f2fs: support data compression

This patch tries to support compression in f2fs.

- New term named cluster is defined as basic unit of compression, file can
be divided into multiple clusters logically. One cluster includes 4 << n
(n >= 0) logical pages, compression size is also cluster size, each of
cluster can be compressed or not.

- In cluster metadata layout, one special flag is used to indicate cluster
is compressed one or normal one, for compressed cluster, following metadata
maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs stores
data including compress header and compressed data.

- In order to eliminate write amplification during overwrite, F2FS only
support compression on write-once file, data can be compressed only when
all logical blocks in file are valid and cluster compress ratio is lower
than specified threshold.

- To enable compression on regular inode, there are three ways:
* chattr +c file
* chattr +c dir; touch dir/file
* mount w/ -o compress_extension=ext; touch file.ext

Compress metadata layout:
                             [Dnode Structure]
             +-----------------------------------------------+
             | cluster 1 | cluster 2 | ......... | cluster N |
             +-----------------------------------------------+
             .           .                       .           .
       .                       .                .                      .
  .         Compressed Cluster       .        .        Normal Cluster            .
+----------+---------+---------+---------+  +---------+---------+---------+---------+
|compr flag| block 1 | block 2 | block 3 |  | block 1 | block 2 | block 3 | block 4 |
+----------+---------+---------+---------+  +---------+---------+---------+---------+
           .                             .
         .                                           .
       .                                                           .
      +-------------+-------------+----------+----------------------------+
      | data length | data chksum | reserved |      compressed data       |
      +-------------+-------------+----------+----------------------------+

Changelog:

20190326:
- fix error handling of read_end_io().
- remove unneeded comments in f2fs_encrypt_one_page().

20190327:
- fix wrong use of f2fs_cluster_is_full() in f2fs_mpage_readpages().
- don't jump into loop directly to avoid uninitialized variables.
- add TODO tag in error path of f2fs_write_cache_pages().

20190328:
- fix wrong merge condition in f2fs_read_multi_pages().
- check compressed file in f2fs_post_read_required().

20190401
- allow overwrite on non-compressed cluster.
- check cluster meta before writing compressed data.

20190402
- don't preallocate blocks for compressed file.

- add lz4 compress algorithm
- process multiple post read works in one workqueue
  Now f2fs supports processing post read work in multiple workqueue,
  it shows low performance due to schedule overhead of multiple
  workqueue executing orderly.

20190921
- compress: support buffered overwrite
C: compress cluster flag
V: valid block address
N: NEW_ADDR

One cluster contain 4 blocks

 before overwrite   after overwrite

- VVVV		->	CVNN
- CVNN		->	VVVV

- CVNN		->	CVNN
- CVNN		->	CVVV

- CVVV		->	CVNN
- CVVV		->	CVVV

20191029
- add kconfig F2FS_FS_COMPRESSION to isolate compression related
codes, add kconfig F2FS_FS_{LZO,LZ4} to cover backend algorithm.
note that: will remove lzo backend if Jaegeuk agreed that too.
- update codes according to Eric's comments.

20191101
- apply fixes from Jaegeuk

20191113
- apply fixes from Jaegeuk
- split workqueue for fsverity

20191216
- apply fixes from Jaegeuk

20200117
- fix to avoid NULL pointer dereference

[Jaegeuk Kim]
- add tracepoint for f2fs_{,de}compress_pages()
- fix many bugs and add some compression stats
- fix overwrite/mmap bugs
- address 32bit build error, reported by Geert.
- bug fixes when handling errors and i_compressed_blocks

Reported-by: <noreply@ellerman.id.au>
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

1 files changed, 111 insertions, 1 deletions

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index e6fb4b52eb91..9d491f8fad4f 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -141,6 +141,9 @@ enum {
 	Opt_checkpoint_disable_cap,
 	Opt_checkpoint_disable_cap_perc,
 	Opt_checkpoint_enable,
+	Opt_compress_algorithm,
+	Opt_compress_log_size,
+	Opt_compress_extension,
 	Opt_err,
 };
 
@@ -203,6 +206,9 @@ static match_table_t f2fs_tokens = {
 	{Opt_checkpoint_disable_cap, "checkpoint=disable:%u"},
 	{Opt_checkpoint_disable_cap_perc, "checkpoint=disable:%u%%"},
 	{Opt_checkpoint_enable, "checkpoint=enable"},
+	{Opt_compress_algorithm, "compress_algorithm=%s"},
+	{Opt_compress_log_size, "compress_log_size=%u"},
+	{Opt_compress_extension, "compress_extension=%s"},
 	{Opt_err, NULL},
 };
 
@@ -391,8 +397,9 @@ static int parse_options(struct super_block *sb, char *options)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	substring_t args[MAX_OPT_ARGS];
+	unsigned char (*ext)[F2FS_EXTENSION_LEN];
 	char *p, *name;
-	int arg = 0;
+	int arg = 0, ext_cnt;
 	kuid_t uid;
 	kgid_t gid;
 #ifdef CONFIG_QUOTA
@@ -810,6 +817,66 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_checkpoint_enable:
 			clear_opt(sbi, DISABLE_CHECKPOINT);
 			break;
+		case Opt_compress_algorithm:
+			if (!f2fs_sb_has_compression(sbi)) {
+				f2fs_err(sbi, "Compression feature if off");
+				return -EINVAL;
+			}
+			name = match_strdup(&args[0]);
+			if (!name)
+				return -ENOMEM;
+			if (strlen(name) == 3 && !strcmp(name, "lzo")) {
+				F2FS_OPTION(sbi).compress_algorithm =
+								COMPRESS_LZO;
+			} else if (strlen(name) == 3 &&
+					!strcmp(name, "lz4")) {
+				F2FS_OPTION(sbi).compress_algorithm =
+								COMPRESS_LZ4;
+			} else {
+				kfree(name);
+				return -EINVAL;
+			}
+			kfree(name);
+			break;
+		case Opt_compress_log_size:
+			if (!f2fs_sb_has_compression(sbi)) {
+				f2fs_err(sbi, "Compression feature is off");
+				return -EINVAL;
+			}
+			if (args->from && match_int(args, &arg))
+				return -EINVAL;
+			if (arg < MIN_COMPRESS_LOG_SIZE ||
+				arg > MAX_COMPRESS_LOG_SIZE) {
+				f2fs_err(sbi,
+					"Compress cluster log size is out of range");
+				return -EINVAL;
+			}
+			F2FS_OPTION(sbi).compress_log_size = arg;
+			break;
+		case Opt_compress_extension:
+			if (!f2fs_sb_has_compression(sbi)) {
+				f2fs_err(sbi, "Compression feature is off");
+				return -EINVAL;
+			}
+			name = match_strdup(&args[0]);
+			if (!name)
+				return -ENOMEM;
+
+			ext = F2FS_OPTION(sbi).extensions;
+			ext_cnt = F2FS_OPTION(sbi).compress_ext_cnt;
+
+			if (strlen(name) >= F2FS_EXTENSION_LEN ||
+				ext_cnt >= COMPRESS_EXT_NUM) {
+				f2fs_err(sbi,
+					"invalid extension length/number");
+				kfree(name);
+				return -EINVAL;
+			}
+
+			strcpy(ext[ext_cnt], name);
+			F2FS_OPTION(sbi).compress_ext_cnt++;
+			kfree(name);
+			break;
 		default:
 			f2fs_err(sbi, "Unrecognized mount option \"%s\" or missing value",
 				 p);
@@ -1125,6 +1192,8 @@ static void f2fs_put_super(struct super_block *sb)
 	f2fs_destroy_node_manager(sbi);
 	f2fs_destroy_segment_manager(sbi);
 
+	f2fs_destroy_post_read_wq(sbi);
+
 	kvfree(sbi->ckpt);
 
 	f2fs_unregister_sysfs(sbi);
@@ -1340,6 +1409,35 @@ static inline void f2fs_show_quota_options(struct seq_file *seq,
 #endif
 }
 
+static inline void f2fs_show_compress_options(struct seq_file *seq,
+							struct super_block *sb)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	char *algtype = "";
+	int i;
+
+	if (!f2fs_sb_has_compression(sbi))
+		return;
+
+	switch (F2FS_OPTION(sbi).compress_algorithm) {
+	case COMPRESS_LZO:
+		algtype = "lzo";
+		break;
+	case COMPRESS_LZ4:
+		algtype = "lz4";
+		break;
+	}
+	seq_printf(seq, ",compress_algorithm=%s", algtype);
+
+	seq_printf(seq, ",compress_log_size=%u",
+			F2FS_OPTION(sbi).compress_log_size);
+
+	for (i = 0; i < F2FS_OPTION(sbi).compress_ext_cnt; i++) {
+		seq_printf(seq, ",compress_extension=%s",
+			F2FS_OPTION(sbi).extensions[i]);
+	}
+}
+
 static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);
@@ -1462,6 +1560,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_printf(seq, ",fsync_mode=%s", "strict");
 	else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_NOBARRIER)
 		seq_printf(seq, ",fsync_mode=%s", "nobarrier");
+
+	f2fs_show_compress_options(seq, sbi->sb);
 	return 0;
 }
 
@@ -1476,6 +1576,9 @@ static void default_options(struct f2fs_sb_info *sbi)
 	F2FS_OPTION(sbi).test_dummy_encryption = false;
 	F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID);
 	F2FS_OPTION(sbi).s_resgid = make_kgid(&init_user_ns, F2FS_DEF_RESGID);
+	F2FS_OPTION(sbi).compress_algorithm = COMPRESS_LZO;
+	F2FS_OPTION(sbi).compress_log_size = MIN_COMPRESS_LOG_SIZE;
+	F2FS_OPTION(sbi).compress_ext_cnt = 0;
 
 	set_opt(sbi, BG_GC);
 	set_opt(sbi, INLINE_XATTR);
@@ -3390,6 +3493,12 @@ try_onemore:
 		goto free_devices;
 	}
 
+	err = f2fs_init_post_read_wq(sbi);
+	if (err) {
+		f2fs_err(sbi, "Failed to initialize post read workqueue");
+		goto free_devices;
+	}
+
 	sbi->total_valid_node_count =
 				le32_to_cpu(sbi->ckpt->valid_node_count);
 	percpu_counter_set(&sbi->total_valid_inode_count,
@@ -3622,6 +3731,7 @@ free_nm:
 	f2fs_destroy_node_manager(sbi);
 free_sm:
 	f2fs_destroy_segment_manager(sbi);
+	f2fs_destroy_post_read_wq(sbi);
 free_devices:
 	destroy_device_list(sbi);
 	kvfree(sbi->ckpt);