linux/fs/erofs/super.c

616 lines
14 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2017-2018 HUAWEI, Inc.
* http://www.huawei.com/
* Created by Gao Xiang <gaoxiang25@huawei.com>
*/
#include <linux/module.h>
#include <linux/buffer_head.h>
#include <linux/statfs.h>
#include <linux/parser.h>
#include <linux/seq_file.h>
#include "xattr.h"
#define CREATE_TRACE_POINTS
#include <trace/events/erofs.h>
static struct kmem_cache *erofs_inode_cachep __read_mostly;
void _erofs_err(struct super_block *sb, const char *function,
const char *fmt, ...)
{
struct va_format vaf;
va_list args;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
pr_err("(device %s): %s: %pV", sb->s_id, function, &vaf);
va_end(args);
}
void _erofs_info(struct super_block *sb, const char *function,
const char *fmt, ...)
{
struct va_format vaf;
va_list args;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
pr_info("(device %s): %pV", sb->s_id, &vaf);
va_end(args);
}
static void erofs_inode_init_once(void *ptr)
{
struct erofs_inode *vi = ptr;
inode_init_once(&vi->vfs_inode);
}
static struct inode *erofs_alloc_inode(struct super_block *sb)
{
struct erofs_inode *vi =
kmem_cache_alloc(erofs_inode_cachep, GFP_KERNEL);
if (!vi)
return NULL;
/* zero out everything except vfs_inode */
memset(vi, 0, offsetof(struct erofs_inode, vfs_inode));
return &vi->vfs_inode;
}
static void erofs_free_inode(struct inode *inode)
{
struct erofs_inode *vi = EROFS_I(inode);
/* be careful of RCU symlink path */
if (inode->i_op == &erofs_fast_symlink_iops)
kfree(inode->i_link);
kfree(vi->xattr_shared_xattrs);
kmem_cache_free(erofs_inode_cachep, vi);
}
static bool check_layout_compatibility(struct super_block *sb,
struct erofs_super_block *dsb)
{
const unsigned int feature = le32_to_cpu(dsb->feature_incompat);
EROFS_SB(sb)->feature_incompat = feature;
/* check if current kernel meets all mandatory requirements */
if (feature & (~EROFS_ALL_FEATURE_INCOMPAT)) {
erofs_err(sb,
"unidentified incompatible feature %x, please upgrade kernel version",
feature & ~EROFS_ALL_FEATURE_INCOMPAT);
return false;
}
return true;
}
static int erofs_read_superblock(struct super_block *sb)
{
struct erofs_sb_info *sbi;
struct page *page;
struct erofs_super_block *dsb;
unsigned int blkszbits;
void *data;
int ret;
page = read_mapping_page(sb->s_bdev->bd_inode->i_mapping, 0, NULL);
if (IS_ERR(page)) {
erofs_err(sb, "cannot read erofs superblock");
return PTR_ERR(page);
}
sbi = EROFS_SB(sb);
data = kmap_atomic(page);
dsb = (struct erofs_super_block *)(data + EROFS_SUPER_OFFSET);
ret = -EINVAL;
if (le32_to_cpu(dsb->magic) != EROFS_SUPER_MAGIC_V1) {
erofs_err(sb, "cannot find valid erofs superblock");
goto out;
}
blkszbits = dsb->blkszbits;
/* 9(512 bytes) + LOG_SECTORS_PER_BLOCK == LOG_BLOCK_SIZE */
if (blkszbits != LOG_BLOCK_SIZE) {
erofs_err(sb, "blksize %u isn't supported on this platform",
1 << blkszbits);
goto out;
}
if (!check_layout_compatibility(sb, dsb))
goto out;
sbi->blocks = le32_to_cpu(dsb->blocks);
sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr);
#ifdef CONFIG_EROFS_FS_XATTR
sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr);
#endif
sbi->islotbits = ilog2(sizeof(struct erofs_inode_compact));
sbi->root_nid = le16_to_cpu(dsb->root_nid);
sbi->inos = le64_to_cpu(dsb->inos);
sbi->build_time = le64_to_cpu(dsb->build_time);
sbi->build_time_nsec = le32_to_cpu(dsb->build_time_nsec);
memcpy(&sb->s_uuid, dsb->uuid, sizeof(dsb->uuid));
ret = strscpy(sbi->volume_name, dsb->volume_name,
sizeof(dsb->volume_name));
if (ret < 0) { /* -E2BIG */
erofs_err(sb, "bad volume name without NIL terminator");
ret = -EFSCORRUPTED;
goto out;
}
ret = 0;
out:
kunmap_atomic(data);
put_page(page);
return ret;
}
#ifdef CONFIG_EROFS_FS_ZIP
static int erofs_build_cache_strategy(struct super_block *sb,
substring_t *args)
{
struct erofs_sb_info *sbi = EROFS_SB(sb);
const char *cs = match_strdup(args);
int err = 0;
if (!cs) {
erofs_err(sb, "Not enough memory to store cache strategy");
return -ENOMEM;
}
if (!strcmp(cs, "disabled")) {
sbi->cache_strategy = EROFS_ZIP_CACHE_DISABLED;
} else if (!strcmp(cs, "readahead")) {
sbi->cache_strategy = EROFS_ZIP_CACHE_READAHEAD;
} else if (!strcmp(cs, "readaround")) {
sbi->cache_strategy = EROFS_ZIP_CACHE_READAROUND;
} else {
erofs_err(sb, "Unrecognized cache strategy \"%s\"", cs);
err = -EINVAL;
}
kfree(cs);
return err;
}
#else
static int erofs_build_cache_strategy(struct super_block *sb,
substring_t *args)
{
erofs_info(sb, "EROFS compression is disabled, so cache strategy is ignored");
return 0;
}
#endif
/* set up default EROFS parameters */
static void erofs_default_options(struct erofs_sb_info *sbi)
{
#ifdef CONFIG_EROFS_FS_ZIP
sbi->cache_strategy = EROFS_ZIP_CACHE_READAROUND;
sbi->max_sync_decompress_pages = 3;
#endif
#ifdef CONFIG_EROFS_FS_XATTR
set_opt(sbi, XATTR_USER);
#endif
#ifdef CONFIG_EROFS_FS_POSIX_ACL
set_opt(sbi, POSIX_ACL);
#endif
}
enum {
Opt_user_xattr,
Opt_nouser_xattr,
Opt_acl,
Opt_noacl,
Opt_cache_strategy,
Opt_err
};
static match_table_t erofs_tokens = {
{Opt_user_xattr, "user_xattr"},
{Opt_nouser_xattr, "nouser_xattr"},
{Opt_acl, "acl"},
{Opt_noacl, "noacl"},
{Opt_cache_strategy, "cache_strategy=%s"},
{Opt_err, NULL}
};
static int erofs_parse_options(struct super_block *sb, char *options)
{
substring_t args[MAX_OPT_ARGS];
char *p;
int err;
if (!options)
return 0;
while ((p = strsep(&options, ","))) {
int token;
if (!*p)
continue;
args[0].to = args[0].from = NULL;
token = match_token(p, erofs_tokens, args);
switch (token) {
#ifdef CONFIG_EROFS_FS_XATTR
case Opt_user_xattr:
set_opt(EROFS_SB(sb), XATTR_USER);
break;
case Opt_nouser_xattr:
clear_opt(EROFS_SB(sb), XATTR_USER);
break;
#else
case Opt_user_xattr:
erofs_info(sb, "user_xattr options not supported");
break;
case Opt_nouser_xattr:
erofs_info(sb, "nouser_xattr options not supported");
break;
#endif
#ifdef CONFIG_EROFS_FS_POSIX_ACL
case Opt_acl:
set_opt(EROFS_SB(sb), POSIX_ACL);
break;
case Opt_noacl:
clear_opt(EROFS_SB(sb), POSIX_ACL);
break;
#else
case Opt_acl:
erofs_info(sb, "acl options not supported");
break;
case Opt_noacl:
erofs_info(sb, "noacl options not supported");
break;
#endif
case Opt_cache_strategy:
err = erofs_build_cache_strategy(sb, args);
if (err)
return err;
break;
default:
erofs_err(sb, "Unrecognized mount option \"%s\" or missing value", p);
return -EINVAL;
}
}
return 0;
}
#ifdef CONFIG_EROFS_FS_ZIP
static const struct address_space_operations managed_cache_aops;
static int erofs_managed_cache_releasepage(struct page *page, gfp_t gfp_mask)
{
int ret = 1; /* 0 - busy */
struct address_space *const mapping = page->mapping;
DBG_BUGON(!PageLocked(page));
DBG_BUGON(mapping->a_ops != &managed_cache_aops);
if (PagePrivate(page))
ret = erofs_try_to_free_cached_page(mapping, page);
return ret;
}
static void erofs_managed_cache_invalidatepage(struct page *page,
unsigned int offset,
unsigned int length)
{
const unsigned int stop = length + offset;
DBG_BUGON(!PageLocked(page));
/* Check for potential overflow in debug mode */
DBG_BUGON(stop > PAGE_SIZE || stop < length);
if (offset == 0 && stop == PAGE_SIZE)
while (!erofs_managed_cache_releasepage(page, GFP_NOFS))
cond_resched();
}
static const struct address_space_operations managed_cache_aops = {
.releasepage = erofs_managed_cache_releasepage,
.invalidatepage = erofs_managed_cache_invalidatepage,
};
static int erofs_init_managed_cache(struct super_block *sb)
{
struct erofs_sb_info *const sbi = EROFS_SB(sb);
struct inode *const inode = new_inode(sb);
if (!inode)
return -ENOMEM;
set_nlink(inode, 1);
inode->i_size = OFFSET_MAX;
inode->i_mapping->a_ops = &managed_cache_aops;
mapping_set_gfp_mask(inode->i_mapping,
GFP_NOFS | __GFP_HIGHMEM | __GFP_MOVABLE);
sbi->managed_cache = inode;
return 0;
}
#else
static int erofs_init_managed_cache(struct super_block *sb) { return 0; }
#endif
static int erofs_fill_super(struct super_block *sb, void *data, int silent)
{
struct inode *inode;
struct erofs_sb_info *sbi;
int err;
sb->s_magic = EROFS_SUPER_MAGIC;
if (!sb_set_blocksize(sb, EROFS_BLKSIZ)) {
erofs_err(sb, "failed to set erofs blksize");
return -EINVAL;
}
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
return -ENOMEM;
sb->s_fs_info = sbi;
err = erofs_read_superblock(sb);
if (err)
return err;
sb->s_flags |= SB_RDONLY | SB_NOATIME;
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_time_gran = 1;
sb->s_op = &erofs_sops;
#ifdef CONFIG_EROFS_FS_XATTR
sb->s_xattr = erofs_xattr_handlers;
#endif
/* set erofs default mount options */
erofs_default_options(sbi);
err = erofs_parse_options(sb, data);
if (err)
return err;
if (test_opt(sbi, POSIX_ACL))
sb->s_flags |= SB_POSIXACL;
else
sb->s_flags &= ~SB_POSIXACL;
#ifdef CONFIG_EROFS_FS_ZIP
INIT_RADIX_TREE(&sbi->workstn_tree, GFP_ATOMIC);
#endif
/* get the root inode */
inode = erofs_iget(sb, ROOT_NID(sbi), true);
if (IS_ERR(inode))
return PTR_ERR(inode);
if (!S_ISDIR(inode->i_mode)) {
erofs_err(sb, "rootino(nid %llu) is not a directory(i_mode %o)",
ROOT_NID(sbi), inode->i_mode);
iput(inode);
return -EINVAL;
}
sb->s_root = d_make_root(inode);
if (!sb->s_root)
return -ENOMEM;
erofs_shrinker_register(sb);
/* sb->s_umount is already locked, SB_ACTIVE and SB_BORN are not set */
err = erofs_init_managed_cache(sb);
if (err)
return err;
erofs_info(sb, "mounted with opts: %s, root inode @ nid %llu.",
(char *)data, ROOT_NID(sbi));
return 0;
}
static struct dentry *erofs_mount(struct file_system_type *fs_type, int flags,
const char *dev_name, void *data)
{
return mount_bdev(fs_type, flags, dev_name, data, erofs_fill_super);
}
/*
* could be triggered after deactivate_locked_super()
* is called, thus including umount and failed to initialize.
*/
static void erofs_kill_sb(struct super_block *sb)
{
struct erofs_sb_info *sbi;
WARN_ON(sb->s_magic != EROFS_SUPER_MAGIC);
kill_block_super(sb);
sbi = EROFS_SB(sb);
if (!sbi)
return;
kfree(sbi);
sb->s_fs_info = NULL;
}
/* called when ->s_root is non-NULL */
static void erofs_put_super(struct super_block *sb)
{
struct erofs_sb_info *const sbi = EROFS_SB(sb);
DBG_BUGON(!sbi);
erofs_shrinker_unregister(sb);
#ifdef CONFIG_EROFS_FS_ZIP
iput(sbi->managed_cache);
sbi->managed_cache = NULL;
#endif
}
static struct file_system_type erofs_fs_type = {
.owner = THIS_MODULE,
.name = "erofs",
.mount = erofs_mount,
.kill_sb = erofs_kill_sb,
.fs_flags = FS_REQUIRES_DEV,
};
MODULE_ALIAS_FS("erofs");
static int __init erofs_module_init(void)
{
int err;
erofs_check_ondisk_layout_definitions();
erofs_inode_cachep = kmem_cache_create("erofs_inode",
sizeof(struct erofs_inode), 0,
SLAB_RECLAIM_ACCOUNT,
erofs_inode_init_once);
if (!erofs_inode_cachep) {
err = -ENOMEM;
goto icache_err;
}
err = erofs_init_shrinker();
if (err)
goto shrinker_err;
staging: erofs: introduce VLE decompression support This patch introduces the basic in-place VLE decompression implementation for the erofs file system. Compared with fixed-sized input compression, it implements what we call 'the variable-length extent compression' which specifies the same output size for each compression block to make the full use of IO bandwidth (which means almost all data from block device can be directly used for decomp- ression), improve the real (rather than just via data caching, which costs more memory) random read and keep the relatively lower compression ratios (it saves more storage space than fixed-sized input compression which is also configured with the same input block size), as illustrated below: |--- variable-length extent ---|------ VLE ------|--- VLE ---| /> clusterofs /> clusterofs /> clusterofs /> clusterofs ++---|-------++-----------++---------|-++-----------++-|---------++-| ...|| | || || | || || | || | ... original data ++---|-------++-----------++---------|-++-----------++-|---------++-| ++->cluster<-++->cluster<-++->cluster<-++->cluster<-++->cluster<-++ size size size size size \ / / / \ / / / \ / / / ++-----------++-----------++-----------++ ... || || || || ... compressed clusters ++-----------++-----------++-----------++ ++->cluster<-++->cluster<-++->cluster<-++ size size size The main point of 'in-place' refers to the decompression mode: Instead of allocating independent compressed pages and data structures, it reuses the allocated file cache pages at most to store its compressed data and the corresponding pagevec in a time-sharing approach by default, which will be useful for low memory scenario. In the end, unlike the other filesystems with (de)compression support using a relatively large compression block size, which reads and decompresses >= 128KB at once, and gains a more good-looking random read (In fact it collects small random reads into large sequential reads and caches all decompressed data in memory, but it is unacceptable especially for embedded devices with limited memory, and it is not the real random read), we select a universal small-sized 4KB compressed cluster, which is the smallest page size for most architectures, and all compressed clusters can be read and decompressed independently, which ensures random read number for all use cases. Signed-off-by: Gao Xiang <gaoxiang25@huawei.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-07-26 12:22:06 +00:00
err = z_erofs_init_zip_subsystem();
if (err)
goto zip_err;
err = register_filesystem(&erofs_fs_type);
if (err)
goto fs_err;
return 0;
fs_err:
staging: erofs: introduce VLE decompression support This patch introduces the basic in-place VLE decompression implementation for the erofs file system. Compared with fixed-sized input compression, it implements what we call 'the variable-length extent compression' which specifies the same output size for each compression block to make the full use of IO bandwidth (which means almost all data from block device can be directly used for decomp- ression), improve the real (rather than just via data caching, which costs more memory) random read and keep the relatively lower compression ratios (it saves more storage space than fixed-sized input compression which is also configured with the same input block size), as illustrated below: |--- variable-length extent ---|------ VLE ------|--- VLE ---| /> clusterofs /> clusterofs /> clusterofs /> clusterofs ++---|-------++-----------++---------|-++-----------++-|---------++-| ...|| | || || | || || | || | ... original data ++---|-------++-----------++---------|-++-----------++-|---------++-| ++->cluster<-++->cluster<-++->cluster<-++->cluster<-++->cluster<-++ size size size size size \ / / / \ / / / \ / / / ++-----------++-----------++-----------++ ... || || || || ... compressed clusters ++-----------++-----------++-----------++ ++->cluster<-++->cluster<-++->cluster<-++ size size size The main point of 'in-place' refers to the decompression mode: Instead of allocating independent compressed pages and data structures, it reuses the allocated file cache pages at most to store its compressed data and the corresponding pagevec in a time-sharing approach by default, which will be useful for low memory scenario. In the end, unlike the other filesystems with (de)compression support using a relatively large compression block size, which reads and decompresses >= 128KB at once, and gains a more good-looking random read (In fact it collects small random reads into large sequential reads and caches all decompressed data in memory, but it is unacceptable especially for embedded devices with limited memory, and it is not the real random read), we select a universal small-sized 4KB compressed cluster, which is the smallest page size for most architectures, and all compressed clusters can be read and decompressed independently, which ensures random read number for all use cases. Signed-off-by: Gao Xiang <gaoxiang25@huawei.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-07-26 12:22:06 +00:00
z_erofs_exit_zip_subsystem();
zip_err:
erofs_exit_shrinker();
shrinker_err:
kmem_cache_destroy(erofs_inode_cachep);
icache_err:
return err;
}
static void __exit erofs_module_exit(void)
{
unregister_filesystem(&erofs_fs_type);
staging: erofs: introduce VLE decompression support This patch introduces the basic in-place VLE decompression implementation for the erofs file system. Compared with fixed-sized input compression, it implements what we call 'the variable-length extent compression' which specifies the same output size for each compression block to make the full use of IO bandwidth (which means almost all data from block device can be directly used for decomp- ression), improve the real (rather than just via data caching, which costs more memory) random read and keep the relatively lower compression ratios (it saves more storage space than fixed-sized input compression which is also configured with the same input block size), as illustrated below: |--- variable-length extent ---|------ VLE ------|--- VLE ---| /> clusterofs /> clusterofs /> clusterofs /> clusterofs ++---|-------++-----------++---------|-++-----------++-|---------++-| ...|| | || || | || || | || | ... original data ++---|-------++-----------++---------|-++-----------++-|---------++-| ++->cluster<-++->cluster<-++->cluster<-++->cluster<-++->cluster<-++ size size size size size \ / / / \ / / / \ / / / ++-----------++-----------++-----------++ ... || || || || ... compressed clusters ++-----------++-----------++-----------++ ++->cluster<-++->cluster<-++->cluster<-++ size size size The main point of 'in-place' refers to the decompression mode: Instead of allocating independent compressed pages and data structures, it reuses the allocated file cache pages at most to store its compressed data and the corresponding pagevec in a time-sharing approach by default, which will be useful for low memory scenario. In the end, unlike the other filesystems with (de)compression support using a relatively large compression block size, which reads and decompresses >= 128KB at once, and gains a more good-looking random read (In fact it collects small random reads into large sequential reads and caches all decompressed data in memory, but it is unacceptable especially for embedded devices with limited memory, and it is not the real random read), we select a universal small-sized 4KB compressed cluster, which is the smallest page size for most architectures, and all compressed clusters can be read and decompressed independently, which ensures random read number for all use cases. Signed-off-by: Gao Xiang <gaoxiang25@huawei.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-07-26 12:22:06 +00:00
z_erofs_exit_zip_subsystem();
erofs_exit_shrinker();
/* Ensure all RCU free inodes are safe before cache is destroyed. */
rcu_barrier();
kmem_cache_destroy(erofs_inode_cachep);
}
/* get filesystem statistics */
static int erofs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct erofs_sb_info *sbi = EROFS_SB(sb);
u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
buf->f_type = sb->s_magic;
buf->f_bsize = EROFS_BLKSIZ;
buf->f_blocks = sbi->blocks;
buf->f_bfree = buf->f_bavail = 0;
buf->f_files = ULLONG_MAX;
buf->f_ffree = ULLONG_MAX - sbi->inos;
buf->f_namelen = EROFS_NAME_LEN;
buf->f_fsid.val[0] = (u32)id;
buf->f_fsid.val[1] = (u32)(id >> 32);
return 0;
}
static int erofs_show_options(struct seq_file *seq, struct dentry *root)
{
struct erofs_sb_info *sbi __maybe_unused = EROFS_SB(root->d_sb);
#ifdef CONFIG_EROFS_FS_XATTR
if (test_opt(sbi, XATTR_USER))
seq_puts(seq, ",user_xattr");
else
seq_puts(seq, ",nouser_xattr");
#endif
#ifdef CONFIG_EROFS_FS_POSIX_ACL
if (test_opt(sbi, POSIX_ACL))
seq_puts(seq, ",acl");
else
seq_puts(seq, ",noacl");
#endif
#ifdef CONFIG_EROFS_FS_ZIP
if (sbi->cache_strategy == EROFS_ZIP_CACHE_DISABLED) {
seq_puts(seq, ",cache_strategy=disabled");
} else if (sbi->cache_strategy == EROFS_ZIP_CACHE_READAHEAD) {
seq_puts(seq, ",cache_strategy=readahead");
} else if (sbi->cache_strategy == EROFS_ZIP_CACHE_READAROUND) {
seq_puts(seq, ",cache_strategy=readaround");
} else {
seq_puts(seq, ",cache_strategy=(unknown)");
DBG_BUGON(1);
}
#endif
return 0;
}
static int erofs_remount(struct super_block *sb, int *flags, char *data)
{
struct erofs_sb_info *sbi = EROFS_SB(sb);
unsigned int org_mnt_opt = sbi->mount_opt;
int err;
DBG_BUGON(!sb_rdonly(sb));
err = erofs_parse_options(sb, data);
if (err)
goto out;
if (test_opt(sbi, POSIX_ACL))
sb->s_flags |= SB_POSIXACL;
else
sb->s_flags &= ~SB_POSIXACL;
*flags |= SB_RDONLY;
return 0;
out:
sbi->mount_opt = org_mnt_opt;
return err;
}
const struct super_operations erofs_sops = {
.put_super = erofs_put_super,
.alloc_inode = erofs_alloc_inode,
.free_inode = erofs_free_inode,
.statfs = erofs_statfs,
.show_options = erofs_show_options,
.remount_fs = erofs_remount,
};
module_init(erofs_module_init);
module_exit(erofs_module_exit);
MODULE_DESCRIPTION("Enhanced ROM File System");
MODULE_AUTHOR("Gao Xiang, Chao Yu, Miao Xie, CONSUMER BG, HUAWEI Inc.");
MODULE_LICENSE("GPL");