Devicetree
 help / color / mirror / Atom feed
* [PATCH phy-next 0/2] phy: ti: add driver for TI DS125DF111 Dual-Channel Retimer
@ 2026-05-13 18:51 Ioana Ciornei
  2026-05-13 18:51 ` [PATCH phy-next 1/2] dt-bindings: phy: add PHY bindings for the TI DS125DF111 Retimer PHY Ioana Ciornei
                   ` (2 more replies)
  0 siblings, 3 replies; 7+ messages in thread
From: Ioana Ciornei @ 2026-05-13 18:51 UTC (permalink / raw)
  To: vkoul, neil.armstrong, robh, krzk+dt, conor+dt, johan, linux-phy
  Cc: devicetree, linux-kernel

This patch set adds a generic PHY driver and the corresponding DT
binding for the TI DS125DF111 Dual-Channel retimer. The datasheet on
which this driver was based on can be found at -
https://www.ti.com/lit/gpn/DS125DF111.

A separate generic PHY is registered for each of the two channels of the
retimer, so consumers can drive each channel independently. This allows
for independent control of the channels, which is especially important
since each channel can be routed to different SerDes lanes and it is not
guaranteed that the same retimer will do both directions of SerDes lane.

This was tested on a LS1088ARDB board with the Lynx10G SerDes PHY driver
yet to be submitted.

Ioana Ciornei (2):
  dt-bindings: phy: add PHY bindings for the TI DS125DF111 Retimer PHY
  phy: ti: add PHY driver for TI DS125DF111 Dual-Channel Retimer

 .../bindings/phy/ti,ds125df111.yaml           |  46 ++++
 drivers/phy/ti/Kconfig                        |  10 +
 drivers/phy/ti/Makefile                       |   1 +
 drivers/phy/ti/phy-ds125df111.c               | 245 ++++++++++++++++++
 4 files changed, 302 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/phy/ti,ds125df111.yaml
 create mode 100644 drivers/phy/ti/phy-ds125df111.c

-- 
2.25.1


^ permalink raw reply	[flat|nested] 7+ messages in thread

* [PATCH phy-next 1/2] dt-bindings: phy: add PHY bindings for the TI DS125DF111 Retimer PHY
  2026-05-13 18:51 [PATCH phy-next 0/2] phy: ti: add driver for TI DS125DF111 Dual-Channel Retimer Ioana Ciornei
@ 2026-05-13 18:51 ` Ioana Ciornei
  2026-05-14 18:09   ` Conor Dooley
  2026-05-13 18:51 ` [PATCH phy-next 2/2] phy: ti: add PHY driver for TI DS125DF111 Dual-Channel Retimer Ioana Ciornei
  2026-05-14 10:52 ` [PATCH phy-next 0/2] phy: ti: add " Vladimir Oltean
  2 siblings, 1 reply; 7+ messages in thread
From: Ioana Ciornei @ 2026-05-13 18:51 UTC (permalink / raw)
  To: vkoul, neil.armstrong, robh, krzk+dt, conor+dt, johan, linux-phy
  Cc: devicetree, linux-kernel

Add device tree binding for the TI DS125DF111 Retimer PHY.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
---
 .../bindings/phy/ti,ds125df111.yaml           | 46 +++++++++++++++++++
 1 file changed, 46 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/phy/ti,ds125df111.yaml

diff --git a/Documentation/devicetree/bindings/phy/ti,ds125df111.yaml b/Documentation/devicetree/bindings/phy/ti,ds125df111.yaml
new file mode 100644
index 000000000000..47e9ba2a8990
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/ti,ds125df111.yaml
@@ -0,0 +1,46 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/ti,ds125df111.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: TI DS125DF111 Retimer PHY
+
+description:
+  This binding describes the TI DS125DF111 multi-protocol Retimer PHY.
+
+maintainers:
+  - Ioana Ciornei <ioana.ciornei@nxp.com>
+
+properties:
+  compatible:
+    const: ti,ds125df111
+
+  reg:
+    maxItems: 1
+
+  "#phy-cells":
+    const: 1
+    description: |
+      The phandle's argument in the PHY specifier selects one of the two
+      channels of the retimer
+
+required:
+  - compatible
+  - reg
+  - "#phy-cells"
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c {
+      #address-cells = <1>;
+      #size-cells = <0>;
+
+      ti_retimer: retimer@18 {
+        compatible = "ti,ds125df111";
+        reg = <0x18>;
+        #phy-cells = <1>;
+      };
+    };
-- 
2.25.1


^ permalink raw reply related	[flat|nested] 7+ messages in thread

* [PATCH phy-next 2/2] phy: ti: add PHY driver for TI DS125DF111 Dual-Channel Retimer
  2026-05-13 18:51 [PATCH phy-next 0/2] phy: ti: add driver for TI DS125DF111 Dual-Channel Retimer Ioana Ciornei
  2026-05-13 18:51 ` [PATCH phy-next 1/2] dt-bindings: phy: add PHY bindings for the TI DS125DF111 Retimer PHY Ioana Ciornei
@ 2026-05-13 18:51 ` Ioana Ciornei
  2026-05-14 10:31   ` sashiko-bot
  2026-05-14 10:52 ` [PATCH phy-next 0/2] phy: ti: add " Vladimir Oltean
  2 siblings, 1 reply; 7+ messages in thread
From: Ioana Ciornei @ 2026-05-13 18:51 UTC (permalink / raw)
  To: vkoul, neil.armstrong, robh, krzk+dt, conor+dt, johan, linux-phy
  Cc: devicetree, linux-kernel

Add a generic PHY driver for the TI DS125DF111 Multi-Protocol
Dual-Channel Retimer. The driver currently supports only 10G and 1G link
speeds but it can easily extended to also cover other usecases.

Since the available datasheet (https://www.ti.com/lit/gpn/DS125DF111)
does not name the registers, the name for the macros were determined by
their usage pattern.

A PHY device is created for each of the two channels present on the
retimer. This allows for independent configuration of the two channels.
This capability is especially important on retimers which have more than
2 channels that can be, depending on the board design, connected in
multiple different ways to the SerDes lanes.

Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
---
 drivers/phy/ti/Kconfig          |  10 ++
 drivers/phy/ti/Makefile         |   1 +
 drivers/phy/ti/phy-ds125df111.c | 245 ++++++++++++++++++++++++++++++++
 3 files changed, 256 insertions(+)
 create mode 100644 drivers/phy/ti/phy-ds125df111.c

diff --git a/drivers/phy/ti/Kconfig b/drivers/phy/ti/Kconfig
index b40f28019131..475e80fcd52d 100644
--- a/drivers/phy/ti/Kconfig
+++ b/drivers/phy/ti/Kconfig
@@ -111,3 +111,13 @@ config PHY_TI_GMII_SEL
 	help
 	  This driver supports configuring of the TI CPSW Port mode depending on
 	  the Ethernet PHY connected to the CPSW Port.
+
+config PHY_TI_DS125DF111
+	tristate "DS125DF111 2-Channel Retimer Driver"
+	depends on OF && I2C
+	select GENERIC_PHY
+	help
+	  Enable this to add support for configuration and runtime management
+	  of the TI DS125DF111 Multi-Protocol 2-Channel Retimer.
+	  The retimer is modeled as a Generic PHY and supports both 10G and 1G
+	  link speeds.
diff --git a/drivers/phy/ti/Makefile b/drivers/phy/ti/Makefile
index dcba2571c9bd..e68445ddd848 100644
--- a/drivers/phy/ti/Makefile
+++ b/drivers/phy/ti/Makefile
@@ -9,3 +9,4 @@ obj-$(CONFIG_TWL4030_USB)		+= phy-twl4030-usb.o
 obj-$(CONFIG_PHY_AM654_SERDES)		+= phy-am654-serdes.o
 obj-$(CONFIG_PHY_TI_GMII_SEL)		+= phy-gmii-sel.o
 obj-$(CONFIG_PHY_J721E_WIZ)		+= phy-j721e-wiz.o
+obj-$(CONFIG_PHY_TI_DS125DF111)		+= phy-ds125df111.o
diff --git a/drivers/phy/ti/phy-ds125df111.c b/drivers/phy/ti/phy-ds125df111.c
new file mode 100644
index 000000000000..8ac10c603bf7
--- /dev/null
+++ b/drivers/phy/ti/phy-ds125df111.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright 2026 NXP */
+
+#include <linux/i2c.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+#include <linux/phy/phy.h>
+
+#define DS125DF111_NUM_CH			2
+#define DS125DF111_NUM_VCO_GROUP_REG		5
+
+#define DS125DF111_CH_SELECT			0xff
+#define DS125DF111_CH_SELECT_TARGET_MASK	GENMASK(3, 0)
+#define DS125DF111_CH_SELECT_EN			BIT(2)
+
+#define DS125DF111_CH_CTRL			0x00
+#define DS125DF111_CH_CTRL_RESET		BIT(2) /* self clearing */
+
+#define DS125DF111_VCO_GROUP_BASE		0x60
+
+#define DS125DF111_RATIOS			0x2F
+#define DS125DF111_RATIOS_RATE_MASK		GENMASK(7, 6)
+#define DS125DF111_RATIOS_SUBRATE_MASK		GENMASK(5, 4)
+
+struct ds125df111_ch {
+	struct phy *phy;
+	struct ds125df111_priv *priv;
+	int idx;
+};
+
+struct ds125df111_priv {
+	struct ds125df111_ch ch[DS125DF111_NUM_CH];
+	struct i2c_client *client;
+	struct mutex mutex; /* protects access to shared registers */
+};
+
+enum ds125df111_mode {
+	FREQ_1G,
+	FREQ_10G,
+};
+
+static const struct ds125df111_config {
+	u8 vco_group[DS125DF111_NUM_VCO_GROUP_REG];
+	u8 rate;
+	u8 subrate;
+} ds125df111_cfg[] = {
+	[FREQ_1G] = {
+		/* VCO group #0 = 10GHz, VCO group #1 = 10GHz */
+		.vco_group = {0x00, 0xB2, 0x00, 0xB2, 0xCC},
+		/* By using the following combination of rate and subrate we
+		 * select divide ratios of 1, 2, 4, 8 on both groups
+		 */
+		.rate = 0x1,
+		.subrate = 0x2,
+	},
+
+	[FREQ_10G] = {
+		/* VCO group #0 = 10.3125GHz, VCO group #1 = 10.3125GHz */
+		.vco_group = {0x90, 0xB3, 0x90, 0xB3, 0xCD},
+		/* By using the following combination of rate and subrate we
+		 * select divide ratios of 1 on both groups
+		 */
+		.rate = 0x1,
+		.subrate = 0x3,
+	},
+};
+
+static int ds125df111_configure(struct phy *phy,
+				const struct ds125df111_config *cfg)
+{
+	struct ds125df111_ch *ch = phy_get_drvdata(phy);
+	struct ds125df111_priv *priv = ch->priv;
+	struct i2c_client *i2c = priv->client;
+	struct device *dev = &phy->dev;
+	u8 val;
+	int err, i;
+
+	mutex_lock(&priv->mutex);
+
+	/* Make sure that any subsequent read/write operation will be directed
+	 * only to the registers of the selected channel
+	 */
+	err = i2c_smbus_read_byte_data(i2c, DS125DF111_CH_SELECT);
+	if (err < 0) {
+		dev_err(dev, "Unable to select channel\n");
+		goto out;
+	}
+	val = (u8)err;
+	val &= ~DS125DF111_CH_SELECT_TARGET_MASK;
+	val |= DS125DF111_CH_SELECT_EN | ch->idx;
+	err = i2c_smbus_write_byte_data(i2c, DS125DF111_CH_SELECT, val);
+	if (err < 0) {
+		dev_err(dev, "Unable to select channel\n");
+		goto out;
+	}
+
+	/* Reset Channel Registers */
+	err = i2c_smbus_read_byte_data(i2c, DS125DF111_CH_CTRL);
+	if (err < 0) {
+		dev_err(dev, "Error resetting channel configuration\n");
+		goto out;
+	}
+	val = (u8)err;
+	val |= DS125DF111_CH_CTRL_RESET;
+	err = i2c_smbus_write_byte_data(i2c, DS125DF111_CH_CTRL, val);
+	if (err < 0) {
+		dev_err(dev, "Error resetting channel configuration\n");
+		goto out;
+	}
+
+	/* Program the VCO group frequencies */
+	for (i = 0; i < DS125DF111_NUM_VCO_GROUP_REG; i++) {
+		err = i2c_smbus_write_byte_data(i2c,
+						DS125DF111_VCO_GROUP_BASE + i,
+						cfg->vco_group[i]);
+		if (err < 0) {
+			dev_err(dev, "Error programming VCO group frequencies\n");
+			goto out;
+		}
+	}
+
+	/* Set the Divide Ratios for the VCO Groups*/
+	err = i2c_smbus_read_byte_data(i2c, DS125DF111_RATIOS);
+	if (err < 0) {
+		dev_err(dev, "Error programming the divide ratios\n");
+		goto out;
+	}
+	val = (u8)err;
+	val &= ~(DS125DF111_RATIOS_RATE_MASK | DS125DF111_RATIOS_SUBRATE_MASK);
+	val |= FIELD_PREP(DS125DF111_RATIOS_RATE_MASK, cfg->rate) |
+		FIELD_PREP(DS125DF111_RATIOS_SUBRATE_MASK, cfg->subrate);
+	err = i2c_smbus_write_byte_data(i2c, DS125DF111_RATIOS, val);
+	if (err < 0) {
+		dev_err(dev, "Error programming the divide ratios\n");
+		goto out;
+	}
+
+	mutex_unlock(&priv->mutex);
+
+	return 0;
+
+out:
+	mutex_unlock(&priv->mutex);
+
+	return err;
+}
+
+static int ds125df111_set_mode(struct phy *phy, enum phy_mode mode, int submode)
+{
+	const struct ds125df111_config *cfg;
+
+	if (mode != PHY_MODE_ETHERNET)
+		return -EOPNOTSUPP;
+
+	switch (submode) {
+	case PHY_INTERFACE_MODE_10GBASER:
+		cfg = &ds125df111_cfg[FREQ_10G];
+		break;
+	case PHY_INTERFACE_MODE_1000BASEX:
+	case PHY_INTERFACE_MODE_SGMII:
+		cfg = &ds125df111_cfg[FREQ_1G];
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return ds125df111_configure(phy, cfg);
+}
+
+static const struct phy_ops ds125df111_ops = {
+	.set_mode	= ds125df111_set_mode,
+	.owner		= THIS_MODULE,
+};
+
+static struct phy *ds125df111_xlate(struct device *dev,
+				    const struct of_phandle_args *args)
+{
+	struct ds125df111_priv *priv = dev_get_drvdata(dev);
+	u32 idx = args->args[0];
+
+	if (idx >= DS125DF111_NUM_CH) {
+		dev_err(dev, "Maximum number of channels is %d\n",
+			DS125DF111_NUM_CH);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return priv->ch[idx].phy;
+}
+
+static int ds125df111_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct phy_provider *provider;
+	struct ds125df111_priv *priv;
+	int i, err;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	priv->client = client;
+	err = devm_mutex_init(dev, &priv->mutex);
+	if (err)
+		return err;
+
+	i2c_set_clientdata(client, priv);
+
+	for (i = 0; i < DS125DF111_NUM_CH; i++) {
+		struct ds125df111_ch *ch = &priv->ch[i];
+		struct phy *phy;
+
+		phy = devm_phy_create(dev, NULL, &ds125df111_ops);
+		if (IS_ERR(phy))
+			return PTR_ERR(phy);
+
+		ch->idx = i;
+		ch->priv = priv;
+		ch->phy = phy;
+
+		phy_set_drvdata(phy, ch);
+	}
+
+	provider = devm_of_phy_provider_register(dev, ds125df111_xlate);
+
+	return PTR_ERR_OR_ZERO(provider);
+}
+
+static const struct of_device_id ds125df111_dt_ids[] = {
+	{ .compatible = "ti,ds125df111", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, ds125df111_dt_ids);
+
+static struct i2c_driver ds125df111_driver = {
+	.driver = {
+		.name = "ds125df111",
+		.of_match_table = ds125df111_dt_ids,
+	},
+	.probe = ds125df111_probe,
+};
+module_i2c_driver(ds125df111_driver);
+
+MODULE_AUTHOR("Ioana Ciornei <ioana.ciornei@nxp.com>");
+MODULE_DESCRIPTION("TI DS125DF111 Retimer driver");
+MODULE_LICENSE("GPL");
-- 
2.25.1


^ permalink raw reply related	[flat|nested] 7+ messages in thread

* Re: [PATCH phy-next 2/2] phy: ti: add PHY driver for TI DS125DF111 Dual-Channel Retimer
  2026-05-13 18:51 ` [PATCH phy-next 2/2] phy: ti: add PHY driver for TI DS125DF111 Dual-Channel Retimer Ioana Ciornei
@ 2026-05-14 10:31   ` sashiko-bot
  2026-05-14 10:47     ` Ioana Ciornei
  0 siblings, 1 reply; 7+ messages in thread
From: sashiko-bot @ 2026-05-14 10:31 UTC (permalink / raw)
  To: Ioana Ciornei
  Cc: robh, krzk+dt, conor+dt, neil.armstrong, olteanv, devicetree,
	vkoul, linux-phy

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Medium] Uninitialized memory read in `ds125df111_xlate` due to missing `args_count` validation.
- [Low] Missing explicit header inclusions for macros and memory allocation functions.
--

commit a5dcf247e2e2a6b752d667ac46227925aa476def
Author: Ioana Ciornei <ioana.ciornei@nxp.com>

phy: ti: add PHY driver for TI DS125DF111 Dual-Channel Retimer

This commit adds a generic PHY driver for the TI DS125DF111 Multi-Protocol
Dual-Channel Retimer over I2C. It currently supports 10G and 1G link speeds,
and registers a separate PHY device for each of the two channels to allow
independent configuration.

> diff --git a/drivers/phy/ti/phy-ds125df111.c b/drivers/phy/ti/phy-ds125df111.c
> new file mode 100644
> index 0000000000000..8ac10c603bf70
> --- /dev/null
> +++ b/drivers/phy/ti/phy-ds125df111.c
> @@ -0,0 +1,245 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/* Copyright 2026 NXP */
> +
> +#include <linux/i2c.h>
> +#include <linux/kernel.h>
> +#include <linux/module.h>
> +#include <linux/phy.h>
> +#include <linux/phy/phy.h>

This isn't a bug, but should this include linux/bitfield.h, linux/bits.h,
and linux/slab.h?

The driver uses FIELD_PREP(), GENMASK(), and devm_kzalloc(), but relies on
implicit inclusions for these headers. Explicitly including them can help
prevent build breakages if the include chains are refactored in the future.

[ ... ]

> +static struct phy *ds125df111_xlate(struct device *dev,
> +				    const struct of_phandle_args *args)
> +{
> +	struct ds125df111_priv *priv = dev_get_drvdata(dev);
> +	u32 idx = args->args[0];

Is it possible to read uninitialized memory here?

If a consumer's Device Tree reference incorrectly configures #phy-cells = <0>,
of_parse_phandle_with_args() sets args->args_count to 0 and leaves the
args array unmodified.

Since the of_phandle_args structure is often allocated on the stack, for
example in _of_phy_get(), evaluating args->args[0] without verifying that
args->args_count >= 1 could result in evaluating stack garbage against the
maximum channel count.

> +
> +	if (idx >= DS125DF111_NUM_CH) {
> +		dev_err(dev, "Maximum number of channels is %d\n",
> +			DS125DF111_NUM_CH);
> +		return ERR_PTR(-EINVAL);
> +	}
> +
> +	return priv->ch[idx].phy;
> +}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260513185103.1371809-1-ioana.ciornei@nxp.com?part=2

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH phy-next 2/2] phy: ti: add PHY driver for TI DS125DF111 Dual-Channel Retimer
  2026-05-14 10:31   ` sashiko-bot
@ 2026-05-14 10:47     ` Ioana Ciornei
  0 siblings, 0 replies; 7+ messages in thread
From: Ioana Ciornei @ 2026-05-14 10:47 UTC (permalink / raw)
  To: sashiko-reviews
  Cc: robh, krzk+dt, conor+dt, neil.armstrong, olteanv, devicetree,
	vkoul, linux-phy

On Thu, May 14, 2026 at 10:31:42AM +0000, sashiko-bot@kernel.org wrote:
> [You don't often get email from sashiko-bot@kernel.org. Learn why this is important at https://aka.ms/LearnAboutSenderIdentification ]
> 
> Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
> - [Medium] Uninitialized memory read in `ds125df111_xlate` due to missing `args_count` validation.
> - [Low] Missing explicit header inclusions for macros and memory allocation functions.
> --
> 
> commit a5dcf247e2e2a6b752d667ac46227925aa476def
> Author: Ioana Ciornei <ioana.ciornei@nxp.com>
> 
> phy: ti: add PHY driver for TI DS125DF111 Dual-Channel Retimer
> 
> This commit adds a generic PHY driver for the TI DS125DF111 Multi-Protocol
> Dual-Channel Retimer over I2C. It currently supports 10G and 1G link speeds,
> and registers a separate PHY device for each of the two channels to allow
> independent configuration.
> 
> > diff --git a/drivers/phy/ti/phy-ds125df111.c b/drivers/phy/ti/phy-ds125df111.c
> > new file mode 100644
> > index 0000000000000..8ac10c603bf70
> > --- /dev/null
> > +++ b/drivers/phy/ti/phy-ds125df111.c
> > @@ -0,0 +1,245 @@
> > +// SPDX-License-Identifier: GPL-2.0
> > +/* Copyright 2026 NXP */
> > +
> > +#include <linux/i2c.h>
> > +#include <linux/kernel.h>
> > +#include <linux/module.h>
> > +#include <linux/phy.h>
> > +#include <linux/phy/phy.h>
> 
> This isn't a bug, but should this include linux/bitfield.h, linux/bits.h,
> and linux/slab.h?
> 
> The driver uses FIELD_PREP(), GENMASK(), and devm_kzalloc(), but relies on
> implicit inclusions for these headers. Explicitly including them can help
> prevent build breakages if the include chains are refactored in the future.

Ok, sure. Will fix in v2.

> 
> [ ... ]
> 
> > +static struct phy *ds125df111_xlate(struct device *dev,
> > +                                 const struct of_phandle_args *args)
> > +{
> > +     struct ds125df111_priv *priv = dev_get_drvdata(dev);
> > +     u32 idx = args->args[0];
> 
> Is it possible to read uninitialized memory here?
> 
> If a consumer's Device Tree reference incorrectly configures #phy-cells = <0>,
> of_parse_phandle_with_args() sets args->args_count to 0 and leaves the
> args array unmodified.
> 
> Since the of_phandle_args structure is often allocated on the stack, for
> example in _of_phy_get(), evaluating args->args[0] without verifying that
> args->args_count >= 1 could result in evaluating stack garbage against the
> maximum channel count.

Good point. Will verify the args_count.

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH phy-next 0/2] phy: ti: add driver for TI DS125DF111 Dual-Channel Retimer
  2026-05-13 18:51 [PATCH phy-next 0/2] phy: ti: add driver for TI DS125DF111 Dual-Channel Retimer Ioana Ciornei
  2026-05-13 18:51 ` [PATCH phy-next 1/2] dt-bindings: phy: add PHY bindings for the TI DS125DF111 Retimer PHY Ioana Ciornei
  2026-05-13 18:51 ` [PATCH phy-next 2/2] phy: ti: add PHY driver for TI DS125DF111 Dual-Channel Retimer Ioana Ciornei
@ 2026-05-14 10:52 ` Vladimir Oltean
  2 siblings, 0 replies; 7+ messages in thread
From: Vladimir Oltean @ 2026-05-14 10:52 UTC (permalink / raw)
  To: Ioana Ciornei
  Cc: vkoul, neil.armstrong, robh, krzk+dt, conor+dt, johan, linux-phy,
	devicetree, linux-kernel

On Wed, May 13, 2026 at 09:51:01PM +0300, Ioana Ciornei wrote:
> This patch set adds a generic PHY driver and the corresponding DT
> binding for the TI DS125DF111 Dual-Channel retimer. The datasheet on
> which this driver was based on can be found at -
> https://www.ti.com/lit/gpn/DS125DF111.
> 
> A separate generic PHY is registered for each of the two channels of the
> retimer, so consumers can drive each channel independently. This allows
> for independent control of the channels, which is especially important
> since each channel can be routed to different SerDes lanes and it is not
> guaranteed that the same retimer will do both directions of SerDes lane.
> 
> This was tested on a LS1088ARDB board with the Lynx10G SerDes PHY driver
> yet to be submitted.
> 
> Ioana Ciornei (2):
>   dt-bindings: phy: add PHY bindings for the TI DS125DF111 Retimer PHY
>   phy: ti: add PHY driver for TI DS125DF111 Dual-Channel Retimer
> 
>  .../bindings/phy/ti,ds125df111.yaml           |  46 ++++
>  drivers/phy/ti/Kconfig                        |  10 +
>  drivers/phy/ti/Makefile                       |   1 +
>  drivers/phy/ti/phy-ds125df111.c               | 245 ++++++++++++++++++
>  4 files changed, 302 insertions(+)
>  create mode 100644 Documentation/devicetree/bindings/phy/ti,ds125df111.yaml
>  create mode 100644 drivers/phy/ti/phy-ds125df111.c
> 
> -- 
> 2.25.1

When you resend, please add a MAINTAINERS entry for this driver.

Thanks!

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH phy-next 1/2] dt-bindings: phy: add PHY bindings for the TI DS125DF111 Retimer PHY
  2026-05-13 18:51 ` [PATCH phy-next 1/2] dt-bindings: phy: add PHY bindings for the TI DS125DF111 Retimer PHY Ioana Ciornei
@ 2026-05-14 18:09   ` Conor Dooley
  0 siblings, 0 replies; 7+ messages in thread
From: Conor Dooley @ 2026-05-14 18:09 UTC (permalink / raw)
  To: Ioana Ciornei
  Cc: vkoul, neil.armstrong, robh, krzk+dt, conor+dt, johan, linux-phy,
	devicetree, linux-kernel

[-- Attachment #1: Type: text/plain, Size: 1963 bytes --]

On Wed, May 13, 2026 at 09:51:02PM +0300, Ioana Ciornei wrote:
> Add device tree binding for the TI DS125DF111 Retimer PHY.
> 
> Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
> ---
>  .../bindings/phy/ti,ds125df111.yaml           | 46 +++++++++++++++++++
>  1 file changed, 46 insertions(+)
>  create mode 100644 Documentation/devicetree/bindings/phy/ti,ds125df111.yaml
> 
> diff --git a/Documentation/devicetree/bindings/phy/ti,ds125df111.yaml b/Documentation/devicetree/bindings/phy/ti,ds125df111.yaml
> new file mode 100644
> index 000000000000..47e9ba2a8990
> --- /dev/null
> +++ b/Documentation/devicetree/bindings/phy/ti,ds125df111.yaml
> @@ -0,0 +1,46 @@
> +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
> +%YAML 1.2
> +---
> +$id: http://devicetree.org/schemas/phy/ti,ds125df111.yaml#
> +$schema: http://devicetree.org/meta-schemas/core.yaml#
> +
> +title: TI DS125DF111 Retimer PHY
> +
> +description:
> +  This binding describes the TI DS125DF111 multi-protocol Retimer PHY.
> +
> +maintainers:
> +  - Ioana Ciornei <ioana.ciornei@nxp.com>
> +
> +properties:
> +  compatible:
> +    const: ti,ds125df111
> +
> +  reg:
> +    maxItems: 1
> +
> +  "#phy-cells":
> +    const: 1
> +    description: |
> +      The phandle's argument in the PHY specifier selects one of the two
> +      channels of the retimer
> +
> +required:
> +  - compatible
> +  - reg
> +  - "#phy-cells"
> +
> +additionalProperties: false
> +
> +examples:
> +  - |
> +    i2c {
> +      #address-cells = <1>;
> +      #size-cells = <0>;
> +
> +      ti_retimer: retimer@18 {

Drop the unused label here please. How come the node name isn't phy@
btw?
Otherwise,
Acked-by: Conor Dooley <conor.dooley@microchip.com>
pw-bot: changes-requested

Cheers,
Conor.

> +        compatible = "ti,ds125df111";
> +        reg = <0x18>;
> +        #phy-cells = <1>;
> +      };
> +    };
> -- 
> 2.25.1
> 

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]

^ permalink raw reply	[flat|nested] 7+ messages in thread

end of thread, other threads:[~2026-05-14 18:09 UTC | newest]

Thread overview: 7+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-05-13 18:51 [PATCH phy-next 0/2] phy: ti: add driver for TI DS125DF111 Dual-Channel Retimer Ioana Ciornei
2026-05-13 18:51 ` [PATCH phy-next 1/2] dt-bindings: phy: add PHY bindings for the TI DS125DF111 Retimer PHY Ioana Ciornei
2026-05-14 18:09   ` Conor Dooley
2026-05-13 18:51 ` [PATCH phy-next 2/2] phy: ti: add PHY driver for TI DS125DF111 Dual-Channel Retimer Ioana Ciornei
2026-05-14 10:31   ` sashiko-bot
2026-05-14 10:47     ` Ioana Ciornei
2026-05-14 10:52 ` [PATCH phy-next 0/2] phy: ti: add " Vladimir Oltean

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox