Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4 (35806b4f) · Commits · 戴 / test

Documentation/filesystems/ext4.txt

+0 −4

Original line number	Diff line number	Diff line
		@@ -226,10 +226,6 @@ acl Enables POSIX Access Control Lists support.
		noacl This option disables POSIX Access Control List
		support.

		reservation

		noreservation

		bsddf (*) Make 'df' act like BSD.
		minixdf Make 'df' act like Minix.

MAINTAINERS

+10 −3

Original line number	Diff line number	Diff line
		@@ -3572,9 +3572,16 @@ M: Andrew Morton <akpm@linux-foundation.org>
		M: Jan Kara <jack@suse.cz>
		L: linux-ext4@vger.kernel.org
		S: Maintained
		F: fs/jbd*/
		F: include/linux/extjbd.h
		F: include/linux/jbd*.h
		F: fs/jbd/
		F: include/linux/ext3_jbd.h
		F: include/linux/jbd.h

		JOURNALLING LAYER FOR BLOCK DEVICES (JBD2)
		M: "Theodore Ts'o" <tytso@mit.edu>
		L: linux-ext4@vger.kernel.org
		S: Maintained
		F: fs/jbd2/
		F: include/linux/jbd2.h

		JSM Neo PCI based serial card
		M: Breno Leitao <leitao@linux.vnet.ibm.com>

fs/ext4/Makefile

+2 −1

Original line number	Diff line number	Diff line
		@@ -6,7 +6,8 @@ obj-$(CONFIG_EXT4_FS) += ext4.o

		ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \
		ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
		ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o
		ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \
		mmp.o

		ext4-$(CONFIG_EXT4_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o
		ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o

fs/ext4/balloc.c

+11 −135

Original line number	Diff line number	Diff line
		@@ -361,130 +361,6 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
		return bh;
		}

		/**
		* ext4_add_groupblocks() -- Add given blocks to an existing group
		* @handle: handle to this transaction
		* @sb: super block
		* @block: start physcial block to add to the block group
		* @count: number of blocks to free
		*
		* This marks the blocks as free in the bitmap. We ask the
		* mballoc to reload the buddy after this by setting group
		* EXT4_GROUP_INFO_NEED_INIT_BIT flag
		*/
		void ext4_add_groupblocks(handle_t handle, struct super_block sb,
		ext4_fsblk_t block, unsigned long count)
		{
		struct buffer_head *bitmap_bh = NULL;
		struct buffer_head *gd_bh;
		ext4_group_t block_group;
		ext4_grpblk_t bit;
		unsigned int i;
		struct ext4_group_desc *desc;
		struct ext4_sb_info *sbi = EXT4_SB(sb);
		int err = 0, ret, blk_free_count;
		ext4_grpblk_t blocks_freed;
		struct ext4_group_info *grp;

		ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1);

		ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
		grp = ext4_get_group_info(sb, block_group);
		/*
		* Check to see if we are freeing blocks across a group
		* boundary.
		*/
		if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
		goto error_return;
		}
		bitmap_bh = ext4_read_block_bitmap(sb, block_group);
		if (!bitmap_bh)
		goto error_return;
		desc = ext4_get_group_desc(sb, block_group, &gd_bh);
		if (!desc)
		goto error_return;

		if (in_range(ext4_block_bitmap(sb, desc), block, count) \|\|
		in_range(ext4_inode_bitmap(sb, desc), block, count) \|\|
		in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) \|\|
		in_range(block + count - 1, ext4_inode_table(sb, desc),
		sbi->s_itb_per_group)) {
		ext4_error(sb, "Adding blocks in system zones - "
		"Block = %llu, count = %lu",
		block, count);
		goto error_return;
		}

		/*
		* We are about to add blocks to the bitmap,
		* so we need undo access.
		*/
		BUFFER_TRACE(bitmap_bh, "getting undo access");
		err = ext4_journal_get_undo_access(handle, bitmap_bh);
		if (err)
		goto error_return;

		/*
		* We are about to modify some metadata. Call the journal APIs
		* to unshare ->b_data if a currently-committing transaction is
		* using it
		*/
		BUFFER_TRACE(gd_bh, "get_write_access");
		err = ext4_journal_get_write_access(handle, gd_bh);
		if (err)
		goto error_return;
		/*
		* make sure we don't allow a parallel init on other groups in the
		* same buddy cache
		*/
		down_write(&grp->alloc_sem);
		for (i = 0, blocks_freed = 0; i < count; i++) {
		BUFFER_TRACE(bitmap_bh, "clear bit");
		if (!ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
		bit + i, bitmap_bh->b_data)) {
		ext4_error(sb, "bit already cleared for block %llu",
		(ext4_fsblk_t)(block + i));
		BUFFER_TRACE(bitmap_bh, "bit already cleared");
		} else {
		blocks_freed++;
		}
		}
		ext4_lock_group(sb, block_group);
		blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
		ext4_free_blks_set(sb, desc, blk_free_count);
		desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
		ext4_unlock_group(sb, block_group);
		percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed);

		if (sbi->s_log_groups_per_flex) {
		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
		atomic_add(blocks_freed,
		&sbi->s_flex_groups[flex_group].free_blocks);
		}
		/*
		* request to reload the buddy with the
		* new bitmap information
		*/
		set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
		grp->bb_free += blocks_freed;
		up_write(&grp->alloc_sem);

		/* We dirtied the bitmap block */
		BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
		err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);

		/* And the group descriptor block */
		BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
		ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
		if (!err)
		err = ret;

		error_return:
		brelse(bitmap_bh);
		ext4_std_error(sb, err);
		return;
		}

		/**
		* ext4_has_free_blocks()
		* @sbi: in-core super block structure.
		@@ -493,7 +369,8 @@ error_return:
		* Check if filesystem has nblocks free & available for allocation.
		* On success return 1, return 0 on failure.
		*/
		static int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks)
		static int ext4_has_free_blocks(struct ext4_sb_info *sbi,
		s64 nblocks, unsigned int flags)
		{
		s64 free_blocks, dirty_blocks, root_blocks;
		struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
		@@ -507,11 +384,6 @@ static int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks)
		EXT4_FREEBLOCKS_WATERMARK) {
		free_blocks = percpu_counter_sum_positive(fbc);
		dirty_blocks = percpu_counter_sum_positive(dbc);
		if (dirty_blocks < 0) {
		printk(KERN_CRIT "Dirty block accounting "
		"went wrong %lld\n",
		(long long)dirty_blocks);
		}
		}
		/* Check whether we have space after
		* accounting for current dirty blocks & root reserved blocks.
		@@ -522,7 +394,9 @@ static int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks)
		/* Hm, nope. Are (enough) root reserved blocks available? */
		if (sbi->s_resuid == current_fsuid() \|\|
		((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) \|\|
		capable(CAP_SYS_RESOURCE)) {
		capable(CAP_SYS_RESOURCE) \|\|
		(flags & EXT4_MB_USE_ROOT_BLOCKS)) {

		if (free_blocks >= (nblocks + dirty_blocks))
		return 1;
		}
		@@ -531,9 +405,9 @@ static int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks)
		}

		int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
		s64 nblocks)
		s64 nblocks, unsigned int flags)
		{
		if (ext4_has_free_blocks(sbi, nblocks)) {
		if (ext4_has_free_blocks(sbi, nblocks, flags)) {
		percpu_counter_add(&sbi->s_dirtyblocks_counter, nblocks);
		return 0;
		} else
		@@ -554,7 +428,7 @@ int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
		*/
		int ext4_should_retry_alloc(struct super_block sb, int retries)
		{
		if (!ext4_has_free_blocks(EXT4_SB(sb), 1) \|\|
		if (!ext4_has_free_blocks(EXT4_SB(sb), 1, 0) \|\|
		(*retries)++ > 3 \|\|
		!EXT4_SB(sb)->s_journal)
		return 0;
		@@ -577,7 +451,8 @@ int ext4_should_retry_alloc(struct super_block sb, int retries)
		* error stores in errp pointer
		*/
		ext4_fsblk_t ext4_new_meta_blocks(handle_t handle, struct inode inode,
		ext4_fsblk_t goal, unsigned long count, int errp)
		ext4_fsblk_t goal, unsigned int flags,
		unsigned long count, int errp)
		{
		struct ext4_allocation_request ar;
		ext4_fsblk_t ret;
		@@ -587,6 +462,7 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t handle, struct inode inode,
		ar.inode = inode;
		ar.goal = goal;
		ar.len = count ? *count : 1;
		ar.flags = flags;

		ret = ext4_mb_new_blocks(handle, &ar, errp);
		if (count)

fs/ext4/ext4.h

+114 −13

Original line number	Diff line number	Diff line
		@@ -108,7 +108,8 @@ typedef unsigned int ext4_group_t;
		#define EXT4_MB_DELALLOC_RESERVED 0x0400
		/* We are doing stream allocation */
		#define EXT4_MB_STREAM_ALLOC 0x0800

		/* Use reserved root blocks if needed */
		#define EXT4_MB_USE_ROOT_BLOCKS 0x1000

		struct ext4_allocation_request {
		/* target inode for block we're allocating */
		@@ -209,6 +210,8 @@ struct ext4_io_submit {
		*/
		#define EXT4_BAD_INO 1 /* Bad blocks inode */
		#define EXT4_ROOT_INO 2 /* Root inode */
		#define EXT4_USR_QUOTA_INO 3 /* User quota inode */
		#define EXT4_GRP_QUOTA_INO 4 /* Group quota inode */
		#define EXT4_BOOT_LOADER_INO 5 /* Boot loader inode */
		#define EXT4_UNDEL_DIR_INO 6 /* Undelete directory inode */
		#define EXT4_RESIZE_INO 7 /* Reserved group descriptors inode */
		@@ -512,6 +515,10 @@ struct ext4_new_group_data {
		/* Convert extent to initialized after IO complete */
		#define EXT4_GET_BLOCKS_IO_CONVERT_EXT (EXT4_GET_BLOCKS_CONVERT\|\
		EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
		/* Punch out blocks of an extent */
		#define EXT4_GET_BLOCKS_PUNCH_OUT_EXT 0x0020
		/* Don't normalize allocation size (used for fallocate) */
		#define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040

		/*
		* Flags used by ext4_free_blocks
		@@ -1028,7 +1035,7 @@ struct ext4_super_block {
		__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 */
		__le16 s_mmp_update_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 (Nstride)/
		__u8 s_log_groups_per_flex; /* FLEX_BG group size */
		@@ -1144,6 +1151,9 @@ struct ext4_sb_info {
		unsigned long s_ext_blocks;
		unsigned long s_ext_extents;
		#endif
		/* ext4 extent cache stats */
		unsigned long extent_cache_hits;
		unsigned long extent_cache_misses;

		/* for buddy allocator */
		struct ext4_group_info ***s_group_info;
		@@ -1201,6 +1211,9 @@ struct ext4_sb_info {
		struct ext4_li_request *s_li_request;
		/* Wait multiplier for lazy initialization thread */
		unsigned int s_li_wait_mult;

		/* Kernel thread for multiple mount protection */
		struct task_struct *s_mmp_tsk;
		};

		static inline struct ext4_sb_info EXT4_SB(struct super_block sb)
		@@ -1338,6 +1351,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
		#define EXT4_FEATURE_RO_COMPAT_GDT_CSUM 0x0010
		#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK 0x0020
		#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040
		#define EXT4_FEATURE_RO_COMPAT_QUOTA 0x0100

		#define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001
		#define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002
		@@ -1351,13 +1365,29 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
		#define EXT4_FEATURE_INCOMPAT_EA_INODE 0x0400 /* EA in inode */
		#define EXT4_FEATURE_INCOMPAT_DIRDATA 0x1000 /* data in dirent */

		#define EXT2_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR
		#define EXT2_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE\| \
		EXT4_FEATURE_INCOMPAT_META_BG)
		#define EXT2_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER\| \
		EXT4_FEATURE_RO_COMPAT_LARGE_FILE\| \
		EXT4_FEATURE_RO_COMPAT_BTREE_DIR)

		#define EXT3_FEATURE_COMPAT_SUPP EXT4_FEATURE_COMPAT_EXT_ATTR
		#define EXT3_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE\| \
		EXT4_FEATURE_INCOMPAT_RECOVER\| \
		EXT4_FEATURE_INCOMPAT_META_BG)
		#define EXT3_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER\| \
		EXT4_FEATURE_RO_COMPAT_LARGE_FILE\| \
		EXT4_FEATURE_RO_COMPAT_BTREE_DIR)

		#define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR
		#define EXT4_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE\| \
		EXT4_FEATURE_INCOMPAT_RECOVER\| \
		EXT4_FEATURE_INCOMPAT_META_BG\| \
		EXT4_FEATURE_INCOMPAT_EXTENTS\| \
		EXT4_FEATURE_INCOMPAT_64BIT\| \
		EXT4_FEATURE_INCOMPAT_FLEX_BG)
		EXT4_FEATURE_INCOMPAT_FLEX_BG\| \
		EXT4_FEATURE_INCOMPAT_MMP)
		#define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER\| \
		EXT4_FEATURE_RO_COMPAT_LARGE_FILE\| \
		EXT4_FEATURE_RO_COMPAT_GDT_CSUM\| \
		@@ -1590,12 +1620,6 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
		*/
		struct ext4_lazy_init {
		unsigned long li_state;

		wait_queue_head_t li_wait_daemon;
		wait_queue_head_t li_wait_task;
		struct timer_list li_timer;
		struct task_struct *li_task;

		struct list_head li_request_list;
		struct mutex li_list_mtx;
		};
		@@ -1614,6 +1638,67 @@ struct ext4_features {
		struct completion f_kobj_unregister;
		};

		/*
		* This structure will be used for multiple mount protection. It will be
		* written into the block number saved in the s_mmp_block field in the
		* superblock. Programs that check MMP should assume that if
		* SEQ_FSCK (or any unknown code above SEQ_MAX) is present then it is NOT safe
		* to use the filesystem, regardless of how old the timestamp is.
		*/
		#define EXT4_MMP_MAGIC 0x004D4D50U /* ASCII for MMP */
		#define EXT4_MMP_SEQ_CLEAN 0xFF4D4D50U /* mmp_seq value for clean unmount */
		#define EXT4_MMP_SEQ_FSCK 0xE24D4D50U /* mmp_seq value when being fscked */
		#define EXT4_MMP_SEQ_MAX 0xE24D4D4FU /* maximum valid mmp_seq value */

		struct mmp_struct {
		__le32 mmp_magic; /* Magic number for MMP */
		__le32 mmp_seq; /* Sequence no. updated periodically */

		/*
		* mmp_time, mmp_nodename & mmp_bdevname are only used for information
		* purposes and do not affect the correctness of the algorithm
		*/
		__le64 mmp_time; /* Time last updated */
		char mmp_nodename[64]; /* Node which last updated MMP block */
		char mmp_bdevname[32]; /* Bdev which last updated MMP block */

		/*
		* mmp_check_interval is used to verify if the MMP block has been
		* updated on the block device. The value is updated based on the
		* maximum time to write the MMP block during an update cycle.
		*/
		__le16 mmp_check_interval;

		__le16 mmp_pad1;
		__le32 mmp_pad2[227];
		};

		/* arguments passed to the mmp thread */
		struct mmpd_data {
		struct buffer_head bh; / bh from initial read_mmp_block() */
		struct super_block sb; / super block of the fs */
		};

		/*
		* Check interval multiplier
		* The MMP block is written every update interval and initially checked every
		* update interval x the multiplier (the value is then adapted based on the
		* write latency). The reason is that writes can be delayed under load and we
		* don't want readers to incorrectly assume that the filesystem is no longer
		* in use.
		*/
		#define EXT4_MMP_CHECK_MULT 2UL

		/*
		* Minimum interval for MMP checking in seconds.
		*/
		#define EXT4_MMP_MIN_CHECK_INTERVAL 5UL

		/*
		* Maximum interval for MMP checking in seconds.
		*/
		#define EXT4_MMP_MAX_CHECK_INTERVAL 300UL

		/*
		* Function prototypes
		*/
		@@ -1638,10 +1723,12 @@ extern int ext4_bg_has_super(struct super_block *sb, ext4_group_t group);
		extern unsigned long ext4_bg_num_gdb(struct super_block *sb,
		ext4_group_t group);
		extern ext4_fsblk_t ext4_new_meta_blocks(handle_t handle, struct inode inode,
		ext4_fsblk_t goal, unsigned long count, int errp);
		extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
		extern void ext4_add_groupblocks(handle_t handle, struct super_block sb,
		ext4_fsblk_t block, unsigned long count);
		ext4_fsblk_t goal,
		unsigned int flags,
		unsigned long *count,
		int *errp);
		extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
		s64 nblocks, unsigned int flags);
		extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
		extern void ext4_check_blocks_bitmap(struct super_block *);
		extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
		@@ -1706,6 +1793,8 @@ extern void ext4_free_blocks(handle_t handle, struct inode inode,
		unsigned long count, int flags);
		extern int ext4_mb_add_groupinfo(struct super_block *sb,
		ext4_group_t i, struct ext4_group_desc *desc);
		extern void ext4_add_groupblocks(handle_t handle, struct super_block sb,
		ext4_fsblk_t block, unsigned long count);
		extern int ext4_trim_fs(struct super_block , struct fstrim_range );

		/* inode.c */
		@@ -1729,6 +1818,7 @@ extern int ext4_change_inode_journal_flag(struct inode *, int);
		extern int ext4_get_inode_loc(struct inode , struct ext4_iloc );
		extern int ext4_can_truncate(struct inode *inode);
		extern void ext4_truncate(struct inode *);
		extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length);
		extern int ext4_truncate_restart_trans(handle_t , struct inode , int nblocks);
		extern void ext4_set_inode_flags(struct inode *);
		extern void ext4_get_inode_flags(struct ext4_inode_info *);
		@@ -1738,6 +1828,8 @@ extern int ext4_writepage_trans_blocks(struct inode *);
		extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
		extern int ext4_block_truncate_page(handle_t *handle,
		struct address_space *mapping, loff_t from);
		extern int ext4_block_zero_page_range(handle_t *handle,
		struct address_space *mapping, loff_t from, loff_t length);
		extern int ext4_page_mkwrite(struct vm_area_struct vma, struct vm_fault vmf);
		extern qsize_t ext4_get_reserved_space(struct inode inode);
		extern void ext4_da_update_reserve_space(struct inode *inode,
		@@ -1788,6 +1880,10 @@ extern void __ext4_warning(struct super_block , const char , unsigned int,
		__LINE__, ## message)
		extern void ext4_msg(struct super_block , const char , const char *, ...)
		__attribute__ ((format (printf, 3, 4)));
		extern void __dump_mmp_msg(struct super_block , struct mmp_struct mmp,
		const char , unsigned int, const char );
		#define dump_mmp_msg(sb, mmp, msg) __dump_mmp_msg(sb, mmp, __func__, \
		__LINE__, msg)
		extern void __ext4_grp_locked_error(const char *, unsigned int, \
		struct super_block *, ext4_group_t, \
		unsigned long, ext4_fsblk_t, \
		@@ -2064,6 +2160,8 @@ extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
		extern int ext4_ext_map_blocks(handle_t handle, struct inode inode,
		struct ext4_map_blocks *map, int flags);
		extern void ext4_ext_truncate(struct inode *);
		extern int ext4_ext_punch_hole(struct file *file, loff_t offset,
		loff_t length);
		extern void ext4_ext_init(struct super_block *);
		extern void ext4_ext_release(struct super_block *);
		extern long ext4_fallocate(struct file *file, int mode, loff_t offset,
		@@ -2092,6 +2190,9 @@ extern int ext4_bio_write_page(struct ext4_io_submit *io,
		int len,
		struct writeback_control *wbc);

		/* mmp.c */
		extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);

		/* BH_Uninit flag: blocks are allocated but uninitialized on disk */
		enum ext4_state_bits {
		BH_Uninit /* blocks are allocated but uninitialized on disk */

Admin message