* [PATCH 0/8] Enable USB host functions on Jetson AGX Thor
From: Wayne Chang @ 2026-06-29 9:33 UTC (permalink / raw)
To: mathias.nyman, vkoul, neil.armstrong, robh, krzk+dt, conor+dt,
gregkh, thierry.reding, jonathanh
Cc: waynec, linux-usb, linux-tegra, linux-kernel, linux-phy,
devicetree
Enable support for USB host functions on the Tegra264 Jetson AGX Thor
platform
Sing-Han Chen (1):
phy: tegra: xusb: Use devm_clk_get_optional to fetch USB2 tracking
clock
Wayne Chang (7):
dt-bindings: phy: tegra-xusb: Add support for Tegra264
dt-bindings: usb: Add Tegra264 XUSB host support
arm64: tegra: Enable XUSB host function on Jetson AGX Thor
phy: tegra: xusb: Increase timeout for USB2_TRK_COMPLETED polling
phy: tegra: xusb: Add Tegra264 support
usb: host: xhci-tegra: Skip MBOX MSG_ENABLED on Tegra264
usb: host: xhci-tegra: Add Tegra264 XHCI support
.../phy/nvidia,tegra194-xusb-padctl.yaml | 1 +
.../bindings/usb/nvidia,tegra234-xusb.yaml | 115 +++++++++----
.../arm64/boot/dts/nvidia/tegra264-p3834.dtsi | 50 ++++++
.../dts/nvidia/tegra264-p4071-0000+p3834.dtsi | 95 +++++++++++
arch/arm64/boot/dts/nvidia/tegra264.dtsi | 154 ++++++++++++++++++
drivers/phy/tegra/Makefile | 1 +
drivers/phy/tegra/xusb-tegra186.c | 30 +++-
drivers/phy/tegra/xusb.c | 6 +
drivers/phy/tegra/xusb.h | 3 +
drivers/usb/host/xhci-tegra.c | 37 +++++
10 files changed, 454 insertions(+), 38 deletions(-)
base-commit: dc59e4fea9d83f03bad6bddf3fa2e52491777482
--
2.25.1
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* [PATCH 1/8] dt-bindings: phy: tegra-xusb: Add support for Tegra264
From: Wayne Chang @ 2026-06-29 9:33 UTC (permalink / raw)
To: mathias.nyman, vkoul, neil.armstrong, robh, krzk+dt, conor+dt,
gregkh, thierry.reding, jonathanh
Cc: waynec, linux-usb, linux-tegra, linux-kernel, linux-phy,
devicetree
In-Reply-To: <20260629093406.1118594-1-waynec@nvidia.com>
Add the compatible string for the Tegra264 XUSB PHY.
Signed-off-by: Wayne Chang <waynec@nvidia.com>
---
.../devicetree/bindings/phy/nvidia,tegra194-xusb-padctl.yaml | 1 +
1 file changed, 1 insertion(+)
diff --git a/Documentation/devicetree/bindings/phy/nvidia,tegra194-xusb-padctl.yaml b/Documentation/devicetree/bindings/phy/nvidia,tegra194-xusb-padctl.yaml
index d8de900a4fce..f6fe3c90b5b0 100644
--- a/Documentation/devicetree/bindings/phy/nvidia,tegra194-xusb-padctl.yaml
+++ b/Documentation/devicetree/bindings/phy/nvidia,tegra194-xusb-padctl.yaml
@@ -45,6 +45,7 @@ properties:
enum:
- nvidia,tegra194-xusb-padctl
- nvidia,tegra234-xusb-padctl
+ - nvidia,tegra264-xusb-padctl
reg:
items:
--
2.25.1
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH 2/8] dt-bindings: usb: Add Tegra264 XUSB host support
From: Wayne Chang @ 2026-06-29 9:34 UTC (permalink / raw)
To: mathias.nyman, vkoul, neil.armstrong, robh, krzk+dt, conor+dt,
gregkh, thierry.reding, jonathanh
Cc: waynec, linux-usb, linux-tegra, linux-kernel, linux-phy,
devicetree
In-Reply-To: <20260629093406.1118594-1-waynec@nvidia.com>
Extend the Tegra234 XUSB host binding to cover Tegra264:
- Add nvidia,tegra264-xusb compatible string
- Document optional USB wake interrupts for Tegra264
- Document Tegra264 PMC wake event to port mapping
- Allow up to five IOMMU specifiers for the additional XUSB host
stream IDs
Signed-off-by: Wayne Chang <waynec@nvidia.com>
---
.../bindings/usb/nvidia,tegra234-xusb.yaml | 115 ++++++++++++------
1 file changed, 80 insertions(+), 35 deletions(-)
diff --git a/Documentation/devicetree/bindings/usb/nvidia,tegra234-xusb.yaml b/Documentation/devicetree/bindings/usb/nvidia,tegra234-xusb.yaml
index ec0993497fbb..94b1dbe2b02f 100644
--- a/Documentation/devicetree/bindings/usb/nvidia,tegra234-xusb.yaml
+++ b/Documentation/devicetree/bindings/usb/nvidia,tegra234-xusb.yaml
@@ -17,7 +17,9 @@ description: |
properties:
compatible:
- const: nvidia,tegra234-xusb
+ enum:
+ - nvidia,tegra234-xusb
+ - nvidia,tegra264-xusb
reg:
items:
@@ -31,37 +33,6 @@ properties:
- const: fpci
- const: bar2
- interrupts:
- minItems: 2
- items:
- - description: xHCI host interrupt
- - description: mailbox interrupt
- - description: USB wake event 0
- - description: USB wake event 1
- - description: USB wake event 2
- - description: USB wake event 3
- - description: USB wake event 4
- - description: USB wake event 5
- - description: USB wake event 6
- description: |
- The first two interrupts are required for the USB host controller. The
- remaining USB wake event interrupts are optional. Each USB wake event is
- independent; it is not necessary to use all of these events on a
- platform. The USB host controller can function even if no wake-up events
- are defined. The USB wake event interrupts are handled by the Tegra PMC;
- hence, the interrupt controller for these is the PMC and the interrupt
- IDs correspond to the PMC wake event IDs. A complete list of wake event
- IDs is provided below, and this information is also present in the Tegra
- TRM document.
-
- PMC wake-up 76 for USB3 port 0 wakeup
- PMC wake-up 77 for USB3 port 1 wakeup
- PMC wake-up 78 for USB3 port 2 and port 3 wakeup
- PMC wake-up 79 for USB2 port 0 wakeup
- PMC wake-up 80 for USB2 port 1 wakeup
- PMC wake-up 81 for USB2 port 2 wakeup
- PMC wake-up 82 for USB2 port 3 wakeup
-
clocks:
items:
- description: XUSB host clock
@@ -96,9 +67,6 @@ properties:
- const: dma-mem # read
- const: write
- iommus:
- maxItems: 1
-
nvidia,xusb-padctl:
$ref: /schemas/types.yaml#/definitions/phandle
description: phandle to the XUSB pad controller that is used to configure
@@ -137,6 +105,83 @@ properties:
allOf:
- $ref: usb-xhci.yaml
+ - if:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - nvidia,tegra234-xusb
+ then:
+ properties:
+ interrupts:
+ minItems: 2
+ description: |
+ The first two interrupts are required for the USB host controller.
+ The remaining USB wake event interrupts are optional. Each USB wake
+ event is independent; it is not necessary to use all of these events
+ on a platform. The USB host controller can function even if no
+ wake-up events are defined. The USB wake event interrupts are
+ handled by the Tegra PMC; hence, the interrupt controller for these
+ is the PMC and the interrupt IDs correspond to the PMC wake event
+ IDs.
+
+ PMC wake-up 76 for USB3 port 0 wakeup
+ PMC wake-up 77 for USB3 port 1 wakeup
+ PMC wake-up 78 for USB3 port 2 and port 3 wakeup
+ PMC wake-up 79 for USB2 port 0 wakeup
+ PMC wake-up 80 for USB2 port 1 wakeup
+ PMC wake-up 81 for USB2 port 2 wakeup
+ PMC wake-up 82 for USB2 port 3 wakeup
+ items:
+ - description: xHCI host interrupt
+ - description: mailbox interrupt
+ - description: USB wake event 0
+ - description: USB wake event 1
+ - description: USB wake event 2
+ - description: USB wake event 3
+ - description: USB wake event 4
+ - description: USB wake event 5
+ - description: USB wake event 6
+ iommus:
+ maxItems: 1
+
+ - if:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - nvidia,tegra264-xusb
+ then:
+ properties:
+ interrupts:
+ minItems: 2
+ description: |
+ Same as Tegra234, with one additional optional USB wake event
+ interrupt. USB3 port 2 and port 3 each have a dedicated wake event
+ interrupt on Tegra264.
+
+ PMC wake-up 79 for USB3 port 0 wakeup
+ PMC wake-up 80 for USB3 port 1 wakeup
+ PMC wake-up 81 for USB3 port 2 wakeup
+ PMC wake-up 82 for USB3 port 3 wakeup
+ PMC wake-up 83 for USB2 port 0 wakeup
+ PMC wake-up 84 for USB2 port 1 wakeup
+ PMC wake-up 85 for USB2 port 2 wakeup
+ PMC wake-up 86 for USB2 port 3 wakeup
+ items:
+ - description: xHCI host interrupt
+ - description: mailbox interrupt
+ - description: USB wake event 0
+ - description: USB wake event 1
+ - description: USB wake event 2
+ - description: USB wake event 3
+ - description: USB wake event 4
+ - description: USB wake event 5
+ - description: USB wake event 6
+ - description: USB wake event 7
+ iommus:
+ maxItems: 5
+
unevaluatedProperties: false
examples:
--
2.25.1
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH 4/8] phy: tegra: xusb: Use devm_clk_get_optional to fetch USB2 tracking clock
From: Wayne Chang @ 2026-06-29 9:34 UTC (permalink / raw)
To: mathias.nyman, vkoul, neil.armstrong, robh, krzk+dt, conor+dt,
gregkh, thierry.reding, jonathanh
Cc: waynec, linux-usb, linux-tegra, linux-kernel, linux-phy,
devicetree, Sing-Han Chen
In-Reply-To: <20260629093406.1118594-1-waynec@nvidia.com>
From: Sing-Han Chen <singhanc@nvidia.com>
The USB2 PAD tracking clock is an optional clock so use
devm_clk_get_optional() so a missing clock in devicetree is
represented as NULL and probe can continue. clk_prepare_enable()
and clk_disable_unprepare() already treat a NULL clock as a no-op.
Signed-off-by: Sing-Han Chen <singhanc@nvidia.com>
Signed-off-by: Wayne Chang <waynec@nvidia.com>
---
drivers/phy/tegra/xusb-tegra186.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c
index 60156aea2707..800be0cbb3f9 100644
--- a/drivers/phy/tegra/xusb-tegra186.c
+++ b/drivers/phy/tegra/xusb-tegra186.c
@@ -1045,7 +1045,7 @@ tegra186_usb2_pad_probe(struct tegra_xusb_padctl *padctl,
goto out;
}
- priv->usb2_trk_clk = devm_clk_get(&pad->dev, "trk");
+ priv->usb2_trk_clk = devm_clk_get_optional(&pad->dev, "trk");
if (IS_ERR(priv->usb2_trk_clk)) {
err = PTR_ERR(priv->usb2_trk_clk);
dev_dbg(&pad->dev, "failed to get usb2 trk clock: %d\n", err);
--
2.25.1
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH 3/8] arm64: tegra: Enable XUSB host function on Jetson AGX Thor
From: Wayne Chang @ 2026-06-29 9:34 UTC (permalink / raw)
To: mathias.nyman, vkoul, neil.armstrong, robh, krzk+dt, conor+dt,
gregkh, thierry.reding, jonathanh
Cc: waynec, linux-usb, linux-tegra, linux-kernel, linux-phy,
devicetree
In-Reply-To: <20260629093406.1118594-1-waynec@nvidia.com>
This commit enables XUSB host and pad controller on Jetson AGX Thor.
Signed-off-by: Wayne Chang <waynec@nvidia.com>
---
.../arm64/boot/dts/nvidia/tegra264-p3834.dtsi | 50 ++++++
.../dts/nvidia/tegra264-p4071-0000+p3834.dtsi | 95 +++++++++++
arch/arm64/boot/dts/nvidia/tegra264.dtsi | 154 ++++++++++++++++++
3 files changed, 299 insertions(+)
diff --git a/arch/arm64/boot/dts/nvidia/tegra264-p3834.dtsi b/arch/arm64/boot/dts/nvidia/tegra264-p3834.dtsi
index 7e2c3e66c2ab..61802334452e 100644
--- a/arch/arm64/boot/dts/nvidia/tegra264-p3834.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra264-p3834.dtsi
@@ -35,4 +35,54 @@ cmdqv@6200000 {
status = "okay";
};
};
+
+ bus@a800000000 {
+ padctl@8680000 {
+ vclamp-usb-supply = <&vdd_ao_1v8>;
+ avdd-usb-supply = <&vdd_ao_3v3>;
+
+ ports {
+ usb2-0 {
+ vbus-supply = <&vdd_5v0_sys>;
+ };
+
+ usb2-1 {
+ vbus-supply = <&vdd_5v0_sys>;
+ };
+
+ usb2-2 {
+ vbus-supply = <&vdd_5v0_sys>;
+ };
+
+ usb2-3 {
+ vbus-supply = <&vdd_5v0_sys>;
+ };
+ };
+ };
+ };
+
+ vdd_5v0_sys: regulator-vdd-5v0-sys {
+ compatible = "regulator-fixed";
+ regulator-name = "VIN_SYS_5V0";
+ regulator-min-microvolt = <5000000>;
+ regulator-max-microvolt = <5000000>;
+ regulator-always-on;
+ regulator-boot-on;
+ };
+
+ vdd_ao_1v8: regulator-vdd-1v8-ao {
+ compatible = "regulator-fixed";
+ regulator-name = "vdd-AO-1v8";
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <1800000>;
+ regulator-always-on;
+ };
+
+ vdd_ao_3v3: regulator-vdd-3v3-ao {
+ compatible = "regulator-fixed";
+ regulator-name = "vdd-AO-3v3";
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
+ regulator-always-on;
+ };
};
diff --git a/arch/arm64/boot/dts/nvidia/tegra264-p4071-0000+p3834.dtsi b/arch/arm64/boot/dts/nvidia/tegra264-p4071-0000+p3834.dtsi
index 45f8df9bbfd6..9d6d0c31f881 100644
--- a/arch/arm64/boot/dts/nvidia/tegra264-p4071-0000+p3834.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra264-p4071-0000+p3834.dtsi
@@ -9,4 +9,99 @@ aliases {
chosen {
stdout-path = "serial0:115200n8";
};
+
+ bus@a800000000 {
+ padctl@8680000 {
+ status = "okay";
+
+ pads {
+ usb2 {
+ lanes {
+ usb2-0 {
+ status = "okay";
+ };
+
+ usb2-1 {
+ status = "okay";
+ };
+
+ usb2-2 {
+ status = "okay";
+ };
+
+ usb2-3 {
+ status = "okay";
+ };
+ };
+ };
+
+ usb3 {
+ lanes {
+ usb3-0 {
+ status = "okay";
+ };
+
+ usb3-1 {
+ status = "okay";
+ };
+
+ usb3-2 {
+ status = "okay";
+ };
+ };
+ };
+ };
+
+ ports {
+ usb2-0 {
+ mode = "host";
+ status = "okay";
+ };
+
+ usb2-1 {
+ mode = "host";
+ status = "okay";
+ };
+
+ usb2-2 {
+ mode = "host";
+ status = "okay";
+ };
+
+ usb2-3 {
+ mode = "host";
+ status = "okay";
+ };
+
+ usb3-0 {
+ nvidia,usb2-companion = <1>;
+ status = "okay";
+ };
+
+ usb3-1 {
+ nvidia,usb2-companion = <0>;
+ status = "okay";
+ };
+
+ usb3-2 {
+ nvidia,usb2-companion = <3>;
+ status = "okay";
+ };
+ };
+ };
+
+ usb@aa10000 {
+ status = "okay";
+
+ phys = <&{/bus@a800000000/padctl@8680000/pads/usb2/lanes/usb2-0}>,
+ <&{/bus@a800000000/padctl@8680000/pads/usb2/lanes/usb2-1}>,
+ <&{/bus@a800000000/padctl@8680000/pads/usb2/lanes/usb2-2}>,
+ <&{/bus@a800000000/padctl@8680000/pads/usb2/lanes/usb2-3}>,
+ <&{/bus@a800000000/padctl@8680000/pads/usb3/lanes/usb3-0}>,
+ <&{/bus@a800000000/padctl@8680000/pads/usb3/lanes/usb3-1}>,
+ <&{/bus@a800000000/padctl@8680000/pads/usb3/lanes/usb3-2}>;
+ phy-names = "usb2-0", "usb2-1", "usb2-2", "usb2-3",
+ "usb3-0", "usb3-1", "usb3-2";
+ };
+ };
};
diff --git a/arch/arm64/boot/dts/nvidia/tegra264.dtsi b/arch/arm64/boot/dts/nvidia/tegra264.dtsi
index 2d8e7e37830f..3433587dc572 100644
--- a/arch/arm64/boot/dts/nvidia/tegra264.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra264.dtsi
@@ -4049,6 +4049,160 @@ pci@8480000 {
nvidia,bpmp = <&bpmp 5>;
status = "disabled";
};
+
+ xusb_padctl: padctl@8680000 {
+ compatible = "nvidia,tegra264-xusb-padctl";
+ reg = <0x00 0x8680000 0x00 0x20000>,
+ <0x00 0x86a0000 0x00 0x10000>;
+ reg-names = "padctl", "ao";
+ interrupts = <GIC_SPI 4101 IRQ_TYPE_LEVEL_HIGH>;
+
+ resets = <&bpmp TEGRA264_RESET_XUSB1_PADCTL>;
+ reset-names = "padctl";
+
+ status = "disabled";
+
+ pads {
+ usb2 {
+ lanes {
+ usb2-0 {
+ nvidia,function = "xusb";
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+
+ usb2-1 {
+ nvidia,function = "xusb";
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+
+ usb2-2 {
+ nvidia,function = "xusb";
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+
+ usb2-3 {
+ nvidia,function = "xusb";
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+ };
+ };
+
+ usb3 {
+ lanes {
+ usb3-0 {
+ nvidia,function = "xusb";
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+
+ usb3-1 {
+ nvidia,function = "xusb";
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+
+ usb3-2 {
+ nvidia,function = "xusb";
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+
+ usb3-3 {
+ nvidia,function = "xusb";
+ status = "disabled";
+ #phy-cells = <0>;
+ };
+ };
+ };
+ };
+
+ ports {
+ usb2-0 {
+ status = "disabled";
+ };
+
+ usb2-1 {
+ status = "disabled";
+ };
+
+ usb2-2 {
+ status = "disabled";
+ };
+
+ usb2-3 {
+ status = "disabled";
+ };
+
+ usb3-0 {
+ status = "disabled";
+ };
+
+ usb3-1 {
+ status = "disabled";
+ };
+
+ usb3-2 {
+ status = "disabled";
+ };
+
+ usb3-3 {
+ status = "disabled";
+ };
+ };
+ };
+
+ usb@aa10000 {
+ compatible = "nvidia,tegra264-xusb";
+ reg = <0x00 0xaa10000 0x00 0x40000>,
+ <0x00 0xaa00000 0x00 0x10000>,
+ <0x00 0xaa50000 0x00 0x10000>;
+ reg-names = "hcd", "fpci", "bar2";
+
+ interrupts-extended = <&gic GIC_SPI 952 IRQ_TYPE_LEVEL_HIGH>,
+ <&gic GIC_SPI 4096 IRQ_TYPE_LEVEL_HIGH>,
+ <&pmc 79 IRQ_TYPE_LEVEL_HIGH>,
+ <&pmc 80 IRQ_TYPE_LEVEL_HIGH>,
+ <&pmc 81 IRQ_TYPE_LEVEL_HIGH>,
+ <&pmc 82 IRQ_TYPE_LEVEL_HIGH>,
+ <&pmc 83 IRQ_TYPE_LEVEL_HIGH>,
+ <&pmc 84 IRQ_TYPE_LEVEL_HIGH>,
+ <&pmc 85 IRQ_TYPE_LEVEL_HIGH>,
+ <&pmc 86 IRQ_TYPE_LEVEL_HIGH>;
+
+ clocks = <&bpmp TEGRA264_CLK_XUSB1_CORE_HOST>,
+ <&bpmp TEGRA264_CLK_XUSB1_FALCON>,
+ <&bpmp TEGRA264_CLK_XUSB1_CORE_SUPERSPEED>,
+ <&bpmp TEGRA264_CLK_XUSB1_SS>,
+ <&bpmp TEGRA264_CLK_OSC>,
+ <&bpmp TEGRA264_CLK_XUSB1_FS>,
+ <&bpmp TEGRA264_CLK_UTMI_PLL1>,
+ <&bpmp TEGRA264_CLK_OSC>,
+ <&bpmp TEGRA264_CLK_PLLE0>;
+ clock-names = "xusb_host", "xusb_falcon_src",
+ "xusb_ss", "xusb_ss_src", "xusb_hs_src",
+ "xusb_fs_src", "pll_u_480m", "clk_m",
+ "pll_e";
+ interconnects = <&mc TEGRA264_MEMORY_CLIENT_XUSB_DEVR &emc>,
+ <&mc TEGRA264_MEMORY_CLIENT_XUSB_DEVW &emc>;
+ interconnect-names = "dma-mem", "write";
+ iommus = <&smmu1 TEGRA264_SID_XUSB_DEV>,
+ <&smmu1 TEGRA264_SID_XUSB_DEV1>,
+ <&smmu1 TEGRA264_SID_XUSB_DEV2>,
+ <&smmu1 TEGRA264_SID_XUSB_DEV3>,
+ <&smmu1 TEGRA264_SID_XUSB_DEV4>;
+
+ power-domains = <&bpmp TEGRA264_POWER_DOMAIN_XUSB_HOST>,
+ <&bpmp TEGRA264_POWER_DOMAIN_XUSB_SS>;
+ power-domain-names = "xusb_host", "xusb_ss";
+
+ nvidia,xusb-padctl = <&xusb_padctl>;
+ dma-coherent;
+ status = "disabled";
+ };
};
cpus {
--
2.25.1
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH 5/8] phy: tegra: xusb: Increase timeout for USB2_TRK_COMPLETED polling
From: Wayne Chang @ 2026-06-29 9:34 UTC (permalink / raw)
To: mathias.nyman, vkoul, neil.armstrong, robh, krzk+dt, conor+dt,
gregkh, thierry.reding, jonathanh
Cc: waynec, linux-usb, linux-tegra, linux-kernel, linux-phy,
devicetree
In-Reply-To: <20260629093406.1118594-1-waynec@nvidia.com>
On Tegra264, the UTMI bias tracking circuit runs at 1 MHz and needs
more cycles for the biases to settle than on earlier SoCs such as
Tegra234. The existing timeout is therefore not long enough and can
cause spurious polling failures during bias pad power-on. Therefore,
increase the timeout to 200 cycles to support Tegra264 devices
Signed-off-by: Wayne Chang <waynec@nvidia.com>
---
drivers/phy/tegra/xusb-tegra186.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c
index 800be0cbb3f9..9c1bcd4a72ac 100644
--- a/drivers/phy/tegra/xusb-tegra186.c
+++ b/drivers/phy/tegra/xusb-tegra186.c
@@ -636,7 +636,7 @@ static void tegra186_utmi_bias_pad_power_on(struct tegra_xusb_padctl *padctl)
if (padctl->soc->poll_trk_completed) {
err = padctl_readl_poll(padctl, XUSB_PADCTL_USB2_BIAS_PAD_CTL1,
- USB2_TRK_COMPLETED, USB2_TRK_COMPLETED, 100);
+ USB2_TRK_COMPLETED, USB2_TRK_COMPLETED, 200);
if (err) {
/* The failure with polling on trk complete will not
* cause the failure of powering on the bias pad.
--
2.25.1
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH 7/8] usb: host: xhci-tegra: Skip MBOX MSG_ENABLED on Tegra264
From: Wayne Chang @ 2026-06-29 9:34 UTC (permalink / raw)
To: mathias.nyman, vkoul, neil.armstrong, robh, krzk+dt, conor+dt,
gregkh, thierry.reding, jonathanh
Cc: waynec, linux-usb, linux-tegra, linux-kernel, linux-phy,
devicetree
In-Reply-To: <20260629093406.1118594-1-waynec@nvidia.com>
Tegra264 XUSB does not use the firmware mailbox handshake to enable
controller messages (MBOX_CMD_MSG_ENABLED). Add a per-SoC flag and
short-circuit __tegra_xusb_enable_firmware_messages() so both probe
and resume avoid sending the command.
Signed-off-by: Wayne Chang <waynec@nvidia.com>
---
drivers/usb/host/xhci-tegra.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index e7e6d569f1db..7d56f35ec9e7 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -250,6 +250,7 @@ struct tegra_xusb_soc {
bool otg_set_port_power;
bool has_bar2;
+ bool enable_firmware_messages;
};
struct tegra_xusb_context {
@@ -1260,6 +1261,9 @@ static int __tegra_xusb_enable_firmware_messages(struct tegra_xusb *tegra)
struct tegra_xusb_mbox_msg msg;
int err;
+ if (!tegra->soc->enable_firmware_messages)
+ return 0;
+
/* Enable firmware messages from controller. */
msg.cmd = MBOX_CMD_MSG_ENABLED;
msg.data = 0;
@@ -2580,6 +2584,7 @@ static const struct tegra_xusb_soc tegra124_soc = {
.owner = 0xf0,
.smi_intr = XUSB_CFG_ARU_SMI_INTR,
},
+ .enable_firmware_messages = true,
};
#if IS_ENABLED(CONFIG_ARCH_TEGRA_124_SOC) || IS_ENABLED(CONFIG_ARCH_TEGRA_132_SOC)
MODULE_FIRMWARE("nvidia/tegra124/xusb.bin");
@@ -2621,6 +2626,7 @@ static const struct tegra_xusb_soc tegra210_soc = {
.owner = 0xf0,
.smi_intr = XUSB_CFG_ARU_SMI_INTR,
},
+ .enable_firmware_messages = true,
};
#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
MODULE_FIRMWARE("nvidia/tegra210/xusb.bin");
@@ -2670,6 +2676,7 @@ static const struct tegra_xusb_soc tegra186_soc = {
.smi_intr = XUSB_CFG_ARU_SMI_INTR,
},
.lpm_support = true,
+ .enable_firmware_messages = true,
};
static const char * const tegra194_supply_names[] = {
@@ -2704,6 +2711,7 @@ static const struct tegra_xusb_soc tegra194_soc = {
.smi_intr = XUSB_CFG_ARU_SMI_INTR,
},
.lpm_support = true,
+ .enable_firmware_messages = true,
};
#if IS_ENABLED(CONFIG_ARCH_TEGRA_194_SOC)
MODULE_FIRMWARE("nvidia/tegra194/xusb.bin");
@@ -2741,6 +2749,7 @@ static const struct tegra_xusb_soc tegra234_soc = {
},
.lpm_support = true,
.has_bar2 = true,
+ .enable_firmware_messages = true,
};
static const struct of_device_id tegra_xusb_of_match[] = {
--
2.25.1
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH 6/8] phy: tegra: xusb: Add Tegra264 support
From: Wayne Chang @ 2026-06-29 9:34 UTC (permalink / raw)
To: mathias.nyman, vkoul, neil.armstrong, robh, krzk+dt, conor+dt,
gregkh, thierry.reding, jonathanh
Cc: waynec, linux-usb, linux-tegra, linux-kernel, linux-phy,
devicetree
In-Reply-To: <20260629093406.1118594-1-waynec@nvidia.com>
Add support for the XUSB pad controller for Tegra264. Most of
the Tegra264 XUSB PADCTL registers definition and programming sequence
are the same as Tegra234, Tegra264 XUSB PADCTL can share the same
driver with Tegra186, Tegra194, and Tegra234 XUSB PADCTL.
Signed-off-by: Wayne Chang <waynec@nvidia.com>
---
drivers/phy/tegra/Makefile | 1 +
drivers/phy/tegra/xusb-tegra186.c | 26 +++++++++++++++++++++++++-
drivers/phy/tegra/xusb.c | 6 ++++++
drivers/phy/tegra/xusb.h | 3 +++
4 files changed, 35 insertions(+), 1 deletion(-)
diff --git a/drivers/phy/tegra/Makefile b/drivers/phy/tegra/Makefile
index eeeea72de117..33a695d4ed59 100644
--- a/drivers/phy/tegra/Makefile
+++ b/drivers/phy/tegra/Makefile
@@ -8,4 +8,5 @@ phy-tegra-xusb-$(CONFIG_ARCH_TEGRA_210_SOC) += xusb-tegra210.o
phy-tegra-xusb-$(CONFIG_ARCH_TEGRA_186_SOC) += xusb-tegra186.o
phy-tegra-xusb-$(CONFIG_ARCH_TEGRA_194_SOC) += xusb-tegra186.o
phy-tegra-xusb-$(CONFIG_ARCH_TEGRA_234_SOC) += xusb-tegra186.o
+phy-tegra-xusb-$(CONFIG_ARCH_TEGRA_264_SOC) += xusb-tegra186.o
obj-$(CONFIG_PHY_TEGRA194_P2U) += phy-tegra194-p2u.o
diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c
index 9c1bcd4a72ac..3eb60ed09b68 100644
--- a/drivers/phy/tegra/xusb-tegra186.c
+++ b/drivers/phy/tegra/xusb-tegra186.c
@@ -1668,7 +1668,8 @@ EXPORT_SYMBOL_GPL(tegra186_xusb_padctl_soc);
#endif
#if IS_ENABLED(CONFIG_ARCH_TEGRA_194_SOC) || \
- IS_ENABLED(CONFIG_ARCH_TEGRA_234_SOC)
+ IS_ENABLED(CONFIG_ARCH_TEGRA_234_SOC) || \
+ IS_ENABLED(CONFIG_ARCH_TEGRA_264_SOC)
static const char * const tegra194_xusb_padctl_supply_names[] = {
"avdd-usb",
"vclamp-usb",
@@ -1753,6 +1754,29 @@ const struct tegra_xusb_padctl_soc tegra234_xusb_padctl_soc = {
.has_per_pad_term = true,
};
EXPORT_SYMBOL_GPL(tegra234_xusb_padctl_soc);
+
+const struct tegra_xusb_padctl_soc tegra264_xusb_padctl_soc = {
+ .num_pads = ARRAY_SIZE(tegra194_pads),
+ .pads = tegra194_pads,
+ .ports = {
+ .usb2 = {
+ .ops = &tegra186_usb2_port_ops,
+ .count = 4,
+ },
+ .usb3 = {
+ .ops = &tegra186_usb3_port_ops,
+ .count = 4,
+ },
+ },
+ .ops = &tegra186_xusb_padctl_ops,
+ .supply_names = tegra194_xusb_padctl_supply_names,
+ .num_supplies = ARRAY_SIZE(tegra194_xusb_padctl_supply_names),
+ .supports_gen2 = true,
+ .poll_trk_completed = true,
+ .trk_hw_mode = true,
+ .supports_lp_cfg_en = true,
+};
+EXPORT_SYMBOL_GPL(tegra264_xusb_padctl_soc);
#endif
MODULE_AUTHOR("JC Kuo <jckuo@nvidia.com>");
diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c
index 9d74c0ecc31b..d0d0b252a205 100644
--- a/drivers/phy/tegra/xusb.c
+++ b/drivers/phy/tegra/xusb.c
@@ -77,6 +77,12 @@ static const struct of_device_id tegra_xusb_padctl_of_match[] = {
.compatible = "nvidia,tegra234-xusb-padctl",
.data = &tegra234_xusb_padctl_soc,
},
+#endif
+#if defined(CONFIG_ARCH_TEGRA_264_SOC)
+ {
+ .compatible = "nvidia,tegra264-xusb-padctl",
+ .data = &tegra264_xusb_padctl_soc,
+ },
#endif
{ }
};
diff --git a/drivers/phy/tegra/xusb.h b/drivers/phy/tegra/xusb.h
index 77609e54de66..d8d799d9e752 100644
--- a/drivers/phy/tegra/xusb.h
+++ b/drivers/phy/tegra/xusb.h
@@ -514,5 +514,8 @@ extern const struct tegra_xusb_padctl_soc tegra194_xusb_padctl_soc;
#if defined(CONFIG_ARCH_TEGRA_234_SOC)
extern const struct tegra_xusb_padctl_soc tegra234_xusb_padctl_soc;
#endif
+#if defined(CONFIG_ARCH_TEGRA_264_SOC)
+extern const struct tegra_xusb_padctl_soc tegra264_xusb_padctl_soc;
+#endif
#endif /* __PHY_TEGRA_XUSB_H */
--
2.25.1
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH 8/8] usb: host: xhci-tegra: Add Tegra264 XHCI support
From: Wayne Chang @ 2026-06-29 9:34 UTC (permalink / raw)
To: mathias.nyman, vkoul, neil.armstrong, robh, krzk+dt, conor+dt,
gregkh, thierry.reding, jonathanh
Cc: waynec, linux-usb, linux-tegra, linux-kernel, linux-phy,
devicetree
In-Reply-To: <20260629093406.1118594-1-waynec@nvidia.com>
This change adds Tegra264 XUSB host mode controller support.
The host controller is very similar to the existing Tegra234 XHCI,
except the number of max_num_wakes.
Signed-off-by: Wayne Chang <waynec@nvidia.com>
---
drivers/usb/host/xhci-tegra.c | 28 ++++++++++++++++++++++++++++
1 file changed, 28 insertions(+)
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index 7d56f35ec9e7..9a55d5818efb 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -2752,12 +2752,40 @@ static const struct tegra_xusb_soc tegra234_soc = {
.enable_firmware_messages = true,
};
+static const struct tegra_xusb_soc tegra264_soc = {
+ .supply_names = tegra194_supply_names,
+ .num_supplies = ARRAY_SIZE(tegra194_supply_names),
+ .phy_types = tegra194_phy_types,
+ .num_types = ARRAY_SIZE(tegra194_phy_types),
+ .max_num_wakes = 8,
+ .context = &tegra186_xusb_context,
+ .ports = {
+ .usb3 = { .offset = 0, .count = 4, },
+ .usb2 = { .offset = 4, .count = 4, },
+ },
+ .scale_ss_clock = false,
+ .has_ipfs = false,
+ .otg_reset_sspi = false,
+ .ops = &tegra234_ops,
+ .mbox = {
+ .cmd = XUSB_BAR2_ARU_MBOX_CMD,
+ .data_in = XUSB_BAR2_ARU_MBOX_DATA_IN,
+ .data_out = XUSB_BAR2_ARU_MBOX_DATA_OUT,
+ .owner = XUSB_BAR2_ARU_MBOX_OWNER,
+ .smi_intr = XUSB_BAR2_ARU_SMI_INTR,
+ },
+ .lpm_support = true,
+ .has_bar2 = true,
+ .enable_firmware_messages = false,
+};
+
static const struct of_device_id tegra_xusb_of_match[] = {
{ .compatible = "nvidia,tegra124-xusb", .data = &tegra124_soc },
{ .compatible = "nvidia,tegra210-xusb", .data = &tegra210_soc },
{ .compatible = "nvidia,tegra186-xusb", .data = &tegra186_soc },
{ .compatible = "nvidia,tegra194-xusb", .data = &tegra194_soc },
{ .compatible = "nvidia,tegra234-xusb", .data = &tegra234_soc },
+ { .compatible = "nvidia,tegra264-xusb", .data = &tegra264_soc },
{ },
};
MODULE_DEVICE_TABLE(of, tegra_xusb_of_match);
--
2.25.1
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* Re: [PATCH 3/8] arm64: tegra: Enable XUSB host function on Jetson AGX Thor
From: sashiko-bot @ 2026-06-29 9:44 UTC (permalink / raw)
To: Wayne Chang
Cc: vkoul, neil.armstrong, olteanv, linux-phy, conor+dt, robh,
devicetree
In-Reply-To: <20260629093406.1118594-4-waynec@nvidia.com>
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] The device tree nodes use `GIC_SPI 4096` and `GIC_SPI 4101` which incorrectly parse as hardware IRQs 4128 and 4133 due to the SPI offset of 32.
--
commit 0e16479e341627ad9fb569ac2ccd54f1ef421b1f
Author: Wayne Chang <waynec@nvidia.com>
arm64: tegra: Enable XUSB host function on Jetson AGX Thor
This commit enables XUSB host and pad controller on Jetson AGX Thor.
> diff --git a/arch/arm64/boot/dts/nvidia/tegra264.dtsi b/arch/arm64/boot/dts/nvidia/tegra264.dtsi
> index 2d8e7e37830ff..3433587dc5725 100644
> --- a/arch/arm64/boot/dts/nvidia/tegra264.dtsi
> +++ b/arch/arm64/boot/dts/nvidia/tegra264.dtsi
> @@ -4049,6 +4049,160 @@ pci@8480000 {
> nvidia,bpmp = <&bpmp 5>;
> status = "disabled";
> };
> +
> + xusb_padctl: padctl@8680000 {
> + compatible = "nvidia,tegra264-xusb-padctl";
> + reg = <0x00 0x8680000 0x00 0x20000>,
> + <0x00 0x86a0000 0x00 0x10000>;
> + reg-names = "padctl", "ao";
> + interrupts = <GIC_SPI 4101 IRQ_TYPE_LEVEL_HIGH>;
[Severity: High]
Does this map to the correct hardware IRQ? Using the GIC_SPI macro for an
ESPI INTID adds an offset of 32, mapping to hwirq 4133 instead of 4101.
The kernel will emit boot warnings about the SPI being out of range.
Should this be replaced with <GIC_ESPI 5 IRQ_TYPE_LEVEL_HIGH>?
[ ... ]
> + usb@aa10000 {
> + compatible = "nvidia,tegra264-xusb";
> + reg = <0x00 0xaa10000 0x00 0x40000>,
> + <0x00 0xaa00000 0x00 0x10000>,
> + <0x00 0xaa50000 0x00 0x10000>;
> + reg-names = "hcd", "fpci", "bar2";
> +
> + interrupts-extended = <&gic GIC_SPI 952 IRQ_TYPE_LEVEL_HIGH>,
> + <&gic GIC_SPI 4096 IRQ_TYPE_LEVEL_HIGH>,
[Severity: High]
Similar to the regression above, does this sequence map correctly? Using the
GIC_SPI macro adds an offset of 32, which maps to hwirq 4128 instead of 4096.
Should this be replaced with <GIC_ESPI 0 IRQ_TYPE_LEVEL_HIGH>?
[ ... ]
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260629093406.1118594-1-waynec@nvidia.com?part=3
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH 6/8] phy: tegra: xusb: Add Tegra264 support
From: sashiko-bot @ 2026-06-29 9:45 UTC (permalink / raw)
To: Wayne Chang
Cc: olteanv, vkoul, conor+dt, neil.armstrong, linux-phy, robh,
devicetree
In-Reply-To: <20260629093406.1118594-7-waynec@nvidia.com>
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Medium] Missing `.has_per_pad_term = true` for `tegra264_xusb_padctl_soc` leads to incorrect USB2 PHY termination calibration.
- [Low] Missing prototype compiler warning for `tegra264_xusb_padctl_soc` when its specific config is disabled.
--
commit 22b0fd28aa94a55231606c8cbbf28effe50f3f35
Author: Wayne Chang <waynec@nvidia.com>
phy: tegra: xusb: Add Tegra264 support
Add support for the XUSB pad controller for Tegra264. Most of the Tegra264
XUSB PADCTL registers definition and programming sequence are the same as
Tegra234, and they can share the same driver.
> diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c
> index 9c1bcd4a72ac6..3eb60ed09b687 100644
> --- a/drivers/phy/tegra/xusb-tegra186.c
> +++ b/drivers/phy/tegra/xusb-tegra186.c
[ ... ]
> @@ -1753,6 +1754,29 @@ const struct tegra_xusb_padctl_soc tegra234_xusb_padctl_soc = {
> .has_per_pad_term = true,
> };
> EXPORT_SYMBOL_GPL(tegra234_xusb_padctl_soc);
> +
> +const struct tegra_xusb_padctl_soc tegra264_xusb_padctl_soc = {
> + .num_pads = ARRAY_SIZE(tegra194_pads),
> + .pads = tegra194_pads,
> + .ports = {
> + .usb2 = {
> + .ops = &tegra186_usb2_port_ops,
> + .count = 4,
> + },
> + .usb3 = {
> + .ops = &tegra186_usb3_port_ops,
> + .count = 4,
> + },
> + },
> + .ops = &tegra186_xusb_padctl_ops,
> + .supply_names = tegra194_xusb_padctl_supply_names,
> + .num_supplies = ARRAY_SIZE(tegra194_xusb_padctl_supply_names),
> + .supports_gen2 = true,
> + .poll_trk_completed = true,
> + .trk_hw_mode = true,
> + .supports_lp_cfg_en = true,
> +};
[Severity: Medium]
Since the commit message states Tegra264 shares the same programming sequence
as Tegra234, should this struct also include .has_per_pad_term = true?
Without this flag, tegra186_xusb_read_fuse_calibration() will default to
copying pad 0's calibration to pads 1-3 instead of reading their specific
hardware values.
> +EXPORT_SYMBOL_GPL(tegra264_xusb_padctl_soc);
> #endif
>
> MODULE_AUTHOR("JC Kuo <jckuo@nvidia.com>");
[ ... ]
> diff --git a/drivers/phy/tegra/xusb.h b/drivers/phy/tegra/xusb.h
> index 77609e54de66a..d8d799d9e7522 100644
> --- a/drivers/phy/tegra/xusb.h
> +++ b/drivers/phy/tegra/xusb.h
> @@ -514,5 +514,8 @@ extern const struct tegra_xusb_padctl_soc tegra194_xusb_padctl_soc;
> #if defined(CONFIG_ARCH_TEGRA_234_SOC)
> extern const struct tegra_xusb_padctl_soc tegra234_xusb_padctl_soc;
> #endif
> +#if defined(CONFIG_ARCH_TEGRA_264_SOC)
> +extern const struct tegra_xusb_padctl_soc tegra264_xusb_padctl_soc;
> +#endif
[Severity: Low]
Does this create a missing prototype warning (-Wmissing-prototypes) when
building with CONFIG_ARCH_TEGRA_194_SOC=y but CONFIG_ARCH_TEGRA_264_SOC=n?
In xusb-tegra186.c, tegra264_xusb_padctl_soc is defined unconditionally if
any of the 194, 234, or 264 configs are enabled. However, the extern
declaration here in xusb.h is only visible if CONFIG_ARCH_TEGRA_264_SOC is set.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260629093406.1118594-1-waynec@nvidia.com?part=6
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH 4/8] phy: tegra: xusb: Use devm_clk_get_optional to fetch USB2 tracking clock
From: sashiko-bot @ 2026-06-29 9:46 UTC (permalink / raw)
To: Wayne Chang
Cc: neil.armstrong, linux-phy, vkoul, devicetree, olteanv, robh,
conor+dt
In-Reply-To: <20260629093406.1118594-5-waynec@nvidia.com>
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
Pre-existing issues:
- [High] Double free of pad allocations on `tegra_xusb_pad_init()` failure due to incorrect device cleanup.
- [High] Kernel panic due to NULL pointer dereference in `tegra_xusb_port_release()` when port initialization fails.
--
commit 9a7eb66c6206c1b8eab420ee00c7a1d273a708fe
Author: Sing-Han Chen <singhanc@nvidia.com>
Subject: phy: tegra: xusb: Use devm_clk_get_optional to fetch USB2 tracking clock
This patch switches the USB2 tracking clock retrieval to use
devm_clk_get_optional. This allows the probe sequence to proceed safely
when the clock is omitted from the devicetree.
> diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c
> index 60156aea27071..800be0cbb3f9f 100644
> --- a/drivers/phy/tegra/xusb-tegra186.c
> +++ b/drivers/phy/tegra/xusb-tegra186.c
> @@ -1045,7 +1045,7 @@ tegra186_usb2_pad_probe(struct tegra_xusb_padctl *padctl,
> goto out;
> }
[Severity: High]
This isn't a bug introduced by this patch, but does the error path for
tegra_xusb_pad_init() just above this change cause a double free?
Looking at tegra186_usb2_pad_probe(), if tegra_xusb_pad_init() fails, it
calls kfree(usb2).
However, inside tegra_xusb_pad_init(), an error causes it to jump to the
unregister label and call device_unregister(&pad->dev). This drops the
device reference and invokes the release callback tegra_xusb_pad_release(),
which frees the pad object.
When tegra_xusb_pad_init() returns the error back to the probe function, the
explicit kfree(usb2) is executed. Could this lead to memory corruption when
initialization fails?
>
> - priv->usb2_trk_clk = devm_clk_get(&pad->dev, "trk");
> + priv->usb2_trk_clk = devm_clk_get_optional(&pad->dev, "trk");
> if (IS_ERR(priv->usb2_trk_clk)) {
> err = PTR_ERR(priv->usb2_trk_clk);
> dev_dbg(&pad->dev, "failed to get usb2 trk clock: %d\n", err);
[ ... ]
[Severity: High]
This is another pre-existing issue in a related file, but does
tegra_xusb_port_release() trigger a NULL pointer dereference on
initialization failure?
In drivers/phy/tegra/xusb.c:tegra_xusb_add_usb2_port(), the port is
allocated via kzalloc() and then initialized:
err = tegra_xusb_port_init(&usb2->base, padctl, np, "usb2", index);
if (err < 0)
goto out;
usb2->base.ops = padctl->soc->ports.usb2.ops;
Notice that the ops pointer is assigned after initialization completes.
If tegra_xusb_port_init() fails, it drops the device refcount and calls
tegra_xusb_port_release(). That release function attempts to evaluate the
ops pointer:
if (port->ops->release)
port->ops->release(port);
Since port->ops is not yet assigned during the init error path, it will
still be NULL from the kzalloc() allocation. Could this cause a panic when
initialization fails?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260629093406.1118594-1-waynec@nvidia.com?part=4
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH 8/8] usb: host: xhci-tegra: Add Tegra264 XHCI support
From: sashiko-bot @ 2026-06-29 9:47 UTC (permalink / raw)
To: Wayne Chang
Cc: olteanv, vkoul, robh, neil.armstrong, devicetree, linux-phy,
conor+dt
In-Reply-To: <20260629093406.1118594-9-waynec@nvidia.com>
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] The `tegra264_soc` struct explicitly sets `enable_firmware_messages` to `false`, contradicting the commit message that claims the only difference from `tegra234_soc` is `max_num_wakes`.
--
commit f38c91ea7436bccae268e6611e1931cff02f07ec
Author: Wayne Chang <waynec@nvidia.com>
usb: host: xhci-tegra: Add Tegra264 XHCI support
This commit adds XUSB host mode controller support for the Tegra264 SoC.
It defines a new tegra_xusb_soc struct for Tegra264 and adds it to the
OF match table.
> The host controller is very similar to the existing Tegra234 XHCI,
> except the number of max_num_wakes.
[ ... ]
> diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
> index 7d56f35ec9e71..9a55d5818efb0 100644
> --- a/drivers/usb/host/xhci-tegra.c
> +++ b/drivers/usb/host/xhci-tegra.c
[ ... ]
> @@ -2752,12 +2752,40 @@ static const struct tegra_xusb_soc tegra234_soc = {
[ ... ]
> +static const struct tegra_xusb_soc tegra264_soc = {
[ ... ]
> + .lpm_support = true,
> + .has_bar2 = true,
> + .enable_firmware_messages = false,
[Severity: Medium]
Is this value intentional?
The commit message states that the only difference from Tegra234 is
max_num_wakes, but tegra234_soc sets enable_firmware_messages to true.
Setting this to false means the driver will skip sending the
MBOX_CMD_MSG_ENABLED command to the controller via
__tegra_xusb_enable_firmware_messages() during initialization.
If Tegra264 requires these messages for clock scaling or power management
like Tegra234 does, this omission might lead to performance or power
management issues. Could you clarify if this should be true, or update the
commit message to reflect this difference?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260629093406.1118594-1-waynec@nvidia.com?part=8
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH v2 1/4] dt-bindings: reset: nuvoton,ma35d1-reset: add simple-mfd and child node support
From: Joey Lu @ 2026-06-29 9:48 UTC (permalink / raw)
To: Krzysztof Kozlowski
Cc: Vinod Koul, Neil Armstrong, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Arnd Bergmann, Catalin Marinas, Jacky Huang,
Shan-Chun Hung, Hui-Ping Chen, Joey Lu, linux-phy, devicetree,
linux-arm-kernel, linux-kernel
In-Reply-To: <20260625-striped-demonic-jerboa-502afb@quoll>
On 6/25/2026 3:51 PM, Krzysztof Kozlowski wrote:
> On Thu, Jun 25, 2026 at 10:39:55AM +0800, Joey Lu wrote:
>> The MA35D1 system-management syscon node hosts the USB PHY register
>> block at offset 0x60. To model usb-phy@60 as a DT child of the syscon
>> node the binding must allow:
> Explain why do you need child node. If you have fixed device @0x60, you do
> not need DT child node at all. Compatible implies that child existence.
The commit message will be rewritten to state the motivation: the USB PHY
register block at offset 0x60 needs a referenceable DT node because consumer
drivers (dwc2, ehci0/ohci0, ehci1/ohci1) look it up via `phys =
<&usb_phy N>`,
which requires an explicit node with a phandle. Optional per-board
calibration
properties (`nuvoton,rcalcode`, `nuvoton,oc-active-high`) also need to be
expressed in DT.
>
>> - simple-mfd as an optional third compatible so the MFD core can
>> instantiate child platform devices.
>>
>> - #address-cells and #size-cells (each const: 1) so child nodes can
>> carry a reg property.
>>
>> - An open child-node pattern (patternProperties "^.*@[0-9a-f]+$")
>> to pass dt-schema validation.
> No. Do not explain what you did - we can read the diff. You must explain
> WHY you are doing that.
Addressed above.
>> Signed-off-by: Joey Lu <a0987203069@gmail.com>
>> ---
>> .../bindings/reset/nuvoton,ma35d1-reset.yaml | 13 ++++++++++++-
>> 1 file changed, 12 insertions(+), 1 deletion(-)
>>
>> diff --git a/Documentation/devicetree/bindings/reset/nuvoton,ma35d1-reset.yaml b/Documentation/devicetree/bindings/reset/nuvoton,ma35d1-reset.yaml
>> index 3ce7dcecd87a..1fda7e8f4b5d 100644
>> --- a/Documentation/devicetree/bindings/reset/nuvoton,ma35d1-reset.yaml
>> +++ b/Documentation/devicetree/bindings/reset/nuvoton,ma35d1-reset.yaml
>> @@ -19,6 +19,8 @@ properties:
>> items:
>> - const: nuvoton,ma35d1-reset
>> - const: syscon
>> + - const: simple-mfd
>> + minItems: 2
>>
>> reg:
>> maxItems: 1
>> @@ -26,6 +28,16 @@ properties:
>> '#reset-cells':
>> const: 1
>>
>> + '#address-cells':
>> + const: 1
>> +
>> + '#size-cells':
>> + const: 1
>> +
>> +patternProperties:
>> + "^.*@[0-9a-f]+$":
> This must be specific.
The `patternProperties` key will be changed from `"^.*@[0-9a-f]+$"` to
`"^usb-phy@[0-9a-f]+$"` so it matches only USB PHY child nodes,
following the
naming convention used by existing vendor bindings.
>> + type: object
> Missing ref and additionalProps. Please look at other simple-mfd.
`$ref: /schemas/phy/nuvoton,ma35d1-usb2-phy.yaml#` will be added under the
patternProperties entry, alongside `type: object`, so the child node will be
validated against the PHY binding schema. This follows the pattern used by
existing vendor bindings.
Thanks for review.
>> +
>> required:
>> - compatible
>> - reg
>> @@ -43,4 +55,3 @@ examples:
>> #reset-cells = <1>;
>> };
>> ...
>> -
>> --
>> 2.43.0
>>
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH v2 2/4] dt-bindings: phy: nuvoton,ma35d1-usb2-phy: extend for dual-port OTG support
From: Joey Lu @ 2026-06-29 10:40 UTC (permalink / raw)
To: Krzysztof Kozlowski
Cc: Vinod Koul, Neil Armstrong, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Arnd Bergmann, Catalin Marinas, Jacky Huang,
Shan-Chun Hung, Hui-Ping Chen, Joey Lu, linux-phy, devicetree,
linux-arm-kernel, linux-kernel
In-Reply-To: <20260625-sexy-black-tarantula-4031a6@quoll>
On 6/25/2026 3:58 PM, Krzysztof Kozlowski wrote:
> On Thu, Jun 25, 2026 at 10:39:56AM +0800, Joey Lu wrote:
>> properties:
>> compatible:
>> enum:
>> - nuvoton,ma35d1-usb2-phy
>>
>> + reg:
>> + maxItems: 1
>> +
>> "#phy-cells":
>> - const: 0
>> + const: 1
>> + description:
>> + The single cell selects the PHY port. 0 selects the OTG port (USB0,
>> + shared with DWC2 gadget controller) and 1 selects the host-only port
>> + (USB1).
>>
>> - clocks:
>> - maxItems: 1
> This is odd, considering that parent does not have clocks. So explain me
> this:
> 1. USB PHY needed clocks.
> 2. You extend USB PHY to cover second part.
> 3. That extension for second part means that clocks are not needed.
> Really, how? How is it possible in hardware?
The hardware has two independent clock domains:
- The PHY analog block takes the 24 MHz HXT as its reference, wired
directly to the PHY's internal PLL, which derives the required
operating
frequencies internally. This reference path is entirely outside the SoC
software clock tree; no software-gatable clock gate needs to be enabled
for the PHY to power up and lock its PLL. The only software control the
PHY driver exercises is toggling each PHY's Power-On Reset (POR) bit,
which resides in the SYS register block. The driver accesses this via
the parent regmap
- `HUSBH0_GATE` / `HUSBH1_GATE` / `USBD_GATE` are AHB/APB bus interface
clocks for the host and gadget (EHCI, OHCI, DWC2). They gate
the register-access path between the CPU and each controller, not
the PHY
analog circuitry itself.
The original single-port driver enabled `HUSBH0_GATE` as if it belonged
to the
PHY, but that gate is actually owned by EHCI0/OHCI0 and is already
managed by
those controller drivers through their own `clocks` DTS bindings. The PHY
driver was redundantly enabling the same gate.
When extending the driver to cover PHY1, the same pattern held: EHCI1/OHCI1
manage `HUSBH1_GATE` themselves. There is no clock that belongs
exclusively to
the PHY, so `clocks` will be dropped from the PHY binding entirely.
>> + nuvoton,rcalcode:
>> + $ref: /schemas/types.yaml#/definitions/uint32-array
>> + minItems: 1
>> + maxItems: 2
> You should require two values. I understand that any PHY is optional,
> thus you skip the entry, so how would you provide value for PHY1 only?
`nuvoton,rcalcode` will be changed to require exactly two values
(`minItems: 2, maxItems: 2`), one for PHY0 and one for PHY1 respectively.
The property will remain optional overall; when absent, each port
retains its
power-on default value loaded at hardware initialisation. When present, both
entries must be supplied.
>> + items:
>> + minimum: 0
>> + maximum: 15
>> + description:
>> + Resistor calibration trim codes for PHY0 and PHY1 respectively.
>> + Each 4-bit value is written to the RCALCODE field in USBPMISCR and
>> + adjusts the PHY's internal termination resistance. Both entries are
>> + optional; when absent the hardware reset default is used.
>>
>> - nuvoton,sys:
>> - $ref: /schemas/types.yaml#/definitions/phandle
>> + nuvoton,oc-active-high:
>> + type: boolean
>> description:
>> - phandle to syscon for checking the PHY clock status.
>> + When present, the over-current detect input from the VBUS power switch
>> + is treated as active-high. The default (property absent) is active-low.
>> + This setting is shared by both USB host ports.
>>
>> required:
>> - compatible
>> + - reg
> That's ABI break which was not explained in the commit msg - neither
> specifying impact nor actually providing reasons why you break ABI.
>
> And honestly, you have no resources here except the address, so now it
> is clear that this should be folded into parent. See DTS101 talk slides.
The commit message will be updated to explicitly acknowledge the ABI break:
existing DTS files that contain a standalone `usb-phy` node without a `reg`
property will fail dt-schema validation after this change. The impact is
limited to the MA35D1 SoC; no upstream DTS for this SoC existed before this
patch series, so no in-tree board files are broken. The break is intentional
and justified: the PHY register block is physically contained within the
syscon
MMIO range, and modelling it as a child of the syscon with a standard `reg`
property correctly reflects the hardware topology and follows the convention
established by similar sub-blocks in other SoCs.
>> - "#phy-cells"
>> - - clocks
>> - - nuvoton,sys
>>
>> additionalProperties: false
>>
>> examples:
>> - |
>> - #include <dt-bindings/clock/nuvoton,ma35d1-clk.h>
>> + system-management@40460000 {
>> + compatible = "nuvoton,ma35d1-reset", "syscon", "simple-mfd";
>> + reg = <0x40460000 0x200>;
>> + #reset-cells = <1>;
>> + #address-cells = <1>;
>> + #size-cells = <1>;
> Drop. Keep only child node and make parent binding example complete.
The example in `nuvoton,ma35d1-usb2-phy.yaml` will be changed to show only
the `usb-phy@60` child node, without wrapping it in the parent node.
The full parent + child example will be moved to
`nuvoton,ma35d1-reset.yaml`.
Thanks for review.
>>
>> - usb_phy: usb-phy {
>> - compatible = "nuvoton,ma35d1-usb2-phy";
>> - clocks = <&clk USBD_GATE>;
>> - nuvoton,sys = <&sys>;
>> - #phy-cells = <0>;
>> + usb-phy@60 {
>> + compatible = "nuvoton,ma35d1-usb2-phy";
>> + reg = <0x60 0x14>;
>> + #phy-cells = <1>;
>> + };
>> };
>> --
>> 2.43.0
>>
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH v2 0/3] phy: qcom: qmp-pcie: Add vdda-refgen supply support for Glymur
From: Konrad Dybcio @ 2026-06-29 10:51 UTC (permalink / raw)
To: Qiang Yu, Vinod Koul, Neil Armstrong, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Bjorn Andersson, Konrad Dybcio
Cc: linux-arm-msm, linux-phy, devicetree, linux-kernel
In-Reply-To: <20260623-phy_refgen-v2-0-4d15983bf91d@oss.qualcomm.com>
On 6/23/26 3:05 PM, Qiang Yu wrote:
> The PCIe QMP PHYs on Glymur require both refgen for stable reference
> voltage and qref for stable reference clock. The refgen requires two power
> supplies: vdda-refgen0p9 and vdda-refgen1p2.
>
> can be extended in the future.
>
> This series creates a Glymur-specific supply list including the refgen
> supplies and updates both Gen5x4 and Gen4x2 configurations to use it.
>
> Signed-off-by: Qiang Yu <qiang.yu@oss.qualcomm.com>
>
> Changes in v2:
> - Add dts patch in this series.
> - Reword commit msg of dtbinding patch.
> - Link to v1: https://lore.kernel.org/all/20260208-refgen-v1-0-87ca84fd78b3@oss.qualcomm.com/
>
> ---
Is this necessary (for Glymur) now that we correlated some of the
TCSR clocks with the right nodes?
Perhaps this would be necessary for Mahua since its clocks don't
require QREF (or we can lie about it and handle them there)?
Konrad
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH v2 0/3] phy: qcom: qmp-pcie: Add vdda-refgen supply support for Glymur
From: Qiang Yu @ 2026-06-29 12:14 UTC (permalink / raw)
To: Konrad Dybcio
Cc: Vinod Koul, Neil Armstrong, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Bjorn Andersson, Konrad Dybcio, linux-arm-msm,
linux-phy, devicetree, linux-kernel
In-Reply-To: <8811c181-9caf-4797-8e17-52311702e292@oss.qualcomm.com>
On Mon, Jun 29, 2026 at 12:51:55PM +0200, Konrad Dybcio wrote:
> On 6/23/26 3:05 PM, Qiang Yu wrote:
> > The PCIe QMP PHYs on Glymur require both refgen for stable reference
> > voltage and qref for stable reference clock. The refgen requires two power
> > supplies: vdda-refgen0p9 and vdda-refgen1p2.
> >
> > can be extended in the future.
> >
> > This series creates a Glymur-specific supply list including the refgen
> > supplies and updates both Gen5x4 and Gen4x2 configurations to use it.
> >
> > Signed-off-by: Qiang Yu <qiang.yu@oss.qualcomm.com>
> >
> > Changes in v2:
> > - Add dts patch in this series.
> > - Reword commit msg of dtbinding patch.
> > - Link to v1: https://lore.kernel.org/all/20260208-refgen-v1-0-87ca84fd78b3@oss.qualcomm.com/
> >
> > ---
>
> Is this necessary (for Glymur) now that we correlated some of the
> TCSR clocks with the right nodes?
This patch is necessary for glymur and mahua and other Qualcomm targets,
which can be verified from the REFGEN page and power grid page on ipcat.
Take Glymur PCIe3 PHY as an example: it requires two REFGENs — REFGEN0 for
the PHY itself and REFGEN4 for QREF. In the TCSR driver, only the LDOs for
REFGEN4 are voted, not REFGEN0. This is intentional: each consumer is
responsible for voting the LDOs of the REFGEN it uses. Since QREF uses
REFGEN4, the TCSR driver votes the REFGEN4 LDOs; since the PHY uses
REFGEN0, the PHY driver votes the REFGEN0 LDOs.
For some PHY instances in power grid, you can only see one REFGEN, that
indicates the phy doesn't require QREF or the phy and the QREF it requires
share same REFGEN.
>
> Perhaps this would be necessary for Mahua since its clocks don't
> require QREF (or we can lie about it and handle them there)?
For Mahua PCIe5 PHY, it doesn't require QREF. So we don't need to vote
REFGEN LDOs for QREF in tcsr driver. But the PHY requires REFGEN. So we
still need to vote in PHY driver.
- Qiang Yu
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH v2 0/3] phy: qcom: qmp-pcie: Add vdda-refgen supply support for Glymur
From: Konrad Dybcio @ 2026-06-29 12:18 UTC (permalink / raw)
To: Qiang Yu
Cc: Vinod Koul, Neil Armstrong, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Bjorn Andersson, Konrad Dybcio, linux-arm-msm,
linux-phy, devicetree, linux-kernel
In-Reply-To: <akJhrpyMuLnoXzJM@hu-qianyu-lv.qualcomm.com>
On 6/29/26 2:14 PM, Qiang Yu wrote:
> On Mon, Jun 29, 2026 at 12:51:55PM +0200, Konrad Dybcio wrote:
>> On 6/23/26 3:05 PM, Qiang Yu wrote:
>>> The PCIe QMP PHYs on Glymur require both refgen for stable reference
>>> voltage and qref for stable reference clock. The refgen requires two power
>>> supplies: vdda-refgen0p9 and vdda-refgen1p2.
>>>
>>> can be extended in the future.
>>>
>>> This series creates a Glymur-specific supply list including the refgen
>>> supplies and updates both Gen5x4 and Gen4x2 configurations to use it.
>>>
>>> Signed-off-by: Qiang Yu <qiang.yu@oss.qualcomm.com>
>>>
>>> Changes in v2:
>>> - Add dts patch in this series.
>>> - Reword commit msg of dtbinding patch.
>>> - Link to v1: https://lore.kernel.org/all/20260208-refgen-v1-0-87ca84fd78b3@oss.qualcomm.com/
>>>
>>> ---
>>
>> Is this necessary (for Glymur) now that we correlated some of the
>> TCSR clocks with the right nodes?
>
> This patch is necessary for glymur and mahua and other Qualcomm targets,
> which can be verified from the REFGEN page and power grid page on ipcat.
>
> Take Glymur PCIe3 PHY as an example: it requires two REFGENs — REFGEN0 for
> the PHY itself and REFGEN4 for QREF. In the TCSR driver, only the LDOs for
> REFGEN4 are voted, not REFGEN0. This is intentional: each consumer is
> responsible for voting the LDOs of the REFGEN it uses. Since QREF uses
> REFGEN4, the TCSR driver votes the REFGEN4 LDOs; since the PHY uses
> REFGEN0, the PHY driver votes the REFGEN0 LDOs.
>
> For some PHY instances in power grid, you can only see one REFGEN, that
> indicates the phy doesn't require QREF or the phy and the QREF it requires
> share same REFGEN.
>>
>> Perhaps this would be necessary for Mahua since its clocks don't
>> require QREF (or we can lie about it and handle them there)?
>
> For Mahua PCIe5 PHY, it doesn't require QREF. So we don't need to vote
> REFGEN LDOs for QREF in tcsr driver. But the PHY requires REFGEN. So we
> still need to vote in PHY driver.
OK, I think I got my mental model of all of this straight. But expect
me to make more mistakes and sorry for that!
Konrad
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH net v5 2/2] Revert "net: phy: sfp: probe for RollBall I2C-to-MDIO bridge in mdio-i2c"
From: Maxime Chevallier @ 2026-06-29 12:23 UTC (permalink / raw)
To: Petr Wozniak, linux, andrew, hkallweit1
Cc: kuba, davem, edumazet, pabeni, netdev, linux-kernel, linux-phy,
bjorn, olek2, kabel
In-Reply-To: <23e3931915c3ed2a14cec95f1490e43d30b225e8.1782581445.git.petr.wozniak@gmail.com>
Hi Petr,
On 6/27/26 19:32, Petr Wozniak wrote:
> This reverts commit 8fe125892f40 ("net: phy: sfp: probe for RollBall
> I2C-to-MDIO bridge in mdio-i2c").
>
> That commit added a RollBall bridge probe at MDIO bus creation time, in
> i2c_mii_init_rollball(), to avoid a multi-minute PHY probe retry loop on
> modules without a bridge (e.g. RTL8261BE). The probe runs in SFP_S_INIT,
> before genuine RollBall modules have finished their firmware/bridge
> initialization, so the bridge does not yet answer CMD_READ/CMD_DONE. The
> probe times out, mdio_protocol is set to MDIO_I2C_NONE, and PHY detection
> is then skipped for genuine RollBall modules that worked before the commit.
>
> This was confirmed on hardware by Maxime Chevallier and Aleksander
> Bajkowski: their RollBall modules no longer detect a PHY, and work again
> on v7.0 (before the bridge probing was introduced). The Sashiko static
> review flagged the same path.
>
> Deferring the probe to PHY discovery time does not fix it either: at that
> point a slow module may still be initializing, so the probe still returns
> -ENODEV. A proper fix needs per-module init timing (a longer module_t_wait
> or a per-module quirk, per SFF-8472 the host must also wait at least 300 ms
> after insertion), which requires genuine RollBall hardware to develop and
> validate. Revert to restore the previous, working behaviour in the meantime.
Sorry this didn't work out :(
>
> The RTL8261BE retry-loop latency that the reverted commit addressed is
> handled in our downstream tree, so reverting upstream is safe on our side.
>
> Fixes: 8fe125892f40 ("net: phy: sfp: probe for RollBall I2C-to-MDIO bridge in mdio-i2c")
> Reported-by: Aleksander Bajkowski <olek2@wp.pl>
> Suggested-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
> Link: https://lore.kernel.org/netdev/20260624084814.20972-1-petr.wozniak@gmail.com/
> Signed-off-by: Petr Wozniak <petr.wozniak@gmail.com>
I confirm this restores rollball PHY detection on my side.
Thanks,
Tested-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Maxime
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* [PATCH 00/13] treewide: replace linux/gpio.h
From: Arnd Bergmann @ 2026-06-29 13:26 UTC (permalink / raw)
To: linux-gpio
Cc: Arnd Bergmann, Bartosz Golaszewski, Andrew Lunn,
Sebastian Hesselbarth, Gregory Clement, Frank Li, Robert Jarzmik,
Krzysztof Kozlowski, Greg Ungerer, Thomas Bogendoerfer,
Hauke Mehrtens, Rafał Miłecki, Yoshinori Sato,
John Paul Adrian Glaubitz, Linus Walleij, Dmitry Torokhov,
Jakub Kicinski, Paolo Abeni, Dominik Brodowski, linux-kernel,
linux-arm-kernel, linux-samsung-soc, patches, linux-m68k,
linux-mips, linux-sh, linux-input, linux-media, netdev,
linux-sunxi, linux-phy, linux-rockchip, linux-sound
From: Arnd Bergmann <arnd@arndb.de>
The linux/gpio.h header used to be the global definition for the gpio
interfaces, with 1100 users back in linux-3.17. In linux-7.2, only about
130 of those remain, so this series cleans out the rest.
In each subsystem, we can replace the header either with
linux/gpio/consumer.h for users of the modern gpio descriptor interface,
or linux/gpio/legacy.h for the few remaining users of the old number
based interface.
All patches in this series can get applied independently, so my
preference would be for each subsystem maintainer to apply these
directly, with the rest going into the gpio tree at some point.
The final patch here obviously needs to wait for all the others
to get merged first.
Arnd
Arnd Bergmann (13):
ARM: replace linux/gpio.h inclusions
m68k/coldfire: replace linux/gpio.h inclusions
mips: replace linux/gpio.h inclusions
sh: replace linux/gpio.h inclusions
mfd: replace linux/gpio.h inclusions
[net-next] net: replace linux/gpio.h inclusions
ASoC: replace linux/gpio.h inclusions
pcmcia: replace linux/gpio.h inclusions
phy: replace linux/gpio.h inclusions
media: replace linux/gpio.h inclusions
Input: matrix_keyboard - replace linux/gpio.h inclusion
gpib: gpio: replace linux/gpio.h inclusion
gpiolib: remove linux/gpio.h
MAINTAINERS | 1 -
arch/arm/mach-davinci/da850.c | 2 +-
arch/arm/mach-dove/mpp.c | 2 +-
arch/arm/mach-mv78xx0/buffalo-wxl-setup.c | 2 +-
arch/arm/mach-mv78xx0/irq.c | 2 +-
arch/arm/mach-mv78xx0/mpp.c | 2 +-
arch/arm/mach-mvebu/pm.c | 2 +-
arch/arm/mach-mxs/mach-mxs.c | 2 +-
arch/arm/mach-orion5x/board-d2net.c | 2 +-
arch/arm/mach-orion5x/board-rd88f5182.c | 2 +-
arch/arm/mach-orion5x/dns323-setup.c | 2 +-
arch/arm/mach-orion5x/irq.c | 2 +-
arch/arm/mach-orion5x/kurobox_pro-setup.c | 2 +-
arch/arm/mach-orion5x/mv2120-setup.c | 2 +-
arch/arm/mach-orion5x/net2big-setup.c | 2 +-
.../arm/mach-orion5x/terastation_pro2-setup.c | 2 +-
arch/arm/mach-orion5x/ts209-setup.c | 2 +-
arch/arm/mach-orion5x/ts409-setup.c | 2 +-
arch/arm/mach-pxa/am200epd.c | 2 +-
arch/arm/mach-pxa/am300epd.c | 2 +-
arch/arm/mach-pxa/generic.c | 2 +-
arch/arm/mach-pxa/gumstix.c | 2 +-
arch/arm/mach-pxa/mfp-pxa2xx.c | 2 +-
arch/arm/mach-pxa/pxa25x.c | 2 +-
arch/arm/mach-pxa/pxa27x.c | 2 +-
arch/arm/mach-pxa/reset.c | 2 +-
arch/arm/mach-pxa/sharpsl_pm.c | 2 +-
arch/arm/mach-pxa/spitz.c | 2 +-
arch/arm/mach-pxa/spitz_pm.c | 2 +-
arch/arm/mach-s3c/dev-audio-s3c64xx.c | 2 +-
arch/arm/mach-s3c/devs.c | 2 +-
arch/arm/mach-s3c/mach-crag6410.c | 2 +-
arch/arm/mach-s3c/pm-gpio.c | 2 +-
arch/arm/mach-s3c/pm-s3c64xx.c | 2 +-
arch/arm/mach-s3c/setup-fb-24bpp-s3c64xx.c | 2 +-
arch/arm/mach-s3c/setup-i2c0-s3c64xx.c | 2 +-
arch/arm/mach-s3c/setup-i2c1-s3c64xx.c | 2 +-
arch/arm/mach-s3c/setup-keypad-s3c64xx.c | 2 +-
arch/arm/mach-s3c/setup-sdhci-gpio-s3c64xx.c | 2 +-
arch/arm/mach-s3c/setup-spi-s3c64xx.c | 2 +-
arch/arm/mach-sa1100/collie.c | 2 +-
arch/arm/mach-sa1100/generic.c | 2 +-
arch/arm/mach-sa1100/h3600.c | 2 +-
arch/arm/mach-sa1100/h3xxx.c | 2 +-
arch/arm/plat-orion/mpp.c | 2 +-
arch/m68k/coldfire/device.c | 2 +-
arch/m68k/include/asm/mcfgpio.h | 2 +-
arch/mips/alchemy/board-xxs1500.c | 2 +-
arch/mips/alchemy/devboards/db1000.c | 2 +-
arch/mips/alchemy/devboards/db1200.c | 2 +-
arch/mips/alchemy/devboards/db1550.c | 2 +-
arch/mips/bcm47xx/workarounds.c | 2 +-
arch/mips/bcm63xx/boards/board_bcm963xx.c | 1 +
.../include/asm/mach-bcm63xx/board_bcm963xx.h | 2 +-
arch/mips/txx9/rbtx4927/setup.c | 2 +-
arch/sh/boards/board-magicpanelr2.c | 2 +-
arch/sh/boards/board-sh7757lcr.c | 2 +-
arch/sh/boards/board-urquell.c | 2 +-
arch/sh/boards/mach-ap325rxa/setup.c | 2 +-
arch/sh/boards/mach-ecovec24/setup.c | 2 +-
.../boards/mach-highlander/pinmux-r7785rp.c | 2 +-
arch/sh/boards/mach-kfr2r09/lcd_wqvga.c | 2 +-
arch/sh/boards/mach-kfr2r09/setup.c | 2 +-
arch/sh/boards/mach-migor/lcd_qvga.c | 2 +-
arch/sh/boards/mach-migor/setup.c | 2 +-
arch/sh/boards/mach-rsk/devices-rsk7203.c | 2 +-
arch/sh/boards/mach-rsk/devices-rsk7269.c | 1 -
arch/sh/boards/mach-se/7724/setup.c | 2 +-
.../include/mach-common/mach/magicpanelr2.h | 2 --
arch/sh/kernel/cpu/sh4a/setup-shx3.c | 2 +-
drivers/gpib/gpio/gpib_bitbang.c | 2 +-
drivers/gpio/TODO | 4 +---
drivers/gpio/gpiolib-cdev.c | 2 +-
drivers/gpio/gpiolib-legacy.c | 3 +--
drivers/gpio/gpiolib.c | 2 +-
drivers/input/keyboard/matrix_keypad.c | 2 +-
drivers/media/pci/ddbridge/ddbridge.h | 2 +-
.../platform/samsung/s3c-camif/camif-core.c | 2 +-
drivers/media/usb/em28xx/em28xx-dvb.c | 2 +-
drivers/mfd/aat2870-core.c | 2 +-
drivers/mfd/arizona-irq.c | 2 +-
drivers/mfd/lp3943.c | 2 +-
drivers/mfd/si476x-cmd.c | 2 +-
drivers/mfd/si476x-i2c.c | 2 +-
drivers/mfd/sm501.c | 2 +-
drivers/mfd/tps6105x.c | 2 +-
drivers/mfd/tps65911-comparator.c | 2 +-
drivers/mfd/wm8994-irq.c | 2 +-
drivers/net/dsa/b53/b53_priv.h | 3 ++-
drivers/net/dsa/microchip/ksz8.c | 2 +-
drivers/net/ethernet/allwinner/sun4i-emac.c | 2 +-
.../net/ethernet/apm/xgene/xgene_enet_main.c | 2 +-
.../ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 2 +-
drivers/net/phy/mdio_device.c | 2 +-
drivers/pcmcia/bcm63xx_pcmcia.c | 2 +-
drivers/pcmcia/db1xxx_ss.c | 2 +-
drivers/pcmcia/sa1100_h3600.c | 2 +-
drivers/pcmcia/soc_common.c | 2 +-
drivers/pcmcia/xxs1500_ss.c | 2 +-
drivers/phy/broadcom/phy-bcm-ns2-usbdrd.c | 2 +-
drivers/phy/rockchip/phy-rockchip-usbdp.c | 2 +-
drivers/phy/ti/phy-j721e-wiz.c | 2 +-
include/linux/gpio.h | 22 -------------------
include/linux/mfd/lp3943.h | 2 +-
include/linux/mfd/ti-lmu.h | 2 +-
include/linux/mfd/tps65910.h | 2 +-
include/linux/mfd/ucb1x00.h | 2 +-
sound/soc/codecs/cs42l84.c | 2 +-
sound/soc/codecs/cx2072x.c | 2 +-
sound/soc/codecs/dmic.c | 2 +-
110 files changed, 107 insertions(+), 134 deletions(-)
delete mode 100644 include/linux/gpio.h
--
2.39.5
Cc: Bartosz Golaszewski <brgl@kernel.org>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Cc: Gregory Clement <gregory.clement@bootlin.com>
Cc: Frank Li <Frank.Li@nxp.com>
Cc: Robert Jarzmik <robert.jarzmik@free.fr>
Cc: Krzysztof Kozlowski <krzk@kernel.org>
Cc: Greg Ungerer <gerg@linux-m68k.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Hauke Mehrtens <hauke@hauke-m.de>
Cc: "Rafał Miłecki" <zajec5@gmail.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: Linus Walleij <linusw@kernel.org>
Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Dominik Brodowski <linux@dominikbrodowski.net>
Cc: linux-kernel@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-samsung-soc@vger.kernel.org
Cc: patches@opensource.cirrus.com
Cc: linux-m68k@lists.linux-m68k.org
Cc: linux-mips@vger.kernel.org
Cc: linux-sh@vger.kernel.org
Cc: linux-gpio@vger.kernel.org
Cc: linux-input@vger.kernel.org
Cc: linux-media@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: linux-sunxi@lists.linux.dev
Cc: linux-phy@lists.infradead.org
Cc: linux-rockchip@lists.infradead.org
Cc: linux-sound@vger.kernel.org
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* [PATCH 01/13] ARM: replace linux/gpio.h inclusions
From: Arnd Bergmann @ 2026-06-29 13:26 UTC (permalink / raw)
To: linux-gpio
Cc: Arnd Bergmann, Bartosz Golaszewski, Andrew Lunn,
Sebastian Hesselbarth, Gregory Clement, Frank Li, Robert Jarzmik,
Krzysztof Kozlowski, Greg Ungerer, Thomas Bogendoerfer,
Hauke Mehrtens, Rafał Miłecki, Yoshinori Sato,
John Paul Adrian Glaubitz, Linus Walleij, Dmitry Torokhov,
Jakub Kicinski, Paolo Abeni, Dominik Brodowski, linux-kernel,
linux-arm-kernel, linux-samsung-soc, patches, linux-m68k,
linux-mips, linux-sh, linux-input, linux-media, netdev,
linux-sunxi, linux-phy, linux-rockchip, linux-sound
In-Reply-To: <20260629132633.1300009-1-arnd@kernel.org>
From: Arnd Bergmann <arnd@arndb.de>
linux/gpio.h should no longer be used, convert these instead to
either linux/gpio/consumer.h or linux/gpio/legacy.h as needed.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
arch/arm/mach-davinci/da850.c | 2 +-
arch/arm/mach-dove/mpp.c | 2 +-
arch/arm/mach-mv78xx0/buffalo-wxl-setup.c | 2 +-
arch/arm/mach-mv78xx0/irq.c | 2 +-
arch/arm/mach-mv78xx0/mpp.c | 2 +-
arch/arm/mach-mvebu/pm.c | 2 +-
arch/arm/mach-mxs/mach-mxs.c | 2 +-
arch/arm/mach-orion5x/board-d2net.c | 2 +-
arch/arm/mach-orion5x/board-rd88f5182.c | 2 +-
arch/arm/mach-orion5x/dns323-setup.c | 2 +-
arch/arm/mach-orion5x/irq.c | 2 +-
arch/arm/mach-orion5x/kurobox_pro-setup.c | 2 +-
arch/arm/mach-orion5x/mv2120-setup.c | 2 +-
arch/arm/mach-orion5x/net2big-setup.c | 2 +-
arch/arm/mach-orion5x/terastation_pro2-setup.c | 2 +-
arch/arm/mach-orion5x/ts209-setup.c | 2 +-
arch/arm/mach-orion5x/ts409-setup.c | 2 +-
arch/arm/mach-pxa/am200epd.c | 2 +-
arch/arm/mach-pxa/am300epd.c | 2 +-
arch/arm/mach-pxa/generic.c | 2 +-
arch/arm/mach-pxa/gumstix.c | 2 +-
arch/arm/mach-pxa/mfp-pxa2xx.c | 2 +-
arch/arm/mach-pxa/pxa25x.c | 2 +-
arch/arm/mach-pxa/pxa27x.c | 2 +-
arch/arm/mach-pxa/reset.c | 2 +-
arch/arm/mach-pxa/sharpsl_pm.c | 2 +-
arch/arm/mach-pxa/spitz.c | 2 +-
arch/arm/mach-pxa/spitz_pm.c | 2 +-
arch/arm/mach-s3c/dev-audio-s3c64xx.c | 2 +-
arch/arm/mach-s3c/devs.c | 2 +-
arch/arm/mach-s3c/mach-crag6410.c | 2 +-
arch/arm/mach-s3c/pm-gpio.c | 2 +-
arch/arm/mach-s3c/pm-s3c64xx.c | 2 +-
arch/arm/mach-s3c/setup-fb-24bpp-s3c64xx.c | 2 +-
arch/arm/mach-s3c/setup-i2c0-s3c64xx.c | 2 +-
arch/arm/mach-s3c/setup-i2c1-s3c64xx.c | 2 +-
arch/arm/mach-s3c/setup-keypad-s3c64xx.c | 2 +-
arch/arm/mach-s3c/setup-sdhci-gpio-s3c64xx.c | 2 +-
arch/arm/mach-s3c/setup-spi-s3c64xx.c | 2 +-
arch/arm/mach-sa1100/collie.c | 2 +-
arch/arm/mach-sa1100/generic.c | 2 +-
arch/arm/mach-sa1100/h3600.c | 2 +-
arch/arm/mach-sa1100/h3xxx.c | 2 +-
arch/arm/plat-orion/mpp.c | 2 +-
44 files changed, 44 insertions(+), 44 deletions(-)
diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c
index 706f8241b5e7..611cce70c5bb 100644
--- a/arch/arm/mach-davinci/da850.c
+++ b/arch/arm/mach-davinci/da850.c
@@ -9,7 +9,7 @@
* 2009 (c) MontaVista Software, Inc.
*/
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/init.h>
#include <linux/io.h>
#include <linux/mfd/da8xx-cfgchip.h>
diff --git a/arch/arm/mach-dove/mpp.c b/arch/arm/mach-dove/mpp.c
index 93cb137da5f8..e41bd473abe9 100644
--- a/arch/arm/mach-dove/mpp.c
+++ b/arch/arm/mach-dove/mpp.c
@@ -6,7 +6,7 @@
*/
#include <linux/kernel.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/io.h>
#include <plat/mpp.h>
#include <plat/orion-gpio.h>
diff --git a/arch/arm/mach-mv78xx0/buffalo-wxl-setup.c b/arch/arm/mach-mv78xx0/buffalo-wxl-setup.c
index 62e982f74bc2..3b2e381b7383 100644
--- a/arch/arm/mach-mv78xx0/buffalo-wxl-setup.c
+++ b/arch/arm/mach-mv78xx0/buffalo-wxl-setup.c
@@ -14,7 +14,7 @@
#include <linux/mv643xx_eth.h>
#include <linux/ethtool.h>
#include <linux/i2c.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio_keys.h>
#include <linux/input.h>
#include <asm/mach-types.h>
diff --git a/arch/arm/mach-mv78xx0/irq.c b/arch/arm/mach-mv78xx0/irq.c
index a34b6855fb19..6e42f6446637 100644
--- a/arch/arm/mach-mv78xx0/irq.c
+++ b/arch/arm/mach-mv78xx0/irq.c
@@ -4,7 +4,7 @@
*
* MV78xx0 IRQ handling.
*/
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/kernel.h>
#include <linux/irq.h>
#include <linux/io.h>
diff --git a/arch/arm/mach-mv78xx0/mpp.c b/arch/arm/mach-mv78xx0/mpp.c
index aff0e612cbba..32bf590d79fe 100644
--- a/arch/arm/mach-mv78xx0/mpp.c
+++ b/arch/arm/mach-mv78xx0/mpp.c
@@ -4,7 +4,7 @@
*
* MPP functions for Marvell MV78x00 SoCs
*/
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/io.h>
diff --git a/arch/arm/mach-mvebu/pm.c b/arch/arm/mach-mvebu/pm.c
index b149d9b77505..616a7fb22d86 100644
--- a/arch/arm/mach-mvebu/pm.c
+++ b/arch/arm/mach-mvebu/pm.c
@@ -9,7 +9,7 @@
#include <linux/cpu_pm.h>
#include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/io.h>
#include <linux/kernel.h>
#include <linux/mbus.h>
diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c
index f639d5004351..c8231a480052 100644
--- a/arch/arm/mach-mxs/mach-mxs.c
+++ b/arch/arm/mach-mxs/mach-mxs.c
@@ -9,7 +9,7 @@
#include <linux/clkdev.h>
#include <linux/delay.h>
#include <linux/err.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/init.h>
#include <linux/reboot.h>
#include <linux/micrel_phy.h>
diff --git a/arch/arm/mach-orion5x/board-d2net.c b/arch/arm/mach-orion5x/board-d2net.c
index 09bf366d05ff..7cf09da9d9e7 100644
--- a/arch/arm/mach-orion5x/board-d2net.c
+++ b/arch/arm/mach-orion5x/board-d2net.c
@@ -13,7 +13,7 @@
#include <linux/pci.h>
#include <linux/irq.h>
#include <linux/leds.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio/machine.h>
#include <asm/mach-types.h>
#include <asm/mach/arch.h>
diff --git a/arch/arm/mach-orion5x/board-rd88f5182.c b/arch/arm/mach-orion5x/board-rd88f5182.c
index 1c14e49a90a6..9e2fe74ec68a 100644
--- a/arch/arm/mach-orion5x/board-rd88f5182.c
+++ b/arch/arm/mach-orion5x/board-rd88f5182.c
@@ -6,7 +6,7 @@
*
* Maintainer: Ronen Shitrit <rshitrit@marvell.com>
*/
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/of.h>
diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c
index fcd38ff7ca45..7b81b08b0dda 100644
--- a/arch/arm/mach-orion5x/dns323-setup.c
+++ b/arch/arm/mach-orion5x/dns323-setup.c
@@ -13,7 +13,7 @@
* License, or (at your option) any later version.
*
*/
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio/machine.h>
#include <linux/kernel.h>
#include <linux/init.h>
diff --git a/arch/arm/mach-orion5x/irq.c b/arch/arm/mach-orion5x/irq.c
index e17727e53cb4..689bec1ebe89 100644
--- a/arch/arm/mach-orion5x/irq.c
+++ b/arch/arm/mach-orion5x/irq.c
@@ -6,7 +6,7 @@
*
* Maintainer: Tzachi Perelstein <tzachi@marvell.com>
*/
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/kernel.h>
#include <linux/irq.h>
#include <linux/io.h>
diff --git a/arch/arm/mach-orion5x/kurobox_pro-setup.c b/arch/arm/mach-orion5x/kurobox_pro-setup.c
index 339b10891808..e61b9ab06943 100644
--- a/arch/arm/mach-orion5x/kurobox_pro-setup.c
+++ b/arch/arm/mach-orion5x/kurobox_pro-setup.c
@@ -4,7 +4,7 @@
*
* Maintainer: Ronen Shitrit <rshitrit@marvell.com>
*/
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/platform_device.h>
diff --git a/arch/arm/mach-orion5x/mv2120-setup.c b/arch/arm/mach-orion5x/mv2120-setup.c
index 5b0249f109cd..b15fe5b7a0f9 100644
--- a/arch/arm/mach-orion5x/mv2120-setup.c
+++ b/arch/arm/mach-orion5x/mv2120-setup.c
@@ -7,7 +7,7 @@
* published by the Free Software Foundation; either version 2 of the
* License, or (at your option) any later version.
*/
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio/machine.h>
#include <linux/kernel.h>
#include <linux/init.h>
diff --git a/arch/arm/mach-orion5x/net2big-setup.c b/arch/arm/mach-orion5x/net2big-setup.c
index 4afd9b4c71a9..f04571e79805 100644
--- a/arch/arm/mach-orion5x/net2big-setup.c
+++ b/arch/arm/mach-orion5x/net2big-setup.c
@@ -17,7 +17,7 @@
#include <linux/input.h>
#include <linux/i2c.h>
#include <linux/ata_platform.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio/machine.h>
#include <linux/delay.h>
#include <asm/mach-types.h>
diff --git a/arch/arm/mach-orion5x/terastation_pro2-setup.c b/arch/arm/mach-orion5x/terastation_pro2-setup.c
index a9f01859d101..c3db3376950a 100644
--- a/arch/arm/mach-orion5x/terastation_pro2-setup.c
+++ b/arch/arm/mach-orion5x/terastation_pro2-setup.c
@@ -4,7 +4,7 @@
*
* Maintainer: Sylver Bruneau <sylver.bruneau@googlemail.com>
*/
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/platform_device.h>
diff --git a/arch/arm/mach-orion5x/ts209-setup.c b/arch/arm/mach-orion5x/ts209-setup.c
index de9092e992c5..25cd50306c65 100644
--- a/arch/arm/mach-orion5x/ts209-setup.c
+++ b/arch/arm/mach-orion5x/ts209-setup.c
@@ -4,7 +4,7 @@
*
* Maintainer: Byron Bradley <byron.bbradley@gmail.com>
*/
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/platform_device.h>
diff --git a/arch/arm/mach-orion5x/ts409-setup.c b/arch/arm/mach-orion5x/ts409-setup.c
index 725688aa5cba..f92acef0b45f 100644
--- a/arch/arm/mach-orion5x/ts409-setup.c
+++ b/arch/arm/mach-orion5x/ts409-setup.c
@@ -7,7 +7,7 @@
* Copyright (C) 2008 Sylver Bruneau <sylver.bruneau@gmail.com>
* Copyright (C) 2008 Martin Michlmayr <tbm@cyrius.com>
*/
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio/machine.h>
#include <linux/kernel.h>
#include <linux/init.h>
diff --git a/arch/arm/mach-pxa/am200epd.c b/arch/arm/mach-pxa/am200epd.c
index cac0bb09db14..4814f3cfe775 100644
--- a/arch/arm/mach-pxa/am200epd.c
+++ b/arch/arm/mach-pxa/am200epd.c
@@ -28,7 +28,7 @@
#include <linux/init.h>
#include <linux/platform_device.h>
#include <linux/irq.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include "pxa25x.h"
#include "gumstix.h"
diff --git a/arch/arm/mach-pxa/am300epd.c b/arch/arm/mach-pxa/am300epd.c
index 4b55bc89db8f..435fb72da7de 100644
--- a/arch/arm/mach-pxa/am300epd.c
+++ b/arch/arm/mach-pxa/am300epd.c
@@ -26,7 +26,7 @@
#include <linux/init.h>
#include <linux/platform_device.h>
#include <linux/irq.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include "gumstix.h"
#include "mfp-pxa25x.h"
diff --git a/arch/arm/mach-pxa/generic.c b/arch/arm/mach-pxa/generic.c
index 02fdde7e3e34..f181e7b7c6be 100644
--- a/arch/arm/mach-pxa/generic.c
+++ b/arch/arm/mach-pxa/generic.c
@@ -13,7 +13,7 @@
* initialization stuff for PXA machines which can be overridden later if
* need be.
*/
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/init.h>
diff --git a/arch/arm/mach-pxa/gumstix.c b/arch/arm/mach-pxa/gumstix.c
index 6074815a4bca..7ab0cb015d1b 100644
--- a/arch/arm/mach-pxa/gumstix.c
+++ b/arch/arm/mach-pxa/gumstix.c
@@ -22,7 +22,7 @@
#include <linux/mtd/partitions.h>
#include <linux/gpio/machine.h>
#include <linux/gpio/property.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/err.h>
#include <linux/clk.h>
diff --git a/arch/arm/mach-pxa/mfp-pxa2xx.c b/arch/arm/mach-pxa/mfp-pxa2xx.c
index d1347055fbe4..566fb4e2adba 100644
--- a/arch/arm/mach-pxa/mfp-pxa2xx.c
+++ b/arch/arm/mach-pxa/mfp-pxa2xx.c
@@ -9,7 +9,7 @@
* on PXA3xx, what's more important, the low power pin state and
* wakeup detection are also supported by the same framework.
*/
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/gpio-pxa.h>
#include <linux/module.h>
#include <linux/kernel.h>
diff --git a/arch/arm/mach-pxa/pxa25x.c b/arch/arm/mach-pxa/pxa25x.c
index a4e878be004a..a273f0af095e 100644
--- a/arch/arm/mach-pxa/pxa25x.c
+++ b/arch/arm/mach-pxa/pxa25x.c
@@ -15,7 +15,7 @@
*/
#include <linux/dmaengine.h>
#include <linux/dma/pxa-dma.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/gpio-pxa.h>
#include <linux/module.h>
#include <linux/kernel.h>
diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c
index 1d34de7e5fbe..814e0a12f38a 100644
--- a/arch/arm/mach-pxa/pxa27x.c
+++ b/arch/arm/mach-pxa/pxa27x.c
@@ -10,7 +10,7 @@
*/
#include <linux/dmaengine.h>
#include <linux/dma/pxa-dma.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/gpio-pxa.h>
#include <linux/module.h>
#include <linux/kernel.h>
diff --git a/arch/arm/mach-pxa/reset.c b/arch/arm/mach-pxa/reset.c
index 27293549f8ad..49d2e46a1fae 100644
--- a/arch/arm/mach-pxa/reset.c
+++ b/arch/arm/mach-pxa/reset.c
@@ -2,7 +2,7 @@
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/io.h>
#include <asm/proc-fns.h>
#include <asm/system_misc.h>
diff --git a/arch/arm/mach-pxa/sharpsl_pm.c b/arch/arm/mach-pxa/sharpsl_pm.c
index 71b282b146d0..a611eea70e5a 100644
--- a/arch/arm/mach-pxa/sharpsl_pm.c
+++ b/arch/arm/mach-pxa/sharpsl_pm.c
@@ -19,7 +19,7 @@
#include <linux/delay.h>
#include <linux/leds.h>
#include <linux/suspend.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/io.h>
#include <asm/mach-types.h>
diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
index 5091b601c4e1..5eaf38243b9e 100644
--- a/arch/arm/mach-pxa/spitz.c
+++ b/arch/arm/mach-pxa/spitz.c
@@ -12,7 +12,7 @@
#include <linux/platform_device.h>
#include <linux/delay.h>
#include <linux/gpio_keys.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio/machine.h>
#include <linux/gpio/property.h>
#include <linux/leds.h>
diff --git a/arch/arm/mach-pxa/spitz_pm.c b/arch/arm/mach-pxa/spitz_pm.c
index 03b4b347f11a..806847c36549 100644
--- a/arch/arm/mach-pxa/spitz_pm.c
+++ b/arch/arm/mach-pxa/spitz_pm.c
@@ -10,7 +10,7 @@
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio-pxa.h>
#include <linux/interrupt.h>
#include <linux/platform_device.h>
diff --git a/arch/arm/mach-s3c/dev-audio-s3c64xx.c b/arch/arm/mach-s3c/dev-audio-s3c64xx.c
index 7ce119dc3a72..8884374dbcdc 100644
--- a/arch/arm/mach-s3c/dev-audio-s3c64xx.c
+++ b/arch/arm/mach-s3c/dev-audio-s3c64xx.c
@@ -7,7 +7,7 @@
#include <linux/string.h>
#include <linux/platform_device.h>
#include <linux/dma-mapping.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/export.h>
#include "irqs.h"
diff --git a/arch/arm/mach-s3c/devs.c b/arch/arm/mach-s3c/devs.c
index bab2abd8a34a..572b156644bd 100644
--- a/arch/arm/mach-s3c/devs.c
+++ b/arch/arm/mach-s3c/devs.c
@@ -5,7 +5,7 @@
//
// Base Samsung platform device definitions
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/interrupt.h>
diff --git a/arch/arm/mach-s3c/mach-crag6410.c b/arch/arm/mach-s3c/mach-crag6410.c
index c4040aad1ed3..57176719d8a6 100644
--- a/arch/arm/mach-s3c/mach-crag6410.c
+++ b/arch/arm/mach-s3c/mach-crag6410.c
@@ -15,7 +15,7 @@
#include <linux/io.h>
#include <linux/init.h>
#include <linux/input-event-codes.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio/machine.h>
#include <linux/leds.h>
#include <linux/delay.h>
diff --git a/arch/arm/mach-s3c/pm-gpio.c b/arch/arm/mach-s3c/pm-gpio.c
index cfdbc2337998..fd5897cc26c7 100644
--- a/arch/arm/mach-s3c/pm-gpio.c
+++ b/arch/arm/mach-s3c/pm-gpio.c
@@ -11,7 +11,7 @@
#include <linux/device.h>
#include <linux/init.h>
#include <linux/io.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include "gpio-samsung.h"
diff --git a/arch/arm/mach-s3c/pm-s3c64xx.c b/arch/arm/mach-s3c/pm-s3c64xx.c
index 284d5f462513..a73b8bd12949 100644
--- a/arch/arm/mach-s3c/pm-s3c64xx.c
+++ b/arch/arm/mach-s3c/pm-s3c64xx.c
@@ -11,7 +11,7 @@
#include <linux/suspend.h>
#include <linux/serial_core.h>
#include <linux/io.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/pm_domain.h>
#include "map.h"
diff --git a/arch/arm/mach-s3c/setup-fb-24bpp-s3c64xx.c b/arch/arm/mach-s3c/setup-fb-24bpp-s3c64xx.c
index c3269cd6a848..20ae926e12db 100644
--- a/arch/arm/mach-s3c/setup-fb-24bpp-s3c64xx.c
+++ b/arch/arm/mach-s3c/setup-fb-24bpp-s3c64xx.c
@@ -9,7 +9,7 @@
#include <linux/kernel.h>
#include <linux/types.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include "fb.h"
#include "gpio-cfg.h"
diff --git a/arch/arm/mach-s3c/setup-i2c0-s3c64xx.c b/arch/arm/mach-s3c/setup-i2c0-s3c64xx.c
index a6ef8d2bc995..520e97dc8754 100644
--- a/arch/arm/mach-s3c/setup-i2c0-s3c64xx.c
+++ b/arch/arm/mach-s3c/setup-i2c0-s3c64xx.c
@@ -9,7 +9,7 @@
#include <linux/kernel.h>
#include <linux/types.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
struct platform_device; /* don't need the contents */
diff --git a/arch/arm/mach-s3c/setup-i2c1-s3c64xx.c b/arch/arm/mach-s3c/setup-i2c1-s3c64xx.c
index 0fe37363d26e..26f7ae455328 100644
--- a/arch/arm/mach-s3c/setup-i2c1-s3c64xx.c
+++ b/arch/arm/mach-s3c/setup-i2c1-s3c64xx.c
@@ -9,7 +9,7 @@
#include <linux/kernel.h>
#include <linux/types.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
struct platform_device; /* don't need the contents */
diff --git a/arch/arm/mach-s3c/setup-keypad-s3c64xx.c b/arch/arm/mach-s3c/setup-keypad-s3c64xx.c
index 8463ad37c6ab..2e1367878fb1 100644
--- a/arch/arm/mach-s3c/setup-keypad-s3c64xx.c
+++ b/arch/arm/mach-s3c/setup-keypad-s3c64xx.c
@@ -5,7 +5,7 @@
//
// GPIO configuration for S3C64XX KeyPad device
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include "gpio-cfg.h"
#include "keypad.h"
#include "gpio-samsung.h"
diff --git a/arch/arm/mach-s3c/setup-sdhci-gpio-s3c64xx.c b/arch/arm/mach-s3c/setup-sdhci-gpio-s3c64xx.c
index 646ff949acd5..728b66f80493 100644
--- a/arch/arm/mach-s3c/setup-sdhci-gpio-s3c64xx.c
+++ b/arch/arm/mach-s3c/setup-sdhci-gpio-s3c64xx.c
@@ -11,7 +11,7 @@
#include <linux/interrupt.h>
#include <linux/platform_device.h>
#include <linux/io.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include "gpio-cfg.h"
#include "sdhci.h"
diff --git a/arch/arm/mach-s3c/setup-spi-s3c64xx.c b/arch/arm/mach-s3c/setup-spi-s3c64xx.c
index 497aff71c29c..8d15b13ed7d5 100644
--- a/arch/arm/mach-s3c/setup-spi-s3c64xx.c
+++ b/arch/arm/mach-s3c/setup-spi-s3c64xx.c
@@ -3,7 +3,7 @@
// Copyright (C) 2011 Samsung Electronics Ltd.
// http://www.samsung.com/
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/platform_data/spi-s3c64xx.h>
#include "gpio-cfg.h"
#include "gpio-samsung.h"
diff --git a/arch/arm/mach-sa1100/collie.c b/arch/arm/mach-sa1100/collie.c
index 466d755d5702..af9c68b2093e 100644
--- a/arch/arm/mach-sa1100/collie.c
+++ b/arch/arm/mach-sa1100/collie.c
@@ -29,7 +29,7 @@
#include <linux/timer.h>
#include <linux/gpio_keys.h>
#include <linux/input.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio/machine.h>
#include <linux/power/gpio-charger.h>
diff --git a/arch/arm/mach-sa1100/generic.c b/arch/arm/mach-sa1100/generic.c
index 99ff55e8131d..a995625ab1a0 100644
--- a/arch/arm/mach-sa1100/generic.c
+++ b/arch/arm/mach-sa1100/generic.c
@@ -6,7 +6,7 @@
*
* Code common to all SA11x0 machines.
*/
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/gpio/machine.h>
#include <linux/module.h>
#include <linux/kernel.h>
diff --git a/arch/arm/mach-sa1100/h3600.c b/arch/arm/mach-sa1100/h3600.c
index 1cfc0b1fa41c..59e9251a138e 100644
--- a/arch/arm/mach-sa1100/h3600.c
+++ b/arch/arm/mach-sa1100/h3600.c
@@ -8,7 +8,7 @@
#include <linux/init.h>
#include <linux/kernel.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <video/sa1100fb.h>
diff --git a/arch/arm/mach-sa1100/h3xxx.c b/arch/arm/mach-sa1100/h3xxx.c
index d685f03f51f3..b8fc1953db9f 100644
--- a/arch/arm/mach-sa1100/h3xxx.c
+++ b/arch/arm/mach-sa1100/h3xxx.c
@@ -8,7 +8,7 @@
#include <linux/kernel.h>
#include <linux/gpio/machine.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio_keys.h>
#include <linux/input.h>
#include <linux/mtd/mtd.h>
diff --git a/arch/arm/plat-orion/mpp.c b/arch/arm/plat-orion/mpp.c
index 8a6880d528b6..673ecedc721d 100644
--- a/arch/arm/plat-orion/mpp.c
+++ b/arch/arm/plat-orion/mpp.c
@@ -12,7 +12,7 @@
#include <linux/init.h>
#include <linux/mbus.h>
#include <linux/io.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <plat/orion-gpio.h>
#include <plat/mpp.h>
--
2.39.5
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH 02/13] m68k/coldfire: replace linux/gpio.h inclusions
From: Arnd Bergmann @ 2026-06-29 13:26 UTC (permalink / raw)
To: linux-gpio
Cc: Arnd Bergmann, Bartosz Golaszewski, Andrew Lunn,
Sebastian Hesselbarth, Gregory Clement, Frank Li, Robert Jarzmik,
Krzysztof Kozlowski, Greg Ungerer, Thomas Bogendoerfer,
Hauke Mehrtens, Rafał Miłecki, Yoshinori Sato,
John Paul Adrian Glaubitz, Linus Walleij, Dmitry Torokhov,
Jakub Kicinski, Paolo Abeni, Dominik Brodowski, linux-kernel,
linux-arm-kernel, linux-samsung-soc, patches, linux-m68k,
linux-mips, linux-sh, linux-input, linux-media, netdev,
linux-sunxi, linux-phy, linux-rockchip, linux-sound
In-Reply-To: <20260629132633.1300009-1-arnd@kernel.org>
From: Arnd Bergmann <arnd@arndb.de>
linux/gpio.h should no longer be used, convert these instead to
linux/gpio/legacy.h for coldfire.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
arch/m68k/coldfire/device.c | 2 +-
arch/m68k/include/asm/mcfgpio.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/m68k/coldfire/device.c b/arch/m68k/coldfire/device.c
index 1420bae0964f..9a0258acd998 100644
--- a/arch/m68k/coldfire/device.c
+++ b/arch/m68k/coldfire/device.c
@@ -12,7 +12,7 @@
#include <linux/init.h>
#include <linux/io.h>
#include <linux/spi/spi.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/fec.h>
#include <linux/dmaengine.h>
#include <asm/traps.h>
diff --git a/arch/m68k/include/asm/mcfgpio.h b/arch/m68k/include/asm/mcfgpio.h
index 7103cfa4edb6..29726aa40eb6 100644
--- a/arch/m68k/include/asm/mcfgpio.h
+++ b/arch/m68k/include/asm/mcfgpio.h
@@ -16,7 +16,7 @@ int __mcfgpio_request(unsigned gpio);
void __mcfgpio_free(unsigned gpio);
#ifdef CONFIG_GPIOLIB
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#else
/* our alternate 'gpiolib' functions */
--
2.39.5
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH 03/13] mips: replace linux/gpio.h inclusions
From: Arnd Bergmann @ 2026-06-29 13:26 UTC (permalink / raw)
To: linux-gpio
Cc: Arnd Bergmann, Bartosz Golaszewski, Andrew Lunn,
Sebastian Hesselbarth, Gregory Clement, Frank Li, Robert Jarzmik,
Krzysztof Kozlowski, Greg Ungerer, Thomas Bogendoerfer,
Hauke Mehrtens, Rafał Miłecki, Yoshinori Sato,
John Paul Adrian Glaubitz, Linus Walleij, Dmitry Torokhov,
Jakub Kicinski, Paolo Abeni, Dominik Brodowski, linux-kernel,
linux-arm-kernel, linux-samsung-soc, patches, linux-m68k,
linux-mips, linux-sh, linux-input, linux-media, netdev,
linux-sunxi, linux-phy, linux-rockchip, linux-sound
In-Reply-To: <20260629132633.1300009-1-arnd@kernel.org>
From: Arnd Bergmann <arnd@arndb.de>
linux/gpio.h should no longer be used, convert these instead to
either linux/gpio/consumer.h or linux/gpio/legacy.h as needed.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
arch/mips/alchemy/board-xxs1500.c | 2 +-
arch/mips/alchemy/devboards/db1000.c | 2 +-
arch/mips/alchemy/devboards/db1200.c | 2 +-
arch/mips/alchemy/devboards/db1550.c | 2 +-
arch/mips/bcm47xx/workarounds.c | 2 +-
arch/mips/bcm63xx/boards/board_bcm963xx.c | 1 +
arch/mips/include/asm/mach-bcm63xx/board_bcm963xx.h | 2 +-
arch/mips/txx9/rbtx4927/setup.c | 2 +-
8 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/arch/mips/alchemy/board-xxs1500.c b/arch/mips/alchemy/board-xxs1500.c
index f175bce2987f..a03762dde4e7 100644
--- a/arch/mips/alchemy/board-xxs1500.c
+++ b/arch/mips/alchemy/board-xxs1500.c
@@ -11,7 +11,7 @@
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/platform_device.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/delay.h>
#include <linux/pm.h>
#include <asm/bootinfo.h>
diff --git a/arch/mips/alchemy/devboards/db1000.c b/arch/mips/alchemy/devboards/db1000.c
index 8fb24b220e3a..5eff34a8683b 100644
--- a/arch/mips/alchemy/devboards/db1000.c
+++ b/arch/mips/alchemy/devboards/db1000.c
@@ -8,7 +8,7 @@
#include <linux/clk.h>
#include <linux/dma-mapping.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio/machine.h>
#include <linux/gpio/property.h>
#include <linux/init.h>
diff --git a/arch/mips/alchemy/devboards/db1200.c b/arch/mips/alchemy/devboards/db1200.c
index de2a9083ed9a..539b311fc8af 100644
--- a/arch/mips/alchemy/devboards/db1200.c
+++ b/arch/mips/alchemy/devboards/db1200.c
@@ -7,7 +7,7 @@
#include <linux/clk.h>
#include <linux/dma-mapping.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/i2c.h>
#include <linux/init.h>
#include <linux/interrupt.h>
diff --git a/arch/mips/alchemy/devboards/db1550.c b/arch/mips/alchemy/devboards/db1550.c
index b8295a5c2e9a..579fc8f1eaed 100644
--- a/arch/mips/alchemy/devboards/db1550.c
+++ b/arch/mips/alchemy/devboards/db1550.c
@@ -7,7 +7,7 @@
#include <linux/clk.h>
#include <linux/dma-mapping.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/i2c.h>
#include <linux/init.h>
#include <linux/io.h>
diff --git a/arch/mips/bcm47xx/workarounds.c b/arch/mips/bcm47xx/workarounds.c
index 745c6228eb2c..dc9e5483347d 100644
--- a/arch/mips/bcm47xx/workarounds.c
+++ b/arch/mips/bcm47xx/workarounds.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include "bcm47xx_private.h"
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <bcm47xx_board.h>
#include <bcm47xx.h>
diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c
index c5617b889b1c..71628dac6c26 100644
--- a/arch/mips/bcm63xx/boards/board_bcm963xx.c
+++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c
@@ -7,6 +7,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/init.h>
+#include <linux/gpio/legacy.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/platform_device.h>
diff --git a/arch/mips/include/asm/mach-bcm63xx/board_bcm963xx.h b/arch/mips/include/asm/mach-bcm63xx/board_bcm963xx.h
index 830f53f28e3f..428cf4508f9a 100644
--- a/arch/mips/include/asm/mach-bcm63xx/board_bcm963xx.h
+++ b/arch/mips/include/asm/mach-bcm63xx/board_bcm963xx.h
@@ -3,7 +3,7 @@
#define BOARD_BCM963XX_H_
#include <linux/types.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/leds.h>
#include <bcm63xx_dev_enet.h>
#include <bcm63xx_dev_usb_usbd.h>
diff --git a/arch/mips/txx9/rbtx4927/setup.c b/arch/mips/txx9/rbtx4927/setup.c
index 31955c1d5555..b4fbe6a2a73a 100644
--- a/arch/mips/txx9/rbtx4927/setup.c
+++ b/arch/mips/txx9/rbtx4927/setup.c
@@ -48,7 +48,7 @@
#include <linux/ioport.h>
#include <linux/platform_device.h>
#include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/leds.h>
#include <asm/io.h>
#include <asm/reboot.h>
--
2.39.5
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH 04/13] sh: replace linux/gpio.h inclusions
From: Arnd Bergmann @ 2026-06-29 13:26 UTC (permalink / raw)
To: linux-gpio
Cc: Arnd Bergmann, Bartosz Golaszewski, Andrew Lunn,
Sebastian Hesselbarth, Gregory Clement, Frank Li, Robert Jarzmik,
Krzysztof Kozlowski, Greg Ungerer, Thomas Bogendoerfer,
Hauke Mehrtens, Rafał Miłecki, Yoshinori Sato,
John Paul Adrian Glaubitz, Linus Walleij, Dmitry Torokhov,
Jakub Kicinski, Paolo Abeni, Dominik Brodowski, linux-kernel,
linux-arm-kernel, linux-samsung-soc, patches, linux-m68k,
linux-mips, linux-sh, linux-input, linux-media, netdev,
linux-sunxi, linux-phy, linux-rockchip, linux-sound
In-Reply-To: <20260629132633.1300009-1-arnd@kernel.org>
From: Arnd Bergmann <arnd@arndb.de>
linux/gpio.h should no longer be used, convert these instead to
linux/gpio/legacy.h for the sh boards using the legacy interfaces,
or remove it where it is not needed at all.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
arch/sh/boards/board-magicpanelr2.c | 2 +-
arch/sh/boards/board-sh7757lcr.c | 2 +-
arch/sh/boards/board-urquell.c | 2 +-
arch/sh/boards/mach-ap325rxa/setup.c | 2 +-
arch/sh/boards/mach-ecovec24/setup.c | 2 +-
arch/sh/boards/mach-highlander/pinmux-r7785rp.c | 2 +-
arch/sh/boards/mach-kfr2r09/lcd_wqvga.c | 2 +-
arch/sh/boards/mach-kfr2r09/setup.c | 2 +-
arch/sh/boards/mach-migor/lcd_qvga.c | 2 +-
arch/sh/boards/mach-migor/setup.c | 2 +-
arch/sh/boards/mach-rsk/devices-rsk7203.c | 2 +-
arch/sh/boards/mach-rsk/devices-rsk7269.c | 1 -
arch/sh/boards/mach-se/7724/setup.c | 2 +-
arch/sh/include/mach-common/mach/magicpanelr2.h | 2 --
arch/sh/kernel/cpu/sh4a/setup-shx3.c | 2 +-
15 files changed, 13 insertions(+), 16 deletions(-)
diff --git a/arch/sh/boards/board-magicpanelr2.c b/arch/sh/boards/board-magicpanelr2.c
index 75de893152af..3f14118a1015 100644
--- a/arch/sh/boards/board-magicpanelr2.c
+++ b/arch/sh/boards/board-magicpanelr2.c
@@ -10,7 +10,7 @@
#include <linux/irq.h>
#include <linux/platform_device.h>
#include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/regulator/fixed.h>
#include <linux/regulator/machine.h>
#include <linux/smsc911x.h>
diff --git a/arch/sh/boards/board-sh7757lcr.c b/arch/sh/boards/board-sh7757lcr.c
index bca54e489e11..6d18f59ef261 100644
--- a/arch/sh/boards/board-sh7757lcr.c
+++ b/arch/sh/boards/board-sh7757lcr.c
@@ -7,7 +7,7 @@
#include <linux/init.h>
#include <linux/platform_device.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/irq.h>
#include <linux/regulator/fixed.h>
#include <linux/regulator/machine.h>
diff --git a/arch/sh/boards/board-urquell.c b/arch/sh/boards/board-urquell.c
index dad2b3b40735..1f73c04d341f 100644
--- a/arch/sh/boards/board-urquell.c
+++ b/arch/sh/boards/board-urquell.c
@@ -14,7 +14,7 @@
#include <linux/smc91x.h>
#include <linux/mtd/physmap.h>
#include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/irq.h>
#include <linux/clk.h>
#include <linux/sh_intc.h>
diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c
index bb5004a8ac02..17c3f568d92e 100644
--- a/arch/sh/boards/mach-ap325rxa/setup.c
+++ b/arch/sh/boards/mach-ap325rxa/setup.c
@@ -17,7 +17,7 @@
#include <linux/clkdev.h>
#include <linux/delay.h>
#include <linux/device.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio/consumer.h>
#include <linux/gpio/machine.h>
#include <linux/i2c.h>
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index a641e26f8fdf..ca4b4dd1ddef 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -20,7 +20,7 @@
#include <linux/mmc/host.h>
#include <linux/platform_data/sh_mmcif.h>
#include <linux/mtd/physmap.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio/machine.h>
#include <linux/platform_data/gpio_backlight.h>
#include <linux/platform_data/tmio.h>
diff --git a/arch/sh/boards/mach-highlander/pinmux-r7785rp.c b/arch/sh/boards/mach-highlander/pinmux-r7785rp.c
index 689bd8732d9e..3a1057ee9ace 100644
--- a/arch/sh/boards/mach-highlander/pinmux-r7785rp.c
+++ b/arch/sh/boards/mach-highlander/pinmux-r7785rp.c
@@ -3,7 +3,7 @@
* Copyright (C) 2008 Paul Mundt
*/
#include <linux/init.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <cpu/sh7785.h>
#include <mach/highlander.h>
diff --git a/arch/sh/boards/mach-kfr2r09/lcd_wqvga.c b/arch/sh/boards/mach-kfr2r09/lcd_wqvga.c
index f6bbac106d13..68716660de34 100644
--- a/arch/sh/boards/mach-kfr2r09/lcd_wqvga.c
+++ b/arch/sh/boards/mach-kfr2r09/lcd_wqvga.c
@@ -14,7 +14,7 @@
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <video/sh_mobile_lcdc.h>
#include <mach/kfr2r09.h>
#include <cpu/sh7724.h>
diff --git a/arch/sh/boards/mach-kfr2r09/setup.c b/arch/sh/boards/mach-kfr2r09/setup.c
index 70236859919d..30dd7dae7906 100644
--- a/arch/sh/boards/mach-kfr2r09/setup.c
+++ b/arch/sh/boards/mach-kfr2r09/setup.c
@@ -14,7 +14,7 @@
#include <linux/clkdev.h>
#include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio/machine.h>
#include <linux/i2c.h>
#include <linux/init.h>
diff --git a/arch/sh/boards/mach-migor/lcd_qvga.c b/arch/sh/boards/mach-migor/lcd_qvga.c
index 4ebf130510bc..f72934e370fd 100644
--- a/arch/sh/boards/mach-migor/lcd_qvga.c
+++ b/arch/sh/boards/mach-migor/lcd_qvga.c
@@ -14,7 +14,7 @@
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <video/sh_mobile_lcdc.h>
#include <cpu/sh7722.h>
#include <mach/migor.h>
diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c
index 1853e6319a66..b0198e7cb9ab 100644
--- a/arch/sh/boards/mach-migor/setup.c
+++ b/arch/sh/boards/mach-migor/setup.c
@@ -22,7 +22,7 @@
#include <linux/smc91x.h>
#include <linux/delay.h>
#include <linux/clk.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio/machine.h>
#include <linux/videodev2.h>
#include <linux/sh_intc.h>
diff --git a/arch/sh/boards/mach-rsk/devices-rsk7203.c b/arch/sh/boards/mach-rsk/devices-rsk7203.c
index e6b05d4588b7..eb56b57812bd 100644
--- a/arch/sh/boards/mach-rsk/devices-rsk7203.c
+++ b/arch/sh/boards/mach-rsk/devices-rsk7203.c
@@ -10,7 +10,7 @@
#include <linux/interrupt.h>
#include <linux/smsc911x.h>
#include <linux/input.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/gpio_keys.h>
#include <linux/leds.h>
#include <asm/machvec.h>
diff --git a/arch/sh/boards/mach-rsk/devices-rsk7269.c b/arch/sh/boards/mach-rsk/devices-rsk7269.c
index 4b1e386b51dd..54edd9958eca 100644
--- a/arch/sh/boards/mach-rsk/devices-rsk7269.c
+++ b/arch/sh/boards/mach-rsk/devices-rsk7269.c
@@ -11,7 +11,6 @@
#include <linux/interrupt.h>
#include <linux/input.h>
#include <linux/smsc911x.h>
-#include <linux/gpio.h>
#include <asm/machvec.h>
#include <asm/io.h>
diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c
index e500feb91053..bed8f44fcecb 100644
--- a/arch/sh/boards/mach-se/7724/setup.c
+++ b/arch/sh/boards/mach-se/7724/setup.c
@@ -15,7 +15,7 @@
#include <linux/delay.h>
#include <linux/device.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/init.h>
#include <linux/input.h>
#include <linux/input/sh_keysc.h>
diff --git a/arch/sh/include/mach-common/mach/magicpanelr2.h b/arch/sh/include/mach-common/mach/magicpanelr2.h
index c2d218cea74b..29d86dd21b7b 100644
--- a/arch/sh/include/mach-common/mach/magicpanelr2.h
+++ b/arch/sh/include/mach-common/mach/magicpanelr2.h
@@ -10,8 +10,6 @@
#ifndef __ASM_SH_MAGICPANELR2_H
#define __ASM_SH_MAGICPANELR2_H
-#include <linux/gpio.h>
-
#define __IO_PREFIX mpr2
#include <asm/io_generic.h>
diff --git a/arch/sh/kernel/cpu/sh4a/setup-shx3.c b/arch/sh/kernel/cpu/sh4a/setup-shx3.c
index 7014d6d199b3..60be8dca54f6 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-shx3.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-shx3.c
@@ -9,7 +9,7 @@
#include <linux/serial.h>
#include <linux/serial_sci.h>
#include <linux/io.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/sh_timer.h>
#include <linux/sh_intc.h>
#include <cpu/shx3.h>
--
2.39.5
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH 05/13] mfd: replace linux/gpio.h inclusions
From: Arnd Bergmann @ 2026-06-29 13:26 UTC (permalink / raw)
To: linux-gpio
Cc: Arnd Bergmann, Bartosz Golaszewski, Andrew Lunn,
Sebastian Hesselbarth, Gregory Clement, Frank Li, Robert Jarzmik,
Krzysztof Kozlowski, Greg Ungerer, Thomas Bogendoerfer,
Hauke Mehrtens, Rafał Miłecki, Yoshinori Sato,
John Paul Adrian Glaubitz, Linus Walleij, Dmitry Torokhov,
Jakub Kicinski, Paolo Abeni, Dominik Brodowski, linux-kernel,
linux-arm-kernel, linux-samsung-soc, patches, linux-m68k,
linux-mips, linux-sh, linux-input, linux-media, netdev,
linux-sunxi, linux-phy, linux-rockchip, linux-sound
In-Reply-To: <20260629132633.1300009-1-arnd@kernel.org>
From: Arnd Bergmann <arnd@arndb.de>
linux/gpio.h should no longer be used, convert these instead to
either linux/gpio/consumer.h or linux/gpio/legacy.h as needed.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
drivers/mfd/aat2870-core.c | 2 +-
drivers/mfd/arizona-irq.c | 2 +-
drivers/mfd/lp3943.c | 2 +-
drivers/mfd/si476x-cmd.c | 2 +-
drivers/mfd/si476x-i2c.c | 2 +-
drivers/mfd/sm501.c | 2 +-
drivers/mfd/tps6105x.c | 2 +-
drivers/mfd/tps65911-comparator.c | 2 +-
drivers/mfd/wm8994-irq.c | 2 +-
include/linux/mfd/lp3943.h | 2 +-
include/linux/mfd/ti-lmu.h | 2 +-
include/linux/mfd/tps65910.h | 2 +-
include/linux/mfd/ucb1x00.h | 2 +-
13 files changed, 13 insertions(+), 13 deletions(-)
diff --git a/drivers/mfd/aat2870-core.c b/drivers/mfd/aat2870-core.c
index 34d66ba9646a..0d56cd6fbc6a 100644
--- a/drivers/mfd/aat2870-core.c
+++ b/drivers/mfd/aat2870-core.c
@@ -13,7 +13,7 @@
#include <linux/uaccess.h>
#include <linux/i2c.h>
#include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/mfd/core.h>
#include <linux/mfd/aat2870.h>
#include <linux/regulator/machine.h>
diff --git a/drivers/mfd/arizona-irq.c b/drivers/mfd/arizona-irq.c
index 544016d420fe..14f9cb2c4b67 100644
--- a/drivers/mfd/arizona-irq.c
+++ b/drivers/mfd/arizona-irq.c
@@ -8,7 +8,7 @@
*/
#include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
diff --git a/drivers/mfd/lp3943.c b/drivers/mfd/lp3943.c
index 6764553147e4..1918b5c7a5e7 100644
--- a/drivers/mfd/lp3943.c
+++ b/drivers/mfd/lp3943.c
@@ -28,7 +28,7 @@
*/
#include <linux/err.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/i2c.h>
#include <linux/mfd/core.h>
#include <linux/mfd/lp3943.h>
diff --git a/drivers/mfd/si476x-cmd.c b/drivers/mfd/si476x-cmd.c
index 3bb2decfebd3..8cbc0a386f3f 100644
--- a/drivers/mfd/si476x-cmd.c
+++ b/drivers/mfd/si476x-cmd.c
@@ -15,7 +15,7 @@
#include <linux/atomic.h>
#include <linux/i2c.h>
#include <linux/device.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/videodev2.h>
#include <linux/mfd/si476x-core.h>
diff --git a/drivers/mfd/si476x-i2c.c b/drivers/mfd/si476x-i2c.c
index 7ddc97dfc940..7be3460b0491 100644
--- a/drivers/mfd/si476x-i2c.c
+++ b/drivers/mfd/si476x-i2c.c
@@ -13,7 +13,7 @@
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
-#include <linux/gpio.h>
+#include <linux/gpio/legacy.h>
#include <linux/regulator/consumer.h>
#include <linux/i2c.h>
#include <linux/err.h>
diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c
index b5bda477ebfc..9d5bb67e8084 100644
--- a/drivers/mfd/sm501.c
+++ b/drivers/mfd/sm501.c
@@ -35,7 +35,7 @@ struct sm501_device {
struct sm501_gpio;
#ifdef CONFIG_MFD_SM501_GPIO
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
struct sm501_gpio_chip {
struct gpio_chip gpio;
diff --git a/drivers/mfd/tps6105x.c b/drivers/mfd/tps6105x.c
index e2f6858d101e..b11cd2c03311 100644
--- a/drivers/mfd/tps6105x.c
+++ b/drivers/mfd/tps6105x.c
@@ -16,7 +16,7 @@
#include <linux/init.h>
#include <linux/i2c.h>
#include <linux/regmap.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/err.h>
diff --git a/drivers/mfd/tps65911-comparator.c b/drivers/mfd/tps65911-comparator.c
index 7098712ea008..cc8545a972bc 100644
--- a/drivers/mfd/tps65911-comparator.c
+++ b/drivers/mfd/tps65911-comparator.c
@@ -14,7 +14,7 @@
#include <linux/err.h>
#include <linux/platform_device.h>
#include <linux/debugfs.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/mfd/tps65910.h>
#define COMP1 0
diff --git a/drivers/mfd/wm8994-irq.c b/drivers/mfd/wm8994-irq.c
index a46cea948763..a15483489b9d 100644
--- a/drivers/mfd/wm8994-irq.c
+++ b/drivers/mfd/wm8994-irq.c
@@ -9,7 +9,7 @@
#include <linux/kernel.h>
#include <linux/module.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/i2c.h>
#include <linux/irq.h>
#include <linux/mfd/core.h>
diff --git a/include/linux/mfd/lp3943.h b/include/linux/mfd/lp3943.h
index 402f01078fcc..5d2d172d3598 100644
--- a/include/linux/mfd/lp3943.h
+++ b/include/linux/mfd/lp3943.h
@@ -10,7 +10,7 @@
#ifndef __MFD_LP3943_H__
#define __MFD_LP3943_H__
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/regmap.h>
/* Registers */
diff --git a/include/linux/mfd/ti-lmu.h b/include/linux/mfd/ti-lmu.h
index 0bc0e8199798..5040c7d1e1b9 100644
--- a/include/linux/mfd/ti-lmu.h
+++ b/include/linux/mfd/ti-lmu.h
@@ -10,7 +10,7 @@
#ifndef __MFD_TI_LMU_H__
#define __MFD_TI_LMU_H__
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/notifier.h>
#include <linux/regmap.h>
#include <linux/gpio/consumer.h>
diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h
index f67ef0a4e041..3813fc9c2b55 100644
--- a/include/linux/mfd/tps65910.h
+++ b/include/linux/mfd/tps65910.h
@@ -12,7 +12,7 @@
#ifndef __LINUX_MFD_TPS65910_H
#define __LINUX_MFD_TPS65910_H
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/regmap.h>
/* TPS chip id list */
diff --git a/include/linux/mfd/ucb1x00.h b/include/linux/mfd/ucb1x00.h
index ede237384723..4ad54e22ed33 100644
--- a/include/linux/mfd/ucb1x00.h
+++ b/include/linux/mfd/ucb1x00.h
@@ -9,7 +9,7 @@
#include <linux/device.h>
#include <linux/mfd/mcp.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
#include <linux/gpio/driver.h>
#include <linux/mutex.h>
--
2.39.5
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ 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