[PATCHv2] drm/i915/pps: reconcile a BIOS-enabled VDD without leaking its wakeref

[Arun R Murthy <arun.r.murthy@intel.com>]

When the BIOS leaves the eDP VDD force bit (EDP_FORCE_VDD) enabled at boot
(or resume), pps_vdd_init() adopts that state by taking an AUX power-domain
reference into intel_dp->pps.vdd_wakeref.

intel_pps_vdd_on_unlocked() decides whether it already owns a reference by
reading the live EDP_FORCE_VDD bit via edp_have_panel_vdd(). That bit can be
reset under the driver after the handover (DC states, DMC, BIOS). When it is,
the VDD-on path believes it holds nothing, overwrites vdd_wakeref with a
freshly acquired reference and orphans the adopted one. The leak surfaces at
suspend-late as:

  i915 raw-wakerefs=1 wakelocks=1 on cleanup

with the leaked wakeref's backtrace pointing at pps_vdd_init() ->
intel_pps_init() from driver probe.

Blindly reusing a held vdd_wakeref in the VDD-on path would fix the leak but
also silently paper over genuine runtime enable/disable imbalances, which is
exactly what the WARN_ON() there is meant to catch.

Instead track the handover explicitly: pps_vdd_init() sets a vdd_wakeref_boot
flag when it adopts a BIOS-enabled VDD, and intel_pps_vdd_on_unlocked() only
reuses the held reference (clearing the flag) while that flag is set. In all
other cases it keeps depending on the HW read and the WARN_ON(), so real
runtime imbalances are still flagged. The flag is cleared whenever the
reference is released so it can never outlive the reference it describes.

v2: Reworked to allow reconcile only at bootime(Jani)

Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/work_items/8477
Assisted-by: Claude:claude-3-opus
Signed-off-by: Arun R Murthy <arun.r.murthy@intel.com>
---
 .../drm/i915/display/intel_display_types.h    |  4 ++++
 drivers/gpu/drm/i915/display/intel_pps.c      | 22 ++++++++++++++++---
 2 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 20a07ea06b5e..f9f1958e8c6a 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -1727,6 +1727,10 @@ struct intel_pps {
 	unsigned long last_backlight_off;
 	ktime_t panel_power_off_time;
 	struct ref_tracker *vdd_wakeref;
+	/* vdd_wakeref was adopted from an already-on VDD at the BIOS/firmware
+	 * handover (boot/resume) and not yet reconciled into normal ownership.
+	 */
+	bool vdd_wakeref_boot;
 
 	union {
 		/*
diff --git a/drivers/gpu/drm/i915/display/intel_pps.c b/drivers/gpu/drm/i915/display/intel_pps.c
index d4c98b150fa2..415288077439 100644
--- a/drivers/gpu/drm/i915/display/intel_pps.c
+++ b/drivers/gpu/drm/i915/display/intel_pps.c
@@ -758,9 +758,22 @@ bool intel_pps_vdd_on_unlocked(struct intel_dp *intel_dp)
 	if (edp_have_panel_vdd(intel_dp))
 		return need_to_disable;
 
-	drm_WARN_ON(display->drm, intel_dp->pps.vdd_wakeref);
-	intel_dp->pps.vdd_wakeref = intel_display_power_get(display,
-							    intel_aux_power_domain(dig_port));
+	/*
+	 * pps_vdd_init() may have taken a reference at the BIOS->driver handover
+	 * for an already-on VDD whose HW force bit was since reset under us (DC
+	 * states, DMC, BIOS). Only in that boot/resume handover case reuse the
+	 * held reference instead of overwriting and leaking it. At runtime a
+	 * held wakeref here is a real imbalance, so keep asserting it and depend
+	 * on the HW read.
+	 */
+	if (intel_dp->pps.vdd_wakeref_boot) {
+		intel_dp->pps.vdd_wakeref_boot = false;
+	} else {
+		drm_WARN_ON(display->drm, intel_dp->pps.vdd_wakeref);
+		intel_dp->pps.vdd_wakeref =
+			intel_display_power_get(display,
+						intel_aux_power_domain(dig_port));
+	}
 
 	pp_stat_reg = _pp_stat_reg(intel_dp);
 	pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
@@ -861,6 +874,7 @@ static void intel_pps_vdd_off_sync_unlocked(struct intel_dp *intel_dp)
 		intel_dp_invalidate_source_oui(intel_dp);
 	}
 
+	intel_dp->pps.vdd_wakeref_boot = false;
 	intel_display_power_put(display,
 				intel_aux_power_domain(dig_port),
 				fetch_and_zero(&intel_dp->pps.vdd_wakeref));
@@ -1063,6 +1077,7 @@ void intel_pps_off_unlocked(struct intel_dp *intel_dp)
 	intel_dp_invalidate_source_oui(intel_dp);
 
 	/* We got a reference when we enabled the VDD. */
+	intel_dp->pps.vdd_wakeref_boot = false;
 	intel_display_power_put(display,
 				intel_aux_power_domain(dig_port),
 				fetch_and_zero(&intel_dp->pps.vdd_wakeref));
@@ -1337,6 +1352,7 @@ static void pps_vdd_init(struct intel_dp *intel_dp)
 	drm_WARN_ON(display->drm, intel_dp->pps.vdd_wakeref);
 	intel_dp->pps.vdd_wakeref = intel_display_power_get(display,
 							    intel_aux_power_domain(dig_port));
+	intel_dp->pps.vdd_wakeref_boot = true;
 }
 
 bool intel_pps_have_panel_power_or_vdd(struct intel_dp *intel_dp)
-- 
2.25.1