
To: Greg Kroah-Hartman, Rafael J. Wysocki, Danilo Krummrich,
Miguel Ojeda, Boqun Feng, Björn Roy Baron, Benno Lossin,
Andreas Hindborg, Alice Ryhl, Trevor Gross, Daniel Almeida,
Tamir Duberstein, Alexandre Courbot, Onur Özkan,
FUJITA Tomonori, David Airlie, Simona Vetter, Bjorn Helgaas,
Krzysztof Wilczyński, Abdiel Janulgue, Robin Murphy,
Dave Ertman, Ira Weiny, Leon Romanovsky, Len Brown, Igor Korotin,
Rob Herring, Saravana Kannan, Viresh Kumar, Michal Wilczynski,
Drew Fustini, Guo Ren, Fu Wei, Uwe Kleine-König
Cc: driver-core, rust-for-linux, linux-kernel, netdev, nova-gpu,
dri-devel, linux-pci, linux-acpi, devicetree, linux-pm,
linux-riscv, linux-pwm, Gary Guo
Most C drivers use a pointer (and cast to kernel_ulong_t) for driver_data
fields in device_id. Rust code currently does not do this, but rather use
indices. These indices then needs to be translated to `&IdInfo` separately
and this is by a side table.
This leads to open-coded ACPI/OF handling in driver.rs, which is not
desirable. Convert the code to use pointers (or rather, static references)
instead.
Signed-off-by: Gary Guo <gary@garyguo.net>
---
Gary Guo (10):
rust: driver: remove `IdTable::id`
rust: driver: simplify `IdArray::new_without_index`
rust: pci: use `Option<&IdInfo>` for device ID info
rust: net/phy: remove expansion from doc
rust: driver: centralize device ID handling
rust: driver: remove `$module_table_name` from `module_device_table`
rust: driver: store pointers in `DeviceId`
rust: driver: remove open-coded matching logic
rust: driver: remove duplicate ID table
RFC: rust: driver: support map-like syntax for ID table
drivers/cpufreq/rcpufreq_dt.rs | 1 -
drivers/gpu/drm/nova/driver.rs | 1 -
drivers/gpu/drm/tyr/driver.rs | 1 -
drivers/gpu/nova-core/driver.rs | 3 +-
drivers/pwm/pwm_th1520.rs | 1 -
rust/kernel/acpi.rs | 14 +--
rust/kernel/auxiliary.rs | 18 +--
rust/kernel/device_id.rs | 205 +++++++++++++++++++---------------
rust/kernel/driver.rs | 114 ++-----------------
rust/kernel/i2c.rs | 26 ++---
rust/kernel/net/phy.rs | 66 +----------
rust/kernel/of.rs | 14 +--
rust/kernel/pci.rs | 24 ++--
rust/kernel/platform.rs | 5 +-
rust/kernel/usb.rs | 18 +--
samples/rust/rust_debugfs.rs | 1 -
samples/rust/rust_dma.rs | 3 +-
samples/rust/rust_driver_auxiliary.rs | 4 +-
samples/rust/rust_driver_i2c.rs | 3 -
samples/rust/rust_driver_pci.rs | 11 +-
samples/rust/rust_driver_platform.rs | 2 -
samples/rust/rust_driver_usb.rs | 1 -
samples/rust/rust_i2c_client.rs | 2 -
samples/rust/rust_soc.rs | 2 -
24 files changed, 166 insertions(+), 374 deletions(-)
---
base-commit: 4fa3f5fabb30bf00d7475d5a33459ea83d639bf9
change-id: 20260612-id_info-23eca472ccd8
Best regards,
--
Gary Guo <gary@garyguo.net>
^ permalink raw reply
* Re: [PATCH v7 2/2] drm: panel: add support for the Renesas R63419 based dual-DSI video mode Display Panels
From: Doug Anderson @ 2026-06-18 17:00 UTC (permalink / raw)
To: Neil Armstrong
Cc: Jessica Zhang, Maarten Lankhorst, Maxime Ripard,
Thomas Zimmermann, David Airlie, Simona Vetter, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Geert Uytterhoeven,
Magnus Damm, dri-devel, devicetree, linux-kernel,
linux-renesas-soc, Dmitry Baryshkov, KancyJoe
In-Reply-To: <20260605-topic-sm8650-ayaneo-pocket-s2-r63419-v7-2-b84b6da84293@linaro.org>
Hi,
On Fri, Jun 5, 2026 at 7:51 AM Neil Armstrong <neil.armstrong@linaro.org> wrote:
>
> From: KancyJoe <kancy2333@outlook.com>
>
> Implement support for the Renesas 63419 based dual-DSI video mode
> Display Panels found in the Ayaneo gaming handled devices.
>
> Signed-off-by: KancyJoe <kancy2333@outlook.com>
I notice "Kancy Joe" has a space in the source files, but not in the
signoff. I guess Signed-off-by isn't necessarily required to be real
names these days, but still seems odd...
> +/*
> + * Helper to switch between DSI links, so we share a single dsi_ctx
> + * for both links, so in case of an error all writes & sleep for
> + * both links are ignored.
> + */
> +static inline void dsi_link_switch(struct renesas_r63419_panel *ctx,
> + struct mipi_dsi_multi_context *dsi_ctx,
> + unsigned int link)
> +{
> + dsi_ctx->dsi = ctx->dsi[link];
> +}
> +
> +static int renesas_r63419_on(struct renesas_r63419_panel *ctx)
> +{
> + struct mipi_dsi_multi_context dsi_ctx = { 0 };
> +
> + /* Panel registers are loaded from DDIC Non Volatile Memory */
> +
> + dsi_link_switch(ctx, &dsi_ctx, 0);
> + mipi_dsi_dcs_exit_sleep_mode_multi(&dsi_ctx);
> + dsi_link_switch(ctx, &dsi_ctx, 1);
> + mipi_dsi_dcs_exit_sleep_mode_multi(&dsi_ctx);
Instead of dsi_link_switch(), can't you use the mipi_dsi_dual()
function? I think it would be:
mipi_dsi_dual(mipi_dsi_dcs_exit_sleep_mode_multi, dsi_ctx,
ctx->dsi[0], ctx->dsi[1]);
> +static int renesas_r63419_disable(struct drm_panel *panel)
> +{
> + struct renesas_r63419_panel *ctx = to_renesas_r63419_panel(panel);
> + struct mipi_dsi_multi_context dsi_ctx = { 0 };
> +
> + dsi_link_switch(ctx, &dsi_ctx, 0);
> + mipi_dsi_dcs_set_display_off_multi(&dsi_ctx);
> + dsi_link_switch(ctx, &dsi_ctx, 1);
> + mipi_dsi_dcs_set_display_off_multi(&dsi_ctx);
> + mipi_dsi_msleep(&dsi_ctx, 50);
> +
> + dsi_link_switch(ctx, &dsi_ctx, 0);
> + mipi_dsi_dcs_enter_sleep_mode_multi(&dsi_ctx);
> + dsi_link_switch(ctx, &dsi_ctx, 1);
> + mipi_dsi_dcs_enter_sleep_mode_multi(&dsi_ctx);
> + mipi_dsi_msleep(&dsi_ctx, 120);
> +
> + return dsi_ctx.accum_err;
I'm not sure we've been terribly consistent, but should the above be
"return 0"? I'm not actually sure there's any benefit to a panel's
disable() function returning an error to begin with.
drm_panel_disable() doesn't return an error, so all this does is skip
setting "panel->enabled" to false and make it harder for the system to
recover.
> +static int renesas_r63419_prepare(struct drm_panel *panel)
> +{
> + struct renesas_r63419_panel *ctx = to_renesas_r63419_panel(panel);
> + int ret;
> +
> + ret = regulator_bulk_enable(ARRAY_SIZE(renesas_r63419_vdd_supplies),
> + ctx->vdd_supplies);
> + if (ret < 0)
> + return ret;
> +
> + usleep_range(1000, 2000);
> +
> + ret = regulator_bulk_enable(ARRAY_SIZE(renesas_r63419_vcc_supplies),
> + ctx->vcc_supplies);
> + if (ret < 0) {
> + regulator_bulk_disable(ARRAY_SIZE(renesas_r63419_vdd_supplies),
> + ctx->vdd_supplies);
> + return ret;
> + }
> +
> + usleep_range(1000, 2000);
> +
> + gpiod_set_value_cansleep(ctx->reset_gpio, 0);
> +
> + usleep_range(3000, 4000);
> +
> + ret = renesas_r63419_on(ctx);
> + if (ret < 0) {
> + dev_err(panel->dev, "Failed to initialize panel: %d\n", ret);
> +
> + /* Power off sequence from the r63419 datasheet */
> + regulator_bulk_disable(ARRAY_SIZE(renesas_r63419_vcc_supplies),
> + ctx->vcc_supplies);
> + regulator_bulk_disable(ARRAY_SIZE(renesas_r63419_vdd_supplies),
> + ctx->vdd_supplies);
> +
> + gpiod_set_value_cansleep(ctx->reset_gpio, 1);
To make de-init opposite to init, shouldn't the reset come before you
turn the regulators off? Depending on the design of the panel, I'd
imagine this could prevent back-powering some logic?
I'd also expect vdd supplies to be turned off first?
> +static int renesas_r63419_unprepare(struct drm_panel *panel)
> +{
> + struct renesas_r63419_panel *ctx = to_renesas_r63419_panel(panel);
> +
> + /* Power off sequence from the r63419 datasheet */
> + regulator_bulk_disable(ARRAY_SIZE(renesas_r63419_vcc_supplies), ctx->vcc_supplies);
> + regulator_bulk_disable(ARRAY_SIZE(renesas_r63419_vdd_supplies), ctx->vdd_supplies);
> +
> + gpiod_set_value_cansleep(ctx->reset_gpio, 1);
Similar: shouldn't the reset come before the regulators to make
power-off the opposite of init.
> +static int renesas_r63419_get_modes(struct drm_panel *panel,
> + struct drm_connector *connector)
> +{
> + struct renesas_r63419_panel *ctx = to_renesas_r63419_panel(panel);
> + const struct drm_display_mode *mode = ctx->desc->mode;
> +
> + drm_connector_set_panel_orientation(connector, ctx->orientation);
IIRC, the above was a workaround that caused a warning splat. Is your
panel used on a system that actually needs it? Could your DRM driver
be fixed rather than persisting this hack? For context, see commit
47bef230225b ("drm/panel: panel-edp: Implement .get_orientation
callback")
> +static int renesas_r63419_probe(struct mipi_dsi_device *dsi)
> +{
> + struct mipi_dsi_device_info info = { };
> + struct device *dev = &dsi->dev;
> + struct renesas_r63419_panel *ctx;
> + struct device_node *dsi1_node;
> + struct mipi_dsi_host *dsi1_host;
> + int ret, i;
> +
> + ctx = devm_drm_panel_alloc(dev, struct renesas_r63419_panel, panel,
> + &renesas_r63419_panel_funcs, DRM_MODE_CONNECTOR_DSI);
> + if (IS_ERR(ctx))
> + return PTR_ERR(ctx);
> +
> + ctx->desc = of_device_get_match_data(dev);
> + if (!ctx->desc)
> + return dev_err_probe(dev, -ENODEV,
> + "Failed to get panel description\n");
> +
> + ret = devm_regulator_bulk_get_const(&dsi->dev,
> + ARRAY_SIZE(renesas_r63419_vdd_supplies),
> + renesas_r63419_vdd_supplies, &ctx->vdd_supplies);
> + if (ret < 0)
> + return ret;
> +
> + ret = devm_regulator_bulk_get_const(&dsi->dev,
> + ARRAY_SIZE(renesas_r63419_vcc_supplies),
> + renesas_r63419_vcc_supplies, &ctx->vcc_supplies);
> + if (ret < 0)
> + return ret;
It seems like both sets of supplies are always enabled / disabled
together with no delay between them. Do you truly need two lists, or
can this be combined to one list of regulators. That would simplify a
bunch of logic.
> + ctx->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
> + if (IS_ERR(ctx->reset_gpio))
> + return dev_err_probe(dev, PTR_ERR(ctx->reset_gpio),
> + "Failed to get reset gpio\n");
> +
> + /* Get second DSI host */
> + dsi1_node = of_graph_get_remote_node(dsi->dev.of_node, 1, -1);
> + if (!dsi1_node)
> + return dev_err_probe(dev, -ENODEV,
> + "Failed to get remote node for second DSI\n");
> +
> + dsi1_host = of_find_mipi_dsi_host_by_node(dsi1_node);
> + of_node_put(dsi1_node);
> + if (!dsi1_host)
> + return dev_err_probe(dev, -EPROBE_DEFER,
> + "Failed to find second DSI host\n");
> +
> + /* Copy current DSI info, do not provide OF node since no driver needs to be attached */
> + strscpy(info.type, dsi->name, sizeof(info.type));
Can't you use the two-argument form of strscpy()?
FWIW, I also notice that the Sashiko AI bot had some comments. Did you
already look all of those over and decide they don't need fixing? I
have a vague recollection that there's no need to worry about someone
calling disable() and then enable() without going through the
unprepare() / prepare(). If my memory is correct, I guess that would
be nice to document... I didn't analyze some of the other claims that
the AI bot had.
-Doug
^ permalink raw reply
* Re: [PATCH 01/11] dt-bindings: power: Convert Ux500 PM domains to schema
From: Rob Herring (Arm) @ 2026-06-18 16:51 UTC (permalink / raw)
To: Linus Walleij
Cc: Lee Jones, dri-devel, linux-pm, Maarten Lankhorst, David Airlie,
linux-arm-kernel, Ulf Hansson, Frank Li, devicetree,
Maxime Ripard, dmaengine, Thomas Zimmermann, Mark Brown,
Simona Vetter, Vinod Koul, Conor Dooley, Krzysztof Kozlowski
In-Reply-To: <20260618-ux500-power-domains-v7-1-v1-1-eb5e50b1a588@kernel.org>
On Thu, 18 Jun 2026 07:00:47 +0200, Linus Walleij wrote:
> Convert the legacy Ux500 power domain text binding to YAML.
>
> Move it under bindings/power.
>
> Reference the generic power-domain schema.
>
> Update MAINTAINERS for the new path.
>
> Assisted-by: Codex:gpt-5-5
> Signed-off-by: Linus Walleij <linusw@kernel.org>
> ---
> .../devicetree/bindings/arm/ux500/power_domain.txt | 35 ----------------
> .../power/stericsson,ux500-pm-domains.yaml | 46 ++++++++++++++++++++++
> MAINTAINERS | 1 +
> 3 files changed, 47 insertions(+), 35 deletions(-)
>
My bot found errors running 'make dt_binding_check' on your patch:
yamllint warnings/errors:
dtschema/dtc warnings/errors:
Documentation/devicetree/bindings/power/stericsson,ux500-pm-domains.example.dts:25.28-28.11: Warning (unit_address_vs_reg): /example-0/sdi0_per1@80126000: node has a unit name, but no reg or ranges property
/builds/robherring/dt-review-ci/linux/Documentation/devicetree/bindings/power/stericsson,ux500-pm-domains.example.dtb: sdi0_per1@80126000 (arm,pl18x): $nodename:0: 'sdi0_per1@80126000' does not match '^mmc(@.*)?$'
from schema $id: http://devicetree.org/schemas/mmc/arm,pl18x.yaml
/builds/robherring/dt-review-ci/linux/Documentation/devicetree/bindings/power/stericsson,ux500-pm-domains.example.dtb: sdi0_per1@80126000 (arm,pl18x): 'oneOf' conditional failed, one must be fixed:
'interrupts' is a required property
'interrupts-extended' is a required property
from schema $id: http://devicetree.org/schemas/mmc/arm,pl18x.yaml
/builds/robherring/dt-review-ci/linux/Documentation/devicetree/bindings/power/stericsson,ux500-pm-domains.example.dtb: sdi0_per1@80126000 (arm,pl18x): 'reg' is a required property
from schema $id: http://devicetree.org/schemas/mmc/arm,pl18x.yaml
doc reference errors (make refcheckdocs):
See https://patchwork.kernel.org/project/devicetree/patch/20260618-ux500-power-domains-v7-1-v1-1-eb5e50b1a588@kernel.org
The base for the series is generally the latest rc1. A different dependency
should be noted in *this* patch.
If you already ran 'make dt_binding_check' and didn't see the above
error(s), then make sure 'yamllint' is installed and dt-schema is up to
date:
pip3 install dtschema --upgrade
Please check and re-submit after running the above command yourself. Note
that DT_SCHEMA_FILES can be set to your schema file to speed up checking
your schema. However, it must be unset to test all examples with your schema.
^ permalink raw reply
* Re: [PATCH v6 00/10] ACPI: APEI: share GHES CPER helpers and add DT FFH provider
From: Borislav Petkov @ 2026-06-18 16:48 UTC (permalink / raw)
To: Ahmed Tiba
Cc: Rafael J. Wysocki, Tony Luck, Hanjun Guo, Mauro Carvalho Chehab,
Shuai Xue, Len Brown, Saket Dumbre, Davidlohr Bueso,
Jonathan Cameron, Dave Jiang, Alison Schofield, Vishal Verma,
Ira Weiny, Dan Williams, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Jonathan Corbet, Shuah Khan, linux-kernel,
linux-acpi, acpica-devel, linux-cxl, devicetree, linux-edac,
linux-doc, Dmitry.Lamerov
In-Reply-To: <20260617-topics-ahmtib01-ras_ffh_arm_internal_review-v6-0-91f725174aa0@arm.com>
On Wed, Jun 17, 2026 at 02:54:38PM +0100, Ahmed Tiba wrote:
> This is v6 of the GHES refactor series. Compared to v5, it addresses
> the latest review comments and tightens the DT CPER provider and
> related helper wiring.
Sashiko has comments:
https://sashiko.dev/#/patchset/20260617-topics-ahmtib01-ras_ffh_arm_internal_review-v6-0-91f725174aa0%40arm.com
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
^ permalink raw reply
* Re: [PATCH v4 1/3] dt-bindings: riscv: describe Svadu as disabled at boot
From: Conor Dooley @ 2026-06-18 16:37 UTC (permalink / raw)
To: Yunhui Cui
Cc: akpm, alex, andrew+kernel, aou, apatel, apopple, atishp,
baolin.wang, cleger, conor+dt, debug, devicetree, guodong,
hui.wang, krzk+dt, linux-kernel, linux-riscv, liu.xuemei1, namcao,
nick.hu, palmer, pincheng.plct, pjw, qingwei.hu, ritesh.list,
rmclure, robh, wangruikang, zhangchunyan, zong.li
In-Reply-To: <20260618064406.14508-2-cuiyunhui@bytedance.com>
[-- Attachment #1: Type: text/plain, Size: 75 bytes --]
Acked-by: Conor Dooley <conor.dooley@microchip.com>
pw-bot: not-applicable
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
^ permalink raw reply
* Re: [PATCH v4 01/16] spi: dt-bindings: add spi-max-post-config-frequency property
From: Conor Dooley @ 2026-06-18 16:36 UTC (permalink / raw)
To: Santhosh Kumar K
Cc: broonie, robh, krzk+dt, conor+dt, miquel.raynal, richard,
vigneshr, pratyush, mwalle, takahiro.kuwano, linux-spi,
devicetree, linux-kernel, linux-mtd, praneeth, u-kumar1, a-dutta
In-Reply-To: <20260618073725.84733-2-s-k6@ti.com>
[-- Attachment #1: Type: text/plain, Size: 680 bytes --]
On Thu, Jun 18, 2026 at 01:07:10PM +0530, Santhosh Kumar K wrote:
> Add spi-max-post-config-frequency, a generic uint32 property for SPI
> peripherals that support two distinct clock rates: a conservative rate
> always reachable without controller configuration, and a higher rate
> reachable only after controller-side configuration such as PHY tuning.
>
> When both properties are present, spi-max-frequency gives the
> conservative pre-configuration rate and spi-max-post-config-frequency
> gives the higher post-configuration target.
>
> Signed-off-by: Santhosh Kumar K <s-k6@ti.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
pw-bot: not-applicable
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
^ permalink raw reply
* Re: [PATCH v2 2/2] iio: magnetometer: add support for Melexis MLX90393
From: sashiko-bot @ 2026-06-18 16:15 UTC (permalink / raw)
To: Nikhil Gautam; +Cc: conor+dt, robh, devicetree
In-Reply-To: <20260618160141.11409-3-nikhilgtr@gmail.com>
Thank you for your contribution! Sashiko AI review found 7 potential issue(s) to consider:
- [High] Data race on statically allocated `scale_avail` array.
- [High] DMA safety violation due to stack-allocated transfer buffers.
- [High] Writing to the temperature scale attribute corrupts the magnetometer gain configuration.
- [Medium] IIO scale values violate ABI standard (Tesla and Celsius instead of Gauss and milli-Celsius).
- [Medium] Missing `id_table` assignment in the I2C driver structure.
- [Medium] Temperature channel exposes raw register exponent values instead of true oversampling ratios.
- [Medium] Lockless state reads in `mlx90393_read_raw` lead to data races.
--
commit bdec68e57f45f6e35e5c0c76d37b8ee5efa9691b
Author: Nikhil Gautam <nikhilgtr@gmail.com>
iio: magnetometer: add support for Melexis MLX90393
Add Industrial I/O subsystem support for the Melexis
MLX90393 3-axis magnetometer and temperature sensor.
> diff --git a/drivers/iio/magnetometer/mlx90393_core.c b/drivers/iio/magnetometer/mlx90393_core.c
> new file mode 100644
> index 0000000000000..0ad4a30c0be96
> --- /dev/null
> +++ b/drivers/iio/magnetometer/mlx90393_core.c
[ ... ]
> +static int mlx90393_write_reg(struct mlx90393_data *data, u8 reg, u16 val)
> +{
> + u8 tx[4];
> + u8 status;
> + int ret;
> +
> + tx[0] = MLX90393_CMD_WR;
> + put_unaligned_be16(val, &tx[1]);
> + /* Register address is encoded in bits [7:2] */
> + tx[3] = reg << 2;
> +
> + ret = mlx90393_xfer(data, tx, sizeof(tx), &status, 1);
[Severity: High]
Is it safe to allocate the transfer buffers on the stack here and in
mlx90393_read_measurement()?
If the I2C host adapter uses DMA and CONFIG_VMAP_STACK is enabled, mapping
stack memory for DMA operations will fail. Should these buffers be
dynamically allocated to ensure DMA safety?
[ ... ]
> +static int mlx90393_get_scale(struct mlx90393_data *data,
> + const struct iio_chan_spec *chan,
> + int *val, int *val2)
> +{
> + enum mlx90393_axis_type axis;
> + u8 res;
> +
> + if (chan->channel2 == IIO_MOD_Z) {
> + axis = MLX90393_AXIS_TYPE_Z;
> + res = data->res_z;
> + } else {
> + axis = MLX90393_AXIS_TYPE_XY;
> + res = data->res_xy;
> + }
> +
> + /*
> + * Convert:
> + * µT × 1000 → nT
> + */
> + *val = 0;
> + *val2 = mlx90393_scale_table[axis][data->gain_sel][res];
> +
> + return IIO_VAL_INT_PLUS_NANO;
> +}
[Severity: Medium]
Does this return the scale in Gauss as required by the IIO ABI for
in_magn_scale? Using IIO_VAL_INT_PLUS_NANO with the current scale table yields
Tesla, which is off by a factor of 10,000 compared to Gauss.
[ ... ]
> +static int mlx90393_write_raw(struct iio_dev *indio_dev,
> + const struct iio_chan_spec *chan,
> + int val, int val2,
> + long mask)
> +{
> + struct mlx90393_data *data = iio_priv(indio_dev);
> + int ret;
> +
> + switch (mask) {
> + case IIO_CHAN_INFO_SCALE: {
> + guard(mutex)(&data->lock);
> + ret = mlx90393_set_scale(data, chan, val, val2);
> + return ret;
> + }
[Severity: High]
Can writing to the temperature scale attribute corrupt the magnetometer gain
configuration?
The IIO_TEMP channel exposes a writable scale attribute, but this case does
not check chan->type before calling mlx90393_set_scale(). Because the
temperature channel's channel2 field is 0, it evaluates as an XY magnetometer
channel and will reconfigure the global gain_sel register.
[ ... ]
> +static int mlx90393_read_raw(struct iio_dev *indio_dev,
> + const struct iio_chan_spec *chan,
> + int *val, int *val2, long mask)
> +{
> + struct mlx90393_data *data = iio_priv(indio_dev);
> + int ret;
> +
> + switch (mask) {
> + case IIO_CHAN_INFO_RAW: {
> + guard(mutex)(&data->lock);
> + ret = mlx90393_read_measurement(data, chan->address, val);
> + if (ret)
> + return ret;
> +
> + return IIO_VAL_INT;
> + }
> + case IIO_CHAN_INFO_SCALE:
> + switch (chan->type) {
> + case IIO_MAGN:
> + return mlx90393_get_scale(data, chan, val, val2);
[Severity: Medium]
Is a lock needed here?
Configuration variables like gain_sel, osr, and osr2 are updated while
holding data->lock in mlx90393_write_raw(), but mlx90393_read_raw() reads
these properties without acquiring the lock.
Can concurrent updates result in stale or inconsistently-read configurations?
> +
> + case IIO_TEMP:
> + /* Datasheet: 22124 millidegC/LSB */
> + *val = 0;
> + *val2 = 22124;
> + return IIO_VAL_INT_PLUS_MICRO;
[Severity: Medium]
Does this return the temperature scale in milli-Celsius as required by the IIO
ABI? Returning 22124 with IIO_VAL_INT_PLUS_MICRO yields Celsius, which is off
by a factor of 1,000.
[ ... ]
> +static int mlx90393_read_avail(struct iio_dev *indio_dev,
> + const struct iio_chan_spec *chan,
> + const int **vals,
> + int *type,
> + int *length,
> + long mask)
> +{
> + struct mlx90393_data *data = iio_priv(indio_dev);
> + static int scale_avail[MLX90393_GAIN_MAX][MLX90393_AXIS_MAX];
[Severity: High]
Is it safe to use a statically allocated local array for scale_avail?
The lock is released before the IIO core iterates over the returned pointer.
Can concurrent sysfs reads across different channels or multiple device
instances clobber the shared array and return corrupted lists to userspace?
> + enum mlx90393_axis_type axis;
> + u8 res;
> +
> + switch (mask) {
> + case IIO_CHAN_INFO_SCALE: {
> + guard(mutex)(&data->lock);
> + axis = chan->channel2 == IIO_MOD_Z;
> + res = axis ? data->res_z : data->res_xy;
> +
> + for (unsigned int i = 0; i < MLX90393_GAIN_MAX; i++) {
> + scale_avail[i][0] = 0;
> + scale_avail[i][1] = mlx90393_scale_table[axis][i][res];
> + }
> +
> + *vals = &scale_avail[0][0];
> + *type = IIO_VAL_INT_PLUS_NANO;
> + *length = MLX90393_GAIN_MAX * MLX90393_AXIS_MAX;
> + return IIO_AVAIL_LIST;
> + }
> + case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
> + if (chan->type == IIO_TEMP) {
> + *vals = mlx90393_osr2_avail;
> + *type = IIO_VAL_INT;
> + *length = MLX90393_OSR2_MAX;
[Severity: Medium]
Does this expose raw register exponent values instead of true oversampling
ratios for the temperature channel?
Returning the register exponents (0, 1, 2, 3) directly violates the IIO ABI
which dictates reflecting the actual number of hardware samples applied.
[ ... ]
> diff --git a/drivers/iio/magnetometer/mlx90393_i2c.c b/drivers/iio/magnetometer/mlx90393_i2c.c
> new file mode 100644
> index 0000000000000..52233b6295c2b
> --- /dev/null
> +++ b/drivers/iio/magnetometer/mlx90393_i2c.c
[ ... ]
> +static struct i2c_driver mlx90393_i2c_driver = {
> + .driver = {
> + .name = "mlx90393",
> + .of_match_table = mlx90393_of_match,
> + },
> + .probe = mlx90393_i2c_probe,
> +};
[Severity: Medium]
Is the id_table assignment missing here?
The driver defines the mlx90393_id table and exports it, but it is not
assigned to the id_table field of this structure. Could this prevent the
driver from binding on systems relying on legacy board-file setups or sysfs
new_device instantiation?
[ ... ]
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260618160141.11409-1-nikhilgtr@gmail.com?part=2
^ permalink raw reply
* Re: [PATCH v6 06/16] iio: core: create local __iio_chan_prefix_emit() for reuse
From: Rodrigo Alencar @ 2026-06-18 16:14 UTC (permalink / raw)
To: Nuno Sá, rodrigo.alencar
Cc: linux-iio, devicetree, linux-kernel, linux-doc, linux-hardening,
Lars-Peter Clausen, Michael Hennerich, Jonathan Cameron,
David Lechner, Andy Shevchenko, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Philipp Zabel, Jonathan Corbet, Shuah Khan,
Kees Cook, Gustavo A. R. Silva
In-Reply-To: <ajQGTQ1_qcOwfzne@nsa>
On 18/06/26 16:06, Nuno Sá wrote:
> On Thu, Jun 18, 2026 at 02:27:22PM +0100, Rodrigo Alencar via B4 Relay wrote:
> > From: Rodrigo Alencar <rodrigo.alencar@analog.com>
> >
> > Move logic to create a channel prefix for naming attribute files into a
> > separate __iio_chan_prefix_emit() function for reuse.
...
> > +static int __iio_chan_prefix_emit(const struct iio_chan_spec *chan,
> > + enum iio_shared_by shared_by,
> > + char *buf, size_t len)
> > +{
> > + const char *dir = iio_direction[chan->output];
> > + const char *type = iio_chan_type_name_spec[chan->type];
> > + int n = 0;
> > +
> > + switch (shared_by) {
> > + case IIO_SHARED_BY_ALL:
> > + buf[0] = '\0'; /* empty channel prefix */
> > + break;
> > + case IIO_SHARED_BY_DIR:
> > + n = scnprintf(buf, len, "%s", dir);
> > + break;
> > + case IIO_SHARED_BY_TYPE:
> > + n = scnprintf(buf, len, "%s_%s", dir, type);
> > + if (chan->differential)
> > + n += scnprintf(buf + n, len - n, "-%s", type);
> > + break;
> > + case IIO_SEPARATE:
> > + if (chan->indexed) {
> > + n = scnprintf(buf, len, "%s_%s%d", dir, type,
> > + chan->channel);
> > + if (chan->differential)
> > + n += scnprintf(buf + n, len - n, "-%s%d", type,
> > + chan->channel2);
> > + } else {
> > + if (chan->differential) {
> > + WARN(1, "Differential channels must be indexed\n");
> > + return -EINVAL;
> > + }
> > + n = scnprintf(buf, len, "%s_%s", dir, type);
> > + }
> > +
> > + if (chan->modified) {
> > + if (chan->differential) {
> > + WARN(1, "Differential channels can not have modifier\n");
> > + return -EINVAL;
>
> WARN() looks too much to me. dev_error() as we're treating it as such. I
> guess you don't want to pass struct device but not really an issue IMHO.
__iio_device_attr_init() also used WARN(), probably because it didnt have
access to a dev pointer. It would not be a problem to add an extra param.
>
> > + }
> > + n += scnprintf(buf + n, len - n, "_%s",
> > + iio_modifier_names[chan->channel2]);
> > + }
> > +
> > + if (chan->extend_name)
> > + n += scnprintf(buf + n, len - n, "_%s", chan->extend_name);
> > + break;
> > + }
> > +
> > + if (n > 0 && n < len - 1) { /* prefix termination if not empty */
> > + buf[n++] = '_';
> > + buf[n] = '\0';
> > + }
> > +
>
> Can't we handle the above in the caller on kasprintf()? Then we could
> simplify and return in place.
I felt like doing this here would get a cleaner logic in the caller, which
would have to add the '_' conditionally.
>
> > + return n;
> > +}
> > +
> > /**
> > * iio_device_id() - query the unique ID for the device
> > * @indio_dev: Device structure whose ID is being queried
> > @@ -1100,106 +1159,19 @@ int __iio_device_attr_init(struct device_attribute *dev_attr,
> > size_t len),
> > enum iio_shared_by shared_by)
> > {
> > - int ret = 0;
> > - char *name = NULL;
> > - char *full_postfix;
> > + char prefix[NAME_MAX + 1];
> > + int ret;
> >
> > sysfs_attr_init(&dev_attr->attr);
> >
> > - /* Build up postfix of <extend_name>_<modifier>_postfix */
> > - if (chan->modified && (shared_by == IIO_SEPARATE)) {
> > - if (chan->extend_name)
> > - full_postfix = kasprintf(GFP_KERNEL, "%s_%s_%s",
> > - iio_modifier_names[chan->channel2],
> > - chan->extend_name,
> > - postfix);
> > - else
> > - full_postfix = kasprintf(GFP_KERNEL, "%s_%s",
> > - iio_modifier_names[chan->channel2],
> > - postfix);
> > - } else {
> > - if (chan->extend_name == NULL || shared_by != IIO_SEPARATE)
> > - full_postfix = kstrdup(postfix, GFP_KERNEL);
> > - else
> > - full_postfix = kasprintf(GFP_KERNEL,
> > - "%s_%s",
> > - chan->extend_name,
> > - postfix);
> > - }
> > - if (full_postfix == NULL)
> > + ret = __iio_chan_prefix_emit(chan, shared_by, prefix, sizeof(prefix));
> > + if (ret < 0)
> > + return ret;
> > +
> > + dev_attr->attr.name = kasprintf(GFP_KERNEL, "%s%s", prefix, postfix);
> > + if (!dev_attr->attr.name)
> > return -ENOMEM;
>
> I don't oppose the change. Looks like a nice cleanup. But bear in mind
> this very sensible as any subtle mistake means ABI breakage.
Yes! I tried to be careful... this is dangerous stuff!
--
Kind regards,
Rodrigo Alencar
^ permalink raw reply
* Re: [PATCH v2 1/2] dt-bindings: iio: magnetometer: add Melexis MLX90393
From: sashiko-bot @ 2026-06-18 16:10 UTC (permalink / raw)
To: Nikhil Gautam; +Cc: devicetree, robh, conor+dt
In-Reply-To: <20260618160141.11409-2-nikhilgtr@gmail.com>
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] The new entry for 'MELEXIS MLX90393 MAGNETOMETER DRIVER' in the MAINTAINERS file is inserted out of alphabetical order.
--
commit 756049ed43f6fd027532ae2aea78e2889e87ad8e
Author: Nikhil Gautam <nikhilgtr@gmail.com>
dt-bindings: iio: magnetometer: add Melexis MLX90393
This commit adds devicetree bindings for the Melexis MLX90393 3-axis
magnetometer and temperature sensor. The initial binding documents the
I2C interface.
[ ... ]
> diff --git a/MAINTAINERS b/MAINTAINERS
> index a92290fffa163..e9ddcd12feb5e 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -24926,6 +24926,12 @@ S: Maintained
> F: Documentation/devicetree/bindings/iio/magnetometer/ti,tmag5273.yaml
> F: drivers/iio/magnetometer/tmag5273.c
>
> +MELEXIS MLX90393 MAGNETOMETER DRIVER
> +M: Nikhil Gautam <nikhilgtr@gmail.com>
> +L: linux-iio@vger.kernel.org
> +S: Maintained
> +F: Documentation/devicetree/bindings/iio/magnetometer/melexis,mlx90393.yaml
> +
> TI TRF7970A NFC DRIVER
[Severity: Low]
This isn't a bug, but should this new entry be placed earlier in the file?
The MAINTAINERS list is generally sorted alphabetically, and the "MELEXIS"
driver block is currently being inserted in the "T" section, between
"TI TMAG5273" and "TI TRF7970A".
> M: Mark Greer <mgreer@animalcreek.com>
> L: linux-wireless@vger.kernel.org
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260618160141.11409-1-nikhilgtr@gmail.com?part=1
^ permalink raw reply
* [PATCH v2 2/2] iio: magnetometer: add support for Melexis MLX90393
From: Nikhil Gautam @ 2026-06-18 16:01 UTC (permalink / raw)
To: linux-iio
Cc: jic23, dlechner, nuno.sa, andy, robh, krzk+dt, conor+dt,
devicetree, linux-kernel, Nikhil Gautam
In-Reply-To: <20260618160141.11409-1-nikhilgtr@gmail.com>
Add Industrial I/O subsystem support for the Melexis
MLX90393 3-axis magnetometer and temperature sensor.
The driver currently supports:
raw magnetic field measurements
raw temperature measurements
configurable gain/scale selection
configurable oversampling ratio
direct mode operation
The MLX90393 supports both I2C and SPI interfaces. This
initial implementation adds support for the I2C interface.
The driver is structured around a shared sensor core with
a small transport abstraction layer to simplify future SPI
support without duplicating sensor logic.
Signed-off-by: Nikhil Gautam <nikhilgtr@gmail.com>
---
MAINTAINERS | 1 +
drivers/iio/magnetometer/Kconfig | 10 +
drivers/iio/magnetometer/Makefile | 2 +
drivers/iio/magnetometer/mlx90393.h | 74 +++
drivers/iio/magnetometer/mlx90393_core.c | 681 +++++++++++++++++++++++
drivers/iio/magnetometer/mlx90393_i2c.c | 72 +++
6 files changed, 840 insertions(+)
create mode 100644 drivers/iio/magnetometer/mlx90393.h
create mode 100644 drivers/iio/magnetometer/mlx90393_core.c
create mode 100644 drivers/iio/magnetometer/mlx90393_i2c.c
diff --git a/MAINTAINERS b/MAINTAINERS
index e9ddcd12feb5..ef7eb6fec0c2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -24931,6 +24931,7 @@ M: Nikhil Gautam <nikhilgtr@gmail.com>
L: linux-iio@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/iio/magnetometer/melexis,mlx90393.yaml
+F: drivers/iio/magnetometer/mlx90393*
TI TRF7970A NFC DRIVER
M: Mark Greer <mgreer@animalcreek.com>
diff --git a/drivers/iio/magnetometer/Kconfig b/drivers/iio/magnetometer/Kconfig
index 3debf1320ad1..e6b74e7e3317 100644
--- a/drivers/iio/magnetometer/Kconfig
+++ b/drivers/iio/magnetometer/Kconfig
@@ -128,6 +128,16 @@ config HID_SENSOR_MAGNETOMETER_3D
Say yes here to build support for the HID SENSOR
Magnetometer 3D.
+config MLX90393
+ tristate "MELEXIS MLX90393 3-axis magnetometer sensor"
+ depends on I2C
+ help
+ Say yes here to build support for the MELEXIS MLX90393 3-axis
+ magnetometer.
+
+ To compile this driver as a module, choose M here: the module
+ will be called mlx90393.
+
config MMC35240
tristate "MEMSIC MMC35240 3-axis magnetic sensor"
select REGMAP_I2C
diff --git a/drivers/iio/magnetometer/Makefile b/drivers/iio/magnetometer/Makefile
index 9297723a97d8..542c89d38a59 100644
--- a/drivers/iio/magnetometer/Makefile
+++ b/drivers/iio/magnetometer/Makefile
@@ -14,6 +14,8 @@ obj-$(CONFIG_BMC150_MAGN_SPI) += bmc150_magn_spi.o
obj-$(CONFIG_MAG3110) += mag3110.o
obj-$(CONFIG_HID_SENSOR_MAGNETOMETER_3D) += hid-sensor-magn-3d.o
+obj-$(CONFIG_MLX90393) += mlx90393_core.o
+obj-$(CONFIG_MLX90393) += mlx90393_i2c.o
obj-$(CONFIG_MMC35240) += mmc35240.o
obj-$(CONFIG_IIO_ST_MAGN_3AXIS) += st_magn.o
diff --git a/drivers/iio/magnetometer/mlx90393.h b/drivers/iio/magnetometer/mlx90393.h
new file mode 100644
index 000000000000..b3356f9521f8
--- /dev/null
+++ b/drivers/iio/magnetometer/mlx90393.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * MLX90393 magnetometer & temperature sensor driver
+ *
+ * Copyright (c) 2026 Nikhil Gautam <nikhilgtr@gmail.com>
+ */
+
+#ifndef MLX90393_H
+#define MLX90393_H
+
+#include <linux/bitops.h>
+#include <linux/bits.h>
+#include <linux/types.h>
+
+#define MLX90393_AXIS_MAX 2
+#define MLX90393_GAIN_MAX 8
+#define MLX90393_RES_MAX 4
+#define MLX90393_OSR2_MAX 4
+#define MLX90393_OSR_MAX 4
+
+#define MLX90393_CMD_MASK GENMASK(7, 4)
+
+/* Commands (datasheet, Table 11 - Command List) */
+#define MLX90393_CMD_SB 0x10 /* Start Burst Mode */
+#define MLX90393_CMD_SW 0x20 /* Start Wake-up on Change Mode */
+#define MLX90393_CMD_SM 0x30 /* Start Single Measurement Mode */
+#define MLX90393_CMD_RM 0x40 /* Read Measurement */
+#define MLX90393_CMD_RR 0x50 /* Read Register */
+#define MLX90393_CMD_WR 0x60 /* Write Register */
+#define MLX90393_CMD_EX 0x80 /* Exit Mode */
+#define MLX90393_CMD_HR 0xD0 /* Memory Recall */
+#define MLX90393_CMD_HS 0xE0 /* Memory Store */
+#define MLX90393_CMD_RT 0xF0 /* Reset Device */
+
+#define MLX90393_MEASURE_Z BIT(0)
+#define MLX90393_MEASURE_Y BIT(1)
+#define MLX90393_MEASURE_X BIT(2)
+#define MLX90393_MEASURE_TEMP BIT(3)
+
+#define MLX90393_MEASURE_ALL \
+ (MLX90393_MEASURE_TEMP | MLX90393_MEASURE_X | \
+ MLX90393_MEASURE_Y | MLX90393_MEASURE_Z)
+
+#define MLX90393_NUM_CHANNELS 4
+
+#define MLX90393_STATUS_RESP GENMASK(1, 0)
+#define MLX90393_STATUS_RT BIT(2)
+#define MLX90393_STATUS_ERROR BIT(4)
+
+#define MLX90393_REG_CONF1 0x00
+#define MLX90393_REG_CONF2 0x01
+#define MLX90393_REG_CONF3 0x02
+#define MLX90393_REG_CONF4 0x03
+
+#define MLX90393_CONF1_GAIN_SEL GENMASK(6, 4)
+#define MLX90393_CONF1_HALLCONF GENMASK(3, 0)
+
+#define MLX90393_CONF3_OSR GENMASK(1, 0)
+#define MLX90393_CONF3_DIG_FILT GENMASK(4, 2)
+#define MLX90393_CONF3_RES_X GENMASK(6, 5)
+#define MLX90393_CONF3_RES_Y GENMASK(8, 7)
+#define MLX90393_CONF3_RES_Z GENMASK(10, 9)
+#define MLX90393_CONF3_OSR2 GENMASK(12, 11)
+
+struct mlx90393_transfer_ops {
+ int (*xfer)(void *context, const u8 *tx, int tx_len,
+ u8 *rx, int rx_len);
+};
+
+int mlx90393_core_probe(struct device *dev,
+ const struct mlx90393_transfer_ops *ops,
+ void *context);
+
+#endif
diff --git a/drivers/iio/magnetometer/mlx90393_core.c b/drivers/iio/magnetometer/mlx90393_core.c
new file mode 100644
index 000000000000..0ad4a30c0be9
--- /dev/null
+++ b/drivers/iio/magnetometer/mlx90393_core.c
@@ -0,0 +1,681 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * MLX90393 magnetometer & temperature sensor driver
+ *
+ * Copyright (c) 2026 Nikhil Gautam <nikhilgtr@gmail.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/unaligned.h>
+#include <linux/units.h>
+
+#include <linux/iio/iio.h>
+
+#include "mlx90393.h"
+
+struct mlx90393_data {
+ /* Protects sensor configuration and measurement operations */
+ struct mutex lock;
+ struct device *dev;
+ void *bus_context;
+ const struct mlx90393_transfer_ops *ops;
+ u8 gain_sel;
+ u8 hallconf;
+
+ u8 res_xy;
+ u8 res_z;
+
+ u8 dig_filt;
+ u8 osr;
+ u8 osr2;
+};
+
+enum mlx90393_channels {
+ MLX90393_CHAN_X,
+ MLX90393_CHAN_Y,
+ MLX90393_CHAN_Z,
+ MLX90393_CHAN_TEMP,
+};
+
+enum mlx90393_axis_type {
+ MLX90393_AXIS_TYPE_XY,
+ MLX90393_AXIS_TYPE_Z,
+};
+
+/* Datasheet: Table no.17 */
+static const int mlx90393_scale_table[MLX90393_AXIS_MAX]
+ [MLX90393_GAIN_MAX]
+ [MLX90393_RES_MAX] = {
+ /* XY axis */
+ {
+ { 751, 1502, 3004, 6009},
+ { 601, 1202, 2403, 4840},
+ { 451, 901, 1803, 3605},
+ { 376, 751, 1502, 3004},
+ { 300, 601, 1202, 2403},
+ { 250, 501, 1001, 2003},
+ { 200, 401, 801, 1602},
+ { 150, 300, 601, 1202},
+ },
+ /* Z axis */
+ {
+ { 1210, 2420, 4840, 9680},
+ { 968, 1936, 3872, 7744},
+ { 726, 1452, 2904, 5808},
+ { 605, 1210, 2420, 4840},
+ { 484, 968, 1936, 3872},
+ { 403, 807, 1613, 3227},
+ { 323, 645, 1291, 2581},
+ { 242, 484, 968, 1936},
+ }
+};
+
+static const int mlx90393_osr2_avail[MLX90393_OSR2_MAX] = {
+ 0, 1, 2, 3,
+};
+
+static const int mlx90393_osr_avail[MLX90393_OSR_MAX] = {
+ 1, 2, 4, 8,
+};
+
+#define MLX90393_CHAN(idx, axis, addr) { \
+ .type = IIO_MAGN, \
+ .modified = 1, \
+ .channel = idx, \
+ .address = addr, \
+ .channel2 = IIO_MOD_##axis, \
+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \
+ BIT(IIO_CHAN_INFO_SCALE), \
+ .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OVERSAMPLING_RATIO),\
+ .info_mask_separate_available = \
+ BIT(IIO_CHAN_INFO_SCALE), \
+ .info_mask_shared_by_type_available = \
+ BIT(IIO_CHAN_INFO_OVERSAMPLING_RATIO), \
+}
+
+static const struct iio_chan_spec mlx90393_channels[] = {
+ MLX90393_CHAN(0, X, MLX90393_CHAN_X),
+ MLX90393_CHAN(1, Y, MLX90393_CHAN_Y),
+ MLX90393_CHAN(2, Z, MLX90393_CHAN_Z),
+ {
+ .type = IIO_TEMP,
+ .address = MLX90393_CHAN_TEMP,
+ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+ BIT(IIO_CHAN_INFO_OFFSET) |
+ BIT(IIO_CHAN_INFO_OVERSAMPLING_RATIO),
+ .info_mask_separate_available =
+ BIT(IIO_CHAN_INFO_OVERSAMPLING_RATIO),
+ .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+ },
+};
+
+/*
+ * Calculate total conversion time in microseconds.
+ *
+ * Formula derived from datasheet timing equations.
+ */
+
+static int mlx90393_get_tconv_us(struct mlx90393_data *data)
+{
+ const int osr = data->osr;
+ const int osr2 = data->osr2;
+ const int df = data->dig_filt;
+
+ int tconvm;
+ int tconvt;
+
+ int m = 3; /* X,Y,Z */
+
+ /*
+ * Datasheet:
+ * TCONVM = 67 + 64 * 2^OSR * (2 + 2^DIG_FILT)
+ */
+ tconvm = 67 + (64 * BIT(osr) * (2 + BIT(df)));
+
+ /*
+ * Datasheet:
+ * TCONVT = 67 + 192 * 2^OSR2
+ */
+ tconvt = 67 + (192 * BIT(osr2));
+ /*
+ * Total conversion time:
+ * TSTBY + TACTIVE + m * TCONVM + TCONVT + TCONV_END
+ */
+ return 220 + 360 + (m * tconvm) + tconvt + 1100;
+}
+
+static int mlx90393_xfer(struct mlx90393_data *data,
+ const u8 *tx, int tx_len,
+ u8 *rx, int rx_len)
+{
+ return data->ops->xfer(data->bus_context,
+ tx, tx_len,
+ rx, rx_len);
+}
+
+static int mlx90393_check_status(u8 cmd, u8 status)
+{
+ /* Always validate error bit */
+ if (status & MLX90393_STATUS_ERROR)
+ return -EIO;
+
+ switch (cmd & MLX90393_CMD_MASK) {
+ case MLX90393_CMD_RM:
+ /*
+ * D1:D0 indicates response availability
+ * 00 means invalid/no measurement
+ */
+ if ((status & MLX90393_STATUS_RESP) == 0)
+ return -EIO;
+ return 0;
+ case MLX90393_CMD_RT:
+ /* Reset acknowledge */
+ if (!(status & MLX90393_STATUS_RT))
+ return -EIO;
+ return 0;
+ default:
+ return 0;
+ }
+}
+
+static int mlx90393_write_cmd(struct mlx90393_data *data, u8 cmd)
+{
+ u8 status;
+ int ret;
+
+ ret = mlx90393_xfer(data, &cmd, 1, &status, 1);
+ if (ret)
+ return ret;
+
+ return mlx90393_check_status(cmd, status);
+}
+
+static int mlx90393_read_cmd(struct mlx90393_data *data, u8 cmd, u8 *rx,
+ int rx_len)
+{
+ int ret;
+
+ ret = mlx90393_xfer(data, &cmd, 1, rx, rx_len);
+ if (ret)
+ return ret;
+
+ return mlx90393_check_status(cmd, rx[0]);
+}
+
+static int mlx90393_read_reg(struct mlx90393_data *data, u8 reg, u16 *val)
+{
+ u8 tx[2];
+ u8 rx[3];
+ int ret;
+
+ tx[0] = MLX90393_CMD_RR;
+ /* Register address is encoded in bits [7:2] */
+ tx[1] = reg << 2;
+
+ ret = mlx90393_xfer(data, tx, sizeof(tx), rx, sizeof(rx));
+ if (ret)
+ return ret;
+
+ ret = mlx90393_check_status(tx[0], rx[0]);
+ if (ret)
+ return ret;
+
+ *val = get_unaligned_be16(&rx[1]);
+
+ return 0;
+}
+
+static int mlx90393_write_reg(struct mlx90393_data *data, u8 reg, u16 val)
+{
+ u8 tx[4];
+ u8 status;
+ int ret;
+
+ tx[0] = MLX90393_CMD_WR;
+ put_unaligned_be16(val, &tx[1]);
+ /* Register address is encoded in bits [7:2] */
+ tx[3] = reg << 2;
+
+ ret = mlx90393_xfer(data, tx, sizeof(tx), &status, 1);
+ if (ret)
+ return ret;
+
+ return mlx90393_check_status(tx[0], status);
+}
+
+static int mlx90393_update_bits(struct mlx90393_data *data, u8 reg_addr,
+ u16 mask, u16 val)
+{
+ u16 reg;
+ int ret;
+
+ ret = mlx90393_read_reg(data, reg_addr, ®);
+ if (ret)
+ return ret;
+
+ reg &= ~mask;
+ reg |= (val << __ffs(mask)) & mask;
+
+ return mlx90393_write_reg(data, reg_addr, reg);
+}
+
+static int mlx90393_read_measurement(struct mlx90393_data *data,
+ enum mlx90393_channels chan, int *val)
+{
+ u8 rx[9];
+ int ret;
+
+ /* Start measurement */
+ ret = mlx90393_write_cmd(data, MLX90393_CMD_SM | MLX90393_MEASURE_ALL);
+ if (ret)
+ return ret;
+
+ /* Wait conversion */
+ fsleep(mlx90393_get_tconv_us(data));
+
+ /* Read measurement */
+ ret = mlx90393_read_cmd(data, MLX90393_CMD_RM | MLX90393_MEASURE_ALL,
+ rx, sizeof(rx));
+ if (ret)
+ return ret;
+ /*
+ * Measurement response layout:
+ * [status][temp][x][y][z]
+ */
+
+ switch (chan) {
+ case MLX90393_CHAN_TEMP:
+ *val = get_unaligned_be16(&rx[1]);
+ return 0;
+
+ case MLX90393_CHAN_X:
+ *val = sign_extend32(get_unaligned_be16(&rx[3]), 15);
+ return 0;
+
+ case MLX90393_CHAN_Y:
+ *val = sign_extend32(get_unaligned_be16(&rx[5]), 15);
+ return 0;
+
+ case MLX90393_CHAN_Z:
+ *val = sign_extend32(get_unaligned_be16(&rx[7]), 15);
+ return 0;
+
+ default:
+ return -EINVAL;
+ }
+}
+
+static int mlx90393_get_scale(struct mlx90393_data *data,
+ const struct iio_chan_spec *chan,
+ int *val, int *val2)
+{
+ enum mlx90393_axis_type axis;
+ u8 res;
+
+ if (chan->channel2 == IIO_MOD_Z) {
+ axis = MLX90393_AXIS_TYPE_Z;
+ res = data->res_z;
+ } else {
+ axis = MLX90393_AXIS_TYPE_XY;
+ res = data->res_xy;
+ }
+
+ /*
+ * Convert:
+ * µT × 1000 → nT
+ */
+ *val = 0;
+ *val2 = mlx90393_scale_table[axis][data->gain_sel][res];
+
+ return IIO_VAL_INT_PLUS_NANO;
+}
+
+static int mlx90393_find_scale(struct mlx90393_data *data, bool z_axis,
+ int val, int val2,
+ int *gain)
+{
+ u8 res;
+ enum mlx90393_axis_type axis;
+
+ if (z_axis) {
+ axis = MLX90393_AXIS_TYPE_Z;
+ res = data->res_z;
+ } else {
+ axis = MLX90393_AXIS_TYPE_XY;
+ res = data->res_xy;
+ }
+
+ if (val != 0)
+ return -EINVAL;
+
+ for (unsigned int i = 0; i < ARRAY_SIZE(mlx90393_scale_table[0]); i++)
+ if (mlx90393_scale_table[axis][i][res] == val2) {
+ *gain = i;
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
+static int mlx90393_set_scale(struct mlx90393_data *data,
+ const struct iio_chan_spec *chan,
+ int val, int val2)
+{
+ bool z_axis;
+ int gain;
+ int ret;
+
+ z_axis = chan->channel2 == IIO_MOD_Z;
+
+ ret = mlx90393_find_scale(data, z_axis, val, val2, &gain);
+ if (ret)
+ return ret;
+
+ ret = mlx90393_update_bits(data, MLX90393_REG_CONF1, MLX90393_CONF1_GAIN_SEL,
+ gain);
+ if (ret)
+ return ret;
+
+ data->gain_sel = gain;
+
+ return 0;
+}
+
+static int mlx90393_get_osr(struct mlx90393_data *data, int *val)
+{
+ *val = mlx90393_osr_avail[data->osr];
+
+ return IIO_VAL_INT;
+}
+
+static int mlx90393_find_osr(int val, int *osr)
+{
+ for (unsigned int i = 0; i < MLX90393_OSR_MAX; i++)
+ if (mlx90393_osr_avail[i] == val) {
+ *osr = i;
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
+static int mlx90393_get_temp_osr2(struct mlx90393_data *data, int *val)
+{
+ *val = mlx90393_osr2_avail[data->osr2];
+ return IIO_VAL_INT;
+}
+
+static int mlx90393_set_osr(struct mlx90393_data *data, int val)
+{
+ int osr;
+ int ret;
+
+ ret = mlx90393_find_osr(val, &osr);
+ if (ret)
+ return ret;
+
+ if (osr == data->osr)
+ return 0;
+
+ ret = mlx90393_update_bits(data, MLX90393_REG_CONF3, MLX90393_CONF3_OSR,
+ osr);
+ if (ret)
+ return ret;
+
+ data->osr = osr;
+ return 0;
+}
+
+static int mlx90393_set_temp_osr2(struct mlx90393_data *data, int val)
+{
+ int ret;
+
+ if (val < 0 || val >= MLX90393_OSR2_MAX)
+ return -EINVAL;
+
+ if (val == data->osr2)
+ return 0;
+
+ ret = mlx90393_update_bits(data, MLX90393_REG_CONF3, MLX90393_CONF3_OSR2,
+ val);
+ if (ret)
+ return ret;
+
+ data->osr2 = val;
+
+ return 0;
+}
+
+static int mlx90393_write_raw_get_fmt(struct iio_dev *indio_dev,
+ struct iio_chan_spec const *chan,
+ long mask)
+{
+ switch (mask) {
+ case IIO_CHAN_INFO_SCALE:
+ return IIO_VAL_INT_PLUS_NANO;
+
+ case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
+ return IIO_VAL_INT;
+
+ default:
+ return -EINVAL;
+ }
+}
+
+static int mlx90393_write_raw(struct iio_dev *indio_dev,
+ const struct iio_chan_spec *chan,
+ int val, int val2,
+ long mask)
+{
+ struct mlx90393_data *data = iio_priv(indio_dev);
+ int ret;
+
+ switch (mask) {
+ case IIO_CHAN_INFO_SCALE: {
+ guard(mutex)(&data->lock);
+ ret = mlx90393_set_scale(data, chan, val, val2);
+ return ret;
+ }
+ case IIO_CHAN_INFO_OVERSAMPLING_RATIO: {
+ guard(mutex)(&data->lock);
+ switch (chan->type) {
+ case IIO_TEMP:
+ return mlx90393_set_temp_osr2(data, val);
+
+ case IIO_MAGN:
+ return mlx90393_set_osr(data, val);
+
+ default:
+ return -EINVAL;
+ }
+ }
+ default:
+ return -EINVAL;
+ }
+}
+
+static int mlx90393_read_raw(struct iio_dev *indio_dev,
+ const struct iio_chan_spec *chan,
+ int *val, int *val2, long mask)
+{
+ struct mlx90393_data *data = iio_priv(indio_dev);
+ int ret;
+
+ switch (mask) {
+ case IIO_CHAN_INFO_RAW: {
+ guard(mutex)(&data->lock);
+ ret = mlx90393_read_measurement(data, chan->address, val);
+ if (ret)
+ return ret;
+
+ return IIO_VAL_INT;
+ }
+ case IIO_CHAN_INFO_SCALE:
+ switch (chan->type) {
+ case IIO_MAGN:
+ return mlx90393_get_scale(data, chan, val, val2);
+
+ case IIO_TEMP:
+ /* Datasheet: 22124 millidegC/LSB */
+ *val = 0;
+ *val2 = 22124;
+ return IIO_VAL_INT_PLUS_MICRO;
+
+ default:
+ return -EINVAL;
+ }
+
+ case IIO_CHAN_INFO_OFFSET:
+ if (chan->type != IIO_TEMP)
+ return -EINVAL;
+
+ /* Datasheet: temperature offset */
+ *val = -45114;
+ return IIO_VAL_INT;
+
+ case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
+ switch (chan->type) {
+ case IIO_TEMP:
+ return mlx90393_get_temp_osr2(data, val);
+ case IIO_MAGN:
+ return mlx90393_get_osr(data, val);
+ default:
+ return -EINVAL;
+ }
+ default:
+ return -EINVAL;
+ }
+}
+
+static int mlx90393_read_avail(struct iio_dev *indio_dev,
+ const struct iio_chan_spec *chan,
+ const int **vals,
+ int *type,
+ int *length,
+ long mask)
+{
+ struct mlx90393_data *data = iio_priv(indio_dev);
+ static int scale_avail[MLX90393_GAIN_MAX][MLX90393_AXIS_MAX];
+ enum mlx90393_axis_type axis;
+ u8 res;
+
+ switch (mask) {
+ case IIO_CHAN_INFO_SCALE: {
+ guard(mutex)(&data->lock);
+ axis = chan->channel2 == IIO_MOD_Z;
+ res = axis ? data->res_z : data->res_xy;
+
+ for (unsigned int i = 0; i < MLX90393_GAIN_MAX; i++) {
+ scale_avail[i][0] = 0;
+ scale_avail[i][1] = mlx90393_scale_table[axis][i][res];
+ }
+
+ *vals = &scale_avail[0][0];
+ *type = IIO_VAL_INT_PLUS_NANO;
+ *length = MLX90393_GAIN_MAX * MLX90393_AXIS_MAX;
+ return IIO_AVAIL_LIST;
+ }
+ case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
+ if (chan->type == IIO_TEMP) {
+ *vals = mlx90393_osr2_avail;
+ *type = IIO_VAL_INT;
+ *length = MLX90393_OSR2_MAX;
+ } else {
+ *vals = mlx90393_osr_avail;
+ *type = IIO_VAL_INT;
+ *length = MLX90393_OSR_MAX;
+ }
+ return IIO_AVAIL_LIST;
+
+ default:
+ return -EINVAL;
+ }
+ return -EINVAL;
+}
+
+static const struct iio_info mlx90393_info = {
+ .read_raw = mlx90393_read_raw,
+ .write_raw = mlx90393_write_raw,
+ .read_avail = mlx90393_read_avail,
+ .write_raw_get_fmt = mlx90393_write_raw_get_fmt,
+};
+
+static int mlx90393_init(struct mlx90393_data *data)
+{
+ int ret;
+ u16 reg;
+
+ /* Exit mode */
+ ret = mlx90393_write_cmd(data, MLX90393_CMD_EX);
+ if (ret)
+ return ret;
+
+ /* Wait for device comes out of reset */
+ fsleep(1000);
+
+ /* Reset device */
+ ret = mlx90393_write_cmd(data, MLX90393_CMD_RT);
+ if (ret)
+ return ret;
+
+ /* Wait for device to reset */
+ fsleep(6000);
+
+ ret = mlx90393_read_reg(data, MLX90393_REG_CONF1, ®);
+ if (ret)
+ return ret;
+
+ data->gain_sel = FIELD_GET(MLX90393_CONF1_GAIN_SEL, reg);
+ data->hallconf = FIELD_GET(MLX90393_CONF1_HALLCONF, reg);
+
+ ret = mlx90393_read_reg(data, MLX90393_REG_CONF3, ®);
+ if (ret)
+ return ret;
+
+ data->res_xy = FIELD_GET(MLX90393_CONF3_RES_X, reg);
+ data->res_z = FIELD_GET(MLX90393_CONF3_RES_Z, reg);
+ data->dig_filt = FIELD_GET(MLX90393_CONF3_DIG_FILT, reg);
+ data->osr = FIELD_GET(MLX90393_CONF3_OSR, reg);
+ data->osr2 = FIELD_GET(MLX90393_CONF3_OSR2, reg);
+
+ return 0;
+}
+
+int mlx90393_core_probe(struct device *dev,
+ const struct mlx90393_transfer_ops *ops,
+ void *context)
+{
+ struct iio_dev *indio_dev;
+ struct mlx90393_data *data;
+ int ret;
+
+ indio_dev = devm_iio_device_alloc(dev, sizeof(*data));
+ if (!indio_dev)
+ return -ENOMEM;
+
+ data = iio_priv(indio_dev);
+ devm_mutex_init(dev, &data->lock);
+
+ data->dev = dev;
+ data->ops = ops;
+ data->bus_context = context;
+
+ indio_dev->name = "mlx90393";
+ indio_dev->info = &mlx90393_info;
+ indio_dev->modes = INDIO_DIRECT_MODE;
+ indio_dev->channels = mlx90393_channels;
+ indio_dev->num_channels = ARRAY_SIZE(mlx90393_channels);
+
+ ret = mlx90393_init(data);
+ if (ret)
+ return dev_err_probe(dev, ret, "failed to initialize device\n");
+
+ return devm_iio_device_register(dev, indio_dev);
+}
+EXPORT_SYMBOL_GPL(mlx90393_core_probe);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Nikhil Gautam <nikhilgtr@gmail.com>");
+MODULE_DESCRIPTION("MLX90393 magnetometer sensor driver");
diff --git a/drivers/iio/magnetometer/mlx90393_i2c.c b/drivers/iio/magnetometer/mlx90393_i2c.c
new file mode 100644
index 000000000000..52233b6295c2
--- /dev/null
+++ b/drivers/iio/magnetometer/mlx90393_i2c.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/mod_devicetable.h>
+
+#include "mlx90393.h"
+
+/*
+ * MLX90393 commands use repeated-start transfers where
+ * every command is followed by a status/data response.
+ */
+static int mlx90393_i2c_xfer(void *context,
+ const u8 *tx, int tx_len,
+ u8 *rx, int rx_len)
+{
+ struct i2c_client *client = context;
+ int ret;
+ struct i2c_msg msgs[2] = {
+ [0] = {
+ .addr = client->addr,
+ .len = tx_len,
+ .buf = (u8 *)tx,
+ },
+ [1] = {
+ .addr = client->addr,
+ .flags = I2C_M_RD,
+ .len = rx_len,
+ .buf = rx,
+ },
+ };
+
+ ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
+ if (ret != ARRAY_SIZE(msgs))
+ return ret < 0 ? ret : -EIO;
+
+ return 0;
+}
+
+static const struct mlx90393_transfer_ops mlx90393_i2c_ops = {
+ .xfer = mlx90393_i2c_xfer,
+};
+
+static int mlx90393_i2c_probe(struct i2c_client *client)
+{
+ return mlx90393_core_probe(&client->dev, &mlx90393_i2c_ops, client);
+}
+
+static const struct i2c_device_id mlx90393_id[] = {
+ { "mlx90393" },
+ { }
+};
+MODULE_DEVICE_TABLE(i2c, mlx90393_id);
+
+static const struct of_device_id mlx90393_of_match[] = {
+ { .compatible = "melexis,mlx90393" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, mlx90393_of_match);
+
+static struct i2c_driver mlx90393_i2c_driver = {
+ .driver = {
+ .name = "mlx90393",
+ .of_match_table = mlx90393_of_match,
+ },
+ .probe = mlx90393_i2c_probe,
+};
+
+module_i2c_driver(mlx90393_i2c_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Nikhil Gautam <nikhilgtr@gmail.com>");
+MODULE_DESCRIPTION("MLX90393 magnetometer sensor driver");
--
2.39.5
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox