[PATCH v2 25/29] drm/xe: Basic SVM BO eviction

[Matthew Brost]

On Mon, Dec 02, 2024 at 01:27:24PM +0100, Thomas Hellström wrote:
> On Tue, 2024-10-15 at 20:25 -0700, Matthew Brost wrote:
> > Wire xe_bo_move to GPUSVM migration to SRAM with trylocking of mmap
> > lock.
> > 
> > v2:
> >  - Use xe_svm_bo_evict
> >  - Drop bo->range
> > 
> > Signed-off-by: Matthew Brost <matthew.brost at intel.com>
> > ---
> >  drivers/gpu/drm/xe/xe_bo.c  | 20 ++++++++++++++++++++
> >  drivers/gpu/drm/xe/xe_svm.c |  5 +++++
> >  drivers/gpu/drm/xe/xe_svm.h |  3 +++
> >  3 files changed, 28 insertions(+)
> > 
> > diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
> > index dbd03383878e..17d158762e03 100644
> > --- a/drivers/gpu/drm/xe/xe_bo.c
> > +++ b/drivers/gpu/drm/xe/xe_bo.c
> > @@ -25,6 +25,7 @@
> >  #include "xe_pm.h"
> >  #include "xe_preempt_fence.h"
> >  #include "xe_res_cursor.h"
> > +#include "xe_svm.h"
> >  #include "xe_trace_bo.h"
> >  #include "xe_ttm_stolen_mgr.h"
> >  #include "xe_vm.h"
> > @@ -250,6 +251,8 @@ int xe_bo_placement_for_flags(struct xe_device
> > *xe, struct xe_bo *bo,
> >  static void xe_evict_flags(struct ttm_buffer_object *tbo,
> >  			   struct ttm_placement *placement)
> >  {
> > +	struct xe_bo *bo;
> > +
> >  	if (!xe_bo_is_xe_bo(tbo)) {
> >  		/* Don't handle scatter gather BOs */
> >  		if (tbo->type == ttm_bo_type_sg) {
> > @@ -261,6 +264,12 @@ static void xe_evict_flags(struct
> > ttm_buffer_object *tbo,
> >  		return;
> >  	}
> >  
> > +	bo = ttm_to_xe_bo(tbo);
> > +	if (bo->flags & XE_BO_FLAG_SYSTEM_ALLOC) {
> > +		*placement = sys_placement;
> > +		return;
> > +	}
> > +
> >  	/*
> >  	 * For xe, sg bos that are evicted to system just triggers a
> >  	 * rebind of the sg list upon subsequent validation to
> > XE_PL_TT.
> > @@ -738,6 +747,17 @@ static int xe_bo_move(struct ttm_buffer_object
> > *ttm_bo, bool evict,
> >  		}
> >  	}
> >  
> > +	if (!move_lacks_source && (bo->flags &
> > XE_BO_FLAG_SYSTEM_ALLOC) &&
> > +	    new_mem->mem_type == XE_PL_SYSTEM) {
> > +		ret = xe_svm_bo_evict(bo);
> > +		if (!ret) {
> > +			drm_dbg(&xe->drm, "Evict system allocator BO
> > success\n");
> > +			ttm_bo_move_null(ttm_bo, new_mem);
> > +		}
> > +
> > +		goto out;
> > +	}
> > +
> >  	if (!move_lacks_source &&
> >  	    ((old_mem_type == XE_PL_SYSTEM &&
> > resource_is_vram(new_mem)) ||
> >  	     (mem_type_is_vram(old_mem_type) &&
> > diff --git a/drivers/gpu/drm/xe/xe_svm.c
> > b/drivers/gpu/drm/xe/xe_svm.c
> > index 31b80cde15c4..555bc71ae523 100644
> > --- a/drivers/gpu/drm/xe/xe_svm.c
> > +++ b/drivers/gpu/drm/xe/xe_svm.c
> > @@ -752,3 +752,8 @@ int xe_devm_add(struct xe_tile *tile, struct
> > xe_mem_region *mr)
> >  		 tile->id, mr->io_start, mr->io_start + mr-
> > >usable_size, res);
> >  	return 0;
> >  }
> > +
> > +int xe_svm_bo_evict(struct xe_bo *bo)
> 
> Kerneldoc. Also important IMO to specify the contract that if this
> function returns success, then no VRAM pages must be in use anymore
> since we will free the vram resource. (Can we guaranteee that?)
> 

Will add kernel doc. Yes, we guaranteee that all VRAM pages are evicted
with a retry loop in the GPUSVM layer.

Matt

> 
> Thanks,
> Thomas
> 
> 
> > +{
> > +	return drm_gpusvm_evict_to_ram(&bo->devmem_allocation);
> > +}
> > diff --git a/drivers/gpu/drm/xe/xe_svm.h
> > b/drivers/gpu/drm/xe/xe_svm.h
> > index 6893664dae70..5b9d5ac9ef72 100644
> > --- a/drivers/gpu/drm/xe/xe_svm.h
> > +++ b/drivers/gpu/drm/xe/xe_svm.h
> > @@ -11,6 +11,7 @@
> >  
> >  #define XE_INTERCONNECT_VRAM DRM_INTERCONNECT_DRIVER
> >  
> > +struct xe_bo;
> >  struct xe_mem_region;
> >  struct xe_tile;
> >  struct xe_vm;
> > @@ -35,6 +36,8 @@ int xe_svm_handle_pagefault(struct xe_vm *vm,
> > struct xe_vma *vma,
> >  			    bool atomic);
> >  bool xe_svm_has_mapping(struct xe_vm *vm, u64 start, u64 end);
> >  
> > +int xe_svm_bo_evict(struct xe_bo *bo);
> > +
> >  static inline bool xe_svm_range_pages_valid(struct xe_svm_range
> > *range)
> >  {
> >  	return drm_gpusvm_range_pages_valid(range->base.gpusvm,
> > &range->base);
>