diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-03-31 13:42:57 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-03-31 13:42:57 -0700 |
commit | 8bb1f229527dee95644e0f8496980bb767c6f620 (patch) | |
tree | 511551e9772f11f855bd5b759b6d449da47e8820 /fs | |
parent | f22e08a79f3765fecf060b225a46931c94fb0a92 (diff) | |
parent | c0d0259481cc6ec2a38cad810055e455de35c733 (diff) | |
download | linux-8bb1f229527dee95644e0f8496980bb767c6f620.tar.gz linux-8bb1f229527dee95644e0f8496980bb767c6f620.tar.bz2 linux-8bb1f229527dee95644e0f8496980bb767c6f620.zip |
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull second try at vfs part d#2 from Al Viro:
"Miklos' first series (with do_lookup() rewrite split into edible
chunks) + assorted bits and pieces.
The 'untangling of do_lookup()' series is is a splitup of what used to
be a monolithic patch from Miklos, so this series is basically "how do
I convince myself that his patch is correct (or find a hole in it)".
No holes found and I like the resulting cleanup, so in it went..."
Changes from try 1: Fix a boot problem with selinux, and commit messages
prettied up a bit.
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (24 commits)
vfs: fix out-of-date dentry_unhash() comment
vfs: split __lookup_hash
untangling do_lookup() - take __lookup_hash()-calling case out of line.
untangling do_lookup() - switch to calling __lookup_hash()
untangling do_lookup() - merge d_alloc_and_lookup() callers
untangling do_lookup() - merge failure exits in !dentry case
untangling do_lookup() - massage !dentry case towards __lookup_hash()
untangling do_lookup() - get rid of need_reval in !dentry case
untangling do_lookup() - eliminate a loop.
untangling do_lookup() - expand the area under ->i_mutex
untangling do_lookup() - isolate !dentry stuff from the rest of it.
vfs: move MAY_EXEC check from __lookup_hash()
vfs: don't revalidate just looked up dentry
vfs: fix d_need_lookup/d_revalidate order in do_lookup
ext3: move headers to fs/ext3/
migrate ext2_fs.h guts to fs/ext2/ext2.h
new helper: ext2_image_size()
get rid of pointless includes of ext2_fs.h
ext2: No longer export ext2_fs.h to user space
mtdchar: kill persistently held vfsmount
...
Diffstat (limited to 'fs')
-rw-r--r-- | fs/aio.c | 32 | ||||
-rw-r--r-- | fs/ext2/ext2.h | 631 | ||||
-rw-r--r-- | fs/ext2/xattr_security.c | 5 | ||||
-rw-r--r-- | fs/ext2/xattr_trusted.c | 5 | ||||
-rw-r--r-- | fs/ext2/xip.c | 2 | ||||
-rw-r--r-- | fs/ext3/acl.c | 8 | ||||
-rw-r--r-- | fs/ext3/balloc.c | 10 | ||||
-rw-r--r-- | fs/ext3/bitmap.c | 4 | ||||
-rw-r--r-- | fs/ext3/dir.c | 7 | ||||
-rw-r--r-- | fs/ext3/ext3.h | 1322 | ||||
-rw-r--r-- | fs/ext3/ext3_jbd.c | 2 | ||||
-rw-r--r-- | fs/ext3/file.c | 6 | ||||
-rw-r--r-- | fs/ext3/fsync.c | 8 | ||||
-rw-r--r-- | fs/ext3/hash.c | 4 | ||||
-rw-r--r-- | fs/ext3/ialloc.c | 13 | ||||
-rw-r--r-- | fs/ext3/inode.c | 12 | ||||
-rw-r--r-- | fs/ext3/ioctl.c | 7 | ||||
-rw-r--r-- | fs/ext3/namei.c | 14 | ||||
-rw-r--r-- | fs/ext3/resize.c | 5 | ||||
-rw-r--r-- | fs/ext3/super.c | 18 | ||||
-rw-r--r-- | fs/ext3/symlink.c | 4 | ||||
-rw-r--r-- | fs/ext3/xattr.c | 7 | ||||
-rw-r--r-- | fs/ext3/xattr_security.c | 6 | ||||
-rw-r--r-- | fs/ext3/xattr_trusted.c | 6 | ||||
-rw-r--r-- | fs/ext3/xattr_user.c | 5 | ||||
-rw-r--r-- | fs/gfs2/file.c | 1 | ||||
-rw-r--r-- | fs/namei.c | 195 | ||||
-rw-r--r-- | fs/ocfs2/ioctl.c | 2 | ||||
-rw-r--r-- | fs/pstore/inode.c | 26 |
29 files changed, 2074 insertions, 293 deletions
@@ -305,15 +305,18 @@ out_freectx: return ERR_PTR(err); } -/* aio_cancel_all +/* kill_ctx * Cancels all outstanding aio requests on an aio context. Used * when the processes owning a context have all exited to encourage * the rapid destruction of the kioctx. */ -static void aio_cancel_all(struct kioctx *ctx) +static void kill_ctx(struct kioctx *ctx) { int (*cancel)(struct kiocb *, struct io_event *); + struct task_struct *tsk = current; + DECLARE_WAITQUEUE(wait, tsk); struct io_event res; + spin_lock_irq(&ctx->ctx_lock); ctx->dead = 1; while (!list_empty(&ctx->active_reqs)) { @@ -329,15 +332,7 @@ static void aio_cancel_all(struct kioctx *ctx) spin_lock_irq(&ctx->ctx_lock); } } - spin_unlock_irq(&ctx->ctx_lock); -} - -static void wait_for_all_aios(struct kioctx *ctx) -{ - struct task_struct *tsk = current; - DECLARE_WAITQUEUE(wait, tsk); - spin_lock_irq(&ctx->ctx_lock); if (!ctx->reqs_active) goto out; @@ -387,9 +382,7 @@ void exit_aio(struct mm_struct *mm) ctx = hlist_entry(mm->ioctx_list.first, struct kioctx, list); hlist_del_rcu(&ctx->list); - aio_cancel_all(ctx); - - wait_for_all_aios(ctx); + kill_ctx(ctx); if (1 != atomic_read(&ctx->users)) printk(KERN_DEBUG @@ -1269,8 +1262,7 @@ static void io_destroy(struct kioctx *ioctx) if (likely(!was_dead)) put_ioctx(ioctx); /* twice for the list */ - aio_cancel_all(ioctx); - wait_for_all_aios(ioctx); + kill_ctx(ioctx); /* * Wake up any waiters. The setting of ctx->dead must be seen @@ -1278,7 +1270,6 @@ static void io_destroy(struct kioctx *ioctx) * locking done by the above calls to ensure this consistency. */ wake_up_all(&ioctx->wait); - put_ioctx(ioctx); /* once for the lookup */ } /* sys_io_setup: @@ -1315,11 +1306,9 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp) ret = PTR_ERR(ioctx); if (!IS_ERR(ioctx)) { ret = put_user(ioctx->user_id, ctxp); - if (!ret) { - put_ioctx(ioctx); - return 0; - } - io_destroy(ioctx); + if (ret) + io_destroy(ioctx); + put_ioctx(ioctx); } out: @@ -1337,6 +1326,7 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) struct kioctx *ioctx = lookup_ioctx(ctx); if (likely(NULL != ioctx)) { io_destroy(ioctx); + put_ioctx(ioctx); return 0; } pr_debug("EINVAL: io_destroy: invalid context id\n"); diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 75ad433c6691..0b2b4db5bdcd 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -1,5 +1,636 @@ +/* + * 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 + +/* + * 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; + uid_t s_resuid; + gid_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; +}; + +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 */ + +/* + * 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 /* Execute in place */ +#define EXT2_MOUNT_USRQUOTA 0x020000 /* user quota */ +#define EXT2_MOUNT_GRPQUOTA 0x040000 /* group quota */ +#define EXT2_MOUNT_RESERVATION 0x080000 /* Preallocation */ + + +#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 diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c index be7a8d02c9a7..cfedb2cb0d8c 100644 --- a/fs/ext2/xattr_security.c +++ b/fs/ext2/xattr_security.c @@ -3,10 +3,7 @@ * Handler for storing security labels as extended attributes. */ -#include <linux/slab.h> -#include <linux/string.h> -#include <linux/fs.h> -#include <linux/ext2_fs.h> +#include "ext2.h" #include <linux/security.h> #include "xattr.h" diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c index 2989467d3595..7e192574c001 100644 --- a/fs/ext2/xattr_trusted.c +++ b/fs/ext2/xattr_trusted.c @@ -5,10 +5,7 @@ * Copyright (C) 2003 by Andreas Gruenbacher, <a.gruenbacher@computer.org> */ -#include <linux/string.h> -#include <linux/capability.h> -#include <linux/fs.h> -#include <linux/ext2_fs.h> +#include "ext2.h" #include "xattr.h" static size_t diff --git a/fs/ext2/xip.c b/fs/ext2/xip.c index 322a56b2dfb1..1c3312858fcf 100644 --- a/fs/ext2/xip.c +++ b/fs/ext2/xip.c @@ -9,8 +9,6 @@ #include <linux/fs.h> #include <linux/genhd.h> #include <linux/buffer_head.h> -#include <linux/ext2_fs_sb.h> -#include <linux/ext2_fs.h> #include <linux/blkdev.h> #include "ext2.h" #include "xip.h" diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c index 3091f62e55b6..c76832c8d192 100644 --- a/fs/ext3/acl.c +++ b/fs/ext3/acl.c @@ -4,13 +4,7 @@ * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> */ -#include <linux/init.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/capability.h> -#include <linux/fs.h> -#include <linux/ext3_jbd.h> -#include <linux/ext3_fs.h> +#include "ext3.h" #include "xattr.h" #include "acl.h" diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index 1e036b79384c..baac1b129fba 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -11,17 +11,9 @@ * David S. Miller (davem@caip.rutgers.edu), 1995 */ -#include <linux/time.h> -#include <linux/capability.h> -#include <linux/fs.h> -#include <linux/slab.h> -#include <linux/jbd.h> -#include <linux/ext3_fs.h> -#include <linux/ext3_jbd.h> #include <linux/quotaops.h> -#include <linux/buffer_head.h> #include <linux/blkdev.h> -#include <trace/events/ext3.h> +#include "ext3.h" /* * balloc.c contains the blocks allocation and deallocation routines diff --git a/fs/ext3/bitmap.c b/fs/ext3/bitmap.c index 6afc39d80253..909d13e26560 100644 --- a/fs/ext3/bitmap.c +++ b/fs/ext3/bitmap.c @@ -7,9 +7,7 @@ * Universite Pierre et Marie Curie (Paris VI) */ -#include <linux/buffer_head.h> -#include <linux/jbd.h> -#include <linux/ext3_fs.h> +#include "ext3.h" #ifdef EXT3FS_DEBUG diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c index 34f0a072b935..cc761ad8fa57 100644 --- a/fs/ext3/dir.c +++ b/fs/ext3/dir.c @@ -21,12 +21,7 @@ * */ -#include <linux/fs.h> -#include <linux/jbd.h> -#include <linux/ext3_fs.h> -#include <linux/buffer_head.h> -#include <linux/slab.h> -#include <linux/rbtree.h> +#include "ext3.h" static unsigned char ext3_filetype_table[] = { DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK diff --git a/fs/ext3/ext3.h b/fs/ext3/ext3.h new file mode 100644 index 000000000000..b6515fd7e56c --- /dev/null +++ b/fs/ext3/ext3.h @@ -0,0 +1,1322 @@ +/* + * Written by Stephen C. Tweedie <sct@redhat.com>, 1999 + * + * Copyright 1998--1999 Red Hat corp --- All Rights Reserved + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + * + * 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/jbd.h> +#include <linux/magic.h> +#include <linux/bug.h> +#include <linux/blockgroup_lock.h> + +/* + * The second extended filesystem constants/structures + */ + +/* + * Define EXT3FS_DEBUG to produce debug messages + */ +#undef EXT3FS_DEBUG + +/* + * Define EXT3_RESERVATION to reserve data blocks for expanding files + */ +#define EXT3_DEFAULT_RESERVE_BLOCKS 8 +/*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */ +#define EXT3_MAX_RESERVE_BLOCKS 1027 +#define EXT3_RESERVE_WINDOW_NOT_ALLOCATED 0 + +/* + * Debug code + */ +#ifdef EXT3FS_DEBUG +#define ext3_debug(f, a...) \ + do { \ + printk (KERN_DEBUG "EXT3-fs DEBUG (%s, %d): %s:", \ + __FILE__, __LINE__, __func__); \ + printk (KERN_DEBUG f, ## a); \ + } while (0) +#else +#define ext3_debug(f, a...) do {} while (0) +#endif + +/* + * Special inodes numbers + */ +#define EXT3_BAD_INO 1 /* Bad blocks inode */ +#define EXT3_ROOT_INO 2 /* Root inode */ +#define EXT3_BOOT_LOADER_INO 5 /* Boot loader inode */ +#define EXT3_UNDEL_DIR_INO 6 /* Undelete directory inode */ +#define EXT3_RESIZE_INO 7 /* Reserved group descriptors inode */ +#define EXT3_JOURNAL_INO 8 /* Journal inode */ + +/* First non-reserved inode for old ext3 filesystems */ +#define EXT3_GOOD_OLD_FIRST_INO 11 + +/* + * Maximal count of links to a file + */ +#define EXT3_LINK_MAX 32000 + +/* + * Macro-instructions used to manage several block sizes + */ +#define EXT3_MIN_BLOCK_SIZE 1024 +#define EXT3_MAX_BLOCK_SIZE 65536 +#define EXT3_MIN_BLOCK_LOG_SIZE 10 +#define EXT3_BLOCK_SIZE(s) ((s)->s_blocksize) +#define EXT3_ADDR_PER_BLOCK(s) (EXT3_BLOCK_SIZE(s) / sizeof (__u32)) +#define EXT3_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits) +#define EXT3_ADDR_PER_BLOCK_BITS(s) (EXT3_SB(s)->s_addr_per_block_bits) +#define EXT3_INODE_SIZE(s) (EXT3_SB(s)->s_inode_size) +#define EXT3_FIRST_INO(s) (EXT3_SB(s)->s_first_ino) + +/* + * Macro-instructions used to manage fragments + */ +#define EXT3_MIN_FRAG_SIZE 1024 +#define EXT3_MAX_FRAG_SIZE 4096 +#define EXT3_MIN_FRAG_LOG_SIZE 10 +#define EXT3_FRAG_SIZE(s) (EXT3_SB(s)->s_frag_size) +#define EXT3_FRAGS_PER_BLOCK(s) (EXT3_SB(s)->s_frags_per_block) + +/* + * Structure of a blocks group descriptor + */ +struct ext3_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 */ + __u16 bg_pad; + __le32 bg_reserved[3]; +}; + +/* + * Macro-instructions used to manage group descriptors + */ +#define EXT3_BLOCKS_PER_GROUP(s) (EXT3_SB(s)->s_blocks_per_group) +#define EXT3_DESC_PER_BLOCK(s) (EXT3_SB(s)->s_desc_per_block) +#define EXT3_INODES_PER_GROUP(s) (EXT3_SB(s)->s_inodes_per_group) +#define EXT3_DESC_PER_BLOCK_BITS(s) (EXT3_SB(s)->s_desc_per_block_bits) + +/* + * Constants relative to the data blocks + */ +#define EXT3_NDIR_BLOCKS 12 +#define EXT3_IND_BLOCK EXT3_NDIR_BLOCKS +#define EXT3_DIND_BLOCK (EXT3_IND_BLOCK + 1) +#define EXT3_TIND_BLOCK (EXT3_DIND_BLOCK + 1) +#define EXT3_N_BLOCKS (EXT3_TIND_BLOCK + 1) + +/* + * Inode flags + */ +#define EXT3_SECRM_FL 0x00000001 /* Secure deletion */ +#define EXT3_UNRM_FL 0x00000002 /* Undelete */ +#define EXT3_COMPR_FL 0x00000004 /* Compress file */ +#define EXT3_SYNC_FL 0x00000008 /* Synchronous updates */ +#define EXT3_IMMUTABLE_FL 0x00000010 /* Immutable file */ +#define EXT3_APPEND_FL 0x00000020 /* writes to file may only append */ +#define EXT3_NODUMP_FL 0x00000040 /* do not dump file */ +#define EXT3_NOATIME_FL 0x00000080 /* do not update atime */ +/* Reserved for compression usage... */ +#define EXT3_DIRTY_FL 0x00000100 +#define EXT3_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ +#define EXT3_NOCOMPR_FL 0x00000400 /* Don't compress */ +#define EXT3_ECOMPR_FL 0x00000800 /* Compression error */ +/* End compression flags --- maybe not all used */ +#define EXT3_INDEX_FL 0x00001000 /* hash-indexed directory */ +#define EXT3_IMAGIC_FL 0x00002000 /* AFS directory */ +#define EXT3_JOURNAL_DATA_FL 0x00004000 /* file data should be journaled */ +#define EXT3_NOTAIL_FL 0x00008000 /* file tail should not be merged */ +#define EXT3_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ +#define EXT3_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ +#define EXT3_RESERVED_FL 0x80000000 /* reserved for ext3 lib */ + +#define EXT3_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ +#define EXT3_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ + +/* Flags that should be inherited by new inodes from their parent. */ +#define EXT3_FL_INHERITED (EXT3_SECRM_FL | EXT3_UNRM_FL | EXT3_COMPR_FL |\ + EXT3_SYNC_FL | EXT3_NODUMP_FL |\ + EXT3_NOATIME_FL | EXT3_COMPRBLK_FL |\ + EXT3_NOCOMPR_FL | EXT3_JOURNAL_DATA_FL |\ + EXT3_NOTAIL_FL | EXT3_DIRSYNC_FL) + +/* Flags that are appropriate for regular files (all but dir-specific ones). */ +#define EXT3_REG_FLMASK (~(EXT3_DIRSYNC_FL | EXT3_TOPDIR_FL)) + +/* Flags that are appropriate for non-directories/regular files. */ +#define EXT3_OTHER_FLMASK (EXT3_NODUMP_FL | EXT3_NOATIME_FL) + +/* Mask out flags that are inappropriate for the given type of inode. */ +static inline __u32 ext3_mask_flags(umode_t mode, __u32 flags) +{ + if (S_ISDIR(mode)) + return flags; + else if (S_ISREG(mode)) + return flags & EXT3_REG_FLMASK; + else + return flags & EXT3_OTHER_FLMASK; +} + +/* Used to pass group descriptor data when online resize is done */ +struct ext3_new_group_input { + __u32 group; /* Group number for this data */ + __u32 block_bitmap; /* Absolute block number of block bitmap */ + __u32 inode_bitmap; /* Absolute block number of inode bitmap */ + __u32 inode_table; /* Absolute block number of inode table start */ + __u32 blocks_count; /* Total number of blocks in this group */ + __u16 reserved_blocks; /* Number of reserved blocks in this group */ + __u16 unused; +}; + +/* The struct ext3_new_group_input in kernel space, with free_blocks_count */ +struct ext3_new_group_data { + __u32 group; + __u32 block_bitmap; + __u32 inode_bitmap; + __u32 inode_table; + __u32 blocks_count; + __u16 reserved_blocks; + __u16 unused; + __u32 free_blocks_count; +}; + + +/* + * ioctl commands + */ +#define EXT3_IOC_GETFLAGS FS_IOC_GETFLAGS +#define EXT3_IOC_SETFLAGS FS_IOC_SETFLAGS +#define EXT3_IOC_GETVERSION _IOR('f', 3, long) +#define EXT3_IOC_SETVERSION _IOW('f', 4, long) +#define EXT3_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long) +#define EXT3_IOC_GROUP_ADD _IOW('f', 8,struct ext3_new_group_input) +#define EXT3_IOC_GETVERSION_OLD FS_IOC_GETVERSION +#define EXT3_IOC_SETVERSION_OLD FS_IOC_SETVERSION +#ifdef CONFIG_JBD_DEBUG +#define EXT3_IOC_WAIT_FOR_READONLY _IOR('f', 99, long) +#endif +#define EXT3_IOC_GETRSVSZ _IOR('f', 5, long) +#define EXT3_IOC_SETRSVSZ _IOW('f', 6, long) + +/* + * ioctl commands in 32 bit emulation + */ +#define EXT3_IOC32_GETFLAGS FS_IOC32_GETFLAGS +#define EXT3_IOC32_SETFLAGS FS_IOC32_SETFLAGS +#define EXT3_IOC32_GETVERSION _IOR('f', 3, int) +#define EXT3_IOC32_SETVERSION _IOW('f', 4, int) +#define EXT3_IOC32_GETRSVSZ _IOR('f', 5, int) +#define EXT3_IOC32_SETRSVSZ _IOW('f', 6, int) +#define EXT3_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int) +#ifdef CONFIG_JBD_DEBUG +#define EXT3_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int) +#endif +#define EXT3_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION +#define EXT3_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION + + +/* + * Mount options + */ +struct ext3_mount_options { + unsigned long s_mount_opt; + uid_t s_resuid; + gid_t s_resgid; + unsigned long s_commit_interval; +#ifdef CONFIG_QUOTA + int s_jquota_fmt; + char *s_qf_names[MAXQUOTAS]; +#endif +}; + +/* + * Structure of an inode on the disk + */ +struct ext3_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 { + __u32 l_i_reserved1; + } linux1; + struct { + __u32 h_i_translator; + } hurd1; + struct { + __u32 m_i_reserved1; + } masix1; + } osd1; /* OS dependent 1 */ + __le32 i_block[EXT3_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 */ + __u16 h_i_mode_high; + __u16 h_i_uid_high; + __u16 h_i_gid_high; + __u32 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 */ + __le16 i_extra_isize; + __le16 i_pad1; +}; + +#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 EXT3_VALID_FS 0x0001 /* Unmounted cleanly */ +#define EXT3_ERROR_FS 0x0002 /* Errors detected */ +#define EXT3_ORPHAN_FS 0x0004 /* Orphans being recovered */ + +/* + * Misc. filesystem flags + */ +#define EXT2_FLAGS_SIGNED_HASH 0x0001 /* Signed dirhash in use */ +#define EXT2_FLAGS_UNSIGNED_HASH 0x0002 /* Unsigned dirhash in use */ +#define EXT2_FLAGS_TEST_FILESYS 0x0004 /* to test development code */ + +/* + * Mount flags + */ +#define EXT3_MOUNT_CHECK 0x00001 /* Do mount-time checks */ +/* EXT3_MOUNT_OLDALLOC was there */ +#define EXT3_MOUNT_GRPID 0x00004 /* Create files with directory's group */ +#define EXT3_MOUNT_DEBUG 0x00008 /* Some debugging messages */ +#define EXT3_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */ +#define EXT3_MOUNT_ERRORS_RO 0x00020 /* Remount fs ro on errors */ +#define EXT3_MOUNT_ERRORS_PANIC 0x00040 /* Panic on errors */ +#define EXT3_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */ +#define EXT3_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/ +#define EXT3_MOUNT_ABORT 0x00200 /* Fatal error detected */ +#define EXT3_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */ +#define EXT3_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */ +#define EXT3_MOUNT_ORDERED_DATA 0x00800 /* Flush data before commit */ +#define EXT3_MOUNT_WRITEBACK_DATA 0x00C00 /* No data ordering */ +#define EXT3_MOUNT_UPDATE_JOURNAL 0x01000 /* Update the journal format */ +#define EXT3_MOUNT_NO_UID32 0x02000 /* Disable 32-bit UIDs */ +#define EXT3_MOUNT_XATTR_USER 0x04000 /* Extended user attributes */ +#define EXT3_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */ +#define EXT3_MOUNT_RESERVATION 0x10000 /* Preallocation */ +#define EXT3_MOUNT_BARRIER 0x20000 /* Use block barriers */ +#define EXT3_MOUNT_QUOTA 0x80000 /* Some quota option set */ +#define EXT3_MOUNT_USRQUOTA 0x100000 /* "old" user quota */ +#define EXT3_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */ +#define EXT3_MOUNT_DATA_ERR_ABORT 0x400000 /* Abort on file data write + * error in ordered mode */ + +/* Compatibility, for having both ext2_fs.h and ext3_fs.h included at once */ +#ifndef _LINUX_EXT2_FS_H +#define clear_opt(o, opt) o &= ~EXT3_MOUNT_##opt +#define set_opt(o, opt) o |= EXT3_MOUNT_##opt +#define test_opt(sb, opt) (EXT3_SB(sb)->s_mount_opt & \ + EXT3_MOUNT_##opt) +#else +#define EXT2_MOUNT_NOLOAD EXT3_MOUNT_NOLOAD +#define EXT2_MOUNT_ABORT EXT3_MOUNT_ABORT +#define EXT2_MOUNT_DATA_FLAGS EXT3_MOUNT_DATA_FLAGS +#endif + +#define ext3_set_bit __set_bit_le +#define ext3_set_bit_atomic ext2_set_bit_atomic +#define ext3_clear_bit __clear_bit_le +#define ext3_clear_bit_atomic ext2_clear_bit_atomic +#define ext3_test_bit test_bit_le +#define ext3_find_next_zero_bit find_next_zero_bit_le + +/* + * Maximal mount counts between two filesystem checks + */ +#define EXT3_DFL_MAX_MNT_COUNT 20 /* Allow 20 mounts */ +#define EXT3_DFL_CHECKINTERVAL 0 /* Don't use interval check */ + +/* + * Behaviour when detecting errors + */ +#define EXT3_ERRORS_CONTINUE 1 /* Continue execution */ +#define EXT3_ERRORS_RO 2 /* Remount fs read-only */ +#define EXT3_ERRORS_PANIC 3 /* Panic */ +#define EXT3_ERRORS_DEFAULT EXT3_ERRORS_CONTINUE + +/* + * Structure of the super block + */ +struct ext3_super_block { +/*00*/ __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 */ +/*10*/ __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 */ +/*20*/ __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 */ +/*30*/ __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 */ +/*40*/ __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 */ +/*50*/ __le16 s_def_resuid; /* Default uid for reserved blocks */ + __le16 s_def_resgid; /* Default gid for reserved blocks */ + /* + * These fields are for EXT3_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 */ +/*60*/ __le32 s_feature_incompat; /* incompatible feature set */ + __le32 s_feature_ro_compat; /* readonly-compatible feature set */ +/*68*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */ +/*78*/ char s_volume_name[16]; /* volume name */ +/*88*/ char s_last_mounted[64]; /* directory where last mounted */ +/*C8*/ __le32 s_algorithm_usage_bitmap; /* For compression */ + /* + * Performance hints. Directory preallocation should only + * happen if the EXT3_FEATURE_COMPAT_DIR_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 */ + __le16 s_reserved_gdt_blocks; /* Per group desc for online growth */ + /* + * Journaling support valid if EXT3_FEATURE_COMPAT_HAS_JOURNAL set. + */ +/*D0*/ __u8 s_journal_uuid[16]; /* uuid of journal superblock */ +/*E0*/ __le32 s_journal_inum; /* inode number of journal file */ + __le32 s_journal_dev; /* device number of journal file */ + __le32 s_last_orphan; /* start of list of inodes to delete */ + __le32 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 */ + __le32 s_mkfs_time; /* When the filesystem was created */ + __le32 s_jnl_blocks[17]; /* Backup of the journal inode */ + /* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */ +/*150*/ __le32 s_blocks_count_hi; /* Blocks count */ + __le32 s_r_blocks_count_hi; /* Reserved blocks count */ + __le32 s_free_blocks_count_hi; /* Free blocks count */ + __le16 s_min_extra_isize; /* All inodes have at least # bytes */ + __le16 s_want_extra_isize; /* New inodes should reserve # bytes */ + __le32 s_flags; /* Miscellaneous flags */ + __le16 s_raid_stride; /* RAID stride */ + __le16 s_mmp_interval; /* # seconds to wait in MMP checking */ + __le64 s_mmp_block; /* Block for multi-mount protection */ + __le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/ + __u8 s_log_groups_per_flex; /* FLEX_BG group size */ + __u8 s_reserved_char_pad2; + __le16 s_reserved_pad; + __u32 s_reserved[162]; /* Padding to the end of the block */ +}; + +/* data type for block offset of block group */ +typedef int ext3_grpblk_t; + +/* data type for filesystem-wide blocks number */ +typedef unsigned long ext3_fsblk_t; + +#define E3FSBLK "%lu" + +struct ext3_reserve_window { + ext3_fsblk_t _rsv_start; /* First byte reserved */ + ext3_fsblk_t _rsv_end; /* Last byte reserved or 0 */ +}; + +struct ext3_reserve_window_node { + struct rb_node rsv_node; + __u32 rsv_goal_size; + __u32 rsv_alloc_hit; + struct ext3_reserve_window rsv_window; +}; + +struct ext3_block_alloc_info { + /* information about reservation window */ + struct ext3_reserve_window_node rsv_window_node; + /* + * was i_next_alloc_block in ext3_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 ext3_inode_info + * is the *physical* companion to i_next_alloc_block. + * it 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. + */ + ext3_fsblk_t last_alloc_physical_block; +}; + +#define rsv_start rsv_window._rsv_start +#define rsv_end rsv_window._rsv_end + +/* + * third extended file system inode data in memory + */ +struct ext3_inode_info { + __le32 i_data[15]; /* unconverted */ + __u32 i_flags; +#ifdef EXT3_FRAGMENTS + __u32 i_faddr; + __u8 i_frag_no; + __u8 i_frag_size; +#endif + ext3_fsblk_t 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 ued 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; + unsigned long i_state_flags; /* Dynamic state flags for ext3 */ + + /* block reservation info */ + struct ext3_block_alloc_info *i_block_alloc_info; + + __u32 i_dir_start_lookup; +#ifdef CONFIG_EXT3_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 + + struct list_head i_orphan; /* unlinked but open inodes */ + + /* + * i_disksize keeps track of what the inode size is ON DISK, not + * in memory. During truncate, i_size is set to the new size by + * the VFS prior to calling ext3_truncate(), but the filesystem won't + * set i_disksize to 0 until the truncate is actually under way. + * + * The intent is that i_disksize always represents the blocks which + * are used by this file. This allows recovery to restart truncate + * on orphans if we crash during truncate. We actually write i_disksize + * into the on-disk inode when writing inodes out, instead of i_size. + * + * The only time when i_disksize and i_size may be different is when + * a truncate is in progress. The only things which change i_disksize + * are ext3_get_block (growth) and ext3_truncate (shrinkth). + */ + loff_t i_disksize; + + /* on-disk additional length */ + __u16 i_extra_isize; + + /* + * truncate_mutex is for serialising ext3_truncate() against + * ext3_getblock(). In the 2.4 ext2 design, great chunks of inode's + * data tree are chopped off during truncate. We can't do that in + * ext3 because whenever we perform intermediate commits during + * truncate, the inode and all the metadata blocks *must* be in a + * consistent state which allows truncation of the orphans to restart + * during recovery. Hence we must fix the get_block-vs-truncate race + * by other means, so we have truncate_mutex. + */ + struct mutex truncate_mutex; + + /* + * Transactions that contain inode's metadata needed to complete + * fsync and fdatasync, respectively. + */ + atomic_t i_sync_tid; + atomic_t i_datasync_tid; + + struct inode vfs_inode; +}; + +/* + * third extended-fs super-block data in memory + */ +struct ext3_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 ext3_super_block * s_es; /* Pointer to the super block in the buffer */ + struct buffer_head ** s_group_desc; + unsigned long s_mount_opt; + ext3_fsblk_t s_sb_block; + uid_t s_resuid; + gid_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; + u32 s_hash_seed[4]; + int s_def_hash_version; + int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */ + 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 ext3_reserve_window_node s_rsv_window_head; + + /* Journaling */ + struct inode * s_journal_inode; + struct journal_s * s_journal; + struct list_head s_orphan; + struct mutex s_orphan_lock; + struct mutex s_resize_lock; + unsigned long s_commit_interval; + struct block_device *journal_bdev; +#ifdef CONFIG_QUOTA + char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */ + int s_jquota_fmt; /* Format of quota to use */ +#endif +}; + +static inline spinlock_t * +sb_bgl_lock(struct ext3_sb_info *sbi, unsigned int block_group) +{ + return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group); +} + +static inline struct ext3_sb_info * EXT3_SB(struct super_block *sb) +{ + return sb->s_fs_info; +} +static inline struct ext3_inode_info *EXT3_I(struct inode *inode) +{ + return container_of(inode, struct ext3_inode_info, vfs_inode); +} + +static inline int ext3_valid_inum(struct super_block *sb, unsigned long ino) +{ + return ino == EXT3_ROOT_INO || + ino == EXT3_JOURNAL_INO || + ino == EXT3_RESIZE_INO || + (ino >= EXT3_FIRST_INO(sb) && + ino <= le32_to_cpu(EXT3_SB(sb)->s_es->s_inodes_count)); +} + +/* + * Inode dynamic state flags + */ +enum { + EXT3_STATE_JDATA, /* journaled data exists */ + EXT3_STATE_NEW, /* inode is newly created */ + EXT3_STATE_XATTR, /* has in-inode xattrs */ + EXT3_STATE_FLUSH_ON_CLOSE, /* flush dirty pages on close */ +}; + +static inline int ext3_test_inode_state(struct inode *inode, int bit) +{ + return test_bit(bit, &EXT3_I(inode)->i_state_flags); +} + +static inline void ext3_set_inode_state(struct inode *inode, int bit) +{ + set_bit(bit, &EXT3_I(inode)->i_state_flags); +} + +static inline void ext3_clear_inode_state(struct inode *inode, int bit) +{ + clear_bit(bit, &EXT3_I(inode)->i_state_flags); +} + +#define NEXT_ORPHAN(inode) EXT3_I(inode)->i_dtime + +/* + * Codes for operating systems + */ +#define EXT3_OS_LINUX 0 +#define EXT3_OS_HURD 1 +#define EXT3_OS_MASIX 2 +#define EXT3_OS_FREEBSD 3 +#define EXT3_OS_LITES 4 + +/* + * Revision levels + */ +#define EXT3_GOOD_OLD_REV 0 /* The good old (original) format */ +#define EXT3_DYNAMIC_REV 1 /* V2 format w/ dynamic inode sizes */ + +#define EXT3_CURRENT_REV EXT3_GOOD_OLD_REV +#define EXT3_MAX_SUPP_REV EXT3_DYNAMIC_REV + +#define EXT3_GOOD_OLD_INODE_SIZE 128 + +/* + * Feature set definitions + */ + +#define EXT3_HAS_COMPAT_FEATURE(sb,mask) \ + ( EXT3_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask) ) +#define EXT3_HAS_RO_COMPAT_FEATURE(sb,mask) \ + ( EXT3_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask) ) +#define EXT3_HAS_INCOMPAT_FEATURE(sb,mask) \ + ( EXT3_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask) ) +#define EXT3_SET_COMPAT_FEATURE(sb,mask) \ + EXT3_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask) +#define EXT3_SET_RO_COMPAT_FEATURE(sb,mask) \ + EXT3_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask) +#define EXT3_SET_INCOMPAT_FEATURE(sb,mask) \ + EXT3_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask) +#define EXT3_CLEAR_COMPAT_FEATURE(sb,mask) \ + EXT3_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask) +#define EXT3_CLEAR_RO_COMPAT_FEATURE(sb,mask) \ + EXT3_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask) +#define EXT3_CLEAR_INCOMPAT_FEATURE(sb,mask) \ + EXT3_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask) + +#define EXT3_FEATURE_COMPAT_DIR_PREALLOC 0x0001 +#define EXT3_FEATURE_COMPAT_IMAGIC_INODES 0x0002 +#define EXT3_FEATURE_COMPAT_HAS_JOURNAL 0x0004 +#define EXT3_FEATURE_COMPAT_EXT_ATTR 0x0008 +#define EXT3_FEATURE_COMPAT_RESIZE_INODE 0x0010 +#define EXT3_FEATURE_COMPAT_DIR_INDEX 0x0020 + +#define EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001 +#define EXT3_FEATURE_RO_COMPAT_LARGE_FILE 0x0002 +#define EXT3_FEATURE_RO_COMPAT_BTREE_DIR 0x0004 + +#define EXT3_FEATURE_INCOMPAT_COMPRESSION 0x0001 +#define EXT3_FEATURE_INCOMPAT_FILETYPE 0x0002 +#define EXT3_FEATURE_INCOMPAT_RECOVER 0x0004 /* Needs recovery */ +#define EXT3_FEATURE_INCOMPAT_JOURNAL_DEV 0x0008 /* Journal device */ +#define EXT3_FEATURE_INCOMPAT_META_BG 0x0010 + +#define EXT3_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR +#define EXT3_FEATURE_INCOMPAT_SUPP (EXT3_FEATURE_INCOMPAT_FILETYPE| \ + EXT3_FEATURE_INCOMPAT_RECOVER| \ + EXT3_FEATURE_INCOMPAT_META_BG) +#define EXT3_FEATURE_RO_COMPAT_SUPP (EXT3_FEATURE_RO_COMPAT_SPARSE_SUPER| \ + EXT3_FEATURE_RO_COMPAT_LARGE_FILE| \ + EXT3_FEATURE_RO_COMPAT_BTREE_DIR) + +/* + * Default values for user and/or group using reserved blocks + */ +#define EXT3_DEF_RESUID 0 +#define EXT3_DEF_RESGID 0 + +/* + * Default mount options + */ +#define EXT3_DEFM_DEBUG 0x0001 +#define EXT3_DEFM_BSDGROUPS 0x0002 +#define EXT3_DEFM_XATTR_USER 0x0004 +#define EXT3_DEFM_ACL 0x0008 +#define EXT3_DEFM_UID16 0x0010 +#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 + */ +#define EXT3_NAME_LEN 255 + +struct ext3_dir_entry { + __le32 inode; /* Inode number */ + __le16 rec_len; /* Directory entry length */ + __le16 name_len; /* Name length */ + char name[EXT3_NAME_LEN]; /* File name */ +}; + +/* + * The new version of the directory entry. Since EXT3 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 ext3_dir_entry_2 { + __le32 inode; /* Inode number */ + __le16 rec_len; /* Directory entry length */ + __u8 name_len; /* Name length */ + __u8 file_type; + char name[EXT3_NAME_LEN]; /* File name */ +}; + +/* + * Ext3 directory file types. Only the low 3 bits are used. The + * other bits are reserved for now. + */ +#define EXT3_FT_UNKNOWN 0 +#define EXT3_FT_REG_FILE 1 +#define EXT3_FT_DIR 2 +#define EXT3_FT_CHRDEV 3 +#define EXT3_FT_BLKDEV 4 +#define EXT3_FT_FIFO 5 +#define EXT3_FT_SOCK 6 +#define EXT3_FT_SYMLINK 7 + +#define EXT3_FT_MAX 8 + +/* + * EXT3_DIR_PAD defines the directory entries boundaries + * + * NOTE: It must be a multiple of 4 + */ +#define EXT3_DIR_PAD 4 +#define EXT3_DIR_ROUND (EXT3_DIR_PAD - 1) +#define EXT3_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT3_DIR_ROUND) & \ + ~EXT3_DIR_ROUND) +#define EXT3_MAX_REC_LEN ((1<<16)-1) + +/* + * Tests against MAX_REC_LEN etc were put in place for 64k block + * sizes; if that is not possible on this arch, we can skip + * those tests and speed things up. + */ +static inline unsigned ext3_rec_len_from_disk(__le16 dlen) +{ + unsigned len = le16_to_cpu(dlen); + +#if (PAGE_CACHE_SIZE >= 65536) + if (len == EXT3_MAX_REC_LEN) + return 1 << 16; +#endif + return len; +} + +static inline __le16 ext3_rec_len_to_disk(unsigned len) +{ +#if (PAGE_CACHE_SIZE >= 65536) + if (len == (1 << 16)) + return cpu_to_le16(EXT3_MAX_REC_LEN); + else if (len > (1 << 16)) + BUG(); +#endif + return cpu_to_le16(len); +} + +/* + * Hash Tree Directory indexing + * (c) Daniel Phillips, 2001 + */ + +#define is_dx(dir) (EXT3_HAS_COMPAT_FEATURE(dir->i_sb, \ + EXT3_FEATURE_COMPAT_DIR_INDEX) && \ + (EXT3_I(dir)->i_flags & EXT3_INDEX_FL)) +#define EXT3_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT3_LINK_MAX) +#define EXT3_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1) + +/* Legal values for the dx_root hash_version field: */ + +#define DX_HASH_LEGACY 0 +#define DX_HASH_HALF_MD4 1 +#define DX_HASH_TEA 2 +#define DX_HASH_LEGACY_UNSIGNED 3 +#define DX_HASH_HALF_MD4_UNSIGNED 4 +#define DX_HASH_TEA_UNSIGNED 5 + +/* hash info structure used by the directory hash */ +struct dx_hash_info +{ + u32 hash; + u32 minor_hash; + int hash_version; + u32 *seed; +}; + +#define EXT3_HTREE_EOF 0x7fffffff + +/* + * Control parameters used by ext3_htree_next_block + */ +#define HASH_NB_ALWAYS 1 + + +/* + * Describe an inode's exact location on disk and in memory + */ +struct ext3_iloc +{ + struct buffer_head *bh; + unsigned long offset; + unsigned long block_group; +}; + +static inline struct ext3_inode *ext3_raw_inode(struct ext3_iloc *iloc) +{ + return (struct ext3_inode *) (iloc->bh->b_data + iloc->offset); +} + +/* + * This structure is stuffed into the struct file's private_data field + * for directories. It is where we put information so that we can do + * readdir operations in hash tree order. + */ +struct dir_private_info { + struct rb_root root; + struct rb_node *curr_node; + struct fname *extra_fname; + loff_t last_pos; + __u32 curr_hash; + __u32 curr_minor_hash; + __u32 next_hash; +}; + +/* calculate the first block number of the group */ +static inline ext3_fsblk_t +ext3_group_first_block_no(struct super_block *sb, unsigned long group_no) +{ + return group_no * (ext3_fsblk_t)EXT3_BLOCKS_PER_GROUP(sb) + + le32_to_cpu(EXT3_SB(sb)->s_es->s_first_data_block); +} + +/* + * Special error return code only used by dx_probe() and its callers. + */ +#define ERR_BAD_DX_DIR -75000 + +/* + * Function prototypes + */ + +/* + * Ok, these declarations are also in <linux/kernel.h> but none of the + * ext3 source programs needs to include it so they are duplicated here. + */ +# define NORET_TYPE /**/ +# define ATTRIB_NORET __attribute__((noreturn)) +# define NORET_AND noreturn, + +/* balloc.c */ +extern int ext3_bg_has_super(struct super_block *sb, int group); +extern unsigned long ext3_bg_num_gdb(struct super_block *sb, int group); +extern ext3_fsblk_t ext3_new_block (handle_t *handle, struct inode *inode, + ext3_fsblk_t goal, int *errp); +extern ext3_fsblk_t ext3_new_blocks (handle_t *handle, struct inode *inode, + ext3_fsblk_t goal, unsigned long *count, int *errp); +extern void ext3_free_blocks (handle_t *handle, struct inode *inode, + ext3_fsblk_t block, unsigned long count); +extern void ext3_free_blocks_sb (handle_t *handle, struct super_block *sb, + ext3_fsblk_t block, unsigned long count, + unsigned long *pdquot_freed_blocks); +extern ext3_fsblk_t ext3_count_free_blocks (struct super_block *); +extern void ext3_check_blocks_bitmap (struct super_block *); +extern struct ext3_group_desc * ext3_get_group_desc(struct super_block * sb, + unsigned int block_group, + struct buffer_head ** bh); +extern int ext3_should_retry_alloc(struct super_block *sb, int *retries); +extern void ext3_init_block_alloc_info(struct inode *); +extern void ext3_rsv_window_add(struct super_block *sb, struct ext3_reserve_window_node *rsv); +extern int ext3_trim_fs(struct super_block *sb, struct fstrim_range *range); + +/* dir.c */ +extern int ext3_check_dir_entry(const char *, struct inode *, + struct ext3_dir_entry_2 *, + struct buffer_head *, unsigned long); +extern int ext3_htree_store_dirent(struct file *dir_file, __u32 hash, + __u32 minor_hash, + struct ext3_dir_entry_2 *dirent); +extern void ext3_htree_free_dir_info(struct dir_private_info *p); + +/* fsync.c */ +extern int ext3_sync_file(struct file *, loff_t, loff_t, int); + +/* hash.c */ +extern int ext3fs_dirhash(const char *name, int len, struct + dx_hash_info *hinfo); + +/* ialloc.c */ +extern struct inode * ext3_new_inode (handle_t *, struct inode *, + const struct qstr *, umode_t); +extern void ext3_free_inode (handle_t *, struct inode *); +extern struct inode * ext3_orphan_get (struct super_block *, unsigned long); +extern unsigned long ext3_count_free_inodes (struct super_block *); +extern unsigned long ext3_count_dirs (struct super_block *); +extern void ext3_check_inodes_bitmap (struct super_block *); +extern unsigned long ext3_count_free (struct buffer_head *, unsigned); + + +/* inode.c */ +int ext3_forget(handle_t *handle, int is_metadata, struct inode *inode, + struct buffer_head *bh, ext3_fsblk_t blocknr); +struct buffer_head * ext3_getblk (handle_t *, struct inode *, long, int, int *); +struct buffer_head * ext3_bread (handle_t *, struct inode *, int, int, int *); +int ext3_get_blocks_handle(handle_t *handle, struct inode *inode, + sector_t iblock, unsigned long maxblocks, struct buffer_head *bh_result, + int create); + +extern struct inode *ext3_iget(struct super_block *, unsigned long); +extern int ext3_write_inode (struct inode *, struct writeback_control *); +extern int ext3_setattr (struct dentry *, struct iattr *); +extern void ext3_evict_inode (struct inode *); +extern int ext3_sync_inode (handle_t *, struct inode *); +extern void ext3_discard_reservation (struct inode *); +extern void ext3_dirty_inode(struct inode *, int); +extern int ext3_change_inode_journal_flag(struct inode *, int); +extern int ext3_get_inode_loc(struct inode *, struct ext3_iloc *); +extern int ext3_can_truncate(struct inode *inode); +extern void ext3_truncate(struct inode *inode); +extern void ext3_set_inode_flags(struct inode *); +extern void ext3_get_inode_flags(struct ext3_inode_info *); +extern void ext3_set_aops(struct inode *inode); +extern int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len); + +/* ioctl.c */ +extern long ext3_ioctl(struct file *, unsigned int, unsigned long); +extern long ext3_compat_ioctl(struct file *, unsigned int, unsigned long); + +/* namei.c */ +extern int ext3_orphan_add(handle_t *, struct inode *); +extern int ext3_orphan_del(handle_t *, struct inode *); +extern int ext3_htree_fill_tree(struct file *dir_file, __u32 start_hash, + __u32 start_minor_hash, __u32 *next_hash); + +/* resize.c */ +extern int ext3_group_add(struct super_block *sb, + struct ext3_new_group_data *input); +extern int ext3_group_extend(struct super_block *sb, + struct ext3_super_block *es, + ext3_fsblk_t n_blocks_count); + +/* super.c */ +extern __printf(3, 4) +void ext3_error(struct super_block *, const char *, const char *, ...); +extern void __ext3_std_error (struct super_block *, const char *, int); +extern __printf(3, 4) +void ext3_abort(struct super_block *, const char *, const char *, ...); +extern __printf(3, 4) +void ext3_warning(struct super_block *, const char *, const char *, ...); +extern __printf(3, 4) +void ext3_msg(struct super_block *, const char *, const char *, ...); +extern void ext3_update_dynamic_rev (struct super_block *sb); + +#define ext3_std_error(sb, errno) \ +do { \ + if ((errno)) \ + __ext3_std_error((sb), __func__, (errno)); \ +} while (0) + +/* + * Inodes and files operations + */ + +/* dir.c */ +extern const struct file_operations ext3_dir_operations; + +/* file.c */ +extern const struct inode_operations ext3_file_inode_operations; +extern const struct file_operations ext3_file_operations; + +/* namei.c */ +extern const struct inode_operations ext3_dir_inode_operations; +extern const struct inode_operations ext3_special_inode_operations; + +/* symlink.c */ +extern const struct inode_operations ext3_symlink_inode_operations; +extern const struct inode_operations ext3_fast_symlink_inode_operations; + +#define EXT3_JOURNAL(inode) (EXT3_SB((inode)->i_sb)->s_journal) + +/* Define the number of blocks we need to account to a transaction to + * modify one block of data. + * + * We may have to touch one inode, one bitmap buffer, up to three + * indirection blocks, the group and superblock summaries, and the data + * block to complete the transaction. */ + +#define EXT3_SINGLEDATA_TRANS_BLOCKS 8U + +/* Extended attribute operations touch at most two data buffers, + * two bitmap buffers, and two group summaries, in addition to the inode + * and the superblock, which are already accounted for. */ + +#define EXT3_XATTR_TRANS_BLOCKS 6U + +/* Define the minimum size for a transaction which modifies data. This + * needs to take into account the fact that we may end up modifying two + * quota files too (one for the group, one for the user quota). The + * superblock only gets updated once, of course, so don't bother + * counting that again for the quota updates. */ + +#define EXT3_DATA_TRANS_BLOCKS(sb) (EXT3_SINGLEDATA_TRANS_BLOCKS + \ + EXT3_XATTR_TRANS_BLOCKS - 2 + \ + EXT3_MAXQUOTAS_TRANS_BLOCKS(sb)) + +/* Delete operations potentially hit one directory's namespace plus an + * entire inode, plus arbitrary amounts of bitmap/indirection data. Be + * generous. We can grow the delete transaction later if necessary. */ + +#define EXT3_DELETE_TRANS_BLOCKS(sb) (EXT3_MAXQUOTAS_TRANS_BLOCKS(sb) + 64) + +/* Define an arbitrary limit for the amount of data we will anticipate + * writing to any given transaction. For unbounded transactions such as + * write(2) and truncate(2) we can write more than this, but we always + * start off at the maximum transaction size and grow the transaction + * optimistically as we go. */ + +#define EXT3_MAX_TRANS_DATA 64U + +/* We break up a large truncate or write transaction once the handle's + * buffer credits gets this low, we need either to extend the + * transaction or to start a new one. Reserve enough space here for + * inode, bitmap, superblock, group and indirection updates for at least + * one block, plus two quota updates. Quota allocations are not + * needed. */ + +#define EXT3_RESERVE_TRANS_BLOCKS 12U + +#define EXT3_INDEX_EXTRA_TRANS_BLOCKS 8 + +#ifdef CONFIG_QUOTA +/* Amount of blocks needed for quota update - we know that the structure was + * allocated so we need to update only inode+data */ +#define EXT3_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0) +/* Amount of blocks needed for quota insert/delete - we do some block writes + * but inode, sb and group updates are done only once */ +#define EXT3_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\ + (EXT3_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_INIT_REWRITE) : 0) +#define EXT3_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\ + (EXT3_SINGLEDATA_TRANS_BLOCKS-3)+3+DQUOT_DEL_REWRITE) : 0) +#else +#define EXT3_QUOTA_TRANS_BLOCKS(sb) 0 +#define EXT3_QUOTA_INIT_BLOCKS(sb) 0 +#define EXT3_QUOTA_DEL_BLOCKS(sb) 0 +#endif +#define EXT3_MAXQUOTAS_TRANS_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_TRANS_BLOCKS(sb)) +#define EXT3_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_INIT_BLOCKS(sb)) +#define EXT3_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT3_QUOTA_DEL_BLOCKS(sb)) + +int +ext3_mark_iloc_dirty(handle_t *handle, + struct inode *inode, + struct ext3_iloc *iloc); + +/* + * On success, We end up with an outstanding reference count against + * iloc->bh. This _must_ be cleaned up later. + */ + +int ext3_reserve_inode_write(handle_t *handle, struct inode *inode, + struct ext3_iloc *iloc); + +int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode); + +/* + * Wrapper functions with which ext3 calls into JBD. The intent here is + * to allow these to be turned into appropriate stubs so ext3 can control + * ext2 filesystems, so ext2+ext3 systems only nee one fs. This work hasn't + * been done yet. + */ + +static inline void ext3_journal_release_buffer(handle_t *handle, + struct buffer_head *bh) +{ + journal_release_buffer(handle, bh); +} + +void ext3_journal_abort_handle(const char *caller, const char *err_fn, + struct buffer_head *bh, handle_t *handle, int err); + +int __ext3_journal_get_undo_access(const char *where, handle_t *handle, + struct buffer_head *bh); + +int __ext3_journal_get_write_access(const char *where, handle_t *handle, + struct buffer_head *bh); + +int __ext3_journal_forget(const char *where, handle_t *handle, + struct buffer_head *bh); + +int __ext3_journal_revoke(const char *where, handle_t *handle, + unsigned long blocknr, struct buffer_head *bh); + +int __ext3_journal_get_create_access(const char *where, + handle_t *handle, struct buffer_head *bh); + +int __ext3_journal_dirty_metadata(const char *where, + handle_t *handle, struct buffer_head *bh); + +#define ext3_journal_get_undo_access(handle, bh) \ + __ext3_journal_get_undo_access(__func__, (handle), (bh)) +#define ext3_journal_get_write_access(handle, bh) \ + __ext3_journal_get_write_access(__func__, (handle), (bh)) +#define ext3_journal_revoke(handle, blocknr, bh) \ + __ext3_journal_revoke(__func__, (handle), (blocknr), (bh)) +#define ext3_journal_get_create_access(handle, bh) \ + __ext3_journal_get_create_access(__func__, (handle), (bh)) +#define ext3_journal_dirty_metadata(handle, bh) \ + __ext3_journal_dirty_metadata(__func__, (handle), (bh)) +#define ext3_journal_forget(handle, bh) \ + __ext3_journal_forget(__func__, (handle), (bh)) + +int ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh); + +handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks); +int __ext3_journal_stop(const char *where, handle_t *handle); + +static inline handle_t *ext3_journal_start(struct inode *inode, int nblocks) +{ + return ext3_journal_start_sb(inode->i_sb, nblocks); +} + +#define ext3_journal_stop(handle) \ + __ext3_journal_stop(__func__, (handle)) + +static inline handle_t *ext3_journal_current_handle(void) +{ + return journal_current_handle(); +} + +static inline int ext3_journal_extend(handle_t *handle, int nblocks) +{ + return journal_extend(handle, nblocks); +} + +static inline int ext3_journal_restart(handle_t *handle, int nblocks) +{ + return journal_restart(handle, nblocks); +} + +static inline int ext3_journal_blocks_per_page(struct inode *inode) +{ + return journal_blocks_per_page(inode); +} + +static inline int ext3_journal_force_commit(journal_t *journal) +{ + return journal_force_commit(journal); +} + +/* super.c */ +int ext3_force_commit(struct super_block *sb); + +static inline int ext3_should_journal_data(struct inode *inode) +{ + if (!S_ISREG(inode->i_mode)) + return 1; + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA) + return 1; + if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL) + return 1; + return 0; +} + +static inline int ext3_should_order_data(struct inode *inode) +{ + if (!S_ISREG(inode->i_mode)) + return 0; + if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL) + return 0; + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA) + return 1; + return 0; +} + +static inline int ext3_should_writeback_data(struct inode *inode) +{ + if (!S_ISREG(inode->i_mode)) + return 0; + if (EXT3_I(inode)->i_flags & EXT3_JOURNAL_DATA_FL) + return 0; + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA) + return 1; + return 0; +} + +#include <trace/events/ext3.h> diff --git a/fs/ext3/ext3_jbd.c b/fs/ext3/ext3_jbd.c index d401f148d74d..785a3261a26c 100644 --- a/fs/ext3/ext3_jbd.c +++ b/fs/ext3/ext3_jbd.c @@ -2,7 +2,7 @@ * Interface between ext3 and JBD */ -#include <linux/ext3_jbd.h> +#include "ext3.h" int __ext3_journal_get_undo_access(const char *where, handle_t *handle, struct buffer_head *bh) diff --git a/fs/ext3/file.c b/fs/ext3/file.c index 724df69847dc..25cb413277e9 100644 --- a/fs/ext3/file.c +++ b/fs/ext3/file.c @@ -18,12 +18,8 @@ * (jj@sunsite.ms.mff.cuni.cz) */ -#include <linux/time.h> -#include <linux/fs.h> -#include <linux/jbd.h> #include <linux/quotaops.h> -#include <linux/ext3_fs.h> -#include <linux/ext3_jbd.h> +#include "ext3.h" #include "xattr.h" #include "acl.h" diff --git a/fs/ext3/fsync.c b/fs/ext3/fsync.c index 1860ed356323..d4dff278cbd8 100644 --- a/fs/ext3/fsync.c +++ b/fs/ext3/fsync.c @@ -22,15 +22,9 @@ * we can depend on generic_block_fdatasync() to sync the data blocks. */ -#include <linux/time.h> #include <linux/blkdev.h> -#include <linux/fs.h> -#include <linux/sched.h> #include <linux/writeback.h> -#include <linux/jbd.h> -#include <linux/ext3_fs.h> -#include <linux/ext3_jbd.h> -#include <trace/events/ext3.h> +#include "ext3.h" /* * akpm: A new design for ext3_sync_file(). diff --git a/fs/ext3/hash.c b/fs/ext3/hash.c index 7d215b4d4f2e..d10231ddcf8a 100644 --- a/fs/ext3/hash.c +++ b/fs/ext3/hash.c @@ -9,9 +9,7 @@ * License. */ -#include <linux/fs.h> -#include <linux/jbd.h> -#include <linux/ext3_fs.h> +#include "ext3.h" #include <linux/cryptohash.h> #define DELTA 0x9E3779B9 diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c index 1cde28438014..e3c39e4cec19 100644 --- a/fs/ext3/ialloc.c +++ b/fs/ext3/ialloc.c @@ -12,21 +12,10 @@ * David S. Miller (davem@caip.rutgers.edu), 1995 */ -#include <linux/time.h> -#include <linux/fs.h> -#include <linux/jbd.h> -#include <linux/ext3_fs.h> -#include <linux/ext3_jbd.h> -#include <linux/stat.h> -#include <linux/string.h> #include <linux/quotaops.h> -#include <linux/buffer_head.h> #include <linux/random.h> -#include <linux/bitops.h> -#include <trace/events/ext3.h> - -#include <asm/byteorder.h> +#include "ext3.h" #include "xattr.h" #include "acl.h" diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 6d3418662b54..10d7812f6021 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -22,22 +22,12 @@ * Assorted race fixes, rewrite of ext3_get_block() by Al Viro, 2000 */ -#include <linux/fs.h> -#include <linux/time.h> -#include <linux/ext3_jbd.h> -#include <linux/jbd.h> #include <linux/highuid.h> -#include <linux/pagemap.h> #include <linux/quotaops.h> -#include <linux/string.h> -#include <linux/buffer_head.h> #include <linux/writeback.h> #include <linux/mpage.h> -#include <linux/uio.h> -#include <linux/bio.h> -#include <linux/fiemap.h> #include <linux/namei.h> -#include <trace/events/ext3.h> +#include "ext3.h" #include "xattr.h" #include "acl.h" diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c index 4af574ce4a46..677a5c27dc69 100644 --- a/fs/ext3/ioctl.c +++ b/fs/ext3/ioctl.c @@ -7,15 +7,10 @@ * Universite Pierre et Marie Curie (Paris VI) */ -#include <linux/fs.h> -#include <linux/jbd.h> -#include <linux/capability.h> -#include <linux/ext3_fs.h> -#include <linux/ext3_jbd.h> #include <linux/mount.h> -#include <linux/time.h> #include <linux/compat.h> #include <asm/uaccess.h> +#include "ext3.h" long ext3_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index e8e211795e9f..d7940b24cf68 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -24,20 +24,8 @@ * Theodore Ts'o, 2002 */ -#include <linux/fs.h> -#include <linux/pagemap.h> -#include <linux/jbd.h> -#include <linux/time.h> -#include <linux/ext3_fs.h> -#include <linux/ext3_jbd.h> -#include <linux/fcntl.h> -#include <linux/stat.h> -#include <linux/string.h> #include <linux/quotaops.h> -#include <linux/buffer_head.h> -#include <linux/bio.h> -#include <trace/events/ext3.h> - +#include "ext3.h" #include "namei.h" #include "xattr.h" #include "acl.h" diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c index 7916e4ce166a..0f814f3450de 100644 --- a/fs/ext3/resize.c +++ b/fs/ext3/resize.c @@ -11,10 +11,7 @@ #define EXT3FS_DEBUG -#include <linux/ext3_jbd.h> - -#include <linux/errno.h> -#include <linux/slab.h> +#include "ext3.h" #define outside(b, first, last) ((b) < (first) || (b) >= (last)) diff --git a/fs/ext3/super.c b/fs/ext3/super.c index e0b45b93327b..cf0b5921cf0f 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -17,22 +17,12 @@ */ #include <linux/module.h> -#include <linux/string.h> -#include <linux/fs.h> -#include <linux/time.h> -#include <linux/jbd.h> -#include <linux/ext3_fs.h> -#include <linux/ext3_jbd.h> -#include <linux/slab.h> -#include <linux/init.h> #include <linux/blkdev.h> #include <linux/parser.h> -#include <linux/buffer_head.h> #include <linux/exportfs.h> -#include <linux/vfs.h> +#include <linux/statfs.h> #include <linux/random.h> #include <linux/mount.h> -#include <linux/namei.h> #include <linux/quotaops.h> #include <linux/seq_file.h> #include <linux/log2.h> @@ -40,13 +30,13 @@ #include <asm/uaccess.h> +#define CREATE_TRACE_POINTS + +#include "ext3.h" #include "xattr.h" #include "acl.h" #include "namei.h" -#define CREATE_TRACE_POINTS -#include <trace/events/ext3.h> - #ifdef CONFIG_EXT3_DEFAULTS_TO_ORDERED #define EXT3_MOUNT_DEFAULT_DATA_MODE EXT3_MOUNT_ORDERED_DATA #else diff --git a/fs/ext3/symlink.c b/fs/ext3/symlink.c index 7c4898207776..6b01c3eab1f3 100644 --- a/fs/ext3/symlink.c +++ b/fs/ext3/symlink.c @@ -17,10 +17,8 @@ * ext3 symlink handling code */ -#include <linux/fs.h> -#include <linux/jbd.h> -#include <linux/ext3_fs.h> #include <linux/namei.h> +#include "ext3.h" #include "xattr.h" static void * ext3_follow_link(struct dentry *dentry, struct nameidata *nd) diff --git a/fs/ext3/xattr.c b/fs/ext3/xattr.c index d565759d82ee..d22ebb7a4f55 100644 --- a/fs/ext3/xattr.c +++ b/fs/ext3/xattr.c @@ -50,14 +50,9 @@ * by the buffer lock. */ -#include <linux/init.h> -#include <linux/fs.h> -#include <linux/slab.h> -#include <linux/ext3_jbd.h> -#include <linux/ext3_fs.h> +#include "ext3.h" #include <linux/mbcache.h> #include <linux/quotaops.h> -#include <linux/rwsem.h> #include "xattr.h" #include "acl.h" diff --git a/fs/ext3/xattr_security.c b/fs/ext3/xattr_security.c index ea26f2acab94..3387664ad70e 100644 --- a/fs/ext3/xattr_security.c +++ b/fs/ext3/xattr_security.c @@ -3,12 +3,8 @@ * Handler for storing security labels as extended attributes. */ -#include <linux/slab.h> -#include <linux/string.h> -#include <linux/fs.h> -#include <linux/ext3_jbd.h> -#include <linux/ext3_fs.h> #include <linux/security.h> +#include "ext3.h" #include "xattr.h" static size_t diff --git a/fs/ext3/xattr_trusted.c b/fs/ext3/xattr_trusted.c index 2526a8829de8..d75727cc67fa 100644 --- a/fs/ext3/xattr_trusted.c +++ b/fs/ext3/xattr_trusted.c @@ -5,11 +5,7 @@ * Copyright (C) 2003 by Andreas Gruenbacher, <a.gruenbacher@computer.org> */ -#include <linux/string.h> -#include <linux/capability.h> -#include <linux/fs.h> -#include <linux/ext3_jbd.h> -#include <linux/ext3_fs.h> +#include "ext3.h" #include "xattr.h" static size_t diff --git a/fs/ext3/xattr_user.c b/fs/ext3/xattr_user.c index b32e473a1e33..5612af3567e0 100644 --- a/fs/ext3/xattr_user.c +++ b/fs/ext3/xattr_user.c @@ -5,10 +5,7 @@ * Copyright (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org> */ -#include <linux/string.h> -#include <linux/fs.h> -#include <linux/ext3_jbd.h> -#include <linux/ext3_fs.h> +#include "ext3.h" #include "xattr.h" static size_t diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 76834587a8a4..a3d2c9ee8d66 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -18,7 +18,6 @@ #include <linux/mount.h> #include <linux/fs.h> #include <linux/gfs2_ondisk.h> -#include <linux/ext2_fs.h> #include <linux/falloc.h> #include <linux/swap.h> #include <linux/crc32.h> diff --git a/fs/namei.c b/fs/namei.c index e615ff37e27d..1898198abc3d 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1054,53 +1054,65 @@ static void follow_dotdot(struct nameidata *nd) } /* - * Allocate a dentry with name and parent, and perform a parent - * directory ->lookup on it. Returns the new dentry, or ERR_PTR - * on error. parent->d_inode->i_mutex must be held. d_lookup must - * have verified that no child exists while under i_mutex. + * This looks up the name in dcache, possibly revalidates the old dentry and + * allocates a new one if not found or not valid. In the need_lookup argument + * returns whether i_op->lookup is necessary. + * + * dir->d_inode->i_mutex must be held */ -static struct dentry *d_alloc_and_lookup(struct dentry *parent, - struct qstr *name, struct nameidata *nd) +static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir, + struct nameidata *nd, bool *need_lookup) { - struct inode *inode = parent->d_inode; struct dentry *dentry; - struct dentry *old; + int error; - /* Don't create child dentry for a dead directory. */ - if (unlikely(IS_DEADDIR(inode))) - return ERR_PTR(-ENOENT); + *need_lookup = false; + dentry = d_lookup(dir, name); + if (dentry) { + if (d_need_lookup(dentry)) { + *need_lookup = true; + } else if (dentry->d_flags & DCACHE_OP_REVALIDATE) { + error = d_revalidate(dentry, nd); + if (unlikely(error <= 0)) { + if (error < 0) { + dput(dentry); + return ERR_PTR(error); + } else if (!d_invalidate(dentry)) { + dput(dentry); + dentry = NULL; + } + } + } + } - dentry = d_alloc(parent, name); - if (unlikely(!dentry)) - return ERR_PTR(-ENOMEM); + if (!dentry) { + dentry = d_alloc(dir, name); + if (unlikely(!dentry)) + return ERR_PTR(-ENOMEM); - old = inode->i_op->lookup(inode, dentry, nd); - if (unlikely(old)) { - dput(dentry); - dentry = old; + *need_lookup = true; } return dentry; } /* - * We already have a dentry, but require a lookup to be performed on the parent - * directory to fill in d_inode. Returns the new dentry, or ERR_PTR on error. - * parent->d_inode->i_mutex must be held. d_lookup must have verified that no - * child exists while under i_mutex. + * Call i_op->lookup on the dentry. The dentry must be negative but may be + * hashed if it was pouplated with DCACHE_NEED_LOOKUP. + * + * dir->d_inode->i_mutex must be held */ -static struct dentry *d_inode_lookup(struct dentry *parent, struct dentry *dentry, - struct nameidata *nd) +static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry, + struct nameidata *nd) { - struct inode *inode = parent->d_inode; struct dentry *old; /* Don't create child dentry for a dead directory. */ - if (unlikely(IS_DEADDIR(inode))) { + if (unlikely(IS_DEADDIR(dir))) { dput(dentry); return ERR_PTR(-ENOENT); } - old = inode->i_op->lookup(inode, dentry, nd); + old = dir->i_op->lookup(dir, dentry, nd); if (unlikely(old)) { dput(dentry); dentry = old; @@ -1108,6 +1120,19 @@ static struct dentry *d_inode_lookup(struct dentry *parent, struct dentry *dentr return dentry; } +static struct dentry *__lookup_hash(struct qstr *name, + struct dentry *base, struct nameidata *nd) +{ + bool need_lookup; + struct dentry *dentry; + + dentry = lookup_dcache(name, base, nd, &need_lookup); + if (!need_lookup) + return dentry; + + return lookup_real(base->d_inode, dentry, nd); +} + /* * It's more convoluted than I'd like it to be, but... it's still fairly * small and for now I'd prefer to have fast path as straight as possible. @@ -1139,6 +1164,8 @@ static int do_lookup(struct nameidata *nd, struct qstr *name, return -ECHILD; nd->seq = seq; + if (unlikely(d_need_lookup(dentry))) + goto unlazy; if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) { status = d_revalidate(dentry, nd); if (unlikely(status <= 0)) { @@ -1147,8 +1174,6 @@ static int do_lookup(struct nameidata *nd, struct qstr *name, goto unlazy; } } - if (unlikely(d_need_lookup(dentry))) - goto unlazy; path->mnt = mnt; path->dentry = dentry; if (unlikely(!__follow_mount_rcu(nd, path, inode))) @@ -1163,38 +1188,14 @@ unlazy: dentry = __d_lookup(parent, name); } - if (dentry && unlikely(d_need_lookup(dentry))) { + if (unlikely(!dentry)) + goto need_lookup; + + if (unlikely(d_need_lookup(dentry))) { dput(dentry); - dentry = NULL; - } -retry: - if (unlikely(!dentry)) { - struct inode *dir = parent->d_inode; - BUG_ON(nd->inode != dir); - - mutex_lock(&dir->i_mutex); - dentry = d_lookup(parent, name); - if (likely(!dentry)) { - dentry = d_alloc_and_lookup(parent, name, nd); - if (IS_ERR(dentry)) { - mutex_unlock(&dir->i_mutex); - return PTR_ERR(dentry); - } - /* known good */ - need_reval = 0; - status = 1; - } else if (unlikely(d_need_lookup(dentry))) { - dentry = d_inode_lookup(parent, dentry, nd); - if (IS_ERR(dentry)) { - mutex_unlock(&dir->i_mutex); - return PTR_ERR(dentry); - } - /* known good */ - need_reval = 0; - status = 1; - } - mutex_unlock(&dir->i_mutex); + goto need_lookup; } + if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval) status = d_revalidate(dentry, nd); if (unlikely(status <= 0)) { @@ -1204,12 +1205,10 @@ retry: } if (!d_invalidate(dentry)) { dput(dentry); - dentry = NULL; - need_reval = 1; - goto retry; + goto need_lookup; } } - +done: path->mnt = mnt; path->dentry = dentry; err = follow_managed(path, nd->flags); @@ -1221,6 +1220,16 @@ retry: nd->flags |= LOOKUP_JUMPED; *inode = path->dentry->d_inode; return 0; + +need_lookup: + BUG_ON(nd->inode != parent->d_inode); + + mutex_lock(&parent->d_inode->i_mutex); + dentry = __lookup_hash(name, parent, nd); + mutex_unlock(&parent->d_inode->i_mutex); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + goto done; } static inline int may_lookup(struct nameidata *nd) @@ -1846,59 +1855,6 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, return err; } -static struct dentry *__lookup_hash(struct qstr *name, - struct dentry *base, struct nameidata *nd) -{ - struct inode *inode = base->d_inode; - struct dentry *dentry; - int err; - - err = inode_permission(inode, MAY_EXEC); - if (err) - return ERR_PTR(err); - - /* - * Don't bother with __d_lookup: callers are for creat as - * well as unlink, so a lot of the time it would cost - * a double lookup. - */ - dentry = d_lookup(base, name); - - if (dentry && d_need_lookup(dentry)) { - /* - * __lookup_hash is called with the parent dir's i_mutex already - * held, so we are good to go here. - */ - dentry = d_inode_lookup(base, dentry, nd); - if (IS_ERR(dentry)) - return dentry; - } - - if (dentry && (dentry->d_flags & DCACHE_OP_REVALIDATE)) { - int status = d_revalidate(dentry, nd); - if (unlikely(status <= 0)) { - /* - * The dentry failed validation. - * If d_revalidate returned 0 attempt to invalidate - * the dentry otherwise d_revalidate is asking us - * to return a fail status. - */ - if (status < 0) { - dput(dentry); - return ERR_PTR(status); - } else if (!d_invalidate(dentry)) { - dput(dentry); - dentry = NULL; - } - } - } - - if (!dentry) - dentry = d_alloc_and_lookup(base, name, nd); - - return dentry; -} - /* * Restricted form of lookup. Doesn't follow links, single-component only, * needs parent already locked. Doesn't follow mounts. @@ -1924,6 +1880,7 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) { struct qstr this; unsigned int c; + int err; WARN_ON_ONCE(!mutex_is_locked(&base->d_inode->i_mutex)); @@ -1948,6 +1905,10 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) return ERR_PTR(err); } + err = inode_permission(base->d_inode, MAY_EXEC); + if (err) + return ERR_PTR(err); + return __lookup_hash(&this, base, NULL); } @@ -2749,7 +2710,7 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) /* * The dentry_unhash() helper will try to drop the dentry early: we - * should have a usage count of 2 if we're the only user of this + * should have a usage count of 1 if we're the only user of this * dentry, and if that is true (possibly after pruning the dcache), * then we drop the dentry now. * diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index a6fda3c188aa..a1a1bfd652c9 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -28,8 +28,6 @@ #include "suballoc.h" #include "move_extents.h" -#include <linux/ext2_fs.h> - #define o2info_from_user(a, b) \ copy_from_user(&(a), (b), sizeof(a)) #define o2info_to_user(a, b) \ diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index f37c32b94525..50952c9bd06c 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -105,26 +105,12 @@ static const struct inode_operations pstore_dir_inode_operations = { .unlink = pstore_unlink, }; -static struct inode *pstore_get_inode(struct super_block *sb, - const struct inode *dir, int mode, dev_t dev) +static struct inode *pstore_get_inode(struct super_block *sb) { struct inode *inode = new_inode(sb); - if (inode) { inode->i_ino = get_next_ino(); - inode->i_uid = inode->i_gid = 0; - inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; - switch (mode & S_IFMT) { - case S_IFREG: - inode->i_fop = &pstore_file_operations; - break; - case S_IFDIR: - inode->i_op = &pstore_dir_inode_operations; - inode->i_fop = &simple_dir_operations; - inc_nlink(inode); - break; - } } return inode; } @@ -216,9 +202,11 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, return rc; rc = -ENOMEM; - inode = pstore_get_inode(pstore_sb, root->d_inode, S_IFREG | 0444, 0); + inode = pstore_get_inode(pstore_sb); if (!inode) goto fail; + inode->i_mode = S_IFREG | 0444; + inode->i_fop = &pstore_file_operations; private = kmalloc(sizeof *private + size, GFP_KERNEL); if (!private) goto fail_alloc; @@ -293,10 +281,12 @@ int pstore_fill_super(struct super_block *sb, void *data, int silent) parse_options(data); - inode = pstore_get_inode(sb, NULL, S_IFDIR | 0755, 0); + inode = pstore_get_inode(sb); if (inode) { - /* override ramfs "dir" options so we catch unlink(2) */ + inode->i_mode = S_IFDIR | 0755; inode->i_op = &pstore_dir_inode_operations; + inode->i_fop = &simple_dir_operations; + inc_nlink(inode); } sb->s_root = d_make_root(inode); if (!sb->s_root) |