f2fs: compress: support compress level

    mainline inclusion
    from mainline-v5.19
    commit 3fde13f8
    category: feature
    bugzilla: https://gitee.com/openeuler/kernel/issues/I5XET6
    CVE: NA
    ---------------------------------

    Expand 'compress_algorithm' mount option to accept parameter as format of
    <algorithm>:<level>, by this way, it gives a way to allow user to do more
    specified config on lz4 and zstd compression level, then f2fs compression
    can provide higher compress ratio.

    In order to set compress level for lz4 algorithm, it needs to set
    CONFIG_LZ4HC_COMPRESS and CONFIG_F2FS_FS_LZ4HC config to enable lz4hc
    compress algorithm.

    CR and performance number on lz4/lz4hc algorithm:

    dd if=enwik9 of=compressed_file conv=fsync

    Original blocks:        244382

                            lz4                     lz4hc-9
    compressed blocks       170647                  163270
    compress ratio          69.8%                   66.8%
    speed                   16.4207 s, 60.9 MB/s    26.7299 s, 37.4 MB/s

    compress ratio = after / before
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: NGewus <1319579758@qq.com>

Documentation/filesystems/f2fs.rst

@@ -249,6 +249,11 @@ checkpoint=%s[:%u[%]]	 Set to "disable" to turn off checkpointing. Set to "enabl
 			 This space is reclaimed once checkpoint=enable.
 compress_algorithm=%s	 Control compress algorithm, currently f2fs supports "lzo",
 			 "lz4", "zstd" and "lzo-rle" algorithm.
+compress_algorithm=%s:%d Control compress algorithm and its compress level, now, only
+			 "lz4" and "zstd" support compress level config.
+			 algorithm	level range
+			 lz4		3 - 16
+			 zstd		1 - 22
 compress_log_size=%u	 Support configuring compress cluster size, the size will
 			 be 4KB * (1 << %u), 16KB is minimum size, also it's
 			 default size.
@@ -260,6 +265,7 @@ compress_extension=%s	 Support adding specified extension, so that f2fs can enab
 			 For other files, we can still enable compression via ioctl.
 			 Note that, there is one reserved special extension '*', it
 			 can be set to enable compression for all files.
+compress_chksum		 Support verifying chksum of raw data in compressed cluster.
 inlinecrypt		 When possible, encrypt/decrypt the contents of encrypted
 			 files using the blk-crypto framework rather than
 			 filesystem-layer encryption. This allows the use of

fs/f2fs/Kconfig

@@ -119,6 +119,16 @@ config F2FS_FS_LZ4
 	help
 	  Support LZ4 compress algorithm, if unsure, say Y.
 
+config F2FS_FS_LZ4HC
+	bool "LZ4HC compression support"
+	depends on F2FS_FS_COMPRESSION
+	depends on F2FS_FS_LZ4
+	select LZ4HC_COMPRESS
+	default y
+	help
+	  Support LZ4HC compress algorithm, LZ4HC has compatible on-disk
+	  layout with LZ4, if unsure, say Y.
+
 config F2FS_FS_ZSTD
 	bool "ZSTD compression support"
 	depends on F2FS_FS_COMPRESSION

fs/f2fs/compress.c

@@ -240,8 +240,14 @@ static const struct f2fs_compress_ops f2fs_lzo_ops = {
 #ifdef CONFIG_F2FS_FS_LZ4
 static int lz4_init_compress_ctx(struct compress_ctx *cc)
 {
-	cc->private = f2fs_kvmalloc(F2FS_I_SB(cc->inode),
-				LZ4_MEM_COMPRESS, GFP_NOFS);
+	unsigned int size = LZ4_MEM_COMPRESS;
+
+#ifdef CONFIG_F2FS_FS_LZ4HC
+	if (F2FS_I(cc->inode)->i_compress_flag >> COMPRESS_LEVEL_OFFSET)
+		size = LZ4HC_MEM_COMPRESS;
+#endif
+
+	cc->private = f2fs_kvmalloc(F2FS_I_SB(cc->inode), size, GFP_NOFS);
 	if (!cc->private)
 		return -ENOMEM;
 
@@ -260,10 +266,34 @@ static void lz4_destroy_compress_ctx(struct compress_ctx *cc)
 	cc->private = NULL;
 }
 
+#ifdef CONFIG_F2FS_FS_LZ4HC
+static int lz4hc_compress_pages(struct compress_ctx *cc)
+{
+	unsigned char level = F2FS_I(cc->inode)->i_compress_flag >>
+						COMPRESS_LEVEL_OFFSET;
+	int len;
+
+	if (level)
+		len = LZ4_compress_HC(cc->rbuf, cc->cbuf->cdata, cc->rlen,
+					cc->clen, level, cc->private);
+	else
+		len = LZ4_compress_default(cc->rbuf, cc->cbuf->cdata, cc->rlen,
+						cc->clen, cc->private);
+	if (!len)
+		return -EAGAIN;
+
+	cc->clen = len;
+	return 0;
+}
+#endif
+
 static int lz4_compress_pages(struct compress_ctx *cc)
 {
 	int len;
 
+#ifdef CONFIG_F2FS_FS_LZ4HC
+	return lz4hc_compress_pages(cc);
+#endif
 	len = LZ4_compress_default(cc->rbuf, cc->cbuf->cdata, cc->rlen,
 						cc->clen, cc->private);
 	if (!len)
@@ -312,8 +342,13 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc)
 	ZSTD_CStream *stream;
 	void *workspace;
 	unsigned int workspace_size;
+	unsigned char level = F2FS_I(cc->inode)->i_compress_flag >>
+						COMPRESS_LEVEL_OFFSET;
 
-	params = ZSTD_getParams(F2FS_ZSTD_DEFAULT_CLEVEL, cc->rlen, 0);
+	if (!level)
+		level = F2FS_ZSTD_DEFAULT_CLEVEL;
+
+	params = ZSTD_getParams(level, cc->rlen, 0);
 	workspace_size = ZSTD_CStreamWorkspaceBound(params.cParams);
 
 	workspace = f2fs_kvmalloc(F2FS_I_SB(cc->inode),
@@ -589,6 +624,7 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 				f2fs_cops[fi->i_compress_algorithm];
 	unsigned int max_len, new_nr_cpages;
 	struct page **new_cpages;
+	u32 chksum = 0;
 	int i, ret;
 
 	trace_f2fs_compress_pages_start(cc->inode, cc->cluster_idx,
@@ -642,6 +678,11 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 
 	cc->cbuf->clen = cpu_to_le32(cc->clen);
 
+	if (fi->i_compress_flag & 1 << COMPRESS_CHKSUM)
+		chksum = f2fs_crc32(F2FS_I_SB(cc->inode),
+					cc->cbuf->cdata, cc->clen);
+	cc->cbuf->chksum = cpu_to_le32(chksum);
+
 	for (i = 0; i < COMPRESS_DATA_RESERVED_SIZE; i++)
 		cc->cbuf->reserved[i] = cpu_to_le32(0);
 
@@ -777,6 +818,23 @@ void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity)
 
 	ret = cops->decompress_pages(dic);
 
+	if (!ret && fi->i_compress_flag & 1 << COMPRESS_CHKSUM) {
+		u32 provided = le32_to_cpu(dic->cbuf->chksum);
+		u32 calculated = f2fs_crc32(sbi, dic->cbuf->cdata, dic->clen);
+
+		if (provided != calculated) {
+			if (!is_inode_flag_set(dic->inode, FI_COMPRESS_CORRUPT)) {
+				set_inode_flag(dic->inode, FI_COMPRESS_CORRUPT);
+				printk_ratelimited(
+					"%sF2FS-fs (%s): checksum invalid, nid = %lu, %x vs %x",
+					KERN_INFO, sbi->sb->s_id, dic->inode->i_ino,
+					provided, calculated);
+			}
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+			WARN_ON_ONCE(1);
+		}
+	}
+
 out_vunmap_cbuf:
 	vm_unmap_ram(dic->cbuf, dic->nr_cpages);
 out_vunmap_rbuf:

fs/f2fs/f2fs.h

@@ -147,7 +147,9 @@ struct f2fs_mount_info {
 
 	/* For compression */
 	unsigned char compress_algorithm;	/* algorithm type */
-	unsigned compress_log_size;		/* cluster log size */
+	unsigned char compress_log_size;	/* cluster log size */
+	unsigned char compress_level;		/* compress level */
+	bool compress_chksum;			/* compressed data chksum */
 	unsigned char compress_ext_cnt;		/* extension count */
 	unsigned char extensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN];	/* extensions */
 };
@@ -674,6 +676,7 @@ enum {
 	FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */
 	FI_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
 	FI_COMPRESSED_FILE,	/* indicate file's data can be compressed */
+	FI_COMPRESS_CORRUPT,	/* indicate compressed cluster is corrupted */
 	FI_MMAP_FILE,		/* indicate file was mmapped */
 	FI_MAX,			/* max flag, never be used */
 };
@@ -731,6 +734,8 @@ struct f2fs_inode_info {
 	atomic_t i_compr_blocks;		/* # of compressed blocks */
 	unsigned char i_compress_algorithm;	/* algorithm type */
 	unsigned char i_log_cluster_size;	/* log of cluster size */
+	unsigned char i_compress_level;		/* compress level (lz4hc,zstd) */
+	unsigned short i_compress_flag;		/* compress flag */
 	unsigned int i_cluster_size;		/* cluster size */
 };
 
@@ -1277,9 +1282,15 @@ enum compress_algorithm_type {
 	COMPRESS_MAX,
 };
 
-#define COMPRESS_DATA_RESERVED_SIZE		5
+enum compress_flag {
+	COMPRESS_CHKSUM,
+	COMPRESS_MAX_FLAG,
+};
+
+#define COMPRESS_DATA_RESERVED_SIZE		4
 struct compress_data {
 	__le32 clen;			/* compressed data size */
+	__le32 chksum;			/* compressed data chksum */
 	__le32 reserved[COMPRESS_DATA_RESERVED_SIZE];	/* reserved */
 	u8 cdata[];			/* compressed data */
 };
@@ -1288,6 +1299,8 @@ struct compress_data {
 
 #define F2FS_COMPRESSED_PAGE_MAGIC	0xF5F2C000
 
+#define	COMPRESS_LEVEL_OFFSET	8
+
 /* compress context */
 struct compress_ctx {
 	struct inode *inode;		/* inode the context belong to */
@@ -3905,8 +3918,16 @@ static inline void set_compress_context(struct inode *inode)
 			F2FS_OPTION(sbi).compress_algorithm;
 	F2FS_I(inode)->i_log_cluster_size =
 			F2FS_OPTION(sbi).compress_log_size;
+	F2FS_I(inode)->i_compress_flag =
+			F2FS_OPTION(sbi).compress_chksum ?
+				1 << COMPRESS_CHKSUM : 0;
 	F2FS_I(inode)->i_cluster_size =
 			1 << F2FS_I(inode)->i_log_cluster_size;
+	if (F2FS_I(inode)->i_compress_algorithm == COMPRESS_LZ4 &&
+			F2FS_OPTION(sbi).compress_level)
+		F2FS_I(inode)->i_compress_flag |=
+				F2FS_OPTION(sbi).compress_level <<
+				COMPRESS_LEVEL_OFFSET;
 	F2FS_I(inode)->i_flags |= F2FS_COMPR_FL;
 	set_inode_flag(inode, FI_COMPRESSED_FILE);
 	stat_inc_compr_inode(inode);

fs/f2fs/inode.c

@@ -456,6 +456,7 @@ static int do_read_inode(struct inode *inode)
 					le64_to_cpu(ri->i_compr_blocks));
 			fi->i_compress_algorithm = ri->i_compress_algorithm;
 			fi->i_log_cluster_size = ri->i_log_cluster_size;
+			fi->i_compress_flag = le16_to_cpu(ri->i_compress_flag);
 			fi->i_cluster_size = 1 << fi->i_log_cluster_size;
 			set_inode_flag(inode, FI_COMPRESSED_FILE);
 		}
@@ -634,6 +635,8 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page)
 					&F2FS_I(inode)->i_compr_blocks));
 			ri->i_compress_algorithm =
 				F2FS_I(inode)->i_compress_algorithm;
+			ri->i_compress_flag =
+				cpu_to_le16(F2FS_I(inode)->i_compress_flag);
 			ri->i_log_cluster_size =
 				F2FS_I(inode)->i_log_cluster_size;
 		}

fs/f2fs/super.c

@@ -25,6 +25,8 @@
 #include <linux/quota.h>
 #include <linux/unicode.h>
 #include <linux/part_stat.h>
+#include <linux/zstd.h>
+#include <linux/lz4.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -146,6 +148,7 @@ enum {
 	Opt_compress_algorithm,
 	Opt_compress_log_size,
 	Opt_compress_extension,
+	Opt_compress_chksum,
 	Opt_atgc,
 	Opt_err,
 };
@@ -214,6 +217,7 @@ static match_table_t f2fs_tokens = {
 	{Opt_compress_algorithm, "compress_algorithm=%s"},
 	{Opt_compress_log_size, "compress_log_size=%u"},
 	{Opt_compress_extension, "compress_extension=%s"},
+	{Opt_compress_chksum, "compress_chksum"},
 	{Opt_atgc, "atgc"},
 	{Opt_err, NULL},
 };
@@ -500,6 +504,74 @@ static int f2fs_set_test_dummy_encryption(struct super_block *sb,
 	return 0;
 }
 
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+#ifdef CONFIG_F2FS_FS_LZ4
+static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str)
+{
+#ifdef CONFIG_F2FS_FS_LZ4HC
+	unsigned int level;
+#endif
+
+	if (strlen(str) == 3) {
+		F2FS_OPTION(sbi).compress_level = 0;
+		return 0;
+	}
+
+#ifdef CONFIG_F2FS_FS_LZ4HC
+	str += 3;
+
+	if (str[0] != ':') {
+		f2fs_info(sbi, "wrong format, e.g. <alg_name>:<compr_level>");
+		return -EINVAL;
+	}
+	if (kstrtouint(str + 1, 10, &level))
+		return -EINVAL;
+
+	if (level < LZ4HC_MIN_CLEVEL || level > LZ4HC_MAX_CLEVEL) {
+		f2fs_info(sbi, "invalid lz4hc compress level: %d", level);
+		return -EINVAL;
+	}
+
+	F2FS_OPTION(sbi).compress_level = level;
+	return 0;
+#else
+	f2fs_info(sbi, "kernel doesn't support lz4hc compression");
+	return -EINVAL;
+#endif
+}
+#endif
+
+#ifdef CONFIG_F2FS_FS_ZSTD
+static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str)
+{
+	unsigned int level;
+	int len = 4;
+
+	if (strlen(str) == len) {
+		F2FS_OPTION(sbi).compress_level = 0;
+		return 0;
+	}
+
+	str += len;
+
+	if (str[0] != ':') {
+		f2fs_info(sbi, "wrong format, e.g. <alg_name>:<compr_level>");
+		return -EINVAL;
+	}
+	if (kstrtouint(str + 1, 10, &level))
+		return -EINVAL;
+
+	if (!level || level > ZSTD_maxCLevel()) {
+		f2fs_info(sbi, "invalid zstd compress level: %d", level);
+		return -EINVAL;
+	}
+
+	F2FS_OPTION(sbi).compress_level = level;
+	return 0;
+}
+#endif
+#endif
+
 static int parse_options(struct super_block *sb, char *options, bool is_remount)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -918,17 +990,45 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 			if (!name)
 				return -ENOMEM;
 			if (!strcmp(name, "lzo")) {
+#ifdef CONFIG_F2FS_FS_LZO
+				F2FS_OPTION(sbi).compress_level = 0;
 				F2FS_OPTION(sbi).compress_algorithm =
 								COMPRESS_LZO;
-			} else if (!strcmp(name, "lz4")) {
+#else
+				f2fs_info(sbi, "kernel doesn't support lzo compression");
+#endif
+			} else if (!strncmp(name, "lz4", 3)) {
+#ifdef CONFIG_F2FS_FS_LZ4
+				ret = f2fs_set_lz4hc_level(sbi, name);
+				if (ret) {
+					kfree(name);
+					return -EINVAL;
+				}
 				F2FS_OPTION(sbi).compress_algorithm =
 								COMPRESS_LZ4;
-			} else if (!strcmp(name, "zstd")) {
+#else
+				f2fs_info(sbi, "kernel doesn't support lz4 compression");
+#endif
+			} else if (!strncmp(name, "zstd", 4)) {
+#ifdef CONFIG_F2FS_FS_ZSTD
+				ret = f2fs_set_zstd_level(sbi, name);
+				if (ret) {
+					kfree(name);
+					return -EINVAL;
+				}
 				F2FS_OPTION(sbi).compress_algorithm =
 								COMPRESS_ZSTD;
+#else
+				f2fs_info(sbi, "kernel doesn't support zstd compression");
+#endif
 			} else if (!strcmp(name, "lzo-rle")) {
+#ifdef CONFIG_F2FS_FS_LZORLE
+				F2FS_OPTION(sbi).compress_level = 0;
 				F2FS_OPTION(sbi).compress_algorithm =
 								COMPRESS_LZORLE;
+#else
+				f2fs_info(sbi, "kernel doesn't support lzorle compression");
+#endif
 			} else {
 				kfree(name);
 				return -EINVAL;
@@ -974,10 +1074,14 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 			F2FS_OPTION(sbi).compress_ext_cnt++;
 			kfree(name);
 			break;
+		case Opt_compress_chksum:
+			F2FS_OPTION(sbi).compress_chksum = true;
+			break;
 #else
 		case Opt_compress_algorithm:
 		case Opt_compress_log_size:
 		case Opt_compress_extension:
+		case Opt_compress_chksum:
 			f2fs_info(sbi, "compression options not supported");
 			break;
 #endif
@@ -1556,6 +1660,9 @@ static inline void f2fs_show_compress_options(struct seq_file *seq,
 	}
 	seq_printf(seq, ",compress_algorithm=%s", algtype);
 
+	if (F2FS_OPTION(sbi).compress_level)
+		seq_printf(seq, ":%d", F2FS_OPTION(sbi).compress_level);
+
 	seq_printf(seq, ",compress_log_size=%u",
 			F2FS_OPTION(sbi).compress_log_size);
 
@@ -1563,6 +1670,9 @@ static inline void f2fs_show_compress_options(struct seq_file *seq,
 		seq_printf(seq, ",compress_extension=%s",
 			F2FS_OPTION(sbi).extensions[i]);
 	}
+
+	if (F2FS_OPTION(sbi).compress_chksum)
+		seq_puts(seq, ",compress_chksum");
 }
 
 static int f2fs_show_options(struct seq_file *seq, struct dentry *root)

include/linux/f2fs_fs.h

@@ -273,7 +273,10 @@ struct f2fs_inode {
 			__le64 i_compr_blocks;	/* # of compressed blocks */
 			__u8 i_compress_algorithm;	/* compress algorithm */
 			__u8 i_log_cluster_size;	/* log of cluster size */
-			__le16 i_padding;		/* padding */
+			__le16 i_compress_flag;		/* compress flag */
+						/* 0 bit: chksum flag
+						 * [10,15] bits: compress level
+						 */
 			__le32 i_extra_end[0];	/* for attribute size calculation */
 		} __packed;
 		__le32 i_addr[DEF_ADDRS_PER_INODE];	/* Pointers to data blocks */