linux/fs/f2fs/super.c

1520 lines
37 KiB
C
Raw Normal View History

/*
* fs/f2fs/super.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/statfs.h>
#include <linux/buffer_head.h>
#include <linux/backing-dev.h>
#include <linux/kthread.h>
#include <linux/parser.h>
#include <linux/mount.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <linux/random.h>
#include <linux/exportfs.h>
#include <linux/blkdev.h>
#include <linux/f2fs_fs.h>
#include <linux/sysfs.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include "xattr.h"
#include "gc.h"
#include "trace.h"
#define CREATE_TRACE_POINTS
#include <trace/events/f2fs.h>
static struct proc_dir_entry *f2fs_proc_root;
static struct kmem_cache *f2fs_inode_cachep;
static struct kset *f2fs_kset;
/* f2fs-wide shrinker description */
static struct shrinker f2fs_shrinker_info = {
.scan_objects = f2fs_shrink_scan,
.count_objects = f2fs_shrink_count,
.seeks = DEFAULT_SEEKS,
};
enum {
Opt_gc_background,
Opt_disable_roll_forward,
Opt_norecovery,
Opt_discard,
Opt_noheap,
Opt_user_xattr,
Opt_nouser_xattr,
Opt_acl,
Opt_noacl,
Opt_active_logs,
Opt_disable_ext_identify,
Opt_inline_xattr,
Opt_inline_data,
Opt_inline_dentry,
Opt_flush_merge,
Opt_nobarrier,
Opt_fastboot,
Opt_extent_cache,
Opt_noextent_cache,
Opt_noinline_data,
Opt_err,
};
static match_table_t f2fs_tokens = {
{Opt_gc_background, "background_gc=%s"},
{Opt_disable_roll_forward, "disable_roll_forward"},
{Opt_norecovery, "norecovery"},
{Opt_discard, "discard"},
{Opt_noheap, "no_heap"},
{Opt_user_xattr, "user_xattr"},
{Opt_nouser_xattr, "nouser_xattr"},
{Opt_acl, "acl"},
{Opt_noacl, "noacl"},
{Opt_active_logs, "active_logs=%u"},
{Opt_disable_ext_identify, "disable_ext_identify"},
{Opt_inline_xattr, "inline_xattr"},
{Opt_inline_data, "inline_data"},
{Opt_inline_dentry, "inline_dentry"},
{Opt_flush_merge, "flush_merge"},
{Opt_nobarrier, "nobarrier"},
{Opt_fastboot, "fastboot"},
{Opt_extent_cache, "extent_cache"},
{Opt_noextent_cache, "noextent_cache"},
{Opt_noinline_data, "noinline_data"},
{Opt_err, NULL},
};
/* Sysfs support for f2fs */
enum {
GC_THREAD, /* struct f2fs_gc_thread */
SM_INFO, /* struct f2fs_sm_info */
NM_INFO, /* struct f2fs_nm_info */
F2FS_SBI, /* struct f2fs_sb_info */
};
struct f2fs_attr {
struct attribute attr;
ssize_t (*show)(struct f2fs_attr *, struct f2fs_sb_info *, char *);
ssize_t (*store)(struct f2fs_attr *, struct f2fs_sb_info *,
const char *, size_t);
int struct_type;
int offset;
};
static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
{
if (struct_type == GC_THREAD)
return (unsigned char *)sbi->gc_thread;
else if (struct_type == SM_INFO)
return (unsigned char *)SM_I(sbi);
else if (struct_type == NM_INFO)
return (unsigned char *)NM_I(sbi);
else if (struct_type == F2FS_SBI)
return (unsigned char *)sbi;
return NULL;
}
static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf)
{
unsigned char *ptr = NULL;
unsigned int *ui;
ptr = __struct_ptr(sbi, a->struct_type);
if (!ptr)
return -EINVAL;
ui = (unsigned int *)(ptr + a->offset);
return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
}
static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
struct f2fs_sb_info *sbi,
const char *buf, size_t count)
{
unsigned char *ptr;
unsigned long t;
unsigned int *ui;
ssize_t ret;
ptr = __struct_ptr(sbi, a->struct_type);
if (!ptr)
return -EINVAL;
ui = (unsigned int *)(ptr + a->offset);
ret = kstrtoul(skip_spaces(buf), 0, &t);
if (ret < 0)
return ret;
*ui = t;
return count;
}
static ssize_t f2fs_attr_show(struct kobject *kobj,
struct attribute *attr, char *buf)
{
struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
s_kobj);
struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
return a->show ? a->show(a, sbi, buf) : 0;
}
static ssize_t f2fs_attr_store(struct kobject *kobj, struct attribute *attr,
const char *buf, size_t len)
{
struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
s_kobj);
struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
return a->store ? a->store(a, sbi, buf, len) : 0;
}
static void f2fs_sb_release(struct kobject *kobj)
{
struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
s_kobj);
complete(&sbi->s_kobj_unregister);
}
#define F2FS_ATTR_OFFSET(_struct_type, _name, _mode, _show, _store, _offset) \
static struct f2fs_attr f2fs_attr_##_name = { \
.attr = {.name = __stringify(_name), .mode = _mode }, \
.show = _show, \
.store = _store, \
.struct_type = _struct_type, \
.offset = _offset \
}
#define F2FS_RW_ATTR(struct_type, struct_name, name, elname) \
F2FS_ATTR_OFFSET(struct_type, name, 0644, \
f2fs_sbi_show, f2fs_sbi_store, \
offsetof(struct struct_name, elname))
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, max_small_discards, max_discards);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
static struct attribute *f2fs_attrs[] = {
ATTR_LIST(gc_min_sleep_time),
ATTR_LIST(gc_max_sleep_time),
ATTR_LIST(gc_no_gc_sleep_time),
ATTR_LIST(gc_idle),
ATTR_LIST(reclaim_segments),
ATTR_LIST(max_small_discards),
ATTR_LIST(batched_trim_sections),
ATTR_LIST(ipu_policy),
ATTR_LIST(min_ipu_util),
ATTR_LIST(min_fsync_blocks),
ATTR_LIST(max_victim_search),
ATTR_LIST(dir_level),
ATTR_LIST(ram_thresh),
NULL,
};
static const struct sysfs_ops f2fs_attr_ops = {
.show = f2fs_attr_show,
.store = f2fs_attr_store,
};
static struct kobj_type f2fs_ktype = {
.default_attrs = f2fs_attrs,
.sysfs_ops = &f2fs_attr_ops,
.release = f2fs_sb_release,
};
void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
printk("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf);
va_end(args);
}
static void init_once(void *foo)
{
struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo;
inode_init_once(&fi->vfs_inode);
}
static int parse_options(struct super_block *sb, char *options)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct request_queue *q;
substring_t args[MAX_OPT_ARGS];
char *p, *name;
int arg = 0;
if (!options)
return 0;
while ((p = strsep(&options, ",")) != NULL) {
int token;
if (!*p)
continue;
/*
* Initialize args struct so we know whether arg was
* found; some options take optional arguments.
*/
args[0].to = args[0].from = NULL;
token = match_token(p, f2fs_tokens, args);
switch (token) {
case Opt_gc_background:
name = match_strdup(&args[0]);
if (!name)
return -ENOMEM;
if (strlen(name) == 2 && !strncmp(name, "on", 2)) {
set_opt(sbi, BG_GC);
clear_opt(sbi, FORCE_FG_GC);
} else if (strlen(name) == 3 && !strncmp(name, "off", 3)) {
clear_opt(sbi, BG_GC);
clear_opt(sbi, FORCE_FG_GC);
} else if (strlen(name) == 4 && !strncmp(name, "sync", 4)) {
set_opt(sbi, BG_GC);
set_opt(sbi, FORCE_FG_GC);
} else {
kfree(name);
return -EINVAL;
}
kfree(name);
break;
case Opt_disable_roll_forward:
set_opt(sbi, DISABLE_ROLL_FORWARD);
break;
case Opt_norecovery:
/* this option mounts f2fs with ro */
set_opt(sbi, DISABLE_ROLL_FORWARD);
if (!f2fs_readonly(sb))
return -EINVAL;
break;
case Opt_discard:
q = bdev_get_queue(sb->s_bdev);
if (blk_queue_discard(q)) {
set_opt(sbi, DISCARD);
} else {
f2fs_msg(sb, KERN_WARNING,
"mounting with \"discard\" option, but "
"the device does not support discard");
}
break;
case Opt_noheap:
set_opt(sbi, NOHEAP);
break;
#ifdef CONFIG_F2FS_FS_XATTR
case Opt_user_xattr:
set_opt(sbi, XATTR_USER);
break;
case Opt_nouser_xattr:
clear_opt(sbi, XATTR_USER);
break;
case Opt_inline_xattr:
set_opt(sbi, INLINE_XATTR);
break;
#else
case Opt_user_xattr:
f2fs_msg(sb, KERN_INFO,
"user_xattr options not supported");
break;
case Opt_nouser_xattr:
f2fs_msg(sb, KERN_INFO,
"nouser_xattr options not supported");
break;
case Opt_inline_xattr:
f2fs_msg(sb, KERN_INFO,
"inline_xattr options not supported");
break;
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
case Opt_acl:
set_opt(sbi, POSIX_ACL);
break;
case Opt_noacl:
clear_opt(sbi, POSIX_ACL);
break;
#else
case Opt_acl:
f2fs_msg(sb, KERN_INFO, "acl options not supported");
break;
case Opt_noacl:
f2fs_msg(sb, KERN_INFO, "noacl options not supported");
break;
#endif
case Opt_active_logs:
if (args->from && match_int(args, &arg))
return -EINVAL;
if (arg != 2 && arg != 4 && arg != NR_CURSEG_TYPE)
return -EINVAL;
sbi->active_logs = arg;
break;
case Opt_disable_ext_identify:
set_opt(sbi, DISABLE_EXT_IDENTIFY);
break;
case Opt_inline_data:
set_opt(sbi, INLINE_DATA);
break;
case Opt_inline_dentry:
set_opt(sbi, INLINE_DENTRY);
break;
case Opt_flush_merge:
set_opt(sbi, FLUSH_MERGE);
break;
case Opt_nobarrier:
set_opt(sbi, NOBARRIER);
break;
case Opt_fastboot:
set_opt(sbi, FASTBOOT);
break;
case Opt_extent_cache:
set_opt(sbi, EXTENT_CACHE);
break;
case Opt_noextent_cache:
clear_opt(sbi, EXTENT_CACHE);
break;
case Opt_noinline_data:
clear_opt(sbi, INLINE_DATA);
break;
default:
f2fs_msg(sb, KERN_ERR,
"Unrecognized mount option \"%s\" or missing value",
p);
return -EINVAL;
}
}
return 0;
}
static struct inode *f2fs_alloc_inode(struct super_block *sb)
{
struct f2fs_inode_info *fi;
fi = kmem_cache_alloc(f2fs_inode_cachep, GFP_F2FS_ZERO);
if (!fi)
return NULL;
init_once((void *) fi);
/* Initialize f2fs-specific inode info */
fi->vfs_inode.i_version = 1;
atomic_set(&fi->dirty_pages, 0);
fi->i_current_depth = 1;
fi->i_advise = 0;
init_rwsem(&fi->i_sem);
INIT_LIST_HEAD(&fi->inmem_pages);
mutex_init(&fi->inmem_lock);
set_inode_flag(fi, FI_NEW_INODE);
if (test_opt(F2FS_SB(sb), INLINE_XATTR))
set_inode_flag(fi, FI_INLINE_XATTR);
/* Will be used by directory only */
fi->i_dir_level = F2FS_SB(sb)->dir_level;
#ifdef CONFIG_F2FS_FS_ENCRYPTION
fi->i_crypt_info = NULL;
#endif
return &fi->vfs_inode;
}
static int f2fs_drop_inode(struct inode *inode)
{
/*
* This is to avoid a deadlock condition like below.
* writeback_single_inode(inode)
* - f2fs_write_data_page
* - f2fs_gc -> iput -> evict
* - inode_wait_for_writeback(inode)
*/
if (!inode_unhashed(inode) && inode->i_state & I_SYNC) {
if (!inode->i_nlink && !is_bad_inode(inode)) {
/* to avoid evict_inode call simultaneously */
atomic_inc(&inode->i_count);
spin_unlock(&inode->i_lock);
/* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
commit_inmem_pages(inode, true);
/* should remain fi->extent_tree for writepage */
f2fs_destroy_extent_node(inode);
sb_start_intwrite(inode->i_sb);
i_size_write(inode, 0);
if (F2FS_HAS_BLOCKS(inode))
f2fs_truncate(inode, true);
sb_end_intwrite(inode->i_sb);
#ifdef CONFIG_F2FS_FS_ENCRYPTION
if (F2FS_I(inode)->i_crypt_info)
f2fs_free_encryption_info(inode,
F2FS_I(inode)->i_crypt_info);
#endif
spin_lock(&inode->i_lock);
atomic_dec(&inode->i_count);
}
return 0;
}
return generic_drop_inode(inode);
}
/*
* f2fs_dirty_inode() is called from __mark_inode_dirty()
*
* We should call set_dirty_inode to write the dirty inode through write_inode.
*/
static void f2fs_dirty_inode(struct inode *inode, int flags)
{
set_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
}
static void f2fs_i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(f2fs_inode_cachep, F2FS_I(inode));
}
static void f2fs_destroy_inode(struct inode *inode)
{
call_rcu(&inode->i_rcu, f2fs_i_callback);
}
static void f2fs_put_super(struct super_block *sb)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
if (sbi->s_proc) {
remove_proc_entry("segment_info", sbi->s_proc);
remove_proc_entry(sb->s_id, f2fs_proc_root);
}
kobject_del(&sbi->s_kobj);
stop_gc_thread(sbi);
/* prevent remaining shrinker jobs */
mutex_lock(&sbi->umount_mutex);
/*
* We don't need to do checkpoint when superblock is clean.
* But, the previous checkpoint was not done by umount, it needs to do
* clean checkpoint again.
*/
if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) ||
!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG)) {
struct cp_control cpc = {
.reason = CP_UMOUNT,
};
write_checkpoint(sbi, &cpc);
}
/* write_checkpoint can update stat informaion */
f2fs_destroy_stats(sbi);
/*
* normally superblock is clean, so we need to release this.
* In addition, EIO will skip do checkpoint, we need this as well.
*/
release_dirty_inode(sbi);
release_discard_addrs(sbi);
f2fs_leave_shrinker(sbi);
mutex_unlock(&sbi->umount_mutex);
iput(sbi->node_inode);
iput(sbi->meta_inode);
/* destroy f2fs internal modules */
destroy_node_manager(sbi);
destroy_segment_manager(sbi);
kfree(sbi->ckpt);
kobject_put(&sbi->s_kobj);
wait_for_completion(&sbi->s_kobj_unregister);
sb->s_fs_info = NULL;
brelse(sbi->raw_super_buf);
kfree(sbi);
}
int f2fs_sync_fs(struct super_block *sb, int sync)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
trace_f2fs_sync_fs(sb, sync);
if (sync) {
struct cp_control cpc;
cpc.reason = __get_cp_reason(sbi);
mutex_lock(&sbi->gc_mutex);
write_checkpoint(sbi, &cpc);
mutex_unlock(&sbi->gc_mutex);
} else {
f2fs_balance_fs(sbi);
}
f2fs_trace_ios(NULL, 1);
return 0;
}
static int f2fs_freeze(struct super_block *sb)
{
int err;
if (f2fs_readonly(sb))
return 0;
err = f2fs_sync_fs(sb, 1);
return err;
}
static int f2fs_unfreeze(struct super_block *sb)
{
return 0;
}
static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct f2fs_sb_info *sbi = F2FS_SB(sb);
u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
block_t total_count, user_block_count, start_count, ovp_count;
total_count = le64_to_cpu(sbi->raw_super->block_count);
user_block_count = sbi->user_block_count;
start_count = le32_to_cpu(sbi->raw_super->segment0_blkaddr);
ovp_count = SM_I(sbi)->ovp_segments << sbi->log_blocks_per_seg;
buf->f_type = F2FS_SUPER_MAGIC;
buf->f_bsize = sbi->blocksize;
buf->f_blocks = total_count - start_count;
buf->f_bfree = buf->f_blocks - valid_user_blocks(sbi) - ovp_count;
buf->f_bavail = user_block_count - valid_user_blocks(sbi);
buf->f_files = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
buf->f_ffree = buf->f_files - valid_inode_count(sbi);
buf->f_namelen = F2FS_NAME_LEN;
buf->f_fsid.val[0] = (u32)id;
buf->f_fsid.val[1] = (u32)(id >> 32);
return 0;
}
static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
{
struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);
if (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC)) {
if (test_opt(sbi, FORCE_FG_GC))
seq_printf(seq, ",background_gc=%s", "sync");
else
seq_printf(seq, ",background_gc=%s", "on");
} else {
seq_printf(seq, ",background_gc=%s", "off");
}
if (test_opt(sbi, DISABLE_ROLL_FORWARD))
seq_puts(seq, ",disable_roll_forward");
if (test_opt(sbi, DISCARD))
seq_puts(seq, ",discard");
if (test_opt(sbi, NOHEAP))
seq_puts(seq, ",no_heap_alloc");
#ifdef CONFIG_F2FS_FS_XATTR
if (test_opt(sbi, XATTR_USER))
seq_puts(seq, ",user_xattr");
else
seq_puts(seq, ",nouser_xattr");
if (test_opt(sbi, INLINE_XATTR))
seq_puts(seq, ",inline_xattr");
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
if (test_opt(sbi, POSIX_ACL))
seq_puts(seq, ",acl");
else
seq_puts(seq, ",noacl");
#endif
if (test_opt(sbi, DISABLE_EXT_IDENTIFY))
seq_puts(seq, ",disable_ext_identify");
if (test_opt(sbi, INLINE_DATA))
seq_puts(seq, ",inline_data");
else
seq_puts(seq, ",noinline_data");
if (test_opt(sbi, INLINE_DENTRY))
seq_puts(seq, ",inline_dentry");
if (!f2fs_readonly(sbi->sb) && test_opt(sbi, FLUSH_MERGE))
seq_puts(seq, ",flush_merge");
if (test_opt(sbi, NOBARRIER))
seq_puts(seq, ",nobarrier");
if (test_opt(sbi, FASTBOOT))
seq_puts(seq, ",fastboot");
if (test_opt(sbi, EXTENT_CACHE))
seq_puts(seq, ",extent_cache");
else
seq_puts(seq, ",noextent_cache");
seq_printf(seq, ",active_logs=%u", sbi->active_logs);
return 0;
}
static int segment_info_seq_show(struct seq_file *seq, void *offset)
{
struct super_block *sb = seq->private;
struct f2fs_sb_info *sbi = F2FS_SB(sb);
unsigned int total_segs =
le32_to_cpu(sbi->raw_super->segment_count_main);
int i;
seq_puts(seq, "format: segment_type|valid_blocks\n"
"segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
for (i = 0; i < total_segs; i++) {
struct seg_entry *se = get_seg_entry(sbi, i);
if ((i % 10) == 0)
seq_printf(seq, "%-10d", i);
seq_printf(seq, "%d|%-3u", se->type,
get_valid_blocks(sbi, i, 1));
if ((i % 10) == 9 || i == (total_segs - 1))
seq_putc(seq, '\n');
else
seq_putc(seq, ' ');
}
return 0;
}
static int segment_info_open_fs(struct inode *inode, struct file *file)
{
return single_open(file, segment_info_seq_show, PDE_DATA(inode));
}
static const struct file_operations f2fs_seq_segment_info_fops = {
.owner = THIS_MODULE,
.open = segment_info_open_fs,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static void default_options(struct f2fs_sb_info *sbi)
{
/* init some FS parameters */
sbi->active_logs = NR_CURSEG_TYPE;
set_opt(sbi, BG_GC);
set_opt(sbi, INLINE_DATA);
set_opt(sbi, EXTENT_CACHE);
#ifdef CONFIG_F2FS_FS_XATTR
set_opt(sbi, XATTR_USER);
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
set_opt(sbi, POSIX_ACL);
#endif
}
static int f2fs_remount(struct super_block *sb, int *flags, char *data)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct f2fs_mount_info org_mount_opt;
int err, active_logs;
bool need_restart_gc = false;
bool need_stop_gc = false;
bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE);
fs: push sync_filesystem() down to the file system's remount_fs() Previously, the no-op "mount -o mount /dev/xxx" operation when the file system is already mounted read-write causes an implied, unconditional syncfs(). This seems pretty stupid, and it's certainly documented or guaraunteed to do this, nor is it particularly useful, except in the case where the file system was mounted rw and is getting remounted read-only. However, it's possible that there might be some file systems that are actually depending on this behavior. In most file systems, it's probably fine to only call sync_filesystem() when transitioning from read-write to read-only, and there are some file systems where this is not needed at all (for example, for a pseudo-filesystem or something like romfs). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: linux-fsdevel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Artem Bityutskiy <dedekind1@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Evgeniy Dushistov <dushistov@mail.ru> Cc: Jan Kara <jack@suse.cz> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Anders Larsen <al@alarsen.net> Cc: Phillip Lougher <phillip@squashfs.org.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz> Cc: Petr Vandrovec <petr@vandrovec.name> Cc: xfs@oss.sgi.com Cc: linux-btrfs@vger.kernel.org Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Cc: codalist@coda.cs.cmu.edu Cc: linux-ext4@vger.kernel.org Cc: linux-f2fs-devel@lists.sourceforge.net Cc: fuse-devel@lists.sourceforge.net Cc: cluster-devel@redhat.com Cc: linux-mtd@lists.infradead.org Cc: jfs-discussion@lists.sourceforge.net Cc: linux-nfs@vger.kernel.org Cc: linux-nilfs@vger.kernel.org Cc: linux-ntfs-dev@lists.sourceforge.net Cc: ocfs2-devel@oss.oracle.com Cc: reiserfs-devel@vger.kernel.org
2014-03-13 15:14:33 +01:00
sync_filesystem(sb);
/*
* Save the old mount options in case we
* need to restore them.
*/
org_mount_opt = sbi->mount_opt;
active_logs = sbi->active_logs;
sbi->mount_opt.opt = 0;
default_options(sbi);
/* parse mount options */
err = parse_options(sb, data);
if (err)
goto restore_opts;
/*
* Previous and new state of filesystem is RO,
* so skip checking GC and FLUSH_MERGE conditions.
*/
if (f2fs_readonly(sb) && (*flags & MS_RDONLY))
goto skip;
/* disallow enable/disable extent_cache dynamically */
if (no_extent_cache == !!test_opt(sbi, EXTENT_CACHE)) {
err = -EINVAL;
f2fs_msg(sbi->sb, KERN_WARNING,
"switch extent_cache option is not allowed");
goto restore_opts;
}
/*
* We stop the GC thread if FS is mounted as RO
* or if background_gc = off is passed in mount
* option. Also sync the filesystem.
*/
if ((*flags & MS_RDONLY) || !test_opt(sbi, BG_GC)) {
if (sbi->gc_thread) {
stop_gc_thread(sbi);
f2fs_sync_fs(sb, 1);
need_restart_gc = true;
}
} else if (!sbi->gc_thread) {
err = start_gc_thread(sbi);
if (err)
goto restore_opts;
need_stop_gc = true;
}
/*
* We stop issue flush thread if FS is mounted as RO
* or if flush_merge is not passed in mount option.
*/
if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) {
destroy_flush_cmd_control(sbi);
} else if (!SM_I(sbi)->cmd_control_info) {
err = create_flush_cmd_control(sbi);
if (err)
goto restore_gc;
}
skip:
/* Update the POSIXACL Flag */
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
return 0;
restore_gc:
if (need_restart_gc) {
if (start_gc_thread(sbi))
f2fs_msg(sbi->sb, KERN_WARNING,
"background gc thread has stopped");
} else if (need_stop_gc) {
stop_gc_thread(sbi);
}
restore_opts:
sbi->mount_opt = org_mount_opt;
sbi->active_logs = active_logs;
return err;
}
static struct super_operations f2fs_sops = {
.alloc_inode = f2fs_alloc_inode,
.drop_inode = f2fs_drop_inode,
.destroy_inode = f2fs_destroy_inode,
.write_inode = f2fs_write_inode,
.dirty_inode = f2fs_dirty_inode,
.show_options = f2fs_show_options,
.evict_inode = f2fs_evict_inode,
.put_super = f2fs_put_super,
.sync_fs = f2fs_sync_fs,
.freeze_fs = f2fs_freeze,
.unfreeze_fs = f2fs_unfreeze,
.statfs = f2fs_statfs,
.remount_fs = f2fs_remount,
};
static struct inode *f2fs_nfs_get_inode(struct super_block *sb,
u64 ino, u32 generation)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct inode *inode;
if (check_nid_range(sbi, ino))
return ERR_PTR(-ESTALE);
/*
* f2fs_iget isn't quite right if the inode is currently unallocated!
* However f2fs_iget currently does appropriate checks to handle stale
* inodes so everything is OK.
*/
inode = f2fs_iget(sb, ino);
if (IS_ERR(inode))
return ERR_CAST(inode);
if (unlikely(generation && inode->i_generation != generation)) {
/* we didn't find the right inode.. */
iput(inode);
return ERR_PTR(-ESTALE);
}
return inode;
}
static struct dentry *f2fs_fh_to_dentry(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type)
{
return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
f2fs_nfs_get_inode);
}
static struct dentry *f2fs_fh_to_parent(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type)
{
return generic_fh_to_parent(sb, fid, fh_len, fh_type,
f2fs_nfs_get_inode);
}
static const struct export_operations f2fs_export_ops = {
.fh_to_dentry = f2fs_fh_to_dentry,
.fh_to_parent = f2fs_fh_to_parent,
.get_parent = f2fs_get_parent,
};
static loff_t max_file_size(unsigned bits)
{
loff_t result = (DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS);
loff_t leaf_count = ADDRS_PER_BLOCK;
/* two direct node blocks */
result += (leaf_count * 2);
/* two indirect node blocks */
leaf_count *= NIDS_PER_BLOCK;
result += (leaf_count * 2);
/* one double indirect node block */
leaf_count *= NIDS_PER_BLOCK;
result += leaf_count;
result <<= bits;
return result;
}
static int sanity_check_raw_super(struct super_block *sb,
struct f2fs_super_block *raw_super)
{
unsigned int blocksize;
if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
f2fs_msg(sb, KERN_INFO,
"Magic Mismatch, valid(0x%x) - read(0x%x)",
F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic));
return 1;
}
/* Currently, support only 4KB page cache size */
if (F2FS_BLKSIZE != PAGE_CACHE_SIZE) {
f2fs_msg(sb, KERN_INFO,
"Invalid page_cache_size (%lu), supports only 4KB\n",
PAGE_CACHE_SIZE);
return 1;
}
/* Currently, support only 4KB block size */
blocksize = 1 << le32_to_cpu(raw_super->log_blocksize);
if (blocksize != F2FS_BLKSIZE) {
f2fs_msg(sb, KERN_INFO,
"Invalid blocksize (%u), supports only 4KB\n",
blocksize);
return 1;
}
/* Currently, support 512/1024/2048/4096 bytes sector size */
if (le32_to_cpu(raw_super->log_sectorsize) >
F2FS_MAX_LOG_SECTOR_SIZE ||
le32_to_cpu(raw_super->log_sectorsize) <
F2FS_MIN_LOG_SECTOR_SIZE) {
f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize (%u)",
le32_to_cpu(raw_super->log_sectorsize));
return 1;
}
if (le32_to_cpu(raw_super->log_sectors_per_block) +
le32_to_cpu(raw_super->log_sectorsize) !=
F2FS_MAX_LOG_SECTOR_SIZE) {
f2fs_msg(sb, KERN_INFO,
"Invalid log sectors per block(%u) log sectorsize(%u)",
le32_to_cpu(raw_super->log_sectors_per_block),
le32_to_cpu(raw_super->log_sectorsize));
return 1;
}
return 0;
}
static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
{
unsigned int total, fsmeta;
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
total = le32_to_cpu(raw_super->segment_count);
fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
fsmeta += le32_to_cpu(raw_super->segment_count_sit);
fsmeta += le32_to_cpu(raw_super->segment_count_nat);
fsmeta += le32_to_cpu(ckpt->rsvd_segment_count);
fsmeta += le32_to_cpu(raw_super->segment_count_ssa);
if (unlikely(fsmeta >= total))
return 1;
if (unlikely(f2fs_cp_error(sbi))) {
f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
return 1;
}
return 0;
}
static void init_sb_info(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *raw_super = sbi->raw_super;
int i;
sbi->log_sectors_per_block =
le32_to_cpu(raw_super->log_sectors_per_block);
sbi->log_blocksize = le32_to_cpu(raw_super->log_blocksize);
sbi->blocksize = 1 << sbi->log_blocksize;
sbi->log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
sbi->blocks_per_seg = 1 << sbi->log_blocks_per_seg;
sbi->segs_per_sec = le32_to_cpu(raw_super->segs_per_sec);
sbi->secs_per_zone = le32_to_cpu(raw_super->secs_per_zone);
sbi->total_sections = le32_to_cpu(raw_super->section_count);
sbi->total_node_count =
(le32_to_cpu(raw_super->segment_count_nat) / 2)
* sbi->blocks_per_seg * NAT_ENTRY_PER_BLOCK;
sbi->root_ino_num = le32_to_cpu(raw_super->root_ino);
sbi->node_ino_num = le32_to_cpu(raw_super->node_ino);
sbi->meta_ino_num = le32_to_cpu(raw_super->meta_ino);
sbi->cur_victim_sec = NULL_SECNO;
sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH;
for (i = 0; i < NR_COUNT_TYPE; i++)
atomic_set(&sbi->nr_pages[i], 0);
sbi->dir_level = DEF_DIR_LEVEL;
clear_sbi_flag(sbi, SBI_NEED_FSCK);
INIT_LIST_HEAD(&sbi->s_list);
mutex_init(&sbi->umount_mutex);
}
/*
* Read f2fs raw super block.
* Because we have two copies of super block, so read the first one at first,
* if the first one is invalid, move to read the second one.
*/
static int read_raw_super_block(struct super_block *sb,
struct f2fs_super_block **raw_super,
struct buffer_head **raw_super_buf,
int *recovery)
{
int block = 0;
struct buffer_head *buffer;
struct f2fs_super_block *super;
int err = 0;
retry:
buffer = sb_bread(sb, block);
if (!buffer) {
*recovery = 1;
f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock",
block + 1);
if (block == 0) {
block++;
goto retry;
} else {
err = -EIO;
goto out;
}
}
super = (struct f2fs_super_block *)
((char *)(buffer)->b_data + F2FS_SUPER_OFFSET);
/* sanity checking of raw super */
if (sanity_check_raw_super(sb, super)) {
brelse(buffer);
*recovery = 1;
f2fs_msg(sb, KERN_ERR,
"Can't find valid F2FS filesystem in %dth superblock",
block + 1);
if (block == 0) {
block++;
goto retry;
} else {
err = -EINVAL;
goto out;
}
}
if (!*raw_super) {
*raw_super_buf = buffer;
*raw_super = super;
} else {
/* already have a valid superblock */
brelse(buffer);
}
/* check the validity of the second superblock */
if (block == 0) {
block++;
goto retry;
}
out:
/* No valid superblock */
if (!*raw_super)
return err;
return 0;
}
int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
{
struct buffer_head *sbh = sbi->raw_super_buf;
sector_t block = sbh->b_blocknr;
int err;
/* write back-up superblock first */
sbh->b_blocknr = block ? 0 : 1;
mark_buffer_dirty(sbh);
err = sync_dirty_buffer(sbh);
sbh->b_blocknr = block;
/* if we are in recovery path, skip writing valid superblock */
if (recover || err)
goto out;
/* write current valid superblock */
mark_buffer_dirty(sbh);
err = sync_dirty_buffer(sbh);
out:
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
return err;
}
static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
{
struct f2fs_sb_info *sbi;
struct f2fs_super_block *raw_super;
struct buffer_head *raw_super_buf;
struct inode *root;
long err;
bool retry = true, need_fsck = false;
char *options = NULL;
int recovery, i;
try_onemore:
err = -EINVAL;
raw_super = NULL;
raw_super_buf = NULL;
recovery = 0;
/* allocate memory for f2fs-specific super block info */
sbi = kzalloc(sizeof(struct f2fs_sb_info), GFP_KERNEL);
if (!sbi)
return -ENOMEM;
/* set a block size */
if (unlikely(!sb_set_blocksize(sb, F2FS_BLKSIZE))) {
f2fs_msg(sb, KERN_ERR, "unable to set blocksize");
goto free_sbi;
}
err = read_raw_super_block(sb, &raw_super, &raw_super_buf, &recovery);
if (err)
goto free_sbi;
sb->s_fs_info = sbi;
default_options(sbi);
/* parse mount options */
options = kstrdup((const char *)data, GFP_KERNEL);
if (data && !options) {
err = -ENOMEM;
goto free_sb_buf;
}
err = parse_options(sb, options);
if (err)
goto free_options;
sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
sb->s_max_links = F2FS_LINK_MAX;
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
sb->s_op = &f2fs_sops;
sb->s_xattr = f2fs_xattr_handlers;
sb->s_export_op = &f2fs_export_ops;
sb->s_magic = F2FS_SUPER_MAGIC;
sb->s_time_gran = 1;
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
/* init f2fs-specific super block info */
sbi->sb = sb;
sbi->raw_super = raw_super;
sbi->raw_super_buf = raw_super_buf;
mutex_init(&sbi->gc_mutex);
mutex_init(&sbi->writepages);
mutex_init(&sbi->cp_mutex);
init_rwsem(&sbi->node_write);
/* disallow all the data/node/meta page writes */
set_sbi_flag(sbi, SBI_POR_DOING);
spin_lock_init(&sbi->stat_lock);
init_rwsem(&sbi->read_io.io_rwsem);
sbi->read_io.sbi = sbi;
sbi->read_io.bio = NULL;
for (i = 0; i < NR_PAGE_TYPE; i++) {
init_rwsem(&sbi->write_io[i].io_rwsem);
sbi->write_io[i].sbi = sbi;
sbi->write_io[i].bio = NULL;
}
f2fs: use rw_sem instead of fs_lock(locks mutex) The fs_locks is used to block other ops(ex, recovery) when doing checkpoint. And each other operate routine(besides checkpoint) needs to acquire a fs_lock, there is a terrible problem here, if these are too many concurrency threads acquiring fs_lock, so that they will block each other and may lead to some performance problem, but this is not the phenomenon we want to see. Though there are some optimization patches introduced to enhance the usage of fs_lock, but the thorough solution is using a *rw_sem* to replace the fs_lock. Checkpoint routine takes write_sem, and other ops take read_sem, so that we can block other ops(ex, recovery) when doing checkpoint, and other ops will not disturb each other, this can avoid the problem described above completely. Because of the weakness of rw_sem, the above change may introduce a potential problem that the checkpoint thread might get starved if other threads are intensively locking the read semaphore for I/O.(Pointed out by Xu Jin) In order to avoid this, a wait_list is introduced, the appending read semaphore ops will be dropped into the wait_list if checkpoint thread is waiting for write semaphore, and will be waked up when checkpoint thread gives up write semaphore. Thanks to Kim's previous review and test, and will be very glad to see other guys' performance tests about this patch. V2: -fix the potential starvation problem. -use more suitable func name suggested by Xu Jin. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> [Jaegeuk Kim: adjust minor coding standard] Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-09-27 12:08:30 +02:00
init_rwsem(&sbi->cp_rwsem);
init_waitqueue_head(&sbi->cp_wait);
init_sb_info(sbi);
/* get an inode for meta space */
sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
if (IS_ERR(sbi->meta_inode)) {
f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode");
err = PTR_ERR(sbi->meta_inode);
goto free_options;
}
err = get_valid_checkpoint(sbi);
if (err) {
f2fs_msg(sb, KERN_ERR, "Failed to get valid F2FS checkpoint");
goto free_meta_inode;
}
/* sanity checking of checkpoint */
err = -EINVAL;
if (sanity_check_ckpt(sbi)) {
f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
goto free_cp;
}
sbi->total_valid_node_count =
le32_to_cpu(sbi->ckpt->valid_node_count);
sbi->total_valid_inode_count =
le32_to_cpu(sbi->ckpt->valid_inode_count);
sbi->user_block_count = le64_to_cpu(sbi->ckpt->user_block_count);
sbi->total_valid_block_count =
le64_to_cpu(sbi->ckpt->valid_block_count);
sbi->last_valid_block_count = sbi->total_valid_block_count;
sbi->alloc_valid_block_count = 0;
INIT_LIST_HEAD(&sbi->dir_inode_list);
spin_lock_init(&sbi->dir_inode_lock);
init_extent_cache_info(sbi);
init_ino_entry_info(sbi);
/* setup f2fs internal modules */
err = build_segment_manager(sbi);
if (err) {
f2fs_msg(sb, KERN_ERR,
"Failed to initialize F2FS segment manager");
goto free_sm;
}
err = build_node_manager(sbi);
if (err) {
f2fs_msg(sb, KERN_ERR,
"Failed to initialize F2FS node manager");
goto free_nm;
}
build_gc_manager(sbi);
/* get an inode for node space */
sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi));
if (IS_ERR(sbi->node_inode)) {
f2fs_msg(sb, KERN_ERR, "Failed to read node inode");
err = PTR_ERR(sbi->node_inode);
goto free_nm;
}
f2fs_join_shrinker(sbi);
/* if there are nt orphan nodes free them */
err = recover_orphan_inodes(sbi);
if (err)
goto free_node_inode;
/* read root inode and dentry */
root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
if (IS_ERR(root)) {
f2fs_msg(sb, KERN_ERR, "Failed to read root inode");
err = PTR_ERR(root);
goto free_node_inode;
}
if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
iput(root);
err = -EINVAL;
goto free_node_inode;
}
sb->s_root = d_make_root(root); /* allocate root dentry */
if (!sb->s_root) {
err = -ENOMEM;
goto free_root_inode;
}
err = f2fs_build_stats(sbi);
if (err)
goto free_root_inode;
if (f2fs_proc_root)
sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
if (sbi->s_proc)
proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
&f2fs_seq_segment_info_fops, sb);
sbi->s_kobj.kset = f2fs_kset;
init_completion(&sbi->s_kobj_unregister);
err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL,
"%s", sb->s_id);
if (err)
goto free_proc;
/* recover fsynced data */
if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
/*
* mount should be failed, when device has readonly mode, and
* previous checkpoint was not done by clean system shutdown.
*/
if (bdev_read_only(sb->s_bdev) &&
!is_set_ckpt_flags(sbi->ckpt, CP_UMOUNT_FLAG)) {
err = -EROFS;
goto free_kobj;
}
if (need_fsck)
set_sbi_flag(sbi, SBI_NEED_FSCK);
err = recover_fsync_data(sbi);
if (err) {
need_fsck = true;
f2fs_msg(sb, KERN_ERR,
"Cannot recover all fsync data errno=%ld", err);
goto free_kobj;
}
}
/* recover_fsync_data() cleared this already */
clear_sbi_flag(sbi, SBI_POR_DOING);
/*
* If filesystem is not mounted as read-only then
* do start the gc_thread.
*/
if (test_opt(sbi, BG_GC) && !f2fs_readonly(sb)) {
/* After POR, we can run background GC thread.*/
err = start_gc_thread(sbi);
if (err)
goto free_kobj;
}
kfree(options);
/* recover broken superblock */
if (recovery && !f2fs_readonly(sb) && !bdev_read_only(sb->s_bdev)) {
f2fs_msg(sb, KERN_INFO, "Recover invalid superblock");
f2fs_commit_super(sbi, true);
}
return 0;
free_kobj:
kobject_del(&sbi->s_kobj);
free_proc:
if (sbi->s_proc) {
remove_proc_entry("segment_info", sbi->s_proc);
remove_proc_entry(sb->s_id, f2fs_proc_root);
}
f2fs_destroy_stats(sbi);
free_root_inode:
dput(sb->s_root);
sb->s_root = NULL;
free_node_inode:
mutex_lock(&sbi->umount_mutex);
f2fs_leave_shrinker(sbi);
iput(sbi->node_inode);
mutex_unlock(&sbi->umount_mutex);
free_nm:
destroy_node_manager(sbi);
free_sm:
destroy_segment_manager(sbi);
free_cp:
kfree(sbi->ckpt);
free_meta_inode:
make_bad_inode(sbi->meta_inode);
iput(sbi->meta_inode);
free_options:
kfree(options);
free_sb_buf:
brelse(raw_super_buf);
free_sbi:
kfree(sbi);
/* give only one another chance */
if (retry) {
retry = false;
shrink_dcache_sb(sb);
goto try_onemore;
}
return err;
}
static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags,
const char *dev_name, void *data)
{
return mount_bdev(fs_type, flags, dev_name, data, f2fs_fill_super);
}
static void kill_f2fs_super(struct super_block *sb)
{
if (sb->s_root)
set_sbi_flag(F2FS_SB(sb), SBI_IS_CLOSE);
kill_block_super(sb);
}
static struct file_system_type f2fs_fs_type = {
.owner = THIS_MODULE,
.name = "f2fs",
.mount = f2fs_mount,
.kill_sb = kill_f2fs_super,
.fs_flags = FS_REQUIRES_DEV,
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-03 04:39:14 +01:00
MODULE_ALIAS_FS("f2fs");
static int __init init_inodecache(void)
{
f2fs_inode_cachep = f2fs_kmem_cache_create("f2fs_inode_cache",
sizeof(struct f2fs_inode_info));
if (!f2fs_inode_cachep)
return -ENOMEM;
return 0;
}
static void destroy_inodecache(void)
{
/*
* Make sure all delayed rcu free inodes are flushed before we
* destroy cache.
*/
rcu_barrier();
kmem_cache_destroy(f2fs_inode_cachep);
}
static int __init init_f2fs_fs(void)
{
int err;
f2fs_build_trace_ios();
err = init_inodecache();
if (err)
goto fail;
err = create_node_manager_caches();
if (err)
goto free_inodecache;
err = create_segment_manager_caches();
if (err)
goto free_node_manager_caches;
err = create_checkpoint_caches();
if (err)
goto free_segment_manager_caches;
err = create_extent_cache();
if (err)
goto free_checkpoint_caches;
f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
if (!f2fs_kset) {
err = -ENOMEM;
goto free_extent_cache;
}
err = f2fs_init_crypto();
if (err)
goto free_kset;
err = register_shrinker(&f2fs_shrinker_info);
if (err)
goto free_crypto;
err = register_filesystem(&f2fs_fs_type);
if (err)
goto free_shrinker;
f2fs_create_root_stats();
f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
return 0;
free_shrinker:
unregister_shrinker(&f2fs_shrinker_info);
free_crypto:
f2fs_exit_crypto();
free_kset:
kset_unregister(f2fs_kset);
free_extent_cache:
destroy_extent_cache();
free_checkpoint_caches:
destroy_checkpoint_caches();
free_segment_manager_caches:
destroy_segment_manager_caches();
free_node_manager_caches:
destroy_node_manager_caches();
free_inodecache:
destroy_inodecache();
fail:
return err;
}
static void __exit exit_f2fs_fs(void)
{
remove_proc_entry("fs/f2fs", NULL);
f2fs_destroy_root_stats();
unregister_shrinker(&f2fs_shrinker_info);
unregister_filesystem(&f2fs_fs_type);
f2fs_exit_crypto();
destroy_extent_cache();
destroy_checkpoint_caches();
destroy_segment_manager_caches();
destroy_node_manager_caches();
destroy_inodecache();
kset_unregister(f2fs_kset);
f2fs_destroy_trace_ios();
}
module_init(init_f2fs_fs)
module_exit(exit_f2fs_fs)
MODULE_AUTHOR("Samsung Electronics's Praesto Team");
MODULE_DESCRIPTION("Flash Friendly File System");
MODULE_LICENSE("GPL");