On Fri, Aug 1, 2025 at 4:36 PM Kanchana P Sridhar
<kanchana.p.sridhar@xxxxxxxxx> wrote:
>
> The Fixed ("deflate-iaa") and Dynamic ("deflate-iaa-dynamic") IAA
> acomp_algs register an implementation for get_batch_size(). zswap can
> query crypto_acomp_batch_size() to get the maximum number of requests
> that can be batch [de]compressed. zswap can use the minimum of this, and
> any zswap-specific upper limits for batch-size to allocate batching
> resources.
>
> This enables zswap to compress/decompress pages in parallel in the IAA
> hardware accelerator to improve swapout/swapin performance and memory
> savings.
>
> Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@xxxxxxxxx>
> ---
> drivers/crypto/intel/iaa/iaa_crypto_main.c | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c
> index 480e12c1d77a5..b7c6fc334dae7 100644
> --- a/drivers/crypto/intel/iaa/iaa_crypto_main.c
> +++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c
> @@ -2785,6 +2785,7 @@ static struct acomp_alg iaa_acomp_fixed_deflate = {
> .init = iaa_comp_init_fixed,
> .compress = iaa_comp_acompress_main,
> .decompress = iaa_comp_adecompress_main,
> + .get_batch_size = iaa_comp_get_max_batch_size,
> .base = {
> .cra_name = "deflate",
> .cra_driver_name = "deflate-iaa",
> @@ -2810,6 +2811,7 @@ static struct acomp_alg iaa_acomp_dynamic_deflate = {
> .init = iaa_comp_init_dynamic,
> .compress = iaa_comp_acompress_main,
> .decompress = iaa_comp_adecompress_main,
> + .get_batch_size = iaa_comp_get_max_batch_size,
I feel the patches are being split too finely and are not fully
self-contained. You added iaa_comp_get_max_batch_size in the previous
patch, but the callback appears in this one. Why not combine them
together? Anyway, since you are moving to a static field, this patch
will be removed automatically. Could you reconsider organizing v12
to make it easier for everyone to follow? :-)
Thanks
Barry
