[Intel-gfx] [PATCH v2 2/4] drm/i915/gt: optimize the ccs_sz calculation per chunk

[Matthew Auld]

On 25/04/2022 17:24, Ramalingam C wrote:
> Calculate the ccs_sz that needs to be emitted based on the src
> and dst pages emitted per chunk. And handle the return value of emit_pte
> for the ccs pages.
> 
> Signed-off-by: Ramalingam C <ramalingam.c at intel.com>
> ---
>   drivers/gpu/drm/i915/gt/intel_migrate.c | 36 +++++++++----------------
>   1 file changed, 12 insertions(+), 24 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c
> index 29d761da02c4..463a6a14b5f9 100644
> --- a/drivers/gpu/drm/i915/gt/intel_migrate.c
> +++ b/drivers/gpu/drm/i915/gt/intel_migrate.c
> @@ -647,17 +647,9 @@ static int scatter_list_length(struct scatterlist *sg)
>   
>   static void
>   calculate_chunk_sz(struct drm_i915_private *i915, bool src_is_lmem,
> -		   int *src_sz, int *ccs_sz, u32 bytes_to_cpy,
> -		   u32 ccs_bytes_to_cpy)
> +		   int *src_sz, u32 bytes_to_cpy, u32 ccs_bytes_to_cpy)
>   {
>   	if (ccs_bytes_to_cpy) {
> -		/*
> -		 * We can only copy the ccs data corresponding to
> -		 * the CHUNK_SZ of lmem which is
> -		 * GET_CCS_BYTES(i915, CHUNK_SZ))
> -		 */
> -		*ccs_sz = min_t(int, ccs_bytes_to_cpy, GET_CCS_BYTES(i915, CHUNK_SZ));
> -
>   		if (!src_is_lmem)
>   			/*
>   			 * When CHUNK_SZ is passed all the pages upto CHUNK_SZ
> @@ -713,10 +705,10 @@ intel_context_migrate_copy(struct intel_context *ce,
>   	struct drm_i915_private *i915 = ce->engine->i915;
>   	u32 ccs_bytes_to_cpy = 0, bytes_to_cpy;
>   	enum i915_cache_level ccs_cache_level;
> -	int src_sz, dst_sz, ccs_sz;
>   	u32 src_offset, dst_offset;
>   	u8 src_access, dst_access;
>   	struct i915_request *rq;
> +	int src_sz, dst_sz;
>   	bool ccs_is_src;
>   	int err;
>   
> @@ -770,7 +762,7 @@ intel_context_migrate_copy(struct intel_context *ce,
>   	}
>   
>   	do {
> -		int len;
> +		int len, ccs_sz;

This could be moved into the reduced scope below.

Reviewed-by: Matthew Auld <matthew.auld at intel.com>

>   
>   		rq = i915_request_create(ce);
>   		if (IS_ERR(rq)) {
> @@ -797,7 +789,7 @@ intel_context_migrate_copy(struct intel_context *ce,
>   		if (err)
>   			goto out_rq;
>   
> -		calculate_chunk_sz(i915, src_is_lmem, &src_sz, &ccs_sz,
> +		calculate_chunk_sz(i915, src_is_lmem, &src_sz,
>   				   bytes_to_cpy, ccs_bytes_to_cpy);
>   
>   		len = emit_pte(rq, &it_src, src_cache_level, src_is_lmem,
> @@ -835,33 +827,29 @@ intel_context_migrate_copy(struct intel_context *ce,
>   			if (err)
>   				goto out_rq;
>   
> +			ccs_sz = GET_CCS_BYTES(i915, len);
>   			err = emit_pte(rq, &it_ccs, ccs_cache_level, false,
>   				       ccs_is_src ? src_offset : dst_offset,
>   				       ccs_sz);
> +			if (err < 0)
> +				goto out_rq;
> +			if (err < ccs_sz) {
> +				err = -EINVAL;
> +				goto out_rq;
> +			}
>   
>   			err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
>   			if (err)
>   				goto out_rq;
>   
> -			/*
> -			 * Using max of src_sz and dst_sz, as we need to
> -			 * pass the lmem size corresponding to the ccs
> -			 * blocks we need to handle.
> -			 */
> -			ccs_sz = max_t(int, ccs_is_src ? ccs_sz : src_sz,
> -				       ccs_is_src ? dst_sz : ccs_sz);
> -
>   			err = emit_copy_ccs(rq, dst_offset, dst_access,
> -					    src_offset, src_access, ccs_sz);
> +					    src_offset, src_access, len);
>   			if (err)
>   				goto out_rq;
>   
>   			err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
>   			if (err)
>   				goto out_rq;
> -
> -			/* Converting back to ccs bytes */
> -			ccs_sz = GET_CCS_BYTES(rq->engine->i915, ccs_sz);
>   			ccs_bytes_to_cpy -= ccs_sz;
>   		}
>