[PATCH v7 3/9] drm/i915/gt: Optimize the migration and clear loop

[Balasubramani Vivekanandan]

On 01.04.2022 18:07, Ramalingam C wrote:
> Move the static calculations out of the loops for copy and clear.
> 
> Signed-off-by: Ramalingam C <ramalingam.c at intel.com>
> Reviewed-by: Thomas Hellstrom <thomas.hellstrom at linux.intel.com>
> ---
>  drivers/gpu/drm/i915/gt/intel_migrate.c | 40 ++++++++++++-------------
>  1 file changed, 19 insertions(+), 21 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c
> index e81f20266f62..580b4cf1efa2 100644
> --- a/drivers/gpu/drm/i915/gt/intel_migrate.c
> +++ b/drivers/gpu/drm/i915/gt/intel_migrate.c
> @@ -526,6 +526,7 @@ intel_context_migrate_copy(struct intel_context *ce,
>  			   struct i915_request **out)
>  {
>  	struct sgt_dma it_src = sg_sgt(src), it_dst = sg_sgt(dst);
> +	u32 src_offset, dst_offset;
>  	struct i915_request *rq;
>  	int err;
>  
> @@ -535,8 +536,18 @@ intel_context_migrate_copy(struct intel_context *ce,
>  
>  	GEM_BUG_ON(ce->ring->size < SZ_64K);
>  
> +	src_offset = 0;
> +	dst_offset = CHUNK_SZ;
> +	if (HAS_64K_PAGES(ce->engine->i915)) {
> +		src_offset = 0;
> +		dst_offset = 0;
> +		if (src_is_lmem)
> +			src_offset = CHUNK_SZ;
> +		if (dst_is_lmem)
> +			dst_offset = 2 * CHUNK_SZ;
> +	}
> +
>  	do {
> -		u32 src_offset, dst_offset;
>  		int len;
>  
>  		rq = i915_request_create(ce);
> @@ -564,17 +575,6 @@ intel_context_migrate_copy(struct intel_context *ce,
>  		if (err)
>  			goto out_rq;
>  
> -		src_offset = 0;
> -		dst_offset = CHUNK_SZ;
> -		if (HAS_64K_PAGES(ce->engine->i915)) {
> -			src_offset = 0;
> -			dst_offset = 0;
> -			if (src_is_lmem)
> -				src_offset = CHUNK_SZ;
> -			if (dst_is_lmem)
> -				dst_offset = 2 * CHUNK_SZ;
> -		}
> -
>  		len = emit_pte(rq, &it_src, src_cache_level, src_is_lmem,
>  			       src_offset, CHUNK_SZ);
>  		if (len <= 0) {
> @@ -584,12 +584,10 @@ intel_context_migrate_copy(struct intel_context *ce,
>  
>  		err = emit_pte(rq, &it_dst, dst_cache_level, dst_is_lmem,
>  			       dst_offset, len);
> -		if (err < 0)
> -			goto out_rq;
> -		if (err < len) {
> +		if (err < len)
>  			err = -EINVAL;
> +		if (err < 0)
>  			goto out_rq;
> -		}
did you take a look at my comment at https://patchwork.freedesktop.org/patch/479847/?series=101106&rev=6?
Above change looks like a regression, can you check again?

Regards,
Bala

>  
>  		err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
>  		if (err)
> @@ -690,6 +688,7 @@ intel_context_migrate_clear(struct intel_context *ce,
>  {
>  	struct sgt_dma it = sg_sgt(sg);
>  	struct i915_request *rq;
> +	u32 offset;
>  	int err;
>  
>  	GEM_BUG_ON(ce->vm != ce->engine->gt->migrate.context->vm);
> @@ -697,8 +696,11 @@ intel_context_migrate_clear(struct intel_context *ce,
>  
>  	GEM_BUG_ON(ce->ring->size < SZ_64K);
>  
> +	offset = 0;
> +	if (HAS_64K_PAGES(ce->engine->i915) && is_lmem)
> +		offset = CHUNK_SZ;
> +
>  	do {
> -		u32 offset;
>  		int len;
>  
>  		rq = i915_request_create(ce);
> @@ -726,10 +728,6 @@ intel_context_migrate_clear(struct intel_context *ce,
>  		if (err)
>  			goto out_rq;
>  
> -		offset = 0;
> -		if (HAS_64K_PAGES(ce->engine->i915) && is_lmem)
> -			offset = CHUNK_SZ;
> -
>  		len = emit_pte(rq, &it, cache_level, is_lmem, offset, CHUNK_SZ);
>  		if (len <= 0) {
>  			err = len;
> -- 
> 2.20.1
>