Merge branch 'next' into upstream-merge

Conflicts:
	fs/ext4/inode.c
	fs/ext4/mballoc.c
	include/trace/events/ext4.h

Documentation/filesystems/ext4.txt

@@ -353,6 +353,20 @@ noauto_da_alloc		replacing existing files via patterns such as
 			system crashes before the delayed allocation
 			blocks are forced to disk.
 
+noinit_itable		Do not initialize any uninitialized inode table
+			blocks in the background.  This feature may be
+			used by installation CD's so that the install
+			process can complete as quickly as possible; the
+			inode table initialization process would then be
+			deferred until the next time the  file system
+			is unmounted.
+
+init_itable=n		The lazy itable init code will wait n times the
+			number of milliseconds it took to zero out the
+			previous block group's inode table.  This
+			minimizes the impact on the systme performance
+			while file system's inode table is being initialized.
+
 discard		Controls whether ext4 should issue discard/TRIM
 nodiscard(*)		commands to the underlying block device when
 			blocks are freed.  This is useful for SSD devices

fs/ext4/Makefile

@@ -4,7 +4,7 @@
 
 obj-$(CONFIG_EXT4_FS) += ext4.o
 
-ext4-y	:= balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.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
 

fs/ext4/balloc.c

@@ -171,7 +171,8 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 		 * less than the blocksize * 8 ( which is the size
 		 * of bitmap ), set rest of the block bitmap to 1
 		 */
-		mark_bitmap_end(group_blocks, sb->s_blocksize * 8, bh->b_data);
+		ext4_mark_bitmap_end(group_blocks, sb->s_blocksize * 8,
+				     bh->b_data);
 	}
 	return free_blocks - ext4_group_used_meta_blocks(sb, block_group, gdp);
 }
@@ -489,7 +490,7 @@ void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
  * Check if filesystem has nblocks free & available for allocation.
  * On success return 1, return 0 on failure.
  */
-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)
 {
 	s64 free_blocks, dirty_blocks, root_blocks;
 	struct percpu_counter *fbc = &sbi->s_freeblocks_counter;

fs/ext4/block_validity.c

@@ -29,16 +29,15 @@ struct ext4_system_zone {
 
 static struct kmem_cache *ext4_system_zone_cachep;
 
-int __init init_ext4_system_zone(void)
+int __init ext4_init_system_zone(void)
 {
-	ext4_system_zone_cachep = KMEM_CACHE(ext4_system_zone,
-					     SLAB_RECLAIM_ACCOUNT);
+	ext4_system_zone_cachep = KMEM_CACHE(ext4_system_zone, 0);
 	if (ext4_system_zone_cachep == NULL)
 		return -ENOMEM;
 	return 0;
 }
 
-void exit_ext4_system_zone(void)
+void ext4_exit_system_zone(void)
 {
 	kmem_cache_destroy(ext4_system_zone_cachep);
 }

fs/ext4/dir.c

@@ -39,7 +39,7 @@ static int ext4_release_dir(struct inode *inode,
 				struct file *filp);
 
 const struct file_operations ext4_dir_operations = {
-	.llseek		= generic_file_llseek,
+	.llseek		= ext4_llseek,
 	.read		= generic_read_dir,
 	.readdir	= ext4_readdir,		/* we take BKL. needed?*/
 	.unlocked_ioctl = ext4_ioctl,

fs/ext4/ext4.h

@@ -168,7 +168,20 @@ struct mpage_da_data {
 	int pages_written;
 	int retval;
 };
-#define	EXT4_IO_UNWRITTEN	0x1
+
+/*
+ * Flags for ext4_io_end->flags
+ */
+#define	EXT4_IO_END_UNWRITTEN	0x0001
+#define EXT4_IO_END_ERROR	0x0002
+
+struct ext4_io_page {
+	struct page	*p_page;
+	int		p_count;
+};
+
+#define MAX_IO_PAGES 128
+
 typedef struct ext4_io_end {
 	struct list_head	list;		/* per-file finished IO list */
 	struct inode		*inode;		/* file being written to */
@@ -179,8 +192,18 @@ typedef struct ext4_io_end {
 	struct work_struct	work;		/* data work queue */
 	struct kiocb		*iocb;		/* iocb struct for AIO */
 	int			result;		/* error value for AIO */
+	int			num_io_pages;
+	struct ext4_io_page	*pages[MAX_IO_PAGES];
 } ext4_io_end_t;
 
+struct ext4_io_submit {
+	int			io_op;
+	struct bio		*io_bio;
+	ext4_io_end_t		*io_end;
+	struct ext4_io_page	*io_page;
+	sector_t		io_next_block;
+};
+
 /*
  * Special inodes numbers
  */
@@ -205,6 +228,7 @@ typedef struct ext4_io_end {
 #define EXT4_MIN_BLOCK_SIZE		1024
 #define	EXT4_MAX_BLOCK_SIZE		65536
 #define EXT4_MIN_BLOCK_LOG_SIZE		10
+#define EXT4_MAX_BLOCK_LOG_SIZE		16
 #ifdef __KERNEL__
 # define EXT4_BLOCK_SIZE(s)		((s)->s_blocksize)
 #else
@@ -889,6 +913,7 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
 #define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
 #define EXT4_MOUNT_DISCARD		0x40000000 /* Issue DISCARD requests */
+#define EXT4_MOUNT_INIT_INODE_TABLE	0x80000000 /* Initialize uninitialized itables */
 
 #define clear_opt(o, opt)		o &= ~EXT4_MOUNT_##opt
 #define set_opt(o, opt)			o |= EXT4_MOUNT_##opt
@@ -1087,7 +1112,6 @@ struct ext4_sb_info {
 	struct completion s_kobj_unregister;
 
 	/* Journaling */
-	struct inode *s_journal_inode;
 	struct journal_s *s_journal;
 	struct list_head s_orphan;
 	struct mutex s_orphan_lock;
@@ -1120,10 +1144,7 @@ struct ext4_sb_info {
 	/* for buddy allocator */
 	struct ext4_group_info ***s_group_info;
 	struct inode *s_buddy_cache;
-	long s_blocks_reserved;
-	spinlock_t s_reserve_lock;
 	spinlock_t s_md_lock;
-	tid_t s_last_transaction;
 	unsigned short *s_mb_offsets;
 	unsigned int *s_mb_maxs;
 
@@ -1141,7 +1162,6 @@ struct ext4_sb_info {
 	unsigned long s_mb_last_start;
 
 	/* stats for buddy allocator */
-	spinlock_t s_mb_pa_lock;
 	atomic_t s_bal_reqs;	/* number of reqs with len > 1 */
 	atomic_t s_bal_success;	/* we found long enough chunks */
 	atomic_t s_bal_allocated;	/* in blocks */
@@ -1172,6 +1192,11 @@ struct ext4_sb_info {
 
 	/* timer for periodic error stats printing */
 	struct timer_list s_err_report;
+
+	/* Lazy inode table initialization info */
+	struct ext4_li_request *s_li_request;
+	/* Wait multiplier for lazy initialization thread */
+	unsigned int s_li_wait_mult;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1533,7 +1558,42 @@ ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
 void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
 			ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp);
 
-extern struct proc_dir_entry *ext4_proc_root;
+/*
+ * Timeout and state flag for lazy initialization inode thread.
+ */
+#define EXT4_DEF_LI_WAIT_MULT			10
+#define EXT4_DEF_LI_MAX_START_DELAY		5
+#define EXT4_LAZYINIT_QUIT			0x0001
+#define EXT4_LAZYINIT_RUNNING			0x0002
+
+/*
+ * Lazy inode table initialization info
+ */
+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;
+};
+
+struct ext4_li_request {
+	struct super_block	*lr_super;
+	struct ext4_sb_info	*lr_sbi;
+	ext4_group_t		lr_next_group;
+	struct list_head	lr_request;
+	unsigned long		lr_next_sched;
+	unsigned long		lr_timeout;
+};
+
+struct ext4_features {
+	struct kobject f_kobj;
+	struct completion f_kobj_unregister;
+};
 
 /*
  * Function prototypes
@@ -1561,7 +1621,6 @@ extern unsigned long ext4_bg_num_gdb(struct super_block *sb,
 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 int ext4_has_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);
 extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *);
@@ -1605,11 +1664,9 @@ extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
 extern unsigned long ext4_count_free_inodes(struct super_block *);
 extern unsigned long ext4_count_dirs(struct super_block *);
 extern void ext4_check_inodes_bitmap(struct super_block *);
-extern unsigned ext4_init_inode_bitmap(struct super_block *sb,
-				       struct buffer_head *bh,
-				       ext4_group_t group,
-				       struct ext4_group_desc *desc);
-extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
+extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap);
+extern int ext4_init_inode_table(struct super_block *sb,
+				 ext4_group_t group, int barrier);
 
 /* mballoc.c */
 extern long ext4_mb_stats;
@@ -1620,16 +1677,15 @@ extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
 				struct ext4_allocation_request *, int *);
 extern int ext4_mb_reserve_blocks(struct super_block *, int);
 extern void ext4_discard_preallocations(struct inode *);
-extern int __init init_ext4_mballoc(void);
-extern void exit_ext4_mballoc(void);
+extern int __init ext4_init_mballoc(void);
+extern void ext4_exit_mballoc(void);
 extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			     struct buffer_head *bh, ext4_fsblk_t block,
 			     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 int ext4_mb_get_buddy_cache_lock(struct super_block *, ext4_group_t);
-extern void ext4_mb_put_buddy_cache_lock(struct super_block *,
-						ext4_group_t, int);
+extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
+
 /* inode.c */
 struct buffer_head *ext4_getblk(handle_t *, struct inode *,
 						ext4_lblk_t, int, int *);
@@ -1657,13 +1713,11 @@ extern void ext4_get_inode_flags(struct ext4_inode_info *);
 extern int ext4_alloc_da_blocks(struct inode *inode);
 extern void ext4_set_aops(struct inode *inode);
 extern int ext4_writepage_trans_blocks(struct inode *);
-extern int ext4_meta_trans_blocks(struct inode *, int nrblocks, int idxblocks);
 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_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 extern qsize_t *ext4_get_reserved_space(struct inode *inode);
-extern int flush_completed_IO(struct inode *inode);
 extern void ext4_da_update_reserve_space(struct inode *inode,
 					int used, int quota_claim);
 /* ioctl.c */
@@ -1960,6 +2014,7 @@ extern const struct file_operations ext4_dir_operations;
 /* file.c */
 extern const struct inode_operations ext4_file_inode_operations;
 extern const struct file_operations ext4_file_operations;
+extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
 
 /* namei.c */
 extern const struct inode_operations ext4_dir_inode_operations;
@@ -1973,8 +2028,8 @@ extern const struct inode_operations ext4_fast_symlink_inode_operations;
 /* block_validity */
 extern void ext4_release_system_zone(struct super_block *sb);
 extern int ext4_setup_system_zone(struct super_block *sb);
-extern int __init init_ext4_system_zone(void);
-extern void exit_ext4_system_zone(void);
+extern int __init ext4_init_system_zone(void);
+extern void ext4_exit_system_zone(void);
 extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
 				 ext4_fsblk_t start_blk,
 				 unsigned int count);
@@ -2002,6 +2057,17 @@ extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
 			     __u64 start_orig, __u64 start_donor,
 			     __u64 len, __u64 *moved_len);
 
+/* page-io.c */
+extern int __init ext4_init_pageio(void);
+extern void ext4_exit_pageio(void);
+extern void ext4_free_io_end(ext4_io_end_t *io);
+extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
+extern int ext4_end_io_nolock(ext4_io_end_t *io);
+extern void ext4_io_submit(struct ext4_io_submit *io);
+extern int ext4_bio_write_page(struct ext4_io_submit *io,
+			       struct page *page,
+			       int len,
+			       struct writeback_control *wbc);
 
 /* BH_Uninit flag: blocks are allocated but uninitialized on disk */
 enum ext4_state_bits {

fs/ext4/ext4_extents.h

@@ -225,11 +225,60 @@ static inline void ext4_ext_mark_initialized(struct ext4_extent *ext)
 	ext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ext));
 }
 
+/*
+ * ext4_ext_pblock:
+ * combine low and high parts of physical block number into ext4_fsblk_t
+ */
+static inline ext4_fsblk_t ext4_ext_pblock(struct ext4_extent *ex)
+{
+	ext4_fsblk_t block;
+
+	block = le32_to_cpu(ex->ee_start_lo);
+	block |= ((ext4_fsblk_t) le16_to_cpu(ex->ee_start_hi) << 31) << 1;
+	return block;
+}
+
+/*
+ * ext4_idx_pblock:
+ * combine low and high parts of a leaf physical block number into ext4_fsblk_t
+ */
+static inline ext4_fsblk_t ext4_idx_pblock(struct ext4_extent_idx *ix)
+{
+	ext4_fsblk_t block;
+
+	block = le32_to_cpu(ix->ei_leaf_lo);
+	block |= ((ext4_fsblk_t) le16_to_cpu(ix->ei_leaf_hi) << 31) << 1;
+	return block;
+}
+
+/*
+ * ext4_ext_store_pblock:
+ * stores a large physical block number into an extent struct,
+ * breaking it into parts
+ */
+static inline void ext4_ext_store_pblock(struct ext4_extent *ex,
+					 ext4_fsblk_t pb)
+{
+	ex->ee_start_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff));
+	ex->ee_start_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) &
+				      0xffff);
+}
+
+/*
+ * ext4_idx_store_pblock:
+ * stores a large physical block number into an index struct,
+ * breaking it into parts
+ */
+static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix,
+					 ext4_fsblk_t pb)
+{
+	ix->ei_leaf_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff));
+	ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) &
+				     0xffff);
+}
+
 extern int ext4_ext_calc_metadata_amount(struct inode *inode,
 					 sector_t lblocks);
-extern ext4_fsblk_t ext_pblock(struct ext4_extent *ex);
-extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *);
-extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t);
 extern int ext4_extent_tree_init(handle_t *, struct inode *);
 extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
 						   int num,
@@ -237,19 +286,9 @@ extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
 extern int ext4_can_extents_be_merged(struct inode *inode,
 				      struct ext4_extent *ex1,
 				      struct ext4_extent *ex2);
-extern int ext4_ext_try_to_merge(struct inode *inode,
-				 struct ext4_ext_path *path,
-				 struct ext4_extent *);
-extern unsigned int ext4_ext_check_overlap(struct inode *, struct ext4_extent *, struct ext4_ext_path *);
 extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *, int);
-extern int ext4_ext_walk_space(struct inode *, ext4_lblk_t, ext4_lblk_t,
-							ext_prepare_callback, void *);
 extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
 							struct ext4_ext_path *);
-extern int ext4_ext_search_left(struct inode *, struct ext4_ext_path *,
-						ext4_lblk_t *, ext4_fsblk_t *);
-extern int ext4_ext_search_right(struct inode *, struct ext4_ext_path *,
-						ext4_lblk_t *, ext4_fsblk_t *);
 extern void ext4_ext_drop_refs(struct ext4_ext_path *);
 extern int ext4_ext_check_inode(struct inode *inode);
 #endif /* _EXT4_EXTENTS */

fs/ext4/file.c

@@ -130,8 +130,50 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 	return dquot_file_open(inode, filp);
 }
 
+/*
+ * ext4_llseek() copied from generic_file_llseek() to handle both
+ * block-mapped and extent-mapped maxbytes values. This should
+ * otherwise be identical with generic_file_llseek().
+ */
+loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
+{
+	struct inode *inode = file->f_mapping->host;
+	loff_t maxbytes;
+
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+		maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes;
+	else
+		maxbytes = inode->i_sb->s_maxbytes;
+	mutex_lock(&inode->i_mutex);
+	switch (origin) {
+	case SEEK_END:
+		offset += inode->i_size;
+		break;
+	case SEEK_CUR:
+		if (offset == 0) {
+			mutex_unlock(&inode->i_mutex);
+			return file->f_pos;
+		}
+		offset += file->f_pos;
+		break;
+	}
+
+	if (offset < 0 || offset > maxbytes) {
+		mutex_unlock(&inode->i_mutex);
+		return -EINVAL;
+	}
+
+	if (offset != file->f_pos) {
+		file->f_pos = offset;
+		file->f_version = 0;
+	}
+	mutex_unlock(&inode->i_mutex);
+
+	return offset;
+}
+
 const struct file_operations ext4_file_operations = {
-	.llseek		= generic_file_llseek,
+	.llseek		= ext4_llseek,
 	.read		= do_sync_read,
 	.write		= do_sync_write,
 	.aio_read	= generic_file_aio_read,

fs/ext4/fsync.c

@@ -34,6 +34,89 @@
 
 #include <trace/events/ext4.h>
 
+static void dump_completed_IO(struct inode * inode)
+{
+#ifdef	EXT4_DEBUG
+	struct list_head *cur, *before, *after;
+	ext4_io_end_t *io, *io0, *io1;
+	unsigned long flags;
+
+	if (list_empty(&EXT4_I(inode)->i_completed_io_list)){
+		ext4_debug("inode %lu completed_io list is empty\n", inode->i_ino);
+		return;
+	}
+
+	ext4_debug("Dump inode %lu completed_io list \n", inode->i_ino);
+	spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
+	list_for_each_entry(io, &EXT4_I(inode)->i_completed_io_list, list){
+		cur = &io->list;
+		before = cur->prev;
+		io0 = container_of(before, ext4_io_end_t, list);
+		after = cur->next;
+		io1 = container_of(after, ext4_io_end_t, list);
+
+		ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n",
+			    io, inode->i_ino, io0, io1);
+	}
+	spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags);
+#endif
+}
+
+/*
+ * This function is called from ext4_sync_file().
+ *
+ * When IO is completed, the work to convert unwritten extents to
+ * written is queued on workqueue but may not get immediately
+ * scheduled. When fsync is called, we need to ensure the
+ * conversion is complete before fsync returns.
+ * The inode keeps track of a list of pending/completed IO that
+ * might needs to do the conversion. This function walks through
+ * the list and convert the related unwritten extents for completed IO
+ * to written.
+ * The function return the number of pending IOs on success.
+ */
+static int flush_completed_IO(struct inode *inode)
+{
+	ext4_io_end_t *io;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	unsigned long flags;
+	int ret = 0;
+	int ret2 = 0;
+
+	if (list_empty(&ei->i_completed_io_list))
+		return ret;
+
+	dump_completed_IO(inode);
+	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+	while (!list_empty(&ei->i_completed_io_list)){
+		io = list_entry(ei->i_completed_io_list.next,
+				ext4_io_end_t, list);
+		/*
+		 * Calling ext4_end_io_nolock() to convert completed
+		 * IO to written.
+		 *
+		 * When ext4_sync_file() is called, run_queue() may already
+		 * about to flush the work corresponding to this io structure.
+		 * It will be upset if it founds the io structure related
+		 * to the work-to-be schedule is freed.
+		 *
+		 * Thus we need to keep the io structure still valid here after
+		 * convertion finished. The io structure has a flag to
+		 * avoid double converting from both fsync and background work
+		 * queue work.
+		 */
+		spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+		ret = ext4_end_io_nolock(io);
+		spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+		if (ret < 0)
+			ret2 = ret;
+		else
+			list_del_init(&io->list);
+	}
+	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+	return (ret2 < 0) ? ret2 : 0;
+}
+
 /*
  * If we're not journaling and this is a just-created file, we have to
  * sync our parent directory (if it was freshly created) since

fs/ext4/ialloc.c

@@ -50,7 +50,7 @@
  * need to use it within a single byte (to ensure we get endianness right).
  * We can use memset for the rest of the bitmap as there are no other users.
  */
-void mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
+void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
 {
 	int i;
 
@@ -65,9 +65,10 @@ void mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
 }
 
 /* Initializes an uninitialized inode bitmap */
-unsigned ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh,
-				ext4_group_t block_group,
-				struct ext4_group_desc *gdp)
+static unsigned ext4_init_inode_bitmap(struct super_block *sb,
+				       struct buffer_head *bh,
+				       ext4_group_t block_group,
+				       struct ext4_group_desc *gdp)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
@@ -85,7 +86,7 @@ unsigned ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh,
 	}
 
 	memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8);
-	mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
+	ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
 			bh->b_data);
 
 	return EXT4_INODES_PER_GROUP(sb);
@@ -107,6 +108,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	desc = ext4_get_group_desc(sb, block_group, NULL);
 	if (!desc)
 		return NULL;
+
 	bitmap_blk = ext4_inode_bitmap(sb, desc);
 	bh = sb_getblk(sb, bitmap_blk);
 	if (unlikely(!bh)) {
@@ -123,6 +125,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 		unlock_buffer(bh);
 		return bh;
 	}
+
 	ext4_lock_group(sb, block_group);
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
 		ext4_init_inode_bitmap(sb, bh, block_group, desc);
@@ -133,6 +136,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 		return bh;
 	}
 	ext4_unlock_group(sb, block_group);
+
 	if (buffer_uptodate(bh)) {
 		/*
 		 * if not uninit if bh is uptodate,
@@ -411,8 +415,8 @@ struct orlov_stats {
  * for a particular block group or flex_bg.  If flex_size is 1, then g
  * is a block group number; otherwise it is flex_bg number.
  */
-void get_orlov_stats(struct super_block *sb, ext4_group_t g,
-		       int flex_size, struct orlov_stats *stats)
+static void get_orlov_stats(struct super_block *sb, ext4_group_t g,
+			    int flex_size, struct orlov_stats *stats)
 {
 	struct ext4_group_desc *desc;
 	struct flex_groups *flex_group = EXT4_SB(sb)->s_flex_groups;
@@ -712,8 +716,17 @@ static int ext4_claim_inode(struct super_block *sb,
 {
 	int free = 0, retval = 0, count;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
 	struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
 
+	/*
+	 * We have to be sure that new inode allocation does not race with
+	 * inode table initialization, because otherwise we may end up
+	 * allocating and writing new inode right before sb_issue_zeroout
+	 * takes place and overwriting our new inode with zeroes. So we
+	 * take alloc_sem to prevent it.
+	 */
+	down_read(&grp->alloc_sem);
 	ext4_lock_group(sb, group);
 	if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) {
 		/* not a free inode */
@@ -724,6 +737,7 @@ static int ext4_claim_inode(struct super_block *sb,
 	if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
 			ino > EXT4_INODES_PER_GROUP(sb)) {
 		ext4_unlock_group(sb, group);
+		up_read(&grp->alloc_sem);
 		ext4_error(sb, "reserved inode or inode > inodes count - "
 			   "block_group = %u, inode=%lu", group,
 			   ino + group * EXT4_INODES_PER_GROUP(sb));
@@ -772,6 +786,7 @@ static int ext4_claim_inode(struct super_block *sb,
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
 err_ret:
 	ext4_unlock_group(sb, group);
+	up_read(&grp->alloc_sem);
 	return retval;
 }
 
@@ -1205,3 +1220,109 @@ unsigned long ext4_count_dirs(struct super_block * sb)
 	}
 	return count;
 }
+
+/*
+ * Zeroes not yet zeroed inode table - just write zeroes through the whole
+ * inode table. Must be called without any spinlock held. The only place
+ * where it is called from on active part of filesystem is ext4lazyinit
+ * thread, so we do not need any special locks, however we have to prevent
+ * inode allocation from the current group, so we take alloc_sem lock, to
+ * block ext4_claim_inode until we are finished.
+ */
+extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
+				 int barrier)
+{
+	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_desc *gdp = NULL;
+	struct buffer_head *group_desc_bh;
+	handle_t *handle;
+	ext4_fsblk_t blk;
+	int num, ret = 0, used_blks = 0;
+
+	/* This should not happen, but just to be sure check this */
+	if (sb->s_flags & MS_RDONLY) {
+		ret = 1;
+		goto out;
+	}
+
+	gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
+	if (!gdp)
+		goto out;
+
+	/*
+	 * We do not need to lock this, because we are the only one
+	 * handling this flag.
+	 */
+	if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))
+		goto out;
+
+	handle = ext4_journal_start_sb(sb, 1);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out;
+	}
+
+	down_write(&grp->alloc_sem);
+	/*
+	 * If inode bitmap was already initialized there may be some
+	 * used inodes so we need to skip blocks with used inodes in
+	 * inode table.
+	 */
+	if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)))
+		used_blks = DIV_ROUND_UP((EXT4_INODES_PER_GROUP(sb) -
+			    ext4_itable_unused_count(sb, gdp)),
+			    sbi->s_inodes_per_block);
+
+	if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) {
+		ext4_error(sb, "Something is wrong with group %u\n"
+			   "Used itable blocks: %d"
+			   "itable unused count: %u\n",
+			   group, used_blks,
+			   ext4_itable_unused_count(sb, gdp));
+		ret = 1;
+		goto out;
+	}
+
+	blk = ext4_inode_table(sb, gdp) + used_blks;
+	num = sbi->s_itb_per_group - used_blks;
+
+	BUFFER_TRACE(group_desc_bh, "get_write_access");
+	ret = ext4_journal_get_write_access(handle,
+					    group_desc_bh);
+	if (ret)
+		goto err_out;
+
+	/*
+	 * Skip zeroout if the inode table is full. But we set the ZEROED
+	 * flag anyway, because obviously, when it is full it does not need
+	 * further zeroing.
+	 */
+	if (unlikely(num == 0))
+		goto skip_zeroout;
+
+	ext4_debug("going to zero out inode table in group %d\n",
+		   group);
+	ret = sb_issue_zeroout(sb, blk, num, GFP_NOFS);
+	if (ret < 0)
+		goto err_out;
+	if (barrier)
+		blkdev_issue_flush(sb->s_bdev, GFP_NOFS, NULL);
+
+skip_zeroout:
+	ext4_lock_group(sb, group);
+	gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED);
+	gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
+	ext4_unlock_group(sb, group);
+
+	BUFFER_TRACE(group_desc_bh,
+		     "call ext4_handle_dirty_metadata");
+	ret = ext4_handle_dirty_metadata(handle, NULL,
+					 group_desc_bh);
+
+err_out:
+	up_write(&grp->alloc_sem);
+	ext4_journal_stop(handle);
+out:
+	return ret;
+}

fs/ext4/migrate.c

@@ -412,7 +412,7 @@ static int free_ext_idx(handle_t *handle, struct inode *inode,
 	struct buffer_head *bh;
 	struct ext4_extent_header *eh;
 
-	block = idx_pblock(ix);
+	block = ext4_idx_pblock(ix);
 	bh = sb_bread(inode->i_sb, block);
 	if (!bh)
 		return -EIO;

fs/ext4/move_extent.c

@@ -85,7 +85,7 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
 	if (EXT_LAST_EXTENT(path[ppos].p_hdr) > path[ppos].p_ext) {
 		/* leaf block */
 		*extent = ++path[ppos].p_ext;
-		path[ppos].p_block = ext_pblock(path[ppos].p_ext);
+		path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext);
 		return 0;
 	}
 
@@ -96,7 +96,7 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
 
 			/* index block */
 			path[ppos].p_idx++;
-			path[ppos].p_block = idx_pblock(path[ppos].p_idx);
+			path[ppos].p_block = ext4_idx_pblock(path[ppos].p_idx);
 			if (path[ppos+1].p_bh)
 				brelse(path[ppos+1].p_bh);
 			path[ppos+1].p_bh =
@@ -111,7 +111,7 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
 				path[cur_ppos].p_idx =
 					EXT_FIRST_INDEX(path[cur_ppos].p_hdr);
 				path[cur_ppos].p_block =
-					idx_pblock(path[cur_ppos].p_idx);
+					ext4_idx_pblock(path[cur_ppos].p_idx);
 				if (path[cur_ppos+1].p_bh)
 					brelse(path[cur_ppos+1].p_bh);
 				path[cur_ppos+1].p_bh = sb_bread(inode->i_sb,
@@ -133,7 +133,7 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path,
 			path[leaf_ppos].p_ext = *extent =
 				EXT_FIRST_EXTENT(path[leaf_ppos].p_hdr);
 			path[leaf_ppos].p_block =
-					ext_pblock(path[leaf_ppos].p_ext);
+					ext4_ext_pblock(path[leaf_ppos].p_ext);
 			return 0;
 		}
 	}
@@ -249,7 +249,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
 			 */
 			o_end->ee_block = end_ext->ee_block;
 			o_end->ee_len = end_ext->ee_len;
-			ext4_ext_store_pblock(o_end, ext_pblock(end_ext));
+			ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext));
 		}
 
 		o_start->ee_len = start_ext->ee_len;
@@ -276,7 +276,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode,
 		 */
 		o_end->ee_block = end_ext->ee_block;
 		o_end->ee_len = end_ext->ee_len;
-		ext4_ext_store_pblock(o_end, ext_pblock(end_ext));
+		ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext));
 
 		/*
 		 * Set 0 to the extent block if new_ext was
@@ -361,7 +361,7 @@ mext_insert_inside_block(struct ext4_extent *o_start,
 	/* Insert new entry */
 	if (new_ext->ee_len) {
 		o_start[i] = *new_ext;
-		ext4_ext_store_pblock(&o_start[i++], ext_pblock(new_ext));
+		ext4_ext_store_pblock(&o_start[i++], ext4_ext_pblock(new_ext));
 	}
 
 	/* Insert end entry */
@@ -488,7 +488,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
 	start_ext.ee_len = end_ext.ee_len = 0;
 
 	new_ext.ee_block = cpu_to_le32(*from);
-	ext4_ext_store_pblock(&new_ext, ext_pblock(dext));
+	ext4_ext_store_pblock(&new_ext, ext4_ext_pblock(dext));
 	new_ext.ee_len = dext->ee_len;
 	new_ext_alen = ext4_ext_get_actual_len(&new_ext);
 	new_ext_end = le32_to_cpu(new_ext.ee_block) + new_ext_alen - 1;
@@ -553,7 +553,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode,
 		copy_extent_status(oext, &end_ext);
 		end_ext_alen = ext4_ext_get_actual_len(&end_ext);
 		ext4_ext_store_pblock(&end_ext,
-			(ext_pblock(o_end) + oext_alen - end_ext_alen));
+			(ext4_ext_pblock(o_end) + oext_alen - end_ext_alen));
 		end_ext.ee_block =
 			cpu_to_le32(le32_to_cpu(o_end->ee_block) +
 			oext_alen - end_ext_alen);
@@ -604,7 +604,7 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext,
 	/* When tmp_dext is too large, pick up the target range. */
 	diff = donor_off - le32_to_cpu(tmp_dext->ee_block);
 
-	ext4_ext_store_pblock(tmp_dext, ext_pblock(tmp_dext) + diff);
+	ext4_ext_store_pblock(tmp_dext, ext4_ext_pblock(tmp_dext) + diff);
 	tmp_dext->ee_block =
 			cpu_to_le32(le32_to_cpu(tmp_dext->ee_block) + diff);
 	tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_dext->ee_len) - diff);
@@ -613,7 +613,7 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext,
 		tmp_dext->ee_len = cpu_to_le16(max_count);
 
 	orig_diff = orig_off - le32_to_cpu(tmp_oext->ee_block);
-	ext4_ext_store_pblock(tmp_oext, ext_pblock(tmp_oext) + orig_diff);
+	ext4_ext_store_pblock(tmp_oext, ext4_ext_pblock(tmp_oext) + orig_diff);
 
 	/* Adjust extent length if donor extent is larger than orig */
 	if (ext4_ext_get_actual_len(tmp_dext) >

fs/ext4/namei.c

@@ -856,6 +856,7 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
 	struct buffer_head *bh_use[NAMEI_RA_SIZE];
 	struct buffer_head *bh, *ret = NULL;
 	ext4_lblk_t start, block, b;
+	const u8 *name = d_name->name;
 	int ra_max = 0;		/* Number of bh's in the readahead
 				   buffer, bh_use[] */
 	int ra_ptr = 0;		/* Current index into readahead
@@ -870,6 +871,16 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
 	namelen = d_name->len;
 	if (namelen > EXT4_NAME_LEN)
 		return NULL;
+	if ((namelen <= 2) && (name[0] == '.') &&
+	    (name[1] == '.' || name[1] == '0')) {
+		/*
+		 * "." or ".." will only be in the first block
+		 * NFS may look up ".."; "." should be handled by the VFS
+		 */
+		block = start = 0;
+		nblocks = 1;
+		goto restart;
+	}
 	if (is_dx(dir)) {
 		bh = ext4_dx_find_entry(dir, d_name, res_dir, &err);
 		/*
@@ -960,55 +971,35 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
 static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct qstr *d_name,
 		       struct ext4_dir_entry_2 **res_dir, int *err)
 {
-	struct super_block * sb;
+	struct super_block * sb = dir->i_sb;
 	struct dx_hash_info	hinfo;
-	u32 hash;
 	struct dx_frame frames[2], *frame;
-	struct ext4_dir_entry_2 *de, *top;
 	struct buffer_head *bh;
 	ext4_lblk_t block;
 	int retval;
-	int namelen = d_name->len;
-	const u8 *name = d_name->name;
 
-	sb = dir->i_sb;
-	/* NFS may look up ".." - look at dx_root directory block */
-	if (namelen > 2 || name[0] != '.'||(name[1] != '.' && name[1] != '\0')){
-		if (!(frame = dx_probe(d_name, dir, &hinfo, frames, err)))
-			return NULL;
-	} else {
-		frame = frames;
-		frame->bh = NULL;			/* for dx_release() */
-		frame->at = (struct dx_entry *)frames;	/* hack for zero entry*/
-		dx_set_block(frame->at, 0);		/* dx_root block is 0 */
-	}
-	hash = hinfo.hash;
+	if (!(frame = dx_probe(d_name, dir, &hinfo, frames, err)))
+		return NULL;
 	do {
 		block = dx_get_block(frame->at);
-		if (!(bh = ext4_bread (NULL,dir, block, 0, err)))
+		if (!(bh = ext4_bread(NULL, dir, block, 0, err)))
 			goto errout;
-		de = (struct ext4_dir_entry_2 *) bh->b_data;
-		top = (struct ext4_dir_entry_2 *) ((char *) de + sb->s_blocksize -
-				       EXT4_DIR_REC_LEN(0));
-		for (; de < top; de = ext4_next_entry(de, sb->s_blocksize)) {
-			int off = (block << EXT4_BLOCK_SIZE_BITS(sb))
-				  + ((char *) de - bh->b_data);
-
-			if (!ext4_check_dir_entry(dir, de, bh, off)) {
-				brelse(bh);
-				*err = ERR_BAD_DX_DIR;
-				goto errout;
-			}
 
-			if (ext4_match(namelen, name, de)) {
-				*res_dir = de;
-				dx_release(frames);
-				return bh;
-			}
+		retval = search_dirblock(bh, dir, d_name,
+					 block << EXT4_BLOCK_SIZE_BITS(sb),
+					 res_dir);
+		if (retval == 1) { 	/* Success! */
+			dx_release(frames);
+			return bh;
 		}
 		brelse(bh);
+		if (retval == -1) {
+			*err = ERR_BAD_DX_DIR;
+			goto errout;
+		}
+
 		/* Check to see if we should continue to search */
-		retval = ext4_htree_next_block(dir, hash, frame,
+		retval = ext4_htree_next_block(dir, hinfo.hash, frame,
 					       frames, NULL);
 		if (retval < 0) {
 			ext4_warning(sb,

fs/ext4/page-io.c

+/*
+ * linux/fs/ext4/page-io.c
+ *
+ * This contains the new page_io functions for ext4
+ *
+ * Written by Theodore Ts'o, 2010.
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/jbd2.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/pagevec.h>
+#include <linux/mpage.h>
+#include <linux/namei.h>
+#include <linux/uio.h>
+#include <linux/bio.h>
+#include <linux/workqueue.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include "ext4_jbd2.h"
+#include "xattr.h"
+#include "acl.h"
+#include "ext4_extents.h"
+
+static struct kmem_cache *io_page_cachep, *io_end_cachep;
+
+int __init ext4_init_pageio(void)
+{
+	io_page_cachep = KMEM_CACHE(ext4_io_page, SLAB_RECLAIM_ACCOUNT);
+	if (io_page_cachep == NULL)
+		return -ENOMEM;
+	io_end_cachep = KMEM_CACHE(ext4_io_end, SLAB_RECLAIM_ACCOUNT);
+	if (io_page_cachep == NULL) {
+		kmem_cache_destroy(io_page_cachep);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void ext4_exit_pageio(void)
+{
+	kmem_cache_destroy(io_end_cachep);
+	kmem_cache_destroy(io_page_cachep);
+}
+
+void ext4_free_io_end(ext4_io_end_t *io)
+{
+	int i;
+
+	BUG_ON(!io);
+	if (io->page)
+		put_page(io->page);
+	for (i = 0; i < io->num_io_pages; i++) {
+		if (--io->pages[i]->p_count == 0) {
+			struct page *page = io->pages[i]->p_page;
+
+			end_page_writeback(page);
+			put_page(page);
+			kmem_cache_free(io_page_cachep, io->pages[i]);
+		}
+	}
+	io->num_io_pages = 0;
+	iput(io->inode);
+	kmem_cache_free(io_end_cachep, io);
+}
+
+/*
+ * check a range of space and convert unwritten extents to written.
+ */
+int ext4_end_io_nolock(ext4_io_end_t *io)
+{
+	struct inode *inode = io->inode;
+	loff_t offset = io->offset;
+	ssize_t size = io->size;
+	int ret = 0;
+
+	ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
+		   "list->prev 0x%p\n",
+		   io, inode->i_ino, io->list.next, io->list.prev);
+
+	if (list_empty(&io->list))
+		return ret;
+
+	if (!(io->flag & EXT4_IO_END_UNWRITTEN))
+		return ret;
+
+	ret = ext4_convert_unwritten_extents(inode, offset, size);
+	if (ret < 0) {
+		printk(KERN_EMERG "%s: failed to convert unwritten "
+			"extents to written extents, error is %d "
+			"io is still on inode %lu aio dio list\n",
+		       __func__, ret, inode->i_ino);
+		return ret;
+	}
+
+	if (io->iocb)
+		aio_complete(io->iocb, io->result, 0);
+	/* clear the DIO AIO unwritten flag */
+	io->flag &= ~EXT4_IO_END_UNWRITTEN;
+	return ret;
+}
+
+/*
+ * work on completed aio dio IO, to convert unwritten extents to extents
+ */
+static void ext4_end_io_work(struct work_struct *work)
+{
+	ext4_io_end_t		*io = container_of(work, ext4_io_end_t, work);
+	struct inode		*inode = io->inode;
+	struct ext4_inode_info	*ei = EXT4_I(inode);
+	unsigned long		flags;
+	int			ret;
+
+	mutex_lock(&inode->i_mutex);
+	ret = ext4_end_io_nolock(io);
+	if (ret < 0) {
+		mutex_unlock(&inode->i_mutex);
+		return;
+	}
+
+	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+	if (!list_empty(&io->list))
+		list_del_init(&io->list);
+	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
+	mutex_unlock(&inode->i_mutex);
+	ext4_free_io_end(io);
+}
+
+ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
+{
+	ext4_io_end_t *io = NULL;
+
+	io = kmem_cache_alloc(io_end_cachep, flags);
+	if (io) {
+		memset(io, 0, sizeof(*io));
+		io->inode = igrab(inode);
+		BUG_ON(!io->inode);
+		INIT_WORK(&io->work, ext4_end_io_work);
+		INIT_LIST_HEAD(&io->list);
+	}
+	return io;
+}
+
+/*
+ * Print an buffer I/O error compatible with the fs/buffer.c.  This
+ * provides compatibility with dmesg scrapers that look for a specific
+ * buffer I/O error message.  We really need a unified error reporting
+ * structure to userspace ala Digital Unix's uerf system, but it's
+ * probably not going to happen in my lifetime, due to LKML politics...
+ */
+static void buffer_io_error(struct buffer_head *bh)
+{
+	char b[BDEVNAME_SIZE];
+	printk(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n",
+			bdevname(bh->b_bdev, b),
+			(unsigned long long)bh->b_blocknr);
+}
+
+static void ext4_end_bio(struct bio *bio, int error)
+{
+	ext4_io_end_t *io_end = bio->bi_private;
+	struct workqueue_struct *wq;
+	struct inode *inode;
+	unsigned long flags;
+	ext4_fsblk_t err_block;
+	int i;
+
+	BUG_ON(!io_end);
+	inode = io_end->inode;
+	bio->bi_private = NULL;
+	bio->bi_end_io = NULL;
+	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
+		error = 0;
+	err_block = bio->bi_sector >> (inode->i_blkbits - 9);
+	bio_put(bio);
+
+	if (!(inode->i_sb->s_flags & MS_ACTIVE)) {
+		pr_err("sb umounted, discard end_io request for inode %lu\n",
+			io_end->inode->i_ino);
+		ext4_free_io_end(io_end);
+		return;
+	}
+
+	if (error) {
+		io_end->flag |= EXT4_IO_END_ERROR;
+		ext4_warning(inode->i_sb, "I/O error writing to inode %lu "
+			     "(offset %llu size %ld starting block %llu)",
+			     inode->i_ino,
+			     (unsigned long long) io_end->offset,
+			     (long) io_end->size,
+			     (unsigned long long) err_block);
+	}
+
+	for (i = 0; i < io_end->num_io_pages; i++) {
+		struct page *page = io_end->pages[i]->p_page;
+		struct buffer_head *bh, *head;
+		int partial_write = 0;
+
+		head = page_buffers(page);
+		if (error)
+			SetPageError(page);
+		BUG_ON(!head);
+		if (head->b_size == PAGE_CACHE_SIZE)
+			clear_buffer_dirty(head);
+		else {
+			loff_t offset;
+			loff_t io_end_offset = io_end->offset + io_end->size;
+
+			offset = (sector_t) page->index << PAGE_CACHE_SHIFT;
+			bh = head;
+			do {
+				if ((offset >= io_end->offset) &&
+				    (offset+bh->b_size <= io_end_offset)) {
+					if (error)
+						buffer_io_error(bh);
+
+					clear_buffer_dirty(bh);
+				}
+				if (buffer_delay(bh))
+					partial_write = 1;
+				else if (!buffer_mapped(bh))
+					clear_buffer_dirty(bh);
+				else if (buffer_dirty(bh))
+					partial_write = 1;
+				offset += bh->b_size;
+				bh = bh->b_this_page;
+			} while (bh != head);
+		}
+
+		if (--io_end->pages[i]->p_count == 0) {
+			struct page *page = io_end->pages[i]->p_page;
+
+			end_page_writeback(page);
+			put_page(page);
+			kmem_cache_free(io_page_cachep, io_end->pages[i]);
+		}
+
+		/*
+		 * If this is a partial write which happened to make
+		 * all buffers uptodate then we can optimize away a
+		 * bogus readpage() for the next read(). Here we
+		 * 'discover' whether the page went uptodate as a
+		 * result of this (potentially partial) write.
+		 */
+		if (!partial_write)
+			SetPageUptodate(page);
+	}
+
+	io_end->num_io_pages = 0;
+
+	/* Add the io_end to per-inode completed io list*/
+	spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
+	list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list);
+	spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags);
+
+	wq = EXT4_SB(inode->i_sb)->dio_unwritten_wq;
+	/* queue the work to convert unwritten extents to written */
+	queue_work(wq, &io_end->work);
+}
+
+void ext4_io_submit(struct ext4_io_submit *io)
+{
+	struct bio *bio = io->io_bio;
+
+	if (bio) {
+		bio_get(io->io_bio);
+		submit_bio(io->io_op, io->io_bio);
+		BUG_ON(bio_flagged(io->io_bio, BIO_EOPNOTSUPP));
+		bio_put(io->io_bio);
+	}
+	io->io_bio = 0;
+	io->io_op = 0;
+	io->io_end = 0;
+}
+
+static int io_submit_init(struct ext4_io_submit *io,
+			  struct inode *inode,
+			  struct writeback_control *wbc,
+			  struct buffer_head *bh)
+{
+	ext4_io_end_t *io_end;
+	struct page *page = bh->b_page;
+	int nvecs = bio_get_nr_vecs(bh->b_bdev);
+	struct bio *bio;
+
+	io_end = ext4_init_io_end(inode, GFP_NOFS);
+	if (!io_end)
+		return -ENOMEM;
+	do {
+		bio = bio_alloc(GFP_NOIO, nvecs);
+		nvecs >>= 1;
+	} while (bio == NULL);
+
+	bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+	bio->bi_bdev = bh->b_bdev;
+	bio->bi_private = io->io_end = io_end;
+	bio->bi_end_io = ext4_end_bio;
+
+	io_end->inode = inode;
+	io_end->offset = (page->index << PAGE_CACHE_SHIFT) + bh_offset(bh);
+
+	io->io_bio = bio;
+	io->io_op = (wbc->sync_mode == WB_SYNC_ALL ?
+			WRITE_SYNC_PLUG : WRITE);
+	io->io_next_block = bh->b_blocknr;
+	return 0;
+}
+
+static int io_submit_add_bh(struct ext4_io_submit *io,
+			    struct ext4_io_page *io_page,
+			    struct inode *inode,
+			    struct writeback_control *wbc,
+			    struct buffer_head *bh)
+{
+	ext4_io_end_t *io_end;
+	int ret;
+
+	if (buffer_new(bh)) {
+		clear_buffer_new(bh);
+		unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
+	}
+
+	if (!buffer_mapped(bh) || buffer_delay(bh)) {
+		if (!buffer_mapped(bh))
+			clear_buffer_dirty(bh);
+		if (io->io_bio)
+			ext4_io_submit(io);
+		return 0;
+	}
+
+	if (io->io_bio && bh->b_blocknr != io->io_next_block) {
+submit_and_retry:
+		ext4_io_submit(io);
+	}
+	if (io->io_bio == NULL) {
+		ret = io_submit_init(io, inode, wbc, bh);
+		if (ret)
+			return ret;
+	}
+	io_end = io->io_end;
+	if ((io_end->num_io_pages >= MAX_IO_PAGES) &&
+	    (io_end->pages[io_end->num_io_pages-1] != io_page))
+		goto submit_and_retry;
+	if (buffer_uninit(bh))
+		io->io_end->flag |= EXT4_IO_END_UNWRITTEN;
+	io->io_end->size += bh->b_size;
+	io->io_next_block++;
+	ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
+	if (ret != bh->b_size)
+		goto submit_and_retry;
+	if ((io_end->num_io_pages == 0) ||
+	    (io_end->pages[io_end->num_io_pages-1] != io_page)) {
+		io_end->pages[io_end->num_io_pages++] = io_page;
+		io_page->p_count++;
+	}
+	return 0;
+}
+
+int ext4_bio_write_page(struct ext4_io_submit *io,
+			struct page *page,
+			int len,
+			struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	unsigned block_start, block_end, blocksize;
+	struct ext4_io_page *io_page;
+	struct buffer_head *bh, *head;
+	int ret = 0;
+
+	blocksize = 1 << inode->i_blkbits;
+
+	BUG_ON(PageWriteback(page));
+	set_page_writeback(page);
+	ClearPageError(page);
+
+	io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
+	if (!io_page) {
+		set_page_dirty(page);
+		unlock_page(page);
+		return -ENOMEM;
+	}
+	io_page->p_page = page;
+	io_page->p_count = 0;
+	get_page(page);
+
+	for (bh = head = page_buffers(page), block_start = 0;
+	     bh != head || !block_start;
+	     block_start = block_end, bh = bh->b_this_page) {
+		block_end = block_start + blocksize;
+		if (block_start >= len) {
+			clear_buffer_dirty(bh);
+			set_buffer_uptodate(bh);
+			continue;
+		}
+		ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
+		if (ret) {
+			/*
+			 * We only get here on ENOMEM.  Not much else
+			 * we can do but mark the page as dirty, and
+			 * better luck next time.
+			 */
+			set_page_dirty(page);
+			break;
+		}
+	}
+	unlock_page(page);
+	/*
+	 * If the page was truncated before we could do the writeback,
+	 * or we had a memory allocation error while trying to write
+	 * the first buffer head, we won't have submitted any pages for
+	 * I/O.  In that case we need to make sure we've cleared the
+	 * PageWriteback bit from the page to prevent the system from
+	 * wedging later on.
+	 */
+	if (io_page->p_count == 0) {
+		put_page(page);
+		end_page_writeback(page);
+		kmem_cache_free(io_page_cachep, io_page);
+	}
+	return ret;
+}

fs/ext4/resize.c

@@ -226,23 +226,13 @@ static int setup_new_group_blocks(struct super_block *sb,
 	}
 
 	/* Zero out all of the reserved backup group descriptor table blocks */
-	for (i = 0, bit = gdblocks + 1, block = start + bit;
-	     i < reserved_gdb; i++, block++, bit++) {
-		struct buffer_head *gdb;
-
-		ext4_debug("clear reserved block %#04llx (+%d)\n", block, bit);
-
-		if ((err = extend_or_restart_transaction(handle, 1, bh)))
-			goto exit_bh;
+	ext4_debug("clear inode table blocks %#04llx -> %#04llx\n",
+			block, sbi->s_itb_per_group);
+	err = sb_issue_zeroout(sb, gdblocks + start + 1, reserved_gdb,
+			       GFP_NOFS);
+	if (err)
+		goto exit_bh;
 
-		if (IS_ERR(gdb = bclean(handle, sb, block))) {
-			err = PTR_ERR(gdb);
-			goto exit_bh;
-		}
-		ext4_handle_dirty_metadata(handle, NULL, gdb);
-		ext4_set_bit(bit, bh->b_data);
-		brelse(gdb);
-	}
 	ext4_debug("mark block bitmap %#04llx (+%llu)\n", input->block_bitmap,
 		   input->block_bitmap - start);
 	ext4_set_bit(input->block_bitmap - start, bh->b_data);
@@ -251,28 +241,18 @@ static int setup_new_group_blocks(struct super_block *sb,
 	ext4_set_bit(input->inode_bitmap - start, bh->b_data);
 
 	/* Zero out all of the inode table blocks */
-	for (i = 0, block = input->inode_table, bit = block - start;
-	     i < sbi->s_itb_per_group; i++, bit++, block++) {
-		struct buffer_head *it;
-
-		ext4_debug("clear inode block %#04llx (+%d)\n", block, bit);
-
-		if ((err = extend_or_restart_transaction(handle, 1, bh)))
-			goto exit_bh;
-
-		if (IS_ERR(it = bclean(handle, sb, block))) {
-			err = PTR_ERR(it);
-			goto exit_bh;
-		}
-		ext4_handle_dirty_metadata(handle, NULL, it);
-		brelse(it);
-		ext4_set_bit(bit, bh->b_data);
-	}
+	block = input->inode_table;
+	ext4_debug("clear inode table blocks %#04llx -> %#04llx\n",
+			block, sbi->s_itb_per_group);
+	err = sb_issue_zeroout(sb, block, sbi->s_itb_per_group, GFP_NOFS);
+	if (err)
+		goto exit_bh;
 
 	if ((err = extend_or_restart_transaction(handle, 2, bh)))
 		goto exit_bh;
 
-	mark_bitmap_end(input->blocks_count, sb->s_blocksize * 8, bh->b_data);
+	ext4_mark_bitmap_end(input->blocks_count, sb->s_blocksize * 8,
+			     bh->b_data);
 	ext4_handle_dirty_metadata(handle, NULL, bh);
 	brelse(bh);
 	/* Mark unused entries in inode bitmap used */
@@ -283,8 +263,8 @@ static int setup_new_group_blocks(struct super_block *sb,
 		goto exit_journal;
 	}
 
-	mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
-			bh->b_data);
+	ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
+			     bh->b_data);
 	ext4_handle_dirty_metadata(handle, NULL, bh);
 exit_bh:
 	brelse(bh);

fs/ext4/xattr.c

@@ -1588,7 +1588,7 @@ static void ext4_xattr_rehash(struct ext4_xattr_header *header,
 #undef BLOCK_HASH_SHIFT
 
 int __init
-init_ext4_xattr(void)
+ext4_init_xattr(void)
 {
 	ext4_xattr_cache = mb_cache_create("ext4_xattr", 6);
 	if (!ext4_xattr_cache)
@@ -1597,7 +1597,7 @@ init_ext4_xattr(void)
 }
 
 void
-exit_ext4_xattr(void)
+ext4_exit_xattr(void)
 {
 	if (ext4_xattr_cache)
 		mb_cache_destroy(ext4_xattr_cache);

fs/ext4/xattr.h

@@ -83,8 +83,8 @@ extern void ext4_xattr_put_super(struct super_block *);
 extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 			    struct ext4_inode *raw_inode, handle_t *handle);
 
-extern int init_ext4_xattr(void);
-extern void exit_ext4_xattr(void);
+extern int __init ext4_init_xattr(void);
+extern void ext4_exit_xattr(void);
 
 extern const struct xattr_handler *ext4_xattr_handlers[];
 
@@ -121,14 +121,14 @@ ext4_xattr_put_super(struct super_block *sb)
 {
 }
 
-static inline int
+static __init inline int
 init_ext4_xattr(void)
 {
 	return 0;
 }
 
 static inline void
-exit_ext4_xattr(void)
+ext4_exit_xattr(void)
 {
 }
 

fs/ioctl.c

@@ -530,6 +530,41 @@ static int ioctl_fsthaw(struct file *filp)
 	return thaw_super(sb);
 }
 
+static int ioctl_fstrim(struct file *filp, void __user *argp)
+{
+	struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;
+	struct fstrim_range range;
+	int ret = 0;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* If filesystem doesn't support trim feature, return. */
+	if (sb->s_op->trim_fs == NULL)
+		return -EOPNOTSUPP;
+
+	/* If a blockdevice-backed filesystem isn't specified, return EINVAL. */
+	if (sb->s_bdev == NULL)
+		return -EINVAL;
+
+	if (argp == NULL) {
+		range.start = 0;
+		range.len = ULLONG_MAX;
+		range.minlen = 0;
+	} else if (copy_from_user(&range, argp, sizeof(range)))
+		return -EFAULT;
+
+	ret = sb->s_op->trim_fs(sb, &range);
+	if (ret < 0)
+		return ret;
+
+	if ((argp != NULL) &&
+	    (copy_to_user(argp, &range, sizeof(range))))
+		return -EFAULT;
+
+	return 0;
+}
+
 /*
  * When you add any new common ioctls to the switches above and below
  * please update compat_sys_ioctl() too.
@@ -580,6 +615,10 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
 		error = ioctl_fsthaw(filp);
 		break;
 
+	case FITRIM:
+		error = ioctl_fstrim(filp, argp);
+		break;
+
 	case FS_IOC_FIEMAP:
 		return ioctl_fiemap(filp, arg);
 

fs/jbd2/checkpoint.c

@@ -299,6 +299,16 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 		transaction->t_chp_stats.cs_forced_to_close++;
 		spin_unlock(&journal->j_list_lock);
 		jbd_unlock_bh_state(bh);
+		if (unlikely(journal->j_flags & JBD2_UNMOUNT))
+			/*
+			 * The journal thread is dead; so starting and
+			 * waiting for a commit to finish will cause
+			 * us to wait for a _very_ long time.
+			 */
+			printk(KERN_ERR "JBD2: %s: "
+			       "Waiting for Godot: block %llu\n",
+			       journal->j_devname,
+			       (unsigned long long) bh->b_blocknr);
 		jbd2_log_start_commit(journal, tid);
 		jbd2_log_wait_commit(journal, tid);
 		ret = 1;

fs/jbd2/commit.c

@@ -26,7 +26,9 @@
 #include <linux/backing-dev.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/bitops.h>
 #include <trace/events/jbd2.h>
+#include <asm/system.h>
 
 /*
  * Default IO end handler for temporary BJ_IO buffer_heads.
@@ -201,7 +203,7 @@ static int journal_submit_data_buffers(journal_t *journal,
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
 		mapping = jinode->i_vfs_inode->i_mapping;
-		jinode->i_flags |= JI_COMMIT_RUNNING;
+		set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
 		spin_unlock(&journal->j_list_lock);
 		/*
 		 * submit the inode data buffers. We use writepage
@@ -216,7 +218,8 @@ static int journal_submit_data_buffers(journal_t *journal,
 		spin_lock(&journal->j_list_lock);
 		J_ASSERT(jinode->i_transaction == commit_transaction);
 		commit_transaction->t_flushed_data_blocks = 1;
-		jinode->i_flags &= ~JI_COMMIT_RUNNING;
+		clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
+		smp_mb__after_clear_bit();
 		wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
 	}
 	spin_unlock(&journal->j_list_lock);
@@ -237,7 +240,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 	/* For locking, see the comment in journal_submit_data_buffers() */
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
-		jinode->i_flags |= JI_COMMIT_RUNNING;
+		set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
 		spin_unlock(&journal->j_list_lock);
 		err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping);
 		if (err) {
@@ -253,7 +256,8 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 				ret = err;
 		}
 		spin_lock(&journal->j_list_lock);
-		jinode->i_flags &= ~JI_COMMIT_RUNNING;
+		clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
+		smp_mb__after_clear_bit();
 		wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
 	}
 

fs/jbd2/journal.c

@@ -42,12 +42,14 @@
 #include <linux/log2.h>
 #include <linux/vmalloc.h>
 #include <linux/backing-dev.h>
+#include <linux/bitops.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/jbd2.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
+#include <asm/system.h>
 
 EXPORT_SYMBOL(jbd2_journal_extend);
 EXPORT_SYMBOL(jbd2_journal_stop);
@@ -2210,7 +2212,7 @@ void jbd2_journal_release_jbd_inode(journal_t *journal,
 restart:
 	spin_lock(&journal->j_list_lock);
 	/* Is commit writing out inode - we have to wait */
-	if (jinode->i_flags & JI_COMMIT_RUNNING) {
+	if (test_bit(__JI_COMMIT_RUNNING, &jinode->i_flags)) {
 		wait_queue_head_t *wq;
 		DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING);
 		wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING);

fs/jbd2/transaction.c

@@ -156,6 +156,7 @@ static int start_this_handle(journal_t *journal, handle_t *handle,
 	 */
 repeat:
 	read_lock(&journal->j_state_lock);
+	BUG_ON(journal->j_flags & JBD2_UNMOUNT);
 	if (is_journal_aborted(journal) ||
 	    (journal->j_errno != 0 && !(journal->j_flags & JBD2_ACK_ERR))) {
 		read_unlock(&journal->j_state_lock);

include/linux/blkdev.h

@@ -891,6 +891,14 @@ static inline int sb_issue_discard(struct super_block *sb, sector_t block,
 				    nr_blocks << (sb->s_blocksize_bits - 9),
 				    gfp_mask, flags);
 }
+static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
+		sector_t nr_blocks, gfp_t gfp_mask)
+{
+	return blkdev_issue_zeroout(sb->s_bdev,
+				    block << (sb->s_blocksize_bits - 9),
+				    nr_blocks << (sb->s_blocksize_bits - 9),
+				    gfp_mask);
+}
 
 extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
 

include/linux/fs.h

@@ -32,6 +32,12 @@
 #define SEEK_END	2	/* seek relative to end of file */
 #define SEEK_MAX	SEEK_END
 
+struct fstrim_range {
+	uint64_t start;
+	uint64_t len;
+	uint64_t minlen;
+};
+
 /* And dynamically-tunable limits and defaults: */
 struct files_stat_struct {
 	unsigned long nr_files;		/* read only */
@@ -317,6 +323,7 @@ struct inodes_stat_t {
 #define FIGETBSZ   _IO(0x00,2)	/* get the block size used for bmap */
 #define FIFREEZE	_IOWR('X', 119, int)	/* Freeze */
 #define FITHAW		_IOWR('X', 120, int)	/* Thaw */
+#define FITRIM		_IOWR('X', 121, struct fstrim_range)	/* Trim */
 
 #define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
 #define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
@@ -1604,6 +1611,7 @@ struct super_operations {
 	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
 #endif
 	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
+	int (*trim_fs) (struct super_block *, struct fstrim_range *);
 };
 
 /*

include/linux/jbd2.h

@@ -395,7 +395,7 @@ struct jbd2_inode {
 	struct inode *i_vfs_inode;
 
 	/* Flags of inode [j_list_lock] */
-	unsigned int i_flags;
+	unsigned long i_flags;
 };
 
 struct jbd2_revoke_table_s;

include/linux/percpu_counter.h

@@ -78,6 +78,11 @@ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc)
 	return 1;
 }
 
+static inline int percpu_counter_initialized(struct percpu_counter *fbc)
+{
+	return (fbc->counters != NULL);
+}
+
 #else
 
 struct percpu_counter {
@@ -143,6 +148,11 @@ static inline s64 percpu_counter_sum(struct percpu_counter *fbc)
 	return percpu_counter_read(fbc);
 }
 
+static inline int percpu_counter_initialized(struct percpu_counter *fbc)
+{
+	return 1;
+}
+
 #endif	/* CONFIG_SMP */
 
 static inline void percpu_counter_inc(struct percpu_counter *fbc)

include/linux/writeback.h

@@ -141,6 +141,8 @@ typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc,
 
 int generic_writepages(struct address_space *mapping,
 		       struct writeback_control *wbc);
+void tag_pages_for_writeback(struct address_space *mapping,
+			     pgoff_t start, pgoff_t end);
 int write_cache_pages(struct address_space *mapping,
 		      struct writeback_control *wbc, writepage_t writepage,
 		      void *data);