OpenCloudOS-Kernel/fs/nilfs2/nilfs.h

374 lines
12 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0+ */
/*
* nilfs.h - NILFS local header file.
*
* Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
*
* Written by Koji Sato and Ryusuke Konishi.
*/
#ifndef _NILFS_H
#define _NILFS_H
#include <linux/kernel.h>
#include <linux/buffer_head.h>
#include <linux/spinlock.h>
#include <linux/blkdev.h>
#include <linux/nilfs2_api.h>
#include <linux/nilfs2_ondisk.h>
#include "the_nilfs.h"
#include "bmap.h"
/**
* struct nilfs_inode_info - nilfs inode data in memory
* @i_flags: inode flags
* @i_state: dynamic state flags
* @i_bmap: pointer on i_bmap_data
* @i_bmap_data: raw block mapping
* @i_xattr: <TODO>
* @i_dir_start_lookup: page index of last successful search
* @i_cno: checkpoint number for GC inode
* @i_assoc_inode: associated inode (B-tree node cache holder or back pointer)
* @i_dirty: list for connecting dirty files
* @xattr_sem: semaphore for extended attributes processing
* @i_bh: buffer contains disk inode
* @i_root: root object of the current filesystem tree
* @vfs_inode: VFS inode object
*/
struct nilfs_inode_info {
__u32 i_flags;
unsigned long i_state; /* Dynamic state flags */
struct nilfs_bmap *i_bmap;
struct nilfs_bmap i_bmap_data;
__u64 i_xattr; /* sector_t ??? */
__u32 i_dir_start_lookup;
__u64 i_cno; /* check point number for GC inode */
struct inode *i_assoc_inode;
struct list_head i_dirty; /* List for connecting dirty files */
#ifdef CONFIG_NILFS_XATTR
/*
* Extended attributes can be read independently of the main file
* data. Taking i_sem even when reading would cause contention
* between readers of EAs and writers of regular file data, so
* instead we synchronize on xattr_sem when reading or changing
* EAs.
*/
struct rw_semaphore xattr_sem;
#endif
struct buffer_head *i_bh; /*
* i_bh contains a new or dirty
* disk inode.
*/
struct nilfs_root *i_root;
struct inode vfs_inode;
};
static inline struct nilfs_inode_info *NILFS_I(const struct inode *inode)
{
return container_of(inode, struct nilfs_inode_info, vfs_inode);
}
static inline struct nilfs_inode_info *
NILFS_BMAP_I(const struct nilfs_bmap *bmap)
{
return container_of(bmap, struct nilfs_inode_info, i_bmap_data);
}
/*
* Dynamic state flags of NILFS on-memory inode (i_state)
*/
enum {
NILFS_I_NEW = 0, /* Inode is newly created */
NILFS_I_DIRTY, /* The file is dirty */
NILFS_I_QUEUED, /* inode is in dirty_files list */
NILFS_I_BUSY, /*
* Inode is grabbed by a segment
* constructor
*/
NILFS_I_COLLECTED, /* All dirty blocks are collected */
NILFS_I_UPDATED, /* The file has been written back */
NILFS_I_INODE_SYNC, /* dsync is not allowed for inode */
NILFS_I_BMAP, /* has bmap and btnode_cache */
NILFS_I_GCINODE, /* inode for GC, on memory only */
NILFS_I_BTNC, /* inode for btree node cache */
NILFS_I_SHADOW, /* inode for shadowed page cache */
};
/*
* commit flags for nilfs_commit_super and nilfs_sync_super
*/
enum {
NILFS_SB_COMMIT = 0, /* Commit a super block alternately */
NILFS_SB_COMMIT_ALL /* Commit both super blocks */
};
/*
* Macros to check inode numbers
*/
#define NILFS_MDT_INO_BITS \
(BIT(NILFS_DAT_INO) | BIT(NILFS_CPFILE_INO) | \
BIT(NILFS_SUFILE_INO) | BIT(NILFS_IFILE_INO) | \
BIT(NILFS_ATIME_INO) | BIT(NILFS_SKETCH_INO))
#define NILFS_SYS_INO_BITS (BIT(NILFS_ROOT_INO) | NILFS_MDT_INO_BITS)
#define NILFS_FIRST_INO(sb) (((struct the_nilfs *)sb->s_fs_info)->ns_first_ino)
#define NILFS_MDT_INODE(sb, ino) \
((ino) < NILFS_FIRST_INO(sb) && (NILFS_MDT_INO_BITS & BIT(ino)))
#define NILFS_VALID_INODE(sb, ino) \
((ino) >= NILFS_FIRST_INO(sb) || (NILFS_SYS_INO_BITS & BIT(ino)))
/**
* struct nilfs_transaction_info: context information for synchronization
* @ti_magic: Magic number
* @ti_save: Backup of journal_info field of task_struct
* @ti_flags: Flags
* @ti_count: Nest level
*/
struct nilfs_transaction_info {
u32 ti_magic;
void *ti_save;
/*
* This should never be used. If it happens,
* one of other filesystems has a bug.
*/
unsigned short ti_flags;
unsigned short ti_count;
};
/* ti_magic */
#define NILFS_TI_MAGIC 0xd9e392fb
/* ti_flags */
#define NILFS_TI_DYNAMIC_ALLOC 0x0001 /* Allocated from slab */
#define NILFS_TI_SYNC 0x0002 /*
* Force to construct segment at the
* end of transaction.
*/
#define NILFS_TI_GC 0x0004 /* GC context */
#define NILFS_TI_COMMIT 0x0008 /* Change happened or not */
#define NILFS_TI_WRITER 0x0010 /* Constructor context */
int nilfs_transaction_begin(struct super_block *,
struct nilfs_transaction_info *, int);
int nilfs_transaction_commit(struct super_block *);
void nilfs_transaction_abort(struct super_block *);
static inline void nilfs_set_transaction_flag(unsigned int flag)
{
struct nilfs_transaction_info *ti = current->journal_info;
ti->ti_flags |= flag;
}
static inline int nilfs_test_transaction_flag(unsigned int flag)
{
struct nilfs_transaction_info *ti = current->journal_info;
if (ti == NULL || ti->ti_magic != NILFS_TI_MAGIC)
return 0;
return !!(ti->ti_flags & flag);
}
static inline int nilfs_doing_gc(void)
{
return nilfs_test_transaction_flag(NILFS_TI_GC);
}
static inline int nilfs_doing_construction(void)
{
return nilfs_test_transaction_flag(NILFS_TI_WRITER);
}
/*
* function prototype
*/
#ifdef CONFIG_NILFS_POSIX_ACL
#error "NILFS: not yet supported POSIX ACL"
extern int nilfs_acl_chmod(struct inode *);
extern int nilfs_init_acl(struct inode *, struct inode *);
#else
static inline int nilfs_acl_chmod(struct inode *inode)
{
return 0;
}
static inline int nilfs_init_acl(struct inode *inode, struct inode *dir)
{
if (S_ISLNK(inode->i_mode))
return 0;
inode->i_mode &= ~current_umask();
return 0;
}
#endif
#define NILFS_ATIME_DISABLE
/* Flags that should be inherited by new inodes from their parent. */
#define NILFS_FL_INHERITED \
(FS_SECRM_FL | FS_UNRM_FL | FS_COMPR_FL | FS_SYNC_FL | \
FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL |\
FS_COMPRBLK_FL | FS_NOCOMP_FL | FS_NOTAIL_FL | FS_DIRSYNC_FL)
/* Mask out flags that are inappropriate for the given type of inode. */
static inline __u32 nilfs_mask_flags(umode_t mode, __u32 flags)
{
if (S_ISDIR(mode))
return flags;
else if (S_ISREG(mode))
return flags & ~(FS_DIRSYNC_FL | FS_TOPDIR_FL);
else
return flags & (FS_NODUMP_FL | FS_NOATIME_FL);
}
/* dir.c */
extern int nilfs_add_link(struct dentry *, struct inode *);
extern ino_t nilfs_inode_by_name(struct inode *, const struct qstr *);
extern int nilfs_make_empty(struct inode *, struct inode *);
extern struct nilfs_dir_entry *
nilfs_find_entry(struct inode *, const struct qstr *, struct page **);
extern int nilfs_delete_entry(struct nilfs_dir_entry *, struct page *);
extern int nilfs_empty_dir(struct inode *);
extern struct nilfs_dir_entry *nilfs_dotdot(struct inode *, struct page **);
extern void nilfs_set_link(struct inode *, struct nilfs_dir_entry *,
struct page *, struct inode *);
/* file.c */
extern int nilfs_sync_file(struct file *, loff_t, loff_t, int);
/* ioctl.c */
long nilfs_ioctl(struct file *, unsigned int, unsigned long);
long nilfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
nilfs2: fix lock order reversal in nilfs_clean_segments ioctl This is a companion patch to ("nilfs2: fix possible circular locking for get information ioctls"). This corrects lock order reversal between mm->mmap_sem and nilfs->ns_segctor_sem in nilfs_clean_segments() which was detected by lockdep check: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.30-rc3-nilfs-00003-g360bdc1 #7 ------------------------------------------------------- mmap/5294 is trying to acquire lock: (&nilfs->ns_segctor_sem){++++.+}, at: [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] but task is already holding lock: (&mm->mmap_sem){++++++}, at: [<c043700a>] do_page_fault+0x1d8/0x30a which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++++}: [<c01470a5>] __lock_acquire+0x1066/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c01836bc>] might_fault+0x68/0x88 [<c023c61d>] copy_from_user+0x2a/0x111 [<d0d120d0>] nilfs_ioctl_prepare_clean_segments+0x1d/0xf1 [nilfs2] [<d0d0e2aa>] nilfs_clean_segments+0x6d/0x1b9 [nilfs2] [<d0d11f68>] nilfs_ioctl+0x2ad/0x318 [nilfs2] [<c01a3be7>] vfs_ioctl+0x22/0x69 [<c01a408e>] do_vfs_ioctl+0x460/0x499 [<c01a4107>] sys_ioctl+0x40/0x5a [<c01031a4>] sysenter_do_call+0x12/0x38 [<ffffffff>] 0xffffffff -> #0 (&nilfs->ns_segctor_sem){++++.+}: [<c0146e0b>] __lock_acquire+0xdcc/0x13b0 [<c01474a9>] lock_acquire+0xba/0xdd [<c0433f1d>] down_read+0x2a/0x3e [<d0d0e846>] nilfs_transaction_begin+0xb6/0x10c [nilfs2] [<d0cfe0e5>] nilfs_page_mkwrite+0xe7/0x154 [nilfs2] [<c0183b0b>] __do_fault+0x165/0x376 [<c01855cd>] handle_mm_fault+0x287/0x5d1 [<c043712d>] do_page_fault+0x2fb/0x30a [<c0435462>] error_code+0x72/0x78 [<ffffffff>] 0xffffffff where nilfs_clean_segments() holds: nilfs->ns_segctor_sem -> copy_from_user() --> page fault -> mm->mmap_sem And, page fault path may hold: page fault -> mm->mmap_sem --> nilfs_page_mkwrite() -> nilfs->ns_segctor_sem Even though nilfs_clean_segments() does not perform write access on given user pages, it may cause deadlock because nilfs->ns_segctor_sem is shared per device and mm->mmap_sem can be shared with other tasks. To avoid this problem, this patch moves all calls of copy_from_user() outside the nilfs->ns_segctor_sem lock in the ioctl. Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
2009-05-10 21:41:43 +08:00
int nilfs_ioctl_prepare_clean_segments(struct the_nilfs *, struct nilfs_argv *,
void **);
/* inode.c */
void nilfs_inode_add_blocks(struct inode *inode, int n);
void nilfs_inode_sub_blocks(struct inode *inode, int n);
extern struct inode *nilfs_new_inode(struct inode *, umode_t);
extern int nilfs_get_block(struct inode *, sector_t, struct buffer_head *, int);
extern void nilfs_set_inode_flags(struct inode *);
extern int nilfs_read_inode_common(struct inode *, struct nilfs_inode *);
extern void nilfs_write_inode_common(struct inode *, struct nilfs_inode *, int);
struct inode *nilfs_ilookup(struct super_block *sb, struct nilfs_root *root,
unsigned long ino);
struct inode *nilfs_iget_locked(struct super_block *sb, struct nilfs_root *root,
unsigned long ino);
struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root,
unsigned long ino);
extern struct inode *nilfs_iget_for_gc(struct super_block *sb,
unsigned long ino, __u64 cno);
int nilfs_attach_btree_node_cache(struct inode *inode);
void nilfs_detach_btree_node_cache(struct inode *inode);
struct inode *nilfs_iget_for_shadow(struct inode *inode);
extern void nilfs_update_inode(struct inode *, struct buffer_head *, int);
extern void nilfs_truncate(struct inode *);
extern void nilfs_evict_inode(struct inode *);
extern int nilfs_setattr(struct dentry *, struct iattr *);
extern void nilfs_write_failed(struct address_space *mapping, loff_t to);
int nilfs_permission(struct inode *inode, int mask);
int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh);
extern int nilfs_inode_dirty(struct inode *);
int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty);
extern int __nilfs_mark_inode_dirty(struct inode *, int);
extern void nilfs_dirty_inode(struct inode *, int flags);
int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
static inline int nilfs_mark_inode_dirty(struct inode *inode)
{
return __nilfs_mark_inode_dirty(inode, I_DIRTY);
}
static inline int nilfs_mark_inode_dirty_sync(struct inode *inode)
{
return __nilfs_mark_inode_dirty(inode, I_DIRTY_SYNC);
}
/* super.c */
extern struct inode *nilfs_alloc_inode(struct super_block *);
extern __printf(3, 4)
void __nilfs_msg(struct super_block *sb, const char *level,
const char *fmt, ...);
extern __printf(3, 4)
void __nilfs_error(struct super_block *sb, const char *function,
const char *fmt, ...);
#ifdef CONFIG_PRINTK
#define nilfs_msg(sb, level, fmt, ...) \
__nilfs_msg(sb, level, fmt, ##__VA_ARGS__)
#define nilfs_error(sb, fmt, ...) \
__nilfs_error(sb, __func__, fmt, ##__VA_ARGS__)
#else
#define nilfs_msg(sb, level, fmt, ...) \
do { \
no_printk(fmt, ##__VA_ARGS__); \
(void)(sb); \
} while (0)
#define nilfs_error(sb, fmt, ...) \
do { \
no_printk(fmt, ##__VA_ARGS__); \
__nilfs_error(sb, "", " "); \
} while (0)
#endif /* CONFIG_PRINTK */
extern struct nilfs_super_block *
nilfs_read_super_block(struct super_block *, u64, int, struct buffer_head **);
extern int nilfs_store_magic_and_option(struct super_block *,
struct nilfs_super_block *, char *);
extern int nilfs_check_feature_compatibility(struct super_block *,
struct nilfs_super_block *);
extern void nilfs_set_log_cursor(struct nilfs_super_block *,
struct the_nilfs *);
struct nilfs_super_block **nilfs_prepare_super(struct super_block *sb,
int flip);
int nilfs_commit_super(struct super_block *sb, int flag);
int nilfs_cleanup_super(struct super_block *sb);
int nilfs_resize_fs(struct super_block *sb, __u64 newsize);
int nilfs_attach_checkpoint(struct super_block *sb, __u64 cno, int curr_mnt,
struct nilfs_root **root);
int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno);
/* gcinode.c */
int nilfs_gccache_submit_read_data(struct inode *, sector_t, sector_t, __u64,
struct buffer_head **);
int nilfs_gccache_submit_read_node(struct inode *, sector_t, __u64,
struct buffer_head **);
int nilfs_gccache_wait_and_mark_dirty(struct buffer_head *);
int nilfs_init_gcinode(struct inode *inode);
void nilfs_remove_all_gcinodes(struct the_nilfs *nilfs);
nilfs2: integrate sysfs support into driver This patch integrates creation of sysfs groups and attributes into NILFS file system driver. It was found the issue with nilfs_sysfs_{create/delete}_snapshot_group functions by Michael L Semon <mlsemon35@gmail.com> in the first version of the patch: BUG: sleeping function called from invalid context at kernel/locking/mutex.c:579 in_atomic(): 1, irqs_disabled(): 0, pid: 32676, name: umount.nilfs2 2 locks held by umount.nilfs2/32676: #0: (&type->s_umount_key#21){++++..}, at: [<790c18e2>] deactivate_super+0x37/0x58 #1: (&(&nilfs->ns_cptree_lock)->rlock){+.+...}, at: [<791bf659>] nilfs_put_root+0x23/0x5a Preemption disabled at:[<791bf659>] nilfs_put_root+0x23/0x5a CPU: 0 PID: 32676 Comm: umount.nilfs2 Not tainted 3.14.0+ #2 Hardware name: Dell Computer Corporation Dimension 2350/07W080, BIOS A01 12/17/2002 Call Trace: dump_stack+0x4b/0x75 __might_sleep+0x111/0x16f mutex_lock_nested+0x1e/0x3ad kernfs_remove+0x12/0x26 sysfs_remove_dir+0x3d/0x62 kobject_del+0x13/0x38 nilfs_sysfs_delete_snapshot_group+0xb/0xd nilfs_put_root+0x2a/0x5a nilfs_detach_log_writer+0x1ab/0x2c1 nilfs_put_super+0x13/0x68 generic_shutdown_super+0x60/0xd1 kill_block_super+0x1d/0x60 deactivate_locked_super+0x22/0x3f deactivate_super+0x3e/0x58 mntput_no_expire+0xe2/0x141 SyS_oldumount+0x70/0xa5 syscall_call+0x7/0xb The reason of the issue was placement of nilfs_sysfs_{create/delete}_snapshot_group() call under nilfs->ns_cptree_lock protection. But this protection is unnecessary and wrong solution. The second version of the patch fixes this issue. [fengguang.wu@intel.com: nilfs_sysfs_create_mounted_snapshots_group can be static] Reported-by: Michael L. Semon <mlsemon35@gmail.com> Signed-off-by: Vyacheslav Dubeyko <Vyacheslav.Dubeyko@hgst.com> Cc: Vyacheslav Dubeyko <slava@dubeyko.com> Cc: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Tested-by: Michael L. Semon <mlsemon35@gmail.com> Signed-off-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:20:55 +08:00
/* sysfs.c */
int __init nilfs_sysfs_init(void);
void nilfs_sysfs_exit(void);
int nilfs_sysfs_create_device_group(struct super_block *);
void nilfs_sysfs_delete_device_group(struct the_nilfs *);
int nilfs_sysfs_create_snapshot_group(struct nilfs_root *);
void nilfs_sysfs_delete_snapshot_group(struct nilfs_root *);
/*
* Inodes and files operations
*/
extern const struct file_operations nilfs_dir_operations;
extern const struct inode_operations nilfs_file_inode_operations;
extern const struct file_operations nilfs_file_operations;
extern const struct address_space_operations nilfs_aops;
extern const struct inode_operations nilfs_dir_inode_operations;
extern const struct inode_operations nilfs_special_inode_operations;
extern const struct inode_operations nilfs_symlink_inode_operations;
/*
* filesystem type
*/
extern struct file_system_type nilfs_fs_type;
#endif /* _NILFS_H */