Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 update from Ted Ts'o:
 "Lots of bug fixes, cleanups and optimizations.  In the bug fixes
  category, of note is a fix for on-line resizing file systems where the
  block size is smaller than the page size (i.e., file systems 1k blocks
  on x86, or more interestingly file systems with 4k blocks on Power or
  ia64 systems.)

  In the cleanup category, the ext4's punch hole implementation was
  significantly improved by Lukas Czerner, and now supports bigalloc
  file systems.  In addition, Jan Kara significantly cleaned up the
  write submission code path.  We also improved error checking and added
  a few sanity checks.

  In the optimizations category, two major optimizations deserve
  mention.  The first is that ext4_writepages() is now used for
  nodelalloc and ext3 compatibility mode.  This allows writes to be
  submitted much more efficiently as a single bio request, instead of
  being sent as individual 4k writes into the block layer (which then
  relied on the elevator code to coalesce the requests in the block
  queue).  Secondly, the extent cache shrink mechanism, which was
  introduce in 3.9, no longer has a scalability bottleneck caused by the
  i_es_lru spinlock.  Other optimizations include some changes to reduce
  CPU usage and to avoid issuing empty commits unnecessarily."

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (86 commits)
  ext4: optimize starting extent in ext4_ext_rm_leaf()
  jbd2: invalidate handle if jbd2_journal_restart() fails
  ext4: translate flag bits to strings in tracepoints
  ext4: fix up error handling for mpage_map_and_submit_extent()
  jbd2: fix theoretical race in jbd2__journal_restart
  ext4: only zero partial blocks in ext4_zero_partial_blocks()
  ext4: check error return from ext4_write_inline_data_end()
  ext4: delete unnecessary C statements
  ext3,ext4: don't mess with dir_file->f_pos in htree_dirblock_to_tree()
  jbd2: move superblock checksum calculation to jbd2_write_superblock()
  ext4: pass inode pointer instead of file pointer to punch hole
  ext4: improve free space calculation for inline_data
  ext4: reduce object size when !CONFIG_PRINTK
  ext4: improve extent cache shrink mechanism to avoid to burn CPU time
  ext4: implement error handling of ext4_mb_new_preallocation()
  ext4: fix corruption when online resizing a fs with 1K block size
  ext4: delete unused variables
  ext4: return FIEMAP_EXTENT_UNKNOWN for delalloc extents
  jbd2: remove debug dependency on debug_fs and update Kconfig help text
  jbd2: use a single printk for jbd_debug()
  ...

1 files changed, 122 insertions, 65 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 4af03ea84aa3..b577e45425b0 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -177,38 +177,28 @@ struct ext4_map_blocks {
 };
 
 /*
- * For delayed allocation tracking
- */
-struct mpage_da_data {
-	struct inode *inode;
-	sector_t b_blocknr;		/* start block number of extent */
-	size_t b_size;			/* size of extent */
-	unsigned long b_state;		/* state of the extent */
-	unsigned long first_page, next_page;	/* extent of pages */
-	struct writeback_control *wbc;
-	int io_done;
-	int pages_written;
-	int retval;
-};
-
-/*
  * Flags for ext4_io_end->flags
  */
 #define	EXT4_IO_END_UNWRITTEN	0x0001
-#define EXT4_IO_END_ERROR	0x0002
-#define EXT4_IO_END_DIRECT	0x0004
+#define EXT4_IO_END_DIRECT	0x0002
 
 /*
- * For converting uninitialized extents on a work queue.
+ * For converting uninitialized extents on a work queue. 'handle' is used for
+ * buffered writeback.
  */
 typedef struct ext4_io_end {
 	struct list_head	list;		/* per-file finished IO list */
+	handle_t		*handle;	/* handle reserved for extent
+						 * conversion */
 	struct inode		*inode;		/* file being written to */
+	struct bio		*bio;		/* Linked list of completed
+						 * bios covering the extent */
 	unsigned int		flag;		/* unwritten or not */
 	loff_t			offset;		/* offset in the file */
 	ssize_t			size;		/* size of the extent */
 	struct kiocb		*iocb;		/* iocb struct for AIO */
 	int			result;		/* error value for AIO */
+	atomic_t		count;		/* reference counter */
 } ext4_io_end_t;
 
 struct ext4_io_submit {
@@ -581,11 +571,6 @@ enum {
 #define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER	0x0020
 
 /*
- * Flags used by ext4_discard_partial_page_buffers
- */
-#define EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED	0x0001
-
-/*
  * ioctl commands
  */
 #define	EXT4_IOC_GETFLAGS		FS_IOC_GETFLAGS
@@ -879,6 +864,7 @@ struct ext4_inode_info {
 	rwlock_t i_es_lock;
 	struct list_head i_es_lru;
 	unsigned int i_es_lru_nr;	/* protected by i_es_lock */
+	unsigned long i_touch_when;	/* jiffies of last accessing */
 
 	/* ialloc */
 	ext4_group_t	i_last_alloc_group;
@@ -903,12 +889,22 @@ struct ext4_inode_info {
 	qsize_t i_reserved_quota;
 #endif
 
-	/* completed IOs that might need unwritten extents handling */
-	struct list_head i_completed_io_list;
+	/* Lock protecting lists below */
 	spinlock_t i_completed_io_lock;
+	/*
+	 * Completed IOs that need unwritten extents handling and have
+	 * transaction reserved
+	 */
+	struct list_head i_rsv_conversion_list;
+	/*
+	 * Completed IOs that need unwritten extents handling and don't have
+	 * transaction reserved
+	 */
+	struct list_head i_unrsv_conversion_list;
 	atomic_t i_ioend_count;	/* Number of outstanding io_end structs */
 	atomic_t i_unwritten; /* Nr. of inflight conversions pending */
-	struct work_struct i_unwritten_work;	/* deferred extent conversion */
+	struct work_struct i_rsv_conversion_work;
+	struct work_struct i_unrsv_conversion_work;
 
 	spinlock_t i_block_reservation_lock;
 
@@ -1245,7 +1241,6 @@ struct ext4_sb_info {
 	unsigned int s_mb_stats;
 	unsigned int s_mb_order2_reqs;
 	unsigned int s_mb_group_prealloc;
-	unsigned int s_max_writeback_mb_bump;
 	unsigned int s_max_dir_size_kb;
 	/* where last allocation was done - for stream allocation */
 	unsigned long s_mb_last_group;
@@ -1281,8 +1276,10 @@ struct ext4_sb_info {
 	struct flex_groups *s_flex_groups;
 	ext4_group_t s_flex_groups_allocated;
 
-	/* workqueue for dio unwritten */
-	struct workqueue_struct *dio_unwritten_wq;
+	/* workqueue for unreserved extent convertions (dio) */
+	struct workqueue_struct *unrsv_conversion_wq;
+	/* workqueue for reserved extent conversions (buffered io) */
+	struct workqueue_struct *rsv_conversion_wq;
 
 	/* timer for periodic error stats printing */
 	struct timer_list s_err_report;
@@ -1307,6 +1304,7 @@ struct ext4_sb_info {
 	/* Reclaim extents from extent status tree */
 	struct shrinker s_es_shrinker;
 	struct list_head s_es_lru;
+	unsigned long s_es_last_sorted;
 	struct percpu_counter s_extent_cache_cnt;
 	spinlock_t s_es_lru_lock ____cacheline_aligned_in_smp;
 };
@@ -1342,6 +1340,9 @@ static inline void ext4_set_io_unwritten_flag(struct inode *inode,
 					      struct ext4_io_end *io_end)
 {
 	if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+		/* Writeback has to have coversion transaction reserved */
+		WARN_ON(EXT4_SB(inode->i_sb)->s_journal && !io_end->handle &&
+			!(io_end->flag & EXT4_IO_END_DIRECT));
 		io_end->flag |= EXT4_IO_END_UNWRITTEN;
 		atomic_inc(&EXT4_I(inode)->i_unwritten);
 	}
@@ -1999,7 +2000,6 @@ static inline  unsigned char get_dtype(struct super_block *sb, int filetype)
 
 /* fsync.c */
 extern int ext4_sync_file(struct file *, loff_t, loff_t, int);
-extern int ext4_flush_unwritten_io(struct inode *);
 
 /* hash.c */
 extern int ext4fs_dirhash(const char *name, int len, struct
@@ -2088,7 +2088,7 @@ 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_punch_hole(struct inode *inode, 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 *);
@@ -2096,9 +2096,12 @@ 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_chunk_trans_blocks(struct inode *, int nrblocks);
-extern int ext4_discard_partial_page_buffers(handle_t *handle,
-		struct address_space *mapping, loff_t from,
-		loff_t length, int flags);
+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_zero_partial_blocks(handle_t *handle, struct inode *inode,
+			     loff_t lstart, loff_t lend);
 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,
@@ -2111,7 +2114,7 @@ extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 				const struct iovec *iov, loff_t offset,
 				unsigned long nr_segs);
 extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
-extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk);
+extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
 extern void ext4_ind_truncate(handle_t *, struct inode *inode);
 extern int ext4_free_hole_blocks(handle_t *handle, struct inode *inode,
 				 ext4_lblk_t first, ext4_lblk_t stop);
@@ -2166,42 +2169,96 @@ extern int ext4_alloc_flex_bg_array(struct super_block *sb,
 				    ext4_group_t ngroup);
 extern const char *ext4_decode_error(struct super_block *sb, int errno,
 				     char nbuf[16]);
+
 extern __printf(4, 5)
 void __ext4_error(struct super_block *, const char *, unsigned int,
 		  const char *, ...);
-#define ext4_error(sb, message...)	__ext4_error(sb, __func__,	\
-						     __LINE__, ## message)
 extern __printf(5, 6)
-void ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t,
+void __ext4_error_inode(struct inode *, const char *, unsigned int, ext4_fsblk_t,
 		      const char *, ...);
 extern __printf(5, 6)
-void ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
+void __ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
 		     const char *, ...);
 extern void __ext4_std_error(struct super_block *, const char *,
 			     unsigned int, int);
 extern __printf(4, 5)
 void __ext4_abort(struct super_block *, const char *, unsigned int,
 		  const char *, ...);
-#define ext4_abort(sb, message...)	__ext4_abort(sb, __func__, \
-						       __LINE__, ## message)
 extern __printf(4, 5)
 void __ext4_warning(struct super_block *, const char *, unsigned int,
 		    const char *, ...);
-#define ext4_warning(sb, message...)	__ext4_warning(sb, __func__, \
-						       __LINE__, ## message)
 extern __printf(3, 4)
-void ext4_msg(struct super_block *, const char *, const char *, ...);
+void __ext4_msg(struct super_block *, const char *, const char *, ...);
 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 __printf(7, 8)
 void __ext4_grp_locked_error(const char *, unsigned int,
 			     struct super_block *, ext4_group_t,
 			     unsigned long, ext4_fsblk_t,
 			     const char *, ...);
-#define ext4_grp_locked_error(sb, grp, message...) \
-	__ext4_grp_locked_error(__func__, __LINE__, (sb), (grp), ## message)
+
+#ifdef CONFIG_PRINTK
+
+#define ext4_error_inode(inode, func, line, block, fmt, ...)		\
+	__ext4_error_inode(inode, func, line, block, fmt, ##__VA_ARGS__)
+#define ext4_error_file(file, func, line, block, fmt, ...)		\
+	__ext4_error_file(file, func, line, block, fmt, ##__VA_ARGS__)
+#define ext4_error(sb, fmt, ...)					\
+	__ext4_error(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
+#define ext4_abort(sb, fmt, ...)					\
+	__ext4_abort(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
+#define ext4_warning(sb, fmt, ...)					\
+	__ext4_warning(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
+#define ext4_msg(sb, level, fmt, ...)				\
+	__ext4_msg(sb, level, fmt, ##__VA_ARGS__)
+#define dump_mmp_msg(sb, mmp, msg)					\
+	__dump_mmp_msg(sb, mmp, __func__, __LINE__, msg)
+#define ext4_grp_locked_error(sb, grp, ino, block, fmt, ...)		\
+	__ext4_grp_locked_error(__func__, __LINE__, sb, grp, ino, block, \
+				fmt, ##__VA_ARGS__)
+
+#else
+
+#define ext4_error_inode(inode, func, line, block, fmt, ...)		\
+do {									\
+	no_printk(fmt, ##__VA_ARGS__);					\
+	__ext4_error_inode(inode, "", 0, block, " ");			\
+} while (0)
+#define ext4_error_file(file, func, line, block, fmt, ...)		\
+do {									\
+	no_printk(fmt, ##__VA_ARGS__);					\
+	__ext4_error_file(file, "", 0, block, " ");			\
+} while (0)
+#define ext4_error(sb, fmt, ...)					\
+do {									\
+	no_printk(fmt, ##__VA_ARGS__);					\
+	__ext4_error(sb, "", 0, " ");					\
+} while (0)
+#define ext4_abort(sb, fmt, ...)					\
+do {									\
+	no_printk(fmt, ##__VA_ARGS__);					\
+	__ext4_abort(sb, "", 0, " ");					\
+} while (0)
+#define ext4_warning(sb, fmt, ...)					\
+do {									\
+	no_printk(fmt, ##__VA_ARGS__);					\
+	__ext4_warning(sb, "", 0, " ");					\
+} while (0)
+#define ext4_msg(sb, level, fmt, ...)					\
+do {									\
+	no_printk(fmt, ##__VA_ARGS__);					\
+	__ext4_msg(sb, "", " ");					\
+} while (0)
+#define dump_mmp_msg(sb, mmp, msg)					\
+	__dump_mmp_msg(sb, mmp, "", 0, "")
+#define ext4_grp_locked_error(sb, grp, ino, block, fmt, ...)		\
+do {									\
+	no_printk(fmt, ##__VA_ARGS__);				\
+	__ext4_grp_locked_error("", 0, sb, grp, ino, block, " ");	\
+} while (0)
+
+#endif
+
 extern void ext4_update_dynamic_rev(struct super_block *sb);
 extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
 					__u32 compat);
@@ -2312,6 +2369,7 @@ struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
 {
 	 struct ext4_group_info ***grp_info;
 	 long indexv, indexh;
+	 BUG_ON(group >= EXT4_SB(sb)->s_groups_count);
 	 grp_info = EXT4_SB(sb)->s_group_info;
 	 indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
 	 indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
@@ -2598,8 +2656,7 @@ struct ext4_extent;
 
 extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
 extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
-extern int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks,
-				       int chunk);
+extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
 extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			       struct ext4_map_blocks *map, int flags);
 extern void ext4_ext_truncate(handle_t *, struct inode *);
@@ -2609,8 +2666,8 @@ 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,
 			  loff_t len);
-extern int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
-			  ssize_t len);
+extern int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode,
+					  loff_t offset, ssize_t len);
 extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
 			   struct ext4_map_blocks *map, int flags);
 extern int ext4_ext_calc_metadata_amount(struct inode *inode,
@@ -2650,12 +2707,15 @@ extern int ext4_move_extents(struct file *o_filp, struct file *d_filp,
 
 /* page-io.c */
 extern int __init ext4_init_pageio(void);
-extern void ext4_add_complete_io(ext4_io_end_t *io_end);
 extern void ext4_exit_pageio(void);
-extern void ext4_ioend_shutdown(struct inode *);
-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 void ext4_end_io_work(struct work_struct *work);
+extern ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end);
+extern int ext4_put_io_end(ext4_io_end_t *io_end);
+extern void ext4_put_io_end_defer(ext4_io_end_t *io_end);
+extern void ext4_io_submit_init(struct ext4_io_submit *io,
+				struct writeback_control *wbc);
+extern void ext4_end_io_rsv_work(struct work_struct *work);
+extern void ext4_end_io_unrsv_work(struct work_struct *work);
 extern void ext4_io_submit(struct ext4_io_submit *io);
 extern int ext4_bio_write_page(struct ext4_io_submit *io,
 			       struct page *page,
@@ -2668,20 +2728,17 @@ extern void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp);
 extern int ext4_mmp_csum_verify(struct super_block *sb,
 				struct mmp_struct *mmp);
 
-/* BH_Uninit flag: blocks are allocated but uninitialized on disk */
+/*
+ * Note that these flags will never ever appear in a buffer_head's state flag.
+ * See EXT4_MAP_... to see where this is used.
+ */
 enum ext4_state_bits {
 	BH_Uninit	/* blocks are allocated but uninitialized on disk */
-	  = BH_JBDPrivateStart,
+	 = BH_JBDPrivateStart,
 	BH_AllocFromCluster,	/* allocated blocks were part of already
-				 * allocated cluster. Note that this flag will
-				 * never, ever appear in a buffer_head's state
-				 * flag. See EXT4_MAP_FROM_CLUSTER to see where
-				 * this is used. */
+				 * allocated cluster. */
 };
 
-BUFFER_FNS(Uninit, uninit)
-TAS_BUFFER_FNS(Uninit, uninit)
-
 /*
  * Add new method to test whether block and inode bitmaps are properly
  * initialized. With uninit_bg reading the block from disk is not enough