Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "Ghimiray, Himal Prasad" <himal.prasad.ghimiray@intel.com>
To: Matthew Brost <matthew.brost@intel.com>
Cc: <intel-xe@lists.freedesktop.org>, <thomas.hellstrom@linux.intel.com>
Subject: Re: [PATCH v2 14/32] drm/xe/svm: Implement prefetch support for SVM ranges
Date: Thu, 24 Apr 2025 15:33:29 +0530	[thread overview]
Message-ID: <0f22ea7e-e6cf-4464-8044-4520ebe9ecd6@intel.com> (raw)
In-Reply-To: <aACJoZMXsfA+hu4F@lstrano-desk.jf.intel.com>



On 17-04-2025 10:24, Matthew Brost wrote:
> On Mon, Apr 07, 2025 at 03:47:01PM +0530, Himal Prasad Ghimiray wrote:
>> This commit adds prefetch support for SVM ranges, utilizing the
>> existing ioctl vm_bind functionality to achieve this.
>>
>> v2: rebase
>>
>> Cc: Matthew Brost <matthew.brost@intel.com>
>> Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
>> ---
>>   drivers/gpu/drm/xe/xe_pt.c |  61 +++++++++---
>>   drivers/gpu/drm/xe/xe_vm.c | 185 +++++++++++++++++++++++++++++++++++--
>>   2 files changed, 222 insertions(+), 24 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
>> index de4e3edda758..59dc065fae93 100644
>> --- a/drivers/gpu/drm/xe/xe_pt.c
>> +++ b/drivers/gpu/drm/xe/xe_pt.c
>> @@ -1458,7 +1458,8 @@ static int xe_pt_svm_pre_commit(struct xe_migrate_pt_update *pt_update)
>>   	struct xe_vm *vm = pt_update->vops->vm;
>>   	struct xe_vma_ops *vops = pt_update->vops;
>>   	struct xe_vma_op *op;
>> -	int err;
>> +	int ranges_count;
>> +	int err, i;
>>   
>>   	err = xe_pt_pre_commit(pt_update);
>>   	if (err)
>> @@ -1467,20 +1468,33 @@ static int xe_pt_svm_pre_commit(struct xe_migrate_pt_update *pt_update)
>>   	xe_svm_notifier_lock(vm);
>>   
>>   	list_for_each_entry(op, &vops->list, link) {
>> -		struct xe_svm_range *range = op->map_range.range;
>> +		struct xe_svm_range *range = NULL;
>>   
>>   		if (op->subop == XE_VMA_SUBOP_UNMAP_RANGE)
>>   			continue;
>>   
>> -		xe_svm_range_debug(range, "PRE-COMMIT");
>> -
>> -		xe_assert(vm->xe, xe_vma_is_cpu_addr_mirror(op->map_range.vma));
>> -		xe_assert(vm->xe, op->subop == XE_VMA_SUBOP_MAP_RANGE);
>> +		if (op->base.op == DRM_GPUVA_OP_PREFETCH) {
>> +			xe_assert(vm->xe,
>> +				  xe_vma_is_cpu_addr_mirror(gpuva_to_vma(op->base.prefetch.va)));
>> +			ranges_count = op->prefetch_range.ranges_count;
>> +		} else {
>> +			xe_assert(vm->xe, xe_vma_is_cpu_addr_mirror(op->map_range.vma));
>> +			xe_assert(vm->xe, op->subop == XE_VMA_SUBOP_MAP_RANGE);
>> +			ranges_count  = 1;
>> +		}
>>   
>> -		if (!xe_svm_range_pages_valid(range)) {
>> -			xe_svm_range_debug(range, "PRE-COMMIT - RETRY");
>> -			xe_svm_notifier_unlock(vm);
>> -			return -EAGAIN;
>> +		for (i = 0; i < ranges_count; i++) {
> 
> xa_for_each as it doesn't make any assumptions above the key (e.g. the value of i).

Sure


> 
>> +			if (op->base.op == DRM_GPUVA_OP_PREFETCH)
>> +				range = xa_load(&op->prefetch_range.range, i);
> 
> I'd move this logic above... So I'd write it like this...
> 
> if (op->base.op == DRM_GPUVA_OP_PREFETCH) {
> 	assert
> 	xe_for_each
> 		do_pages_check()
> } else {
> 	assert
> 	do_pages_check();
> }

Looks better.

> 
>> +			else
>> +				range = op->map_range.range;
>> +			xe_svm_range_debug(range, "PRE-COMMIT");
>> +
>> +			if (!xe_svm_range_pages_valid(range)) {
>> +				xe_svm_range_debug(range, "PRE-COMMIT - RETRY");
>> +				xe_svm_notifier_unlock(vm);
>> +				return -EAGAIN;
> 
> So in the case of prefetch, this is bit inconsistent as below when
> things race, you return -ENODATA which is converted to 0 in the IOCTL.
> -EAGAIN here could result in a livelock in the right conditions as
> -EAGAIN means must retry. I think maybe just -ENODATA if a prefetch
> fails... If there are any other binds in the array of IOCTL they will
> just fault I guess. Maybe not a concern as only VK uses array of binds
> at the moment.

Ok

> 
>> +			}
>>   		}
>>   	}
>>   
>> @@ -2065,11 +2079,21 @@ static int op_prepare(struct xe_vm *vm,
>>   	{
>>   		struct xe_vma *vma = gpuva_to_vma(op->base.prefetch.va);
>>   
>> -		if (xe_vma_is_cpu_addr_mirror(vma))
>> -			break;
>> +		if (xe_vma_is_cpu_addr_mirror(vma)) {
>> +			struct xe_svm_range *range;
>> +			int i;
>>   
>> -		err = bind_op_prepare(vm, tile, pt_update_ops, vma, false);
>> -		pt_update_ops->wait_vm_kernel = true;
>> +			for (i = 0; i < op->prefetch_range.ranges_count; i++) {
>> +				range = xa_load(&op->prefetch_range.range, i);
> 
> Again xe_for_each...

Noted

> 
>> +				err = bind_range_prepare(vm, tile, pt_update_ops,
>> +							 vma, range);
>> +				if (err)
>> +					return err;
>> +			}
>> +		} else {
>> +			err = bind_op_prepare(vm, tile, pt_update_ops, vma, false);
>> +			pt_update_ops->wait_vm_kernel = true;
>> +		}
>>   		break;
>>   	}
>>   	case DRM_GPUVA_OP_DRIVER:
>> @@ -2273,9 +2297,16 @@ static void op_commit(struct xe_vm *vm,
>>   	{
>>   		struct xe_vma *vma = gpuva_to_vma(op->base.prefetch.va);
>>   
>> -		if (!xe_vma_is_cpu_addr_mirror(vma))
>> +		if (xe_vma_is_cpu_addr_mirror(vma)) {
>> +			for (int i = 0 ; i < op->prefetch_range.ranges_count; i++) {
> 
> Again xe_for_each...
> 
>> +				struct xe_svm_range *range = xa_load(&op->prefetch_range.range, i);
>> +
>> +				range_present_and_invalidated_tile(vm, range, tile->id);
>> +			}
>> +		} else {
>>   			bind_op_commit(vm, tile, pt_update_ops, vma, fence,
>>   				       fence2, false);
>> +		}
>>   		break;
>>   	}
>>   	case DRM_GPUVA_OP_DRIVER:
>> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
>> index 57af2c37f927..ffd7ad664921 100644
>> --- a/drivers/gpu/drm/xe/xe_vm.c
>> +++ b/drivers/gpu/drm/xe/xe_vm.c
>> @@ -798,10 +798,36 @@ static int xe_vma_ops_alloc(struct xe_vma_ops *vops, bool array_of_binds)
>>   }
>>   ALLOW_ERROR_INJECTION(xe_vma_ops_alloc, ERRNO);
>>   
>> +static void clean_svm_prefetch_op(struct xe_vma_op *op)
>> +{
> 
> Can we rename this with fini convention to match xe_vma_ops_fini?

Sure

> 
>> +	struct xe_vma *vma;
>> +
>> +	vma = gpuva_to_vma(op->base.prefetch.va);
>> +
>> +	if (op->base.op == DRM_GPUVA_OP_PREFETCH && xe_vma_is_cpu_addr_mirror(vma)) {
>> +		xa_destroy(&op->prefetch_range.range);
>> +		op->prefetch_range.ranges_count = 0;
> 
> Do you need to set 'op->prefetch_range.ranges_count' to zero here.

Looks redundant.

> 
>> +	}
>> +}
>> +
>> +static void clean_svm_prefetch_in_vma_ops(struct xe_vma_ops *vops)
>> +{
> 
> Same here, fini convention?

Sure

> 
>> +	struct xe_vma_op *op;
>> +
>> +	if (!(vops->flags & XE_VMA_OPS_HAS_SVM_PREFETCH))
>> +		return;
>> +
>> +	list_for_each_entry(op, &vops->list, link) {
>> +		clean_svm_prefetch_op(op);
>> +	}
> 
> Brackets not needed.

Noted

> 
>> +}
>> +
>>   static void xe_vma_ops_fini(struct xe_vma_ops *vops)
>>   {
>>   	int i;
>>   
>> +	clean_svm_prefetch_in_vma_ops(vops);
>> +
>>   	for (i = 0; i < XE_MAX_TILES_PER_DEVICE; ++i)
>>   		kfree(vops->pt_update_ops[i].ops);
>>   }
>> @@ -2248,13 +2274,25 @@ static bool __xe_vm_needs_clear_scratch_pages(struct xe_vm *vm, u32 bind_flags)
>>   	return true;
>>   }
>>   
>> +static void clean_svm_prefetch_in_gpuva_ops(struct drm_gpuva_ops *ops)
>> +{
> 
> Same here, fini convention?
> 
>> +	struct drm_gpuva_op *__op;
>> +
>> +	drm_gpuva_for_each_op(__op, ops) {
>> +		struct xe_vma_op *op = gpuva_op_to_vma_op(__op);
>> +
>> +		clean_svm_prefetch_op(op);
>> +	}
>> +}
>> +
>>   /*
>>    * Create operations list from IOCTL arguments, setup operations fields so parse
>>    * and commit steps are decoupled from IOCTL arguments. This step can fail.
>>    */
>>   static struct drm_gpuva_ops *
>> -vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
>> -			 u64 bo_offset_or_userptr, u64 addr, u64 range,
>> +vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_vma_ops *vops,
>> +			 struct xe_bo *bo, u64 bo_offset_or_userptr,
>> +			 u64 addr, u64 range,
>>   			 u32 operation, u32 flags,
>>   			 u32 prefetch_region, u16 pat_index)
>>   {
>> @@ -2262,6 +2300,7 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
>>   	struct drm_gpuva_ops *ops;
>>   	struct drm_gpuva_op *__op;
>>   	struct drm_gpuvm_bo *vm_bo;
>> +	u64 range_end = addr + range;
>>   	int err;
>>   
>>   	lockdep_assert_held_write(&vm->lock);
>> @@ -2323,14 +2362,61 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo,
>>   			op->map.invalidate_on_bind =
>>   				__xe_vm_needs_clear_scratch_pages(vm, flags);
>>   		} else if (__op->op == DRM_GPUVA_OP_PREFETCH) {
>> -			op->prefetch.region = prefetch_region;
>> -		}
>> +			struct xe_vma *vma = gpuva_to_vma(op->base.prefetch.va);
>> +
>> +			if (!xe_vma_is_cpu_addr_mirror(vma)) {
>> +				op->prefetch.region = prefetch_region;
>> +				break;
>> +			}
>>   
>> +			struct drm_gpusvm_ctx ctx = {
>> +			.read_only = xe_vma_read_only(vma),
>> +			.devmem_possible = IS_DGFX(vm->xe) &&
>> +					   IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR),
>> +			.check_pages_threshold = IS_DGFX(vm->xe) &&
>> +						 IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR) ?
>> +						 SZ_64K : 0,
> 
> The alignment looks weird here.

Checkpatch confirms its good.

> 
> Also you don't techincally need to set check_pages_threshold here give
> this is used by get_pages which is not called here.

Thats true, will remove it

> 
>> +			};
>> +
>> +			op->prefetch_range.region = prefetch_region;
>> +			struct xe_svm_range *svm_range;
>> +			int i = 0;
> 
> I don't think you need 'i' here, you probably just can use xa_alloc
> rather than xa_store if use xe_for_each everywhere else.

Yes xa_alloc with xa_init_flags will be cleaner here. Will change

> 
> 
>> +
>> +			xa_init(&op->prefetch_range.range);
>> +			op->prefetch_range.ranges_count = 0;
>> +alloc_next_range:
>> +			svm_range = xe_svm_range_find_or_insert(vm, addr, vma, &ctx);
>> +
> 
> I think you want to check if range has a mapping and is in preferred
> location, if it is then don't add to the xarray as no reason to try to
> migrate it or rebind the GPU pages.

Makes sense, will add a check here.

> 
>> +			if (PTR_ERR(svm_range) == -ENOENT)
>> +				break;
>> +
>> +			if (IS_ERR(svm_range)) {
>> +				err = PTR_ERR(svm_range);
>> +				goto unwind_prefetch_ops;
>> +			}
>> +
>> +			xa_store(&op->prefetch_range.range, i, svm_range, GFP_KERNEL);
>> +			op->prefetch_range.ranges_count++;
>> +			vops->flags |= XE_VMA_OPS_HAS_SVM_PREFETCH;
>> +
>> +			if (range_end > xe_svm_range_end(svm_range) &&
>> +			    xe_svm_range_end(svm_range) < xe_vma_end(vma)) {
>> +				i++;
>> +				addr = xe_svm_range_end(svm_range);
>> +				goto alloc_next_range;
>> +			}
>> +		}
>>   		print_op(vm->xe, __op);
>>   	}
>>   
>>   	return ops;
>> +
>> +unwind_prefetch_ops:
>> +	clean_svm_prefetch_in_gpuva_ops(ops);
>> +	drm_gpuva_ops_free(&vm->gpuvm, ops);
>> +	return ERR_PTR(err);
>>   }
>> +
>>   ALLOW_ERROR_INJECTION(vm_bind_ioctl_ops_create, ERRNO);
>>   
>>   static struct xe_vma *new_vma(struct xe_vm *vm, struct drm_gpuva_op_map *op,
>> @@ -2645,8 +2731,12 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
>>   					return err;
>>   			}
>>   
>> -			if (!xe_vma_is_cpu_addr_mirror(vma))
>> +			if (xe_vma_is_cpu_addr_mirror(vma))
>> +				xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask,
>> +							      op->prefetch_range.ranges_count);
>> +			else
>>   				xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask, 1);
>> +
>>   			break;
>>   		default:
>>   			drm_warn(&vm->xe->drm, "NOT POSSIBLE");
>> @@ -2772,6 +2862,58 @@ static int check_ufence(struct xe_vma *vma)
>>   	return 0;
>>   }
>>   
>> +static int prefetch_ranges_lock_and_prep(struct xe_vm *vm,
>> +					 struct xe_vma_op *op)
>> +{
>> +	int err = 0;
>> +
>> +	if (op->base.op  == DRM_GPUVA_OP_PREFETCH) {
> 
> 
> if (op->base.op != DRM_GPUVA_OP_PREFETCH || xe_vma_is_cpu_addr_mirror(vma))
> 	return 0;
> 
> Will help with spacing. Or do this check at the caller.
> 
>> +		struct xe_vma *vma = gpuva_to_vma(op->base.prefetch.va);
>> +		struct drm_gpusvm_ctx ctx = {
>> +			.read_only = xe_vma_read_only(vma),
>> +			.devmem_possible = IS_DGFX(vm->xe) &&
>> +					   IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR),
>> +			.check_pages_threshold = IS_DGFX(vm->xe) &&
>> +						 IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR) ?
>> +						 SZ_64K : 0,
>> +		};
>> +		struct xe_svm_range *svm_range;
>> +		struct xe_tile *tile;
>> +		u32 region;
>> +		int i;
>> +
>> +		if (!xe_vma_is_cpu_addr_mirror(vma))
>> +			return 0;
>> +
>> +		region = op->prefetch_range.region;
>> +
>> +		/* TODO: Threading the migration */
>> +		for (i = 0; i < op->prefetch_range.ranges_count; i++) {
> 
> Again xa_for_each...
> 
>> +			svm_range = xa_load(&op->prefetch_range.range, i);
>> +			if (xe_svm_range_needs_migrate_to_vram(svm_range, vma, region)) {
>> +				tile = &vm->xe->tiles[region_to_mem_type[region] - XE_PL_VRAM0];
>> +				err = xe_svm_alloc_vram(vm, tile, svm_range, &ctx);
>> +				if (err) {
>> +					drm_err(&vm->xe->drm, "VRAM allocation failed, can be retried from userspace, asid=%u, gpusvm=%p, errno=%pe\n",
>> +						vm->usm.asid, &vm->svm.gpusvm, ERR_PTR(err));
> 
> Not drm_err here, drm_dbg as user space can easily retrigger this.

Sure

> 
>> +					return -ENODATA;
> 
> So this gets squashed into return 0, which I think is correct for now.
> Same explaination as above wrt to error codes.
> 
>> +				}
>> +			}
>> +
>> +			err = xe_svm_range_get_pages(vm, svm_range, &ctx);
>> +			if (err) {
>> +				if (err == -EOPNOTSUPP || err == -EFAULT || err == -EPERM)
>> +					err = -ENODATA;
>> +
>> +				drm_err(&vm->xe->drm, "Get pages failed, asid=%u, gpusvm=%p, errno=%pe\n",
>> +					vm->usm.asid, &vm->svm.gpusvm, ERR_PTR(err));
> 
> Same as above.
> 
> We are going to want IGTs to test these error paths btw, issue prefetch
> then have another thread immediately touch some of the memory to abort
> the prefetch.

Sure will look into it.

> 
>> +				return err;
>> +			}
>> +		}
>> +	}
>> +	return err;
>> +}
>> +
>>   static int op_lock_and_prep(struct drm_exec *exec, struct xe_vm *vm,
>>   			    struct xe_vma_op *op)
>>   {
>> @@ -2809,7 +2951,12 @@ static int op_lock_and_prep(struct drm_exec *exec, struct xe_vm *vm,
>>   	case DRM_GPUVA_OP_PREFETCH:
>>   	{
>>   		struct xe_vma *vma = gpuva_to_vma(op->base.prefetch.va);
>> -		u32 region = op->prefetch.region;
>> +		u32 region;
>> +
>> +		if (xe_vma_is_cpu_addr_mirror(vma))
>> +			region = op->prefetch_range.region;
>> +		else
>> +			region = op->prefetch.region;
>>   
>>   		xe_assert(vm->xe, region <= ARRAY_SIZE(region_to_mem_type));
>>   
>> @@ -2828,6 +2975,23 @@ static int op_lock_and_prep(struct drm_exec *exec, struct xe_vm *vm,
>>   	return err;
>>   }
>>   
>> +static int xe_vma_ops_execute_ready(struct xe_vm *vm, struct xe_vma_ops *vops)
>> +{
> 
> Let's make these names consistent.
> 
> How about...
> 
> s/xe_vma_ops_execute_ready/vm_bind_ioctl_ops_prefetch_ranges
> 
> s/prefetch_ranges_lock_and_prep/prefetch_ranges

Sure

> 
>> +	struct xe_vma_op *op;
>> +	int err;
>> +
>> +	if (!(vops->flags & XE_VMA_OPS_HAS_SVM_PREFETCH))
>> +		return 0;
>> +
>> +	list_for_each_entry(op, &vops->list, link) {
>> +		err = prefetch_ranges_lock_and_prep(vm, op);
>> +		if (err)
>> +			return err;
>> +	}
>> +
>> +	return 0;
>> +}
>> +
>>   static int vm_bind_ioctl_ops_lock_and_prep(struct drm_exec *exec,
>>   					   struct xe_vm *vm,
>>   					   struct xe_vma_ops *vops)
>> @@ -2850,7 +3014,6 @@ static int vm_bind_ioctl_ops_lock_and_prep(struct drm_exec *exec,
>>   	    vm->xe->vm_inject_error_position == FORCE_OP_ERROR_LOCK)
>>   		return -ENOSPC;
>>   #endif
>> -
> 
> Look unrelated.
> 
> Matt
> 
>>   	return 0;
>>   }
>>   
>> @@ -3492,7 +3655,7 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
>>   		u32 prefetch_region = bind_ops[i].prefetch_mem_region_instance;
>>   		u16 pat_index = bind_ops[i].pat_index;
>>   
>> -		ops[i] = vm_bind_ioctl_ops_create(vm, bos[i], obj_offset,
>> +		ops[i] = vm_bind_ioctl_ops_create(vm, &vops, bos[i], obj_offset,
>>   						  addr, range, op, flags,
>>   						  prefetch_region, pat_index);
>>   		if (IS_ERR(ops[i])) {
>> @@ -3525,6 +3688,10 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
>>   	if (err)
>>   		goto unwind_ops;
>>   
>> +	err = xe_vma_ops_execute_ready(vm, &vops);
>> +	if (err)
>> +		goto unwind_ops;
>> +
>>   	fence = vm_bind_ioctl_ops_execute(vm, &vops);
>>   	if (IS_ERR(fence))
>>   		err = PTR_ERR(fence);
>> @@ -3594,7 +3761,7 @@ struct dma_fence *xe_vm_bind_kernel_bo(struct xe_vm *vm, struct xe_bo *bo,
>>   
>>   	xe_vma_ops_init(&vops, vm, q, NULL, 0);
>>   
>> -	ops = vm_bind_ioctl_ops_create(vm, bo, 0, addr, bo->size,
>> +	ops = vm_bind_ioctl_ops_create(vm, &vops, bo, 0, addr, bo->size,
>>   				       DRM_XE_VM_BIND_OP_MAP, 0, 0,
>>   				       vm->xe->pat.idx[cache_lvl]);
>>   	if (IS_ERR(ops)) {
>> -- 
>> 2.34.1
>>


  reply	other threads:[~2025-04-24 10:04 UTC|newest]

Thread overview: 120+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-04-07 10:16 [PATCH v2 00/32] PREFETCH and MADVISE for SVM ranges Himal Prasad Ghimiray
2025-04-07 10:16 ` [PATCH v2 01/32] drm/xe: Introduce xe_vma_op_prefetch_range struct for prefetch of ranges Himal Prasad Ghimiray
2025-04-07 10:16 ` [PATCH v2 02/32] drm/xe: Make xe_svm_alloc_vram public Himal Prasad Ghimiray
2025-04-17  2:50   ` Matthew Brost
2025-04-21  4:06     ` Ghimiray, Himal Prasad
2025-04-07 10:16 ` [PATCH v2 03/32] drm/xe/svm: Helper to add tile masks to svm ranges Himal Prasad Ghimiray
2025-04-07 10:16 ` [PATCH v2 04/32] drm/xe/svm: Make to_xe_range a public function Himal Prasad Ghimiray
2025-04-07 10:16 ` [PATCH v2 05/32] drm/xe/svm: Make xe_svm_range_* end/start/size public Himal Prasad Ghimiray
2025-04-07 10:16 ` [PATCH v2 06/32] drm/xe/vm: Update xe_vma_ops_incr_pt_update_ops to take an increment value Himal Prasad Ghimiray
2025-04-17  0:10   ` Matthew Brost
2025-04-21  4:09     ` Ghimiray, Himal Prasad
2025-04-07 10:16 ` [PATCH v2 07/32] drm/xe/vm: Add an identifier in xe_vma_ops for svm prefetch Himal Prasad Ghimiray
2025-04-17  2:53   ` Matthew Brost
2025-04-07 10:16 ` [PATCH v2 08/32] drm/xe: Rename lookup_vma function to xe_find_vma_by_addr Himal Prasad Ghimiray
2025-04-07 22:42   ` kernel test robot
2025-04-07 10:16 ` [PATCH v2 09/32] drm/xe/svm: Allow unaligned addresses and ranges for prefetch Himal Prasad Ghimiray
2025-04-17  2:53   ` Matthew Brost
2025-04-07 10:16 ` [PATCH v2 10/32] drm/xe/svm: Refactor usage of drm_gpusvm* function in xe_svm Himal Prasad Ghimiray
2025-04-17  2:57   ` Matthew Brost
2025-04-21  4:30     ` Ghimiray, Himal Prasad
2025-04-07 10:16 ` [PATCH v2 11/32] drm/xe/svm: Add function to determine if range needs VRAM migration Himal Prasad Ghimiray
2025-04-17  3:05   ` Matthew Brost
2025-04-21  4:52     ` Ghimiray, Himal Prasad
2025-04-07 10:16 ` [PATCH v2 12/32] drm/gpusvm: Introduce vram_only flag for VRAM allocation Himal Prasad Ghimiray
2025-04-17  3:07   ` Matthew Brost
2025-04-21  4:55     ` Ghimiray, Himal Prasad
2025-04-07 10:17 ` [PATCH v2 13/32] drm/xe/svm: Incase of atomic access ensure get_pages happens from vram Himal Prasad Ghimiray
2025-04-17  4:19   ` Matthew Brost
2025-04-21  4:58     ` Ghimiray, Himal Prasad
2025-04-21  6:29       ` Ghimiray, Himal Prasad
2025-04-22 15:25         ` Matthew Brost
2025-04-22 15:27       ` Matthew Brost
2025-04-07 10:17 ` [PATCH v2 14/32] drm/xe/svm: Implement prefetch support for SVM ranges Himal Prasad Ghimiray
2025-04-17  4:54   ` Matthew Brost
2025-04-24 10:03     ` Ghimiray, Himal Prasad [this message]
2025-04-24 23:48   ` Matthew Brost
2025-04-28  6:44     ` Ghimiray, Himal Prasad
2025-04-07 10:17 ` [PATCH v2 15/32] drm/xe/vm: Add debug prints for SVM range prefetch Himal Prasad Ghimiray
2025-04-17  4:56   ` Matthew Brost
2025-04-07 10:17 ` [PATCH v2 16/32] Introduce drm_gpuvm_sm_map_ops_flags enums for sm_map_ops Himal Prasad Ghimiray
2025-04-07 10:30   ` Boris Brezillon
2025-05-26 13:48     ` Ghimiray, Himal Prasad
2025-04-07 22:42   ` kernel test robot
2025-04-07 10:17 ` [PATCH v2 17/32] drm/xe/uapi: Add madvise interface Himal Prasad Ghimiray
2025-04-17 18:19   ` Souza, Jose
2025-04-17 18:24     ` Souza, Jose
2025-04-22 15:34       ` Matthew Brost
2025-04-22 15:55         ` Souza, Jose
2025-04-22 16:19           ` Matthew Brost
2025-04-22 15:40     ` Matthew Brost
2025-04-22 16:02       ` Souza, Jose
2025-04-22 16:12         ` Matthew Brost
2025-04-22 16:16           ` Souza, Jose
2025-05-02 14:00   ` Thomas Hellström
2025-05-20  8:13     ` Ghimiray, Himal Prasad
2025-05-20  8:49     ` Ghimiray, Himal Prasad
2025-04-07 10:17 ` [PATCH v2 18/32] drm/xe/vm: Add attributes struct as member of vma Himal Prasad Ghimiray
2025-05-14 18:36   ` Matthew Brost
2025-05-20  9:27     ` Ghimiray, Himal Prasad
2025-05-27 17:37       ` Matthew Brost
2025-05-28  5:33         ` Ghimiray, Himal Prasad
2025-05-28 16:09           ` Matthew Brost
2025-05-28 16:16             ` Ghimiray, Himal Prasad
2025-04-07 10:17 ` [PATCH v2 19/32] drm/xe/vma: Move pat_index to vma attributes Himal Prasad Ghimiray
2025-05-14 18:37   ` Matthew Brost
2025-04-07 10:17 ` [PATCH v2 20/32] drm/xe/vma: Modify new_vma to accept struct xe_vma_mem_attr as parameter Himal Prasad Ghimiray
2025-05-13  2:36   ` Matthew Brost
2025-05-14 18:40     ` Matthew Brost
2025-05-20  9:28       ` Ghimiray, Himal Prasad
2025-04-07 10:17 ` [PATCH v2 21/32] drm/gpusvm: Make drm_gpusvm_for_each_* macros public Himal Prasad Ghimiray
2025-04-08  1:49   ` kernel test robot
2025-05-14 18:47   ` Matthew Brost
2025-04-07 10:17 ` [PATCH v2 22/32] drm/xe/svm: Split system allocator vma incase of madvise call Himal Prasad Ghimiray
2025-05-14 19:01   ` Matthew Brost
2025-05-20  9:46     ` Ghimiray, Himal Prasad
2025-05-14 19:02   ` Matthew Brost
2025-04-07 10:17 ` [PATCH v2 23/32] drm/xe: Implement madvise ioctl for xe Himal Prasad Ghimiray
2025-05-14 21:41   ` Matthew Brost
2025-05-20 10:15     ` Ghimiray, Himal Prasad
2025-05-28  5:22       ` Ghimiray, Himal Prasad
2025-04-07 10:17 ` [PATCH v2 24/32] drm/xe: Allow CPU address mirror VMA unbind with gpu bindings for madvise Himal Prasad Ghimiray
2025-05-14 19:20   ` Matthew Brost
2025-05-20 10:21     ` Ghimiray, Himal Prasad
2025-05-27 17:32       ` Matthew Brost
2025-04-07 10:17 ` [PATCH v2 25/32] drm/xe/svm : Add svm ranges migration policy on atomic access Himal Prasad Ghimiray
2025-05-14 22:21   ` Matthew Brost
2025-05-20 10:22     ` Ghimiray, Himal Prasad
2025-04-07 10:17 ` [PATCH v2 26/32] drm/xe/madvise: Update migration policy based on preferred location Himal Prasad Ghimiray
2025-05-14 22:04   ` Matthew Brost
2025-05-21  8:50     ` Ghimiray, Himal Prasad
2025-05-21 16:51       ` Ghimiray, Himal Prasad
2025-04-07 10:17 ` [PATCH v2 27/32] drm/xe/svm: Support DRM_XE_SVM_ATTR_PAT memory attribute Himal Prasad Ghimiray
2025-05-14 21:52   ` Matthew Brost
2025-05-21  8:51     ` Ghimiray, Himal Prasad
2025-04-07 10:17 ` [PATCH v2 28/32] drm/xe/uapi: Add flag for consulting madvise hints on svm prefetch Himal Prasad Ghimiray
2025-05-14 21:05   ` Matthew Brost
2025-05-21  8:52     ` Ghimiray, Himal Prasad
2025-04-07 10:17 ` [PATCH v2 29/32] drm/xe/svm: Consult madvise preferred location in prefetch Himal Prasad Ghimiray
2025-05-14 22:17   ` Matthew Brost
2025-04-07 10:17 ` [PATCH v2 30/32] drm/xe/uapi: Add uapi for vma count and mem attributes Himal Prasad Ghimiray
2025-05-14 21:08   ` Matthew Brost
2025-05-21  8:54     ` Ghimiray, Himal Prasad
2025-05-28 16:18       ` Ghimiray, Himal Prasad
2025-04-07 10:17 ` [PATCH v2 31/32] drm/xe/bo: Add attributes field to xe_bo Himal Prasad Ghimiray
2025-05-14 21:10   ` Matthew Brost
2025-04-07 10:17 ` [PATCH v2 32/32] drm/xe/bo: Update atomic_access attribute on madvise Himal Prasad Ghimiray
2025-05-14 22:31   ` Matthew Brost
2025-05-21  9:13     ` Ghimiray, Himal Prasad
2025-04-07 14:07 ` ✓ CI.Patch_applied: success for PREFETCH and MADVISE for SVM ranges (rev3) Patchwork
2025-04-07 14:07 ` ✗ CI.checkpatch: warning " Patchwork
2025-04-07 14:09 ` ✓ CI.KUnit: success " Patchwork
2025-04-07 14:12 ` ✗ CI.Build: failure " Patchwork
2025-04-09  5:11 ` ✓ CI.Patch_applied: success for PREFETCH and MADVISE for SVM ranges (rev4) Patchwork
2025-04-09  5:11 ` ✗ CI.checkpatch: warning " Patchwork
2025-04-09  5:12 ` ✓ CI.KUnit: success " Patchwork
2025-04-09  5:29 ` ✓ CI.Build: " Patchwork
2025-04-09  5:31 ` ✗ CI.Hooks: failure " Patchwork
2025-04-09  5:32 ` ✗ CI.checksparse: warning " Patchwork
2025-04-09  5:52 ` ✓ Xe.CI.BAT: success " Patchwork
2025-04-09  7:00 ` ✗ Xe.CI.Full: failure " Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=0f22ea7e-e6cf-4464-8044-4520ebe9ecd6@intel.com \
    --to=himal.prasad.ghimiray@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=matthew.brost@intel.com \
    --cc=thomas.hellstrom@linux.intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox