[PATCH v5 27/32] drm/xe: Add SVM VRAM migration

[Thomas Hellström]

On Thu, 2025-02-20 at 15:53 +0000, Matthew Auld wrote:
> On 13/02/2025 02:11, Matthew Brost wrote:
> > Migration is implemented with range granularity, with VRAM backing
> > being
> > a VM private TTM BO (i.e., shares dma-resv with VM). The lifetime
> > of the
> > TTM BO is limited to when the SVM range is in VRAM (i.e., when a
> > VRAM
> > SVM range is migrated to SRAM, the TTM BO is destroyed).
> > 
> > The design choice for using TTM BO for VRAM backing store, as
> > opposed to
> > direct buddy allocation, is as follows:
> > 
> > - DRM buddy allocations are not at page granularity, offering no
> >    advantage over a BO.
> > - Unified eviction is required (SVM VRAM and TTM BOs need to be
> > able to
> >    evict each other).
> > - For exhaustive eviction [1], SVM VRAM allocations will almost
> > certainly
> >    require a dma-resv.
> > - Likely allocation size is 2M which makes of size of BO (872)
> >    acceptable per allocation (872 / 2M == .0004158).
> > 
> > With this, using TTM BO for VRAM backing store seems to be an
> > obvious
> > choice as it allows leveraging of the TTM eviction code.
> > 
> > Current migration policy is migrate any SVM range greater than or
> > equal
> > to 64k once.
> > 
> > [1] https://patchwork.freedesktop.org/series/133643/
> > 
> > v2:
> >   - Rebase on latest GPU SVM
> >   - Retry page fault on get pages returning mixed allocation
> >   - Use drm_gpusvm_devmem
> > v3:
> >   - Use new BO flags
> >   - New range structure (Thomas)
> >   - Hide migration behind Kconfig
> >   - Kernel doc (Thomas)
> >   - Use check_pages_threshold
> > v4:
> >   - Don't evict partial unmaps in garbage collector (Thomas)
> >   - Use %pe to print errors (Thomas)
> >   - Use %p to print pointers (Thomas)
> > v5:
> >   - Use range size helper (Thomas)
> >   - Make BO external (Thomas)
> >   - Set tile to NULL for BO creation (Thomas)
> >   - Drop BO mirror flag (Thomas)
> >   - Hold BO dma-resv lock across migration (Auld, Thomas)
> > 
> > Signed-off-by: Matthew Brost <matthew.brost at intel.com>
> > ---
> >   drivers/gpu/drm/xe/xe_svm.c | 111
> > ++++++++++++++++++++++++++++++++++--
> >   drivers/gpu/drm/xe/xe_svm.h |   5 ++
> >   2 files changed, 112 insertions(+), 4 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/xe/xe_svm.c
> > b/drivers/gpu/drm/xe/xe_svm.c
> > index 0a78a838508c..2e1e0f31c1a8 100644
> > --- a/drivers/gpu/drm/xe/xe_svm.c
> > +++ b/drivers/gpu/drm/xe/xe_svm.c
> > @@ -32,6 +32,11 @@ static unsigned long xe_svm_range_end(struct
> > xe_svm_range *range)
> >   	return drm_gpusvm_range_end(&range->base);
> >   }
> >   
> > +static unsigned long xe_svm_range_size(struct xe_svm_range *range)
> > +{
> > +	return drm_gpusvm_range_size(&range->base);
> > +}
> > +
> >   static void *xe_svm_devm_owner(struct xe_device *xe)
> >   {
> >   	return xe;
> > @@ -512,7 +517,6 @@ static int xe_svm_populate_devmem_pfn(struct
> > drm_gpusvm_devmem *devmem_allocatio
> >   	return 0;
> >   }
> >   
> > -__maybe_unused
> >   static const struct drm_gpusvm_devmem_ops gpusvm_devmem_ops = {
> >   	.devmem_release = xe_svm_devmem_release,
> >   	.populate_devmem_pfn = xe_svm_populate_devmem_pfn,
> > @@ -592,6 +596,71 @@ static bool xe_svm_range_is_valid(struct
> > xe_svm_range *range,
> >   	return (range->tile_present & ~range->tile_invalidated) &
> > BIT(tile->id);
> >   }
> >   
> > +static struct xe_vram_region *tile_to_vr(struct xe_tile *tile)
> > +{
> > +	return &tile->mem.vram;
> > +}
> > +
> > +static struct xe_bo *xe_svm_alloc_vram(struct xe_vm *vm, struct
> > xe_tile *tile,
> > +				       struct xe_svm_range *range,
> > +				       const struct drm_gpusvm_ctx
> > *ctx)
> > +{
> > +	struct mm_struct *mm = vm->svm.gpusvm.mm;
> > +	struct xe_vram_region *vr = tile_to_vr(tile);
> > +	struct drm_buddy_block *block;
> > +	struct list_head *blocks;
> > +	struct xe_bo *bo;
> > +	ktime_t end = 0;
> > +	int err;
> > +
> > +	if (!mmget_not_zero(mm))
> > +		return ERR_PTR(-EFAULT);
> > +	mmap_read_lock(mm);
> > +
> > +retry:
> > +	bo = xe_bo_create_locked(tile_to_xe(tile), NULL, NULL,
> > +				 xe_svm_range_size(range),
> > +				 ttm_bo_type_device,
> > +				 XE_BO_FLAG_VRAM_IF_DGFX(tile));
> 
> Just to confirm, there is nothing scary with the vram still
> potentially 
> being used by the GPU at this point (like with an async eviction +
> clear 
> op), right? At some point we have some kind of synchronisation before
> the user can touch this memory?

Good point. I don't think there is.

> 
> > +	if (IS_ERR(bo)) {
> > +		err = PTR_ERR(bo);
> > +		if (xe_vm_validate_should_retry(NULL, err, &end))
> > +			goto retry;
> > +		goto unlock;
> > +	}
> > +
> > +	drm_gpusvm_devmem_init(&bo->devmem_allocation,
> > +			       vm->xe->drm.dev, mm,
> > +			       &gpusvm_devmem_ops,
> > +			       &tile->mem.vram.dpagemap,
> > +			       xe_svm_range_size(range));
> > +
> > +	blocks = &to_xe_ttm_vram_mgr_resource(bo->ttm.resource)-
> > >blocks;
> > +	list_for_each_entry(block, blocks, link)
> > +		block->private = vr;
> > +
> > +	/*
> > +	 * Take ref because as soon as
> > drm_gpusvm_migrate_to_devmem succeeds the
> > +	 * creation ref can be dropped upon CPU fault or unmap.
> > +	 */
> > +	xe_bo_get(bo);
> > +
> > +	err = drm_gpusvm_migrate_to_devmem(&vm->svm.gpusvm,
> > &range->base,
> > +					   &bo->devmem_allocation,
> > ctx);
> > +	xe_bo_unlock(bo);
> > +	if (err) {
> > +		xe_bo_put(bo);	/* Local ref */
> > +		xe_bo_put(bo);	/* Creation ref */
> > +		bo = ERR_PTR(err);
> > +	}
> > +
> > +unlock:
> > +	mmap_read_unlock(mm);
> > +	mmput(mm);
> > +
> > +	return bo;
> > +}
> > +
> >   /**
> >    * xe_svm_handle_pagefault() - SVM handle page fault
> >    * @vm: The VM.
> > @@ -600,7 +669,8 @@ static bool xe_svm_range_is_valid(struct
> > xe_svm_range *range,
> >    * @fault_addr: The GPU fault address.
> >    * @atomic: The fault atomic access bit.
> >    *
> > - * Create GPU bindings for a SVM page fault.
> > + * Create GPU bindings for a SVM page fault. Optionally migrate to
> > device
> > + * memory.
> >    *
> >    * Return: 0 on success, negative error code on error.
> >    */
> > @@ -608,11 +678,18 @@ int xe_svm_handle_pagefault(struct xe_vm *vm,
> > struct xe_vma *vma,
> >   			    struct xe_tile *tile, u64 fault_addr,
> >   			    bool atomic)
> >   {
> > -	struct drm_gpusvm_ctx ctx = { .read_only =
> > xe_vma_read_only(vma), };
> > +	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 *range;
> >   	struct drm_gpusvm_range *r;
> >   	struct drm_exec exec;
> >   	struct dma_fence *fence;
> > +	struct xe_bo *bo = NULL;
> >   	ktime_t end = 0;
> >   	int err;
> >   
> > @@ -620,6 +697,9 @@ int xe_svm_handle_pagefault(struct xe_vm *vm,
> > struct xe_vma *vma,
> >   	xe_assert(vm->xe, xe_vma_is_cpu_addr_mirror(vma));
> >   
> >   retry:
> > +	xe_bo_put(bo);
> > +	bo = NULL;
> > +
> >   	/* Always process UNMAPs first so view SVM ranges is
> > current */
> >   	err = xe_svm_garbage_collector(vm);
> >   	if (err)
> > @@ -635,9 +715,31 @@ int xe_svm_handle_pagefault(struct xe_vm *vm,
> > struct xe_vma *vma,
> >   	if (xe_svm_range_is_valid(range, tile))
> >   		return 0;
> >   
> > +	/* XXX: Add migration policy, for now migrate range once
> > */
> > +	if (!range->migrated && range->base.flags.migrate_devmem
> > &&
> > +	    xe_svm_range_size(range) >= SZ_64K) {
> > +		range->migrated = true;
> > +
> > +		bo = xe_svm_alloc_vram(vm, tile, range, &ctx);
> > +		if (IS_ERR(bo)) {
> > +			drm_info(&vm->xe->drm,
> > +				 "VRAM allocation failed, falling
> > back to retrying, asid=%u, errno %pe\n",
> > +				 vm->usm.asid, bo);
> > +			bo = NULL;
> > +			goto retry;
> > +		}
> > +	}
> > +
> >   	err = drm_gpusvm_range_get_pages(&vm->svm.gpusvm, r,
> > &ctx);
> > -	if (err == -EFAULT || err == -EPERM)	/* Corner where
> > CPU mappings have changed */
> > +	/* Corner where CPU mappings have changed */
> > +	if (err == -EOPNOTSUPP || err == -EFAULT || err == -EPERM)
> > {
> > +		if (err == -EOPNOTSUPP)
> > +			drm_gpusvm_range_evict(&vm->svm.gpusvm,
> > &range->base);
> > +		drm_info(&vm->xe->drm,
> > +			 "Get pages failed, falling back to
> > retrying, asid=%u, gpusvm=%p, errno %pe\n",
> > +			 vm->usm.asid, &vm->svm.gpusvm,
> > ERR_PTR(err));
> >   		goto retry;
> > +	}
> >   	if (err)
> >   		goto err_out;
> >   
> > @@ -668,6 +770,7 @@ int xe_svm_handle_pagefault(struct xe_vm *vm,
> > struct xe_vma *vma,
> >   	dma_fence_put(fence);
> >   
> >   err_out:
> > +	xe_bo_put(bo);
> >   
> >   	return err;
> >   }
> > diff --git a/drivers/gpu/drm/xe/xe_svm.h
> > b/drivers/gpu/drm/xe/xe_svm.h
> > index 0fa525d34987..984a61651d9e 100644
> > --- a/drivers/gpu/drm/xe/xe_svm.h
> > +++ b/drivers/gpu/drm/xe/xe_svm.h
> > @@ -35,6 +35,11 @@ struct xe_svm_range {
> >   	 * range. Protected by GPU SVM notifier lock.
> >   	 */
> >   	u8 tile_invalidated;
> > +	/**
> > +	 * @migrated: Range has been migrated to device memory,
> > protected by
> > +	 * GPU fault handler locking.
> > +	 */
> > +	u8 migrated	:1;
> >   };
> >   
> >   int xe_devm_add(struct xe_tile *tile, struct xe_vram_region *vr);
>