[PATCH v2 10/15] drm/xe/irq: Protect IRQ state during wedge isolation

[Arvind Yadav <arvind.yadav@intel.com>]

Wedge isolation can disable interrupts from a worker while PM resume
enables them. If both state changes overlap, resume can leave interrupts
enabled after the device is wedged.

Add a mutex to protect updates to `irq.enabled` and the related hardware
programming. Check the wedged state while holding the same lock so the
final IRQ state remains disabled.

v2:
 - Rename pm_lock to state_lock and document the IRQ state it protects.

Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Arvind Yadav <arvind.yadav@intel.com>
---
 drivers/gpu/drm/xe/xe_device_types.h |  4 ++++
 drivers/gpu/drm/xe/xe_irq.c          | 23 ++++++++++++++++++++---
 2 files changed, 24 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index df4e274bc719..f89d539df010 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -6,6 +6,7 @@
 #ifndef _XE_DEVICE_TYPES_H_
 #define _XE_DEVICE_TYPES_H_
 
+#include <linux/mutex.h>
 #include <linux/pci.h>
 
 #include <drm/drm_device.h>
@@ -272,6 +273,9 @@ struct xe_device {
 		/** @irq.lock: lock for processing irq's on this device */
 		spinlock_t lock;
 
+		/** @irq.state_lock: Protects suspend and resume IRQ state updates */
+		struct mutex state_lock;
+
 		/** @irq.enabled: interrupts enabled on this device */
 		atomic_t enabled;
 
diff --git a/drivers/gpu/drm/xe/xe_irq.c b/drivers/gpu/drm/xe/xe_irq.c
index d314993b14a1..f7ff3fe5b843 100644
--- a/drivers/gpu/drm/xe/xe_irq.c
+++ b/drivers/gpu/drm/xe/xe_irq.c
@@ -797,8 +797,14 @@ static void irq_uninstall(void *arg)
 
 int xe_irq_init(struct xe_device *xe)
 {
+	int err;
+
 	spin_lock_init(&xe->irq.lock);
 
+	err = drmm_mutex_init(&xe->drm, &xe->irq.state_lock);
+	if (err)
+		return err;
+
 	return xe_irq_msix_init(xe);
 }
 
@@ -843,6 +849,8 @@ static void xe_irq_msi_synchronize_irq(struct xe_device *xe)
 
 void xe_irq_suspend(struct xe_device *xe)
 {
+	mutex_lock(&xe->irq.state_lock);
+
 	atomic_set(&xe->irq.enabled, 0); /* no new irqs */
 
 	/* flush irqs */
@@ -851,6 +859,8 @@ void xe_irq_suspend(struct xe_device *xe)
 	else
 		xe_irq_msi_synchronize_irq(xe);
 	xe_irq_reset(xe); /* turn irqs off */
+
+	mutex_unlock(&xe->irq.state_lock);
 }
 
 void xe_irq_resume(struct xe_device *xe)
@@ -858,10 +868,14 @@ void xe_irq_resume(struct xe_device *xe)
 	struct xe_gt *gt;
 	int id;
 
+	mutex_lock(&xe->irq.state_lock);
+
+	if (xe_device_wedged(xe))
+		goto out_unlock;
+
 	/*
-	 * lock not needed:
-	 * 1. no irq will arrive before the postinstall
-	 * 2. display is not yet resumed
+	 * irq.lock is not needed because no IRQ can arrive before
+	 * postinstall and the display has not been resumed yet.
 	 */
 	atomic_set(&xe->irq.enabled, 1);
 	xe_irq_reset(xe);
@@ -869,6 +883,9 @@ void xe_irq_resume(struct xe_device *xe)
 
 	for_each_gt(gt, xe, id)
 		xe_irq_enable_hwe(gt);
+
+out_unlock:
+	mutex_unlock(&xe->irq.state_lock);
 }
 
 /* MSI-X related definitions and functions below. */
-- 
2.43.0