Received-SPF: pass (google.com: domain of linux-kernel+bounces-179570-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
From: Sergey Senozhatsky <senozhatsky@chromium.org>
To: Andrew Morton <akpm@linux-foundation.org>,
	Minchan Kim <minchan@kernel.org>
Cc: linux-kernel@vger.kernel.org,
	linux-block@vger.kernel.org,
	Sergey Senozhatsky <senozhatsky@chromium.org>
Subject: [PATCHv4 18/21] zram: add dictionary support to lz4
Date: Wed, 15 May 2024 16:12:55 +0900
Message-ID: <20240515071645.1788128-19-senozhatsky@chromium.org>
In-Reply-To: <20240515071645.1788128-1-senozhatsky@chromium.org>
References: <20240515071645.1788128-1-senozhatsky@chromium.org>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

Support pre-trained dictionary param. lz4 doesn't
mandate specific format of the dictionary and even
zstd --train can be used to train a dictionary for
lz4, according to [1].

TEST
====

- default lz4

/sys/block/zram0/mm_stat
1750323200 664258735 676990976        0 676990976        2        0    34288    34288

- lz4 dict=/etc/dictionary

/sys/block/zram0/mm_stat
1750310912 620608254 632852480        0 632852480        1        0    34288    34288

[1] https://github.com/lz4/lz4/issues/557

Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
---
 drivers/block/zram/backend_lz4.c | 54 ++++++++++++++++++++++++++++----
 1 file changed, 48 insertions(+), 6 deletions(-)

diff --git a/drivers/block/zram/backend_lz4.c b/drivers/block/zram/backend_lz4.c
index cf39bfc30f5b..47d0e719d5d7 100644
--- a/drivers/block/zram/backend_lz4.c
+++ b/drivers/block/zram/backend_lz4.c
@@ -8,6 +8,12 @@
 struct lz4_ctx {
 	void *mem;
 	s32 level;
+	LZ4_streamDecode_t *dstrm;
+	LZ4_stream_t *cstrm;
+
+	/* Shared between C/D streams */
+	void *dict;
+	size_t dict_sz;
 };
 
 static int lz4_init_config(struct zcomp_config *config)
@@ -26,6 +32,8 @@ static void lz4_destroy(void *ctx)
 {
 	struct lz4_ctx *zctx = ctx;
 
+	kfree(zctx->dstrm);
+	kfree(zctx->cstrm);
 	vfree(zctx->mem);
 	kfree(zctx);
 }
@@ -39,9 +47,22 @@ static void *lz4_create(struct zcomp_config *config)
 		return NULL;
 
 	ctx->level = config->level;
-	ctx->mem = vmalloc(LZ4_MEM_COMPRESS);
-	if (!ctx->mem)
-		goto error;
+	if (!config->dict) {
+		ctx->mem = vmalloc(LZ4_MEM_COMPRESS);
+		if (!ctx->mem)
+			goto error;
+	} else {
+		ctx->dstrm = kzalloc(sizeof(*ctx->dstrm), GFP_KERNEL);
+		if (!ctx->dstrm)
+			goto error;
+
+		ctx->cstrm = kzalloc(sizeof(*ctx->cstrm), GFP_KERNEL);
+		if (!ctx->cstrm)
+			goto error;
+
+		ctx->dict = config->dict;
+		ctx->dict_sz = config->dict_sz;
+	}
 
 	return ctx;
 error:
@@ -55,8 +76,18 @@ static int lz4_compress(void *ctx, const unsigned char *src,
 	struct lz4_ctx *zctx = ctx;
 	int ret;
 
-	ret = LZ4_compress_fast(src, dst, PAGE_SIZE, *dst_len,
-				zctx->level, zctx->mem);
+	if (!zctx->cstrm) {
+		ret = LZ4_compress_fast(src, dst, PAGE_SIZE, *dst_len,
+					zctx->level, zctx->mem);
+	} else {
+		/* Cstrm needs to be reset */
+		ret = LZ4_loadDict(zctx->cstrm, zctx->dict, zctx->dict_sz);
+		if (ret != zctx->dict_sz)
+			return -EINVAL;
+		ret = LZ4_compress_fast_continue(zctx->cstrm, src, dst,
+						 PAGE_SIZE, *dst_len,
+						 zctx->level);
+	}
 	if (!ret)
 		return -EINVAL;
 	*dst_len = ret;
@@ -66,10 +97,21 @@ static int lz4_compress(void *ctx, const unsigned char *src,
 static int lz4_decompress(void *ctx, const unsigned char *src,
 			  size_t src_len, unsigned char *dst)
 {
+	struct lz4_ctx *zctx = ctx;
 	int dst_len = PAGE_SIZE;
 	int ret;
 
-	ret = LZ4_decompress_safe(src, dst, src_len, dst_len);
+	if (!zctx->dstrm) {
+		ret = LZ4_decompress_safe(src, dst, src_len, dst_len);
+	} else {
+		/* Dstrm needs to be reset */
+		ret = LZ4_setStreamDecode(zctx->dstrm, zctx->dict,
+					  zctx->dict_sz);
+		if (!ret)
+			return -EINVAL;
+		ret = LZ4_decompress_safe_continue(zctx->dstrm, src, dst,
+						   src_len, dst_len);
+	}
 	if (ret < 0)
 		return -EINVAL;
 	return 0;
-- 
2.45.0.rc1.225.g2a3ae87e7f-goog