[PATCH v2] drm/i915/tc: Recover AUX channel after external TC port mode change

[ChunAn Wu <an.wu@canonical.com>]

When Fn+F4 triggers mirror mode, the BIOS/EC reconfigures a TC port
mode (e.g. DP-Alt to TBT-Alt via UCSI) without generating HPD. The
driver's cached TC mode becomes stale, so intel_dp_aux_xfer() uses
the wrong power domain and IO routing, and AUX transactions fail.

This occurs when the USB-C-to-HDMI dongle does not support TBT, so
the mode switch creates a mismatch. It also occurs with slow monitors
whose delayed HPD/DDC/EDID recovery causes the Type-C layer to settle
on a stale tbt-alt state before the dongle finishes re-negotiation.

Add intel_tc_port_aux_recover() to detect hardware/cached TC mode
divergence and reset the PHY. Wrap it with
intel_dp_aux_xfer_with_recovery() to retry with corrected settings.

Tested on Panther Lake and Lunar Lake with a BenQ HDMI monitor via
USB-C-to-HDMI dongle.

Signed-off-by: ChunAn Wu <an.wu@canonical.com>
---
 drivers/gpu/drm/i915/display/intel_dp_aux.c | 41 +++++++++--
 drivers/gpu/drm/i915/display/intel_tc.c     | 75 +++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_tc.h     |  1 +
 3 files changed, 113 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux.c b/drivers/gpu/drm/i915/display/intel_dp_aux.c
index b20ec3e589fa..d496b2231656 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_aux.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_aux.c
@@ -481,6 +481,39 @@ static u32 intel_dp_aux_xfer_flags(const struct drm_dp_aux_msg *msg)
 	return 0;
 }
 
+/**
+ * intel_dp_aux_xfer_with_recovery - AUX transfer with TC port recovery
+ * @intel_dp: the DP port
+ * @send: buffer of bytes to send
+ * @send_bytes: number of bytes to send
+ * @recv: buffer to store received reply
+ * @recv_size: maximum number of bytes to receive
+ * @aux_send_ctl_flags: extra flags for the AUX send control register
+ *
+ * Wrapper around intel_dp_aux_xfer() that attempts to recover from an
+ * external TC port mode change (e.g., dp-alt -> tbt-alt via hotkey BIOS
+ * action) when the initial AUX transfer fails. On failure, recovery is
+ * attempted once via intel_tc_port_aux_recover() before retrying.
+ *
+ * Returns: number of received bytes on success, negative error code on failure.
+ */
+static int
+intel_dp_aux_xfer_with_recovery(struct intel_dp *intel_dp,
+				const u8 *send, int send_bytes,
+				u8 *recv, int recv_size,
+				u32 aux_send_ctl_flags)
+{
+	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
+	int ret;
+
+	ret = intel_dp_aux_xfer(intel_dp, send, send_bytes, recv, recv_size,
+				aux_send_ctl_flags);
+	if (ret < 0 && intel_tc_port_aux_recover(dig_port))
+		ret = intel_dp_aux_xfer(intel_dp, send, send_bytes, recv,
+					recv_size, aux_send_ctl_flags);
+	return ret;
+}
+
 static ssize_t
 intel_dp_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
 {
@@ -508,8 +541,8 @@ intel_dp_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
 		if (msg->buffer)
 			memcpy(txbuf + HEADER_SIZE, msg->buffer, msg->size);
 
-		ret = intel_dp_aux_xfer(intel_dp, txbuf, txsize,
-					rxbuf, rxsize, flags);
+		ret = intel_dp_aux_xfer_with_recovery(intel_dp, txbuf, txsize,
+						      rxbuf, rxsize, flags);
 		if (ret > 0) {
 			msg->reply = rxbuf[0] >> 4;
 
@@ -531,8 +564,8 @@ intel_dp_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
 		if (drm_WARN_ON(display->drm, rxsize > 20))
 			return -E2BIG;
 
-		ret = intel_dp_aux_xfer(intel_dp, txbuf, txsize,
-					rxbuf, rxsize, flags);
+		ret = intel_dp_aux_xfer_with_recovery(intel_dp, txbuf, txsize,
+						      rxbuf, rxsize, flags);
 		if (ret > 0) {
 			msg->reply = rxbuf[0] >> 4;
 			/*
diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index a21dd4e3fe4c..1b23161e4eea 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -1861,6 +1861,81 @@ void intel_tc_port_link_cancel_reset_work(struct intel_digital_port *dig_port)
 	cancel_delayed_work(&tc->link_reset_work);
 }
 
+/**
+ * intel_tc_port_aux_recover - Recover AUX channel after external TC mode change
+ * @dig_port: digital port
+ *
+ * When firmware causes a TC port mode change (e.g., dp-alt -> disconnect ->
+ * tbt-alt) during a hotkey-triggered display mode switch, AUX transactions
+ * using the stale power domain and IO flags will fail with timeouts or errors.
+ * This happens because:
+ *
+ *   1. The display driver holds the TC link in dp-alt mode (link_refcount > 0)
+ *   2. Firmware (e.g., via HP WMI hotkey BIOS action) reconfigures the TC port
+ *      mode externally without notifying the display driver
+ *   3. tc->mode stays as TC_PORT_DP_ALT while HW transitions to a different
+ *      mode, invalidating the AUX power domain and IO flags used by
+ *      intel_dp_aux_xfer()
+ *
+ * This function detects the discrepancy between tc->mode and actual HW state,
+ * and re-synchronizes them via a TC PHY reset. After recovery, AUX retries
+ * will use the correct power domain and control flags.
+ *
+ * The link_refcount is temporarily cleared to allow intel_tc_port_reset_mode()
+ * to proceed without the PHY-ownership assertion that fires when link_refcount
+ * is non-zero and firmware has already released PHY ownership.
+ *
+ * Must be called outside the TC port lock (tc->lock).
+ *
+ * Returns: %true if recovery was performed and AUX can be retried,
+ *          %false if recovery was not needed or not possible.
+ */
+bool intel_tc_port_aux_recover(struct intel_digital_port *dig_port)
+{
+	struct intel_tc_port *tc;
+	struct intel_display *display;
+	bool recovered = false;
+
+	if (!intel_encoder_is_tc(&dig_port->base))
+		return false;
+
+	tc = to_tc_port(dig_port);
+	display = to_intel_display(dig_port);
+
+	mutex_lock(&tc->lock);
+
+	/*
+	 * Recovery is only needed when the link is actively held AND the HW
+	 * TC mode has diverged from the driver's cached state.
+	 */
+	if (!tc->link_refcount || !intel_tc_port_needs_reset(tc))
+		goto out;
+
+	drm_dbg_kms(display->drm,
+		    "Port %s: AUX recover: external TC mode change detected (%s -> HW), reconnecting TC PHY\n",
+		    tc->port_name, tc_port_mode_name(tc->mode));
+
+	/*
+	 * Temporarily clear link_refcount so intel_tc_port_reset_mode() can
+	 * run the PHY disconnect/connect cycle without the ownership assertion
+	 * that fires when link_refcount > 0 and firmware has already released
+	 * PHY ownership externally.
+	 */
+	tc->link_refcount = 0;
+	intel_tc_port_reset_mode(tc, 1, false);
+	tc->link_refcount = 1;
+
+	recovered = tc->mode != TC_PORT_DISCONNECTED;
+	if (!recovered)
+		drm_warn(display->drm,
+			 "Port %s: AUX recover: failed to restore TC port mode\n",
+			 tc->port_name);
+
+out:
+	mutex_unlock(&tc->lock);
+	return recovered;
+}
+
 static void __intel_tc_port_lock(struct intel_tc_port *tc,
 				 int required_lanes)
 {
diff --git a/drivers/gpu/drm/i915/display/intel_tc.h b/drivers/gpu/drm/i915/display/intel_tc.h
index 6719aea5bd58..d44998a3081a 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.h
+++ b/drivers/gpu/drm/i915/display/intel_tc.h
@@ -108,6 +108,7 @@ bool intel_tc_port_ref_held(struct intel_digital_port *dig_port);
 bool intel_tc_port_link_needs_reset(struct intel_digital_port *dig_port);
 bool intel_tc_port_link_reset(struct intel_digital_port *dig_port);
 void intel_tc_port_link_cancel_reset_work(struct intel_digital_port *dig_port);
+bool intel_tc_port_aux_recover(struct intel_digital_port *dig_port);
 
 int intel_tc_port_init(struct intel_digital_port *dig_port, bool is_legacy);
 void intel_tc_port_cleanup(struct intel_digital_port *dig_port);
-- 
2.34.1