* [PATCH v4 0/4] gpio: realtek: Add support for Realtek DHC RTD1625
@ 2026-06-22 9:23 Yu-Chun Lin
2026-06-22 9:23 ` [PATCH v4 1/4] dt-bindings: gpio: realtek: Add realtek,rtd1625-gpio Yu-Chun Lin
` (3 more replies)
0 siblings, 4 replies; 7+ messages in thread
From: Yu-Chun Lin @ 2026-06-22 9:23 UTC (permalink / raw)
To: linusw, brgl, robh, krzk+dt, conor+dt, afaerber, mwalle,
andriy.shevchenko, tychang
Cc: linux-gpio, devicetree, linux-kernel, linux-arm-kernel,
linux-realtek-soc, cy.huang, stanley_chang, eleanor.lin,
james.tai
This series adds GPIO support for the Realtek DHC RTD1625 SoC.
Unlike the existing driver (gpio-rtd.c) which uses shared bank registers,
the RTD1625 features a per-pin register architecture where each GPIO line
is managed by its own dedicated 32-bit control register. This distinct
hardware design requires a new, separate driver.
Best Regards,
Yu-Chun Lin
---
Patches 1-3 (fix, dt-bindings, and driver) are targeted for the GPIO tree.
Patch 4 (dts) will be taken via the Realtek SoC tree later. It is included
here for context.
Changes in v4:
- Reverted to the v2 approach (without gpio-regmap integration).
As a result, dropped patches 2, 3, and 4 from the v3 series.
Changes in Patch 3 (driver) since v2:
- IRQ handling fixes:
- Added enum rtd1625_irq_index with named constants.
- Documented the hardware quirk.
- Code cleanup and coding style improvements.
- Included the <linux/cleanup.h> header.
- Updated the copyright year.
- Retained Linus Walleij's Reviewed-by tag from v1, as the recent updates are
cleanups and fixes rather than major feature changes.
(Linus, please let me know if you have any concerns regarding this).
v3: https://lore.kernel.org/lkml/20260512033317.1602537-1-eleanor.lin@realtek.com/
v2: https://lore.kernel.org/lkml/20260408025243.1155482-1-eleanor.lin@realtek.com/
v1: https://lore.kernel.org/lkml/20260331113835.3510341-1-eleanor.lin@realtek.com/
Tzuyi Chang (2):
dt-bindings: gpio: realtek: Add realtek,rtd1625-gpio
gpio: realtek: Add driver for Realtek DHC RTD1625 SoC
Yu-Chun Lin (2):
gpio: Replace "default y" with "default ARCH_REALTEK" in Kconfig
arm64: dts: realtek: Add GPIO support for RTD1625
.../bindings/gpio/realtek,rtd1625-gpio.yaml | 71 ++
arch/arm64/boot/dts/realtek/kent.dtsi | 39 ++
drivers/gpio/Kconfig | 14 +-
drivers/gpio/Makefile | 1 +
drivers/gpio/gpio-rtd1625.c | 611 ++++++++++++++++++
5 files changed, 735 insertions(+), 1 deletion(-)
create mode 100644 Documentation/devicetree/bindings/gpio/realtek,rtd1625-gpio.yaml
create mode 100644 drivers/gpio/gpio-rtd1625.c
--
2.43.0
^ permalink raw reply [flat|nested] 7+ messages in thread
* [PATCH v4 1/4] dt-bindings: gpio: realtek: Add realtek,rtd1625-gpio
2026-06-22 9:23 [PATCH v4 0/4] gpio: realtek: Add support for Realtek DHC RTD1625 Yu-Chun Lin
@ 2026-06-22 9:23 ` Yu-Chun Lin
2026-06-22 9:39 ` sashiko-bot
2026-06-22 9:23 ` [PATCH v4 2/4] gpio: Replace "default y" with "default ARCH_REALTEK" in Kconfig Yu-Chun Lin
` (2 subsequent siblings)
3 siblings, 1 reply; 7+ messages in thread
From: Yu-Chun Lin @ 2026-06-22 9:23 UTC (permalink / raw)
To: linusw, brgl, robh, krzk+dt, conor+dt, afaerber, mwalle,
andriy.shevchenko, tychang
Cc: linux-gpio, devicetree, linux-kernel, linux-arm-kernel,
linux-realtek-soc, cy.huang, stanley_chang, eleanor.lin,
james.tai, Krzysztof Kozlowski
From: Tzuyi Chang <tychang@realtek.com>
Add the device tree bindings for the Realtek DHC (Digital Home Center)
RTD1625 GPIO controllers.
The RTD1625 GPIO controller features a per-pin register architecture
that differs significantly from previous generations. It utilizes
separate register blocks for GPIO configuration and interrupt control.
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Signed-off-by: Tzuyi Chang <tychang@realtek.com>
Signed-off-by: Yu-Chun Lin <eleanor.lin@realtek.com>
---
Changes in v4:
- None.
---
.../bindings/gpio/realtek,rtd1625-gpio.yaml | 71 +++++++++++++++++++
1 file changed, 71 insertions(+)
create mode 100644 Documentation/devicetree/bindings/gpio/realtek,rtd1625-gpio.yaml
diff --git a/Documentation/devicetree/bindings/gpio/realtek,rtd1625-gpio.yaml b/Documentation/devicetree/bindings/gpio/realtek,rtd1625-gpio.yaml
new file mode 100644
index 000000000000..f13c910b73c6
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/realtek,rtd1625-gpio.yaml
@@ -0,0 +1,71 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+# Copyright 2023 Realtek Semiconductor Corporation
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/gpio/realtek,rtd1625-gpio.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Realtek DHC RTD1625 GPIO controller
+
+maintainers:
+ - Tzuyi Chang <tychang@realtek.com>
+
+description: |
+ GPIO controller for the Realtek RTD1625 SoC, featuring a per-pin register
+ architecture that differs significantly from earlier RTD series controllers.
+ Each GPIO has dedicated registers for configuration (direction, input/output
+ values, debounce), and interrupt control supporting edge and level detection
+ modes.
+
+properties:
+ compatible:
+ enum:
+ - realtek,rtd1625-iso-gpio
+ - realtek,rtd1625-isom-gpio
+
+ reg:
+ maxItems: 1
+
+ interrupts:
+ items:
+ - description: Interrupt number of the assert GPIO interrupt, which is
+ triggered when there is a rising edge.
+ - description: Interrupt number of the deassert GPIO interrupt, which is
+ triggered when there is a falling edge.
+ - description: Interrupt number of the level-sensitive GPIO interrupt,
+ triggered by a configured logic level.
+
+ interrupt-controller: true
+
+ "#interrupt-cells":
+ const: 2
+
+ gpio-ranges: true
+
+ gpio-controller: true
+
+ "#gpio-cells":
+ const: 2
+
+required:
+ - compatible
+ - reg
+ - gpio-ranges
+ - gpio-controller
+ - "#gpio-cells"
+
+additionalProperties: false
+
+examples:
+ - |
+ gpio@89100 {
+ compatible = "realtek,rtd1625-isom-gpio";
+ reg = <0x89100 0x30>;
+ interrupt-parent = <&iso_m_irq_mux>;
+ interrupts = <0>, <1>, <2>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ gpio-ranges = <&isom_pinctrl 0 0 4>;
+ gpio-controller;
+ #gpio-cells = <2>;
+ };
--
2.43.0
^ permalink raw reply related [flat|nested] 7+ messages in thread
* [PATCH v4 2/4] gpio: Replace "default y" with "default ARCH_REALTEK" in Kconfig
2026-06-22 9:23 [PATCH v4 0/4] gpio: realtek: Add support for Realtek DHC RTD1625 Yu-Chun Lin
2026-06-22 9:23 ` [PATCH v4 1/4] dt-bindings: gpio: realtek: Add realtek,rtd1625-gpio Yu-Chun Lin
@ 2026-06-22 9:23 ` Yu-Chun Lin
2026-06-22 9:23 ` [PATCH v4 3/4] gpio: realtek: Add driver for Realtek DHC RTD1625 SoC Yu-Chun Lin
2026-06-22 9:23 ` [PATCH v4 4/4] arm64: dts: realtek: Add GPIO support for RTD1625 Yu-Chun Lin
3 siblings, 0 replies; 7+ messages in thread
From: Yu-Chun Lin @ 2026-06-22 9:23 UTC (permalink / raw)
To: linusw, brgl, robh, krzk+dt, conor+dt, afaerber, mwalle,
andriy.shevchenko, tychang
Cc: linux-gpio, devicetree, linux-kernel, linux-arm-kernel,
linux-realtek-soc, cy.huang, stanley_chang, eleanor.lin,
james.tai
Replace "default y" with "default ARCH_REALTEK" to avoid bloating the build
for non-Realtek platforms when COMPILE_TEST is enabled on other platforms.
Signed-off-by: Yu-Chun Lin <eleanor.lin@realtek.com>
---
Changes in v4:
- None.
---
drivers/gpio/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 28cf6d2e83c2..ed2bc3113374 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -646,7 +646,7 @@ config GPIO_ROCKCHIP
config GPIO_RTD
tristate "Realtek DHC GPIO support"
depends on ARCH_REALTEK || COMPILE_TEST
- default y
+ default ARCH_REALTEK
select GPIOLIB_IRQCHIP
help
This option enables support for GPIOs found on Realtek DHC(Digital
--
2.43.0
^ permalink raw reply related [flat|nested] 7+ messages in thread
* [PATCH v4 3/4] gpio: realtek: Add driver for Realtek DHC RTD1625 SoC
2026-06-22 9:23 [PATCH v4 0/4] gpio: realtek: Add support for Realtek DHC RTD1625 Yu-Chun Lin
2026-06-22 9:23 ` [PATCH v4 1/4] dt-bindings: gpio: realtek: Add realtek,rtd1625-gpio Yu-Chun Lin
2026-06-22 9:23 ` [PATCH v4 2/4] gpio: Replace "default y" with "default ARCH_REALTEK" in Kconfig Yu-Chun Lin
@ 2026-06-22 9:23 ` Yu-Chun Lin
2026-06-22 9:48 ` sashiko-bot
2026-06-22 9:23 ` [PATCH v4 4/4] arm64: dts: realtek: Add GPIO support for RTD1625 Yu-Chun Lin
3 siblings, 1 reply; 7+ messages in thread
From: Yu-Chun Lin @ 2026-06-22 9:23 UTC (permalink / raw)
To: linusw, brgl, robh, krzk+dt, conor+dt, afaerber, mwalle,
andriy.shevchenko, tychang
Cc: linux-gpio, devicetree, linux-kernel, linux-arm-kernel,
linux-realtek-soc, cy.huang, stanley_chang, eleanor.lin,
james.tai
From: Tzuyi Chang <tychang@realtek.com>
Add support for the GPIO controller found on Realtek DHC RTD1625 SoCs.
Unlike the existing Realtek GPIO driver (drivers/gpio/gpio-rtd.c),
which manages pins via shared bank registers, the RTD1625 introduces
a per-pin register architecture. Each GPIO line now has its own
dedicated 32-bit control register to manage configuration independently,
including direction, output value, input value, interrupt enable, and
debounce. Therefore, this distinct hardware design requires a separate
driver.
Additionally, the RTD1625 GPIO controller has a specific hardware quirk:
it fires both 'assert' and 'de-assert' interrupts simultaneously on any
edge toggle. To handle this, we utilize the polarity register to route
the requested edge (rising/falling) to the 'assert' IRQ line. The driver
then filters out the unwanted 'de-assert' interrupt in the IRQ handler
and pre-clears edge interrupts to prevent interrupt storms caused by
unhandled dropped interrupts.
Interrupt support is optional for this device, matching the dt-bindings.
If the interrupts property is not provided, the driver simply skips IRQ
initialization and operates purely as a basic GPIO controller.
Reviewed-by: Linus Walleij <linusw@kernel.org>
Signed-off-by: Tzuyi Chang <tychang@realtek.com>
Co-developed-by: Yu-Chun Lin <eleanor.lin@realtek.com>
Signed-off-by: Yu-Chun Lin <eleanor.lin@realtek.com>
---
Changes between v2 and v4:
IRQ Handling Fix
- Added enum rtd1625_irq_index with named constants to replace magic array
indices 0/1/2.
- Documented hardware quirk.
Coding style & cleanup:
- In rtd1625_gpio_irq_set_type(), using return directly in each switch case.
- Changed int loop counters to unsigned int.
- Replaced devm_kzalloc() with devm_kcalloc() in probe.
- Moved of_device_id table closer to its user.
- Added static to DEFINE_NOIRQ_DEV_PM_OPS.
- Formatting consistency: zero-padded hex constants.
New header:
- Added #include <linux/cleanup.h> (required for the guard() / scoped_guard()
macros).
Copyright year updated:
- 2023 -> 2023-2026.
---
drivers/gpio/Kconfig | 12 +
drivers/gpio/Makefile | 1 +
drivers/gpio/gpio-rtd1625.c | 611 ++++++++++++++++++++++++++++++++++++
3 files changed, 624 insertions(+)
create mode 100644 drivers/gpio/gpio-rtd1625.c
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index ed2bc3113374..f03c05288376 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -656,6 +656,18 @@ config GPIO_RTD
Say yes here to support GPIO functionality and GPIO interrupt on
Realtek DHC SoCs.
+config GPIO_RTD1625
+ tristate "Realtek DHC RTD1625 GPIO support"
+ depends on ARCH_REALTEK || COMPILE_TEST
+ default ARCH_REALTEK
+ select GPIOLIB_IRQCHIP
+ help
+ This option enables support for the GPIO controller on Realtek
+ DHC (Digital Home Center) RTD1625 SoC.
+
+ Say yes here to support both basic GPIO line functionality
+ and GPIO interrupt handling capabilities for this platform.
+
config GPIO_SAMA5D2_PIOBU
tristate "SAMA5D2 PIOBU GPIO support"
depends on OF
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 4d0e900402fc..fa14581e3995 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -160,6 +160,7 @@ obj-$(CONFIG_GPIO_REALTEK_OTTO) += gpio-realtek-otto.o
obj-$(CONFIG_GPIO_REG) += gpio-reg.o
obj-$(CONFIG_GPIO_ROCKCHIP) += gpio-rockchip.o
obj-$(CONFIG_GPIO_RTD) += gpio-rtd.o
+obj-$(CONFIG_GPIO_RTD1625) += gpio-rtd1625.o
obj-$(CONFIG_ARCH_SA1100) += gpio-sa1100.o
obj-$(CONFIG_GPIO_SAMA5D2_PIOBU) += gpio-sama5d2-piobu.o
obj-$(CONFIG_GPIO_SCH311X) += gpio-sch311x.o
diff --git a/drivers/gpio/gpio-rtd1625.c b/drivers/gpio/gpio-rtd1625.c
new file mode 100644
index 000000000000..409e540bf40b
--- /dev/null
+++ b/drivers/gpio/gpio-rtd1625.c
@@ -0,0 +1,611 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Realtek DHC RTD1625 gpio driver
+ *
+ * Copyright (c) 2023-2026 Realtek Semiconductor Corp.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/cleanup.h>
+#include <linux/gpio/driver.h>
+#include <linux/interrupt.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#define RTD1625_GPIO_DIR BIT(0)
+#define RTD1625_GPIO_OUT BIT(2)
+#define RTD1625_GPIO_IN BIT(4)
+#define RTD1625_GPIO_EDGE_INT_DP BIT(6)
+#define RTD1625_GPIO_EDGE_INT_EN BIT(8)
+#define RTD1625_GPIO_LEVEL_INT_EN BIT(16)
+#define RTD1625_GPIO_LEVEL_INT_DP BIT(18)
+#define RTD1625_GPIO_DEBOUNCE GENMASK(30, 28)
+#define RTD1625_GPIO_DEBOUNCE_WREN BIT(31)
+
+#define RTD1625_GPIO_WREN(x) ((x) << 1)
+
+/* Write-enable masks for all GPIO configs and reserved hardware bits */
+#define RTD1625_ISO_GPIO_WREN_ALL 0x8000aa8a
+#define RTD1625_ISOM_GPIO_WREN_ALL 0x800aaa8a
+
+#define RTD1625_GPIO_DEBOUNCE_1US 0
+#define RTD1625_GPIO_DEBOUNCE_10US 1
+#define RTD1625_GPIO_DEBOUNCE_100US 2
+#define RTD1625_GPIO_DEBOUNCE_1MS 3
+#define RTD1625_GPIO_DEBOUNCE_10MS 4
+#define RTD1625_GPIO_DEBOUNCE_20MS 5
+#define RTD1625_GPIO_DEBOUNCE_30MS 6
+#define RTD1625_GPIO_DEBOUNCE_50MS 7
+
+#define GPIO_CONTROL(gpio) ((gpio) * 4)
+
+enum rtd1625_irq_index {
+ RTD1625_IRQ_ASSERT,
+ RTD1625_IRQ_DEASSERT,
+ RTD1625_IRQ_LEVEL,
+ RTD1625_MAX_IRQS
+};
+
+/**
+ * struct rtd1625_gpio_info - Specific GPIO register information
+ * @num_gpios: The number of GPIOs
+ * @irq_type_support: Supported IRQ types
+ * @gpa_offset: Offset for GPIO assert interrupt status registers
+ * @gpda_offset: Offset for GPIO deassert interrupt status registers
+ * @level_offset: Offset of level interrupt status register
+ * @write_en_all: Write-enable mask for all configurable bits
+ */
+struct rtd1625_gpio_info {
+ unsigned int num_gpios;
+ unsigned int irq_type_support;
+ unsigned int base_offset;
+ unsigned int gpa_offset;
+ unsigned int gpda_offset;
+ unsigned int level_offset;
+ unsigned int write_en_all;
+};
+
+struct rtd1625_gpio {
+ struct gpio_chip gpio_chip;
+ const struct rtd1625_gpio_info *info;
+ void __iomem *base;
+ void __iomem *irq_base;
+ unsigned int irqs[RTD1625_MAX_IRQS];
+ raw_spinlock_t lock;
+ unsigned int *save_regs;
+};
+
+static unsigned int rtd1625_gpio_gpa_offset(struct rtd1625_gpio *data, unsigned int offset)
+{
+ return data->info->gpa_offset + ((offset / 32) * 4);
+}
+
+static unsigned int rtd1625_gpio_gpda_offset(struct rtd1625_gpio *data, unsigned int offset)
+{
+ return data->info->gpda_offset + ((offset / 32) * 4);
+}
+
+static unsigned int rtd1625_gpio_level_offset(struct rtd1625_gpio *data, unsigned int offset)
+{
+ return data->info->level_offset + ((offset / 32) * 4);
+}
+
+static int rtd1625_gpio_set_debounce(struct gpio_chip *chip, unsigned int offset,
+ unsigned int debounce)
+{
+ struct rtd1625_gpio *data = gpiochip_get_data(chip);
+ u8 deb_val;
+ u32 val;
+
+ switch (debounce) {
+ case 1:
+ deb_val = RTD1625_GPIO_DEBOUNCE_1US;
+ break;
+ case 10:
+ deb_val = RTD1625_GPIO_DEBOUNCE_10US;
+ break;
+ case 100:
+ deb_val = RTD1625_GPIO_DEBOUNCE_100US;
+ break;
+ case 1000:
+ deb_val = RTD1625_GPIO_DEBOUNCE_1MS;
+ break;
+ case 10000:
+ deb_val = RTD1625_GPIO_DEBOUNCE_10MS;
+ break;
+ case 20000:
+ deb_val = RTD1625_GPIO_DEBOUNCE_20MS;
+ break;
+ case 30000:
+ deb_val = RTD1625_GPIO_DEBOUNCE_30MS;
+ break;
+ case 50000:
+ deb_val = RTD1625_GPIO_DEBOUNCE_50MS;
+ break;
+ default:
+ return -ENOTSUPP;
+ }
+
+ val = FIELD_PREP(RTD1625_GPIO_DEBOUNCE, deb_val) | RTD1625_GPIO_DEBOUNCE_WREN;
+
+ guard(raw_spinlock_irqsave)(&data->lock);
+
+ writel_relaxed(val, data->base + GPIO_CONTROL(offset));
+
+ return 0;
+}
+
+static int rtd1625_gpio_set_config(struct gpio_chip *chip, unsigned int offset,
+ unsigned long config)
+{
+ u32 debounce;
+
+ if (pinconf_to_config_param(config) == PIN_CONFIG_INPUT_DEBOUNCE) {
+ debounce = pinconf_to_config_argument(config);
+ return rtd1625_gpio_set_debounce(chip, offset, debounce);
+ }
+
+ return gpiochip_generic_config(chip, offset, config);
+}
+
+static int rtd1625_gpio_set(struct gpio_chip *chip, unsigned int offset, int value)
+{
+ struct rtd1625_gpio *data = gpiochip_get_data(chip);
+ u32 val = RTD1625_GPIO_WREN(RTD1625_GPIO_OUT);
+
+ if (value)
+ val |= RTD1625_GPIO_OUT;
+
+ guard(raw_spinlock_irqsave)(&data->lock);
+
+ writel_relaxed(val, data->base + GPIO_CONTROL(offset));
+
+ return 0;
+}
+
+static int rtd1625_gpio_get(struct gpio_chip *chip, unsigned int offset)
+{
+ struct rtd1625_gpio *data = gpiochip_get_data(chip);
+ u32 val;
+
+ guard(raw_spinlock_irqsave)(&data->lock);
+
+ val = readl_relaxed(data->base + GPIO_CONTROL(offset));
+
+ if (val & RTD1625_GPIO_DIR)
+ return !!(val & RTD1625_GPIO_OUT);
+ else
+ return !!(val & RTD1625_GPIO_IN);
+}
+
+static int rtd1625_gpio_get_direction(struct gpio_chip *chip, unsigned int offset)
+{
+ struct rtd1625_gpio *data = gpiochip_get_data(chip);
+ u32 val;
+
+ guard(raw_spinlock_irqsave)(&data->lock);
+
+ val = readl_relaxed(data->base + GPIO_CONTROL(offset));
+
+ if (val & RTD1625_GPIO_DIR)
+ return GPIO_LINE_DIRECTION_OUT;
+
+ return GPIO_LINE_DIRECTION_IN;
+}
+
+static int rtd1625_gpio_set_direction(struct gpio_chip *chip, unsigned int offset, bool out)
+{
+ struct rtd1625_gpio *data = gpiochip_get_data(chip);
+ u32 val = RTD1625_GPIO_WREN(RTD1625_GPIO_DIR);
+
+ if (out)
+ val |= RTD1625_GPIO_DIR;
+
+ guard(raw_spinlock_irqsave)(&data->lock);
+
+ writel_relaxed(val, data->base + GPIO_CONTROL(offset));
+
+ return 0;
+}
+
+static int rtd1625_gpio_direction_input(struct gpio_chip *chip, unsigned int offset)
+{
+ return rtd1625_gpio_set_direction(chip, offset, false);
+}
+
+static int rtd1625_gpio_direction_output(struct gpio_chip *chip, unsigned int offset, int value)
+{
+ rtd1625_gpio_set(chip, offset, value);
+
+ return rtd1625_gpio_set_direction(chip, offset, true);
+}
+
+static void rtd1625_gpio_irq_handle(struct irq_desc *desc)
+{
+ unsigned int (*get_reg_offset)(struct rtd1625_gpio *gpio, unsigned int offset);
+ struct rtd1625_gpio *data = irq_desc_get_handler_data(desc);
+ struct irq_domain *domain = data->gpio_chip.irq.domain;
+ struct irq_chip *chip = irq_desc_get_chip(desc);
+ unsigned int irq = irq_desc_get_irq(desc);
+ unsigned long status;
+ unsigned int reg_offset, i, j;
+ unsigned int girq;
+ irq_hw_number_t hwirq;
+ u32 irq_type;
+
+ if (irq == data->irqs[RTD1625_IRQ_ASSERT])
+ get_reg_offset = &rtd1625_gpio_gpa_offset;
+ else if (irq == data->irqs[RTD1625_IRQ_DEASSERT])
+ get_reg_offset = &rtd1625_gpio_gpda_offset;
+ else if (irq == data->irqs[2])
+ get_reg_offset = &rtd1625_gpio_level_offset;
+ else
+ return;
+
+ chained_irq_enter(chip, desc);
+
+ for (i = 0; i < data->info->num_gpios; i += 32) {
+ reg_offset = get_reg_offset(data, i);
+ status = readl_relaxed(data->irq_base + reg_offset);
+
+ /*
+ * Hardware quirk: The controller fires both "assert" and "de-assert"
+ * interrupts simultaneously on any edge toggle.
+ * We must pre-clear edge interrupts here. If we drop an unwanted
+ * de-assert interrupt below, it will never reach the IRQ core
+ * (generic_handle_domain_irq), meaning ->irq_ack() won't be called.
+ * Failing to clear it here leads to an interrupt storm.
+ */
+ if (irq != data->irqs[RTD1625_IRQ_LEVEL])
+ writel_relaxed(status, data->irq_base + reg_offset);
+
+ for_each_set_bit(j, &status, 32) {
+ hwirq = i + j;
+ girq = irq_find_mapping(domain, hwirq);
+ irq_type = irq_get_trigger_type(girq);
+
+ /*
+ * Filter out the hardware-forced de-assert interrupt unless
+ * the user explicitly requested IRQ_TYPE_EDGE_BOTH.
+ */
+ if (irq == data->irqs[RTD1625_IRQ_DEASSERT] &&
+ irq_type != IRQ_TYPE_EDGE_BOTH)
+ continue;
+
+ generic_handle_domain_irq(domain, hwirq);
+ }
+ }
+
+ chained_irq_exit(chip, desc);
+}
+
+static void rtd1625_gpio_ack_irq(struct irq_data *d)
+{
+ struct rtd1625_gpio *data = irq_data_get_irq_chip_data(d);
+ irq_hw_number_t hwirq = irqd_to_hwirq(d);
+ u32 irq_type = irqd_get_trigger_type(d);
+ u32 bit_mask = BIT(hwirq % 32);
+ int reg_offset;
+
+ if (irq_type & IRQ_TYPE_LEVEL_MASK) {
+ reg_offset = rtd1625_gpio_level_offset(data, hwirq);
+ writel_relaxed(bit_mask, data->irq_base + reg_offset);
+ }
+}
+
+static void rtd1625_gpio_enable_edge_irq(struct rtd1625_gpio *data, irq_hw_number_t hwirq)
+{
+ int gpda_reg_offset = rtd1625_gpio_gpda_offset(data, hwirq);
+ int gpa_reg_offset = rtd1625_gpio_gpa_offset(data, hwirq);
+ u32 clr_mask = BIT(hwirq % 32);
+ u32 val;
+
+ guard(raw_spinlock_irqsave)(&data->lock);
+
+ writel_relaxed(clr_mask, data->irq_base + gpa_reg_offset);
+ writel_relaxed(clr_mask, data->irq_base + gpda_reg_offset);
+ val = RTD1625_GPIO_EDGE_INT_EN | RTD1625_GPIO_WREN(RTD1625_GPIO_EDGE_INT_EN);
+ writel_relaxed(val, data->base + GPIO_CONTROL(hwirq));
+}
+
+static void rtd1625_gpio_disable_edge_irq(struct rtd1625_gpio *data, irq_hw_number_t hwirq)
+{
+ u32 val;
+
+ guard(raw_spinlock_irqsave)(&data->lock);
+
+ val = RTD1625_GPIO_WREN(RTD1625_GPIO_EDGE_INT_EN);
+ writel_relaxed(val, data->base + GPIO_CONTROL(hwirq));
+}
+
+static void rtd1625_gpio_enable_level_irq(struct rtd1625_gpio *data, irq_hw_number_t hwirq)
+{
+ int level_reg_offset = rtd1625_gpio_level_offset(data, hwirq);
+ u32 clr_mask = BIT(hwirq % 32);
+ u32 val;
+
+ guard(raw_spinlock_irqsave)(&data->lock);
+
+ writel_relaxed(clr_mask, data->irq_base + level_reg_offset);
+ val = RTD1625_GPIO_LEVEL_INT_EN | RTD1625_GPIO_WREN(RTD1625_GPIO_LEVEL_INT_EN);
+ writel_relaxed(val, data->base + GPIO_CONTROL(hwirq));
+}
+
+static void rtd1625_gpio_disable_level_irq(struct rtd1625_gpio *data, irq_hw_number_t hwirq)
+{
+ u32 val;
+
+ guard(raw_spinlock_irqsave)(&data->lock);
+
+ val = RTD1625_GPIO_WREN(RTD1625_GPIO_LEVEL_INT_EN);
+ writel_relaxed(val, data->base + GPIO_CONTROL(hwirq));
+}
+
+static void rtd1625_gpio_enable_irq(struct irq_data *d)
+{
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct rtd1625_gpio *data = gpiochip_get_data(gc);
+ irq_hw_number_t hwirq = irqd_to_hwirq(d);
+ u32 irq_type = irqd_get_trigger_type(d);
+
+ gpiochip_enable_irq(gc, hwirq);
+
+ if (irq_type & IRQ_TYPE_EDGE_BOTH)
+ rtd1625_gpio_enable_edge_irq(data, hwirq);
+ else if (irq_type & IRQ_TYPE_LEVEL_MASK)
+ rtd1625_gpio_enable_level_irq(data, hwirq);
+}
+
+static void rtd1625_gpio_disable_irq(struct irq_data *d)
+{
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct rtd1625_gpio *data = gpiochip_get_data(gc);
+ irq_hw_number_t hwirq = irqd_to_hwirq(d);
+ u32 irq_type = irqd_get_trigger_type(d);
+
+ if (irq_type & IRQ_TYPE_EDGE_BOTH)
+ rtd1625_gpio_disable_edge_irq(data, hwirq);
+ else if (irq_type & IRQ_TYPE_LEVEL_MASK)
+ rtd1625_gpio_disable_level_irq(data, hwirq);
+
+ gpiochip_disable_irq(gc, hwirq);
+}
+
+static int rtd1625_gpio_irq_set_level_type(struct irq_data *d, bool level)
+{
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct rtd1625_gpio *data = gpiochip_get_data(gc);
+ irq_hw_number_t hwirq = irqd_to_hwirq(d);
+ u32 val = RTD1625_GPIO_WREN(RTD1625_GPIO_LEVEL_INT_DP);
+
+ if (!(data->info->irq_type_support & IRQ_TYPE_LEVEL_MASK))
+ return -EINVAL;
+
+ if (level)
+ val |= RTD1625_GPIO_LEVEL_INT_DP;
+
+ scoped_guard(raw_spinlock_irqsave, &data->lock)
+ writel_relaxed(val, data->base + GPIO_CONTROL(hwirq));
+
+ irq_set_handler_locked(d, handle_level_irq);
+
+ return 0;
+}
+
+static int rtd1625_gpio_irq_set_edge_type(struct irq_data *d, bool polarity)
+{
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct rtd1625_gpio *data = gpiochip_get_data(gc);
+ irq_hw_number_t hwirq = irqd_to_hwirq(d);
+ u32 val = RTD1625_GPIO_WREN(RTD1625_GPIO_EDGE_INT_DP);
+
+ if (!(data->info->irq_type_support & IRQ_TYPE_EDGE_BOTH))
+ return -EINVAL;
+
+ if (polarity)
+ val |= RTD1625_GPIO_EDGE_INT_DP;
+
+ scoped_guard(raw_spinlock_irqsave, &data->lock)
+ writel_relaxed(val, data->base + GPIO_CONTROL(hwirq));
+
+ irq_set_handler_locked(d, handle_edge_irq);
+
+ return 0;
+}
+
+static int rtd1625_gpio_irq_set_type(struct irq_data *d, unsigned int type)
+{
+ switch (type & IRQ_TYPE_SENSE_MASK) {
+ case IRQ_TYPE_EDGE_RISING:
+ return rtd1625_gpio_irq_set_edge_type(d, 1);
+
+ case IRQ_TYPE_EDGE_FALLING:
+ return rtd1625_gpio_irq_set_edge_type(d, 0);
+
+ case IRQ_TYPE_EDGE_BOTH:
+ return rtd1625_gpio_irq_set_edge_type(d, 1);
+
+ case IRQ_TYPE_LEVEL_HIGH:
+ return rtd1625_gpio_irq_set_level_type(d, 0);
+
+ case IRQ_TYPE_LEVEL_LOW:
+ return rtd1625_gpio_irq_set_level_type(d, 1);
+
+ default:
+ return -EINVAL;
+ }
+}
+
+static struct irq_chip rtd1625_iso_gpio_irq_chip = {
+ .name = "rtd1625-gpio",
+ .irq_ack = rtd1625_gpio_ack_irq,
+ .irq_mask = rtd1625_gpio_disable_irq,
+ .irq_unmask = rtd1625_gpio_enable_irq,
+ .irq_set_type = rtd1625_gpio_irq_set_type,
+ .flags = IRQCHIP_IMMUTABLE | IRQCHIP_SKIP_SET_WAKE,
+ GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
+
+static int rtd1625_gpio_setup_irq(struct platform_device *pdev, struct rtd1625_gpio *data)
+{
+ struct gpio_irq_chip *irq_chip;
+ unsigned int num_irqs;
+ int irq;
+
+ /*
+ * Interrupt support is optional. All IRQs must be provided together.
+ * If index 0 is missing, we assume no interrupts are configured in DT
+ * and fall back to basic GPIO operation.
+ */
+ irq = platform_get_irq_optional(pdev, 0);
+ if (irq == -ENXIO)
+ return 0;
+ if (irq < 0)
+ return irq;
+
+ num_irqs = (data->info->irq_type_support & IRQ_TYPE_LEVEL_MASK) ? 3 : 2;
+ data->irqs[RTD1625_IRQ_ASSERT] = irq;
+
+ for (unsigned int i = 1; i < num_irqs; i++) {
+ irq = platform_get_irq(pdev, i);
+ if (irq < 0)
+ return irq;
+ data->irqs[i] = irq;
+ }
+
+ irq_chip = &data->gpio_chip.irq;
+ irq_chip->handler = handle_bad_irq;
+ irq_chip->default_type = IRQ_TYPE_NONE;
+ irq_chip->parent_handler = rtd1625_gpio_irq_handle;
+ irq_chip->parent_handler_data = data;
+ irq_chip->num_parents = num_irqs;
+ irq_chip->parents = data->irqs;
+
+ gpio_irq_chip_set_chip(irq_chip, &rtd1625_iso_gpio_irq_chip);
+
+ return 0;
+}
+
+static int rtd1625_gpio_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct rtd1625_gpio *data;
+ void __iomem *irq_base;
+ int ret;
+
+ data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ data->info = device_get_match_data(dev);
+ if (!data->info)
+ return -EINVAL;
+
+ raw_spin_lock_init(&data->lock);
+
+ irq_base = devm_platform_ioremap_resource(pdev, 0);
+ if (IS_ERR(irq_base))
+ return PTR_ERR(irq_base);
+
+ data->irq_base = irq_base;
+ data->base = irq_base + data->info->base_offset;
+
+ data->save_regs = devm_kcalloc(dev, data->info->num_gpios, sizeof(*data->save_regs),
+ GFP_KERNEL);
+ if (!data->save_regs)
+ return -ENOMEM;
+
+ data->gpio_chip.label = dev_name(dev);
+ data->gpio_chip.base = -1;
+ data->gpio_chip.ngpio = data->info->num_gpios;
+ data->gpio_chip.request = gpiochip_generic_request;
+ data->gpio_chip.free = gpiochip_generic_free;
+ data->gpio_chip.get_direction = rtd1625_gpio_get_direction;
+ data->gpio_chip.direction_input = rtd1625_gpio_direction_input;
+ data->gpio_chip.direction_output = rtd1625_gpio_direction_output;
+ data->gpio_chip.set = rtd1625_gpio_set;
+ data->gpio_chip.get = rtd1625_gpio_get;
+ data->gpio_chip.set_config = rtd1625_gpio_set_config;
+ data->gpio_chip.parent = dev;
+
+ ret = rtd1625_gpio_setup_irq(pdev, data);
+ if (ret)
+ return ret;
+
+ platform_set_drvdata(pdev, data);
+
+ return devm_gpiochip_add_data(dev, &data->gpio_chip, data);
+}
+
+static const struct rtd1625_gpio_info rtd1625_iso_gpio_info = {
+ .num_gpios = 166,
+ .irq_type_support = IRQ_TYPE_EDGE_BOTH,
+ .base_offset = 0x100,
+ .gpa_offset = 0x000,
+ .gpda_offset = 0x020,
+ .write_en_all = RTD1625_ISO_GPIO_WREN_ALL,
+};
+
+static const struct rtd1625_gpio_info rtd1625_isom_gpio_info = {
+ .num_gpios = 4,
+ .irq_type_support = IRQ_TYPE_EDGE_BOTH | IRQ_TYPE_LEVEL_LOW |
+ IRQ_TYPE_LEVEL_HIGH,
+ .base_offset = 0x20,
+ .gpa_offset = 0x00,
+ .gpda_offset = 0x04,
+ .level_offset = 0x18,
+ .write_en_all = RTD1625_ISOM_GPIO_WREN_ALL,
+};
+
+static int rtd1625_gpio_suspend(struct device *dev)
+{
+ struct rtd1625_gpio *data = dev_get_drvdata(dev);
+ const struct rtd1625_gpio_info *info = data->info;
+
+ for (unsigned int i = 0; i < info->num_gpios; i++)
+ data->save_regs[i] = readl_relaxed(data->base + GPIO_CONTROL(i));
+
+ return 0;
+}
+
+static int rtd1625_gpio_resume(struct device *dev)
+{
+ struct rtd1625_gpio *data = dev_get_drvdata(dev);
+ const struct rtd1625_gpio_info *info = data->info;
+
+ for (unsigned int i = 0; i < info->num_gpios; i++)
+ writel_relaxed(data->save_regs[i] | info->write_en_all,
+ data->base + GPIO_CONTROL(i));
+
+ return 0;
+}
+
+static DEFINE_NOIRQ_DEV_PM_OPS(rtd1625_gpio_pm_ops, rtd1625_gpio_suspend, rtd1625_gpio_resume);
+
+static const struct of_device_id rtd1625_gpio_of_matches[] = {
+ { .compatible = "realtek,rtd1625-iso-gpio", .data = &rtd1625_iso_gpio_info },
+ { .compatible = "realtek,rtd1625-isom-gpio", .data = &rtd1625_isom_gpio_info },
+ { }
+};
+MODULE_DEVICE_TABLE(of, rtd1625_gpio_of_matches);
+
+static struct platform_driver rtd1625_gpio_platform_driver = {
+ .driver = {
+ .name = "gpio-rtd1625",
+ .of_match_table = rtd1625_gpio_of_matches,
+ .pm = pm_sleep_ptr(&rtd1625_gpio_pm_ops),
+ },
+ .probe = rtd1625_gpio_probe,
+};
+module_platform_driver(rtd1625_gpio_platform_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Realtek Semiconductor Corporation");
+MODULE_DESCRIPTION("Realtek DHC SoC RTD1625 gpio driver");
--
2.43.0
^ permalink raw reply related [flat|nested] 7+ messages in thread
* [PATCH v4 4/4] arm64: dts: realtek: Add GPIO support for RTD1625
2026-06-22 9:23 [PATCH v4 0/4] gpio: realtek: Add support for Realtek DHC RTD1625 Yu-Chun Lin
` (2 preceding siblings ...)
2026-06-22 9:23 ` [PATCH v4 3/4] gpio: realtek: Add driver for Realtek DHC RTD1625 SoC Yu-Chun Lin
@ 2026-06-22 9:23 ` Yu-Chun Lin
3 siblings, 0 replies; 7+ messages in thread
From: Yu-Chun Lin @ 2026-06-22 9:23 UTC (permalink / raw)
To: linusw, brgl, robh, krzk+dt, conor+dt, afaerber, mwalle,
andriy.shevchenko, tychang
Cc: linux-gpio, devicetree, linux-kernel, linux-arm-kernel,
linux-realtek-soc, cy.huang, stanley_chang, eleanor.lin,
james.tai, Bartosz Golaszewski
Add the GPIO node for the Realtek RTD1625 SoC.
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Signed-off-by: Yu-Chun Lin <eleanor.lin@realtek.com>
---
Changes in v4:
- None.
---
arch/arm64/boot/dts/realtek/kent.dtsi | 39 +++++++++++++++++++++++++++
1 file changed, 39 insertions(+)
diff --git a/arch/arm64/boot/dts/realtek/kent.dtsi b/arch/arm64/boot/dts/realtek/kent.dtsi
index 8d4293cd4c03..228b82dfdb7a 100644
--- a/arch/arm64/boot/dts/realtek/kent.dtsi
+++ b/arch/arm64/boot/dts/realtek/kent.dtsi
@@ -151,6 +151,37 @@ uart0: serial@7800 {
status = "disabled";
};
+ gpio: gpio@31000 {
+ compatible = "realtek,rtd1625-iso-gpio";
+ reg = <0x31000 0x398>;
+ gpio-controller;
+ gpio-ranges = <&isom_pinctrl 0 0 2>,
+ <&ve4_pinctrl 2 0 6>,
+ <&iso_pinctrl 8 0 4>,
+ <&ve4_pinctrl 12 6 2>,
+ <&main2_pinctrl 14 0 2>,
+ <&ve4_pinctrl 16 8 4>,
+ <&main2_pinctrl 20 2 3>,
+ <&ve4_pinctrl 23 12 3>,
+ <&iso_pinctrl 26 4 2>,
+ <&isom_pinctrl 28 2 2>,
+ <&ve4_pinctrl 30 15 6>,
+ <&main2_pinctrl 36 5 6>,
+ <&ve4_pinctrl 42 21 3>,
+ <&iso_pinctrl 45 6 6>,
+ <&ve4_pinctrl 51 24 1>,
+ <&iso_pinctrl 52 12 1>,
+ <&ve4_pinctrl 53 25 11>,
+ <&main2_pinctrl 64 11 28>,
+ <&ve4_pinctrl 92 36 2>,
+ <&iso_pinctrl 94 13 19>,
+ <&iso_pinctrl 128 32 4>,
+ <&ve4_pinctrl 132 38 13>,
+ <&iso_pinctrl 145 36 19>,
+ <&ve4_pinctrl 164 51 2>;
+ #gpio-cells = <2>;
+ };
+
iso_pinctrl: pinctrl@4e000 {
compatible = "realtek,rtd1625-iso-pinctrl";
reg = <0x4e000 0x1a4>;
@@ -161,6 +192,14 @@ main2_pinctrl: pinctrl@4f200 {
reg = <0x4f200 0x50>;
};
+ iso_m_gpio: gpio@89100 {
+ compatible = "realtek,rtd1625-isom-gpio";
+ reg = <0x89100 0x30>;
+ gpio-controller;
+ gpio-ranges = <&isom_pinctrl 0 0 4>;
+ #gpio-cells = <2>;
+ };
+
isom_pinctrl: pinctrl@146200 {
compatible = "realtek,rtd1625-isom-pinctrl";
reg = <0x146200 0x34>;
--
2.43.0
^ permalink raw reply related [flat|nested] 7+ messages in thread
* Re: [PATCH v4 1/4] dt-bindings: gpio: realtek: Add realtek,rtd1625-gpio
2026-06-22 9:23 ` [PATCH v4 1/4] dt-bindings: gpio: realtek: Add realtek,rtd1625-gpio Yu-Chun Lin
@ 2026-06-22 9:39 ` sashiko-bot
0 siblings, 0 replies; 7+ messages in thread
From: sashiko-bot @ 2026-06-22 9:39 UTC (permalink / raw)
To: Yu-Chun Lin; +Cc: devicetree, robh, conor+dt
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] The binding defines the GPIO controller as an interrupt controller but fails to include `interrupt-controller` and `#interrupt-cells` in the `required` list.
--
commit c069bdfb1e6325b567084e608f2dc45bf15e2fcf
Author: Tzuyi Chang <tychang@realtek.com>
dt-bindings: gpio: realtek: Add realtek,rtd1625-gpio
This commit adds the device tree bindings for the Realtek DHC RTD1625 GPIO
controllers. It introduces support for a new per-pin register architecture
that includes separate register blocks for configuration and interrupt control.
> diff --git a/Documentation/devicetree/bindings/gpio/realtek,rtd1625-gpio.yaml b/Documentation/devicetree/bindings/gpio/realtek,rtd1625-gpio.yaml
> new file mode 100644
> index 0000000000000..f13c910b73c69
> --- /dev/null
> +++ b/Documentation/devicetree/bindings/gpio/realtek,rtd1625-gpio.yaml
[ ... ]
> + interrupt-controller: true
> +
> + "#interrupt-cells":
> + const: 2
> +
> + gpio-ranges: true
> +
> + gpio-controller: true
> +
> + "#gpio-cells":
> + const: 2
> +
> +required:
> + - compatible
> + - reg
> + - gpio-ranges
> + - gpio-controller
> + - "#gpio-cells"
[Severity: Medium]
Since this binding defines the hardware as an interrupt controller, should
interrupt-controller and #interrupt-cells be included in this required list?
Omitting these provider properties might allow incomplete device tree nodes
to pass schema validation, which could then cause runtime failures for
drivers attempting to use the undocumented functionality.
> +
> +additionalProperties: false
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260622092335.1166876-1-eleanor.lin@realtek.com?part=1
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH v4 3/4] gpio: realtek: Add driver for Realtek DHC RTD1625 SoC
2026-06-22 9:23 ` [PATCH v4 3/4] gpio: realtek: Add driver for Realtek DHC RTD1625 SoC Yu-Chun Lin
@ 2026-06-22 9:48 ` sashiko-bot
0 siblings, 0 replies; 7+ messages in thread
From: sashiko-bot @ 2026-06-22 9:48 UTC (permalink / raw)
To: Yu-Chun Lin; +Cc: devicetree, robh, conor+dt
Thank you for your contribution! Sashiko AI review found 4 potential issue(s) to consider:
- [High] Incorrect hardware configuration and filtering for IRQ_TYPE_EDGE_BOTH causes missed falling edges and spurious double-interrupts.
- [High] Unmapped level interrupts are not masked, causing an infinite interrupt storm.
- [High] Clearing the hardware interrupt status in the .irq_unmask callback causes lost edge interrupts.
- [Medium] The driver uses a global raw_spinlock_irqsave for all register accesses, causing severe unnecessary contention.
--
commit 2c67ad7ec485f951d81fe09ef1853cbf7ebd2d95
Author: Tzuyi Chang <tychang@realtek.com>
gpio: realtek: Add driver for Realtek DHC RTD1625 SoC
Add support for the GPIO controller found on Realtek DHC RTD1625 SoCs.
The RTD1625 introduces a per-pin register architecture with a dedicated
32-bit control register per GPIO line. Interrupt support is optional.
> diff --git a/drivers/gpio/gpio-rtd1625.c b/drivers/gpio/gpio-rtd1625.c
> new file mode 100644
> index 0000000000000..409e540bf40b3
> --- /dev/null
> +++ b/drivers/gpio/gpio-rtd1625.c
[ ... ]
> +static int rtd1625_gpio_set(struct gpio_chip *chip, unsigned int offset, int value)
> +{
> + struct rtd1625_gpio *data = gpiochip_get_data(chip);
> + u32 val = RTD1625_GPIO_WREN(RTD1625_GPIO_OUT);
> +
> + if (value)
> + val |= RTD1625_GPIO_OUT;
> +
> + guard(raw_spinlock_irqsave)(&data->lock);
> +
> + writel_relaxed(val, data->base + GPIO_CONTROL(offset));
> +
> + return 0;
> +}
> +
> +static int rtd1625_gpio_get(struct gpio_chip *chip, unsigned int offset)
> +{
> + struct rtd1625_gpio *data = gpiochip_get_data(chip);
> + u32 val;
> +
> + guard(raw_spinlock_irqsave)(&data->lock);
> +
> + val = readl_relaxed(data->base + GPIO_CONTROL(offset));
[Severity: Medium]
Since the RTD1625 hardware features a dedicated control register per GPIO
line and uses a Write-Enable bitmask design, do we need this global raw
spinlock?
It seems updates to individual bits are independent and atomic, and
readl_relaxed is inherently an atomic bus operation. Does wrapping these
operations in a single global lock across all 166 GPIOs unnecessarily
serialize all GPIO operations globally?
[ ... ]
> +static void rtd1625_gpio_irq_handle(struct irq_desc *desc)
> +{
[ ... ]
> + for_each_set_bit(j, &status, 32) {
> + hwirq = i + j;
> + girq = irq_find_mapping(domain, hwirq);
> + irq_type = irq_get_trigger_type(girq);
[Severity: High]
If a level interrupt fires on a pin that has no mapping (for example, if it
was left enabled by the bootloader), irq_find_mapping() returns 0 and
generic_handle_domain_irq() will return -EINVAL.
Because the child handler is never invoked, the active level interrupt is
never cleared or masked. Once the parent IRQ is unmasked, will the pending
level interrupt immediately re-trigger and cause an interrupt storm?
> +
> + /*
> + * Filter out the hardware-forced de-assert interrupt unless
> + * the user explicitly requested IRQ_TYPE_EDGE_BOTH.
> + */
> + if (irq == data->irqs[RTD1625_IRQ_DEASSERT] &&
> + irq_type != IRQ_TYPE_EDGE_BOTH)
> + continue;
> +
> + generic_handle_domain_irq(domain, hwirq);
> + }
[Severity: High]
For IRQ_TYPE_EDGE_BOTH, does this filter intentionally let the duplicate
de-assert interrupt through?
Due to the hardware quirk where a single edge triggers both the assert and
de-assert IRQ lines, it appears this would cause generic_handle_domain_irq()
to be called twice sequentially for the exact same physical rising edge.
[ ... ]
> +static void rtd1625_gpio_enable_edge_irq(struct rtd1625_gpio *data, irq_hw_number_t hwirq)
> +{
> + int gpda_reg_offset = rtd1625_gpio_gpda_offset(data, hwirq);
> + int gpa_reg_offset = rtd1625_gpio_gpa_offset(data, hwirq);
> + u32 clr_mask = BIT(hwirq % 32);
> + u32 val;
> +
> + guard(raw_spinlock_irqsave)(&data->lock);
> +
> + writel_relaxed(clr_mask, data->irq_base + gpa_reg_offset);
> + writel_relaxed(clr_mask, data->irq_base + gpda_reg_offset);
> + val = RTD1625_GPIO_EDGE_INT_EN | RTD1625_GPIO_WREN(RTD1625_GPIO_EDGE_INT_EN);
> + writel_relaxed(val, data->base + GPIO_CONTROL(hwirq));
> +}
[Severity: High]
This explicitly clears any pending hardware interrupts. Since this function
is called via the irq_unmask callback (mapped to rtd1625_gpio_enable_irq),
will this cause edge interrupts to be permanently lost if a hardware edge
occurs while the IRQ is temporarily masked?
Could status clearing be restricted to irq_startup or irq_ack?
[ ... ]
> +static int rtd1625_gpio_irq_set_type(struct irq_data *d, unsigned int type)
> +{
> + switch (type & IRQ_TYPE_SENSE_MASK) {
> + case IRQ_TYPE_EDGE_RISING:
> + return rtd1625_gpio_irq_set_edge_type(d, 1);
> +
> + case IRQ_TYPE_EDGE_FALLING:
> + return rtd1625_gpio_irq_set_edge_type(d, 0);
> +
> + case IRQ_TYPE_EDGE_BOTH:
> + return rtd1625_gpio_irq_set_edge_type(d, 1);
[Severity: High]
Does this map IRQ_TYPE_EDGE_BOTH to the exact same hardware polarity
configuration as IRQ_TYPE_EDGE_RISING?
It seems the hardware will only detect rising edges and completely miss
falling edges. When combined with the filter in rtd1625_gpio_irq_handle(),
does EDGE_BOTH miss all falling edges and duplicate all rising edges?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260622092335.1166876-1-eleanor.lin@realtek.com?part=3
^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2026-06-22 9:48 UTC | newest]
Thread overview: 7+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-06-22 9:23 [PATCH v4 0/4] gpio: realtek: Add support for Realtek DHC RTD1625 Yu-Chun Lin
2026-06-22 9:23 ` [PATCH v4 1/4] dt-bindings: gpio: realtek: Add realtek,rtd1625-gpio Yu-Chun Lin
2026-06-22 9:39 ` sashiko-bot
2026-06-22 9:23 ` [PATCH v4 2/4] gpio: Replace "default y" with "default ARCH_REALTEK" in Kconfig Yu-Chun Lin
2026-06-22 9:23 ` [PATCH v4 3/4] gpio: realtek: Add driver for Realtek DHC RTD1625 SoC Yu-Chun Lin
2026-06-22 9:48 ` sashiko-bot
2026-06-22 9:23 ` [PATCH v4 4/4] arm64: dts: realtek: Add GPIO support for RTD1625 Yu-Chun Lin
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox