[PATCH v3 0/9] Add RZ/G3L USB2.0 host support

[PATCH v3 0/9] Add RZ/G3L USB2.0 host support

[Biju]

From: Biju Das <biju.das.jz@bp.renesas.com>

Add device tree binding support for the RZ/G3L (r9a08g046) USB PHY
controller. The RZ/G3L USB PHY block is similar to RZ/G3S, but each port
has an OTG controller, unlike RZ/G3S, which has an OTG controller only on
port 1.

v2->v3:
 * Replaced items->enum in reset controller bindings.
 * Collected the tag for reset binding patch.
 * Dropped clock patch as it is accepted.
v1->v2:
 * Dropped patch#6(Introduce helper for regulator registration)
 * Passing pointer to an array of regulators to make it scalable.
 * Dropped regulator1-vbus and added a regulators group node.
 * Updated commit description for patch#1,#4,#6,#7,#8,#9 and #10.
 * Added enum instead of const in the compatible section.
 * Updated schema check.
 * Collected tag for PHY binding patch.
   in the regulator driver.
 * Added regulators group node and its children in SoC dtsi.

Biju Das (9):
  dt-bindings: reset: renesas,rzg2l-usbphy-ctrl: Document RZ/G3L support
  dt-bindings: phy: renesas,usb2-phy: Document RZ/G3L PHY bindings
  reset: rzg2l-usbphy-ctrl: Introduce info struct for match data
  reset: rzg2l-usbphy-ctrl: Add RZ/G3L support
  regulator: renesas-usb-vbus-regulator: Add RZ/G3L VBUS regulator
    support
  phy: renesas: phy-rcar-gen3-usb2: Add RZ/G3L support
  phy: renesas: phy-rcar-gen3-usb2: Fix devm action registration for
    disabled VBUS regulator
  arm64: dts: renesas: r9a08g046: Add USB2.0 device nodes
  arm64: dts: renesas: r9a08g046l48-smarc: Add USB2.0 support

 .../bindings/phy/renesas,usb2-phy.yaml        |   2 +
 .../reset/renesas,rzg2l-usbphy-ctrl.yaml      |  48 +++++++-
 arch/arm64/boot/dts/renesas/r9a08g046.dtsi    | 105 ++++++++++++++++++
 .../boot/dts/renesas/r9a08g046l48-smarc.dts   |  49 ++++++++
 drivers/phy/renesas/phy-rcar-gen3-usb2.c      |  20 ++--
 .../regulator/renesas-usb-vbus-regulator.c    |  53 +++++++++
 drivers/reset/reset-rzg2l-usbphy-ctrl.c       |  44 +++++---
 7 files changed, 296 insertions(+), 25 deletions(-)

-- 
2.43.0

[PATCH v3 0/9] Add RZ/G3L USB2.0 host support

[Biju]

From: Biju Das <biju.das.jz@bp.renesas.com>

Add device tree binding support for the RZ/G3L (r9a08g046) USB PHY
controller. The RZ/G3L USB PHY block is similar to RZ/G3S, but each port
has an OTG controller, unlike RZ/G3S, which has an OTG controller only on
port 1.

v2->v3:
 * Replaced items->enum in reset controller bindings.
 * Collected the tag for reset binding patch.
 * Dropped clock patch as it is accepted.
v1->v2:
 * Dropped patch#6(Introduce helper for regulator registration)
 * Passing pointer to an array of regulators to make it scalable.
 * Dropped regulator1-vbus and added a regulators group node.
 * Updated commit description for patch#1,#4,#6,#7,#8,#9 and #10.
 * Added enum instead of const in the compatible section.
 * Updated schema check.
 * Collected tag for PHY binding patch.
   in the regulator driver.
 * Added regulators group node and its children in SoC dtsi.

Biju Das (9):
  dt-bindings: reset: renesas,rzg2l-usbphy-ctrl: Document RZ/G3L support
  dt-bindings: phy: renesas,usb2-phy: Document RZ/G3L PHY bindings
  reset: rzg2l-usbphy-ctrl: Introduce info struct for match data
  reset: rzg2l-usbphy-ctrl: Add RZ/G3L support
  regulator: renesas-usb-vbus-regulator: Add RZ/G3L VBUS regulator
    support
  phy: renesas: phy-rcar-gen3-usb2: Add RZ/G3L support
  phy: renesas: phy-rcar-gen3-usb2: Fix devm action registration for
    disabled VBUS regulator
  arm64: dts: renesas: r9a08g046: Add USB2.0 device nodes
  arm64: dts: renesas: r9a08g046l48-smarc: Add USB2.0 support

 .../bindings/phy/renesas,usb2-phy.yaml        |   2 +
 .../reset/renesas,rzg2l-usbphy-ctrl.yaml      |  48 +++++++-
 arch/arm64/boot/dts/renesas/r9a08g046.dtsi    | 105 ++++++++++++++++++
 .../boot/dts/renesas/r9a08g046l48-smarc.dts   |  49 ++++++++
 drivers/phy/renesas/phy-rcar-gen3-usb2.c      |  20 ++--
 .../regulator/renesas-usb-vbus-regulator.c    |  53 +++++++++
 drivers/reset/reset-rzg2l-usbphy-ctrl.c       |  44 +++++---
 7 files changed, 296 insertions(+), 25 deletions(-)

-- 
2.43.0


-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

[PATCH v3 1/9] dt-bindings: reset: renesas,rzg2l-usbphy-ctrl: Document RZ/G3L support

[Biju]

From: Biju Das <biju.das.jz@bp.renesas.com>

Document Renesas RZ/G3L (r9a08g046) USB PHY controller bindings.
The RZ/G3L USB PHY block is similar to RZ/G3S but differs in that each
port has its own OTG controller, whereas RZ/G3S only has one on port 1.
To reflect this, RZ/G3L uses a regulators sub-node with per-port vbus0
and vbus1 entries instead of the single regulator-vbus property used
by other compatible SoCs.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
---
v2->v3:
 * Replaced items->enum
 * Collected tag.
v1->v2:
 * Updated commit description.
 * Added enum instead of const in the compatible section.
 * Dropped regulator1-vbus and added a regulators group node.
 * Updated schema check.
---
 .../reset/renesas,rzg2l-usbphy-ctrl.yaml      | 48 +++++++++++++++++--
 1 file changed, 45 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/reset/renesas,rzg2l-usbphy-ctrl.yaml b/Documentation/devicetree/bindings/reset/renesas,rzg2l-usbphy-ctrl.yaml
index c83469a1b379..06e003218d2a 100644
--- a/Documentation/devicetree/bindings/reset/renesas,rzg2l-usbphy-ctrl.yaml
+++ b/Documentation/devicetree/bindings/reset/renesas,rzg2l-usbphy-ctrl.yaml
@@ -16,13 +16,16 @@ description:
 properties:
   compatible:
     oneOf:
+      - enum:
+          - renesas,r9a08g045-usbphy-ctrl # RZ/G3S
+          - renesas,r9a08g046-usbphy-ctrl # RZ/G3L
+
       - items:
           - enum:
               - renesas,r9a07g043-usbphy-ctrl # RZ/G2UL and RZ/Five
               - renesas,r9a07g044-usbphy-ctrl # RZ/G2{L,LC}
               - renesas,r9a07g054-usbphy-ctrl # RZ/V2L
           - const: renesas,rzg2l-usbphy-ctrl
-      - const: renesas,r9a08g045-usbphy-ctrl # RZ/G3S
 
   reg:
     maxItems: 1
@@ -50,6 +53,28 @@ properties:
     $ref: /schemas/regulator/regulator.yaml#
     unevaluatedProperties: false
 
+  regulators:
+    type: object
+    description:
+      list of vbus regulators provided by this controller.
+
+    properties:
+      vbus0:
+        type: object
+        description: Port 1 USB VBUS regulator
+        $ref: /schemas/regulator/regulator.yaml#
+        unevaluatedProperties: false
+
+      vbus1:
+        type: object
+        description: Port 2 USB VBUS regulator
+        $ref: /schemas/regulator/regulator.yaml#
+        unevaluatedProperties: false
+
+    required:
+      - vbus0
+      - vbus1
+
   renesas,sysc-pwrrdy:
     description:
       The system controller PWRRDY indicates to the USB PHY if the power supply
@@ -71,14 +96,15 @@ required:
   - resets
   - power-domains
   - '#reset-cells'
-  - regulator-vbus
 
 allOf:
   - if:
       properties:
         compatible:
           contains:
-            const: renesas,r9a08g045-usbphy-ctrl
+            enum:
+              - renesas,r9a08g045-usbphy-ctrl
+              - renesas,r9a08g046-usbphy-ctrl
     then:
       required:
         - renesas,sysc-pwrrdy
@@ -86,6 +112,22 @@ allOf:
       properties:
         renesas,sysc-pwrrdy: false
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: renesas,r9a08g046-usbphy-ctrl
+    then:
+      properties:
+        regulator-vbus: false
+      required:
+        - regulators
+    else:
+      properties:
+        regulators: false
+      required:
+        - regulator-vbus
+
 additionalProperties: false
 
 examples:
-- 
2.43.0

[PATCH v3 2/9] dt-bindings: phy: renesas,usb2-phy: Document RZ/G3L PHY bindings

[Biju]

From: Biju Das <biju.das.jz@bp.renesas.com>

Add device tree binding support for the RZ/G3L (r9a08g046) USB2 PHY.
The RZ/G3L USB PHY is almost identical to the RZ/G3S USB PHY, the
difference being 2 OTG blocks on RZ/G3L compared to 1 on RZ/G3S.

Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
---
v2->v3:
 * No change
v1->v2:
 * Collected tag.
---
 Documentation/devicetree/bindings/phy/renesas,usb2-phy.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/phy/renesas,usb2-phy.yaml b/Documentation/devicetree/bindings/phy/renesas,usb2-phy.yaml
index 9740e5b335f9..d6b9d08ceec6 100644
--- a/Documentation/devicetree/bindings/phy/renesas,usb2-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/renesas,usb2-phy.yaml
@@ -16,6 +16,7 @@ properties:
           - enum:
               - renesas,usb2-phy-r8a77470  # RZ/G1C
               - renesas,usb2-phy-r9a08g045 # RZ/G3S
+              - renesas,usb2-phy-r9a08g046 # RZ/G3L
               - renesas,usb2-phy-r9a09g057 # RZ/V2H(P)
 
       - items:
@@ -132,6 +133,7 @@ allOf:
             enum:
               - renesas,usb2-phy-r9a09g057
               - renesas,usb2-phy-r9a08g045
+              - renesas,usb2-phy-r9a08g046
               - renesas,rzg2l-usb2-phy
     then:
       properties:
-- 
2.43.0

[PATCH v3 2/9] dt-bindings: phy: renesas,usb2-phy: Document RZ/G3L PHY bindings

[Biju]

From: Biju Das <biju.das.jz@bp.renesas.com>

Add device tree binding support for the RZ/G3L (r9a08g046) USB2 PHY.
The RZ/G3L USB PHY is almost identical to the RZ/G3S USB PHY, the
difference being 2 OTG blocks on RZ/G3L compared to 1 on RZ/G3S.

Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
---
v2->v3:
 * No change
v1->v2:
 * Collected tag.
---
 Documentation/devicetree/bindings/phy/renesas,usb2-phy.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/phy/renesas,usb2-phy.yaml b/Documentation/devicetree/bindings/phy/renesas,usb2-phy.yaml
index 9740e5b335f9..d6b9d08ceec6 100644
--- a/Documentation/devicetree/bindings/phy/renesas,usb2-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/renesas,usb2-phy.yaml
@@ -16,6 +16,7 @@ properties:
           - enum:
               - renesas,usb2-phy-r8a77470  # RZ/G1C
               - renesas,usb2-phy-r9a08g045 # RZ/G3S
+              - renesas,usb2-phy-r9a08g046 # RZ/G3L
               - renesas,usb2-phy-r9a09g057 # RZ/V2H(P)
 
       - items:
@@ -132,6 +133,7 @@ allOf:
             enum:
               - renesas,usb2-phy-r9a09g057
               - renesas,usb2-phy-r9a08g045
+              - renesas,usb2-phy-r9a08g046
               - renesas,rzg2l-usb2-phy
     then:
       properties:
-- 
2.43.0


-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

[PATCH v3 3/9] reset: rzg2l-usbphy-ctrl: Introduce info struct for match data

[Biju]

From: Biju Das <biju.das.jz@bp.renesas.com>

Replace the integer flag RZG2L_USBPHY_CTRL_PWRRDY with a structured
rzg2l_usbphy_ctrl_info type to hold per-compatible configuration data.

The new struct carries a regulator_driver_name string and a pwrrdy
boolean. The probe function now retrieves this struct via
device_get_match_data() and conditionally calls
rzg2l_usbphy_ctrl_pwrrdy_init() based on the pwrrdy flag, removing
the previous integer cast approach.

This refactoring prepares the driver for RZ/G3L (r9a08g046) support,
which requires a different regulator configuration with two per-port
VBUS regulators.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
---
v2->v3:
  No change.
v1->v2:
 * Updated commit description.
---
 drivers/reset/reset-rzg2l-usbphy-ctrl.c | 38 +++++++++++++++----------
 1 file changed, 23 insertions(+), 15 deletions(-)

diff --git a/drivers/reset/reset-rzg2l-usbphy-ctrl.c b/drivers/reset/reset-rzg2l-usbphy-ctrl.c
index fd75d9601a3b..1c4c8aae0e80 100644
--- a/drivers/reset/reset-rzg2l-usbphy-ctrl.c
+++ b/drivers/reset/reset-rzg2l-usbphy-ctrl.c
@@ -41,6 +41,11 @@ struct rzg2l_usbphy_ctrl_priv {
 	spinlock_t lock;
 };
 
+struct rzg2l_usbphy_ctrl_info {
+	const char *regulator_driver_name;
+	bool pwrrdy;
+};
+
 #define rcdev_to_priv(x)	container_of(x, struct rzg2l_usbphy_ctrl_priv, rcdev)
 
 static int rzg2l_usbphy_ctrl_assert(struct reset_controller_dev *rcdev,
@@ -106,14 +111,18 @@ static void rzg2l_usbphy_ctrl_init(struct rzg2l_usbphy_ctrl_priv *priv)
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
-#define RZG2L_USBPHY_CTRL_PWRRDY	1
+static const struct rzg2l_usbphy_ctrl_info rzg2l_info = {
+	.regulator_driver_name = "rzg2l-usb-vbus-regulator",
+};
+
+static const struct rzg2l_usbphy_ctrl_info rzg3s_info = {
+	.regulator_driver_name = "rzg2l-usb-vbus-regulator",
+	.pwrrdy = true,
+};
 
 static const struct of_device_id rzg2l_usbphy_ctrl_match_table[] = {
-	{ .compatible = "renesas,rzg2l-usbphy-ctrl" },
-	{
-		.compatible = "renesas,r9a08g045-usbphy-ctrl",
-		.data = (void *)RZG2L_USBPHY_CTRL_PWRRDY
-	},
+	{ .compatible = "renesas,rzg2l-usbphy-ctrl", .data = &rzg2l_info },
+	{ .compatible = "renesas,r9a08g045-usbphy-ctrl", .data = &rzg3s_info },
 	{ /* Sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, rzg2l_usbphy_ctrl_match_table);
@@ -153,14 +162,9 @@ static int rzg2l_usbphy_ctrl_pwrrdy_init(struct device *dev,
 {
 	struct reg_field field;
 	struct regmap *regmap;
-	const int *data;
 	u32 args[2];
 	int ret;
 
-	data = device_get_match_data(dev);
-	if ((uintptr_t)data != RZG2L_USBPHY_CTRL_PWRRDY)
-		return 0;
-
 	regmap = syscon_regmap_lookup_by_phandle_args(dev->of_node,
 						      "renesas,sysc-pwrrdy",
 						      ARRAY_SIZE(args), args);
@@ -188,6 +192,7 @@ static int rzg2l_usbphy_ctrl_pwrrdy_init(struct device *dev,
 
 static int rzg2l_usbphy_ctrl_probe(struct platform_device *pdev)
 {
+	const struct rzg2l_usbphy_ctrl_info *info;
 	struct device *dev = &pdev->dev;
 	struct rzg2l_usbphy_ctrl_priv *priv;
 	struct platform_device *vdev;
@@ -206,9 +211,12 @@ static int rzg2l_usbphy_ctrl_probe(struct platform_device *pdev)
 	if (IS_ERR(regmap))
 		return PTR_ERR(regmap);
 
-	error = rzg2l_usbphy_ctrl_pwrrdy_init(dev, priv);
-	if (error)
-		return error;
+	info = device_get_match_data(dev);
+	if (info->pwrrdy) {
+		error = rzg2l_usbphy_ctrl_pwrrdy_init(dev, priv);
+		if (error)
+			return error;
+	}
 
 	priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL);
 	if (IS_ERR(priv->rstc))
@@ -241,7 +249,7 @@ static int rzg2l_usbphy_ctrl_probe(struct platform_device *pdev)
 	if (error)
 		goto err_pm_runtime_put;
 
-	vdev = platform_device_alloc("rzg2l-usb-vbus-regulator", pdev->id);
+	vdev = platform_device_alloc(info->regulator_driver_name, pdev->id);
 	if (!vdev) {
 		error = -ENOMEM;
 		goto err_pm_runtime_put;
-- 
2.43.0

[PATCH v3 4/9] reset: rzg2l-usbphy-ctrl: Add RZ/G3L support

[Biju]

From: Biju Das <biju.das.jz@bp.renesas.com>

Add the renesas,r9a08g046-usbphy-ctrl compatible string to the OF match
table for the RZ/G3L (r9a08g046) SoC, using a dedicated rzg3l_info
struct with pwr_rdy set, similar to RZ/G3S. The RZ/G3L SoC has 2 OTG
controllers compared to one on RZ/G3S, so it uses a separate
rzg3l-usb-vbus-regulator driver to handle the additional VBUSEN control
for port 2.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
---
v2->v3:
 * No change.
v1->v2:
 * No change.
---
 drivers/reset/reset-rzg2l-usbphy-ctrl.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/reset/reset-rzg2l-usbphy-ctrl.c b/drivers/reset/reset-rzg2l-usbphy-ctrl.c
index 1c4c8aae0e80..734255258b69 100644
--- a/drivers/reset/reset-rzg2l-usbphy-ctrl.c
+++ b/drivers/reset/reset-rzg2l-usbphy-ctrl.c
@@ -120,9 +120,15 @@ static const struct rzg2l_usbphy_ctrl_info rzg3s_info = {
 	.pwrrdy = true,
 };
 
+static const struct rzg2l_usbphy_ctrl_info rzg3l_info = {
+	.regulator_driver_name = "rzg3l-usb-vbus-regulator",
+	.pwrrdy = true,
+};
+
 static const struct of_device_id rzg2l_usbphy_ctrl_match_table[] = {
 	{ .compatible = "renesas,rzg2l-usbphy-ctrl", .data = &rzg2l_info },
 	{ .compatible = "renesas,r9a08g045-usbphy-ctrl", .data = &rzg3s_info },
+	{ .compatible = "renesas,r9a08g046-usbphy-ctrl", .data = &rzg3l_info },
 	{ /* Sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, rzg2l_usbphy_ctrl_match_table);
-- 
2.43.0

[PATCH v3 5/9] regulator: renesas-usb-vbus-regulator: Add RZ/G3L VBUS regulator support

[Biju]

From: Biju Das <biju.das.jz@bp.renesas.com>

Add dual USB VBUS regulator support for the RZ/G3L (r9a08g046) SoC, which
has two OTG controllers (one per port), unlike RZ/G3S which has only one.

Introduce a RZG3L_USB_VBUS_REG macro and a rzg3l_usb_vbus_regulators
array with two descriptors: vbus0 (BIT(0)) and vbus1 (BIT(1)), both
sourced from a regulators sub-node as defined in the binding. Add a
dedicated rzg3l_usb_vbus_regulator_probe() that iterates over the array
and registers both regulators using devm_regulator_register(). Register
a separate rzg3l-usb-vbus-regulator platform driver backed by this probe
function.

The existing rzg2l_usb_vbus_regulator_probe() and its platform driver
are unchanged and continue to handle the single regulator-vbus case for
all other SoCs.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
---
v2->v3:
 * No change.
v1->v2:
 * Passing pointer to an array of regulators to make it scalable.
 * Updated commit description.
---
 .../regulator/renesas-usb-vbus-regulator.c    | 53 +++++++++++++++++++
 1 file changed, 53 insertions(+)

diff --git a/drivers/regulator/renesas-usb-vbus-regulator.c b/drivers/regulator/renesas-usb-vbus-regulator.c
index 9ba791bd72ec..902834000874 100644
--- a/drivers/regulator/renesas-usb-vbus-regulator.c
+++ b/drivers/regulator/renesas-usb-vbus-regulator.c
@@ -55,6 +55,50 @@ static int rzg2l_usb_vbus_regulator_probe(struct platform_device *pdev)
 	return 0;
 }
 
+#define RZG3L_USB_VBUS_REG(rname, en_mask)				\
+	{								\
+		.name			= #rname,			\
+		.of_match		= of_match_ptr(#rname),		\
+		.regulators_node	= of_match_ptr("regulators"),	\
+		.type			= REGULATOR_VOLTAGE,		\
+		.owner			= THIS_MODULE,			\
+		.ops			= &rzg2l_usb_vbus_reg_ops,	\
+		.enable_reg		= 0,				\
+		.enable_mask		= (en_mask),			\
+		.enable_is_inverted	= true,				\
+		.fixed_uV		= 5000000,			\
+		.n_voltages		= 1,				\
+	}
+
+static const struct regulator_desc rzg3l_usb_vbus_regulators[] = {
+	RZG3L_USB_VBUS_REG(vbus0, BIT(0)),
+	RZG3L_USB_VBUS_REG(vbus1, BIT(1)),
+};
+
+static int rzg3l_usb_vbus_regulator_probe(struct platform_device *pdev)
+{
+	struct regulator_config config = { };
+	struct device *dev = &pdev->dev;
+	struct regulator_dev *rdev;
+
+	config.dev = pdev->dev.parent;
+	config.regmap = dev_get_regmap(dev->parent, NULL);
+	if (!config.regmap)
+		return dev_err_probe(dev, -ENOENT, "Failed to get regmap\n");
+
+	for (unsigned int i = 0; i < ARRAY_SIZE(rzg3l_usb_vbus_regulators); i++) {
+		rdev = devm_regulator_register(dev, &rzg3l_usb_vbus_regulators[i],
+					       &config);
+		if (IS_ERR(rdev)) {
+			dev_err(dev, "failed to register %s regulator\n",
+				rzg3l_usb_vbus_regulators[i].name);
+			return PTR_ERR(rdev);
+		}
+	}
+
+	return 0;
+}
+
 static struct platform_driver rzg2l_usb_vbus_regulator_driver = {
 	.probe = rzg2l_usb_vbus_regulator_probe,
 	.driver	= {
@@ -64,6 +108,15 @@ static struct platform_driver rzg2l_usb_vbus_regulator_driver = {
 };
 module_platform_driver(rzg2l_usb_vbus_regulator_driver);
 
+static struct platform_driver rzg3l_usb_vbus_regulator_driver = {
+	.probe = rzg3l_usb_vbus_regulator_probe,
+	.driver	= {
+		.name = "rzg3l-usb-vbus-regulator",
+		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
+	},
+};
+module_platform_driver(rzg3l_usb_vbus_regulator_driver);
+
 MODULE_AUTHOR("Biju Das <biju.das.jz@bp.renesas.com>");
 MODULE_DESCRIPTION("Renesas RZ/G2L USB Vbus Regulator Driver");
 MODULE_LICENSE("GPL");
-- 
2.43.0

[PATCH v3 6/9] phy: renesas: phy-rcar-gen3-usb2: Add RZ/G3L support

[Biju]

From: Biju Das <biju.das.jz@bp.renesas.com>

Add renesas,usb2-phy-r9a08g046 to the OF match table, reusing
rz_g3s_phy_usb2_data as the PHY configuration is shared with RZ/G3S.

While the PHY data is shared, RZ/G3L differs from RZ/G3S in that it has
two OTG controllers, OTG interrupts on port 2, and a controllable
OTG_PERI bit in COMMCTRL for host/device switching on the port 2 USB
controller, which is fixed to host-only on RZ/G3S.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
---
v2->v3:
 * No change.
v1->v2:
 * Updated commit description.
---
 drivers/phy/renesas/phy-rcar-gen3-usb2.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
index 9a45d840efeb..d06fb52ed5f1 100644
--- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
+++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
@@ -721,6 +721,10 @@ static const struct of_device_id rcar_gen3_phy_usb2_match_table[] = {
 		.compatible = "renesas,usb2-phy-r9a08g045",
 		.data = &rz_g3s_phy_usb2_data,
 	},
+	{
+		.compatible = "renesas,usb2-phy-r9a08g046",
+		.data = &rz_g3s_phy_usb2_data,
+	},
 	{
 		.compatible = "renesas,usb2-phy-r9a09g057",
 		.data = &rz_v2h_phy_usb2_data,
-- 
2.43.0

[PATCH v3 6/9] phy: renesas: phy-rcar-gen3-usb2: Add RZ/G3L support

[Biju]

From: Biju Das <biju.das.jz@bp.renesas.com>

Add renesas,usb2-phy-r9a08g046 to the OF match table, reusing
rz_g3s_phy_usb2_data as the PHY configuration is shared with RZ/G3S.

While the PHY data is shared, RZ/G3L differs from RZ/G3S in that it has
two OTG controllers, OTG interrupts on port 2, and a controllable
OTG_PERI bit in COMMCTRL for host/device switching on the port 2 USB
controller, which is fixed to host-only on RZ/G3S.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
---
v2->v3:
 * No change.
v1->v2:
 * Updated commit description.
---
 drivers/phy/renesas/phy-rcar-gen3-usb2.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
index 9a45d840efeb..d06fb52ed5f1 100644
--- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
+++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
@@ -721,6 +721,10 @@ static const struct of_device_id rcar_gen3_phy_usb2_match_table[] = {
 		.compatible = "renesas,usb2-phy-r9a08g045",
 		.data = &rz_g3s_phy_usb2_data,
 	},
+	{
+		.compatible = "renesas,usb2-phy-r9a08g046",
+		.data = &rz_g3s_phy_usb2_data,
+	},
 	{
 		.compatible = "renesas,usb2-phy-r9a09g057",
 		.data = &rz_v2h_phy_usb2_data,
-- 
2.43.0


-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

[PATCH v3 7/9] phy: renesas: phy-rcar-gen3-usb2: Fix devm action registration for disabled VBUS regulator

[Biju]

From: Biju Das <biju.das.jz@bp.renesas.com>

devm_regulator_get_exclusive() initialises the regulator with
enable_count = 1, requiring the consumer to disable it before release.

The devm disable action was previously only registered when the caller
explicitly requested enable, so when the regulator was left in its initial
enabled state without an explicit enable call, the cleanup path skipped
decrementing enable_count, triggering a WARN_ON during regulator
release on device removal.

Fix this by always registering the devm disable action based on the actual
enabled state via regulator_is_enabled(), regardless of whether the
caller requested an explicit enable. This covers both the explicitly-enabled
case and the initial state set by devm_regulator_get_exclusive().

Fixes: 24843404efe4 ("phy: renesas: phy-rcar-gen3-usb2: Control VBUS for RZ/G2L SoCs")
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
---
v2->v3:
 * No change.
v1->v2:
 * Updated commit description.
---
 drivers/phy/renesas/phy-rcar-gen3-usb2.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
index d06fb52ed5f1..ef38c3b365d4 100644
--- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
+++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
@@ -905,15 +905,17 @@ static int rcar_gen3_phy_usb2_vbus_regulator_get_exclusive_enable(struct rcar_ge
 	if (IS_ERR(channel->vbus))
 		return PTR_ERR(channel->vbus);
 
-	if (!enable)
-		return 0;
+	if (enable) {
+		ret = regulator_enable(channel->vbus);
+		if (ret)
+			return ret;
+	}
 
-	ret = regulator_enable(channel->vbus);
-	if (ret)
-		return ret;
+	if (regulator_is_enabled(channel->vbus))
+		return devm_add_action_or_reset(dev, rcar_gen3_phy_usb2_vbus_disable_action,
+						channel->vbus);
 
-	return devm_add_action_or_reset(dev, rcar_gen3_phy_usb2_vbus_disable_action,
-					channel->vbus);
+	return 0;
 }
 
 static int rcar_gen3_phy_usb2_vbus_regulator_register(struct rcar_gen3_chan *channel)
-- 
2.43.0

[PATCH v3 7/9] phy: renesas: phy-rcar-gen3-usb2: Fix devm action registration for disabled VBUS regulator

[Biju]

From: Biju Das <biju.das.jz@bp.renesas.com>

devm_regulator_get_exclusive() initialises the regulator with
enable_count = 1, requiring the consumer to disable it before release.

The devm disable action was previously only registered when the caller
explicitly requested enable, so when the regulator was left in its initial
enabled state without an explicit enable call, the cleanup path skipped
decrementing enable_count, triggering a WARN_ON during regulator
release on device removal.

Fix this by always registering the devm disable action based on the actual
enabled state via regulator_is_enabled(), regardless of whether the
caller requested an explicit enable. This covers both the explicitly-enabled
case and the initial state set by devm_regulator_get_exclusive().

Fixes: 24843404efe4 ("phy: renesas: phy-rcar-gen3-usb2: Control VBUS for RZ/G2L SoCs")
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
---
v2->v3:
 * No change.
v1->v2:
 * Updated commit description.
---
 drivers/phy/renesas/phy-rcar-gen3-usb2.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
index d06fb52ed5f1..ef38c3b365d4 100644
--- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
+++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
@@ -905,15 +905,17 @@ static int rcar_gen3_phy_usb2_vbus_regulator_get_exclusive_enable(struct rcar_ge
 	if (IS_ERR(channel->vbus))
 		return PTR_ERR(channel->vbus);
 
-	if (!enable)
-		return 0;
+	if (enable) {
+		ret = regulator_enable(channel->vbus);
+		if (ret)
+			return ret;
+	}
 
-	ret = regulator_enable(channel->vbus);
-	if (ret)
-		return ret;
+	if (regulator_is_enabled(channel->vbus))
+		return devm_add_action_or_reset(dev, rcar_gen3_phy_usb2_vbus_disable_action,
+						channel->vbus);
 
-	return devm_add_action_or_reset(dev, rcar_gen3_phy_usb2_vbus_disable_action,
-					channel->vbus);
+	return 0;
 }
 
 static int rcar_gen3_phy_usb2_vbus_regulator_register(struct rcar_gen3_chan *channel)
-- 
2.43.0


-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

[PATCH v3 8/9] arm64: dts: renesas: r9a08g046: Add USB2.0 device nodes

[Biju]

From: Biju Das <biju.das.jz@bp.renesas.com>

Add USB2.0 device nodes to the RZ/G3L (r9a08g046) SoC DTSI, covering
the USB PHY controller, OHCI/EHCI host controllers, and USB2 PHYs for
both ports.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
---
v1->v2:
 * Updated commit description.
 * Added regulators group node and its children.
---
 arch/arm64/boot/dts/renesas/r9a08g046.dtsi | 105 +++++++++++++++++++++
 1 file changed, 105 insertions(+)

diff --git a/arch/arm64/boot/dts/renesas/r9a08g046.dtsi b/arch/arm64/boot/dts/renesas/r9a08g046.dtsi
index 85e409ac8d5c..926a81cec37e 100644
--- a/arch/arm64/boot/dts/renesas/r9a08g046.dtsi
+++ b/arch/arm64/boot/dts/renesas/r9a08g046.dtsi
@@ -1198,6 +1198,111 @@ queue3 {
 			};
 		};
 
+		phyrst: usbphy-ctrl@11e00000 {
+			compatible = "renesas,r9a08g046-usbphy-ctrl";
+			reg = <0 0x11e00000 0 0x10000>;
+			clocks = <&cpg CPG_MOD R9A08G046_USB_PCLK>;
+			resets = <&cpg R9A08G046_USB_PRESETN>;
+			power-domains = <&cpg>;
+			#reset-cells = <1>;
+			renesas,sysc-pwrrdy = <&sysc 0xd70 0x1>;
+			status = "disabled";
+
+			regulators {
+				usb0_vbus_otg: vbus0 {
+					regulator-name = "usb0_vbus";
+				};
+
+				usb1_vbus_otg: vbus1 {
+					regulator-name = "usb1_vbus";
+				};
+			};
+		};
+
+		ohci0: usb@11e10000 {
+			compatible = "generic-ohci";
+			reg = <0 0x11e10000 0 0x100>;
+			interrupts = <GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD R9A08G046_USB_PCLK>,
+				 <&cpg CPG_MOD R9A08G046_USB_U2H0_HCLK>;
+			resets = <&phyrst 0>,
+				 <&cpg R9A08G046_USB_U2H0_HRESETN>;
+			phys = <&usb2_phy0 1>;
+			phy-names = "usb";
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
+
+		ohci1: usb@11e90000 {
+			compatible = "generic-ohci";
+			reg = <0 0x11e90000 0 0x100>;
+			interrupts = <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD R9A08G046_USB_PCLK>,
+				 <&cpg CPG_MOD R9A08G046_USB_U2H1_HCLK>;
+			resets = <&phyrst 1>,
+				 <&cpg R9A08G046_USB_U2H1_HRESETN>;
+			phys = <&usb2_phy1 1>;
+			phy-names = "usb";
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
+
+		ehci0: usb@11e10100 {
+			compatible = "generic-ehci";
+			reg = <0 0x11e10100 0 0x100>;
+			interrupts = <GIC_SPI 114 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD R9A08G046_USB_PCLK>,
+				 <&cpg CPG_MOD R9A08G046_USB_U2H0_HCLK>;
+			resets = <&phyrst 0>,
+				 <&cpg R9A08G046_USB_U2H0_HRESETN>;
+			phys = <&usb2_phy0 2>;
+			phy-names = "usb";
+			companion = <&ohci0>;
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
+
+		ehci1: usb@11e90100 {
+			compatible = "generic-ehci";
+			reg = <0 0x11e90100 0 0x100>;
+			interrupts = <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD R9A08G046_USB_PCLK>,
+				 <&cpg CPG_MOD R9A08G046_USB_U2H1_HCLK>;
+			resets = <&phyrst 1>,
+				 <&cpg R9A08G046_USB_U2H1_HRESETN>;
+			phys = <&usb2_phy1 2>;
+			phy-names = "usb";
+			companion = <&ohci1>;
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
+
+		usb2_phy0: usb-phy@11e10200 {
+			compatible = "renesas,usb2-phy-r9a08g046";
+			reg = <0 0x11e10200 0 0x700>;
+			interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD R9A08G046_USB_PCLK>,
+				 <&cpg CPG_MOD R9A08G046_USB_U2H0_HCLK>;
+			resets = <&phyrst 0>,
+				 <&cpg R9A08G046_USB_U2H0_HRESETN>;
+			#phy-cells = <1>;
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
+
+		usb2_phy1: usb-phy@11e90200 {
+			compatible = "renesas,usb2-phy-r9a08g046";
+			reg = <0 0x11e90200 0 0x700>;
+			interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&cpg CPG_MOD R9A08G046_USB_PCLK>,
+				 <&cpg CPG_MOD R9A08G046_USB_U2H1_HCLK>;
+			resets = <&phyrst 1>,
+				 <&cpg R9A08G046_USB_U2H1_HRESETN>;
+			#phy-cells = <1>;
+			power-domains = <&cpg>;
+			status = "disabled";
+		};
+
 		pcie: pcie@11e40000 {
 			reg = <0 0x11e40000 0 0x10000>;
 			ranges = <0x02000000 0 0x30000000 0 0x30000000 0 0x08000000>;
-- 
2.43.0

[PATCH v3 9/9] arm64: dts: renesas: r9a08g046l48-smarc: Add USB2.0 support

[Biju]

From: Biju Das <biju.das.jz@bp.renesas.com>

Enable USB2.0 on the RZ/G3L SMARC board (r9a08g046l48-smarc).

Port 0 (ehci0, ohci0, usb2_phy0) is configured as OTG with
usb0_pins pinmux (USB20_OVRCUR, USB20_VBUSEN) and usb0_vbus_otg
as the VBUS supply. Port 1 (ehci1, ohci1, usb2_phy1) is configured
as host-only with usb1_pins pinmux (USB21_OVRCUR, USB21_VBUSEN),
usb1_vbus_otg as the VBUS supply, and renesas,no-otg-pins set to
indicate no OTG pin routing. The phyrst USB PHY reset controller is
also enabled.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
---
v2->v3:
 * No change.
v1->v2:
 * Updated commit description.
---
 .../boot/dts/renesas/r9a08g046l48-smarc.dts   | 49 +++++++++++++++++++
 1 file changed, 49 insertions(+)

diff --git a/arch/arm64/boot/dts/renesas/r9a08g046l48-smarc.dts b/arch/arm64/boot/dts/renesas/r9a08g046l48-smarc.dts
index 96cc7ee46a6a..b189ae8e808d 100644
--- a/arch/arm64/boot/dts/renesas/r9a08g046l48-smarc.dts
+++ b/arch/arm64/boot/dts/renesas/r9a08g046l48-smarc.dts
@@ -87,6 +87,16 @@ vqmmc_sd1_pvdd: regulator-vqmmc-sd1-pvdd {
 #endif
 };
 
+&ehci0 {
+	dr_mode = "otg";
+	status = "okay";
+};
+
+&ehci1 {
+	dr_mode = "host";
+	status = "okay";
+};
+
 &i2c2 {
 	pinctrl-0 = <&i2c2_pins>;
 	pinctrl-names = "default";
@@ -138,6 +148,20 @@ &keys {
 #endif
 };
 
+&ohci0 {
+	dr_mode = "otg";
+	status = "okay";
+};
+
+&ohci1 {
+	dr_mode = "host";
+	status = "okay";
+};
+
+&phyrst {
+	status = "okay";
+};
+
 &pinctrl {
 	audio_clk_pins: audio-clock {
 		pinmux = <RZG3L_PORT_PINMUX(H, 4, 6)>, /* AUDIO_CLK_B */
@@ -259,6 +283,16 @@ ssi0_pins: ssi0 {
 			 <RZG3L_PORT_PINMUX(H, 2, 9)>, /* SSIF0_RCK */
 			 <RZG3L_PORT_PINMUX(H, 3, 9)>; /* SSIF0_TXD */
 	};
+
+	usb0_pins: usb0 {
+		pinmux = <RZG3L_PORT_PINMUX(3, 0, 12)>, /* USB20_OVRCUR */
+			 <RZG3L_PORT_PINMUX(3, 1, 12)>; /* USB20_VBUSEN */
+	};
+
+	usb1_pins: usb1 {
+		pinmux = <RZG3L_PORT_PINMUX(3, 4, 12)>, /* USB21_OVRCUR */
+			 <RZG3L_PORT_PINMUX(3, 5, 12)>; /* USB21_VBUSEN */
+	};
 };
 
 #if SW_SER0_PMOD
@@ -330,3 +364,18 @@ &ssi0 {
 	status = "okay";
 };
 #endif
+
+&usb2_phy0 {
+	pinctrl-0 = <&usb0_pins>;
+	pinctrl-names = "default";
+	vbus-supply = <&usb0_vbus_otg>;
+	status = "okay";
+};
+
+&usb2_phy1 {
+	pinctrl-0 = <&usb1_pins>;
+	pinctrl-names = "default";
+	vbus-supply = <&usb1_vbus_otg>;
+	renesas,no-otg-pins;
+	status = "okay";
+};
-- 
2.43.0

Re: [PATCH v3 1/9] dt-bindings: reset: renesas,rzg2l-usbphy-ctrl: Document RZ/G3L support

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] The newly added `regulators` object node is missing the `additionalProperties: false` constraint.
--

--- Patch [1]: [PATCH v3 1/9] dt-bindings: reset: renesas,rzg2l-usbphy-ctrl: Document RZ/G3L support ---
commit 13d2a223ee35259aa34d58ec5e02e2fa9d54297b
Author: Biju Das <biju.das.jz@bp.renesas.com>

dt-bindings: reset: renesas,rzg2l-usbphy-ctrl: Document RZ/G3L support

Document Renesas RZ/G3L (r9a08g046) USB PHY controller bindings.
The RZ/G3L USB PHY block uses a regulators sub-node with per-port vbus0
and vbus1 entries instead of the single regulator-vbus property used
by other compatible SoCs.

> diff --git a/Documentation/devicetree/bindings/reset/renesas,rzg2l-usbphy-ctrl.yaml b/Documentation/devicetree/bindings/reset/renesas,rzg2l-usbphy-ctrl.yaml
> index c83469a1b379a..06e003218d2a8 100644
> --- a/Documentation/devicetree/bindings/reset/renesas,rzg2l-usbphy-ctrl.yaml
> +++ b/Documentation/devicetree/bindings/reset/renesas,rzg2l-usbphy-ctrl.yaml

[ ... ]

> @@ -50,6 +53,28 @@ properties:
>      $ref: /schemas/regulator/regulator.yaml#
>      unevaluatedProperties: false
>  
> +  regulators:
> +    type: object
> +    description:
> +      list of vbus regulators provided by this controller.
> +

[Severity: Low]
Is the additionalProperties: false constraint missing here?

Without this constraint, device tree schema validation will silently accept
undocumented or malformed properties (like typos in vbus names) inside the
regulators node, as the parent object doesn't strictly forbid them.

> +    properties:
> +      vbus0:
> +        type: object
> +        description: Port 1 USB VBUS regulator
> +        $ref: /schemas/regulator/regulator.yaml#
> +        unevaluatedProperties: false

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260707143646.245177-1-biju.das.jz@bp.renesas.com?part=1

Re: [PATCH v3 6/9] phy: renesas: phy-rcar-gen3-usb2: Add RZ/G3L support

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] Sleep-in-atomic bug due to calling regulator_hardware_enable() inside a spinlock and from a hardirq handler.
--

--- Patch [6]: [PATCH v3 6/9] phy: renesas: phy-rcar-gen3-usb2: Add RZ/G3L support ---
commit 502c90feba61fdb92ccdaff21a3e226e6113ab48
Author: Biju Das <biju.das.jz@bp.renesas.com>

phy: renesas: phy-rcar-gen3-usb2: Add RZ/G3L support

This commit adds support for the RZ/G3L SoC to the phy-rcar-gen3-usb2 driver
by adding the "renesas,usb2-phy-r9a08g046" compatible string. The PHY data
configuration is shared with RZ/G3S.

> diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
> index 9a45d840efeb2..d06fb52ed5f1b 100644
> --- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
> +++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
> @@ -721,6 +721,10 @@ static const struct of_device_id rcar_gen3_phy_usb2_match_table[] = {
>  		.compatible = "renesas,usb2-phy-r9a08g045",
>  		.data = &rz_g3s_phy_usb2_data,
>  	},
> +	{
> +		.compatible = "renesas,usb2-phy-r9a08g046",
> +		.data = &rz_g3s_phy_usb2_data,
> +	},

[Severity: High]
This is a pre-existing issue, but since this patch exposes this hardware to 
existing code paths, I wanted to ask about a potential sleep-in-atomic bug.

When a user writes to the role sysfs attribute, role_store() acquires a
spinlock and disables interrupts:

drivers/phy/renesas/phy-rcar-gen3-usb2.c:role_store() {
    guard(spinlock_irqsave)(&ch->lock);
    ...
    if (!is_b_device)    /* A-Peripheral */
        rcar_gen3_init_from_a_peri_to_a_host(ch);
}

This calls down to rcar_gen3_enable_vbus_ctrl(), which then triggers the
regulator operations:

drivers/phy/renesas/phy-rcar-gen3-usb2.c:rcar_gen3_enable_vbus_ctrl() {
    ...
    if (ch->otg_internal_reg) {
        regulator_hardware_enable(ch->vbus, vbus);
        return;
    }

    if (ch->phy_data->no_adp_ctrl || ch->phy_data->vblvl_ctrl) {
        if (ch->vbus)
            regulator_hardware_enable(ch->vbus, vbus);
    ...
}

For SoCs using the internal regulator (such as RZ/G3L), the enable callback
invokes pm_runtime_resume_and_get():

drivers/phy/renesas/phy-rcar-gen3-usb2.c:rcar_gen3_phy_usb2_regulator_endisable() {
    ...
    ret = pm_runtime_resume_and_get(dev);
    ...
}

Can this sequence cause a panic? 

If the device state is RPM_SUSPENDING, pm_runtime_resume_and_get() might sleep
waiting for the asynchronous suspend to finish, but we are inside an atomic
section holding ch->lock with interrupts disabled.

Similarly, does the rcar_gen3_phy_usb2_irq() hardirq handler also reach
this regulator_hardware_enable() path on OTG plug/unplug events? If so,
would it hit the same sleep-in-atomic issue?

>  	{
>  		.compatible = "renesas,usb2-phy-r9a09g057",
>  		.data = &rz_v2h_phy_usb2_data,

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260707143646.245177-1-biju.das.jz@bp.renesas.com?part=6

-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

Re: [PATCH v3 8/9] arm64: dts: renesas: r9a08g046: Add USB2.0 device nodes

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

New issues:
- [Low] module_platform_driver() is invoked twice in the same C file, which will cause a build failure when compiled as a loadable module.

Pre-existing issues:
- [High] The fix for the VBUS regulator enable_count leak is incomplete and leaves the count unbalanced if the driver explicitly calls regulator_enable() on a pre-enabled regulator.
--

--- Patch [8]: [PATCH v3 8/9] arm64: dts: renesas: r9a08g046: Add USB2.0 device nodes ---
commit 5af51dcc7dc2267ce2a724cd23f6ac8e1361e710
Author: Biju Das <biju.das.jz@bp.renesas.com>

regulator: renesas-usb-vbus-regulator: Add RZ/G3L VBUS regulator support

Add dual USB VBUS regulator support for the RZ/G3L (r9a08g046) SoC.
Register a separate rzg3l-usb-vbus-regulator platform driver for it.

> diff --git a/drivers/regulator/renesas-usb-vbus-regulator.c b/drivers/regulator/renesas-usb-vbus-regulator.c
> index 9ba791bd72eca..9028340008749 100644
> --- a/drivers/regulator/renesas-usb-vbus-regulator.c
> +++ b/drivers/regulator/renesas-usb-vbus-regulator.c

[ ... ]

> @@ -64,6 +108,15 @@ static struct platform_driver rzg2l_usb_vbus_regulator_driver = {
>  };
>  module_platform_driver(rzg2l_usb_vbus_regulator_driver);
>  
> +static struct platform_driver rzg3l_usb_vbus_regulator_driver = {
> +	.probe = rzg3l_usb_vbus_regulator_probe,
> +	.driver	= {
> +		.name = "rzg3l-usb-vbus-regulator",
> +		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
> +	},
> +};
> +module_platform_driver(rzg3l_usb_vbus_regulator_driver);

[Severity: Low]
Will this cause a build failure when compiled as a loadable module?

The module_platform_driver() macro is invoked twice in the same C file, which
will expand to redefine the init_module and cleanup_module alias functions.


commit 30054990ee806fb8d79768ae79587b9acfe0f6a6
Author: Biju Das <biju.das.jz@bp.renesas.com>

phy: renesas: phy-rcar-gen3-usb2: Fix devm action registration for disabled VBUS regulator

Fix the devm disable action registration to base it on actual enabled state via
regulator_is_enabled(), regardless of whether the caller requested an explicit
enable.

> diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
> index d06fb52ed5f1b..ef38c3b365d42 100644
> --- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
> +++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c

[ ... ]

> @@ -905,15 +905,17 @@ static int rcar_gen3_phy_usb2_vbus_regulator_get_exclusive_enable(struct rcar_ge
>  	if (IS_ERR(channel->vbus))
>  		return PTR_ERR(channel->vbus);
>  
> -	if (!enable)
> -		return 0;
> +	if (enable) {
> +		ret = regulator_enable(channel->vbus);
> +		if (ret)
> +			return ret;
> +	}
>  
> -	ret = regulator_enable(channel->vbus);
> -	if (ret)
> -		return ret;
> +	if (regulator_is_enabled(channel->vbus))
> +		return devm_add_action_or_reset(dev, rcar_gen3_phy_usb2_vbus_disable_action,
> +						channel->vbus);

[Severity: High]
This isn't a bug introduced by this patch, but does this leave the enable_count
unbalanced if the driver explicitly calls regulator_enable() on a pre-enabled
regulator?

If the enable parameter is true, regulator_enable() increments the count.
If the regulator was already enabled by hardware, registering a single devm
disable action here fails to account for the double-incremented enable_count.

This would trigger a WARN_ON during device removal, which could panic the
kernel if panic_on_warn is set.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260707143646.245177-1-biju.das.jz@bp.renesas.com?part=8

Re: [PATCH v3 9/9] arm64: dts: renesas: r9a08g046l48-smarc: Add USB2.0 support

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] Using `module_platform_driver()` twice in the same C file causes a build failure due to the redefinition of `init_module` and `cleanup_module`.
--

--- Patch [9]: [PATCH v3 9/9] arm64: dts: renesas: r9a08g046l48-smarc: Add USB2.0 support ---
commit 5af51dcc7dc2267ce2a724cd23f6ac8e1361e710
Author: Biju Das <biju.das.jz@bp.renesas.com>

regulator: renesas-usb-vbus-regulator: Add RZ/G3L VBUS regulator support

This commit adds dual USB VBUS regulator support for the RZ/G3L SoC. It
introduces an array of regulator descriptors and a dedicated probe
function to register both regulators. A new platform driver is also added
to handle this dual regulator configuration.

> diff --git a/drivers/regulator/renesas-usb-vbus-regulator.c b/drivers/regulator/renesas-usb-vbus-regulator.c
> index 9ba791bd72eca..9028340008749 100644
> --- a/drivers/regulator/renesas-usb-vbus-regulator.c
> +++ b/drivers/regulator/renesas-usb-vbus-regulator.c

[ ... ]

> @@ -64,6 +108,15 @@ static struct platform_driver rzg2l_usb_vbus_regulator_driver = {
>  };
>  module_platform_driver(rzg2l_usb_vbus_regulator_driver);
>  
> +static struct platform_driver rzg3l_usb_vbus_regulator_driver = {
> +	.probe = rzg3l_usb_vbus_regulator_probe,
> +	.driver	= {
> +		.name = "rzg3l-usb-vbus-regulator",
> +		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
> +	},
> +};
> +module_platform_driver(rzg3l_usb_vbus_regulator_driver);

[Severity: Low]
Will this regression cause a build failure when the driver is compiled as a
module?

Using module_platform_driver() twice in the same C file expands into
module_init() and module_exit() twice.

This creates conflicting global aliases for init_module and cleanup_module,
causing the compiler to flag a redefinition error.

Could these drivers be registered with a custom module_init() function
that registers both, or perhaps combined into a single driver using match data?

> +
>  MODULE_AUTHOR("Biju Das <biju.das.jz@bp.renesas.com>");
>  MODULE_DESCRIPTION("Renesas RZ/G2L USB Vbus Regulator Driver");
>  MODULE_LICENSE("GPL");

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260707143646.245177-1-biju.das.jz@bp.renesas.com?part=9

Re: [PATCH v3 7/9] phy: renesas: phy-rcar-gen3-usb2: Fix devm action registration for disabled VBUS regulator

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 4 potential issue(s) to consider:

New issues:
- [Medium] `regulator_is_enabled()` returns a negative error code on failure, which incorrectly evaluates to true and causes an unbalanced disable WARN_ON.

Pre-existing issues:
- [High] If the regulator was initially enabled in hardware AND explicitly enabled by the driver, only one disable action is registered, leading to a resource leak and WARN_ON.
- [High] If `regulator_enable()` fails, the function returns early without registering a disable action, leaking the implicit `enable_count` reference if the regulator was already enabled.
- [High] Missing cancellation of the pending workqueue task (`channel->work`) during device removal leads to a Use-After-Free.
--

--- Patch [7]: [PATCH v3 7/9] phy: renesas: phy-rcar-gen3-usb2: Fix devm action registration for disabled VBUS regulator ---
commit 30054990ee806fb8d79768ae79587b9acfe0f6a6
Author: Biju Das <biju.das.jz@bp.renesas.com>

phy: renesas: phy-rcar-gen3-usb2: Fix devm action registration for disabled VBUS regulator

This commit updates the VBUS regulator registration to always add a devm
disable action based on the actual enabled state, rather than only when
an explicit enable was requested. This ensures the regulator's enable_count
is correctly decremented during device removal even if it was left enabled
by the bootloader.

> diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
> index d06fb52ed5f1b..ef38c3b365d42 100644
> --- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c
> +++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c
> @@ -905,15 +905,17 @@ static int rcar_gen3_phy_usb2_vbus_regulator_get_exclusive_enable(struct rcar_ge
>  	if (IS_ERR(channel->vbus))
>  		return PTR_ERR(channel->vbus);
>  
> -	if (!enable)
> -		return 0;
> +	if (enable) {
> +		ret = regulator_enable(channel->vbus);
> +		if (ret)
> +			return ret;

[Severity: High]
This is a pre-existing issue, but does this early return leak the implicit
enable_count reference if the regulator was already enabled?

If devm_regulator_get_exclusive() initializes enable_count to 1 (because the
hardware was already enabled), and this regulator_enable() call fails, we
return early and bypass registering the devm disable action. When the probe
fails and devres cleans up, regulator_put() will be called with
enable_count == 1, which triggers a WARN_ON(regulator->enable_count) and
leaks the underlying rdev->use_count.

> +	}
>  
> -	ret = regulator_enable(channel->vbus);
> -	if (ret)
> -		return ret;
> +	if (regulator_is_enabled(channel->vbus))
> +		return devm_add_action_or_reset(dev, rcar_gen3_phy_usb2_vbus_disable_action,
> +						channel->vbus);

[Severity: Medium]
Does regulator_is_enabled() return a negative error code on failure, and
will that be incorrectly evaluated as true here?

If a hardware or I2C error occurs, regulator_is_enabled() can return a
negative value. This condition would evaluate as true, queueing the
rcar_gen3_phy_usb2_vbus_disable_action even if the regulator is actually
disabled or its enable_count is 0. 

On device removal, calling regulator_disable() with an enable_count of 0
triggers a WARN in the regulator core.

[Severity: High]
This is a pre-existing issue, but does this logic lead to a resource leak if
the regulator was initially enabled in hardware and explicitly enabled by the
driver?

If the bootloader leaves the regulator enabled,
devm_regulator_get_exclusive() initializes enable_count to 1. If the driver
also explicitly requests enable = true, regulator_enable() increments
enable_count to 2. 

However, this logic only registers a single disable action. During unbind,
the action decrements enable_count to 1, and devm_regulator_release() calls
regulator_put() which triggers a WARN_ON and destroys the consumer struct
without fully decrementing the underlying rdev->use_count.

> -	return devm_add_action_or_reset(dev, rcar_gen3_phy_usb2_vbus_disable_action,
> -					channel->vbus);
> +	return 0;
>  }

[Severity: High]
This is a pre-existing issue, but does this device removal sequence miss
canceling the pending workqueue task?

drivers/phy/renesas/phy-rcar-gen3-usb2.c:rcar_gen3_phy_usb2_remove() {
	struct rcar_gen3_chan *channel = platform_get_drvdata(pdev);

	if (channel->is_otg_channel)
		device_remove_file(&pdev->dev, &dev_attr_role);
}

The driver schedules channel->work from its IRQ handler. If the driver is
unbound while an IRQ is being processed, rcar_gen3_phy_usb2_remove()
executes but does not call cancel_work_sync(&channel->work).

As devres cleans up, it frees the channel structure. If the workqueue
executes after channel is freed, it will dereference freed memory leading
to a use-after-free.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260707143646.245177-1-biju.das.jz@bp.renesas.com?part=7

-- 
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy

Re: [PATCH v3 5/9] regulator: renesas-usb-vbus-regulator: Add RZ/G3L VBUS regulator support

[Mark Brown]

[-- Attachment #1: Type: text/plain, Size: 308 bytes --]

On Tue, Jul 07, 2026 at 03:36:37PM +0100, Biju wrote:
> From: Biju Das <biju.das.jz@bp.renesas.com>
> 
> Add dual USB VBUS regulator support for the RZ/G3L (r9a08g046) SoC, which
> has two OTG controllers (one per port), unlike RZ/G3S which has only one.

Reviewed-by: Mark Brown <broonie@kernel.org>

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

RE: [PATCH v3 5/9] regulator: renesas-usb-vbus-regulator: Add RZ/G3L VBUS regulator support

[Biju Das]

Hi Mark,

> -----Original Message-----
> From: Mark Brown <broonie@kernel.org>
> Sent: 07 July 2026 16:09
> Subject: Re: [PATCH v3 5/9] regulator: renesas-usb-vbus-regulator: Add RZ/G3L VBUS regulator support
> 
> On Tue, Jul 07, 2026 at 03:36:37PM +0100, Biju wrote:
> > From: Biju Das <biju.das.jz@bp.renesas.com>
> >
> > Add dual USB VBUS regulator support for the RZ/G3L (r9a08g046) SoC,
> > which has two OTG controllers (one per port), unlike RZ/G3S which has only one.
> 
> Reviewed-by: Mark Brown <broonie@kernel.org>

I have encountered compilation issue on x86 with compile_test,
that build this driver as module.

Looks like I cannot use two module_platform_driver definitions
in a C file.

I will switch to single init explicitly registering 2 drivers like [1]

[1] https://elixir.bootlin.com/linux/v7.2-rc1/source/arch/sparc/kernel/central.c#L264

Cheers,
Biju

Re: [PATCH v3 5/9] regulator: renesas-usb-vbus-regulator: Add RZ/G3L VBUS regulator support

[Geert Uytterhoeven]

Hi Biju,

On Wed, 8 Jul 2026 at 10:10, Biju Das <biju.das.jz@bp.renesas.com> wrote:
> > From: Mark Brown <broonie@kernel.org>
> > On Tue, Jul 07, 2026 at 03:36:37PM +0100, Biju wrote:
> > > From: Biju Das <biju.das.jz@bp.renesas.com>
> > >
> > > Add dual USB VBUS regulator support for the RZ/G3L (r9a08g046) SoC,
> > > which has two OTG controllers (one per port), unlike RZ/G3S which has only one.
> >
> > Reviewed-by: Mark Brown <broonie@kernel.org>
>
> I have encountered compilation issue on x86 with compile_test,
> that build this driver as module.
>
> Looks like I cannot use two module_platform_driver definitions
> in a C file.
>
> I will switch to single init explicitly registering 2 drivers like [1]
>
> [1] https://elixir.bootlin.com/linux/v7.2-rc1/source/arch/sparc/kernel/central.c#L264

Why do you need two platform_driver instances?
Because of the different device names? You can use
platform_driver.id_table for named platform devices, just like you
use platform_driver.driver.of_match_table for DT.

Gr{oetje,eeting}s,

                        Geert

-- 
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
                                -- Linus Torvalds

Re: [PATCH v3 5/9] regulator: renesas-usb-vbus-regulator: Add RZ/G3L VBUS regulator support

[Mark Brown]

[-- Attachment #1: Type: text/plain, Size: 546 bytes --]

On Wed, Jul 08, 2026 at 10:28:46AM +0200, Geert Uytterhoeven wrote:
> On Wed, 8 Jul 2026 at 10:10, Biju Das <biju.das.jz@bp.renesas.com> wrote:

> > I will switch to single init explicitly registering 2 drivers like [1]

> Why do you need two platform_driver instances?
> Because of the different device names? You can use
> platform_driver.id_table for named platform devices, just like you
> use platform_driver.driver.of_match_table for DT.

Yes, that seems more natural for this - the ID table can point to the
set of regulators to register.

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

RE: [PATCH v3 5/9] regulator: renesas-usb-vbus-regulator: Add RZ/G3L VBUS regulator support

[Biju Das]

Hi Geert, Mark,

Thanks for the feedback.

> -----Original Message-----
> From: Mark Brown <broonie@kernel.org>
> Sent: 08 July 2026 11:39
> Subject: Re: [PATCH v3 5/9] regulator: renesas-usb-vbus-regulator: Add RZ/G3L VBUS regulator support
> 
> On Wed, Jul 08, 2026 at 10:28:46AM +0200, Geert Uytterhoeven wrote:
> > On Wed, 8 Jul 2026 at 10:10, Biju Das <biju.das.jz@bp.renesas.com> wrote:
> 
> > > I will switch to single init explicitly registering 2 drivers like
> > > [1]
> 
> > Why do you need two platform_driver instances?
> > Because of the different device names? You can use
> > platform_driver.id_table for named platform devices, just like you use
> > platform_driver.driver.of_match_table for DT.
> 
> Yes, that seems more natural for this - the ID table can point to the set of regulators to register.

OK, will switch to platform_driver.id_table.

Note, Initially I had an issue in probing the device related to
id_table match due to string length restriction in [1], so adjusted
the length to less than 24 chars.

[1]https://elixir.bootlin.com/linux/v7.1.2/source/include/linux/mod_devicetable.h#L604

Cheers,
Biju