diff --git a/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h b/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h
index 18d0fde8c98f..faf8d7e2c5c1 100644
--- a/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h
+++ b/drivers/gpu/drm/xe/instructions/xe_gpu_commands.h
@@ -46,6 +46,7 @@
 #define GFX_OP_PIPE_CONTROL(len)	((0x3<<29)|(0x3<<27)|(0x2<<24)|((len)-2))
 
 #define   PIPE_CONTROL0_QUEUE_DRAIN_MODE		BIT(12)
+#define	  PIPE_CONTROL0_UNTYPED_DATAPORT_CACHE_FLUSH	BIT(11)	/* gen12 */
 #define	  PIPE_CONTROL0_L3_READ_ONLY_CACHE_INVALIDATE	BIT(10)	/* gen12 */
 #define	  PIPE_CONTROL0_HDC_PIPELINE_FLUSH		BIT(9)	/* gen12 */
 
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
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 39a670e91ba7..08b4a4283e96 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -212,6 +212,7 @@ static int emit_render_cache_flush(struct xe_sched_job *job, u32 *dw, int i)
 {
 	struct xe_exec_queue *q = job->q;
 	struct xe_gt *gt = q->gt;
+	struct xe_device *xe = gt_to_xe(gt);
 	bool lacks_render = !(gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK);
 	u32 flags0, flags1;
 
@@ -220,6 +221,16 @@ static int emit_render_cache_flush(struct xe_sched_job *job, u32 *dw, int i)
 				      LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR, 0);
 
 	flags0 = PIPE_CONTROL0_HDC_PIPELINE_FLUSH;
+	/*
+	 * Prior to MTL, HDC Pipeline Flush reliably also flushes the LSC
+	 * untyped L1 dataport cache, provided HDC_CHICKEN0 is programmed
+	 * correctly. Starting with MTL that coupling no longer holds
+	 * regardless of how HDC_CHICKEN0 is programmed, but explicitly
+	 * requesting the flush via PIPE_CONTROL is itself only reliable
+	 * from Xe2 onward, so only gate it in on Xe2+.
+	 */
+	if (GRAPHICS_VERx100(xe) >= 2000)
+		flags0 |= PIPE_CONTROL0_UNTYPED_DATAPORT_CACHE_FLUSH;
 	flags1 = (PIPE_CONTROL_TILE_CACHE_FLUSH |
 		 PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
 		 PIPE_CONTROL_DEPTH_CACHE_FLUSH |