From aa26e08ed1c636c7c4d682e3d7b9a7ebe911bfcc Mon Sep 17 00:00:00 2001 From: Barry Song Date: Sat, 2 Mar 2024 08:27:45 +1300 Subject: crypto: scomp - remove memcpy if sg_nents is 1 and pages are lowmem while sg_nents is 1, which is always true for the current kernel as the only user - zswap is this case, we might have a chance to remove memcpy, thus improve the performance. Though sg_nents is 1, its buffer might cross two pages. If those pages are highmem, we have no cheap way to map them to contiguous virtual address because kmap doesn't support more than one page (kmap single higmem page could be still expensive for tlb) and vmap is expensive. So we also test and enure page is not highmem in order to safely use page_to_virt before removing the memcpy. The good news is that in the most majority of cases, we are lowmem, and we are always lowmem in those modern and popular hardware. Cc: Johannes Weiner Cc: Nhat Pham Cc: Yosry Ahmed Signed-off-by: Barry Song Tested-by: Chengming Zhou Signed-off-by: Herbert Xu --- crypto/scompress.c | 36 +++++++++++++++++++++++++++++------- 1 file changed, 29 insertions(+), 7 deletions(-) (limited to 'crypto') diff --git a/crypto/scompress.c b/crypto/scompress.c index 9cda4ef8..93daf3eb 100644 --- a/crypto/scompress.c +++ b/crypto/scompress.c @@ -117,6 +117,7 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) struct crypto_scomp *scomp = *tfm_ctx; void **ctx = acomp_request_ctx(req); struct scomp_scratch *scratch; + void *src, *dst; unsigned int dlen; int ret; @@ -134,13 +135,25 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) scratch = raw_cpu_ptr(&scomp_scratch); spin_lock(&scratch->lock); - scatterwalk_map_and_copy(scratch->src, req->src, 0, req->slen, 0); + if (sg_nents(req->src) == 1 && !PageHighMem(sg_page(req->src))) { + src = page_to_virt(sg_page(req->src)) + req->src->offset; + } else { + scatterwalk_map_and_copy(scratch->src, req->src, 0, + req->slen, 0); + src = scratch->src; + } + + if (req->dst && sg_nents(req->dst) == 1 && !PageHighMem(sg_page(req->dst))) + dst = page_to_virt(sg_page(req->dst)) + req->dst->offset; + else + dst = scratch->dst; + if (dir) - ret = crypto_scomp_compress(scomp, scratch->src, req->slen, - scratch->dst, &req->dlen, *ctx); + ret = crypto_scomp_compress(scomp, src, req->slen, + dst, &req->dlen, *ctx); else - ret = crypto_scomp_decompress(scomp, scratch->src, req->slen, - scratch->dst, &req->dlen, *ctx); + ret = crypto_scomp_decompress(scomp, src, req->slen, + dst, &req->dlen, *ctx); if (!ret) { if (!req->dst) { req->dst = sgl_alloc(req->dlen, GFP_ATOMIC, NULL); @@ -152,8 +165,17 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) ret = -ENOSPC; goto out; } - scatterwalk_map_and_copy(scratch->dst, req->dst, 0, req->dlen, - 1); + if (dst == scratch->dst) { + scatterwalk_map_and_copy(scratch->dst, req->dst, 0, + req->dlen, 1); + } else { + int nr_pages = DIV_ROUND_UP(req->dst->offset + req->dlen, PAGE_SIZE); + int i; + struct page *dst_page = sg_page(req->dst); + + for (i = 0; i < nr_pages; i++) + flush_dcache_page(dst_page + i); + } } out: spin_unlock(&scratch->lock); -- cgit v1.2.3