[RFC PATCH v2 1/1] drm/xe: keep VM-bound WC BOs resident during reclaim

[RFC PATCH v2 1/1] drm/xe: keep VM-bound WC BOs resident during reclaim

[Neil Zhong]

On x86, restoring a backed-up write-combined (WC) buffer object can be
expensive. The restore path allocates WB pages and converts them with
set_pages_array_wc(), which performs synchronous cache and TLB flushes.

Xe currently allows its shrinker to back up the pages of a WC BO while
the BO still has GPUVA mappings created by VM_BIND. A later validation
restores the pages while holding the BO's dma-resv. The cache-attribute
conversion then serializes EXEC, VM_BIND and dma-buf users on that
reservation object.

This was observed as intermittent HDR 4K60 playback stalls on two
Panther Lake systems with 8 GiB of memory. In a pre-change reproducer,
the maximum ioctl latencies were 549 ms for XE_EXEC, 291 ms for
XE_VM_BIND and 343 ms for DMA-BUF IMPORT. ttm_tt_restore reached 80.6 ms.

Keep a non-purgeable WC BO resident while it has at least one GPUVA
mapping. Purgeable BOs are still discarded, and after the last
VM_UNBIND the BO becomes reclaimable again. Add an A/B module parameter
which can restore the old behavior.

With the change, a 21-minute capture had no XE_EXEC, XE_VM_BIND or
DMA-BUF ioctl over the 16.7 ms frame interval. Their respective maxima
were 348 us, 136 us and 20 us. The ttm_tt_restore maximum was 8.33 ms,
and the set_pages_array_wc call rate fell from 14.64/s to 0.179/s.

The change intentionally trades reclaimable memory for latency while a
WC BO remains mapped. It does not take an additional BO reference or
change teardown: VM destruction and process exit remove the GPUVA
mappings and drop their existing references. During testing,
MemAvailable remained near 3 GiB and the dma-buf working set released
five 24 MiB surfaces while playback continued.

Signed-off-by: Neil Zhong <neil.zhong@ugreen.com>
---
Changes in v2:
- Call ttm_bo_shrink_suitable() before the Xe-specific WC predicate, so
  ttm_bo->ttm is known to be non-NULL before checking its cache mode.

 drivers/gpu/drm/xe/xe_defaults.h |  1 +
 drivers/gpu/drm/xe/xe_module.c   |  6 ++++++
 drivers/gpu/drm/xe/xe_module.h   |  2 +-
 drivers/gpu/drm/xe/xe_shrinker.c | 28 ++++++++++++++++++++++++++++
 4 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_defaults.h b/drivers/gpu/drm/xe/xe_defaults.h
index c8ae1d5f..645e289f 100644
--- a/drivers/gpu/drm/xe/xe_defaults.h
+++ b/drivers/gpu/drm/xe/xe_defaults.h
@@ -22,5 +22,6 @@
 #define XE_DEFAULT_WEDGED_MODE			XE_WEDGED_MODE_UPON_CRITICAL_ERROR
 #define XE_DEFAULT_WEDGED_MODE_STR		"upon-critical-error"
 #define XE_DEFAULT_SVM_NOTIFIER_SIZE		512
+#define XE_DEFAULT_ALLOW_BOUND_WC_SHRINK	false
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c
index 848d6526..67bcaf54 100644
--- a/drivers/gpu/drm/xe/xe_module.c
+++ b/drivers/gpu/drm/xe/xe_module.c
@@ -22,6 +22,7 @@
 #include "xe_sched_job.h"
 
 struct xe_modparam xe_modparam = {
+	.allow_bound_wc_shrink = XE_DEFAULT_ALLOW_BOUND_WC_SHRINK,
 	.probe_display =	XE_DEFAULT_PROBE_DISPLAY,
 	.guc_log_level =	XE_DEFAULT_GUC_LOG_LEVEL,
 	.force_probe =		XE_DEFAULT_FORCE_PROBE,
@@ -33,6 +34,11 @@ struct xe_modparam xe_modparam = {
 	/* the rest are 0 by default */
 };
 
+module_param_named(allow_bound_wc_shrink, xe_modparam.allow_bound_wc_shrink,
+		   bool, 0600);
+MODULE_PARM_DESC(allow_bound_wc_shrink,
+		 "Permit reclaim of VM-bound write-combined BOs");
+
 module_param_named(svm_notifier_size, xe_modparam.svm_notifier_size, uint, 0600);
 MODULE_PARM_DESC(svm_notifier_size, "Set the svm notifier size in MiB, must be power of 2 "
 		 "[default=" __stringify(XE_DEFAULT_SVM_NOTIFIER_SIZE) "]");
diff --git a/drivers/gpu/drm/xe/xe_module.h b/drivers/gpu/drm/xe/xe_module.h
index a0eb7db0..bf2c49ce 100644
--- a/drivers/gpu/drm/xe/xe_module.h
+++ b/drivers/gpu/drm/xe/xe_module.h
@@ -12,6 +12,7 @@ struct work_struct;
 
 /* Module modprobe variables */
 struct xe_modparam {
+	bool allow_bound_wc_shrink;
 	bool probe_display;
 	int force_vram_bar_size;
 	int guc_log_level;
@@ -32,4 +33,3 @@ bool xe_destroy_wq_queue(struct work_struct *work);
 void xe_destroy_wq_flush(void);
 
 #endif
-
diff --git a/drivers/gpu/drm/xe/xe_shrinker.c b/drivers/gpu/drm/xe/xe_shrinker.c
index 83374cd5..edbc22b2 100644
--- a/drivers/gpu/drm/xe/xe_shrinker.c
+++ b/drivers/gpu/drm/xe/xe_shrinker.c
@@ -11,6 +11,7 @@
 #include <drm/ttm/ttm_tt.h>
 
 #include "xe_bo.h"
+#include "xe_module.h"
 #include "xe_pm.h"
 #include "xe_shrinker.h"
 
@@ -54,6 +55,30 @@ xe_shrinker_mod_pages(struct xe_shrinker *shrinker, long shrinkable, long purgea
 	write_unlock(&shrinker->lock);
 }
 
+static bool xe_shrinker_skip_bound_wc(struct ttm_buffer_object *ttm_bo,
+				      const struct xe_bo_shrink_flags flags)
+{
+	struct xe_bo *bo;
+
+	if (flags.purge || xe_modparam.allow_bound_wc_shrink ||
+	    !xe_bo_is_xe_bo(ttm_bo))
+		return false;
+
+	bo = ttm_to_xe_bo(ttm_bo);
+
+	/*
+	 * Restoring a backed-up WC BO changes freshly allocated WB pages to WC.
+	 * On x86 that runs CPA cache/TLB flushes synchronously while validation
+	 * holds this BO's dma-resv. A VM-bound BO is also likely to be reused by
+	 * a following EXEC, so reclaiming it can turn moderate memory pressure
+	 * into a multi-client reservation-lock stall. Keep that working set
+	 * resident; purgeable objects and objects after VM_UNBIND remain
+	 * reclaimable.
+	 */
+	return ttm_bo->ttm->caching == ttm_write_combined &&
+		xe_bo_is_vm_bound(bo);
+}
+
 static s64 __xe_shrinker_walk(struct xe_device *xe,
 			      struct ttm_operation_ctx *ctx,
 			      const struct xe_bo_shrink_flags flags,
@@ -78,6 +103,9 @@ static s64 __xe_shrinker_walk(struct xe_device *xe,
 			if (!ttm_bo_shrink_suitable(ttm_bo, ctx))
 				continue;
 
+			if (xe_shrinker_skip_bound_wc(ttm_bo, flags))
+				continue;
+
 			lret = xe_bo_shrink(ctx, ttm_bo, flags, scanned);
 			if (lret < 0)
 				return lret;
-- 
2.50.1 (Apple Git-155)

✗ LGCI.VerificationFailed: failure for series starting with [RFC,v2,1/1] drm/xe: keep VM-bound WC BOs resident during reclaim

[Patchwork]

== Series Details ==

Series: series starting with [RFC,v2,1/1] drm/xe: keep VM-bound WC BOs resident during reclaim
URL   : https://patchwork.freedesktop.org/series/171386/
State : failure

== Summary ==

Series author address 'neil.zhong@ugreen.com' is not on the allowlist, which prevents CI from being automatically triggered.
If you want CI to run for this series, ask Patchwork project owners to click 'retest' on the series in Patchwork.
Exception occurred during validation, bailing out!
Build URL: http://intel-gfx-ci-public.igk.intel.com:8080/job/xe_pw_trigger/1232455/ (on master)

Re: [RFC PATCH v2 1/1] drm/xe: keep VM-bound WC BOs resident during reclaim

[Matthew Brost]

On Tue, Jul 28, 2026 at 02:55:12PM +0800, Neil Zhong wrote:
> On x86, restoring a backed-up write-combined (WC) buffer object can be
> expensive. The restore path allocates WB pages and converts them with
> set_pages_array_wc(), which performs synchronous cache and TLB flushes.
> 
> Xe currently allows its shrinker to back up the pages of a WC BO while
> the BO still has GPUVA mappings created by VM_BIND. A later validation
> restores the pages while holding the BO's dma-resv. The cache-attribute
> conversion then serializes EXEC, VM_BIND and dma-buf users on that
> reservation object.
> 
> This was observed as intermittent HDR 4K60 playback stalls on two
> Panther Lake systems with 8 GiB of memory. In a pre-change reproducer,
> the maximum ioctl latencies were 549 ms for XE_EXEC, 291 ms for
> XE_VM_BIND and 343 ms for DMA-BUF IMPORT. ttm_tt_restore reached 80.6 ms.
> 
> Keep a non-purgeable WC BO resident while it has at least one GPUVA
> mapping. Purgeable BOs are still discarded, and after the last
> VM_UNBIND the BO becomes reclaimable again. Add an A/B module parameter
> which can restore the old behavior.
> 
> With the change, a 21-minute capture had no XE_EXEC, XE_VM_BIND or
> DMA-BUF ioctl over the 16.7 ms frame interval. Their respective maxima
> were 348 us, 136 us and 20 us. The ttm_tt_restore maximum was 8.33 ms,
> and the set_pages_array_wc call rate fell from 14.64/s to 0.179/s.
> 
> The change intentionally trades reclaimable memory for latency while a
> WC BO remains mapped. It does not take an additional BO reference or
> change teardown: VM destruction and process exit remove the GPUVA
> mappings and drop their existing references. During testing,
> MemAvailable remained near 3 GiB and the dma-buf working set released
> five 24 MiB surfaces while playback continued.
> 

I think integrating WC into the TTM priority scheme for LRU-based
eviction is probably the right approach rather than blocking WC from
shrinking. I have a series on the list that implements TTM priorities
for Xe [1], but WC isn't currently taken into account. It probably
should be, although I think we'd need more than four TTM priority levels
to do it properly.

If I respin that series with some WC awareness, would you be willing to
give it a try?

Also btw, we are aware of bunch shrinker / memory pressure /
fragmentation issues with Xe on iGPU devices and are actively working on
this, here are a couple more examples of in flight work [2] [3], here
some which have been merged [4] [5] [6].

Matt

[1] https://patchwork.freedesktop.org/series/170454/
[2] https://patchwork.freedesktop.org/series/170216/
[3] https://patchwork.freedesktop.org/series/168651/
[4] https://patchwork.freedesktop.org/series/165878/
[5] https://patchwork.freedesktop.org/series/168649/
[6] https://patchwork.freedesktop.org/series/168466/

> Signed-off-by: Neil Zhong <neil.zhong@ugreen.com>
> ---
> Changes in v2:
> - Call ttm_bo_shrink_suitable() before the Xe-specific WC predicate, so
>   ttm_bo->ttm is known to be non-NULL before checking its cache mode.
> 
>  drivers/gpu/drm/xe/xe_defaults.h |  1 +
>  drivers/gpu/drm/xe/xe_module.c   |  6 ++++++
>  drivers/gpu/drm/xe/xe_module.h   |  2 +-
>  drivers/gpu/drm/xe/xe_shrinker.c | 28 ++++++++++++++++++++++++++++
>  4 files changed, 36 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_defaults.h b/drivers/gpu/drm/xe/xe_defaults.h
> index c8ae1d5f..645e289f 100644
> --- a/drivers/gpu/drm/xe/xe_defaults.h
> +++ b/drivers/gpu/drm/xe/xe_defaults.h
> @@ -22,5 +22,6 @@
>  #define XE_DEFAULT_WEDGED_MODE			XE_WEDGED_MODE_UPON_CRITICAL_ERROR
>  #define XE_DEFAULT_WEDGED_MODE_STR		"upon-critical-error"
>  #define XE_DEFAULT_SVM_NOTIFIER_SIZE		512
> +#define XE_DEFAULT_ALLOW_BOUND_WC_SHRINK	false
>  
>  #endif
> diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c
> index 848d6526..67bcaf54 100644
> --- a/drivers/gpu/drm/xe/xe_module.c
> +++ b/drivers/gpu/drm/xe/xe_module.c
> @@ -22,6 +22,7 @@
>  #include "xe_sched_job.h"
>  
>  struct xe_modparam xe_modparam = {
> +	.allow_bound_wc_shrink = XE_DEFAULT_ALLOW_BOUND_WC_SHRINK,
>  	.probe_display =	XE_DEFAULT_PROBE_DISPLAY,
>  	.guc_log_level =	XE_DEFAULT_GUC_LOG_LEVEL,
>  	.force_probe =		XE_DEFAULT_FORCE_PROBE,
> @@ -33,6 +34,11 @@ struct xe_modparam xe_modparam = {
>  	/* the rest are 0 by default */
>  };
>  
> +module_param_named(allow_bound_wc_shrink, xe_modparam.allow_bound_wc_shrink,
> +		   bool, 0600);
> +MODULE_PARM_DESC(allow_bound_wc_shrink,
> +		 "Permit reclaim of VM-bound write-combined BOs");
> +
>  module_param_named(svm_notifier_size, xe_modparam.svm_notifier_size, uint, 0600);
>  MODULE_PARM_DESC(svm_notifier_size, "Set the svm notifier size in MiB, must be power of 2 "
>  		 "[default=" __stringify(XE_DEFAULT_SVM_NOTIFIER_SIZE) "]");
> diff --git a/drivers/gpu/drm/xe/xe_module.h b/drivers/gpu/drm/xe/xe_module.h
> index a0eb7db0..bf2c49ce 100644
> --- a/drivers/gpu/drm/xe/xe_module.h
> +++ b/drivers/gpu/drm/xe/xe_module.h
> @@ -12,6 +12,7 @@ struct work_struct;
>  
>  /* Module modprobe variables */
>  struct xe_modparam {
> +	bool allow_bound_wc_shrink;
>  	bool probe_display;
>  	int force_vram_bar_size;
>  	int guc_log_level;
> @@ -32,4 +33,3 @@ bool xe_destroy_wq_queue(struct work_struct *work);
>  void xe_destroy_wq_flush(void);
>  
>  #endif
> -
> diff --git a/drivers/gpu/drm/xe/xe_shrinker.c b/drivers/gpu/drm/xe/xe_shrinker.c
> index 83374cd5..edbc22b2 100644
> --- a/drivers/gpu/drm/xe/xe_shrinker.c
> +++ b/drivers/gpu/drm/xe/xe_shrinker.c
> @@ -11,6 +11,7 @@
>  #include <drm/ttm/ttm_tt.h>
>  
>  #include "xe_bo.h"
> +#include "xe_module.h"
>  #include "xe_pm.h"
>  #include "xe_shrinker.h"
>  
> @@ -54,6 +55,30 @@ xe_shrinker_mod_pages(struct xe_shrinker *shrinker, long shrinkable, long purgea
>  	write_unlock(&shrinker->lock);
>  }
>  
> +static bool xe_shrinker_skip_bound_wc(struct ttm_buffer_object *ttm_bo,
> +				      const struct xe_bo_shrink_flags flags)
> +{
> +	struct xe_bo *bo;
> +
> +	if (flags.purge || xe_modparam.allow_bound_wc_shrink ||
> +	    !xe_bo_is_xe_bo(ttm_bo))
> +		return false;
> +
> +	bo = ttm_to_xe_bo(ttm_bo);
> +
> +	/*
> +	 * Restoring a backed-up WC BO changes freshly allocated WB pages to WC.
> +	 * On x86 that runs CPA cache/TLB flushes synchronously while validation
> +	 * holds this BO's dma-resv. A VM-bound BO is also likely to be reused by
> +	 * a following EXEC, so reclaiming it can turn moderate memory pressure
> +	 * into a multi-client reservation-lock stall. Keep that working set
> +	 * resident; purgeable objects and objects after VM_UNBIND remain
> +	 * reclaimable.
> +	 */
> +	return ttm_bo->ttm->caching == ttm_write_combined &&
> +		xe_bo_is_vm_bound(bo);
> +}
> +
>  static s64 __xe_shrinker_walk(struct xe_device *xe,
>  			      struct ttm_operation_ctx *ctx,
>  			      const struct xe_bo_shrink_flags flags,
> @@ -78,6 +103,9 @@ static s64 __xe_shrinker_walk(struct xe_device *xe,
>  			if (!ttm_bo_shrink_suitable(ttm_bo, ctx))
>  				continue;
>  
> +			if (xe_shrinker_skip_bound_wc(ttm_bo, flags))
> +				continue;
> +
>  			lret = xe_bo_shrink(ctx, ttm_bo, flags, scanned);
>  			if (lret < 0)
>  				return lret;
> -- 
> 2.50.1 (Apple Git-155)

✗ LGCI.VerificationFailed: failure for series starting with [RFC,v2,1/1] drm/xe: keep VM-bound WC BOs resident during reclaim (rev4)

[Patchwork]

== Series Details ==

Series: series starting with [RFC,v2,1/1] drm/xe: keep VM-bound WC BOs resident during reclaim (rev4)
URL   : https://patchwork.freedesktop.org/series/171386/
State : failure

== Summary ==

Series author address 'neil.zhong@ugreen.com' is not on the allowlist, which prevents CI from being automatically triggered.
If you want CI to run for this series, ask Patchwork project owners to click 'retest' on the series in Patchwork.
Exception occurred during validation, bailing out!
Build URL: http://intel-gfx-ci-public.igk.intel.com:8080/job/xe_pw_trigger/1232615/ (on master)

Re: [RFC PATCH v2 1/1] drm/xe: keep VM-bound WC BOs resident during reclaim

[Matthew Brost]

On Thu, Jul 30, 2026 at 06:36:46PM -0700, Matthew Brost wrote:
> On Tue, Jul 28, 2026 at 02:55:12PM +0800, Neil Zhong wrote:
> > On x86, restoring a backed-up write-combined (WC) buffer object can be
> > expensive. The restore path allocates WB pages and converts them with
> > set_pages_array_wc(), which performs synchronous cache and TLB flushes.
> > 
> > Xe currently allows its shrinker to back up the pages of a WC BO while
> > the BO still has GPUVA mappings created by VM_BIND. A later validation
> > restores the pages while holding the BO's dma-resv. The cache-attribute
> > conversion then serializes EXEC, VM_BIND and dma-buf users on that
> > reservation object.
> > 
> > This was observed as intermittent HDR 4K60 playback stalls on two
> > Panther Lake systems with 8 GiB of memory. In a pre-change reproducer,
> > the maximum ioctl latencies were 549 ms for XE_EXEC, 291 ms for
> > XE_VM_BIND and 343 ms for DMA-BUF IMPORT. ttm_tt_restore reached 80.6 ms.
> > 
> > Keep a non-purgeable WC BO resident while it has at least one GPUVA
> > mapping. Purgeable BOs are still discarded, and after the last
> > VM_UNBIND the BO becomes reclaimable again. Add an A/B module parameter
> > which can restore the old behavior.
> > 
> > With the change, a 21-minute capture had no XE_EXEC, XE_VM_BIND or
> > DMA-BUF ioctl over the 16.7 ms frame interval. Their respective maxima
> > were 348 us, 136 us and 20 us. The ttm_tt_restore maximum was 8.33 ms,
> > and the set_pages_array_wc call rate fell from 14.64/s to 0.179/s.
> > 
> > The change intentionally trades reclaimable memory for latency while a
> > WC BO remains mapped. It does not take an additional BO reference or
> > change teardown: VM destruction and process exit remove the GPUVA
> > mappings and drop their existing references. During testing,
> > MemAvailable remained near 3 GiB and the dma-buf working set released
> > five 24 MiB surfaces while playback continued.
> > 
> 
> I think integrating WC into the TTM priority scheme for LRU-based
> eviction is probably the right approach rather than blocking WC from
> shrinking. I have a series on the list that implements TTM priorities
> for Xe [1], but WC isn't currently taken into account. It probably
> should be, although I think we'd need more than four TTM priority levels
> to do it properly.
> 
> If I respin that series with some WC awareness, would you be willing to
> give it a try?
> 

So I posted another rev priority changes to account WB vs WB/UC:

[7] https://patchwork.freedesktop.org/series/170454/
gitlab branch: https://gitlab.freedesktop.org/mbrost/xe-kernel-driver-svn-perf-6-15-2025/-/commits/priority_fixes.v4

But after reading this a bit more carefully, I suspect the real issue is
that fragmentation is driving shrinker activity. Your changes more or
less prevent Xe from shrinking its working set, since nearly every
buffer is WC. In my opinion, that behavior is reasonable for
fragmentation-driven reclaim, but it is much less appropriate in genuine
low-memory situations.

This is also a known issue for us. We most recently attempted to address
it here [8], but the fix was blocked by the shrinker maintainer - the
same has happened to other proposed solutions as well. We have several
downstream customers carrying non-upstream fixes to work around this
problem too...

[8] https://patchwork.freedesktop.org/series/168651/

I guess if it isn't too much trouble could you test:

1. Priority changes [7]
2. Avoid shrinking working sets on fragmentation [8]
3. Both [7], [8]

Matt

> Also btw, we are aware of bunch shrinker / memory pressure /
> fragmentation issues with Xe on iGPU devices and are actively working on
> this, here are a couple more examples of in flight work [2] [3], here
> some which have been merged [4] [5] [6].
> 
> Matt
> 
> [1] https://patchwork.freedesktop.org/series/170454/
> [2] https://patchwork.freedesktop.org/series/170216/
> [3] https://patchwork.freedesktop.org/series/168651/
> [4] https://patchwork.freedesktop.org/series/165878/
> [5] https://patchwork.freedesktop.org/series/168649/
> [6] https://patchwork.freedesktop.org/series/168466/
> 
> > Signed-off-by: Neil Zhong <neil.zhong@ugreen.com>
> > ---
> > Changes in v2:
> > - Call ttm_bo_shrink_suitable() before the Xe-specific WC predicate, so
> >   ttm_bo->ttm is known to be non-NULL before checking its cache mode.
> > 
> >  drivers/gpu/drm/xe/xe_defaults.h |  1 +
> >  drivers/gpu/drm/xe/xe_module.c   |  6 ++++++
> >  drivers/gpu/drm/xe/xe_module.h   |  2 +-
> >  drivers/gpu/drm/xe/xe_shrinker.c | 28 ++++++++++++++++++++++++++++
> >  4 files changed, 36 insertions(+), 1 deletion(-)
> > 
> > diff --git a/drivers/gpu/drm/xe/xe_defaults.h b/drivers/gpu/drm/xe/xe_defaults.h
> > index c8ae1d5f..645e289f 100644
> > --- a/drivers/gpu/drm/xe/xe_defaults.h
> > +++ b/drivers/gpu/drm/xe/xe_defaults.h
> > @@ -22,5 +22,6 @@
> >  #define XE_DEFAULT_WEDGED_MODE			XE_WEDGED_MODE_UPON_CRITICAL_ERROR
> >  #define XE_DEFAULT_WEDGED_MODE_STR		"upon-critical-error"
> >  #define XE_DEFAULT_SVM_NOTIFIER_SIZE		512
> > +#define XE_DEFAULT_ALLOW_BOUND_WC_SHRINK	false
> >  
> >  #endif
> > diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c
> > index 848d6526..67bcaf54 100644
> > --- a/drivers/gpu/drm/xe/xe_module.c
> > +++ b/drivers/gpu/drm/xe/xe_module.c
> > @@ -22,6 +22,7 @@
> >  #include "xe_sched_job.h"
> >  
> >  struct xe_modparam xe_modparam = {
> > +	.allow_bound_wc_shrink = XE_DEFAULT_ALLOW_BOUND_WC_SHRINK,
> >  	.probe_display =	XE_DEFAULT_PROBE_DISPLAY,
> >  	.guc_log_level =	XE_DEFAULT_GUC_LOG_LEVEL,
> >  	.force_probe =		XE_DEFAULT_FORCE_PROBE,
> > @@ -33,6 +34,11 @@ struct xe_modparam xe_modparam = {
> >  	/* the rest are 0 by default */
> >  };
> >  
> > +module_param_named(allow_bound_wc_shrink, xe_modparam.allow_bound_wc_shrink,
> > +		   bool, 0600);
> > +MODULE_PARM_DESC(allow_bound_wc_shrink,
> > +		 "Permit reclaim of VM-bound write-combined BOs");
> > +
> >  module_param_named(svm_notifier_size, xe_modparam.svm_notifier_size, uint, 0600);
> >  MODULE_PARM_DESC(svm_notifier_size, "Set the svm notifier size in MiB, must be power of 2 "
> >  		 "[default=" __stringify(XE_DEFAULT_SVM_NOTIFIER_SIZE) "]");
> > diff --git a/drivers/gpu/drm/xe/xe_module.h b/drivers/gpu/drm/xe/xe_module.h
> > index a0eb7db0..bf2c49ce 100644
> > --- a/drivers/gpu/drm/xe/xe_module.h
> > +++ b/drivers/gpu/drm/xe/xe_module.h
> > @@ -12,6 +12,7 @@ struct work_struct;
> >  
> >  /* Module modprobe variables */
> >  struct xe_modparam {
> > +	bool allow_bound_wc_shrink;
> >  	bool probe_display;
> >  	int force_vram_bar_size;
> >  	int guc_log_level;
> > @@ -32,4 +33,3 @@ bool xe_destroy_wq_queue(struct work_struct *work);
> >  void xe_destroy_wq_flush(void);
> >  
> >  #endif
> > -
> > diff --git a/drivers/gpu/drm/xe/xe_shrinker.c b/drivers/gpu/drm/xe/xe_shrinker.c
> > index 83374cd5..edbc22b2 100644
> > --- a/drivers/gpu/drm/xe/xe_shrinker.c
> > +++ b/drivers/gpu/drm/xe/xe_shrinker.c
> > @@ -11,6 +11,7 @@
> >  #include <drm/ttm/ttm_tt.h>
> >  
> >  #include "xe_bo.h"
> > +#include "xe_module.h"
> >  #include "xe_pm.h"
> >  #include "xe_shrinker.h"
> >  
> > @@ -54,6 +55,30 @@ xe_shrinker_mod_pages(struct xe_shrinker *shrinker, long shrinkable, long purgea
> >  	write_unlock(&shrinker->lock);
> >  }
> >  
> > +static bool xe_shrinker_skip_bound_wc(struct ttm_buffer_object *ttm_bo,
> > +				      const struct xe_bo_shrink_flags flags)
> > +{
> > +	struct xe_bo *bo;
> > +
> > +	if (flags.purge || xe_modparam.allow_bound_wc_shrink ||
> > +	    !xe_bo_is_xe_bo(ttm_bo))
> > +		return false;
> > +
> > +	bo = ttm_to_xe_bo(ttm_bo);
> > +
> > +	/*
> > +	 * Restoring a backed-up WC BO changes freshly allocated WB pages to WC.
> > +	 * On x86 that runs CPA cache/TLB flushes synchronously while validation
> > +	 * holds this BO's dma-resv. A VM-bound BO is also likely to be reused by
> > +	 * a following EXEC, so reclaiming it can turn moderate memory pressure
> > +	 * into a multi-client reservation-lock stall. Keep that working set
> > +	 * resident; purgeable objects and objects after VM_UNBIND remain
> > +	 * reclaimable.
> > +	 */
> > +	return ttm_bo->ttm->caching == ttm_write_combined &&
> > +		xe_bo_is_vm_bound(bo);
> > +}
> > +
> >  static s64 __xe_shrinker_walk(struct xe_device *xe,
> >  			      struct ttm_operation_ctx *ctx,
> >  			      const struct xe_bo_shrink_flags flags,
> > @@ -78,6 +103,9 @@ static s64 __xe_shrinker_walk(struct xe_device *xe,
> >  			if (!ttm_bo_shrink_suitable(ttm_bo, ctx))
> >  				continue;
> >  
> > +			if (xe_shrinker_skip_bound_wc(ttm_bo, flags))
> > +				continue;
> > +
> >  			lret = xe_bo_shrink(ctx, ttm_bo, flags, scanned);
> >  			if (lret < 0)
> >  				return lret;
> > -- 
> > 2.50.1 (Apple Git-155)