linux/fs/ext2/ext2.h
Carlos Maiolino ff0031d848 ext2: fix filesystem deadlock while reading corrupted xattr block
This bug can be reproducible with fsfuzzer, although, I couldn't reproduce it
100% of my tries, it is quite easily reproducible.

During the deletion of an inode, ext2_xattr_delete_inode() does not check if the
block pointed by EXT2_I(inode)->i_file_acl is a valid data block, this might
lead to a deadlock, when i_file_acl == 1, and the filesystem block size is 1024.

In that situation, ext2_xattr_delete_inode, will load the superblock's buffer
head (instead of a valid i_file_acl block), and then lock that buffer head,
which, ext2_sync_super will also try to lock, making the filesystem deadlock in
the following stack trace:

root     17180  0.0  0.0 113660   660 pts/0    D+   07:08   0:00 rmdir
/media/test/dir1

[<ffffffff8125da9f>] __sync_dirty_buffer+0xaf/0x100
[<ffffffff8125db03>] sync_dirty_buffer+0x13/0x20
[<ffffffffa03f0d57>] ext2_sync_super+0xb7/0xc0 [ext2]
[<ffffffffa03f10b9>] ext2_error+0x119/0x130 [ext2]
[<ffffffffa03e9d93>] ext2_free_blocks+0x83/0x350 [ext2]
[<ffffffffa03f3d03>] ext2_xattr_delete_inode+0x173/0x190 [ext2]
[<ffffffffa03ee9e9>] ext2_evict_inode+0xc9/0x130 [ext2]
[<ffffffff8123fd23>] evict+0xb3/0x180
[<ffffffff81240008>] iput+0x1b8/0x240
[<ffffffff8123c4ac>] d_delete+0x11c/0x150
[<ffffffff8122fa7e>] vfs_rmdir+0xfe/0x120
[<ffffffff812340ee>] do_rmdir+0x17e/0x1f0
[<ffffffff81234dd6>] SyS_rmdir+0x16/0x20
[<ffffffff81838cf2>] entry_SYSCALL_64_fastpath+0x1a/0xa4
[<ffffffffffffffff>] 0xffffffffffffffff

Fix this by using the same approach ext4 uses to test data blocks validity,
implementing ext2_data_block_valid.

An another possibility when the superblock is very corrupted, is that i_file_acl
is 1, block_count is 1 and first_data_block is 0. For such situations, we might
have i_file_acl pointing to a 'valid' block, but still step over the superblock.
The approach I used was to also test if the superblock is not in the range
described by ext2_data_block_valid() arguments

Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2016-07-05 22:02:41 -04:00

838 lines
28 KiB
C

/*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card (card@masi.ibp.fr)
* Laboratoire MASI - Institut Blaise Pascal
* Universite Pierre et Marie Curie (Paris VI)
*
* from
*
* linux/include/linux/minix_fs.h
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/fs.h>
#include <linux/ext2_fs.h>
#include <linux/blockgroup_lock.h>
#include <linux/percpu_counter.h>
#include <linux/rbtree.h>
/* XXX Here for now... not interested in restructing headers JUST now */
/* data type for block offset of block group */
typedef int ext2_grpblk_t;
/* data type for filesystem-wide blocks number */
typedef unsigned long ext2_fsblk_t;
#define E2FSBLK "%lu"
struct ext2_reserve_window {
ext2_fsblk_t _rsv_start; /* First byte reserved */
ext2_fsblk_t _rsv_end; /* Last byte reserved or 0 */
};
struct ext2_reserve_window_node {
struct rb_node rsv_node;
__u32 rsv_goal_size;
__u32 rsv_alloc_hit;
struct ext2_reserve_window rsv_window;
};
struct ext2_block_alloc_info {
/* information about reservation window */
struct ext2_reserve_window_node rsv_window_node;
/*
* was i_next_alloc_block in ext2_inode_info
* is the logical (file-relative) number of the
* most-recently-allocated block in this file.
* We use this for detecting linearly ascending allocation requests.
*/
__u32 last_alloc_logical_block;
/*
* Was i_next_alloc_goal in ext2_inode_info
* is the *physical* companion to i_next_alloc_block.
* it the the physical block number of the block which was most-recentl
* allocated to this file. This give us the goal (target) for the next
* allocation when we detect linearly ascending requests.
*/
ext2_fsblk_t last_alloc_physical_block;
};
#define rsv_start rsv_window._rsv_start
#define rsv_end rsv_window._rsv_end
struct mb_cache;
/*
* second extended-fs super-block data in memory
*/
struct ext2_sb_info {
unsigned long s_frag_size; /* Size of a fragment in bytes */
unsigned long s_frags_per_block;/* Number of fragments per block */
unsigned long s_inodes_per_block;/* Number of inodes per block */
unsigned long s_frags_per_group;/* Number of fragments in a group */
unsigned long s_blocks_per_group;/* Number of blocks in a group */
unsigned long s_inodes_per_group;/* Number of inodes in a group */
unsigned long s_itb_per_group; /* Number of inode table blocks per group */
unsigned long s_gdb_count; /* Number of group descriptor blocks */
unsigned long s_desc_per_block; /* Number of group descriptors per block */
unsigned long s_groups_count; /* Number of groups in the fs */
unsigned long s_overhead_last; /* Last calculated overhead */
unsigned long s_blocks_last; /* Last seen block count */
struct buffer_head * s_sbh; /* Buffer containing the super block */
struct ext2_super_block * s_es; /* Pointer to the super block in the buffer */
struct buffer_head ** s_group_desc;
unsigned long s_mount_opt;
unsigned long s_sb_block;
kuid_t s_resuid;
kgid_t s_resgid;
unsigned short s_mount_state;
unsigned short s_pad;
int s_addr_per_block_bits;
int s_desc_per_block_bits;
int s_inode_size;
int s_first_ino;
spinlock_t s_next_gen_lock;
u32 s_next_generation;
unsigned long s_dir_count;
u8 *s_debts;
struct percpu_counter s_freeblocks_counter;
struct percpu_counter s_freeinodes_counter;
struct percpu_counter s_dirs_counter;
struct blockgroup_lock *s_blockgroup_lock;
/* root of the per fs reservation window tree */
spinlock_t s_rsv_window_lock;
struct rb_root s_rsv_window_root;
struct ext2_reserve_window_node s_rsv_window_head;
/*
* s_lock protects against concurrent modifications of s_mount_state,
* s_blocks_last, s_overhead_last and the content of superblock's
* buffer pointed to by sbi->s_es.
*
* Note: It is used in ext2_show_options() to provide a consistent view
* of the mount options.
*/
spinlock_t s_lock;
struct mb_cache *s_mb_cache;
};
static inline spinlock_t *
sb_bgl_lock(struct ext2_sb_info *sbi, unsigned int block_group)
{
return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group);
}
/*
* Define EXT2FS_DEBUG to produce debug messages
*/
#undef EXT2FS_DEBUG
/*
* Define EXT2_RESERVATION to reserve data blocks for expanding files
*/
#define EXT2_DEFAULT_RESERVE_BLOCKS 8
/*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */
#define EXT2_MAX_RESERVE_BLOCKS 1027
#define EXT2_RESERVE_WINDOW_NOT_ALLOCATED 0
/*
* The second extended file system version
*/
#define EXT2FS_DATE "95/08/09"
#define EXT2FS_VERSION "0.5b"
/*
* Debug code
*/
#ifdef EXT2FS_DEBUG
# define ext2_debug(f, a...) { \
printk ("EXT2-fs DEBUG (%s, %d): %s:", \
__FILE__, __LINE__, __func__); \
printk (f, ## a); \
}
#else
# define ext2_debug(f, a...) /**/
#endif
/*
* Special inode numbers
*/
#define EXT2_BAD_INO 1 /* Bad blocks inode */
#define EXT2_ROOT_INO 2 /* Root inode */
#define EXT2_BOOT_LOADER_INO 5 /* Boot loader inode */
#define EXT2_UNDEL_DIR_INO 6 /* Undelete directory inode */
/* First non-reserved inode for old ext2 filesystems */
#define EXT2_GOOD_OLD_FIRST_INO 11
static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb)
{
return sb->s_fs_info;
}
/*
* Macro-instructions used to manage several block sizes
*/
#define EXT2_MIN_BLOCK_SIZE 1024
#define EXT2_MAX_BLOCK_SIZE 4096
#define EXT2_MIN_BLOCK_LOG_SIZE 10
#define EXT2_BLOCK_SIZE(s) ((s)->s_blocksize)
#define EXT2_ADDR_PER_BLOCK(s) (EXT2_BLOCK_SIZE(s) / sizeof (__u32))
#define EXT2_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits)
#define EXT2_ADDR_PER_BLOCK_BITS(s) (EXT2_SB(s)->s_addr_per_block_bits)
#define EXT2_INODE_SIZE(s) (EXT2_SB(s)->s_inode_size)
#define EXT2_FIRST_INO(s) (EXT2_SB(s)->s_first_ino)
/*
* Macro-instructions used to manage fragments
*/
#define EXT2_MIN_FRAG_SIZE 1024
#define EXT2_MAX_FRAG_SIZE 4096
#define EXT2_MIN_FRAG_LOG_SIZE 10
#define EXT2_FRAG_SIZE(s) (EXT2_SB(s)->s_frag_size)
#define EXT2_FRAGS_PER_BLOCK(s) (EXT2_SB(s)->s_frags_per_block)
/*
* Structure of a blocks group descriptor
*/
struct ext2_group_desc
{
__le32 bg_block_bitmap; /* Blocks bitmap block */
__le32 bg_inode_bitmap; /* Inodes bitmap block */
__le32 bg_inode_table; /* Inodes table block */
__le16 bg_free_blocks_count; /* Free blocks count */
__le16 bg_free_inodes_count; /* Free inodes count */
__le16 bg_used_dirs_count; /* Directories count */
__le16 bg_pad;
__le32 bg_reserved[3];
};
/*
* Macro-instructions used to manage group descriptors
*/
#define EXT2_BLOCKS_PER_GROUP(s) (EXT2_SB(s)->s_blocks_per_group)
#define EXT2_DESC_PER_BLOCK(s) (EXT2_SB(s)->s_desc_per_block)
#define EXT2_INODES_PER_GROUP(s) (EXT2_SB(s)->s_inodes_per_group)
#define EXT2_DESC_PER_BLOCK_BITS(s) (EXT2_SB(s)->s_desc_per_block_bits)
/*
* Constants relative to the data blocks
*/
#define EXT2_NDIR_BLOCKS 12
#define EXT2_IND_BLOCK EXT2_NDIR_BLOCKS
#define EXT2_DIND_BLOCK (EXT2_IND_BLOCK + 1)
#define EXT2_TIND_BLOCK (EXT2_DIND_BLOCK + 1)
#define EXT2_N_BLOCKS (EXT2_TIND_BLOCK + 1)
/*
* Inode flags (GETFLAGS/SETFLAGS)
*/
#define EXT2_SECRM_FL FS_SECRM_FL /* Secure deletion */
#define EXT2_UNRM_FL FS_UNRM_FL /* Undelete */
#define EXT2_COMPR_FL FS_COMPR_FL /* Compress file */
#define EXT2_SYNC_FL FS_SYNC_FL /* Synchronous updates */
#define EXT2_IMMUTABLE_FL FS_IMMUTABLE_FL /* Immutable file */
#define EXT2_APPEND_FL FS_APPEND_FL /* writes to file may only append */
#define EXT2_NODUMP_FL FS_NODUMP_FL /* do not dump file */
#define EXT2_NOATIME_FL FS_NOATIME_FL /* do not update atime */
/* Reserved for compression usage... */
#define EXT2_DIRTY_FL FS_DIRTY_FL
#define EXT2_COMPRBLK_FL FS_COMPRBLK_FL /* One or more compressed clusters */
#define EXT2_NOCOMP_FL FS_NOCOMP_FL /* Don't compress */
#define EXT2_ECOMPR_FL FS_ECOMPR_FL /* Compression error */
/* End compression flags --- maybe not all used */
#define EXT2_BTREE_FL FS_BTREE_FL /* btree format dir */
#define EXT2_INDEX_FL FS_INDEX_FL /* hash-indexed directory */
#define EXT2_IMAGIC_FL FS_IMAGIC_FL /* AFS directory */
#define EXT2_JOURNAL_DATA_FL FS_JOURNAL_DATA_FL /* Reserved for ext3 */
#define EXT2_NOTAIL_FL FS_NOTAIL_FL /* file tail should not be merged */
#define EXT2_DIRSYNC_FL FS_DIRSYNC_FL /* dirsync behaviour (directories only) */
#define EXT2_TOPDIR_FL FS_TOPDIR_FL /* Top of directory hierarchies*/
#define EXT2_RESERVED_FL FS_RESERVED_FL /* reserved for ext2 lib */
#define EXT2_FL_USER_VISIBLE FS_FL_USER_VISIBLE /* User visible flags */
#define EXT2_FL_USER_MODIFIABLE FS_FL_USER_MODIFIABLE /* User modifiable flags */
/* Flags that should be inherited by new inodes from their parent. */
#define EXT2_FL_INHERITED (EXT2_SECRM_FL | EXT2_UNRM_FL | EXT2_COMPR_FL |\
EXT2_SYNC_FL | EXT2_NODUMP_FL |\
EXT2_NOATIME_FL | EXT2_COMPRBLK_FL |\
EXT2_NOCOMP_FL | EXT2_JOURNAL_DATA_FL |\
EXT2_NOTAIL_FL | EXT2_DIRSYNC_FL)
/* Flags that are appropriate for regular files (all but dir-specific ones). */
#define EXT2_REG_FLMASK (~(EXT2_DIRSYNC_FL | EXT2_TOPDIR_FL))
/* Flags that are appropriate for non-directories/regular files. */
#define EXT2_OTHER_FLMASK (EXT2_NODUMP_FL | EXT2_NOATIME_FL)
/* Mask out flags that are inappropriate for the given type of inode. */
static inline __u32 ext2_mask_flags(umode_t mode, __u32 flags)
{
if (S_ISDIR(mode))
return flags;
else if (S_ISREG(mode))
return flags & EXT2_REG_FLMASK;
else
return flags & EXT2_OTHER_FLMASK;
}
/*
* ioctl commands
*/
#define EXT2_IOC_GETFLAGS FS_IOC_GETFLAGS
#define EXT2_IOC_SETFLAGS FS_IOC_SETFLAGS
#define EXT2_IOC_GETVERSION FS_IOC_GETVERSION
#define EXT2_IOC_SETVERSION FS_IOC_SETVERSION
#define EXT2_IOC_GETRSVSZ _IOR('f', 5, long)
#define EXT2_IOC_SETRSVSZ _IOW('f', 6, long)
/*
* ioctl commands in 32 bit emulation
*/
#define EXT2_IOC32_GETFLAGS FS_IOC32_GETFLAGS
#define EXT2_IOC32_SETFLAGS FS_IOC32_SETFLAGS
#define EXT2_IOC32_GETVERSION FS_IOC32_GETVERSION
#define EXT2_IOC32_SETVERSION FS_IOC32_SETVERSION
/*
* Structure of an inode on the disk
*/
struct ext2_inode {
__le16 i_mode; /* File mode */
__le16 i_uid; /* Low 16 bits of Owner Uid */
__le32 i_size; /* Size in bytes */
__le32 i_atime; /* Access time */
__le32 i_ctime; /* Creation time */
__le32 i_mtime; /* Modification time */
__le32 i_dtime; /* Deletion Time */
__le16 i_gid; /* Low 16 bits of Group Id */
__le16 i_links_count; /* Links count */
__le32 i_blocks; /* Blocks count */
__le32 i_flags; /* File flags */
union {
struct {
__le32 l_i_reserved1;
} linux1;
struct {
__le32 h_i_translator;
} hurd1;
struct {
__le32 m_i_reserved1;
} masix1;
} osd1; /* OS dependent 1 */
__le32 i_block[EXT2_N_BLOCKS];/* Pointers to blocks */
__le32 i_generation; /* File version (for NFS) */
__le32 i_file_acl; /* File ACL */
__le32 i_dir_acl; /* Directory ACL */
__le32 i_faddr; /* Fragment address */
union {
struct {
__u8 l_i_frag; /* Fragment number */
__u8 l_i_fsize; /* Fragment size */
__u16 i_pad1;
__le16 l_i_uid_high; /* these 2 fields */
__le16 l_i_gid_high; /* were reserved2[0] */
__u32 l_i_reserved2;
} linux2;
struct {
__u8 h_i_frag; /* Fragment number */
__u8 h_i_fsize; /* Fragment size */
__le16 h_i_mode_high;
__le16 h_i_uid_high;
__le16 h_i_gid_high;
__le32 h_i_author;
} hurd2;
struct {
__u8 m_i_frag; /* Fragment number */
__u8 m_i_fsize; /* Fragment size */
__u16 m_pad1;
__u32 m_i_reserved2[2];
} masix2;
} osd2; /* OS dependent 2 */
};
#define i_size_high i_dir_acl
#define i_reserved1 osd1.linux1.l_i_reserved1
#define i_frag osd2.linux2.l_i_frag
#define i_fsize osd2.linux2.l_i_fsize
#define i_uid_low i_uid
#define i_gid_low i_gid
#define i_uid_high osd2.linux2.l_i_uid_high
#define i_gid_high osd2.linux2.l_i_gid_high
#define i_reserved2 osd2.linux2.l_i_reserved2
/*
* File system states
*/
#define EXT2_VALID_FS 0x0001 /* Unmounted cleanly */
#define EXT2_ERROR_FS 0x0002 /* Errors detected */
#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */
/*
* Mount flags
*/
#define EXT2_MOUNT_CHECK 0x000001 /* Do mount-time checks */
#define EXT2_MOUNT_OLDALLOC 0x000002 /* Don't use the new Orlov allocator */
#define EXT2_MOUNT_GRPID 0x000004 /* Create files with directory's group */
#define EXT2_MOUNT_DEBUG 0x000008 /* Some debugging messages */
#define EXT2_MOUNT_ERRORS_CONT 0x000010 /* Continue on errors */
#define EXT2_MOUNT_ERRORS_RO 0x000020 /* Remount fs ro on errors */
#define EXT2_MOUNT_ERRORS_PANIC 0x000040 /* Panic on errors */
#define EXT2_MOUNT_MINIX_DF 0x000080 /* Mimics the Minix statfs */
#define EXT2_MOUNT_NOBH 0x000100 /* No buffer_heads */
#define EXT2_MOUNT_NO_UID32 0x000200 /* Disable 32-bit UIDs */
#define EXT2_MOUNT_XATTR_USER 0x004000 /* Extended user attributes */
#define EXT2_MOUNT_POSIX_ACL 0x008000 /* POSIX Access Control Lists */
#define EXT2_MOUNT_XIP 0x010000 /* Obsolete, use DAX */
#define EXT2_MOUNT_USRQUOTA 0x020000 /* user quota */
#define EXT2_MOUNT_GRPQUOTA 0x040000 /* group quota */
#define EXT2_MOUNT_RESERVATION 0x080000 /* Preallocation */
#ifdef CONFIG_FS_DAX
#define EXT2_MOUNT_DAX 0x100000 /* Direct Access */
#else
#define EXT2_MOUNT_DAX 0
#endif
#define clear_opt(o, opt) o &= ~EXT2_MOUNT_##opt
#define set_opt(o, opt) o |= EXT2_MOUNT_##opt
#define test_opt(sb, opt) (EXT2_SB(sb)->s_mount_opt & \
EXT2_MOUNT_##opt)
/*
* Maximal mount counts between two filesystem checks
*/
#define EXT2_DFL_MAX_MNT_COUNT 20 /* Allow 20 mounts */
#define EXT2_DFL_CHECKINTERVAL 0 /* Don't use interval check */
/*
* Behaviour when detecting errors
*/
#define EXT2_ERRORS_CONTINUE 1 /* Continue execution */
#define EXT2_ERRORS_RO 2 /* Remount fs read-only */
#define EXT2_ERRORS_PANIC 3 /* Panic */
#define EXT2_ERRORS_DEFAULT EXT2_ERRORS_CONTINUE
/*
* Structure of the super block
*/
struct ext2_super_block {
__le32 s_inodes_count; /* Inodes count */
__le32 s_blocks_count; /* Blocks count */
__le32 s_r_blocks_count; /* Reserved blocks count */
__le32 s_free_blocks_count; /* Free blocks count */
__le32 s_free_inodes_count; /* Free inodes count */
__le32 s_first_data_block; /* First Data Block */
__le32 s_log_block_size; /* Block size */
__le32 s_log_frag_size; /* Fragment size */
__le32 s_blocks_per_group; /* # Blocks per group */
__le32 s_frags_per_group; /* # Fragments per group */
__le32 s_inodes_per_group; /* # Inodes per group */
__le32 s_mtime; /* Mount time */
__le32 s_wtime; /* Write time */
__le16 s_mnt_count; /* Mount count */
__le16 s_max_mnt_count; /* Maximal mount count */
__le16 s_magic; /* Magic signature */
__le16 s_state; /* File system state */
__le16 s_errors; /* Behaviour when detecting errors */
__le16 s_minor_rev_level; /* minor revision level */
__le32 s_lastcheck; /* time of last check */
__le32 s_checkinterval; /* max. time between checks */
__le32 s_creator_os; /* OS */
__le32 s_rev_level; /* Revision level */
__le16 s_def_resuid; /* Default uid for reserved blocks */
__le16 s_def_resgid; /* Default gid for reserved blocks */
/*
* These fields are for EXT2_DYNAMIC_REV superblocks only.
*
* Note: the difference between the compatible feature set and
* the incompatible feature set is that if there is a bit set
* in the incompatible feature set that the kernel doesn't
* know about, it should refuse to mount the filesystem.
*
* e2fsck's requirements are more strict; if it doesn't know
* about a feature in either the compatible or incompatible
* feature set, it must abort and not try to meddle with
* things it doesn't understand...
*/
__le32 s_first_ino; /* First non-reserved inode */
__le16 s_inode_size; /* size of inode structure */
__le16 s_block_group_nr; /* block group # of this superblock */
__le32 s_feature_compat; /* compatible feature set */
__le32 s_feature_incompat; /* incompatible feature set */
__le32 s_feature_ro_compat; /* readonly-compatible feature set */
__u8 s_uuid[16]; /* 128-bit uuid for volume */
char s_volume_name[16]; /* volume name */
char s_last_mounted[64]; /* directory where last mounted */
__le32 s_algorithm_usage_bitmap; /* For compression */
/*
* Performance hints. Directory preallocation should only
* happen if the EXT2_COMPAT_PREALLOC flag is on.
*/
__u8 s_prealloc_blocks; /* Nr of blocks to try to preallocate*/
__u8 s_prealloc_dir_blocks; /* Nr to preallocate for dirs */
__u16 s_padding1;
/*
* Journaling support valid if EXT3_FEATURE_COMPAT_HAS_JOURNAL set.
*/
__u8 s_journal_uuid[16]; /* uuid of journal superblock */
__u32 s_journal_inum; /* inode number of journal file */
__u32 s_journal_dev; /* device number of journal file */
__u32 s_last_orphan; /* start of list of inodes to delete */
__u32 s_hash_seed[4]; /* HTREE hash seed */
__u8 s_def_hash_version; /* Default hash version to use */
__u8 s_reserved_char_pad;
__u16 s_reserved_word_pad;
__le32 s_default_mount_opts;
__le32 s_first_meta_bg; /* First metablock block group */
__u32 s_reserved[190]; /* Padding to the end of the block */
};
/*
* Codes for operating systems
*/
#define EXT2_OS_LINUX 0
#define EXT2_OS_HURD 1
#define EXT2_OS_MASIX 2
#define EXT2_OS_FREEBSD 3
#define EXT2_OS_LITES 4
/*
* Revision levels
*/
#define EXT2_GOOD_OLD_REV 0 /* The good old (original) format */
#define EXT2_DYNAMIC_REV 1 /* V2 format w/ dynamic inode sizes */
#define EXT2_CURRENT_REV EXT2_GOOD_OLD_REV
#define EXT2_MAX_SUPP_REV EXT2_DYNAMIC_REV
#define EXT2_GOOD_OLD_INODE_SIZE 128
/*
* Feature set definitions
*/
#define EXT2_HAS_COMPAT_FEATURE(sb,mask) \
( EXT2_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask) )
#define EXT2_HAS_RO_COMPAT_FEATURE(sb,mask) \
( EXT2_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask) )
#define EXT2_HAS_INCOMPAT_FEATURE(sb,mask) \
( EXT2_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask) )
#define EXT2_SET_COMPAT_FEATURE(sb,mask) \
EXT2_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask)
#define EXT2_SET_RO_COMPAT_FEATURE(sb,mask) \
EXT2_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask)
#define EXT2_SET_INCOMPAT_FEATURE(sb,mask) \
EXT2_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask)
#define EXT2_CLEAR_COMPAT_FEATURE(sb,mask) \
EXT2_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask)
#define EXT2_CLEAR_RO_COMPAT_FEATURE(sb,mask) \
EXT2_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask)
#define EXT2_CLEAR_INCOMPAT_FEATURE(sb,mask) \
EXT2_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask)
#define EXT2_FEATURE_COMPAT_DIR_PREALLOC 0x0001
#define EXT2_FEATURE_COMPAT_IMAGIC_INODES 0x0002
#define EXT3_FEATURE_COMPAT_HAS_JOURNAL 0x0004
#define EXT2_FEATURE_COMPAT_EXT_ATTR 0x0008
#define EXT2_FEATURE_COMPAT_RESIZE_INO 0x0010
#define EXT2_FEATURE_COMPAT_DIR_INDEX 0x0020
#define EXT2_FEATURE_COMPAT_ANY 0xffffffff
#define EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001
#define EXT2_FEATURE_RO_COMPAT_LARGE_FILE 0x0002
#define EXT2_FEATURE_RO_COMPAT_BTREE_DIR 0x0004
#define EXT2_FEATURE_RO_COMPAT_ANY 0xffffffff
#define EXT2_FEATURE_INCOMPAT_COMPRESSION 0x0001
#define EXT2_FEATURE_INCOMPAT_FILETYPE 0x0002
#define EXT3_FEATURE_INCOMPAT_RECOVER 0x0004
#define EXT3_FEATURE_INCOMPAT_JOURNAL_DEV 0x0008
#define EXT2_FEATURE_INCOMPAT_META_BG 0x0010
#define EXT2_FEATURE_INCOMPAT_ANY 0xffffffff
#define EXT2_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR
#define EXT2_FEATURE_INCOMPAT_SUPP (EXT2_FEATURE_INCOMPAT_FILETYPE| \
EXT2_FEATURE_INCOMPAT_META_BG)
#define EXT2_FEATURE_RO_COMPAT_SUPP (EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER| \
EXT2_FEATURE_RO_COMPAT_LARGE_FILE| \
EXT2_FEATURE_RO_COMPAT_BTREE_DIR)
#define EXT2_FEATURE_RO_COMPAT_UNSUPPORTED ~EXT2_FEATURE_RO_COMPAT_SUPP
#define EXT2_FEATURE_INCOMPAT_UNSUPPORTED ~EXT2_FEATURE_INCOMPAT_SUPP
/*
* Default values for user and/or group using reserved blocks
*/
#define EXT2_DEF_RESUID 0
#define EXT2_DEF_RESGID 0
/*
* Default mount options
*/
#define EXT2_DEFM_DEBUG 0x0001
#define EXT2_DEFM_BSDGROUPS 0x0002
#define EXT2_DEFM_XATTR_USER 0x0004
#define EXT2_DEFM_ACL 0x0008
#define EXT2_DEFM_UID16 0x0010
/* Not used by ext2, but reserved for use by ext3 */
#define EXT3_DEFM_JMODE 0x0060
#define EXT3_DEFM_JMODE_DATA 0x0020
#define EXT3_DEFM_JMODE_ORDERED 0x0040
#define EXT3_DEFM_JMODE_WBACK 0x0060
/*
* Structure of a directory entry
*/
struct ext2_dir_entry {
__le32 inode; /* Inode number */
__le16 rec_len; /* Directory entry length */
__le16 name_len; /* Name length */
char name[]; /* File name, up to EXT2_NAME_LEN */
};
/*
* The new version of the directory entry. Since EXT2 structures are
* stored in intel byte order, and the name_len field could never be
* bigger than 255 chars, it's safe to reclaim the extra byte for the
* file_type field.
*/
struct ext2_dir_entry_2 {
__le32 inode; /* Inode number */
__le16 rec_len; /* Directory entry length */
__u8 name_len; /* Name length */
__u8 file_type;
char name[]; /* File name, up to EXT2_NAME_LEN */
};
/*
* Ext2 directory file types. Only the low 3 bits are used. The
* other bits are reserved for now.
*/
enum {
EXT2_FT_UNKNOWN = 0,
EXT2_FT_REG_FILE = 1,
EXT2_FT_DIR = 2,
EXT2_FT_CHRDEV = 3,
EXT2_FT_BLKDEV = 4,
EXT2_FT_FIFO = 5,
EXT2_FT_SOCK = 6,
EXT2_FT_SYMLINK = 7,
EXT2_FT_MAX
};
/*
* EXT2_DIR_PAD defines the directory entries boundaries
*
* NOTE: It must be a multiple of 4
*/
#define EXT2_DIR_PAD 4
#define EXT2_DIR_ROUND (EXT2_DIR_PAD - 1)
#define EXT2_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT2_DIR_ROUND) & \
~EXT2_DIR_ROUND)
#define EXT2_MAX_REC_LEN ((1<<16)-1)
static inline void verify_offsets(void)
{
#define A(x,y) BUILD_BUG_ON(x != offsetof(struct ext2_super_block, y));
A(EXT2_SB_MAGIC_OFFSET, s_magic);
A(EXT2_SB_BLOCKS_OFFSET, s_blocks_count);
A(EXT2_SB_BSIZE_OFFSET, s_log_block_size);
#undef A
}
/*
* ext2 mount options
*/
struct ext2_mount_options {
unsigned long s_mount_opt;
kuid_t s_resuid;
kgid_t s_resgid;
};
/*
* second extended file system inode data in memory
*/
struct ext2_inode_info {
__le32 i_data[15];
__u32 i_flags;
__u32 i_faddr;
__u8 i_frag_no;
__u8 i_frag_size;
__u16 i_state;
__u32 i_file_acl;
__u32 i_dir_acl;
__u32 i_dtime;
/*
* i_block_group is the number of the block group which contains
* this file's inode. Constant across the lifetime of the inode,
* it is used for making block allocation decisions - we try to
* place a file's data blocks near its inode block, and new inodes
* near to their parent directory's inode.
*/
__u32 i_block_group;
/* block reservation info */
struct ext2_block_alloc_info *i_block_alloc_info;
__u32 i_dir_start_lookup;
#ifdef CONFIG_EXT2_FS_XATTR
/*
* Extended attributes can be read independently of the main file
* data. Taking i_mutex 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
rwlock_t i_meta_lock;
#ifdef CONFIG_FS_DAX
struct rw_semaphore dax_sem;
#endif
/*
* truncate_mutex is for serialising ext2_truncate() against
* ext2_getblock(). It also protects the internals of the inode's
* reservation data structures: ext2_reserve_window and
* ext2_reserve_window_node.
*/
struct mutex truncate_mutex;
struct inode vfs_inode;
struct list_head i_orphan; /* unlinked but open inodes */
#ifdef CONFIG_QUOTA
struct dquot *i_dquot[MAXQUOTAS];
#endif
};
#ifdef CONFIG_FS_DAX
#define dax_sem_down_write(ext2_inode) down_write(&(ext2_inode)->dax_sem)
#define dax_sem_up_write(ext2_inode) up_write(&(ext2_inode)->dax_sem)
#else
#define dax_sem_down_write(ext2_inode)
#define dax_sem_up_write(ext2_inode)
#endif
/*
* Inode dynamic state flags
*/
#define EXT2_STATE_NEW 0x00000001 /* inode is newly created */
/*
* Function prototypes
*/
/*
* Ok, these declarations are also in <linux/kernel.h> but none of the
* ext2 source programs needs to include it so they are duplicated here.
*/
static inline struct ext2_inode_info *EXT2_I(struct inode *inode)
{
return container_of(inode, struct ext2_inode_info, vfs_inode);
}
/* balloc.c */
extern int ext2_bg_has_super(struct super_block *sb, int group);
extern unsigned long ext2_bg_num_gdb(struct super_block *sb, int group);
extern ext2_fsblk_t ext2_new_block(struct inode *, unsigned long, int *);
extern ext2_fsblk_t ext2_new_blocks(struct inode *, unsigned long,
unsigned long *, int *);
extern int ext2_data_block_valid(struct ext2_sb_info *sbi, ext2_fsblk_t start_blk,
unsigned int count);
extern void ext2_free_blocks (struct inode *, unsigned long,
unsigned long);
extern unsigned long ext2_count_free_blocks (struct super_block *);
extern unsigned long ext2_count_dirs (struct super_block *);
extern void ext2_check_blocks_bitmap (struct super_block *);
extern struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb,
unsigned int block_group,
struct buffer_head ** bh);
extern void ext2_discard_reservation (struct inode *);
extern int ext2_should_retry_alloc(struct super_block *sb, int *retries);
extern void ext2_init_block_alloc_info(struct inode *);
extern void ext2_rsv_window_add(struct super_block *sb, struct ext2_reserve_window_node *rsv);
/* dir.c */
extern int ext2_add_link (struct dentry *, struct inode *);
extern ino_t ext2_inode_by_name(struct inode *, struct qstr *);
extern int ext2_make_empty(struct inode *, struct inode *);
extern struct ext2_dir_entry_2 * ext2_find_entry (struct inode *,struct qstr *, struct page **);
extern int ext2_delete_entry (struct ext2_dir_entry_2 *, struct page *);
extern int ext2_empty_dir (struct inode *);
extern struct ext2_dir_entry_2 * ext2_dotdot (struct inode *, struct page **);
extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, struct inode *, int);
/* ialloc.c */
extern struct inode * ext2_new_inode (struct inode *, umode_t, const struct qstr *);
extern void ext2_free_inode (struct inode *);
extern unsigned long ext2_count_free_inodes (struct super_block *);
extern void ext2_check_inodes_bitmap (struct super_block *);
extern unsigned long ext2_count_free (struct buffer_head *, unsigned);
/* inode.c */
extern struct inode *ext2_iget (struct super_block *, unsigned long);
extern int ext2_write_inode (struct inode *, struct writeback_control *);
extern void ext2_evict_inode(struct inode *);
extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int);
extern int ext2_setattr (struct dentry *, struct iattr *);
extern void ext2_set_inode_flags(struct inode *inode);
extern void ext2_get_inode_flags(struct ext2_inode_info *);
extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len);
/* ioctl.c */
extern long ext2_ioctl(struct file *, unsigned int, unsigned long);
extern long ext2_compat_ioctl(struct file *, unsigned int, unsigned long);
/* namei.c */
struct dentry *ext2_get_parent(struct dentry *child);
/* super.c */
extern __printf(3, 4)
void ext2_error(struct super_block *, const char *, const char *, ...);
extern __printf(3, 4)
void ext2_msg(struct super_block *, const char *, const char *, ...);
extern void ext2_update_dynamic_rev (struct super_block *sb);
extern void ext2_write_super (struct super_block *);
/*
* Inodes and files operations
*/
/* dir.c */
extern const struct file_operations ext2_dir_operations;
/* file.c */
extern int ext2_fsync(struct file *file, loff_t start, loff_t end,
int datasync);
extern const struct inode_operations ext2_file_inode_operations;
extern const struct file_operations ext2_file_operations;
/* inode.c */
extern const struct address_space_operations ext2_aops;
extern const struct address_space_operations ext2_nobh_aops;
/* namei.c */
extern const struct inode_operations ext2_dir_inode_operations;
extern const struct inode_operations ext2_special_inode_operations;
/* symlink.c */
extern const struct inode_operations ext2_fast_symlink_inode_operations;
extern const struct inode_operations ext2_symlink_inode_operations;
static inline ext2_fsblk_t
ext2_group_first_block_no(struct super_block *sb, unsigned long group_no)
{
return group_no * (ext2_fsblk_t)EXT2_BLOCKS_PER_GROUP(sb) +
le32_to_cpu(EXT2_SB(sb)->s_es->s_first_data_block);
}
#define ext2_set_bit __test_and_set_bit_le
#define ext2_clear_bit __test_and_clear_bit_le
#define ext2_test_bit test_bit_le
#define ext2_find_first_zero_bit find_first_zero_bit_le
#define ext2_find_next_zero_bit find_next_zero_bit_le