[PATCH v5 1/2] dt-bindings: display: bridge: cdns,mhdp8546: Add no-hpd property to the cadence bridge

[PATCH v5 1/2] dt-bindings: display: bridge: cdns,mhdp8546: Add no-hpd property to the cadence bridge

[Yashas D]

From: Rahul T R <r-ravikumar@ti.com>

The mhdp bridge can work without its HPD pin hooked up to the connector,
but the current bridge driver throws an error when hpd line is not
connected to the connector. For such cases, we need an indication for
no-hpd, using which we can bypass the hpd detection and instead use the
auxiliary channels connected to the DP connector to confirm the
connection.
So add no-hpd property to the bindings, to disable hpd when not
connected or cannot be used for hotplug detection.

Signed-off-by: Rahul T R <r-ravikumar@ti.com>
Signed-off-by: Jayesh Choudhary <j-choudhary@ti.com>
Signed-off-by: Yashas D <y-d@ti.com>
---
 .../bindings/display/bridge/cdns,mhdp8546.yaml  | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml b/Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml
index c2b369456e4e..f19a4900ecd8 100644
--- a/Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml
@@ -57,6 +57,23 @@ properties:
   interrupts:
     maxItems: 1
 
+  no-hpd:
+    type: boolean
+    description:
+      Set if the HPD line on the bridge isn't physically connected to the
+      DisplayPort connector or cannot be used for hotplug detection.
+
+      Valid use cases include:
+      - HPD pin not routed to the connector on the PCB
+      - HPD signal muxed with another function (e.g., audio) on the SoC,
+        making it unavailable for hotplug detection
+      - Hardware design where HPD cannot reliably detect monitor presence
+
+      When this property is set, the driver will use auxiliary channel (AUX)
+      DPCD reads to detect monitor connection instead of relying on the
+      hardware HPD signal. Monitor detection will use polling rather than
+      interrupt-driven detection.
+
   ports:
     $ref: /schemas/graph.yaml#/properties/ports
 
-- 
2.34.1

[PATCH v5 0/2] Add no-hpd property to the cadence bridge

[Yashas D]

This series adds 'no-hpd' device tree property support to the Cadence
MHDP8546 bridge driver for boards where the HPD line cannot be used for
hotplug detection.

On TI J721S2 EVMs, the HPD signal is routed to SoC pin AA24
(MCASP1_ACLKX/DP0_HPD). This pin is muxed with the McASP1 audio bit
clock; selecting DP0_HPD breaks audio. There is no alternative pin
carrying the HPD signal which makes it impossible to use HPD
without loosing the audio capabilities.

When 'no-hpd' is set, DRM_BRIDGE_OP_HPD is omitted so the framework
falls back to polling .detect() every ~10 seconds. Monitor presence is
determined via AUX DPCD reads instead of firmware HPD status registers.
The .detect() callback drives cdns_mhdp_update_link_status() on each
poll to keep mhdp->plugged current. At attach time, the driver waits
for firmware to be ready before performing the initial AUX poll since
no interrupt will trigger it.

Changes since v4:
- Corrected the dt-binding Subject

Link to v4: https://lore.kernel.org/all/20260630102610.1849902-1-y-d@ti.com/

Rahul T R (2):
  dt-bindings: display: bridge: cdns,mhdp8546: Add no-hpd property to
    the cadence bridge
  drm: bridge: cdns-mhdp8546: Add no-hpd property

 .../display/bridge/cdns,mhdp8546.yaml         | 17 ++++++
 .../drm/bridge/cadence/cdns-mhdp8546-core.c   | 58 ++++++++++++++++---
 .../drm/bridge/cadence/cdns-mhdp8546-core.h   |  1 +
 3 files changed, 69 insertions(+), 7 deletions(-)

-- 
2.34.1

[PATCH v5 1/2] dt-bindings: display: bridge: cdns, mhdp8546: Add no-hpd property to the cadence bridge

[Yashas D]

From: Rahul T R <r-ravikumar@ti.com>

The mhdp bridge can work without its HPD pin hooked up to the connector,
but the current bridge driver throws an error when hpd line is not
connected to the connector. For such cases, we need an indication for
no-hpd, using which we can bypass the hpd detection and instead use the
auxiliary channels connected to the DP connector to confirm the
connection.
So add no-hpd property to the bindings, to disable hpd when not
connected or cannot be used for hotplug detection.

Signed-off-by: Rahul T R <r-ravikumar@ti.com>
Signed-off-by: Jayesh Choudhary <j-choudhary@ti.com>
Signed-off-by: Yashas D <y-d@ti.com>
---
 .../bindings/display/bridge/cdns,mhdp8546.yaml  | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml b/Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml
index c2b369456e4e..f19a4900ecd8 100644
--- a/Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml
@@ -57,6 +57,23 @@ properties:
   interrupts:
     maxItems: 1
 
+  no-hpd:
+    type: boolean
+    description:
+      Set if the HPD line on the bridge isn't physically connected to the
+      DisplayPort connector or cannot be used for hotplug detection.
+
+      Valid use cases include:
+      - HPD pin not routed to the connector on the PCB
+      - HPD signal muxed with another function (e.g., audio) on the SoC,
+        making it unavailable for hotplug detection
+      - Hardware design where HPD cannot reliably detect monitor presence
+
+      When this property is set, the driver will use auxiliary channel (AUX)
+      DPCD reads to detect monitor connection instead of relying on the
+      hardware HPD signal. Monitor detection will use polling rather than
+      interrupt-driven detection.
+
   ports:
     $ref: /schemas/graph.yaml#/properties/ports
 
-- 
2.34.1

[PATCH v5 2/2] drm: bridge: cdns-mhdp8546: Add no-hpd property

[Yashas D]

From: Rahul T R <r-ravikumar@ti.com>

Add a 'no-hpd' boolean property to support boards where the HPD line
cannot be used for hotplug detection due to hardware limitations.

On TI J721S2 EVMs, the DP0 HPD signal has a MUX conflict with audio
functionality. While the HPD pin is physically connected to GPIO0_18,
routing it to the SoC requires sacrificing audio capability due to pin
muxing constraints. This board-level hardware limitation necessitates
an alternative detection mechanism.

When this property is set, the driver uses auxiliary channel (AUX) DPCD
reads to detect monitor presence instead of hardware HPD signals. The
DRM framework polls the connection status via the .detect() callback,
providing hotplug detection without requiring the HPD pin.

Valid use cases:
- HPD pin not routed to connector on PCB
- HPD signal muxed with another function (e.g., audio) on SoC
- Hardware designs where HPD cannot reliably detect monitor presence

Limitations:
- DP "attention" IRQs from sink will not be received
- Hotplug detection latency increases to ~10 seconds (polling interval)

This follows the same pattern as 'no-hpd' in ti-sn65dsi86 and panel-edp
bindings, providing consistent semantics across the DRM subsystem.

Signed-off-by: Rahul T R <r-ravikumar@ti.com>
Signed-off-by: Jayesh Choudhary <j-choudhary@ti.com>
Signed-off-by: Harikrishna Shenoy <h-shenoy@ti.com>
Signed-off-by: Yashas D <y-d@ti.com>
---
 .../drm/bridge/cadence/cdns-mhdp8546-core.c   | 58 ++++++++++++++++---
 .../drm/bridge/cadence/cdns-mhdp8546-core.h   |  1 +
 2 files changed, 52 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c
index 504a3186ebb3..73d5c718c7db 100644
--- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c
+++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c
@@ -53,6 +53,8 @@
 #include "cdns-mhdp8546-hdcp.h"
 #include "cdns-mhdp8546-j721e.h"
 
+static int cdns_mhdp_update_link_status(struct cdns_mhdp_device *mhdp);
+
 static void cdns_mhdp_bridge_hpd_enable(struct drm_bridge *bridge)
 {
 	struct cdns_mhdp_device *mhdp = bridge_to_mhdp(bridge);
@@ -698,7 +700,9 @@ static int cdns_mhdp_fw_activate(const struct firmware *fw,
 	 * MHDP_HW_STOPPED happens only due to driver removal when
 	 * bridge should already be detached.
 	 */
-	cdns_mhdp_bridge_hpd_enable(&mhdp->bridge);
+
+	if (!mhdp->no_hpd)
+		cdns_mhdp_bridge_hpd_enable(&mhdp->bridge);
 
 	spin_unlock(&mhdp->start_lock);
 
@@ -788,9 +792,14 @@ static ssize_t cdns_mhdp_transfer(struct drm_dp_aux *aux,
 		ret = cdns_mhdp_dpcd_read(mhdp, msg->address,
 					  msg->buffer, msg->size);
 		if (ret) {
-			dev_dbg(mhdp->dev,
-				"Failed to read DPCD addr %u\n",
-				msg->address);
+			if (mhdp->no_hpd)
+				dev_dbg(mhdp->dev,
+					"Failed to read DPCD addr %u\n",
+					msg->address);
+			else
+				dev_err(mhdp->dev,
+					"Failed to read DPCD addr %u\n",
+					msg->address);
 
 			return ret;
 		}
@@ -1523,6 +1532,26 @@ static int cdns_mhdp_attach(struct drm_bridge *bridge,
 
 	spin_unlock(&mhdp->start_lock);
 
+	if (mhdp->no_hpd) {
+		/*
+		 * In no-hpd mode there is no interrupt to signal firmware
+		 * readiness. The firmware loads asynchronously after probe(),
+		 * so we must wait here until the uCPU is running before
+		 * attempting the first AUX channel poll for monitor presence.
+		 */
+		ret = wait_event_timeout(mhdp->fw_load_wq,
+					 mhdp->hw_state == MHDP_HW_READY,
+					 msecs_to_jiffies(100));
+		if (ret == 0) {
+			dev_err(mhdp->dev, "%s: Timeout waiting for fw loading\n",
+				__func__);
+			return -ETIMEDOUT;
+		}
+
+		cdns_mhdp_update_link_status(mhdp);
+		return 0;
+	}
+
 	/* Enable SW event interrupts */
 	if (hw_ready)
 		cdns_mhdp_bridge_hpd_enable(bridge);
@@ -2013,6 +2042,9 @@ cdns_mhdp_bridge_detect(struct drm_bridge *bridge, struct drm_connector *connect
 {
 	struct cdns_mhdp_device *mhdp = bridge_to_mhdp(bridge);
 
+	if (mhdp->no_hpd)
+		cdns_mhdp_update_link_status(mhdp);
+
 	return cdns_mhdp_detect(mhdp);
 }
 
@@ -2100,7 +2132,16 @@ static int cdns_mhdp_update_link_status(struct cdns_mhdp_device *mhdp)
 
 	mutex_lock(&mhdp->link_mutex);
 
-	mhdp->plugged = cdns_mhdp_detect_hpd(mhdp, &hpd_pulse);
+	if (mhdp->no_hpd) {
+		ret = drm_dp_dpcd_read_link_status(&mhdp->aux, status);
+		hpd_pulse = false;
+		if (ret < 0)
+			mhdp->plugged = false;
+		else
+			mhdp->plugged = true;
+	} else {
+		mhdp->plugged = cdns_mhdp_detect_hpd(mhdp, &hpd_pulse);
+	}
 
 	if (!mhdp->plugged) {
 		cdns_mhdp_link_down(mhdp);
@@ -2288,6 +2329,8 @@ static int cdns_mhdp_probe(struct platform_device *pdev)
 	mhdp->aux.dev = dev;
 	mhdp->aux.transfer = cdns_mhdp_transfer;
 
+	mhdp->no_hpd = of_property_read_bool(dev->of_node, "no-hpd");
+
 	mhdp->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(mhdp->regs)) {
 		dev_err(dev, "Failed to get memory resource\n");
@@ -2360,8 +2403,9 @@ static int cdns_mhdp_probe(struct platform_device *pdev)
 	mhdp->display_fmt.bpc = 8;
 
 	mhdp->bridge.of_node = pdev->dev.of_node;
-	mhdp->bridge.ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID |
-			   DRM_BRIDGE_OP_HPD;
+	mhdp->bridge.ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID;
+	if (!mhdp->no_hpd)
+		mhdp->bridge.ops |= DRM_BRIDGE_OP_HPD;
 	mhdp->bridge.type = DRM_MODE_CONNECTOR_DisplayPort;
 
 	ret = phy_init(mhdp->phy);
diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.h b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.h
index b53335b0d22c..24ffb732a207 100644
--- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.h
+++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.h
@@ -388,6 +388,7 @@ struct cdns_mhdp_device {
 
 	bool link_up;
 	bool plugged;
+	bool no_hpd;
 
 	/*
 	 * "start_lock" protects the access to bridge_attached and
-- 
2.34.1

Re: [PATCH v5 1/2] dt-bindings: display: bridge: cdns, mhdp8546: Add no-hpd property to the cadence bridge

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] The `no-hpd` property is documented in the device tree bindings but has no corresponding implementation in the driver.
--

--- Patch [1]: [PATCH v5 1/2] dt-bindings: display: bridge: cdns, mhdp8546: Add no-hpd property to the cadence bridge ---
commit 4ac60fbbcafba148711703269045306014cd935a
Author: Rahul T R <r-ravikumar@ti.com>

dt-bindings: display: bridge: cdns, mhdp8546: Add no-hpd property to the cadence bridge

This commit introduces the no-hpd property to the mhdp8546 device tree
bindings. It provides a way to indicate when the hardware HPD line is not
available, specifying that the driver should fall back to auxiliary channel
DPCD reads for hotplug detection.

> diff --git a/Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml b/Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml
> --- a/Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml
> +++ b/Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml

[ ... ]

> @@ -57,6 +57,23 @@ properties:
>    interrupts:
>      maxItems: 1
>  
> +  no-hpd:
> +    type: boolean
> +    description:
> +      Set if the HPD line on the bridge isn't physically connected to the
> +      DisplayPort connector or cannot be used for hotplug detection.
> +
> +      Valid use cases include:
> +      - HPD pin not routed to the connector on the PCB
> +      - HPD signal muxed with another function (e.g., audio) on the SoC,
> +        making it unavailable for hotplug detection
> +      - Hardware design where HPD cannot reliably detect monitor presence
> +
> +      When this property is set, the driver will use auxiliary channel (AUX)
> +      DPCD reads to detect monitor connection instead of relying on the
> +      hardware HPD signal. Monitor detection will use polling rather than
> +      interrupt-driven detection.
> +

[Severity: Medium]
Is the driver implementation missing for this new property?

The binding documentation states that the driver will use polling rather than
interrupt-driven detection when this property is set. However, looking at the
driver in cdns_mhdp_probe(), it unconditionally requires hardware HPD
operations:

drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c:cdns_mhdp_probe() {
	...
	mhdp->bridge.of_node = pdev->dev.of_node;
	mhdp->bridge.ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID |
			   DRM_BRIDGE_OP_HPD;
	mhdp->bridge.type = DRM_MODE_CONNECTOR_DisplayPort;
	...
}

Does the driver need logic to parse the no-hpd property and conditionally
adjust these operations to enable polling instead of enforcing hardware HPD?

>    ports:
>      $ref: /schemas/graph.yaml#/properties/ports
>

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260728125336.776116-1-y-d@ti.com?part=1

Re: [PATCH v5 2/2] drm: bridge: cdns-mhdp8546: Add no-hpd property

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 5 potential issue(s) to consider:
- [High] Reading `DP_LANE0_1_STATUS` (0x202) for connection polling violates DRM guidelines and disrupts link training state machines.
- [High] The `.detect()` callback unconditionally triggers hardware stream re-enablement during periodic polling in `no-hpd` mode.
- [High] Resource leak of `drm_dp_aux` if firmware loading times out during `cdns_mhdp_attach()`, leading to a Use-After-Free.
- [Medium] Hardcoded 100ms timeout for asynchronous firmware loading in `cdns_mhdp_attach()` can spuriously fail bridge attachment.
- [Medium] Changing DPCD read failures to `dev_err()` will flood the kernel log with false-positive errors during normal operations.
--

--- Patch [2]: [PATCH v5 2/2] drm: bridge: cdns-mhdp8546: Add no-hpd property ---
commit d6385d712222c0d749e282f8179c659c2e87c45d
Author: Rahul T R <r-ravikumar@ti.com>
Subject: drm: bridge: cdns-mhdp8546: Add no-hpd property

This commit adds a 'no-hpd' property to support boards where the HPD line
cannot be used for hotplug detection due to hardware limitations. When set,
the driver uses auxiliary channel (AUX) DPCD reads to detect monitor presence
by polling the connection status via the .detect() callback.

> diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c
> --- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c
> +++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c
[ ... ]
> @@ -788,9 +792,14 @@ static ssize_t cdns_mhdp_transfer(struct drm_dp_aux *aux,
>  		ret = cdns_mhdp_dpcd_read(mhdp, msg->address,
>  					  msg->buffer, msg->size);
>  		if (ret) {
> -			dev_dbg(mhdp->dev,
> -				"Failed to read DPCD addr %u\n",
> -				msg->address);
> +			if (mhdp->no_hpd)
> +				dev_dbg(mhdp->dev,
> +					"Failed to read DPCD addr %u\n",
> +					msg->address);
> +			else
> +				dev_err(mhdp->dev,
> +					"Failed to read DPCD addr %u\n",
> +					msg->address);

[Severity: Medium]
Will this change spam the kernel log with false-positive errors during normal
operations?

DP AUX channel transactions routinely fail during normal operations, such as
when a disconnected monitor is probed, during DP sleep states, or when the
DRM DP helper retries transient link training failures. Emitting a dev_err()
on every AUX read failure might flood the kernel log on standard hardware.

[ ... ]
> @@ -1523,6 +1532,26 @@ static int cdns_mhdp_attach(struct drm_bridge *bridge,
>  
>  	spin_unlock(&mhdp->start_lock);
>  
> +	if (mhdp->no_hpd) {
> +		/*
> +		 * In no-hpd mode there is no interrupt to signal firmware
> +		 * readiness. The firmware loads asynchronously after probe(),
> +		 * so we must wait here until the uCPU is running before
> +		 * attempting the first AUX channel poll for monitor presence.
> +		 */
> +		ret = wait_event_timeout(mhdp->fw_load_wq,
> +					 mhdp->hw_state == MHDP_HW_READY,
> +					 msecs_to_jiffies(100));

[Severity: Medium]
Could this hardcoded 100ms timeout spuriously fail bridge attachment?

Firmware loading from a filesystem (via request_firmware_nowait) can easily
take hundreds of milliseconds or longer depending on storage performance and
system load. If the timeout expires prematurely, the driver aborts with
-ETIMEDOUT, which could permanently break the display pipeline for that boot.

> +		if (ret == 0) {
> +			dev_err(mhdp->dev, "%s: Timeout waiting for fw loading\n",
> +				__func__);
> +			return -ETIMEDOUT;

[Severity: High]
Does this direct return leak the drm_dp_aux resource?

If the firmware loading timeout expires, this returns -ETIMEDOUT directly
instead of jumping to the aux_unregister error handling label.

Since drm_dp_aux_register() sets up an I2C adapter and the DRM core does not
call .detach() if attach fails, bypassing drm_dp_aux_unregister() leaks the
I2C adapter. Because the memory backing the drm_dp_aux structure is
devm-managed, unloading the module frees the memory while the adapter is still
registered, which can cause a use-after-free when the I2C subsystem accesses
it.

> +		}
> +
> +		cdns_mhdp_update_link_status(mhdp);
> +		return 0;
> +	}
[ ... ]
> @@ -2100,7 +2132,16 @@ static int cdns_mhdp_update_link_status(struct cdns_mhdp_device *mhdp)
>  
>  	mutex_lock(&mhdp->link_mutex);
>  
> -	mhdp->plugged = cdns_mhdp_detect_hpd(mhdp, &hpd_pulse);
> +	if (mhdp->no_hpd) {
> +		ret = drm_dp_dpcd_read_link_status(&mhdp->aux, status);

[Severity: High]
Does reading the link status here violate DRM subsystem guidelines and disrupt
link training state machines?

The DRM core polls .detect() every 10 seconds when no-hpd is set, which
calls cdns_mhdp_update_link_status(). This unconditionally calls
drm_dp_dpcd_read_link_status() which reads DP_LANE0_1_STATUS (0x202).

According to DRM guidelines, registers in the link training status range
(0x202-0x207) participate in the CR/EQ training state machine and are not
safe for arbitrary read access outside of a link training sequence. Reading
this register continuously for presence detection can induce hardware
instability, screen flickering, and link drops. Should a safe register like
DP_DPCD_REV (0x000) be used instead?

> +		hpd_pulse = false;

[Severity: High]
Does hardcoding hpd_pulse to false cause the active display stream to be
re-initialized on every 10-second poll?

In no-hpd mode, .detect() is polled every 10 seconds. Because hpd_pulse is
hardcoded to false here, the later logic bypasses the check that validates
link status without state mutation:

    if (hpd_pulse && old_plugged == mhdp->plugged) {
        ret = drm_dp_dpcd_read_link_status(&mhdp->aux, status);
        if (!ret && ...)
            goto out;
        ...
    }

Instead, execution falls through to the end of the function. If
mhdp->bridge_enabled is true, this causes cdns_mhdp_sst_enable() to be
called:

    if (mhdp->bridge_enabled) {
        ...
        cdns_mhdp_sst_enable(mhdp, current_mode);
    }

This repeatedly re-programs active stream and framer configuration registers
on every poll, which can cause the active video stream to reset and glitch
every 10 seconds.

> +		if (ret < 0)
> +			mhdp->plugged = false;
> +		else
> +			mhdp->plugged = true;
> +	} else {
> +		mhdp->plugged = cdns_mhdp_detect_hpd(mhdp, &hpd_pulse);
> +	}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260728125336.776116-1-y-d@ti.com?part=2

Re: [PATCH v5 1/2] dt-bindings: display: bridge: cdns,mhdp8546: Add no-hpd property to the cadence bridge

[Rob Herring (Arm)]

On Tue, 28 Jul 2026 18:12:23 +0530, Yashas D wrote:
> From: Rahul T R <r-ravikumar@ti.com>
> 
> The mhdp bridge can work without its HPD pin hooked up to the connector,
> but the current bridge driver throws an error when hpd line is not
> connected to the connector. For such cases, we need an indication for
> no-hpd, using which we can bypass the hpd detection and instead use the
> auxiliary channels connected to the DP connector to confirm the
> connection.
> So add no-hpd property to the bindings, to disable hpd when not
> connected or cannot be used for hotplug detection.
> 
> Signed-off-by: Rahul T R <r-ravikumar@ti.com>
> Signed-off-by: Jayesh Choudhary <j-choudhary@ti.com>
> Signed-off-by: Yashas D <y-d@ti.com>
> ---
>  .../bindings/display/bridge/cdns,mhdp8546.yaml  | 17 +++++++++++++++++
>  1 file changed, 17 insertions(+)
> 

My bot found errors running 'make dt_binding_check' on your patch:

yamllint warnings/errors:
./Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml:66:30: [error] syntax error: mapping values are not allowed here (syntax)

dtschema/dtc warnings/errors:
/builds/robherring/dt-review-ci/linux/Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml: ignoring, error parsing file
./Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml: error loading YAML: mapping values are not allowed here
  in "./Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml", line 66, column 30
./Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml:66:30: mapping values are not allowed here
make[2]: *** Deleting file 'Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.example.dts'
Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.yaml:66:30: mapping values are not allowed here
make[2]: *** [Documentation/devicetree/bindings/Makefile:26: Documentation/devicetree/bindings/display/bridge/cdns,mhdp8546.example.dts] Error 1
make[2]: *** Waiting for unfinished jobs....
make[1]: *** [/builds/robherring/dt-review-ci/linux/Makefile:1703: dt_binding_check] Error 2
make: *** [Makefile:248: __sub-make] Error 2

doc reference errors (make refcheckdocs):

See https://patchwork.kernel.org/project/devicetree/patch/20260728124224.774785-2-y-d@ti.com

The base for the series is generally the latest rc1. A different dependency
should be noted in *this* patch.

If you already ran 'make dt_binding_check' and didn't see the above
error(s), then make sure 'yamllint' is installed and dt-schema is up to
date:

pip3 install dtschema --upgrade

Please check and re-submit after running the above command yourself. Note
that DT_SCHEMA_FILES can be set to your schema file to speed up checking
your schema. However, it must be unset to test all examples with your schema.