drm/xe: Guard page-fault worker with runtime PM check

During VM teardown, the VM's runtime PM reference is dropped
asynchronously, allowing the device to autosuspend while stale page
faults belonging to the now-dead VM are still queued. When the
page-fault worker later tries to ack one of these, it calls into
guc_ct_send_locked() on an already-suspended device, tripping:

  Assertion `!xe_pm_runtime_suspended(xe)` failed!
  WARNING at xe_device.c:1267 xe_device_assert_mem_access+0x11c/0x140 [xe]

A live VM/exec queue always holds a PM reference while it has
outstanding work, so if the device is suspended at ack time, the
owning context is already gone and the fault is stale.

Take a runtime PM reference across the entire pagefault
queue worker to safely deliver acks for torn-down VMs.

v3:
 - Move PM ref to the generic xe_pagefault_queue_work using
   guard(xe_pm_runtime)(xe) instead of tracking it in the GuC
   backend(Matt Brost).

v2:
 - Hold PM ref across the entire batch (begin/end) instead of per-ack.
   This prevents the device from autosuspending mid-batch, which would
   leave write_only acks written but the end flush skipped, and skip
   counter++, desyncing the cadence check.(Himal)
 - Add a comment explaining stale faults.(Himal)

Fixes: f289f7807119 ("drm/xe: Add xe_guc_pagefault layer")
Signed-off-by: Varun Gupta <varun.gupta@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Link: https://patch.msgid.link/20260907050011.497181-2-varun.gupta@intel.com
Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
(cherry picked from commit fcc2431d2213dc4d04250c4f1ae87d9c3ae0d455)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
[Rodrigo: Added xe_device struct for compatibility while cherry-picking]

2 files changed, 13 insertions, 0 deletions

diff --git a/drivers/gpu/drm/xe/xe_pagefault.c b/drivers/gpu/drm/xe/xe_pagefault.c
index dbf8f71d3328..a4986df8328d 100644
--- a/drivers/gpu/drm/xe/xe_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_pagefault.c
@@ -16,6 +16,7 @@
 #include "xe_hw_engine.h"
 #include "xe_pagefault.h"
 #include "xe_pagefault_types.h"
+#include "xe_pm.h"
 #include "xe_svm.h"
 #include "xe_trace_bo.h"
 #include "xe_vm.h"
@@ -292,9 +293,17 @@ static void xe_pagefault_queue_work(struct work_struct *w)
 {
 	struct xe_pagefault_queue *pf_queue =
 		container_of(w, typeof(*pf_queue), worker);
+	struct xe_device *xe = pf_queue->xe;
 	struct xe_pagefault pf;
 	unsigned long threshold;
 
+	/*
+	 * A live VM holds a PM reference, but a torn-down VM does not.
+	 * Guard the entire worker loop to safely drain stale faults and
+	 * prevent autosuspends from desyncing batched CT flushes.
+	 */
+	guard(xe_pm_runtime)(xe);
+
 #define USM_QUEUE_MAX_RUNTIME_MS      20
 	threshold = jiffies + msecs_to_jiffies(USM_QUEUE_MAX_RUNTIME_MS);
 
@@ -365,6 +374,7 @@ static int xe_pagefault_queue_init(struct xe_device *xe,
 	drm_dbg(&xe->drm, "xe_pagefault_entry_size=%d, total_num_eus=%d, pf_queue->size=%u",
 		xe_pagefault_entry_size(), total_num_eus, pf_queue->size);
 
+	pf_queue->xe = xe;
 	spin_lock_init(&pf_queue->lock);
 	INIT_WORK(&pf_queue->worker, xe_pagefault_queue_work);
 
diff --git a/drivers/gpu/drm/xe/xe_pagefault_types.h b/drivers/gpu/drm/xe/xe_pagefault_types.h
index c4ee625b93dd..f63a12aa0d4f 100644
--- a/drivers/gpu/drm/xe/xe_pagefault_types.h
+++ b/drivers/gpu/drm/xe/xe_pagefault_types.h
@@ -8,6 +8,7 @@
 
 #include <linux/workqueue.h>
 
+struct xe_device;
 struct xe_gt;
 struct xe_pagefault;
 
@@ -118,6 +119,8 @@ struct xe_pagefault {
  * queue to absorb the device’s worst-case number of outstanding faults.
  */
 struct xe_pagefault_queue {
+	/** @xe: Back-pointer to the Xe device */
+	struct xe_device *xe;
 	/**
 	 * @data: Data in queue containing struct xe_pagefault, protected by
 	 * @lock