zswap is allocating acomp on one different cpu with those cpus which will eventually committing acomp_req. this patch specifies the numa node to help compression/decompression done by local (de)compressors hardware.
Cc: Seth Jennings <sjenn...@redhat.com> Cc: Dan Streetman <ddstr...@ieee.org> Cc: Vitaly Wool <vitaly.w...@konsulko.com> Cc: Herbert Xu <herb...@gondor.apana.org.au> Cc: David S. Miller" <da...@davemloft.net> Signed-off-by: Barry Song <song.bao....@hisilicon.com> --- -v2: patch is rebased againest "[PATCH] mm/zswap: careful error path implementation in comp_prepare" [1] [1] https://lkml.org/lkml/2020/6/22/347 mm/zswap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/zswap.c b/mm/zswap.c index c0a85ef46610..98db09524af6 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -438,7 +438,7 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) pr_err("Could not allocate acomp_ctx\n"); return -ENOMEM; } - acomp = crypto_alloc_acomp(pool->tfm_name, 0, 0); + acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu)); if (IS_ERR(acomp)) { pr_err("could not alloc crypto acomp %s : %ld\n", pool->tfm_name, PTR_ERR(acomp)); -- 2.27.0
