[Intel-gfx] [PATCH v2 2/3] drm/i915/gtt: Split gen8_ppgtt_clear_pte_range

[Mika Kuoppala]

Michał Winiarski <michal.winiarski at intel.com> writes:

> Let's use more top-down approach, where each gen8_ppgtt_clear_* function
> is responsible for clearing the struct passed as an argument and calling
> relevant clear_range functions on lower-level tables.
> Doing this rather than operating on PTE ranges makes the implementation
> of shrinking page tables quite simple.
>
> v2: Drop min when calculating num_entries, no negation in 48b ppgtt
> check, no newlines in vars block (Joonas)
>
> Cc: Chris Wilson <chris at chris-wilson.co.uk>
> Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
> Cc: Michel Thierry <michel.thierry at intel.com>
> Cc: Mika Kuoppala <mika.kuoppala at intel.com>
> Signed-off-by: Michał Winiarski <michal.winiarski at intel.com>

Reviewed-by: Mika Kuoppala <mika.kuoppala at intel.com>

> ---
>  drivers/gpu/drm/i915/i915_gem_gtt.c | 107 +++++++++++++++++++-----------------
>  1 file changed, 58 insertions(+), 49 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
> index 08e2f35..adabf58 100644
> --- a/drivers/gpu/drm/i915/i915_gem_gtt.c
> +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
> @@ -704,59 +704,78 @@ static int gen8_48b_mm_switch(struct i915_hw_ppgtt *ppgtt,
>  	return gen8_write_pdp(req, 0, px_dma(&ppgtt->pml4));
>  }
>  
> -static void gen8_ppgtt_clear_pte_range(struct i915_address_space *vm,
> -				       struct i915_page_directory_pointer *pdp,
> -				       uint64_t start,
> -				       uint64_t length,
> -				       gen8_pte_t scratch_pte)
> +static void gen8_ppgtt_clear_pt(struct i915_address_space *vm,
> +				struct i915_page_table *pt,
> +				uint64_t start,
> +				uint64_t length)
>  {
>  	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
> +
> +	unsigned int pte_start = gen8_pte_index(start);
> +	unsigned int num_entries = gen8_pte_count(start, length);
> +	uint64_t pte;
>  	gen8_pte_t *pt_vaddr;
> -	unsigned pdpe = gen8_pdpe_index(start);
> -	unsigned pde = gen8_pde_index(start);
> -	unsigned pte = gen8_pte_index(start);
> -	unsigned num_entries = length >> PAGE_SHIFT;
> -	unsigned last_pte, i;
> +	gen8_pte_t scratch_pte = gen8_pte_encode(vm->scratch_page.daddr,
> +						 I915_CACHE_LLC);
>  
> -	if (WARN_ON(!pdp))
> +	if (WARN_ON(!px_page(pt)))
>  		return;
>  
> -	while (num_entries) {
> -		struct i915_page_directory *pd;
> -		struct i915_page_table *pt;
> +	bitmap_clear(pt->used_ptes, pte_start, num_entries);
>  
> -		if (WARN_ON(!pdp->page_directory[pdpe]))
> -			break;
> +	pt_vaddr = kmap_px(pt);
> +
> +	for (pte = pte_start; pte < num_entries; pte++)
> +		pt_vaddr[pte] = scratch_pte;
>  
> -		pd = pdp->page_directory[pdpe];
> +	kunmap_px(ppgtt, pt_vaddr);
> +}
> +
> +static void gen8_ppgtt_clear_pd(struct i915_address_space *vm,
> +				struct i915_page_directory *pd,
> +				uint64_t start,
> +				uint64_t length)
> +{
> +	struct i915_page_table *pt;
> +	uint64_t pde;
>  
> +	gen8_for_each_pde(pt, pd, start, length, pde) {
>  		if (WARN_ON(!pd->page_table[pde]))
>  			break;
>  
> -		pt = pd->page_table[pde];
> +		gen8_ppgtt_clear_pt(vm, pt, start, length);
> +	}
> +}
>  
> -		if (WARN_ON(!px_page(pt)))
> -			break;
> +static void gen8_ppgtt_clear_pdp(struct i915_address_space *vm,
> +				 struct i915_page_directory_pointer *pdp,
> +				 uint64_t start,
> +				 uint64_t length)
> +{
> +	struct i915_page_directory *pd;
> +	uint64_t pdpe;
>  
> -		last_pte = pte + num_entries;
> -		if (last_pte > GEN8_PTES)
> -			last_pte = GEN8_PTES;
> +	gen8_for_each_pdpe(pd, pdp, start, length, pdpe) {
> +		if (WARN_ON(!pdp->page_directory[pdpe]))
> +			break;
>  
> -		pt_vaddr = kmap_px(pt);
> +		gen8_ppgtt_clear_pd(vm, pd, start, length);
> +	}
> +}
>  
> -		for (i = pte; i < last_pte; i++) {
> -			pt_vaddr[i] = scratch_pte;
> -			num_entries--;
> -		}
> +static void gen8_ppgtt_clear_pml4(struct i915_address_space *vm,
> +				  struct i915_pml4 *pml4,
> +				  uint64_t start,
> +				  uint64_t length)
> +{
> +	struct i915_page_directory_pointer *pdp;
> +	uint64_t pml4e;
>  
> -		kunmap_px(ppgtt, pt_vaddr);
> +	gen8_for_each_pml4e(pdp, pml4, start, length, pml4e) {
> +		if (WARN_ON(!pml4->pdps[pml4e]))
> +			break;
>  
> -		pte = 0;
> -		if (++pde == I915_PDES) {
> -			if (++pdpe == I915_PDPES_PER_PDP(vm->dev))
> -				break;
> -			pde = 0;
> -		}
> +		gen8_ppgtt_clear_pdp(vm, pdp, start, length);
>  	}
>  }
>  
> @@ -764,21 +783,11 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
>  				   uint64_t start, uint64_t length)
>  {
>  	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
> -	gen8_pte_t scratch_pte = gen8_pte_encode(vm->scratch_page.daddr,
> -						 I915_CACHE_LLC);
>  
> -	if (!USES_FULL_48BIT_PPGTT(vm->dev)) {
> -		gen8_ppgtt_clear_pte_range(vm, &ppgtt->pdp, start, length,
> -					   scratch_pte);
> -	} else {
> -		uint64_t pml4e;
> -		struct i915_page_directory_pointer *pdp;
> -
> -		gen8_for_each_pml4e(pdp, &ppgtt->pml4, start, length, pml4e) {
> -			gen8_ppgtt_clear_pte_range(vm, pdp, start, length,
> -						   scratch_pte);
> -		}
> -	}
> +	if (USES_FULL_48BIT_PPGTT(vm->dev))
> +		gen8_ppgtt_clear_pml4(vm, &ppgtt->pml4, start, length);
> +	else
> +		gen8_ppgtt_clear_pdp(vm, &ppgtt->pdp, start, length);
>  }
>  
>  static void
> -- 
> 2.7.4