[PATCH v6 0/2] Add Lontium LT7911EXC eDP to MIPI DSI bridge

[PATCH v6 0/2] Add Lontium LT7911EXC eDP to MIPI DSI bridge

[syyang]

From: Sunyun Yang <syyang@lontium.com>

The LT7911EXC is an I2C-controlled bridge that Receiver eDP1.4
and output signal/dual port mipi dsi. This series introduces:

- A device tree binding YAML file describing the hardware
- A new DRM bridge driver implementing the basic functionality

Signed-off-by: Sunyun Yang<syyang@lontium.com>
---
Change in v6:
- dt-binding:
- drm/bridge:
 1. use #define FW_FILE  "Lontium/lt7911exc_fw.bin" to match linux-firmware
- Link to v5: https://lore.kernel.org/lkml/20260506013153.2240-1-syyang@lontium.com/

Change in v5:
- dt-binding:
- drm/bridge:
 1. Change "mipi" to "mipi dsi" in the commit message.     [Dmitry]
 2. Change "eDP/MIPI" to "eDP/MIPI DSI" in Kconfig.
- Link to v4: https://lore.kernel.org/lkml/20260430094612.3408174-1-syyang@lontium.com/

Change in v4:
- dt-binding:
 1. Fix the missing spaces on the "subject".             [Krzysztof]
 2. Fix the error descriptions for port@0 and port@1.
- drm/bridge:
- Link to v3: https://lore.kernel.org/lkml/20260429040541.3404116-1-syyang@lontium.com/

Change in v3:
- dt-binding:
- drm/bridge:
 1. already submit lt7911exc_fw.bin to linux-firmware.  [Dmitry]
 2. remove lt7911exc_remove function.
 3. drop  the "lontium, "  in lt7911exc_i2c_table.
- Link to v2: https://lore.kernel.org/lkml/20260428063224.3316655-1-syyang@lontium.com/

Change in v2:
- dt-binding:
 1. reset pins use active low.                        [Dmitry]
- drm/bridge:
 1. use atomic_* callbacks.                           [Quentin]
 2. fix the incorrect formatting and spaces.
 3. add the required header files.                    [Dmitry]
 4. remove "enabled" flag.
 5. remove *fw from the lt7911exc struct.
 6. .max_register and .range_max use actual range.
 7. regulator use bulk interface.
 8. use dev_err_probe, devm_mutex_init and devm_drm_bridge_add.
 9. Replace GPL v2 with GPL.
- Link to v1: https://lore.kernel.org/lkml/20260420023354.1192642-1-syyang@lontium.com/
---
Sunyun Yang (2):
  dt-bindings: bridge: Add Lontium LT7911EXC eDP to MIPI DSI bridge
  drm/bridge: Add Lontium LT7911EXC eDP to MIPI DSI bridge

 .../display/bridge/lontium,lt7911exc.yaml     |  89 ++++
 drivers/gpu/drm/bridge/Kconfig                |  13 +
 drivers/gpu/drm/bridge/Makefile               |   1 +
 drivers/gpu/drm/bridge/lontium-lt7911exc.c    | 493 ++++++++++++++++++
 4 files changed, 596 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/bridge/lontium,lt7911exc.yaml
 create mode 100644 drivers/gpu/drm/bridge/lontium-lt7911exc.c

-- 
2.34.1

[PATCH v6 1/2] dt-bindings: bridge: Add Lontium LT7911EXC eDP to MIPI DSI bridge

[syyang]

From: Sunyun Yang <syyang@lontium.com>

The LT7911EXC is an I2C-controlled bridge that Receiver eDP1.4
and output signal/dual port mipi dsi.

Signed-off-by: Sunyun Yang <syyang@lontium.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
---
 .../display/bridge/lontium,lt7911exc.yaml     | 89 +++++++++++++++++++
 1 file changed, 89 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/bridge/lontium,lt7911exc.yaml

diff --git a/Documentation/devicetree/bindings/display/bridge/lontium,lt7911exc.yaml b/Documentation/devicetree/bindings/display/bridge/lontium,lt7911exc.yaml
new file mode 100644
index 000000000000..3290b10ce883
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/bridge/lontium,lt7911exc.yaml
@@ -0,0 +1,89 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/bridge/lontium,lt7911exc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Lontium LT7911EXC eDP to MIPI DSI Bridge
+
+maintainers:
+  - Sunyun Yang <syyang@lontium.com>
+
+properties:
+  compatible:
+    enum:
+      - lontium,lt7911exc
+
+  reg:
+    maxItems: 1
+
+  reset-gpios:
+    maxItems: 1
+    description: GPIO connected to RST_ pin.
+
+  vdd-supply:
+    description: Regulator for 1.2V MIPI phy power.
+
+  vcc-supply:
+    description: Regulator for 3.3V IO power.
+
+  ports:
+    $ref: /schemas/graph.yaml#/properties/ports
+
+    properties:
+      port@0:
+        $ref: /schemas/graph.yaml#/properties/port
+        description: Video port for eDP input.
+
+      port@1:
+        $ref: /schemas/graph.yaml#/properties/port
+        description: Video port for MIPI DSI output.
+
+    required:
+      - port@0
+      - port@1
+
+required:
+  - compatible
+  - reg
+  - reset-gpios
+  - vdd-supply
+  - vcc-supply
+  - ports
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        mipi-bridge@41 {
+            compatible = "lontium,lt7911exc";
+            reg = <0x41>;
+            reset-gpios = <&gpy8 8 GPIO_ACTIVE_LOW>;
+            vdd-supply = <&lt7911exc_1v2>;
+            vcc-supply = <&lt7911exc_3v3>;
+
+            ports {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                port@0 {
+                    reg = <0>;
+                    bridge_in: endpoint {
+                        remote-endpoint = <&edp_out>;
+                    };
+                };
+
+                port@1 {
+                    reg = <1>;
+                    bridge_out: endpoint {
+                        remote-endpoint = <&panel_in>;
+                    };
+                };
+            };
+        };
+    };
-- 
2.34.1

[PATCH v6 2/2] drm/bridge: Add Lontium LT7911EXC eDP to MIPI DSI bridge

[syyang]

From: Sunyun Yang <syyang@lontium.com>

The LT7911EXC is an I2C-controlled bridge that Receiver eDP1.4
and output signal/dual port mipi dsi.

Signed-off-by: Sunyun Yang <syyang@lontium.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/bridge/Kconfig             |  13 +
 drivers/gpu/drm/bridge/Makefile            |   1 +
 drivers/gpu/drm/bridge/lontium-lt7911exc.c | 493 +++++++++++++++++++++
 3 files changed, 507 insertions(+)
 create mode 100644 drivers/gpu/drm/bridge/lontium-lt7911exc.c

diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
index c3209b0f4678..fe45a9052aa0 100644
--- a/drivers/gpu/drm/bridge/Kconfig
+++ b/drivers/gpu/drm/bridge/Kconfig
@@ -132,6 +132,19 @@ config DRM_ITE_IT6505
 	help
 	  ITE IT6505 DisplayPort bridge chip driver.
 
+config DRM_LONTIUM_LT7911EXC
+	tristate "Lontium eDP/MIPI DSI bridge"
+	depends on OF
+	select CRC32
+	select FW_LOADER
+	select DRM_PANEL
+	select DRM_KMS_HELPER
+	help
+	  DRM driver for the Lontium LT7911EXC bridge chip.
+	  The LT7911EXC converts eDP input to single/dual port
+	  MIPI DSI output.
+	  Please say Y if you have such hardware.
+
 config DRM_LONTIUM_LT8912B
 	tristate "Lontium LT8912B DSI/HDMI bridge"
 	depends on OF
diff --git a/drivers/gpu/drm/bridge/Makefile b/drivers/gpu/drm/bridge/Makefile
index beab5b695a6e..70ddca75dd3a 100644
--- a/drivers/gpu/drm/bridge/Makefile
+++ b/drivers/gpu/drm/bridge/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_DRM_I2C_NXP_TDA998X) += tda998x.o
 obj-$(CONFIG_DRM_INNO_HDMI) += inno-hdmi.o
 obj-$(CONFIG_DRM_ITE_IT6263) += ite-it6263.o
 obj-$(CONFIG_DRM_ITE_IT6505) += ite-it6505.o
+obj-$(CONFIG_DRM_LONTIUM_LT7911EXC) += lontium-lt7911exc.o
 obj-$(CONFIG_DRM_LONTIUM_LT8912B) += lontium-lt8912b.o
 obj-$(CONFIG_DRM_LONTIUM_LT9211) += lontium-lt9211.o
 obj-$(CONFIG_DRM_LONTIUM_LT9611) += lontium-lt9611.o
diff --git a/drivers/gpu/drm/bridge/lontium-lt7911exc.c b/drivers/gpu/drm/bridge/lontium-lt7911exc.c
new file mode 100644
index 000000000000..d50fc979ebd4
--- /dev/null
+++ b/drivers/gpu/drm/bridge/lontium-lt7911exc.c
@@ -0,0 +1,493 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2026 Lontium Semiconductor, Inc.
+ */
+
+#include <linux/crc32.h>
+#include <linux/firmware.h>
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of_graph.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include <drm/drm_bridge.h>
+#include <drm/drm_mipi_dsi.h>
+#include <drm/drm_of.h>
+
+#define FW_SIZE (64 * 1024)
+#define LT_PAGE_SIZE 32
+#define FW_FILE  "Lontium/lt7911exc_fw.bin"
+#define LT7911EXC_PAGE_CONTROL 0xff
+
+struct lt7911exc {
+	struct device *dev;
+	struct i2c_client *client;
+	struct drm_bridge bridge;
+	struct regmap *regmap;
+	/* Protects all accesses to registers by stopping the on-chip MCU */
+	struct mutex ocm_lock;
+	struct regulator_bulk_data supplies[2];
+	struct gpio_desc *reset_gpio;
+	int fw_version;
+};
+
+static const struct regmap_range_cfg lt7911exc_ranges[] = {
+	{
+		.name = "register_range",
+		.range_min =  0,
+		.range_max = 0xe8ff,
+		.selector_reg = LT7911EXC_PAGE_CONTROL,
+		.selector_mask = 0xff,
+		.selector_shift = 0,
+		.window_start = 0,
+		.window_len = 0x100,
+	},
+};
+
+static const struct regmap_config lt7911exc_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = 0xe8ff,
+	.ranges = lt7911exc_ranges,
+	.num_ranges = ARRAY_SIZE(lt7911exc_ranges),
+};
+
+static u32 cal_crc32_custom(const u8 *data, u64 length)
+{
+	u32 crc = 0xffffffff;
+	u8 buf[4];
+	u64 i;
+
+	for (i = 0; i < length; i += 4) {
+		buf[0] = data[i + 3];
+		buf[1] = data[i + 2];
+		buf[2] = data[i + 1];
+		buf[3] = data[i + 0];
+		crc = crc32_be(crc, buf, 4);
+	}
+
+	return crc;
+}
+
+static inline struct lt7911exc *bridge_to_lt7911exc(struct drm_bridge *bridge)
+{
+	return container_of(bridge, struct lt7911exc, bridge);
+}
+
+static void lt7911exc_reset(struct lt7911exc *lt7911exc)
+{
+	gpiod_set_value_cansleep(lt7911exc->reset_gpio, 0);
+	msleep(20);
+
+	gpiod_set_value_cansleep(lt7911exc->reset_gpio, 1);
+	msleep(20);
+
+	gpiod_set_value_cansleep(lt7911exc->reset_gpio, 0);
+	msleep(400);
+
+	dev_dbg(lt7911exc->dev, "lt7911exc reset.\n");
+}
+
+static int lt7911exc_parse_dt(struct lt7911exc *lt7911exc)
+{
+	struct device *dev = lt7911exc->dev;
+	int ret;
+
+	lt7911exc->supplies[0].supply = "vcc";
+	lt7911exc->supplies[1].supply = "vdd";
+
+	ret = devm_regulator_bulk_get(dev, 2, lt7911exc->supplies);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed get regulator\n");
+
+	lt7911exc->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(lt7911exc->reset_gpio))
+		return dev_err_probe(dev, PTR_ERR(lt7911exc->reset_gpio),
+				     "failed to acquire reset gpio\n");
+
+	return 0;
+}
+
+static int lt7911exc_read_version(struct lt7911exc *lt7911exc)
+{
+	u8 buf[3];
+	int ret;
+
+	ret = regmap_write(lt7911exc->regmap, 0xe0ee, 0x01);
+	if (ret)
+		return ret;
+	ret = regmap_bulk_read(lt7911exc->regmap, 0xe081, buf, sizeof(buf));
+	if (ret)
+		return ret;
+
+	return (buf[0] << 16) | (buf[1] << 8) | buf[2];
+}
+
+static void lt7911exc_lock(struct lt7911exc *lt7911exc)
+{
+	mutex_lock(&lt7911exc->ocm_lock);
+	regmap_write(lt7911exc->regmap, 0xe0ee, 0x01);
+}
+
+static void lt7911exc_unlock(struct lt7911exc *lt7911exc)
+{
+	regmap_write(lt7911exc->regmap, 0xe0ee, 0x00);
+	mutex_unlock(&lt7911exc->ocm_lock);
+}
+
+static void lt7911exc_block_erase(struct lt7911exc *lt7911exc)
+{
+	struct device *dev = lt7911exc->dev;
+	const u32 addr = 0x00;
+
+	const struct reg_sequence seq_write[] = {
+		REG_SEQ0(0xe0ee, 0x01),
+		REG_SEQ0(0xe054, 0x01),
+		REG_SEQ0(0xe055, 0x06),
+		REG_SEQ0(0xe051, 0x01),
+		REG_SEQ0(0xe051, 0x00),
+		REG_SEQ0(0xe054, 0x05),
+		REG_SEQ0(0xe055, 0xd8),
+		REG_SEQ0(0xe05a, (addr >> 16) & 0xff),
+		REG_SEQ0(0xe05b, (addr >> 8) & 0xff),
+		REG_SEQ0(0xe05c, addr & 0xff),
+		REG_SEQ0(0xe051, 0x01),
+		REG_SEQ0(0xe050, 0x00),
+	};
+
+	regmap_multi_reg_write(lt7911exc->regmap, seq_write, ARRAY_SIZE(seq_write));
+
+	msleep(200);
+	dev_dbg(dev, "erase flash done.\n");
+}
+
+static void lt7911exc_prog_init(struct lt7911exc *lt7911exc, u64 addr)
+{
+	const struct reg_sequence seq_write[] = {
+		REG_SEQ0(0xe0ee, 0x01),
+		REG_SEQ0(0xe05f, 0x01),
+		REG_SEQ0(0xe05a, (addr >> 16) & 0xff),
+		REG_SEQ0(0xe05b, (addr >> 8) & 0xff),
+		REG_SEQ0(0xe05c, addr & 0xff),
+	};
+
+	regmap_multi_reg_write(lt7911exc->regmap, seq_write, ARRAY_SIZE(seq_write));
+}
+
+static int lt7911exc_write_data(struct lt7911exc *lt7911exc, const struct firmware *fw, u64 addr)
+{
+	struct device *dev = lt7911exc->dev;
+	int ret;
+	int page = 0, num = 0, page_len = 0;
+	u64 size, offset;
+	const u8 *data;
+
+	data = fw->data;
+	size = fw->size;
+	page = (size + LT_PAGE_SIZE - 1) / LT_PAGE_SIZE;
+	if (page * LT_PAGE_SIZE > FW_SIZE) {
+		dev_err(dev, "firmware size out of range\n");
+		return -EINVAL;
+	}
+
+	dev_dbg(dev, "%u pages, total size %llu byte\n", page, size);
+
+	for (num = 0; num < page; num++) {
+		offset = num * LT_PAGE_SIZE;
+		page_len = (offset + LT_PAGE_SIZE <= size) ? LT_PAGE_SIZE : (size - offset);
+		lt7911exc_prog_init(lt7911exc, addr);
+
+		ret = regmap_raw_write(lt7911exc->regmap, 0xe05d, &data[offset], page_len);
+		if (ret) {
+			dev_err(dev, "write error at page %d\n", num);
+			return ret;
+		}
+
+		if (page_len < LT_PAGE_SIZE) {
+			regmap_write(lt7911exc->regmap, 0xe05f, 0x05);
+			regmap_write(lt7911exc->regmap, 0xe05f, 0x01);
+			//hardware requires delay
+			usleep_range(1000, 2000);
+		}
+
+		regmap_write(lt7911exc->regmap, 0xe05f, 0x00);
+		addr += LT_PAGE_SIZE;
+	}
+
+	return 0;
+}
+
+static int lt7911exc_write_crc(struct lt7911exc *lt7911exc, u32 crc32, u64 addr)
+{
+	u8 crc[4];
+	int ret;
+
+	crc[0] = crc32 & 0xff;
+	crc[1] = (crc32 >> 8) & 0xff;
+	crc[2] = (crc32 >> 16) & 0xff;
+	crc[3] = (crc32 >> 24) & 0xff;
+
+	regmap_write(lt7911exc->regmap, 0xe05f, 0x01);
+	regmap_write(lt7911exc->regmap, 0xe05a, (addr >> 16) & 0xff);
+	regmap_write(lt7911exc->regmap, 0xe05b, (addr >> 8) & 0xff);
+	regmap_write(lt7911exc->regmap, 0xe05c, addr & 0xff);
+
+	ret = regmap_raw_write(lt7911exc->regmap, 0xe05d, crc, 4);
+	if (ret)
+		return ret;
+
+	regmap_write(lt7911exc->regmap, 0xe05f, 0x05);
+	regmap_write(lt7911exc->regmap, 0xe05f, 0x01);
+	usleep_range(1000, 2000);
+	regmap_write(lt7911exc->regmap, 0xe05f, 0x00);
+
+	return 0;
+}
+
+static int lt7911exc_upgrade_result(struct lt7911exc *lt7911exc, u32 crc32)
+{
+	struct device *dev = lt7911exc->dev;
+	u32 read_hw_crc = 0;
+	u8 crc_tmp[4];
+	int ret;
+
+	regmap_write(lt7911exc->regmap, 0xe0ee, 0x01);
+	regmap_write(lt7911exc->regmap, 0xe07b, 0x60);
+	regmap_write(lt7911exc->regmap, 0xe07b, 0x40);
+	msleep(150);
+	ret = regmap_bulk_read(lt7911exc->regmap, 0x22, crc_tmp, 4);
+	if (ret) {
+		dev_err(lt7911exc->dev, "Failed to read CRC: %d\n", ret);
+		return ret;
+	}
+
+	read_hw_crc = crc_tmp[0] << 24 | crc_tmp[1] << 16 |
+				crc_tmp[2] << 8 | crc_tmp[3];
+
+	if (read_hw_crc != crc32) {
+		dev_err(dev, "lt7911exc firmware upgrade failed, expected CRC=0x%08x, read CRC=0x%08x\n",
+			crc32, read_hw_crc);
+		return -EIO;
+	}
+
+	dev_dbg(dev, "lt7911exc firmware upgrade success, CRC=0x%08x\n", read_hw_crc);
+	return 0;
+}
+
+static int lt7911exc_firmware_upgrade(struct lt7911exc *lt7911exc)
+{
+	struct device *dev = lt7911exc->dev;
+	const struct firmware *fw;
+	u8 *buffer;
+	size_t total_size = FW_SIZE - 4;
+	u32 crc32;
+	int ret;
+
+	/*1. load firmware*/
+	ret = request_firmware(&fw, FW_FILE, dev);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to load '%s'\n", FW_FILE);
+
+	/*2. check size*/
+	if (fw->size > total_size) {
+		dev_err(dev, "firmware too large (%zu > %zu)\n", fw->size, total_size);
+		ret = -EINVAL;
+		goto out_release_fw;
+	}
+
+	/*3. calculate crc32 */
+	buffer = kzalloc(total_size, GFP_KERNEL);
+	if (!buffer) {
+		ret = -ENOMEM;
+		goto out_release_fw;
+	}
+	memset(buffer, 0xff, total_size);
+	memcpy(buffer, fw->data, fw->size);
+
+	crc32 = cal_crc32_custom(buffer, total_size);
+	kfree(buffer);
+
+	/*4. firmware upgrade */
+	dev_dbg(dev, "starting firmware upgrade, size: %zu bytes\n", fw->size);
+
+	lt7911exc_block_erase(lt7911exc);
+
+	ret = lt7911exc_write_data(lt7911exc, fw, 0);
+	if (ret < 0) {
+		dev_err(dev, "failed to write firmware data\n");
+		goto out_release_fw;
+	}
+
+	ret = lt7911exc_write_crc(lt7911exc, crc32, FW_SIZE - 4);
+	if (ret < 0) {
+		dev_err(dev, "failed to write firmware crc\n");
+		goto out_release_fw;
+	}
+
+	/*5. check upgrade of result*/
+	lt7911exc_reset(lt7911exc);
+
+	ret = lt7911exc_upgrade_result(lt7911exc, crc32);
+
+out_release_fw:
+	release_firmware(fw);
+	return ret;
+}
+
+static void lt7911exc_atomic_pre_enable(struct drm_bridge *bridge, struct drm_atomic_state *state)
+{
+	struct lt7911exc *lt7911exc = bridge_to_lt7911exc(bridge);
+	int ret;
+
+	ret = regulator_bulk_enable(ARRAY_SIZE(lt7911exc->supplies), lt7911exc->supplies);
+	if (ret)
+		return;
+
+	lt7911exc_reset(lt7911exc);
+}
+
+static void lt7911exc_atomic_disable(struct drm_bridge *bridge, struct drm_atomic_state *state)
+{
+	/* Delay after panel is disabled */
+	msleep(20);
+}
+
+static void lt7911exc_atomic_post_disable(struct drm_bridge *bridge, struct drm_atomic_state *state)
+{
+	struct lt7911exc *lt7911exc = bridge_to_lt7911exc(bridge);
+	int ret;
+
+	ret = regulator_bulk_disable(ARRAY_SIZE(lt7911exc->supplies), lt7911exc->supplies);
+	if (ret)
+		return;
+
+	gpiod_set_value_cansleep(lt7911exc->reset_gpio, 1);
+}
+
+static int lt7911exc_attach(struct drm_bridge *bridge,
+			    struct drm_encoder *encoder,
+			    enum drm_bridge_attach_flags flags)
+{
+	struct lt7911exc *lt7911exc = bridge_to_lt7911exc(bridge);
+
+	return drm_bridge_attach(lt7911exc->bridge.encoder, lt7911exc->bridge.next_bridge,
+				 &lt7911exc->bridge, flags);
+}
+
+static const struct drm_bridge_funcs lt7911exc_bridge_funcs = {
+	.attach = lt7911exc_attach,
+	.atomic_pre_enable = lt7911exc_atomic_pre_enable,
+	.atomic_disable = lt7911exc_atomic_disable,
+	.atomic_post_disable = lt7911exc_atomic_post_disable,
+};
+
+static int lt7911exc_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct lt7911exc *lt7911exc;
+	bool fw_updated = false;
+	int ret;
+
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
+		dev_err(dev, "device doesn't support I2C\n");
+		return -ENODEV;
+	}
+
+	lt7911exc = devm_drm_bridge_alloc(dev, struct lt7911exc, bridge,
+					  &lt7911exc_bridge_funcs);
+	if (IS_ERR(lt7911exc))
+		return dev_err_probe(dev, PTR_ERR(lt7911exc), "drm bridge alloc failed.\n");
+
+	lt7911exc->bridge.next_bridge = devm_drm_of_get_bridge(dev, dev->of_node, 1, 0);
+	if (IS_ERR(lt7911exc->bridge.next_bridge))
+		return PTR_ERR(lt7911exc->bridge.next_bridge);
+
+	lt7911exc->client = client;
+	lt7911exc->dev = dev;
+	i2c_set_clientdata(client, lt7911exc);
+
+	ret = devm_mutex_init(dev, &lt7911exc->ocm_lock);
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to init mutex\n");
+
+	lt7911exc->regmap = devm_regmap_init_i2c(client, &lt7911exc_regmap_config);
+	if (IS_ERR(lt7911exc->regmap))
+		return dev_err_probe(dev, PTR_ERR(lt7911exc->regmap), "regmap i2c init failed\n");
+
+	ret = lt7911exc_parse_dt(lt7911exc);
+	if (ret)
+		return ret;
+
+	ret = regulator_bulk_enable(ARRAY_SIZE(lt7911exc->supplies), lt7911exc->supplies);
+	if (ret)
+		return ret;
+
+	lt7911exc_reset(lt7911exc);
+	lt7911exc_lock(lt7911exc);
+
+retry:
+	lt7911exc->fw_version = lt7911exc_read_version(lt7911exc);
+	if (lt7911exc->fw_version < 0) {
+		dev_err(dev, "failed to read chip fw version\n");
+		ret = -EOPNOTSUPP;
+		goto err_disable_regulators;
+
+	} else if (lt7911exc->fw_version == 0) {
+		if (!fw_updated) {
+			fw_updated = true;
+			ret = lt7911exc_firmware_upgrade(lt7911exc);
+			if (ret < 0)
+				goto err_disable_regulators;
+
+			goto retry;
+
+		} else {
+			dev_err(dev, "fw version 0x%04x, update failed\n", lt7911exc->fw_version);
+			ret = -EOPNOTSUPP;
+			goto err_disable_regulators;
+		}
+	}
+
+	lt7911exc_unlock(lt7911exc);
+
+	lt7911exc->bridge.of_node = dev->of_node;
+	devm_drm_bridge_add(dev, &lt7911exc->bridge);
+
+	return 0;
+
+err_disable_regulators:
+	lt7911exc_unlock(lt7911exc);
+	regulator_bulk_disable(ARRAY_SIZE(lt7911exc->supplies), lt7911exc->supplies);
+	return ret;
+}
+
+static const struct i2c_device_id lt7911exc_i2c_table[] = {
+	{"lt7911exc"},
+	{/* sentinel */}
+};
+
+MODULE_DEVICE_TABLE(i2c, lt7911exc_i2c_table);
+
+static const struct of_device_id lt7911exc_devices[] = {
+	{.compatible = "lontium,lt7911exc"},
+	{/* sentinel */}
+};
+MODULE_DEVICE_TABLE(of, lt7911exc_devices);
+
+static struct i2c_driver lt7911exc_driver = {
+	.id_table	= lt7911exc_i2c_table,
+	.probe		= lt7911exc_probe,
+	.driver		= {
+		.name	= "lt7911exc",
+		.of_match_table = lt7911exc_devices,
+	},
+};
+module_i2c_driver(lt7911exc_driver);
+
+MODULE_AUTHOR("SunYun Yang <syyang@lontium.com>");
+MODULE_DESCRIPTION("Lontium LT7911EXC EDP to MIPI DSI bridge driver");
+MODULE_LICENSE("GPL");
+MODULE_FIRMWARE(FW_FILE);
-- 
2.34.1

Re: [PATCH v6 1/2] dt-bindings: bridge: Add Lontium LT7911EXC eDP to MIPI DSI bridge

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Medium] The binding lacks support for the dual-port MIPI DSI output claimed in the commit message.
- [Low] Typographical errors in the commit message alter the meaning and reduce clarity.
--

commit d7e3500f4741bb0ae26a44a80c52b86455bf1c05
Author: Sunyun Yang <syyang@lontium.com>

dt-bindings: bridge: Add Lontium LT7911EXC eDP to MIPI DSI bridge

This commit adds the device tree binding schema for the Lontium LT7911EXC.
This device is an I2C-controlled bridge that converts eDP 1.4 input to MIPI
DSI output.

> The LT7911EXC is an I2C-controlled bridge that Receiver eDP1.4
> and output signal/dual port mipi dsi.

This isn't a bug, but there appear to be a few typos in the commit message
description. The word Receiver reads like it should be receives, and the
word signal looks like a typo for single.

> diff --git a/Documentation/devicetree/bindings/display/bridge/lontium,lt7911exc.yaml b/Documentation/devicetree/bindings/display/bridge/lontium,lt7911exc.yaml
> new file mode 100644
> index 0000000000000..3290b10ce8835
> --- /dev/null
> +++ b/Documentation/devicetree/bindings/display/bridge/lontium,lt7911exc.yaml

[ ... ]

>   ports:
>     $ref: /schemas/graph.yaml#/properties/ports
> 
>     properties:
>       port@0:
>         $ref: /schemas/graph.yaml#/properties/port
>         description: Video port for eDP input.
> 
>       port@1:
>         $ref: /schemas/graph.yaml#/properties/port
>         description: Video port for MIPI DSI output.

Since the commit message indicates the hardware supports dual port MIPI DSI
output, should the schema define a secondary DSI interface here?

Without a second endpoint or an additional port defined, it seems device
tree authors would be unable to properly model a dual-port display panel
connection.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260508134702.4713-1-syyang@lontium.com?part=1

Re: [PATCH v6 2/2] drm/bridge: Add Lontium LT7911EXC eDP to MIPI DSI bridge

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 6 potential issue(s) to consider:
- [High] Regulators enabled in `probe()` are never disabled on the success path, causing a permanent power leak.
- [High] Reset GPIO is driven high after cutting off power, violating power sequencing and risking hardware backpowering.
- [High] Synchronous `request_firmware` in `probe` can cause permanent probe failure if the driver is built-in.
- [Medium] Missing `depends on I2C` and `select REGMAP_I2C` in Kconfig.
- [Medium] The return value of `devm_drm_bridge_add()` is ignored in `probe()`.
- [Low] Missing header includes for core kernel APIs.
--

commit d9cebea8e10096b0200ef8f220724550dd554963
Author: Sunyun Yang <syyang@lontium.com>
drm/bridge: Add Lontium LT7911EXC eDP to MIPI DSI bridge

This commit adds support for the Lontium LT7911EXC eDP to MIPI DSI
bridge. It implements I2C-based setup, display configuration, and
provides a firmware update mechanism.

> diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
> index c3209b0f46786..fe45a9052aa0d 100644
> --- a/drivers/gpu/drm/bridge/Kconfig
> +++ b/drivers/gpu/drm/bridge/Kconfig
> @@ -132,6 +132,19 @@ config DRM_ITE_IT6505
>  	help
>  	  ITE IT6505 DisplayPort bridge chip driver.
>  
> +config DRM_LONTIUM_LT7911EXC
> +	tristate "Lontium eDP/MIPI DSI bridge"
> +	depends on OF

Should this config also depend on I2C and select REGMAP_I2C?

The driver explicitly registers an I2C driver and utilizes
devm_regmap_init_i2c(). Building without I2C enabled might cause
compilation or linker errors.

[ ... ]
> diff --git a/drivers/gpu/drm/bridge/lontium-lt7911exc.c b/drivers/gpu/drm/bridge/lontium-lt7911exc.c
> new file mode 100644
> index 0000000000000..d50fc979ebd4b
> --- /dev/null
> +++ b/drivers/gpu/drm/bridge/lontium-lt7911exc.c
> @@ -0,0 +1,493 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * Copyright (C) 2026 Lontium Semiconductor, Inc.
> + */
> +
> +#include <linux/crc32.h>
> +#include <linux/firmware.h>
> +#include <linux/gpio/consumer.h>
> +#include <linux/i2c.h>
> +#include <linux/module.h>
> +#include <linux/mutex.h>
> +#include <linux/of_graph.h>
> +#include <linux/platform_device.h>
> +#include <linux/regmap.h>

This isn't a bug, but it looks like some core headers are missing.

The driver uses kzalloc() and kfree(), msleep() and usleep_range(), as well
as regulator_bulk_enable(). Could linux/slab.h, linux/delay.h, and
linux/regulator/consumer.h be included directly to avoid relying on
transitive includes?

[ ... ]
> +static int lt7911exc_firmware_upgrade(struct lt7911exc *lt7911exc)
> +{
> +	struct device *dev = lt7911exc->dev;
> +	const struct firmware *fw;
> +	u8 *buffer;
> +	size_t total_size = FW_SIZE - 4;
> +	u32 crc32;
> +	int ret;
> +
> +	/*1. load firmware*/
> +	ret = request_firmware(&fw, FW_FILE, dev);

Can this synchronous request_firmware() call cause a permanent probe failure
if the driver is built-in?

When built into the kernel, probe executes before the root filesystem is
mounted, which would cause this to fail with -ENOENT. Because the error
is propagated without returning -EPROBE_DEFER, the subsystem might not
retry the probe later.

[ ... ]
> +static void lt7911exc_atomic_post_disable(struct drm_bridge *bridge, struct drm_atomic_state *state)
> +{
> +	struct lt7911exc *lt7911exc = bridge_to_lt7911exc(bridge);
> +	int ret;
> +
> +	ret = regulator_bulk_disable(ARRAY_SIZE(lt7911exc->supplies), lt7911exc->supplies);
> +	if (ret)
> +		return;
> +
> +	gpiod_set_value_cansleep(lt7911exc->reset_gpio, 1);
> +}

Does driving the reset GPIO high after cutting off the regulator power
violate power sequencing?

Driving a logic high signal into an unpowered IC can sometimes backpower
the device through its internal ESD protection diodes.

[ ... ]
> +static int lt7911exc_probe(struct i2c_client *client)
> +{
> +	struct device *dev = &client->dev;
> +	struct lt7911exc *lt7911exc;
> +	bool fw_updated = false;
> +	int ret;
[ ... ]
> +	ret = regulator_bulk_enable(ARRAY_SIZE(lt7911exc->supplies), lt7911exc->supplies);
> +	if (ret)
> +		return ret;
> +
> +	lt7911exc_reset(lt7911exc);
> +	lt7911exc_lock(lt7911exc);
[ ... ]
> +	lt7911exc_unlock(lt7911exc);
> +
> +	lt7911exc->bridge.of_node = dev->of_node;
> +	devm_drm_bridge_add(dev, &lt7911exc->bridge);
> +
> +	return 0;

Is there a resource leak for the regulators here?

The regulator_bulk_enable() call at the beginning of probe increments the
use count to power the device, but it appears the success path returns 0
without calling regulator_bulk_disable().

If lt7911exc_atomic_post_disable() later decrements the count, it seems
the count might still remain elevated by 1, leaving the hardware permanently
powered on.

Additionally, should the return value of devm_drm_bridge_add() be checked?

If it fails, the bridge is internally removed, but returning 0 here would
lead the driver to successfully bind to the I2C device without exposing
a functional DRM bridge.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260508134702.4713-1-syyang@lontium.com?part=2

Re: [PATCH v6 1/2] dt-bindings: bridge: Add Lontium LT7911EXC eDP to MIPI DSI bridge

[Sunyun Yang]

在 2026/5/9 4:50, sashiko-bot@kernel.org 写道:
> Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
> - [Medium] The binding lacks support for the dual-port MIPI DSI output claimed in the commit message.

1. When using single-port mode:
   (a). Only either Port A or Port B can be output at a time.
   (b). Port A and Port B are combined into a single port to output 
8-lane DSI.

2. When using dual-port mode:
Port A outputs the signal, and Port B copy the same signal from Port 
A.Both ports output the same image, and configuration for Port A alone 
is sufficient.

I need to look into how to modify it.

> - [Low] Typographical errors in the commit message alter the meaning and reduce clarity.
      it will be fixed.> --
> 
> commit d7e3500f4741bb0ae26a44a80c52b86455bf1c05
> Author: Sunyun Yang <syyang@lontium.com>
> 
> dt-bindings: bridge: Add Lontium LT7911EXC eDP to MIPI DSI bridge
> 
> This commit adds the device tree binding schema for the Lontium LT7911EXC.
> This device is an I2C-controlled bridge that converts eDP 1.4 input to MIPI
> DSI output.
> 
>> The LT7911EXC is an I2C-controlled bridge that Receiver eDP1.4
>> and output signal/dual port mipi dsi.
> 
> This isn't a bug, but there appear to be a few typos in the commit message
> description. The word Receiver reads like it should be receives, and the
> word signal looks like a typo for single.
> 
it will be fixed in next version.

>> diff --git a/Documentation/devicetree/bindings/display/bridge/lontium,lt7911exc.yaml b/Documentation/devicetree/bindings/display/bridge/lontium,lt7911exc.yaml
>> new file mode 100644
>> index 0000000000000..3290b10ce8835
>> --- /dev/null
>> +++ b/Documentation/devicetree/bindings/display/bridge/lontium,lt7911exc.yaml
> 
> [ ... ]
> 
>>    ports:
>>      $ref: /schemas/graph.yaml#/properties/ports
>>
>>      properties:
>>        port@0:
>>          $ref: /schemas/graph.yaml#/properties/port
>>          description: Video port for eDP input.
>>
>>        port@1:
>>          $ref: /schemas/graph.yaml#/properties/port
>>          description: Video port for MIPI DSI output.
> 
> Since the commit message indicates the hardware supports dual port MIPI DSI
> output, should the schema define a secondary DSI interface here?
> 
> Without a second endpoint or an additional port defined, it seems device
> tree authors would be unable to properly model a dual-port display panel
> connection.
> 

Re: [PATCH v6 2/2] drm/bridge: Add Lontium LT7911EXC eDP to MIPI DSI bridge

[Sunyun Yang]

在 2026/5/9 5:13, sashiko-bot@kernel.org 写道:
> Thank you for your contribution! Sashiko AI review found 6 potential issue(s) to consider:
> - [High] Regulators enabled in `probe()` are never disabled on the success path, causing a permanent power leak.
    it will be fixed in next version.> - [High] Reset GPIO is driven 
high after cutting off power, violating power sequencing and risking 
hardware backpowering.
> - [High] Synchronous `request_firmware` in `probe` can cause permanent probe failure if the driver is built-in.
> - [Medium] Missing `depends on I2C` and `select REGMAP_I2C` in Kconfig.
> - [Medium] The return value of `devm_drm_bridge_add()` is ignored in `probe()`.
> - [Low] Missing header includes for core kernel APIs.
> --
> 
> commit d9cebea8e10096b0200ef8f220724550dd554963
> Author: Sunyun Yang <syyang@lontium.com>
> drm/bridge: Add Lontium LT7911EXC eDP to MIPI DSI bridge
> 
> This commit adds support for the Lontium LT7911EXC eDP to MIPI DSI
> bridge. It implements I2C-based setup, display configuration, and
> provides a firmware update mechanism.
> 
>> diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
>> index c3209b0f46786..fe45a9052aa0d 100644
>> --- a/drivers/gpu/drm/bridge/Kconfig
>> +++ b/drivers/gpu/drm/bridge/Kconfig
>> @@ -132,6 +132,19 @@ config DRM_ITE_IT6505
>>   	help
>>   	  ITE IT6505 DisplayPort bridge chip driver.
>>   
>> +config DRM_LONTIUM_LT7911EXC
>> +	tristate "Lontium eDP/MIPI DSI bridge"
>> +	depends on OF
> 
> Should this config also depend on I2C and select REGMAP_I2C?
> 
> The driver explicitly registers an I2C driver and utilizes
> devm_regmap_init_i2c(). Building without I2C enabled might cause
> compilation or linker errors.
> 
> [ ... ]
>> diff --git a/drivers/gpu/drm/bridge/lontium-lt7911exc.c b/drivers/gpu/drm/bridge/lontium-lt7911exc.c
>> new file mode 100644
>> index 0000000000000..d50fc979ebd4b
>> --- /dev/null
>> +++ b/drivers/gpu/drm/bridge/lontium-lt7911exc.c
>> @@ -0,0 +1,493 @@
>> +// SPDX-License-Identifier: GPL-2.0
>> +/*
>> + * Copyright (C) 2026 Lontium Semiconductor, Inc.
>> + */
>> +
>> +#include <linux/crc32.h>
>> +#include <linux/firmware.h>
>> +#include <linux/gpio/consumer.h>
>> +#include <linux/i2c.h>
>> +#include <linux/module.h>
>> +#include <linux/mutex.h>
>> +#include <linux/of_graph.h>
>> +#include <linux/platform_device.h>
>> +#include <linux/regmap.h>
> 
> This isn't a bug, but it looks like some core headers are missing.
> 
> The driver uses kzalloc() and kfree(), msleep() and usleep_range(), as well
> as regulator_bulk_enable(). Could linux/slab.h, linux/delay.h, and
> linux/regulator/consumer.h be included directly to avoid relying on
> transitive includes?
> 
it will be fixed in next version.

> [ ... ]
>> +static int lt7911exc_firmware_upgrade(struct lt7911exc *lt7911exc)
>> +{
>> +	struct device *dev = lt7911exc->dev;
>> +	const struct firmware *fw;
>> +	u8 *buffer;
>> +	size_t total_size = FW_SIZE - 4;
>> +	u32 crc32;
>> +	int ret;
>> +
>> +	/*1. load firmware*/
>> +	ret = request_firmware(&fw, FW_FILE, dev);
> 
> Can this synchronous request_firmware() call cause a permanent probe failure
> if the driver is built-in?
> 
> When built into the kernel, probe executes before the root filesystem is
> mounted, which would cause this to fail with -ENOENT. Because the error
> is propagated without returning -EPROBE_DEFER, the subsystem might not
> retry the probe later.
> 
it will be fixed in next version.> [ ... ]
>> +static void lt7911exc_atomic_post_disable(struct drm_bridge *bridge, struct drm_atomic_state *state)
>> +{
>> +	struct lt7911exc *lt7911exc = bridge_to_lt7911exc(bridge);
>> +	int ret;
>> +
>> +	ret = regulator_bulk_disable(ARRAY_SIZE(lt7911exc->supplies), lt7911exc->supplies);
>> +	if (ret)
>> +		return;
>> +
>> +	gpiod_set_value_cansleep(lt7911exc->reset_gpio, 1);
>> +}
> 
> Does driving the reset GPIO high after cutting off the regulator power
> violate power sequencing?
> 
> Driving a logic high signal into an unpowered IC can sometimes backpower
> the device through its internal ESD protection diodes.
> 
it will be fixed in next version.

> [ ... ]
>> +static int lt7911exc_probe(struct i2c_client *client)
>> +{
>> +	struct device *dev = &client->dev;
>> +	struct lt7911exc *lt7911exc;
>> +	bool fw_updated = false;
>> +	int ret;
> [ ... ]
>> +	ret = regulator_bulk_enable(ARRAY_SIZE(lt7911exc->supplies), lt7911exc->supplies);
>> +	if (ret)
>> +		return ret;
>> +
>> +	lt7911exc_reset(lt7911exc);
>> +	lt7911exc_lock(lt7911exc);
> [ ... ]
>> +	lt7911exc_unlock(lt7911exc);
>> +
>> +	lt7911exc->bridge.of_node = dev->of_node;
>> +	devm_drm_bridge_add(dev, &lt7911exc->bridge);
>> +
>> +	return 0;
> 
> Is there a resource leak for the regulators here?
> 
> The regulator_bulk_enable() call at the beginning of probe increments the
> use count to power the device, but it appears the success path returns 0
> without calling regulator_bulk_disable().
> 
> If lt7911exc_atomic_post_disable() later decrements the count, it seems
> the count might still remain elevated by 1, leaving the hardware permanently
> powered on.
> 
> Additionally, should the return value of devm_drm_bridge_add() be checked?
> 
> If it fails, the bridge is internally removed, but returning 0 here would
> lead the driver to successfully bind to the I2C device without exposing
> a functional DRM bridge.
it will be fixed in next version.
>