All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v3 07/19] drm/xe/vm: Add a helper xe_vm_range_tilemask_tlb_invalidation()
  2025-05-27 16:39 [PATCH v3 00/19] MADVISE FOR XE Himal Prasad Ghimiray
@ 2025-05-27 16:39 ` Himal Prasad Ghimiray
  2025-05-28 23:12   ` Matthew Brost
  0 siblings, 1 reply; 4+ messages in thread
From: Himal Prasad Ghimiray @ 2025-05-27 16:39 UTC (permalink / raw)
  To: intel-xe; +Cc: Himal Prasad Ghimiray, Matthew Brost

Introduce xe_vm_range_tilemask_tlb_invalidation(), which issues a TLB
invalidation for a specified address range across GTs indicated by a
tilemask.

Suggested-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_svm.c |  43 +--------------
 drivers/gpu/drm/xe/xe_vm.c  | 103 ++++++++++++++++++++++++------------
 drivers/gpu/drm/xe/xe_vm.h  |   3 ++
 3 files changed, 75 insertions(+), 74 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 871ac81bb04a..59e73187114d 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -167,14 +167,9 @@ static void xe_svm_invalidate(struct drm_gpusvm *gpusvm,
 {
 	struct xe_vm *vm = gpusvm_to_vm(gpusvm);
 	struct xe_device *xe = vm->xe;
-	struct xe_tile *tile;
 	struct drm_gpusvm_range *r, *first;
-	struct xe_gt_tlb_invalidation_fence
-		fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
 	u64 adj_start = mmu_range->start, adj_end = mmu_range->end;
 	u8 tile_mask = 0;
-	u8 id;
-	u32 fence_id = 0;
 	long err;
 
 	xe_svm_assert_in_notifier(vm);
@@ -220,42 +215,8 @@ static void xe_svm_invalidate(struct drm_gpusvm *gpusvm,
 
 	xe_device_wmb(xe);
 
-	for_each_tile(tile, xe, id) {
-		if (tile_mask & BIT(id)) {
-			int err;
-
-			xe_gt_tlb_invalidation_fence_init(tile->primary_gt,
-							  &fence[fence_id], true);
-
-			err = xe_gt_tlb_invalidation_range(tile->primary_gt,
-							   &fence[fence_id],
-							   adj_start,
-							   adj_end,
-							   vm->usm.asid);
-			if (WARN_ON_ONCE(err < 0))
-				goto wait;
-			++fence_id;
-
-			if (!tile->media_gt)
-				continue;
-
-			xe_gt_tlb_invalidation_fence_init(tile->media_gt,
-							  &fence[fence_id], true);
-
-			err = xe_gt_tlb_invalidation_range(tile->media_gt,
-							   &fence[fence_id],
-							   adj_start,
-							   adj_end,
-							   vm->usm.asid);
-			if (WARN_ON_ONCE(err < 0))
-				goto wait;
-			++fence_id;
-		}
-	}
-
-wait:
-	for (id = 0; id < fence_id; ++id)
-		xe_gt_tlb_invalidation_fence_wait(&fence[id]);
+	err = xe_vm_range_tilemask_tlb_invalidation(vm, adj_start, adj_end, tile_mask);
+	XE_WARN_ON(err);
 
 range_notifier_event_end:
 	r = first;
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index de6ecff237a6..d60b711e97e9 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -3851,6 +3851,68 @@ void xe_vm_unlock(struct xe_vm *vm)
 	dma_resv_unlock(xe_vm_resv(vm));
 }
 
+/**
+ * xe_vm_range_tilemask_tlb_invalidation - Issue a TLB invalidation on this tilemask for an
+ * address range
+ * @vm: The VM
+ * @start: start address
+ * @end: end address
+ * @tile_mask: mask for which gt's issue tlb invalidation
+ *
+ * Issue a range based TLB invalidation for gt's in tilemask
+ *
+ * Returns 0 for success, negative error code otherwise.
+ */
+int xe_vm_range_tilemask_tlb_invalidation(struct xe_vm *vm, u64 start,
+					  u64 end, u8 tile_mask)
+{
+	struct xe_gt_tlb_invalidation_fence fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
+	struct xe_tile *tile;
+	u32 fence_id = 0;
+	u8 id;
+	int err;
+
+	if (!tile_mask)
+		return 0;
+
+	for_each_tile(tile, vm->xe, id) {
+		if (tile_mask & BIT(id)) {
+			xe_gt_tlb_invalidation_fence_init(tile->primary_gt,
+							  &fence[fence_id], true);
+
+			err = xe_gt_tlb_invalidation_range(tile->primary_gt,
+							   &fence[fence_id],
+							   start,
+							   end,
+							   vm->usm.asid);
+			if (WARN_ON_ONCE(err < 0))
+				goto wait;
+			++fence_id;
+
+			if (!tile->media_gt)
+				continue;
+
+			xe_gt_tlb_invalidation_fence_init(tile->media_gt,
+							  &fence[fence_id], true);
+
+			err = xe_gt_tlb_invalidation_range(tile->media_gt,
+							   &fence[fence_id],
+							   start,
+							   end,
+							   vm->usm.asid);
+			if (WARN_ON_ONCE(err < 0))
+				goto wait;
+			++fence_id;
+		}
+	}
+
+wait:
+	for (id = 0; id < fence_id; ++id)
+		xe_gt_tlb_invalidation_fence_wait(&fence[id]);
+
+	return err;
+}
+
 /**
  * xe_vm_invalidate_vma - invalidate GPU mappings for VMA without a lock
  * @vma: VMA to invalidate
@@ -3865,11 +3927,9 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 {
 	struct xe_device *xe = xe_vma_vm(vma)->xe;
 	struct xe_tile *tile;
-	struct xe_gt_tlb_invalidation_fence
-		fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
-	u8 id;
-	u32 fence_id = 0;
+	u8 tile_mask = 0;
 	int ret = 0;
+	u8 id;
 
 	xe_assert(xe, !xe_vma_is_null(vma));
 	xe_assert(xe, !xe_vma_is_cpu_addr_mirror(vma));
@@ -3893,37 +3953,14 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 		}
 	}
 
-	for_each_tile(tile, xe, id) {
-		if (xe_pt_zap_ptes(tile, vma)) {
-			xe_device_wmb(xe);
-			xe_gt_tlb_invalidation_fence_init(tile->primary_gt,
-							  &fence[fence_id],
-							  true);
-
-			ret = xe_gt_tlb_invalidation_vma(tile->primary_gt,
-							 &fence[fence_id], vma);
-			if (ret)
-				goto wait;
-			++fence_id;
+	for_each_tile(tile, xe, id)
+		if (xe_pt_zap_ptes(tile, vma))
+			tile_mask |= BIT(id);
 
-			if (!tile->media_gt)
-				continue;
+	xe_device_wmb(xe);
 
-			xe_gt_tlb_invalidation_fence_init(tile->media_gt,
-							  &fence[fence_id],
-							  true);
-
-			ret = xe_gt_tlb_invalidation_vma(tile->media_gt,
-							 &fence[fence_id], vma);
-			if (ret)
-				goto wait;
-			++fence_id;
-		}
-	}
-
-wait:
-	for (id = 0; id < fence_id; ++id)
-		xe_gt_tlb_invalidation_fence_wait(&fence[id]);
+	ret = xe_vm_range_tilemask_tlb_invalidation(xe_vma_vm(vma), xe_vma_start(vma),
+						    xe_vma_end(vma), tile_mask);
 
 	vma->tile_invalidated = vma->tile_mask;
 
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 99e164852f63..1ef98113fa5b 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -228,6 +228,9 @@ struct dma_fence *xe_vm_range_rebind(struct xe_vm *vm,
 struct dma_fence *xe_vm_range_unbind(struct xe_vm *vm,
 				     struct xe_svm_range *range);
 
+int xe_vm_range_tilemask_tlb_invalidation(struct xe_vm *vm, u64 start,
+					  u64 end, u8 tile_mask);
+
 int xe_vm_invalidate_vma(struct xe_vma *vma);
 
 int xe_vm_validate_protected(struct xe_vm *vm);
-- 
2.34.1


^ permalink raw reply related	[flat|nested] 4+ messages in thread

* Re: [PATCH v3 07/19] drm/xe/vm: Add a helper xe_vm_range_tilemask_tlb_invalidation()
  2025-05-27 16:39 ` [PATCH v3 07/19] drm/xe/vm: Add a helper xe_vm_range_tilemask_tlb_invalidation() Himal Prasad Ghimiray
@ 2025-05-28 23:12   ` Matthew Brost
  2025-05-29  3:21     ` Ghimiray, Himal Prasad
  0 siblings, 1 reply; 4+ messages in thread
From: Matthew Brost @ 2025-05-28 23:12 UTC (permalink / raw)
  To: Himal Prasad Ghimiray; +Cc: intel-xe

On Tue, May 27, 2025 at 10:09:51PM +0530, Himal Prasad Ghimiray wrote:
> Introduce xe_vm_range_tilemask_tlb_invalidation(), which issues a TLB
> invalidation for a specified address range across GTs indicated by a
> tilemask.
> 
> Suggested-by: Matthew Brost <matthew.brost@intel.com>
> Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>

A couple nits, but feel free to post a follow up as independent patch to
merge ahead of madvise.

> ---
>  drivers/gpu/drm/xe/xe_svm.c |  43 +--------------
>  drivers/gpu/drm/xe/xe_vm.c  | 103 ++++++++++++++++++++++++------------
>  drivers/gpu/drm/xe/xe_vm.h  |   3 ++
>  3 files changed, 75 insertions(+), 74 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
> index 871ac81bb04a..59e73187114d 100644
> --- a/drivers/gpu/drm/xe/xe_svm.c
> +++ b/drivers/gpu/drm/xe/xe_svm.c
> @@ -167,14 +167,9 @@ static void xe_svm_invalidate(struct drm_gpusvm *gpusvm,
>  {
>  	struct xe_vm *vm = gpusvm_to_vm(gpusvm);
>  	struct xe_device *xe = vm->xe;
> -	struct xe_tile *tile;
>  	struct drm_gpusvm_range *r, *first;
> -	struct xe_gt_tlb_invalidation_fence
> -		fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
>  	u64 adj_start = mmu_range->start, adj_end = mmu_range->end;
>  	u8 tile_mask = 0;
> -	u8 id;
> -	u32 fence_id = 0;
>  	long err;
>  
>  	xe_svm_assert_in_notifier(vm);
> @@ -220,42 +215,8 @@ static void xe_svm_invalidate(struct drm_gpusvm *gpusvm,
>  
>  	xe_device_wmb(xe);
>  
> -	for_each_tile(tile, xe, id) {
> -		if (tile_mask & BIT(id)) {
> -			int err;
> -
> -			xe_gt_tlb_invalidation_fence_init(tile->primary_gt,
> -							  &fence[fence_id], true);
> -
> -			err = xe_gt_tlb_invalidation_range(tile->primary_gt,
> -							   &fence[fence_id],
> -							   adj_start,
> -							   adj_end,
> -							   vm->usm.asid);
> -			if (WARN_ON_ONCE(err < 0))
> -				goto wait;
> -			++fence_id;
> -
> -			if (!tile->media_gt)
> -				continue;
> -
> -			xe_gt_tlb_invalidation_fence_init(tile->media_gt,
> -							  &fence[fence_id], true);
> -
> -			err = xe_gt_tlb_invalidation_range(tile->media_gt,
> -							   &fence[fence_id],
> -							   adj_start,
> -							   adj_end,
> -							   vm->usm.asid);
> -			if (WARN_ON_ONCE(err < 0))
> -				goto wait;
> -			++fence_id;
> -		}
> -	}
> -
> -wait:
> -	for (id = 0; id < fence_id; ++id)
> -		xe_gt_tlb_invalidation_fence_wait(&fence[id]);
> +	err = xe_vm_range_tilemask_tlb_invalidation(vm, adj_start, adj_end, tile_mask);
> +	XE_WARN_ON(err);

WARN_ON_ONCE

>  
>  range_notifier_event_end:
>  	r = first;
> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
> index de6ecff237a6..d60b711e97e9 100644
> --- a/drivers/gpu/drm/xe/xe_vm.c
> +++ b/drivers/gpu/drm/xe/xe_vm.c
> @@ -3851,6 +3851,68 @@ void xe_vm_unlock(struct xe_vm *vm)
>  	dma_resv_unlock(xe_vm_resv(vm));
>  }
>  
> +/**
> + * xe_vm_range_tilemask_tlb_invalidation - Issue a TLB invalidation on this tilemask for an
> + * address range
> + * @vm: The VM
> + * @start: start address
> + * @end: end address
> + * @tile_mask: mask for which gt's issue tlb invalidation
> + *
> + * Issue a range based TLB invalidation for gt's in tilemask
> + *
> + * Returns 0 for success, negative error code otherwise.
> + */
> +int xe_vm_range_tilemask_tlb_invalidation(struct xe_vm *vm, u64 start,
> +					  u64 end, u8 tile_mask)
> +{
> +	struct xe_gt_tlb_invalidation_fence fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
> +	struct xe_tile *tile;
> +	u32 fence_id = 0;
> +	u8 id;
> +	int err;
> +
> +	if (!tile_mask)
> +		return 0;
> +
> +	for_each_tile(tile, vm->xe, id) {
> +		if (tile_mask & BIT(id)) {
> +			xe_gt_tlb_invalidation_fence_init(tile->primary_gt,
> +							  &fence[fence_id], true);
> +
> +			err = xe_gt_tlb_invalidation_range(tile->primary_gt,
> +							   &fence[fence_id],
> +							   start,
> +							   end,
> +							   vm->usm.asid);
> +			if (WARN_ON_ONCE(err < 0))
> +				goto wait;

Let's just have the WARN_ON_ONCE in the SVM code at the caller - that is
the place where we can't really fail and warrents the warn. 

> +			++fence_id;
> +
> +			if (!tile->media_gt)
> +				continue;
> +
> +			xe_gt_tlb_invalidation_fence_init(tile->media_gt,
> +							  &fence[fence_id], true);
> +
> +			err = xe_gt_tlb_invalidation_range(tile->media_gt,
> +							   &fence[fence_id],
> +							   start,
> +							   end,
> +							   vm->usm.asid);
> +			if (WARN_ON_ONCE(err < 0))
> +				goto wait;
> +			++fence_id;
> +		}
> +	}
> +
> +wait:
> +	for (id = 0; id < fence_id; ++id)
> +		xe_gt_tlb_invalidation_fence_wait(&fence[id]);
> +
> +	return err;
> +}
> +
>  /**
>   * xe_vm_invalidate_vma - invalidate GPU mappings for VMA without a lock
>   * @vma: VMA to invalidate
> @@ -3865,11 +3927,9 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
>  {
>  	struct xe_device *xe = xe_vma_vm(vma)->xe;
>  	struct xe_tile *tile;
> -	struct xe_gt_tlb_invalidation_fence
> -		fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
> -	u8 id;
> -	u32 fence_id = 0;
> +	u8 tile_mask = 0;
>  	int ret = 0;
> +	u8 id;
>  
>  	xe_assert(xe, !xe_vma_is_null(vma));
>  	xe_assert(xe, !xe_vma_is_cpu_addr_mirror(vma));
> @@ -3893,37 +3953,14 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
>  		}
>  	}
>  
> -	for_each_tile(tile, xe, id) {
> -		if (xe_pt_zap_ptes(tile, vma)) {
> -			xe_device_wmb(xe);
> -			xe_gt_tlb_invalidation_fence_init(tile->primary_gt,
> -							  &fence[fence_id],
> -							  true);
> -
> -			ret = xe_gt_tlb_invalidation_vma(tile->primary_gt,
> -							 &fence[fence_id], vma);

You can delete xe_gt_tlb_invalidation_vma now as this was the only
caller.

Matt

> -			if (ret)
> -				goto wait;
> -			++fence_id;
> +	for_each_tile(tile, xe, id)
> +		if (xe_pt_zap_ptes(tile, vma))
> +			tile_mask |= BIT(id);
>  
> -			if (!tile->media_gt)
> -				continue;
> +	xe_device_wmb(xe);
>  
> -			xe_gt_tlb_invalidation_fence_init(tile->media_gt,
> -							  &fence[fence_id],
> -							  true);
> -
> -			ret = xe_gt_tlb_invalidation_vma(tile->media_gt,
> -							 &fence[fence_id], vma);
> -			if (ret)
> -				goto wait;
> -			++fence_id;
> -		}
> -	}
> -
> -wait:
> -	for (id = 0; id < fence_id; ++id)
> -		xe_gt_tlb_invalidation_fence_wait(&fence[id]);
> +	ret = xe_vm_range_tilemask_tlb_invalidation(xe_vma_vm(vma), xe_vma_start(vma),
> +						    xe_vma_end(vma), tile_mask);
>  
>  	vma->tile_invalidated = vma->tile_mask;
>  
> diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
> index 99e164852f63..1ef98113fa5b 100644
> --- a/drivers/gpu/drm/xe/xe_vm.h
> +++ b/drivers/gpu/drm/xe/xe_vm.h
> @@ -228,6 +228,9 @@ struct dma_fence *xe_vm_range_rebind(struct xe_vm *vm,
>  struct dma_fence *xe_vm_range_unbind(struct xe_vm *vm,
>  				     struct xe_svm_range *range);
>  
> +int xe_vm_range_tilemask_tlb_invalidation(struct xe_vm *vm, u64 start,
> +					  u64 end, u8 tile_mask);
> +
>  int xe_vm_invalidate_vma(struct xe_vma *vma);
>  
>  int xe_vm_validate_protected(struct xe_vm *vm);
> -- 
> 2.34.1
> 

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [PATCH v3 07/19] drm/xe/vm: Add a helper xe_vm_range_tilemask_tlb_invalidation()
  2025-05-28 23:12   ` Matthew Brost
@ 2025-05-29  3:21     ` Ghimiray, Himal Prasad
  0 siblings, 0 replies; 4+ messages in thread
From: Ghimiray, Himal Prasad @ 2025-05-29  3:21 UTC (permalink / raw)
  To: Matthew Brost; +Cc: intel-xe



On 29-05-2025 04:42, Matthew Brost wrote:
> On Tue, May 27, 2025 at 10:09:51PM +0530, Himal Prasad Ghimiray wrote:
>> Introduce xe_vm_range_tilemask_tlb_invalidation(), which issues a TLB
>> invalidation for a specified address range across GTs indicated by a
>> tilemask.
>>
>> Suggested-by: Matthew Brost <matthew.brost@intel.com>
>> Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
> 
> A couple nits, but feel free to post a follow up as independent patch to
> merge ahead of madvise.

Sure

> 
>> ---
>>   drivers/gpu/drm/xe/xe_svm.c |  43 +--------------
>>   drivers/gpu/drm/xe/xe_vm.c  | 103 ++++++++++++++++++++++++------------
>>   drivers/gpu/drm/xe/xe_vm.h  |   3 ++
>>   3 files changed, 75 insertions(+), 74 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
>> index 871ac81bb04a..59e73187114d 100644
>> --- a/drivers/gpu/drm/xe/xe_svm.c
>> +++ b/drivers/gpu/drm/xe/xe_svm.c
>> @@ -167,14 +167,9 @@ static void xe_svm_invalidate(struct drm_gpusvm *gpusvm,
>>   {
>>   	struct xe_vm *vm = gpusvm_to_vm(gpusvm);
>>   	struct xe_device *xe = vm->xe;
>> -	struct xe_tile *tile;
>>   	struct drm_gpusvm_range *r, *first;
>> -	struct xe_gt_tlb_invalidation_fence
>> -		fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
>>   	u64 adj_start = mmu_range->start, adj_end = mmu_range->end;
>>   	u8 tile_mask = 0;
>> -	u8 id;
>> -	u32 fence_id = 0;
>>   	long err;
>>   
>>   	xe_svm_assert_in_notifier(vm);
>> @@ -220,42 +215,8 @@ static void xe_svm_invalidate(struct drm_gpusvm *gpusvm,
>>   
>>   	xe_device_wmb(xe);
>>   
>> -	for_each_tile(tile, xe, id) {
>> -		if (tile_mask & BIT(id)) {
>> -			int err;
>> -
>> -			xe_gt_tlb_invalidation_fence_init(tile->primary_gt,
>> -							  &fence[fence_id], true);
>> -
>> -			err = xe_gt_tlb_invalidation_range(tile->primary_gt,
>> -							   &fence[fence_id],
>> -							   adj_start,
>> -							   adj_end,
>> -							   vm->usm.asid);
>> -			if (WARN_ON_ONCE(err < 0))
>> -				goto wait;
>> -			++fence_id;
>> -
>> -			if (!tile->media_gt)
>> -				continue;
>> -
>> -			xe_gt_tlb_invalidation_fence_init(tile->media_gt,
>> -							  &fence[fence_id], true);
>> -
>> -			err = xe_gt_tlb_invalidation_range(tile->media_gt,
>> -							   &fence[fence_id],
>> -							   adj_start,
>> -							   adj_end,
>> -							   vm->usm.asid);
>> -			if (WARN_ON_ONCE(err < 0))
>> -				goto wait;
>> -			++fence_id;
>> -		}
>> -	}
>> -
>> -wait:
>> -	for (id = 0; id < fence_id; ++id)
>> -		xe_gt_tlb_invalidation_fence_wait(&fence[id]);
>> +	err = xe_vm_range_tilemask_tlb_invalidation(vm, adj_start, adj_end, tile_mask);
>> +	XE_WARN_ON(err);
> 
> WARN_ON_ONCE

ok.

> 
>>   
>>   range_notifier_event_end:
>>   	r = first;
>> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
>> index de6ecff237a6..d60b711e97e9 100644
>> --- a/drivers/gpu/drm/xe/xe_vm.c
>> +++ b/drivers/gpu/drm/xe/xe_vm.c
>> @@ -3851,6 +3851,68 @@ void xe_vm_unlock(struct xe_vm *vm)
>>   	dma_resv_unlock(xe_vm_resv(vm));
>>   }
>>   
>> +/**
>> + * xe_vm_range_tilemask_tlb_invalidation - Issue a TLB invalidation on this tilemask for an
>> + * address range
>> + * @vm: The VM
>> + * @start: start address
>> + * @end: end address
>> + * @tile_mask: mask for which gt's issue tlb invalidation
>> + *
>> + * Issue a range based TLB invalidation for gt's in tilemask
>> + *
>> + * Returns 0 for success, negative error code otherwise.
>> + */
>> +int xe_vm_range_tilemask_tlb_invalidation(struct xe_vm *vm, u64 start,
>> +					  u64 end, u8 tile_mask)
>> +{
>> +	struct xe_gt_tlb_invalidation_fence fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
>> +	struct xe_tile *tile;
>> +	u32 fence_id = 0;
>> +	u8 id;
>> +	int err;
>> +
>> +	if (!tile_mask)
>> +		return 0;
>> +
>> +	for_each_tile(tile, vm->xe, id) {
>> +		if (tile_mask & BIT(id)) {
>> +			xe_gt_tlb_invalidation_fence_init(tile->primary_gt,
>> +							  &fence[fence_id], true);
>> +
>> +			err = xe_gt_tlb_invalidation_range(tile->primary_gt,
>> +							   &fence[fence_id],
>> +							   start,
>> +							   end,
>> +							   vm->usm.asid);
>> +			if (WARN_ON_ONCE(err < 0))
>> +				goto wait;
> 
> Let's just have the WARN_ON_ONCE in the SVM code at the caller - that is
> the place where we can't really fail and warrents the warn.

ok

> 
>> +			++fence_id;
>> +
>> +			if (!tile->media_gt)
>> +				continue;
>> +
>> +			xe_gt_tlb_invalidation_fence_init(tile->media_gt,
>> +							  &fence[fence_id], true);
>> +
>> +			err = xe_gt_tlb_invalidation_range(tile->media_gt,
>> +							   &fence[fence_id],
>> +							   start,
>> +							   end,
>> +							   vm->usm.asid);
>> +			if (WARN_ON_ONCE(err < 0))
>> +				goto wait;
>> +			++fence_id;
>> +		}
>> +	}
>> +
>> +wait:
>> +	for (id = 0; id < fence_id; ++id)
>> +		xe_gt_tlb_invalidation_fence_wait(&fence[id]);
>> +
>> +	return err;
>> +}
>> +
>>   /**
>>    * xe_vm_invalidate_vma - invalidate GPU mappings for VMA without a lock
>>    * @vma: VMA to invalidate
>> @@ -3865,11 +3927,9 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
>>   {
>>   	struct xe_device *xe = xe_vma_vm(vma)->xe;
>>   	struct xe_tile *tile;
>> -	struct xe_gt_tlb_invalidation_fence
>> -		fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
>> -	u8 id;
>> -	u32 fence_id = 0;
>> +	u8 tile_mask = 0;
>>   	int ret = 0;
>> +	u8 id;
>>   
>>   	xe_assert(xe, !xe_vma_is_null(vma));
>>   	xe_assert(xe, !xe_vma_is_cpu_addr_mirror(vma));
>> @@ -3893,37 +3953,14 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
>>   		}
>>   	}
>>   
>> -	for_each_tile(tile, xe, id) {
>> -		if (xe_pt_zap_ptes(tile, vma)) {
>> -			xe_device_wmb(xe);
>> -			xe_gt_tlb_invalidation_fence_init(tile->primary_gt,
>> -							  &fence[fence_id],
>> -							  true);
>> -
>> -			ret = xe_gt_tlb_invalidation_vma(tile->primary_gt,
>> -							 &fence[fence_id], vma);
> 
> You can delete xe_gt_tlb_invalidation_vma now as this was the only
> caller.

Makes sense.

> 
> Matt
> 
>> -			if (ret)
>> -				goto wait;
>> -			++fence_id;
>> +	for_each_tile(tile, xe, id)
>> +		if (xe_pt_zap_ptes(tile, vma))
>> +			tile_mask |= BIT(id);
>>   
>> -			if (!tile->media_gt)
>> -				continue;
>> +	xe_device_wmb(xe);
>>   
>> -			xe_gt_tlb_invalidation_fence_init(tile->media_gt,
>> -							  &fence[fence_id],
>> -							  true);
>> -
>> -			ret = xe_gt_tlb_invalidation_vma(tile->media_gt,
>> -							 &fence[fence_id], vma);
>> -			if (ret)
>> -				goto wait;
>> -			++fence_id;
>> -		}
>> -	}
>> -
>> -wait:
>> -	for (id = 0; id < fence_id; ++id)
>> -		xe_gt_tlb_invalidation_fence_wait(&fence[id]);
>> +	ret = xe_vm_range_tilemask_tlb_invalidation(xe_vma_vm(vma), xe_vma_start(vma),
>> +						    xe_vma_end(vma), tile_mask);
>>   
>>   	vma->tile_invalidated = vma->tile_mask;
>>   
>> diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
>> index 99e164852f63..1ef98113fa5b 100644
>> --- a/drivers/gpu/drm/xe/xe_vm.h
>> +++ b/drivers/gpu/drm/xe/xe_vm.h
>> @@ -228,6 +228,9 @@ struct dma_fence *xe_vm_range_rebind(struct xe_vm *vm,
>>   struct dma_fence *xe_vm_range_unbind(struct xe_vm *vm,
>>   				     struct xe_svm_range *range);
>>   
>> +int xe_vm_range_tilemask_tlb_invalidation(struct xe_vm *vm, u64 start,
>> +					  u64 end, u8 tile_mask);
>> +
>>   int xe_vm_invalidate_vma(struct xe_vma *vma);
>>   
>>   int xe_vm_validate_protected(struct xe_vm *vm);
>> -- 
>> 2.34.1
>>


^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [PATCH v3 07/19] drm/xe/vm: Add a helper xe_vm_range_tilemask_tlb_invalidation()
@ 2025-05-29 21:22 kernel test robot
  0 siblings, 0 replies; 4+ messages in thread
From: kernel test robot @ 2025-05-29 21:22 UTC (permalink / raw)
  To: oe-kbuild; +Cc: lkp, Dan Carpenter

BCC: lkp@intel.com
CC: oe-kbuild-all@lists.linux.dev
In-Reply-To: <20250527164003.1068118-8-himal.prasad.ghimiray@intel.com>
References: <20250527164003.1068118-8-himal.prasad.ghimiray@intel.com>
TO: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
TO: intel-xe@lists.freedesktop.org
CC: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
CC: Matthew Brost <matthew.brost@intel.com>

Hi Himal,

kernel test robot noticed the following build warnings:

[auto build test WARNING on drm-xe/drm-xe-next]
[also build test WARNING on linus/master v6.15 next-20250529]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Himal-Prasad-Ghimiray/Introduce-drm_gpuvm_sm_map_ops_flags-enums-for-sm_map_ops/20250528-041919
base:   https://gitlab.freedesktop.org/drm/xe/kernel.git drm-xe-next
patch link:    https://lore.kernel.org/r/20250527164003.1068118-8-himal.prasad.ghimiray%40intel.com
patch subject: [PATCH v3 07/19] drm/xe/vm: Add a helper xe_vm_range_tilemask_tlb_invalidation()
:::::: branch date: 2 days ago
:::::: commit date: 2 days ago
config: loongarch-randconfig-r073-20250529 (https://download.01.org/0day-ci/archive/20250530/202505300542.iz30Sd3K-lkp@intel.com/config)
compiler: loongarch64-linux-gcc (GCC) 15.1.0

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Reported-by: Dan Carpenter <error27@gmail.com>
| Closes: https://lore.kernel.org/r/202505300542.iz30Sd3K-lkp@intel.com/

New smatch warnings:
drivers/gpu/drm/xe/xe_vm.c:3913 xe_vm_range_tilemask_tlb_invalidation() error: uninitialized symbol 'err'.

Old smatch warnings:
drivers/gpu/drm/xe/xe_vm.c:2480 new_vma() error: we previously assumed 'bo' could be null (see line 2454)
drivers/gpu/drm/xe/xe_vm.c:2492 new_vma() error: 'vma' dereferencing possible ERR_PTR()
drivers/gpu/drm/xe/xe_vm.c:2919 prefetch_ranges() warn: iterator 'i' not incremented
arch/loongarch/include/asm/atomic.h:135 arch_atomic_fetch_add_unless() warn: inconsistent indenting
drivers/gpu/drm/xe/xe_vm.c:4119 xe_vm_snapshot_print() warn: passing zero to 'PTR_ERR'

vim +/err +3913 drivers/gpu/drm/xe/xe_vm.c

dd08ebf6c3525a Matthew Brost         2023-03-30  3853  
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3854  /**
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3855   * xe_vm_range_tilemask_tlb_invalidation - Issue a TLB invalidation on this tilemask for an
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3856   * address range
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3857   * @vm: The VM
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3858   * @start: start address
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3859   * @end: end address
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3860   * @tile_mask: mask for which gt's issue tlb invalidation
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3861   *
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3862   * Issue a range based TLB invalidation for gt's in tilemask
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3863   *
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3864   * Returns 0 for success, negative error code otherwise.
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3865   */
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3866  int xe_vm_range_tilemask_tlb_invalidation(struct xe_vm *vm, u64 start,
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3867  					  u64 end, u8 tile_mask)
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3868  {
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3869  	struct xe_gt_tlb_invalidation_fence fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3870  	struct xe_tile *tile;
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3871  	u32 fence_id = 0;
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3872  	u8 id;
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3873  	int err;
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3874  
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3875  	if (!tile_mask)
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3876  		return 0;
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3877  
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3878  	for_each_tile(tile, vm->xe, id) {
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3879  		if (tile_mask & BIT(id)) {
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3880  			xe_gt_tlb_invalidation_fence_init(tile->primary_gt,
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3881  							  &fence[fence_id], true);
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3882  
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3883  			err = xe_gt_tlb_invalidation_range(tile->primary_gt,
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3884  							   &fence[fence_id],
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3885  							   start,
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3886  							   end,
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3887  							   vm->usm.asid);
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3888  			if (WARN_ON_ONCE(err < 0))
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3889  				goto wait;
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3890  			++fence_id;
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3891  
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3892  			if (!tile->media_gt)
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3893  				continue;
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3894  
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3895  			xe_gt_tlb_invalidation_fence_init(tile->media_gt,
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3896  							  &fence[fence_id], true);
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3897  
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3898  			err = xe_gt_tlb_invalidation_range(tile->media_gt,
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3899  							   &fence[fence_id],
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3900  							   start,
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3901  							   end,
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3902  							   vm->usm.asid);
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3903  			if (WARN_ON_ONCE(err < 0))
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3904  				goto wait;
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3905  			++fence_id;
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3906  		}
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3907  	}
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3908  
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3909  wait:
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3910  	for (id = 0; id < fence_id; ++id)
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3911  		xe_gt_tlb_invalidation_fence_wait(&fence[id]);
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3912  
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27 @3913  	return err;
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3914  }
511b2f09f331fc Himal Prasad Ghimiray 2025-05-27  3915  

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

^ permalink raw reply	[flat|nested] 4+ messages in thread

end of thread, other threads:[~2025-05-29 21:22 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-05-29 21:22 [PATCH v3 07/19] drm/xe/vm: Add a helper xe_vm_range_tilemask_tlb_invalidation() kernel test robot
  -- strict thread matches above, loose matches on Subject: below --
2025-05-27 16:39 [PATCH v3 00/19] MADVISE FOR XE Himal Prasad Ghimiray
2025-05-27 16:39 ` [PATCH v3 07/19] drm/xe/vm: Add a helper xe_vm_range_tilemask_tlb_invalidation() Himal Prasad Ghimiray
2025-05-28 23:12   ` Matthew Brost
2025-05-29  3:21     ` Ghimiray, Himal Prasad

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.