[PATCHv3] drm/xe/display: use mul_u32_u32 for multiplying operands

[Rodrigo Vivi]

On Wed, Apr 10, 2024 at 08:18:10AM +0530, Arun R Murthy wrote:
> Use mul_u32_u32 to avoid potential overflow in multiplying two u32 and
> store the u64 result.
> 
> v2: remove u64 typecast and use mul_u32_u32 (Ville)
> v3: Reframe the commit message <Rodrigo>

I still believe that the message is not that clear tbh.
I mean, just by reading that without the understanding of the flow,
one might simply ask, how can you overflow a 64bit with a u32 times u32?

I was going to tweak that while pushing, but I got a conflict.

So it needs a rebase anyway, so probably making sure that it is
clear that compiler can use a u32 for storing the multiplication
before it moves the result to the u64 and that could overflow.
So, this cast forces the compiler to already use a u64 during
the multiplication, before the final store.

> 
> Signed-off-by: Arun R Murthy <arun.r.murthy at intel.com>
> ---
>  drivers/gpu/drm/xe/display/xe_fb_pin.c | 10 +++++-----
>  1 file changed, 5 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c
> index 3a584bc3a0a3..c73054c09ae9 100644
> --- a/drivers/gpu/drm/xe/display/xe_fb_pin.c
> +++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c
> @@ -29,7 +29,7 @@ write_dpt_rotated(struct xe_bo *bo, struct iosys_map *map, u32 *dpt_ofs, u32 bo_
>  		u32 src_idx = src_stride * (height - 1) + column + bo_ofs;
>  
>  		for (row = 0; row < height; row++) {
> -			u64 pte = ggtt->pt_ops->pte_encode_bo(bo, src_idx * XE_PAGE_SIZE,
> +			u64 pte = ggtt->pt_ops->pte_encode_bo(bo, mul_u32_u32(src_idx, XE_PAGE_SIZE),
>  							      xe->pat.idx[XE_CACHE_NONE]);
>  
>  			iosys_map_wr(map, *dpt_ofs, u64, pte);
> @@ -61,8 +61,8 @@ write_dpt_remapped(struct xe_bo *bo, struct iosys_map *map, u32 *dpt_ofs,
>  
>  		for (column = 0; column < width; column++) {
>  			iosys_map_wr(map, *dpt_ofs, u64,
> -				     pte_encode_bo(bo, src_idx * XE_PAGE_SIZE,
> -				     xe->pat.idx[XE_CACHE_NONE]));
> +				     pte_encode_bo(bo, mul_u32_u32(src_idx, XE_PAGE_SIZE),
> +						   xe->pat.idx[XE_CACHE_NONE]));
>  
>  			*dpt_ofs += 8;
>  			src_idx++;
> @@ -121,7 +121,7 @@ static int __xe_pin_fb_vma_dpt(struct intel_framebuffer *fb,
>  		u32 x;
>  
>  		for (x = 0; x < size / XE_PAGE_SIZE; x++) {
> -			u64 pte = ggtt->pt_ops->pte_encode_bo(bo, x * XE_PAGE_SIZE,
> +			u64 pte = ggtt->pt_ops->pte_encode_bo(bo, mul_u32_u32(x, XE_PAGE_SIZE),
>  							      xe->pat.idx[XE_CACHE_NONE]);
>  
>  			iosys_map_wr(&dpt->vmap, x * 8, u64, pte);
> @@ -167,7 +167,7 @@ write_ggtt_rotated(struct xe_bo *bo, struct xe_ggtt *ggtt, u32 *ggtt_ofs, u32 bo
>  		u32 src_idx = src_stride * (height - 1) + column + bo_ofs;
>  
>  		for (row = 0; row < height; row++) {
> -			u64 pte = ggtt->pt_ops->pte_encode_bo(bo, src_idx * XE_PAGE_SIZE,
> +			u64 pte = ggtt->pt_ops->pte_encode_bo(bo, mul_u32_u32(src_idx, XE_PAGE_SIZE),
>  							      xe->pat.idx[XE_CACHE_NONE]);
>  
>  			xe_ggtt_set_pte(ggtt, *ggtt_ofs, pte);
> -- 
> 2.25.1
>