[PATCH 0/5] drm/bridge: Implement generic USB Type-C DP HPD bridge

[PATCH 0/5] drm/bridge: Implement generic USB Type-C DP HPD bridge

[Chaoyi Chen]

From: Chaoyi Chen <chaoyi.chen@rock-chips.com>

This series is split from the v15 "Add Type-C DP support for RK3399 EVB
IND board" series [1]. It focuses on the DRM bridge and Rockchip
platform CDN-DP controller changes.

[1] https://lore.kernel.org/all/20260304094152.92-1-kernel@airkyi.com/

====
1. Generic Type-C DP HPD bridge

Currently, several USB-C controller drivers register their own DP HPD
bridge via aux-hpd-bridge.c, each duplicating the same logic. For
devicetree based platforms, the USB-C controller may vary across boards,
and not every USB-C controller driver implements this feature. Patch 1
implements a generic DP HPD bridge that monitors Type-C bus events and
automatically creates an HPD bridge when a Type-C port device with DP
SVID is registered.

2. Multiple bridge model for CDN-DP

The RK3399 has two USB/DP combo PHY and one CDN-DP controller. Patch 5
introduces a multi-bridge model where each PHY port gets a separate
encoder and bridge, allowing flexible selection of the output PHY port.
This is based on the DRM AUX HPD bridge rather than extcon.

====
Patch 1 adds generic USB Type-C DP HPD bridge (Dmitry, Heikki).
Patch 2 adds new API drm_aux_bridge_register_from_node() (Neil).
Patch 3 adds DRM AUX bridge support for RK3399 USBDP PHY (Neil).
Patch 4 drops CDN-DP's extcon dependency when Type-C is present (Dmitry).
Patch 5 adds multiple bridges to support PHY port selection (Dmitry, Luca).

Chaoyi Chen (5):
  drm/bridge: Implement generic USB Type-C DP HPD bridge
  drm/bridge: aux: Add drm_aux_bridge_register_from_node()
  phy: rockchip: phy-rockchip-typec: Add DRM AUX bridge
  drm/rockchip: cdn-dp: Support handle lane info without extcon
  drm/rockchip: cdn-dp: Add multiple bridges to support PHY port
    selection

 drivers/gpu/drm/bridge/Kconfig                |  10 +
 drivers/gpu/drm/bridge/Makefile               |   1 +
 drivers/gpu/drm/bridge/aux-bridge.c           |  24 +-
 .../gpu/drm/bridge/aux-hpd-typec-dp-bridge.c  |  49 +++
 drivers/gpu/drm/rockchip/Kconfig              |   1 +
 drivers/gpu/drm/rockchip/cdn-dp-core.c        | 349 ++++++++++++++----
 drivers/gpu/drm/rockchip/cdn-dp-core.h        |  18 +-
 drivers/phy/rockchip/Kconfig                  |   2 +
 drivers/phy/rockchip/phy-rockchip-typec.c     |  13 +-
 include/drm/bridge/aux-bridge.h               |   6 +
 10 files changed, 404 insertions(+), 69 deletions(-)
 create mode 100644 drivers/gpu/drm/bridge/aux-hpd-typec-dp-bridge.c

-- 
2.53.0


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

[PATCH 1/5] drm/bridge: Implement generic USB Type-C DP HPD bridge

[Chaoyi Chen]

From: Chaoyi Chen <chaoyi.chen@rock-chips.com>

The HPD function of Type-C DP is implemented through
drm_connector_oob_hotplug_event(). For embedded DP, it is required
that the DRM connector fwnode corresponds to the Type-C port fwnode.

To describe the relationship between the DP controller and the Type-C
port device, we usually using drm_bridge to build a bridge chain.

Now several USB-C controller drivers have already implemented the DP
HPD bridge function provided by aux-hpd-bridge.c, it will build a DP
HPD bridge on USB-C connector port device.

But this requires the USB-C controller driver to manually register the
HPD bridge. If the driver does not implement this feature, the bridge
will not be create.

So this patch implements a generic DP HPD bridge based on
aux-hpd-bridge.c. It will monitor Type-C bus events, and when a
Type-C port device containing the DP svid is registered, it will
create an HPD bridge for it without the need for the USB-C controller
driver to implement it.

Signed-off-by: Chaoyi Chen <chaoyi.chen@rock-chips.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
---
 drivers/gpu/drm/bridge/Kconfig                | 10 ++++
 drivers/gpu/drm/bridge/Makefile               |  1 +
 .../gpu/drm/bridge/aux-hpd-typec-dp-bridge.c  | 49 +++++++++++++++++++
 3 files changed, 60 insertions(+)
 create mode 100644 drivers/gpu/drm/bridge/aux-hpd-typec-dp-bridge.c

diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
index c3209b0f4678..d92e93875793 100644
--- a/drivers/gpu/drm/bridge/Kconfig
+++ b/drivers/gpu/drm/bridge/Kconfig
@@ -30,6 +30,16 @@ config DRM_AUX_HPD_BRIDGE
 	  Simple bridge that terminates the bridge chain and provides HPD
 	  support.
 
+if DRM_AUX_HPD_BRIDGE
+config DRM_AUX_HPD_TYPEC_BRIDGE
+	tristate
+	depends on TYPEC || !TYPEC
+	default TYPEC
+	help
+	  Simple bridge that terminates the bridge chain and provides HPD
+	  support. It build bridge on each USB-C connector device node.
+endif
+
 menu "Display Interface Bridges"
 	depends on DRM && DRM_BRIDGE
 
diff --git a/drivers/gpu/drm/bridge/Makefile b/drivers/gpu/drm/bridge/Makefile
index beab5b695a6e..c4761526ba0a 100644
--- a/drivers/gpu/drm/bridge/Makefile
+++ b/drivers/gpu/drm/bridge/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_DRM_AUX_BRIDGE) += aux-bridge.o
 obj-$(CONFIG_DRM_AUX_HPD_BRIDGE) += aux-hpd-bridge.o
+obj-$(CONFIG_DRM_AUX_HPD_TYPEC_BRIDGE) += aux-hpd-typec-dp-bridge.o
 obj-$(CONFIG_DRM_CHIPONE_ICN6211) += chipone-icn6211.o
 obj-$(CONFIG_DRM_CHRONTEL_CH7033) += chrontel-ch7033.o
 obj-$(CONFIG_DRM_CROS_EC_ANX7688) += cros-ec-anx7688.o
diff --git a/drivers/gpu/drm/bridge/aux-hpd-typec-dp-bridge.c b/drivers/gpu/drm/bridge/aux-hpd-typec-dp-bridge.c
new file mode 100644
index 000000000000..d915e0fb0668
--- /dev/null
+++ b/drivers/gpu/drm/bridge/aux-hpd-typec-dp-bridge.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0+
+#include <linux/of.h>
+#include <linux/usb/typec_altmode.h>
+#include <linux/usb/typec_dp.h>
+
+#include <drm/bridge/aux-bridge.h>
+
+static int drm_typec_bus_event(struct notifier_block *nb,
+			       unsigned long action, void *data)
+{
+	struct device *dev = (struct device *)data;
+	struct typec_altmode *alt = to_typec_altmode(dev);
+
+	if (action != BUS_NOTIFY_ADD_DEVICE)
+		goto done;
+
+	/*
+	 * alt->dev.parent->parent : USB-C controller device
+	 * alt->dev.parent         : USB-C connector device
+	 */
+	if (is_typec_port_altmode(&alt->dev) && alt->svid == USB_TYPEC_DP_SID)
+		drm_dp_hpd_bridge_register(alt->dev.parent->parent,
+					   to_of_node(alt->dev.parent->fwnode));
+
+done:
+	return NOTIFY_OK;
+}
+
+static struct notifier_block drm_typec_event_nb = {
+	.notifier_call = drm_typec_bus_event,
+};
+
+static void drm_aux_hpd_typec_dp_bridge_module_exit(void)
+{
+	bus_unregister_notifier(&typec_bus, &drm_typec_event_nb);
+}
+
+static int __init drm_aux_hpd_typec_dp_bridge_module_init(void)
+{
+	bus_register_notifier(&typec_bus, &drm_typec_event_nb);
+
+	return 0;
+}
+
+module_init(drm_aux_hpd_typec_dp_bridge_module_init);
+module_exit(drm_aux_hpd_typec_dp_bridge_module_exit);
+
+MODULE_DESCRIPTION("DRM TYPEC DP HPD BRIDGE");
+MODULE_LICENSE("GPL");
-- 
2.53.0


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

[PATCH 2/5] drm/bridge: aux: Add drm_aux_bridge_register_from_node()

[Chaoyi Chen]

From: Chaoyi Chen <chaoyi.chen@rock-chips.com>

The drm_aux_bridge_register() uses the device->of_node as the
bridge->of_node.

This patch adds drm_aux_bridge_register_from_node() to allow
specifying the of_node corresponding to the bridge.

Signed-off-by: Chaoyi Chen <chaoyi.chen@rock-chips.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
---
 drivers/gpu/drm/bridge/aux-bridge.c | 24 ++++++++++++++++++++++--
 include/drm/bridge/aux-bridge.h     |  6 ++++++
 2 files changed, 28 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/bridge/aux-bridge.c b/drivers/gpu/drm/bridge/aux-bridge.c
index 1ed21a8713bf..f50283abed5f 100644
--- a/drivers/gpu/drm/bridge/aux-bridge.c
+++ b/drivers/gpu/drm/bridge/aux-bridge.c
@@ -35,6 +35,7 @@ static void drm_aux_bridge_unregister_adev(void *_adev)
 /**
  * drm_aux_bridge_register - Create a simple bridge device to link the chain
  * @parent: device instance providing this bridge
+ * @np: device node pointer corresponding to this bridge instance
  *
  * Creates a simple DRM bridge that doesn't implement any drm_bridge
  * operations. Such bridges merely fill a place in the bridge chain linking
@@ -42,7 +43,7 @@ static void drm_aux_bridge_unregister_adev(void *_adev)
  *
  * Return: zero on success, negative error code on failure
  */
-int drm_aux_bridge_register(struct device *parent)
+int drm_aux_bridge_register_from_node(struct device *parent, struct device_node *np)
 {
 	struct auxiliary_device *adev;
 	int ret;
@@ -62,7 +63,10 @@ int drm_aux_bridge_register(struct device *parent)
 	adev->dev.parent = parent;
 	adev->dev.release = drm_aux_bridge_release;
 
-	device_set_of_node_from_dev(&adev->dev, parent);
+	if (np)
+		device_set_node(&adev->dev, of_fwnode_handle(np));
+	else
+		device_set_of_node_from_dev(&adev->dev, parent);
 
 	ret = auxiliary_device_init(adev);
 	if (ret) {
@@ -80,6 +84,22 @@ int drm_aux_bridge_register(struct device *parent)
 
 	return devm_add_action_or_reset(parent, drm_aux_bridge_unregister_adev, adev);
 }
+EXPORT_SYMBOL_GPL(drm_aux_bridge_register_from_node);
+
+/**
+ * drm_aux_bridge_register - Create a simple bridge device to link the chain
+ * @parent: device instance providing this bridge
+ *
+ * Creates a simple DRM bridge that doesn't implement any drm_bridge
+ * operations. Such bridges merely fill a place in the bridge chain linking
+ * surrounding DRM bridges.
+ *
+ * Return: zero on success, negative error code on failure
+ */
+int drm_aux_bridge_register(struct device *parent)
+{
+	return drm_aux_bridge_register_from_node(parent, NULL);
+}
 EXPORT_SYMBOL_GPL(drm_aux_bridge_register);
 
 struct drm_aux_bridge_data {
diff --git a/include/drm/bridge/aux-bridge.h b/include/drm/bridge/aux-bridge.h
index c2f5a855512f..7dd1f17a1354 100644
--- a/include/drm/bridge/aux-bridge.h
+++ b/include/drm/bridge/aux-bridge.h
@@ -13,11 +13,17 @@ struct auxiliary_device;
 
 #if IS_ENABLED(CONFIG_DRM_AUX_BRIDGE)
 int drm_aux_bridge_register(struct device *parent);
+int drm_aux_bridge_register_from_node(struct device *parent, struct device_node *np);
 #else
 static inline int drm_aux_bridge_register(struct device *parent)
 {
 	return 0;
 }
+
+static inline int drm_aux_bridge_register_from_node(struct device *parent, struct device_node *np)
+{
+	return 0;
+}
 #endif
 
 #if IS_ENABLED(CONFIG_DRM_AUX_HPD_BRIDGE)
-- 
2.53.0


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

[PATCH 3/5] phy: rockchip: phy-rockchip-typec: Add DRM AUX bridge

[Chaoyi Chen]

From: Chaoyi Chen <chaoyi.chen@rock-chips.com>

Using the DRM_AUX_BRIDGE helper to create the transparent DRM bridge
device.

Signed-off-by: Chaoyi Chen <chaoyi.chen@rock-chips.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
---
 drivers/phy/rockchip/Kconfig              |  2 ++
 drivers/phy/rockchip/phy-rockchip-typec.c | 13 +++++++++++--
 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/phy/rockchip/Kconfig b/drivers/phy/rockchip/Kconfig
index 14698571b607..9173d3b4fef4 100644
--- a/drivers/phy/rockchip/Kconfig
+++ b/drivers/phy/rockchip/Kconfig
@@ -119,6 +119,8 @@ config PHY_ROCKCHIP_SNPS_PCIE3
 config PHY_ROCKCHIP_TYPEC
 	tristate "Rockchip TYPEC PHY Driver"
 	depends on OF && (ARCH_ROCKCHIP || COMPILE_TEST)
+	depends on DRM || DRM=n
+	select DRM_AUX_BRIDGE if DRM_BRIDGE
 	select EXTCON
 	select GENERIC_PHY
 	select RESET_CONTROLLER
diff --git a/drivers/phy/rockchip/phy-rockchip-typec.c b/drivers/phy/rockchip/phy-rockchip-typec.c
index d9701b6106d5..48070b50416e 100644
--- a/drivers/phy/rockchip/phy-rockchip-typec.c
+++ b/drivers/phy/rockchip/phy-rockchip-typec.c
@@ -54,6 +54,7 @@
 
 #include <linux/mfd/syscon.h>
 #include <linux/phy/phy.h>
+#include <drm/bridge/aux-bridge.h>
 
 #define CMN_SSM_BANDGAP			(0x21 << 2)
 #define CMN_SSM_BIAS			(0x22 << 2)
@@ -1162,16 +1163,24 @@ static int rockchip_typec_phy_probe(struct platform_device *pdev)
 
 	for_each_available_child_of_node(np, child_np) {
 		struct phy *phy;
+		ret = 0;
 
-		if (of_node_name_eq(child_np, "dp-port"))
+		if (of_node_name_eq(child_np, "dp-port")) {
 			phy = devm_phy_create(dev, child_np,
 					      &rockchip_dp_phy_ops);
-		else if (of_node_name_eq(child_np, "usb3-port"))
+			ret = drm_aux_bridge_register_from_node(dev, child_np);
+		} else if (of_node_name_eq(child_np, "usb3-port"))
 			phy = devm_phy_create(dev, child_np,
 					      &rockchip_usb3_phy_ops);
 		else
 			continue;
 
+		if (ret) {
+			pm_runtime_disable(dev);
+			of_node_put(child_np);
+			return ret;
+		}
+
 		if (IS_ERR(phy)) {
 			dev_err(dev, "failed to create phy: %pOFn\n",
 				child_np);
-- 
2.53.0


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

[PATCH 4/5] drm/rockchip: cdn-dp: Support handle lane info without extcon

[Chaoyi Chen]

From: Chaoyi Chen <chaoyi.chen@rock-chips.com>

This patch add support for get PHY lane info without help of extcon.

There is no extcon needed if the Type-C controller is present. In this
case, the lane info can be get from PHY instead of extcon.

The extcon device should still be supported if Type-C controller is
not present.

Signed-off-by: Chaoyi Chen <chaoyi.chen@rock-chips.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
---
 drivers/gpu/drm/rockchip/cdn-dp-core.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c
index 177e30445ee8..9068118859e2 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-core.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c
@@ -157,6 +157,9 @@ static int cdn_dp_get_port_lanes(struct cdn_dp_port *port)
 	int dptx;
 	u8 lanes;
 
+	if (!edev)
+		return phy_get_bus_width(port->phy);
+
 	dptx = extcon_get_state(edev, EXTCON_DISP_DP);
 	if (dptx > 0) {
 		extcon_get_property(edev, EXTCON_DISP_DP,
@@ -220,7 +223,7 @@ static bool cdn_dp_check_sink_connection(struct cdn_dp_device *dp)
 	 * some docks need more time to power up.
 	 */
 	while (time_before(jiffies, timeout)) {
-		if (!extcon_get_state(port->extcon, EXTCON_DISP_DP))
+		if (port->extcon && !extcon_get_state(port->extcon, EXTCON_DISP_DP))
 			return false;
 
 		if (!cdn_dp_get_sink_count(dp, &sink_count))
@@ -386,11 +389,14 @@ static int cdn_dp_enable_phy(struct cdn_dp_device *dp, struct cdn_dp_port *port)
 		goto err_power_on;
 	}
 
-	ret = extcon_get_property(port->extcon, EXTCON_DISP_DP,
-				  EXTCON_PROP_USB_TYPEC_POLARITY, &property);
-	if (ret) {
-		DRM_DEV_ERROR(dp->dev, "get property failed\n");
-		goto err_power_on;
+	property.intval = 0;
+	if (port->extcon) {
+		ret = extcon_get_property(port->extcon, EXTCON_DISP_DP,
+					  EXTCON_PROP_USB_TYPEC_POLARITY, &property);
+		if (ret) {
+			DRM_DEV_ERROR(dp->dev, "get property failed\n");
+			goto err_power_on;
+		}
 	}
 
 	port->lanes = cdn_dp_get_port_lanes(port);
@@ -1029,6 +1035,9 @@ static int cdn_dp_bind(struct device *dev, struct device *master, void *data)
 	for (i = 0; i < dp->ports; i++) {
 		port = dp->port[i];
 
+		if (!port->extcon)
+			continue;
+
 		port->event_nb.notifier_call = cdn_dp_pd_event;
 		ret = devm_extcon_register_notifier(dp->dev, port->extcon,
 						    EXTCON_DISP_DP,
@@ -1121,14 +1130,14 @@ static int cdn_dp_probe(struct platform_device *pdev)
 		    PTR_ERR(phy) == -EPROBE_DEFER)
 			return -EPROBE_DEFER;
 
-		if (IS_ERR(extcon) || IS_ERR(phy))
+		if (IS_ERR(phy) || PTR_ERR(extcon) != -ENODEV)
 			continue;
 
 		port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL);
 		if (!port)
 			return -ENOMEM;
 
-		port->extcon = extcon;
+		port->extcon = IS_ERR(extcon) ? NULL : extcon;
 		port->phy = phy;
 		port->dp = dp;
 		port->id = i;
-- 
2.53.0


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

[PATCH 5/5] drm/rockchip: cdn-dp: Add multiple bridges to support PHY port selection

[Chaoyi Chen]

From: Chaoyi Chen <chaoyi.chen@rock-chips.com>

The RK3399 has two USB/DP combo PHY and one CDN-DP controller. And
the CDN-DP can be switched to output to one of the PHYs. If both ports
are plugged into DP, DP will select the first port for output.

This patch adds support for multiple bridges, enabling users to flexibly
select the output port. For each PHY port, a separate encoder and bridge
are registered.

The change is based on the DRM AUX HPD bridge, rather than the
extcon approach. This requires the DT to correctly describe the
connections between the first bridge in bridge chain and DP
controller. For example, the bridge chain may be like this:

PHY aux birdge -> fsa4480 analog audio switch bridge ->
onnn,nb7vpq904m USB reminder bridge -> USB-C controller AUX HPD bridge

In this case, the connection relationships among the PHY aux bridge
and the DP contorller need to be described in DT.

In addition, the cdn_dp_parse_next_bridge_dt() will parses it and
determines whether to register one or two bridges.

Since there is only one DP controller, only one of the PHY ports can
output at a time. The key is how to switch between different PHYs,
which is handled by cdn_dp_switch_port() and cdn_dp_enable().

There are two cases:

1. Neither bridge is enabled. In this case, both bridges can
independently read the EDID, and the PHY port may switch before
reading the EDID.

2. One bridge is already enabled. In this case, other bridges are not
allowed to read the EDID. So we will try to return the cached EDID.

Since the scenario of two ports plug in at the same time is rare,
I don't have a board which support two TypeC connector to test this.
Therefore, I tested forced switching on a single PHY port, as well as
output using a fake PHY port alongside a real PHY port.

Signed-off-by: Chaoyi Chen <chaoyi.chen@rock-chips.com>
Reviewed-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
---
 drivers/gpu/drm/rockchip/Kconfig       |   1 +
 drivers/gpu/drm/rockchip/cdn-dp-core.c | 324 ++++++++++++++++++++-----
 drivers/gpu/drm/rockchip/cdn-dp-core.h |  18 +-
 3 files changed, 286 insertions(+), 57 deletions(-)

diff --git a/drivers/gpu/drm/rockchip/Kconfig b/drivers/gpu/drm/rockchip/Kconfig
index 1479b8c4ed40..cb97690c5a5d 100644
--- a/drivers/gpu/drm/rockchip/Kconfig
+++ b/drivers/gpu/drm/rockchip/Kconfig
@@ -59,6 +59,7 @@ config ROCKCHIP_CDN_DP
 	select DRM_DISPLAY_HELPER
 	select DRM_BRIDGE_CONNECTOR
 	select DRM_DISPLAY_DP_HELPER
+	select DRM_AUX_HPD_BRIDGE
 	help
 	  This selects support for Rockchip SoC specific extensions
 	  for the cdn DP driver. If you want to enable Dp on
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c
index 9068118859e2..b9ba279ca653 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-core.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c
@@ -28,16 +28,17 @@
 #include "cdn-dp-core.h"
 #include "cdn-dp-reg.h"
 
-static inline struct cdn_dp_device *bridge_to_dp(struct drm_bridge *bridge)
+static int cdn_dp_switch_port(struct cdn_dp_device *dp, struct cdn_dp_port *prev_port,
+			      struct cdn_dp_port *port);
+
+static inline struct cdn_dp_bridge *bridge_to_dp_bridge(struct drm_bridge *bridge)
 {
-	return container_of(bridge, struct cdn_dp_device, bridge);
+	return container_of(bridge, struct cdn_dp_bridge, bridge);
 }
 
-static inline struct cdn_dp_device *encoder_to_dp(struct drm_encoder *encoder)
+static inline struct cdn_dp_device *bridge_to_dp(struct drm_bridge *bridge)
 {
-	struct rockchip_encoder *rkencoder = to_rockchip_encoder(encoder);
-
-	return container_of(rkencoder, struct cdn_dp_device, encoder);
+	return bridge_to_dp_bridge(bridge)->parent;
 }
 
 #define GRF_SOC_CON9		0x6224
@@ -192,14 +193,27 @@ static int cdn_dp_get_sink_count(struct cdn_dp_device *dp, u8 *sink_count)
 static struct cdn_dp_port *cdn_dp_connected_port(struct cdn_dp_device *dp)
 {
 	struct cdn_dp_port *port;
-	int i, lanes;
+	int i, lanes[MAX_PHY];
 
 	for (i = 0; i < dp->ports; i++) {
 		port = dp->port[i];
-		lanes = cdn_dp_get_port_lanes(port);
-		if (lanes)
+		lanes[i] = cdn_dp_get_port_lanes(port);
+		if (!dp->next_bridge_valid)
 			return port;
 	}
+
+	if (dp->next_bridge_valid) {
+		/* If more than one port is available, pick the last active port */
+		if (dp->active_port > 0 && lanes[dp->active_port])
+			return dp->port[dp->active_port];
+
+		/* If the last active port is not available, pick an available port in order */
+		for (i = 0; i < dp->bridge_count; i++) {
+			if (lanes[i])
+				return dp->port[i];
+		}
+	}
+
 	return NULL;
 }
 
@@ -254,12 +268,45 @@ static const struct drm_edid *
 cdn_dp_bridge_edid_read(struct drm_bridge *bridge, struct drm_connector *connector)
 {
 	struct cdn_dp_device *dp = bridge_to_dp(bridge);
-	const struct drm_edid *drm_edid;
+	struct cdn_dp_bridge *dp_bridge = bridge_to_dp_bridge(bridge);
+	struct cdn_dp_port *port = dp->port[dp_bridge->id];
+	struct cdn_dp_port *prev_port;
+	const struct drm_edid *drm_edid = NULL;
+	int i, ret;
 
 	mutex_lock(&dp->lock);
+
+	/* More than one port is available */
+	if (dp->bridge_count > 1 && !port->phy_enabled) {
+		for (i = 0; i < dp->bridge_count; i++) {
+			/* Another port already enable */
+			if (dp->bridge_list[i] != dp_bridge && dp->bridge_list[i]->enabled)
+				goto get_cache;
+			/* Find already enabled port */
+			if (dp->port[i]->phy_enabled)
+				prev_port = dp->port[i];
+		}
+
+		/* Switch to current port */
+		if (prev_port) {
+			ret = cdn_dp_switch_port(dp, prev_port, port);
+			if (ret)
+				goto get_cache;
+		}
+	}
+
 	drm_edid = drm_edid_read_custom(connector, cdn_dp_get_edid_block, dp);
+	/* replace edid cache */
+	if (dp->edid_cache[dp_bridge->id])
+		drm_edid_free(dp->edid_cache[dp_bridge->id]);
+	dp->edid_cache[dp_bridge->id] = drm_edid_dup(drm_edid);
+
 	mutex_unlock(&dp->lock);
+	return drm_edid;
 
+get_cache:
+	drm_edid = drm_edid_dup(dp->edid_cache[dp_bridge->id]);
+	mutex_unlock(&dp->lock);
 	return drm_edid;
 }
 
@@ -268,12 +315,13 @@ cdn_dp_bridge_mode_valid(struct drm_bridge *bridge,
 			 const struct drm_display_info *display_info,
 			 const struct drm_display_mode *mode)
 {
+	struct cdn_dp_bridge *dp_bridge = bridge_to_dp_bridge(bridge);
 	struct cdn_dp_device *dp = bridge_to_dp(bridge);
 	u32 requested, actual, rate, sink_max, source_max = 0;
 	u8 lanes, bpc;
 
 	/* If DP is disconnected, every mode is invalid */
-	if (!dp->connected)
+	if (!dp_bridge->connected || !dp->connected)
 		return MODE_BAD;
 
 	switch (display_info->bpc) {
@@ -551,6 +599,54 @@ static bool cdn_dp_check_link_status(struct cdn_dp_device *dp)
 	return drm_dp_channel_eq_ok(link_status, min(port->lanes, sink_lanes));
 }
 
+static int cdn_dp_switch_port(struct cdn_dp_device *dp, struct cdn_dp_port *prev_port,
+			      struct cdn_dp_port *port)
+{
+	int ret;
+
+	if (dp->active)
+		return 0;
+
+	ret = cdn_dp_disable_phy(dp, prev_port);
+	if (ret)
+		goto out;
+	ret = cdn_dp_enable_phy(dp, port);
+	if (ret)
+		goto out;
+
+	ret = cdn_dp_get_sink_capability(dp);
+	if (ret) {
+		cdn_dp_disable_phy(dp, port);
+		goto out;
+	}
+
+	dp->active = true;
+	dp->lanes = port->lanes;
+
+	if (!cdn_dp_check_link_status(dp)) {
+		dev_info(dp->dev, "Connected with sink; re-train link\n");
+
+		ret = cdn_dp_train_link(dp);
+		if (ret) {
+			dev_err(dp->dev, "Training link failed: %d\n", ret);
+			goto out;
+		}
+
+		ret = cdn_dp_set_video_status(dp, CONTROL_VIDEO_IDLE);
+		if (ret) {
+			dev_err(dp->dev, "Failed to idle video %d\n", ret);
+			goto out;
+		}
+
+		ret = cdn_dp_config_video(dp);
+		if (ret)
+			dev_err(dp->dev, "Failed to configure video: %d\n", ret);
+	}
+
+out:
+	return ret;
+}
+
 static void cdn_dp_display_info_update(struct cdn_dp_device *dp,
 				       struct drm_display_info *display_info)
 {
@@ -572,6 +668,7 @@ static void cdn_dp_display_info_update(struct cdn_dp_device *dp,
 static void cdn_dp_bridge_atomic_enable(struct drm_bridge *bridge, struct drm_atomic_state *state)
 {
 	struct cdn_dp_device *dp = bridge_to_dp(bridge);
+	struct cdn_dp_bridge *dp_bridge = bridge_to_dp_bridge(bridge);
 	struct drm_connector *connector;
 	int ret, val;
 
@@ -581,7 +678,7 @@ static void cdn_dp_bridge_atomic_enable(struct drm_bridge *bridge, struct drm_at
 
 	cdn_dp_display_info_update(dp, &connector->display_info);
 
-	ret = drm_of_encoder_active_endpoint_id(dp->dev->of_node, &dp->encoder.encoder);
+	ret = drm_of_encoder_active_endpoint_id(dp->dev->of_node, &dp_bridge->encoder.encoder);
 	if (ret < 0) {
 		DRM_DEV_ERROR(dp->dev, "Could not get vop id, %d", ret);
 		return;
@@ -600,6 +697,9 @@ static void cdn_dp_bridge_atomic_enable(struct drm_bridge *bridge, struct drm_at
 
 	mutex_lock(&dp->lock);
 
+	if (dp->next_bridge_valid)
+		dp->active_port = dp_bridge->id;
+
 	ret = cdn_dp_enable(dp);
 	if (ret) {
 		DRM_DEV_ERROR(dp->dev, "Failed to enable bridge %d\n",
@@ -632,6 +732,7 @@ static void cdn_dp_bridge_atomic_enable(struct drm_bridge *bridge, struct drm_at
 		goto out;
 	}
 
+	dp_bridge->enabled = true;
 out:
 	mutex_unlock(&dp->lock);
 }
@@ -639,9 +740,11 @@ static void cdn_dp_bridge_atomic_enable(struct drm_bridge *bridge, struct drm_at
 static void cdn_dp_bridge_atomic_disable(struct drm_bridge *bridge, struct drm_atomic_state *state)
 {
 	struct cdn_dp_device *dp = bridge_to_dp(bridge);
+	struct cdn_dp_bridge *dp_bridge = bridge_to_dp_bridge(bridge);
 	int ret;
 
 	mutex_lock(&dp->lock);
+	dp_bridge->enabled = false;
 
 	if (dp->active) {
 		ret = cdn_dp_disable(dp);
@@ -828,6 +931,16 @@ static int cdn_dp_audio_mute_stream(struct drm_bridge *bridge,
 	return ret;
 }
 
+static void cdn_dp_bridge_hpd_notify(struct drm_bridge *bridge,
+			   enum drm_connector_status status)
+{
+	struct cdn_dp_bridge *dp_bridge = bridge_to_dp_bridge(bridge);
+	struct cdn_dp_device *dp = bridge_to_dp(bridge);
+
+	dp->bridge_list[dp_bridge->id]->connected = status == connector_status_connected;
+	schedule_work(&dp->event_work);
+}
+
 static const struct drm_bridge_funcs cdn_dp_bridge_funcs = {
 	.atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_bridge_destroy_state,
@@ -838,6 +951,7 @@ static const struct drm_bridge_funcs cdn_dp_bridge_funcs = {
 	.atomic_disable = cdn_dp_bridge_atomic_disable,
 	.mode_valid = cdn_dp_bridge_mode_valid,
 	.mode_set = cdn_dp_bridge_mode_set,
+	.hpd_notify = cdn_dp_bridge_hpd_notify,
 
 	.dp_audio_prepare = cdn_dp_audio_prepare,
 	.dp_audio_mute_stream = cdn_dp_audio_mute_stream,
@@ -886,7 +1000,8 @@ static void cdn_dp_pd_event_work(struct work_struct *work)
 {
 	struct cdn_dp_device *dp = container_of(work, struct cdn_dp_device,
 						event_work);
-	int ret;
+	bool connected;
+	int i, ret;
 
 	mutex_lock(&dp->lock);
 
@@ -945,9 +1060,12 @@ static void cdn_dp_pd_event_work(struct work_struct *work)
 
 out:
 	mutex_unlock(&dp->lock);
-	drm_bridge_hpd_notify(&dp->bridge,
-			      dp->connected ? connector_status_connected
-					    : connector_status_disconnected);
+	for (i = 0; i < dp->bridge_count; i++) {
+		connected = dp->connected && dp->bridge_list[i]->connected;
+		drm_bridge_hpd_notify(&dp->bridge_list[i]->bridge,
+				      connected ? connector_status_connected
+						: connector_status_disconnected);
+	}
 }
 
 static int cdn_dp_pd_event(struct notifier_block *nb,
@@ -967,28 +1085,16 @@ static int cdn_dp_pd_event(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
-static int cdn_dp_bind(struct device *dev, struct device *master, void *data)
+static int cdn_bridge_add(struct device *dev,
+			  struct drm_bridge *bridge,
+			  struct drm_bridge *next_bridge,
+			  struct drm_encoder *encoder)
 {
 	struct cdn_dp_device *dp = dev_get_drvdata(dev);
-	struct drm_encoder *encoder;
+	struct drm_device *drm_dev = dp->drm_dev;
+	struct drm_bridge *last_bridge __free(drm_bridge_put) = NULL;
 	struct drm_connector *connector;
-	struct cdn_dp_port *port;
-	struct drm_device *drm_dev = data;
-	int ret, i;
-
-	ret = cdn_dp_parse_dt(dp);
-	if (ret < 0)
-		return ret;
-
-	dp->drm_dev = drm_dev;
-	dp->connected = false;
-	dp->active = false;
-	dp->active_port = -1;
-	dp->fw_loaded = false;
-
-	INIT_WORK(&dp->event_work, cdn_dp_pd_event_work);
-
-	encoder = &dp->encoder.encoder;
+	int ret;
 
 	encoder->possible_crtcs = drm_of_find_possible_crtcs(drm_dev,
 							     dev->of_node);
@@ -1003,26 +1109,35 @@ static int cdn_dp_bind(struct device *dev, struct device *master, void *data)
 
 	drm_encoder_helper_add(encoder, &cdn_dp_encoder_helper_funcs);
 
-	dp->bridge.ops =
-			DRM_BRIDGE_OP_DETECT |
-			DRM_BRIDGE_OP_EDID |
-			DRM_BRIDGE_OP_HPD |
-			DRM_BRIDGE_OP_DP_AUDIO;
-	dp->bridge.of_node = dp->dev->of_node;
-	dp->bridge.type = DRM_MODE_CONNECTOR_DisplayPort;
-	dp->bridge.hdmi_audio_dev = dp->dev;
-	dp->bridge.hdmi_audio_max_i2s_playback_channels = 8;
-	dp->bridge.hdmi_audio_spdif_playback = 1;
-	dp->bridge.hdmi_audio_dai_port = -1;
-
-	ret = devm_drm_bridge_add(dev, &dp->bridge);
+	bridge->ops =
+		DRM_BRIDGE_OP_DETECT |
+		DRM_BRIDGE_OP_EDID |
+		DRM_BRIDGE_OP_HPD |
+		DRM_BRIDGE_OP_DP_AUDIO;
+	bridge->of_node = dp->dev->of_node;
+	bridge->type = DRM_MODE_CONNECTOR_DisplayPort;
+	bridge->hdmi_audio_dev = dp->dev;
+	bridge->hdmi_audio_max_i2s_playback_channels = 8;
+	bridge->hdmi_audio_spdif_playback = 1;
+	bridge->hdmi_audio_dai_port = -1;
+
+	ret = devm_drm_bridge_add(dev, bridge);
 	if (ret)
 		return ret;
 
-	ret = drm_bridge_attach(encoder, &dp->bridge, NULL, DRM_BRIDGE_ATTACH_NO_CONNECTOR);
+	ret = drm_bridge_attach(encoder, bridge, NULL, DRM_BRIDGE_ATTACH_NO_CONNECTOR);
 	if (ret)
 		return ret;
 
+	if (next_bridge) {
+		ret = drm_bridge_attach(encoder, next_bridge, bridge,
+					DRM_BRIDGE_ATTACH_NO_CONNECTOR);
+		if (ret)
+			return ret;
+
+		last_bridge = drm_bridge_chain_get_last_bridge(bridge->encoder);
+	}
+
 	connector = drm_bridge_connector_init(drm_dev, encoder);
 	if (IS_ERR(connector)) {
 		ret = PTR_ERR(connector);
@@ -1030,8 +1145,99 @@ static int cdn_dp_bind(struct device *dev, struct device *master, void *data)
 		return ret;
 	}
 
+	if (last_bridge)
+		connector->fwnode = fwnode_handle_get(of_fwnode_handle(last_bridge->of_node));
+
 	drm_connector_attach_encoder(connector, encoder);
 
+	return 0;
+}
+
+static int cdn_dp_parse_next_bridge_dt(struct cdn_dp_device *dp)
+{
+	struct device_node *np = dp->dev->of_node;
+	struct device_node *port __free(device_node) = of_graph_get_port_by_id(np, 1);
+	struct drm_bridge *bridge;
+	int count = 0;
+	int ret = 0;
+	int i;
+
+	/* If device use extcon, do not use hpd bridge */
+	for (i = 0; i < dp->ports; i++) {
+		if (dp->port[i]->extcon) {
+			dp->bridge_count = 1;
+			return 0;
+		}
+	}
+
+	/* One endpoint may correspond to one next bridge. */
+	for_each_of_graph_port_endpoint(port, dp_ep) {
+		struct device_node *next_bridge_node __free(device_node) =
+			of_graph_get_remote_port_parent(dp_ep);
+
+		bridge = of_drm_find_bridge(next_bridge_node);
+		if (!bridge) {
+			ret = -EPROBE_DEFER;
+			goto out;
+		}
+
+		dp->next_bridge_valid = true;
+		dp->next_bridge_list[count] = drm_bridge_get(bridge);
+		count++;
+	}
+
+out:
+	dp->bridge_count = count ? count : 1;
+	return ret;
+}
+
+static int cdn_dp_bind(struct device *dev, struct device *master, void *data)
+{
+	struct cdn_dp_device *dp = dev_get_drvdata(dev);
+	struct drm_bridge *bridge, *next_bridge;
+	struct drm_encoder *encoder;
+	struct cdn_dp_port *port;
+	struct drm_device *drm_dev = data;
+	struct cdn_dp_bridge *dp_bridge;
+	int ret, i;
+
+	ret = cdn_dp_parse_dt(dp);
+	if (ret < 0)
+		return ret;
+
+	ret = cdn_dp_parse_next_bridge_dt(dp);
+	if (ret)
+		return ret;
+
+	dp->drm_dev = drm_dev;
+	dp->connected = false;
+	dp->active = false;
+	dp->active_port = -1;
+	dp->fw_loaded = false;
+
+	for (i = 0; i < dp->bridge_count; i++) {
+		dp_bridge = devm_drm_bridge_alloc(dev, struct cdn_dp_bridge, bridge,
+						    &cdn_dp_bridge_funcs);
+		if (IS_ERR(dp_bridge))
+			return PTR_ERR(dp_bridge);
+		dp_bridge->id = i;
+		dp_bridge->parent = dp;
+		if (!dp->next_bridge_valid)
+			dp_bridge->connected = true;
+		dp->bridge_list[i] = dp_bridge;
+	}
+
+	for (i = 0; i < dp->bridge_count; i++) {
+		encoder = &dp->bridge_list[i]->encoder.encoder;
+		bridge = &dp->bridge_list[i]->bridge;
+		next_bridge = dp->next_bridge_list[i];
+		ret = cdn_bridge_add(dev, bridge, next_bridge, encoder);
+		if (ret)
+			return ret;
+	}
+
+	INIT_WORK(&dp->event_work, cdn_dp_pd_event_work);
+
 	for (i = 0; i < dp->ports; i++) {
 		port = dp->port[i];
 
@@ -1059,10 +1265,18 @@ static int cdn_dp_bind(struct device *dev, struct device *master, void *data)
 static void cdn_dp_unbind(struct device *dev, struct device *master, void *data)
 {
 	struct cdn_dp_device *dp = dev_get_drvdata(dev);
-	struct drm_encoder *encoder = &dp->encoder.encoder;
+	struct drm_encoder *encoder;
+	int i;
 
 	cancel_work_sync(&dp->event_work);
-	encoder->funcs->destroy(encoder);
+	for (i = 0; i < dp->bridge_count; i++) {
+		encoder = &dp->bridge_list[i]->encoder.encoder;
+		encoder->funcs->destroy(encoder);
+		drm_bridge_put(dp->next_bridge_list[i]);
+	}
+
+	for (i = 0; i < MAX_PHY; i++)
+		drm_edid_free(dp->edid_cache[i]);
 
 	pm_runtime_disable(dev);
 	if (dp->fw_loaded)
@@ -1113,10 +1327,10 @@ static int cdn_dp_probe(struct platform_device *pdev)
 	int ret;
 	int i;
 
-	dp = devm_drm_bridge_alloc(dev, struct cdn_dp_device, bridge,
-				   &cdn_dp_bridge_funcs);
-	if (IS_ERR(dp))
-		return PTR_ERR(dp);
+	dp = devm_kzalloc(dev, sizeof(*dp), GFP_KERNEL);
+	if (!dp)
+		return -ENOMEM;
+
 	dp->dev = dev;
 
 	match = of_match_node(cdn_dp_dt_ids, pdev->dev.of_node);
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.h b/drivers/gpu/drm/rockchip/cdn-dp-core.h
index e9c30b9fd543..c10e423bbf06 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-core.h
+++ b/drivers/gpu/drm/rockchip/cdn-dp-core.h
@@ -38,6 +38,8 @@ enum vic_pxl_encoding_format {
 	Y_ONLY = 0x10,
 };
 
+struct cdn_dp_device;
+
 struct video_info {
 	bool h_sync_polarity;
 	bool v_sync_polarity;
@@ -63,16 +65,28 @@ struct cdn_dp_port {
 	u8 id;
 };
 
+struct cdn_dp_bridge {
+	struct cdn_dp_device *parent;
+	struct drm_bridge bridge;
+	struct rockchip_encoder encoder;
+	bool connected;
+	bool enabled;
+	int id;
+};
+
 struct cdn_dp_device {
 	struct device *dev;
 	struct drm_device *drm_dev;
-	struct drm_bridge bridge;
-	struct rockchip_encoder encoder;
+	int bridge_count;
+	struct cdn_dp_bridge *bridge_list[MAX_PHY];
+	struct drm_bridge *next_bridge_list[MAX_PHY];
+	const struct drm_edid *edid_cache[MAX_PHY];
 	struct drm_display_mode mode;
 	struct platform_device *audio_pdev;
 	struct work_struct event_work;
 
 	struct mutex lock;
+	bool next_bridge_valid;
 	bool connected;
 	bool active;
 	bool suspended;
-- 
2.53.0


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

Re: [PATCH 1/5] drm/bridge: Implement generic USB Type-C DP HPD bridge

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 5 potential issue(s) to consider:
- [High] Module initialization misses Type-C ports that are already registered.
- [High] Missing `BUS_NOTIFY_DEL_DEVICE` handling and incorrect `devm` usage leads to memory leaks and use-after-free on module unload.
- [High] Generic notifier blindly creates duplicate bridges for controllers that already register them natively.
- [High] Blind use of `alt->dev.parent->parent` causes NULL pointer dereference in devm_ functions if the port lacks a parent.
- [Medium] Kconfig entry lacks a prompt string and has an incorrect dependency structure.
--

commit 6278338190ad225c12a2042f8bb6669eb188e362
Author: Chaoyi Chen <chaoyi.chen@rock-chips.com>

drm/bridge: Implement generic USB Type-C DP HPD bridge

This patch implements a generic DP HPD bridge based on aux-hpd-bridge.c.
It monitors Type-C bus events, and when a Type-C port device containing
the DP svid is registered, it automatically creates an HPD bridge.

> diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
> index c3209b0f46786..d92e938757931 100644
> --- a/drivers/gpu/drm/bridge/Kconfig
> +++ b/drivers/gpu/drm/bridge/Kconfig
> @@ -30,6 +30,16 @@ config DRM_AUX_HPD_BRIDGE
>  	  Simple bridge that terminates the bridge chain and provides HPD
>  	  support.
>  
> +if DRM_AUX_HPD_BRIDGE
> +config DRM_AUX_HPD_TYPEC_BRIDGE
> +	tristate
> +	depends on TYPEC || !TYPEC

[Severity: Medium]
Is there a missing prompt string for this tristate? Without it, the option
is invisible in menuconfig.

Also, since this module directly uses symbols like typec_bus, won't
depends on TYPEC || !TYPEC cause a build failure when CONFIG_TYPEC=n since
the dependency evaluates to true?

> +	default TYPEC
> +	help
> +	  Simple bridge that terminates the bridge chain and provides HPD
> +	  support. It build bridge on each USB-C connector device node.
> +endif

[ ... ]

> diff --git a/drivers/gpu/drm/bridge/aux-hpd-typec-dp-bridge.c b/drivers/gpu/drm/bridge/aux-hpd-typec-dp-bridge.c
> new file mode 100644
> index 0000000000000..d915e0fb0668c
> --- /dev/null
> +++ b/drivers/gpu/drm/bridge/aux-hpd-typec-dp-bridge.c
> @@ -0,0 +1,49 @@
> +// SPDX-License-Identifier: GPL-2.0+
> +#include <linux/of.h>
> +#include <linux/usb/typec_altmode.h>
> +#include <linux/usb/typec_dp.h>
> +
> +#include <drm/bridge/aux-bridge.h>
> +
> +static int drm_typec_bus_event(struct notifier_block *nb,
> +			       unsigned long action, void *data)
> +{
> +	struct device *dev = (struct device *)data;
> +	struct typec_altmode *alt = to_typec_altmode(dev);
> +
> +	if (action != BUS_NOTIFY_ADD_DEVICE)
> +		goto done;

[Severity: High]
What happens when a port is unregistered? Since drm_dp_hpd_bridge_register()
allocates resources using devm tied to the controller device, ignoring
BUS_NOTIFY_DEL_DEVICE means the bridge won't be freed if the port altmode
is dynamically unregistered, leading to duplicate bridges and memory leaks on
re-registration.

If this module is unloaded, the devres callbacks remain attached to the
controller. Will that cause a use-after-free kernel panic when the controller
is unbound later?

> +
> +	/*
> +	 * alt->dev.parent->parent : USB-C controller device
> +	 * alt->dev.parent         : USB-C connector device
> +	 */
> +	if (is_typec_port_altmode(&alt->dev) && alt->svid == USB_TYPEC_DP_SID)
> +		drm_dp_hpd_bridge_register(alt->dev.parent->parent,
> +					   to_of_node(alt->dev.parent->fwnode));

[Severity: High]
Can alt->dev.parent be NULL here? The Type-C subsystem allows ports to be
registered without a parent. If so, dereferencing alt->dev.parent->parent
will cause a NULL pointer dereference.

[Severity: High]
Several Type-C controller drivers already register their own DP HPD bridges.
Does this unconditionally create a second bridge for those ports?

If two bridges are registered for the same device node, the controller driver
will route HPD events to its native bridge, while the DRM driver might bind
to this generic one, breaking hotplug detection.

> +
> +done:
> +	return NOTIFY_OK;
> +}
> +
> +static struct notifier_block drm_typec_event_nb = {
> +	.notifier_call = drm_typec_bus_event,
> +};
> +
> +static void drm_aux_hpd_typec_dp_bridge_module_exit(void)
> +{
> +	bus_unregister_notifier(&typec_bus, &drm_typec_event_nb);
> +}
> +
> +static int __init drm_aux_hpd_typec_dp_bridge_module_init(void)
> +{
> +	bus_register_notifier(&typec_bus, &drm_typec_event_nb);
> +
> +	return 0;
> +}

[Severity: High]
If this module is loaded after Type-C port controllers have already probed,
will it miss the existing ports?

Calling bus_register_notifier() only catches new BUS_NOTIFY_ADD_DEVICE events,
so bridges wouldn't be created for devices already on the bus.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260521032854.103-1-kernel@airkyi.com?part=1

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

Re: [PATCH 2/5] drm/bridge: aux: Add drm_aux_bridge_register_from_node()

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Critical] The `drm_aux_bridge_register_from_node()` function fails to acquire a reference to the provided `device_node` (`np`), leading to a reference count underflow and potential use-after-free during cleanup.
- [Low] The kernel-doc comment for `drm_aux_bridge_register_from_node()` retains the old function name, causing a documentation build warning.
--

commit a4484cec194d2731c92e629a32b7e17a725601d7
Author: Chaoyi Chen <chaoyi.chen@rock-chips.com>

drm/bridge: aux: Add drm_aux_bridge_register_from_node()

This patch adds drm_aux_bridge_register_from_node() to allow
specifying the of_node corresponding to the bridge.

> diff --git a/drivers/gpu/drm/bridge/aux-bridge.c b/drivers/gpu/drm/bridge/aux-bridge.c
> index 1ed21a8713bfd..f50283abed5f6 100644
> --- a/drivers/gpu/drm/bridge/aux-bridge.c
> +++ b/drivers/gpu/drm/bridge/aux-bridge.c
> @@ -35,6 +35,7 @@ static void drm_aux_bridge_unregister_adev(void *_adev)
>  /**
>   * drm_aux_bridge_register - Create a simple bridge device to link the chain

[Severity: Low]
This isn't a bug, but there's a mismatch between the kernel-doc identifier
and the new function name. Should this be updated to
drm_aux_bridge_register_from_node?

>   * @parent: device instance providing this bridge
> + * @np: device node pointer corresponding to this bridge instance

[ ... ]

> @@ -62,7 +63,10 @@ int drm_aux_bridge_register(struct device *parent)
>  	adev->dev.parent = parent;
>  	adev->dev.release = drm_aux_bridge_release;
>  
> -	device_set_of_node_from_dev(&adev->dev, parent);
> +	if (np)
> +		device_set_node(&adev->dev, of_fwnode_handle(np));

[Severity: Critical]
Will this cause a reference count underflow on the device node?

If np is provided, device_set_node() assigns the fwnode without incrementing
the device node's reference count.

However, both the auxiliary_device_init() error path (shown below) and the
device's release callback drm_aux_bridge_release() unconditionally call
of_node_put(adev->dev.of_node).

Since there is no matching of_node_get(), this could corrupt the reference
count and lead to a use-after-free. Should we call of_node_get(np) here?

> +	else
> +		device_set_of_node_from_dev(&adev->dev, parent);
>  
>  	ret = auxiliary_device_init(adev);
>  	if (ret) {
>  		of_node_put(adev->dev.of_node);

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260521032854.103-1-kernel@airkyi.com?part=2

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

Re: [PATCH 3/5] phy: rockchip: phy-rockchip-typec: Add DRM AUX bridge

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] Double-free of the `child_np` device node reference leading to a Use-After-Free.
- [Medium] Incorrect error check ordering masks `devm_phy_create` failures and attempts bridge registration on invalid PHY pointers.
--

commit 83430d0b883e6ab3238d19fd9d398fef26aa6ab7
Author: Chaoyi Chen <chaoyi.chen@rock-chips.com>

phy: rockchip: phy-rockchip-typec: Add DRM AUX bridge

Using the DRM_AUX_BRIDGE helper to create the transparent DRM bridge
device.

> diff --git a/drivers/phy/rockchip/phy-rockchip-typec.c b/drivers/phy/rockchip/phy-rockchip-typec.c
> index d9701b6106d55..48070b50416e5 100644
> --- a/drivers/phy/rockchip/phy-rockchip-typec.c
> +++ b/drivers/phy/rockchip/phy-rockchip-typec.c
[ ... ]
> @@ -1162,16 +1163,24 @@ static int rockchip_typec_phy_probe(struct platform_device *pdev)
>  
>  	for_each_available_child_of_node(np, child_np) {
>  		struct phy *phy;
> +		ret = 0;
>  
> -		if (of_node_name_eq(child_np, "dp-port"))
> +		if (of_node_name_eq(child_np, "dp-port")) {
>  			phy = devm_phy_create(dev, child_np,
>  					      &rockchip_dp_phy_ops);
> -		else if (of_node_name_eq(child_np, "usb3-port"))
> +			ret = drm_aux_bridge_register_from_node(dev, child_np);

[Severity: High]
Does this code result in a double-free of the child_np device node
reference?

The macro for_each_available_child_of_node() automatically manages the
reference count for child_np, acquiring it for the current iteration and
dropping it when advancing.

drm_aux_bridge_register_from_node() assigns the node to the auxiliary bridge
device, and the auxiliary bridge assumes ownership of a reference (calling
of_node_put() in its error paths and release callback).

Because an additional reference is not acquired via of_node_get()
before passing it, the reference is decremented twice, which can lead to a
use-after-free.

> +		} else if (of_node_name_eq(child_np, "usb3-port"))
>  			phy = devm_phy_create(dev, child_np,
>  					      &rockchip_usb3_phy_ops);
>  		else
>  			continue;
>  
> +		if (ret) {
> +			pm_runtime_disable(dev);
> +			of_node_put(child_np);
> +			return ret;
> +		}
> +
>  		if (IS_ERR(phy)) {

[Severity: Medium]
Will this error check ordering mask devm_phy_create() failures?

The check for bridge registration failure (if (ret)) happens before the
check for PHY creation failure (if (IS_ERR(phy))). If devm_phy_create()
fails (e.g., returning -EPROBE_DEFER) and the subsequent bridge registration
also fails, the function will return the bridge error and mask the PHY error.

Additionally, this attempts to register the auxiliary bridge even after the
underlying PHY creation has already failed. Should IS_ERR(phy) be checked
before calling drm_aux_bridge_register_from_node(), or at least before
checking ret?

>  			dev_err(dev, "failed to create phy: %pOFn\n",
>  				child_np);

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260521032854.103-1-kernel@airkyi.com?part=3

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

Re: [PATCH 4/5] drm/rockchip: cdn-dp: Support handle lane info without extcon

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] The condition `PTR_ERR(extcon) != -ENODEV` in `cdn_dp_probe()` evaluates to true for valid `extcon` pointers, breaking initialization for devices with `extcon`.
--

commit 1c12cc989734f906a15b7d45d90d57d21f55c2d3
Author: Chaoyi Chen <chaoyi.chen@rock-chips.com>

drm/rockchip: cdn-dp: Support handle lane info without extcon

This commit adds support for getting PHY lane information directly from the
PHY instead of relying on extcon when a Type-C controller is present. It
updates the probe, bind, and phy enable paths to allow operation without
an extcon device, while intending to keep extcon supported for older setups.

> diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c
> index 177e30445ee83..9068118859e21 100644
> --- a/drivers/gpu/drm/rockchip/cdn-dp-core.c
> +++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c

[ ... ]

> @@ -1121,14 +1130,14 @@ static int cdn_dp_probe(struct platform_device *pdev)
>  		    PTR_ERR(phy) == -EPROBE_DEFER)
>  			return -EPROBE_DEFER;
>  
> -		if (IS_ERR(extcon) || IS_ERR(phy))
> +		if (IS_ERR(phy) || PTR_ERR(extcon) != -ENODEV)

[Severity: High]
Does this condition inadvertently skip port initialization for valid extcon
devices?

When extcon_get_edev_by_phandle() successfully returns a valid pointer,
PTR_ERR(extcon) evaluates to the pointer's memory address. Since a valid
pointer address is not equal to -ENODEV, this condition will evaluate to
true and trigger the continue statement.

This appears to break enumeration for all existing devices that use an extcon
by unconditionally skipping their setup. 

Would it be better to ensure we only check the error code when the pointer
is actually an error?

		if (IS_ERR(phy) || (IS_ERR(extcon) && PTR_ERR(extcon) != -ENODEV))

>  			continue;
>  
>  		port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL);
>  		if (!port)
>  			return -ENOMEM;
>  
> -		port->extcon = extcon;
> +		port->extcon = IS_ERR(extcon) ? NULL : extcon;
>  		port->phy = phy;
>  		port->dp = dp;
>  		port->id = i;

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260521032854.103-1-kernel@airkyi.com?part=4

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

Re: [PATCH 5/5] drm/rockchip: cdn-dp: Add multiple bridges to support PHY port selection

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 11 potential issue(s) to consider:
- [High] Prematurely dropping the reference count of the last bridge in `cdn_bridge_add()` will cause a use-after-free.
- [High] The `prev_port` pointer is used uninitialized in `cdn_dp_bridge_edid_read()`, leading to a kernel crash.
- [High] `cdn_dp_connected_port()` ignores connection status for extcon configurations, breaking hotplug detection.
- [High] Missing bounds check in `cdn_dp_parse_next_bridge_dt()` allows an out-of-bounds write to the `next_bridge_list` array.
- [High] The `lanes` stack array is read out-of-bounds or uninitialized in `cdn_dp_connected_port()`.
- [High] DRM bridge references are leaked on error paths during DT parsing and driver binding.
- [High] If link training fails in `cdn_dp_switch_port()`, it returns an error but leaves the DP controller erroneously marked as active.
- [High] `cdn_dp_switch_port()` incorrectly aborts hardware switching when the DP controller is active, causing EDID reads from the wrong port.
- [High] Disabling an inactive bridge erroneously disables the active DP controller for another bridge.
- [Medium] Overwriting `connector->fwnode` in `cdn_bridge_add()` causes a memory leak.
- [Medium] Incorrect check for the active port treats valid index 0 as invalid.
--

Hi,

I have reviewed the patch and found some potential issues to share.

commit 082c705aa7547b521ad9df20ac76e0592b41864f
Author: Chaoyi Chen <chaoyi.chen@rock-chips.com>

    drm/rockchip: cdn-dp: Add multiple bridges to support PHY port selection

This commit adds support for multiple bridges to the Rockchip cdn-dp driver
to allow switching between two USB/DP combo PHYs. It changes the driver to
use the DRM AUX HPD bridge and adds DT parsing logic to register multiple
bridges.

> @@ -192,14 +193,27 @@ static int cdn_dp_get_sink_count(struct cdn_dp_device *dp, u8 *sink_count)
>  static struct cdn_dp_port *cdn_dp_connected_port(struct cdn_dp_device *dp)
>  {
>  	struct cdn_dp_port *port;
> -	int i, lanes;
> +	int i, lanes[MAX_PHY];
>  
>  	for (i = 0; i < dp->ports; i++) {
>  		port = dp->port[i];
> -		lanes = cdn_dp_get_port_lanes(port);
> -		if (lanes)
> +		lanes[i] = cdn_dp_get_port_lanes(port);
> +		if (!dp->next_bridge_valid)
>  			return port;

[Severity: High]
Does this unconditionally return the first port without checking if it is
actually connected? If dp->next_bridge_valid is false (which is the case for
extcon setups), it appears to return port on the first iteration regardless
of lanes[i], completely breaking hotplug detection.

>  	}
> +
> +	if (dp->next_bridge_valid) {
> +		/* If more than one port is available, pick the last active port */
> +		if (dp->active_port > 0 && lanes[dp->active_port])

[Severity: Medium]
Since dp->active_port is initialized to -1, valid port indices are 0 and 1.
Does the check dp->active_port > 0 incorrectly evaluate to false when the
active port is 0, skipping the active port?

> +			return dp->port[dp->active_port];
> +
> +		/* If the last active port is not available, pick an available port in order */
> +		for (i = 0; i < dp->bridge_count; i++) {
> +			if (lanes[i])

[Severity: High]
Can this read uninitialized stack memory? The lanes stack array is populated
in a loop bounded by dp->ports, but accessed here in a loop bounded by
dp->bridge_count.

If dp->bridge_count > dp->ports, this will read uninitialized values.
Furthermore, since lanes is sized to MAX_PHY, if dp->bridge_count > MAX_PHY,
it will perform an out-of-bounds stack read.

> +				return dp->port[i];
> +		}
> +	}
> +
>  	return NULL;
>  }

[ ... ]

> @@ -254,12 +268,45 @@ static const struct drm_edid *
>  cdn_dp_bridge_edid_read(struct drm_bridge *bridge, struct drm_connector *connector)
>  {
>  	struct cdn_dp_device *dp = bridge_to_dp(bridge);
> -	const struct drm_edid *drm_edid;
> +	struct cdn_dp_bridge *dp_bridge = bridge_to_dp_bridge(bridge);
> +	struct cdn_dp_port *port = dp->port[dp_bridge->id];
> +	struct cdn_dp_port *prev_port;
> +	const struct drm_edid *drm_edid = NULL;
>  	int i, ret;
>  
>  	mutex_lock(&dp->lock);
> +
> +	/* More than one port is available */
> +	if (dp->bridge_count > 1 && !port->phy_enabled) {
> +		for (i = 0; i < dp->bridge_count; i++) {
> +			/* Another port already enable */
> +			if (dp->bridge_list[i] != dp_bridge && dp->bridge_list[i]->enabled)
> +				goto get_cache;
> +			/* Find already enabled port */
> +			if (dp->port[i]->phy_enabled)
> +				prev_port = dp->port[i];
> +		}
> +
> +		/* Switch to current port */
> +		if (prev_port) {

[Severity: High]
Can this lead to a kernel crash by dereferencing an uninitialized pointer?
The prev_port variable is not initialized. If no ports are currently enabled
(which is common at boot), the for loop will complete without assigning
anything to prev_port.

Then if (prev_port) evaluates garbage memory, and calling cdn_dp_switch_port
with it will cause a kernel panic.

> +			ret = cdn_dp_switch_port(dp, prev_port, port);
> +			if (ret)
> +				goto get_cache;
> +		}
> +	}

[ ... ]

> @@ -551,6 +599,54 @@ static bool cdn_dp_check_link_status(struct cdn_dp_device *dp)
>  	return drm_dp_channel_eq_ok(link_status, min(port->lanes, sink_lanes));
>  }
>  
> +static int cdn_dp_switch_port(struct cdn_dp_device *dp, struct cdn_dp_port *prev_port,
> +			      struct cdn_dp_port *port)
> +{
> +	int ret;
> +
> +	if (dp->active)
> +		return 0;

[Severity: High]
Does this incorrectly abort hardware switching? If the DP controller is
already active but currently on a different port, returning 0 skips the
actual port switch. The caller cdn_dp_bridge_edid_read() will proceed with
reading EDID from the wrong (already-active) port and caching it for the
new port.

> +
> +	ret = cdn_dp_disable_phy(dp, prev_port);
> +	if (ret)
> +		goto out;
> +	ret = cdn_dp_enable_phy(dp, port);
> +	if (ret)
> +		goto out;
> +
> +	ret = cdn_dp_get_sink_capability(dp);
> +	if (ret) {
> +		cdn_dp_disable_phy(dp, port);
> +		goto out;
> +	}
> +
> +	dp->active = true;
> +	dp->lanes = port->lanes;
> +
> +	if (!cdn_dp_check_link_status(dp)) {
> +		dev_info(dp->dev, "Connected with sink; re-train link\n");
> +
> +		ret = cdn_dp_train_link(dp);
> +		if (ret) {
> +			dev_err(dp->dev, "Training link failed: %d\n", ret);
> +			goto out;

[Severity: High]
If link training fails, this jumps to out and returns the error code, but
leaves dp->active = true. Does this trap the port in a permanently broken,
untrained state since subsequent calls to cdn_dp_switch_port() will
immediately return 0?

> +		}

[ ... ]

> @@ -639,9 +740,11 @@ static void cdn_dp_bridge_atomic_enable(struct drm_bridge *bridge, struct drm_at
>  static void cdn_dp_bridge_atomic_disable(struct drm_bridge *bridge, struct drm_atomic_state *state)
>  {
>  	struct cdn_dp_device *dp = bridge_to_dp(bridge);
> +	struct cdn_dp_bridge *dp_bridge = bridge_to_dp_bridge(bridge);
>  	int ret;
>  
>  	mutex_lock(&dp->lock);
> +	dp_bridge->enabled = false;
>  
>  	if (dp->active) {
>  		ret = cdn_dp_disable(dp);

[Severity: High]
Does this accidentally disable the active DP controller when another inactive
bridge is disabled? If dp->active is true, the entire DP controller is
disabled, without checking if the bridge being disabled (dp_bridge) is
actually the one driving the active DP port. This would break an active
Bridge A if userspace disables an inactive Bridge B.

[ ... ]

> @@ -967,28 +1085,16 @@ static int cdn_dp_pd_event(struct notifier_block *nb,
>  	return NOTIFY_DONE;
>  }
>  
> -static int cdn_dp_bind(struct device *dev, struct device *master, void *data)
> +static int cdn_bridge_add(struct device *dev,
> +			  struct drm_bridge *bridge,
> +			  struct drm_bridge *next_bridge,
> +			  struct drm_encoder *encoder)
>  {
>  	struct cdn_dp_device *dp = dev_get_drvdata(dev);
> -	struct drm_encoder *encoder;
> +	struct drm_device *drm_dev = dp->drm_dev;
> +	struct drm_bridge *last_bridge __free(drm_bridge_put) = NULL;

[Severity: High]
Will this cause a reference count underflow and a use-after-free
vulnerability? The last_bridge pointer is populated by
drm_bridge_chain_get_last_bridge(), which returns a raw pointer without
incrementing the bridge's reference count. When last_bridge goes out of
scope, the automatic drm_bridge_put() will prematurely decrement the
refcount.

>  	struct drm_connector *connector;
> -	struct cdn_dp_port *port;
> -	struct drm_device *drm_dev = data;
> -	int ret, i;
> -

[ ... ]

> +	if (next_bridge) {
> +		ret = drm_bridge_attach(encoder, next_bridge, bridge,
> +					DRM_BRIDGE_ATTACH_NO_CONNECTOR);
> +		if (ret)
> +			return ret;
> +
> +		last_bridge = drm_bridge_chain_get_last_bridge(bridge->encoder);
> +	}
> +
>  	connector = drm_bridge_connector_init(drm_dev, encoder);
>  	if (IS_ERR(connector)) {
>  		ret = PTR_ERR(connector);
> @@ -1030,8 +1145,99 @@ static int cdn_dp_bind(struct device *dev, struct device *master, void *data)
>  		return ret;
>  	}
>  
> +	if (last_bridge)
> +		connector->fwnode = fwnode_handle_get(of_fwnode_handle(last_bridge->of_node));

[Severity: Medium]
Is this assignment leaking an fwnode reference? drm_bridge_connector_init()
automatically sets connector->fwnode using the of_node of the last bridge
and acquires a reference via fwnode_handle_get(). Overwriting it here without
dropping the original reference will cause a memory leak.

> +
>  	drm_connector_attach_encoder(connector, encoder);
>  
> +	return 0;
> +}
> +
> +static int cdn_dp_parse_next_bridge_dt(struct cdn_dp_device *dp)
> +{
> +	struct device_node *np = dp->dev->of_node;
> +	struct device_node *port __free(device_node) = of_graph_get_port_by_id(np, 1);
> +	struct drm_bridge *bridge;
> +	int count = 0;
> +	int ret = 0;
> +	int i;
> +
> +	/* If device use extcon, do not use hpd bridge */
> +	for (i = 0; i < dp->ports; i++) {
> +		if (dp->port[i]->extcon) {
> +			dp->bridge_count = 1;
> +			return 0;
> +		}
> +	}
> +
> +	/* One endpoint may correspond to one next bridge. */
> +	for_each_of_graph_port_endpoint(port, dp_ep) {
> +		struct device_node *next_bridge_node __free(device_node) =
> +			of_graph_get_remote_port_parent(dp_ep);
> +
> +		bridge = of_drm_find_bridge(next_bridge_node);
> +		if (!bridge) {
> +			ret = -EPROBE_DEFER;
> +			goto out;

[Severity: High]
Does this leak the DRM bridge references acquired in earlier loop iterations?
If of_drm_find_bridge() returns NULL on a subsequent iteration, it jumps to
out and returns -EPROBE_DEFER without releasing the references previously
obtained with drm_bridge_get().

> +		}
> +
> +		dp->next_bridge_valid = true;
> +		dp->next_bridge_list[count] = drm_bridge_get(bridge);
> +		count++;

[Severity: High]
Could this overflow the next_bridge_list array? next_bridge_list is sized to
MAX_PHY (2). If a device tree specifies more than two endpoints, count will
exceed the array bounds and corrupt adjacent fields in the cdn_dp_device
struct.

> +	}
> +
> +out:
> +	dp->bridge_count = count ? count : 1;
> +	return ret;
> +}
> +
> +static int cdn_dp_bind(struct device *dev, struct device *master, void *data)
> +{

[ ... ]

> +	for (i = 0; i < dp->bridge_count; i++) {
> +		encoder = &dp->bridge_list[i]->encoder.encoder;
> +		bridge = &dp->bridge_list[i]->bridge;
> +		next_bridge = dp->next_bridge_list[i];
> +		ret = cdn_bridge_add(dev, bridge, next_bridge, encoder);
> +		if (ret)
> +			return ret;

[Severity: High]
Does this leak the bridge references acquired in cdn_dp_parse_next_bridge_dt
if cdn_bridge_add() fails? Returning directly without a cleanup path means
drm_bridge_put() is never called for dp->next_bridge_list.

> +	}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260521032854.103-1-kernel@airkyi.com?part=5

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

Re: [PATCH 3/5] phy: rockchip: phy-rockchip-typec: Add DRM AUX bridge

[Heiko Stuebner]

Hi,

Am Donnerstag, 21. Mai 2026, 05:28:52 Mitteleuropäische Sommerzeit schrieb Chaoyi Chen:
> From: Chaoyi Chen <chaoyi.chen@rock-chips.com>
> 
> Using the DRM_AUX_BRIDGE helper to create the transparent DRM bridge
> device.
> 
> Signed-off-by: Chaoyi Chen <chaoyi.chen@rock-chips.com>
> Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>

Reviewed-by: Heiko Stuebner <heiko@sntech.de>


@Vinod:
could you give this patch an Ack to go through the DRM tree please?

It is independent of any other phy changes, but needs the drm-patches 1+2
from this series, so ideally would go through the drm tree together with
them.

Thanks a lot
Heiko


> ---
>  drivers/phy/rockchip/Kconfig              |  2 ++
>  drivers/phy/rockchip/phy-rockchip-typec.c | 13 +++++++++++--
>  2 files changed, 13 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/phy/rockchip/Kconfig b/drivers/phy/rockchip/Kconfig
> index 14698571b607..9173d3b4fef4 100644
> --- a/drivers/phy/rockchip/Kconfig
> +++ b/drivers/phy/rockchip/Kconfig
> @@ -119,6 +119,8 @@ config PHY_ROCKCHIP_SNPS_PCIE3
>  config PHY_ROCKCHIP_TYPEC
>  	tristate "Rockchip TYPEC PHY Driver"
>  	depends on OF && (ARCH_ROCKCHIP || COMPILE_TEST)
> +	depends on DRM || DRM=n
> +	select DRM_AUX_BRIDGE if DRM_BRIDGE
>  	select EXTCON
>  	select GENERIC_PHY
>  	select RESET_CONTROLLER
> diff --git a/drivers/phy/rockchip/phy-rockchip-typec.c b/drivers/phy/rockchip/phy-rockchip-typec.c
> index d9701b6106d5..48070b50416e 100644
> --- a/drivers/phy/rockchip/phy-rockchip-typec.c
> +++ b/drivers/phy/rockchip/phy-rockchip-typec.c
> @@ -54,6 +54,7 @@
>  
>  #include <linux/mfd/syscon.h>
>  #include <linux/phy/phy.h>
> +#include <drm/bridge/aux-bridge.h>
>  
>  #define CMN_SSM_BANDGAP			(0x21 << 2)
>  #define CMN_SSM_BIAS			(0x22 << 2)
> @@ -1162,16 +1163,24 @@ static int rockchip_typec_phy_probe(struct platform_device *pdev)
>  
>  	for_each_available_child_of_node(np, child_np) {
>  		struct phy *phy;
> +		ret = 0;
>  
> -		if (of_node_name_eq(child_np, "dp-port"))
> +		if (of_node_name_eq(child_np, "dp-port")) {
>  			phy = devm_phy_create(dev, child_np,
>  					      &rockchip_dp_phy_ops);
> -		else if (of_node_name_eq(child_np, "usb3-port"))
> +			ret = drm_aux_bridge_register_from_node(dev, child_np);
> +		} else if (of_node_name_eq(child_np, "usb3-port"))
>  			phy = devm_phy_create(dev, child_np,
>  					      &rockchip_usb3_phy_ops);
>  		else
>  			continue;
>  
> +		if (ret) {
> +			pm_runtime_disable(dev);
> +			of_node_put(child_np);
> +			return ret;
> +		}
> +
>  		if (IS_ERR(phy)) {
>  			dev_err(dev, "failed to create phy: %pOFn\n",
>  				child_np);
> 





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