Commit a894c274 authored by Himal Prasad Ghimiray's avatar Himal Prasad Ghimiray
Browse files

drm/xe/madvise: Update migration policy based on preferred location 



When the user sets the valid devmem_fd as a preferred location, GPU fault
will trigger migration to tile of device associated with devmem_fd.

If the user sets an invalid devmem_fd the preferred location is current
placement(smem) only.

v2(Matthew Brost)
- Default should be faulting tile
- remove devmem_fd used as region

v3 (Matthew Brost)
- Add migration_policy
- Fix return condition
- fix migrate condition

v4
-Rebase

v5
- Add check for userptr and bo based vmas

Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: default avatarMatthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-11-himal.prasad.ghimiray@intel.com


Signed-off-by: default avatarHimal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
parent d6db1711

drivers/gpu/drm/xe/xe_svm.c

+44 −1
Original line number Diff line number Diff line
@@ -806,6 +806,7 @@ static int __xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma, 
	};

	struct xe_svm_range *range;

	struct dma_fence *fence;

	struct drm_pagemap *dpagemap;

	struct xe_tile *tile = gt_to_tile(gt);

	int migrate_try_count = ctx.devmem_only ? 3 : 1;

	ktime_t end = 0;
@@ -835,8 +836,14 @@ static int __xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma, 


	range_debug(range, "PAGE FAULT");



	dpagemap = xe_vma_resolve_pagemap(vma, tile);

	if (--migrate_try_count >= 0 &&

	    xe_svm_range_needs_migrate_to_vram(range, vma, IS_DGFX(vm->xe))) {

	    xe_svm_range_needs_migrate_to_vram(range, vma, !!dpagemap || ctx.devmem_only)) {

		/* TODO : For multi-device dpagemap will be used to find the

		 * remote tile and remote device. Will need to modify

		 * xe_svm_alloc_vram to use dpagemap for future multi-device

		 * support.

		 */

		err = xe_svm_alloc_vram(tile, range, &ctx);

		ctx.timeslice_ms <<= 1;	/* Double timeslice if we have to retry */

		if (err) {
@@ -1100,6 +1107,37 @@ static struct drm_pagemap *tile_local_pagemap(struct xe_tile *tile) 
	return &tile->mem.vram->dpagemap;

}



/**

 * xe_vma_resolve_pagemap - Resolve the appropriate DRM pagemap for a VMA

 * @vma: Pointer to the xe_vma structure containing memory attributes

 * @tile: Pointer to the xe_tile structure used as fallback for VRAM mapping

 *

 * This function determines the correct DRM pagemap to use for a given VMA.

 * It first checks if a valid devmem_fd is provided in the VMA's preferred

 * location. If the devmem_fd is negative, it returns NULL, indicating no

 * pagemap is available and smem to be used as preferred location.

 * If the devmem_fd is equal to the default faulting

 * GT identifier, it returns the VRAM pagemap associated with the tile.

 *

 * Future support for multi-device configurations may use drm_pagemap_from_fd()

 * to resolve pagemaps from arbitrary file descriptors.

 *

 * Return: A pointer to the resolved drm_pagemap, or NULL if none is applicable.

 */

struct drm_pagemap *xe_vma_resolve_pagemap(struct xe_vma *vma, struct xe_tile *tile)

{

	s32 fd = (s32)vma->attr.preferred_loc.devmem_fd;



	if (fd == DRM_XE_PREFERRED_LOC_DEFAULT_SYSTEM)

		return NULL;



	if (fd == DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE)

		return IS_DGFX(tile_to_xe(tile)) ? tile_local_pagemap(tile) : NULL;



	/* TODO: Support multi-device with drm_pagemap_from_fd(fd) */

	return NULL;

}



/**

 * xe_svm_alloc_vram()- Allocate device memory pages for range,

 * migrating existing data.
@@ -1212,6 +1250,11 @@ int xe_devm_add(struct xe_tile *tile, struct xe_vram_region *vr) 
{

	return 0;

}



struct drm_pagemap *xe_vma_resolve_pagemap(struct xe_vma *vma, struct xe_tile *tile)

{

	return NULL;

}

#endif



/**

drivers/gpu/drm/xe/xe_svm.h

+8 −0
Original line number Diff line number Diff line
@@ -94,6 +94,8 @@ void xe_svm_unmap_address_range(struct xe_vm *vm, u64 start, u64 end); 


u8 xe_svm_ranges_zap_ptes_in_range(struct xe_vm *vm, u64 start, u64 end);



struct drm_pagemap *xe_vma_resolve_pagemap(struct xe_vma *vma, struct xe_tile *tile);



/**

 * xe_svm_range_has_dma_mapping() - SVM range has DMA mapping

 * @range: SVM range
@@ -318,6 +320,12 @@ u8 xe_svm_ranges_zap_ptes_in_range(struct xe_vm *vm, u64 start, u64 end) 
	return 0;

}



static inline

struct drm_pagemap *xe_vma_resolve_pagemap(struct xe_vma *vma, struct xe_tile *tile)

{

	return NULL;

}



#define xe_svm_assert_in_notifier(...) do {} while (0)

#define xe_svm_range_has_dma_mapping(...) false

drivers/gpu/drm/xe/xe_vm_madvise.c

+24 −1
Original line number Diff line number Diff line
@@ -78,7 +78,23 @@ static void madvise_preferred_mem_loc(struct xe_device *xe, struct xe_vm *vm, 
				      struct xe_vma **vmas, int num_vmas,

				      struct drm_xe_madvise *op)

{

	/* Implementation pending */

	int i;



	xe_assert(vm->xe, op->type == DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC);



	for (i = 0; i < num_vmas; i++) {

		/*TODO: Extend attributes to bo based vmas */

		if (!xe_vma_is_cpu_addr_mirror(vmas[i]))

			continue;



		vmas[i]->attr.preferred_loc.devmem_fd = op->preferred_mem_loc.devmem_fd;



		/* Till multi-device support is not added migration_policy

		 * is of no use and can be ignored.

		 */

		vmas[i]->attr.preferred_loc.migration_policy =

						op->preferred_mem_loc.migration_policy;

	}

}



static void madvise_atomic(struct xe_device *xe, struct xe_vm *vm,
@@ -184,6 +200,12 @@ static bool madvise_args_are_sane(struct xe_device *xe, const struct drm_xe_madv 


	switch (args->type) {

	case DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC:

	{

		s32 fd = (s32)args->preferred_mem_loc.devmem_fd;



		if (XE_IOCTL_DBG(xe, fd < DRM_XE_PREFERRED_LOC_DEFAULT_SYSTEM))

			return false;



		if (XE_IOCTL_DBG(xe, args->preferred_mem_loc.migration_policy >

				     DRM_XE_MIGRATE_ONLY_SYSTEM_PAGES))

			return false;
@@ -194,6 +216,7 @@ static bool madvise_args_are_sane(struct xe_device *xe, const struct drm_xe_madv 
		if (XE_IOCTL_DBG(xe, args->atomic.reserved))

			return false;

		break;

	}

	case DRM_XE_MEM_RANGE_ATTR_ATOMIC:

		if (XE_IOCTL_DBG(xe, args->atomic.val > DRM_XE_ATOMIC_CPU))

			return false;