Received-SPF: pass (google.com: domain of linux-crypto+bounces-2145-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
From: Barry Song <21cnbao@gmail.com>
To: akpm@linux-foundation.org,
	davem@davemloft.net,
	hannes@cmpxchg.org,
	herbert@gondor.apana.org.au,
	linux-crypto@vger.kernel.org,
	linux-mm@kvack.org,
	nphamcs@gmail.com,
	yosryahmed@google.com,
	zhouchengming@bytedance.com
Cc: chriscli@google.com,
	chrisl@kernel.org,
	ddstreet@ieee.org,
	linux-kernel@vger.kernel.org,
	sjenning@redhat.com,
	vitaly.wool@konsulko.com,
	Barry Song <v-songbaohua@oppo.com>
Subject: [PATCH v3 3/3] crypto: scompress: remove memcpy if sg_nents is 1
Date: Sat, 17 Feb 2024 17:51:02 +1300
Message-Id: <20240217045102.55339-4-21cnbao@gmail.com>
In-Reply-To: <20240217045102.55339-1-21cnbao@gmail.com>
References: <20240217045102.55339-1-21cnbao@gmail.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

From: Barry Song <v-songbaohua@oppo.com>

while sg_nents is 1 which is always true for the current kernel
as the only user - zswap is the case, we should remove two big
memcpy.

Signed-off-by: Barry Song <v-songbaohua@oppo.com>
Tested-by: Chengming Zhou <zhouchengming@bytedance.com>
---
 crypto/scompress.c | 36 +++++++++++++++++++++++++++++-------
 1 file changed, 29 insertions(+), 7 deletions(-)

diff --git a/crypto/scompress.c b/crypto/scompress.c
index b108a30a7600..50a487eac792 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) {
+		src = kmap_local_page(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)
+		dst = kmap_local_page(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);
@@ -152,10 +165,19 @@ 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 {
+			flush_dcache_page(sg_page(req->dst));
+		}
 	}
 out:
+	if (src != scratch->src)
+		kunmap_local(src);
+	if (dst != scratch->dst)
+		kunmap_local(dst);
+
 	spin_unlock(&scratch->lock);
 	return ret;
 }
-- 
2.34.1