Received-SPF: pass (google.com: domain of linux-crypto-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Nick Terrell <nickrterrell@gmail.com>
To:     Herbert Xu <herbert@gondor.apana.org.au>
Cc:     linux-crypto@vger.kernel.org, linux-btrfs@vger.kernel.org,
        squashfs-devel@lists.sourceforge.net,
        linux-f2fs-devel@lists.sourceforge.net,
        linux-kernel@vger.kernel.org, Kernel Team <Kernel-team@fb.com>,
        Nick Terrell <nickrterrell@gmail.com>,
        Nick Terrell <terrelln@fb.com>, Chris Mason <clm@fb.com>,
        Petr Malat <oss@malat.biz>, Johannes Weiner <jweiner@fb.com>,
        Niket Agarwal <niketa@fb.com>, Yann Collet <cyan@fb.com>
Subject: [PATCH v5 6/9] f2fs: zstd: Switch to the zstd-1.4.6 API
Date:   Mon,  2 Nov 2020 22:05:32 -0800
Message-Id: <20201103060535.8460-7-nickrterrell@gmail.com>
In-Reply-To: <20201103060535.8460-1-nickrterrell@gmail.com>
References: <20201103060535.8460-1-nickrterrell@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Nick Terrell <terrelln@fb.com>

Move away from the compatibility wrapper to the zstd-1.4.6 API. This
code is more efficient because it uses the single-pass API instead of
the streaming API. The streaming API is not necessary because the whole
input and output buffers are available. This saves memory because we
don't need to allocate a buffer for the window. It is also more
efficient because it saves unnecessary memcpy calls.

Compression memory increases from 168 KB to 204 KB because upstream
uses slightly more memory. Decompression memory decreases from 1.4 MB
to 158 KB.

Signed-off-by: Nick Terrell <terrelln@fb.com>
---
 fs/f2fs/compress.c | 101 +++++++++++++++++----------------------------
 1 file changed, 37 insertions(+), 64 deletions(-)

diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 57a6360b9827..8f8234877666 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -11,7 +11,8 @@
 #include <linux/backing-dev.h>
 #include <linux/lzo.h>
 #include <linux/lz4.h>
-#include <linux/zstd_compat.h>
+#include <linux/zstd.h>
+#include <linux/zstd_errors.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -322,21 +323,21 @@ static const struct f2fs_compress_ops f2fs_lz4_ops = {
 static int zstd_init_compress_ctx(struct compress_ctx *cc)
 {
 	ZSTD_parameters params;
-	ZSTD_CStream *stream;
+	ZSTD_CCtx *ctx;
 	void *workspace;
 	unsigned int workspace_size;
 
 	params = ZSTD_getParams(F2FS_ZSTD_DEFAULT_CLEVEL, cc->rlen, 0);
-	workspace_size = ZSTD_CStreamWorkspaceBound(params.cParams);
+	workspace_size = ZSTD_estimateCCtxSize_usingCParams(params.cParams);
 
 	workspace = f2fs_kvmalloc(F2FS_I_SB(cc->inode),
 					workspace_size, GFP_NOFS);
 	if (!workspace)
 		return -ENOMEM;
 
-	stream = ZSTD_initCStream(params, 0, workspace, workspace_size);
-	if (!stream) {
-		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_initCStream failed\n",
+	ctx = ZSTD_initStaticCCtx(workspace, workspace_size);
+	if (!ctx) {
+		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_inittaticCStream failed\n",
 				KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id,
 				__func__);
 		kvfree(workspace);
@@ -344,7 +345,7 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc)
 	}
 
 	cc->private = workspace;
-	cc->private2 = stream;
+	cc->private2 = ctx;
 
 	cc->clen = cc->rlen - PAGE_SIZE - COMPRESS_HEADER_SIZE;
 	return 0;
@@ -359,66 +360,48 @@ static void zstd_destroy_compress_ctx(struct compress_ctx *cc)
 
 static int zstd_compress_pages(struct compress_ctx *cc)
 {
-	ZSTD_CStream *stream = cc->private2;
-	ZSTD_inBuffer inbuf;
-	ZSTD_outBuffer outbuf;
-	int src_size = cc->rlen;
-	int dst_size = src_size - PAGE_SIZE - COMPRESS_HEADER_SIZE;
-	int ret;
-
-	inbuf.pos = 0;
-	inbuf.src = cc->rbuf;
-	inbuf.size = src_size;
-
-	outbuf.pos = 0;
-	outbuf.dst = cc->cbuf->cdata;
-	outbuf.size = dst_size;
+	ZSTD_CCtx *ctx = cc->private2;
+	const size_t src_size = cc->rlen;
+	const size_t dst_size = src_size - PAGE_SIZE - COMPRESS_HEADER_SIZE;
+	ZSTD_parameters params = ZSTD_getParams(F2FS_ZSTD_DEFAULT_CLEVEL, src_size, 0);
+	size_t ret;
 
-	ret = ZSTD_compressStream(stream, &outbuf, &inbuf);
+	ret = ZSTD_compress_advanced(
+			ctx, cc->cbuf->cdata, dst_size, cc->rbuf, src_size, NULL, 0, params);
 	if (ZSTD_isError(ret)) {
-		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_compressStream failed, ret: %d\n",
-				KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id,
-				__func__, ZSTD_getErrorCode(ret));
-		return -EIO;
-	}
-
-	ret = ZSTD_endStream(stream, &outbuf);
-	if (ZSTD_isError(ret)) {
-		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_endStream returned %d\n",
+		/*
+		 * there is compressed data remained in intermediate buffer due to
+		 * no more space in cbuf.cdata
+		 */
+		if (ZSTD_getErrorCode(ret) == ZSTD_error_dstSize_tooSmall)
+			return -EAGAIN;
+		/* other compression errors return -EIO */
+		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_compress_advanced failed, err: %s\n",
 				KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id,
-				__func__, ZSTD_getErrorCode(ret));
+				__func__, ZSTD_getErrorName(ret));
 		return -EIO;
 	}
 
-	/*
-	 * there is compressed data remained in intermediate buffer due to
-	 * no more space in cbuf.cdata
-	 */
-	if (ret)
-		return -EAGAIN;
-
-	cc->clen = outbuf.pos;
+	cc->clen = ret;
 	return 0;
 }
 
 static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic)
 {
-	ZSTD_DStream *stream;
+	ZSTD_DCtx *ctx;
 	void *workspace;
 	unsigned int workspace_size;
-	unsigned int max_window_size =
-			MAX_COMPRESS_WINDOW_SIZE(dic->log_cluster_size);
 
-	workspace_size = ZSTD_DStreamWorkspaceBound(max_window_size);
+	workspace_size = ZSTD_estimateDCtxSize();
 
 	workspace = f2fs_kvmalloc(F2FS_I_SB(dic->inode),
 					workspace_size, GFP_NOFS);
 	if (!workspace)
 		return -ENOMEM;
 
-	stream = ZSTD_initDStream(max_window_size, workspace, workspace_size);
-	if (!stream) {
-		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_initDStream failed\n",
+	ctx = ZSTD_initStaticDCtx(workspace, workspace_size);
+	if (!ctx) {
+		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_initStaticDCtx failed\n",
 				KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id,
 				__func__);
 		kvfree(workspace);
@@ -426,7 +409,7 @@ static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic)
 	}
 
 	dic->private = workspace;
-	dic->private2 = stream;
+	dic->private2 = ctx;
 
 	return 0;
 }
@@ -440,28 +423,18 @@ static void zstd_destroy_decompress_ctx(struct decompress_io_ctx *dic)
 
 static int zstd_decompress_pages(struct decompress_io_ctx *dic)
 {
-	ZSTD_DStream *stream = dic->private2;
-	ZSTD_inBuffer inbuf;
-	ZSTD_outBuffer outbuf;
-	int ret;
-
-	inbuf.pos = 0;
-	inbuf.src = dic->cbuf->cdata;
-	inbuf.size = dic->clen;
-
-	outbuf.pos = 0;
-	outbuf.dst = dic->rbuf;
-	outbuf.size = dic->rlen;
+	ZSTD_DCtx *ctx = dic->private2;
+	size_t ret;
 
-	ret = ZSTD_decompressStream(stream, &outbuf, &inbuf);
+	ret = ZSTD_decompressDCtx(ctx, dic->rbuf, dic->rlen, dic->cbuf->cdata, dic->clen);
 	if (ZSTD_isError(ret)) {
-		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_compressStream failed, ret: %d\n",
+		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_decompressDCtx failed, err: %s\n",
 				KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id,
-				__func__, ZSTD_getErrorCode(ret));
+				__func__, ZSTD_getErrorName(ret));
 		return -EIO;
 	}
 
-	if (dic->rlen != outbuf.pos) {
+	if (dic->rlen != ret) {
 		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD invalid rlen:%zu, "
 				"expected:%lu\n", KERN_ERR,
 				F2FS_I_SB(dic->inode)->sb->s_id,
-- 
2.28.0