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()
  ...

63 files changed, 2652 insertions, 2170 deletions

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index bdd82b2339d..9858f337529 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -189,7 +189,7 @@ prototypes:
 				loff_t pos, unsigned len, unsigned copied,
 				struct page *page, void *fsdata);
 	sector_t (*bmap)(struct address_space *, sector_t);
-	int (*invalidatepage) (struct page *, unsigned long);
+	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
 	int (*releasepage) (struct page *, int);
 	void (*freepage)(struct page *);
 	int (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
@@ -310,8 +310,8 @@ filesystems and by the swapper. The latter will eventually go away.  Please,
 keep it that way and don't breed new callers.
 
 	->invalidatepage() is called when the filesystem must attempt to drop
-some or all of the buffers from the page when it is being truncated.  It
-returns zero on success.  If ->invalidatepage is zero, the kernel uses
+some or all of the buffers from the page when it is being truncated. It
+returns zero on success. If ->invalidatepage is zero, the kernel uses
 block_invalidatepage() instead.
 
 	->releasepage() is called when the kernel is about to try to drop the
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 4a35f6614a6..e6bd1ffd821 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -549,7 +549,7 @@ struct address_space_operations
 -------------------------------
 
 This describes how the VFS can manipulate mapping of a file to page cache in
-your filesystem. As of kernel 2.6.22, the following members are defined:
+your filesystem. The following members are defined:
 
 struct address_space_operations {
 	int (*writepage)(struct page *page, struct writeback_control *wbc);
@@ -566,7 +566,7 @@ struct address_space_operations {
 				loff_t pos, unsigned len, unsigned copied,
 				struct page *page, void *fsdata);
 	sector_t (*bmap)(struct address_space *, sector_t);
-	int (*invalidatepage) (struct page *, unsigned long);
+	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
 	int (*releasepage) (struct page *, int);
 	void (*freepage)(struct page *);
 	ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
@@ -685,14 +685,14 @@ struct address_space_operations {
   invalidatepage: If a page has PagePrivate set, then invalidatepage
         will be called when part or all of the page is to be removed
 	from the address space.  This generally corresponds to either a
-	truncation or a complete invalidation of the address space
-	(in the latter case 'offset' will always be 0).
-	Any private data associated with the page should be updated
-	to reflect this truncation.  If offset is 0, then
-	the private data should be released, because the page
-	must be able to be completely discarded.  This may be done by
-        calling the ->releasepage function, but in this case the
-        release MUST succeed.
+	truncation, punch hole  or a complete invalidation of the address
+	space (in the latter case 'offset' will always be 0 and 'length'
+	will be PAGE_CACHE_SIZE). Any private data associated with the page
+	should be updated to reflect this truncation.  If offset is 0 and
+	length is PAGE_CACHE_SIZE, then the private data should be released,
+	because the page must be able to be completely discarded.  This may
+	be done by calling the ->releasepage function, but in this case the
+	release MUST succeed.
 
   releasepage: releasepage is called on PagePrivate pages to indicate
         that the page should be freed if possible.  ->releasepage
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 055562c580b..9ff073f4090 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -148,13 +148,14 @@ static int v9fs_release_page(struct page *page, gfp_t gfp)
  * @offset: offset in the page
  */
 
-static void v9fs_invalidate_page(struct page *page, unsigned long offset)
+static void v9fs_invalidate_page(struct page *page, unsigned int offset,
+				 unsigned int length)
 {
 	/*
 	 * If called with zero offset, we should release
 	 * the private state assocated with the page
 	 */
-	if (offset == 0)
+	if (offset == 0 && length == PAGE_CACHE_SIZE)
 		v9fs_fscache_invalidate_page(page);
 }
 
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 8f6e9234d56..66d50fe2ee4 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -19,7 +19,8 @@
 #include "internal.h"
 
 static int afs_readpage(struct file *file, struct page *page);
-static void afs_invalidatepage(struct page *page, unsigned long offset);
+static void afs_invalidatepage(struct page *page, unsigned int offset,
+			       unsigned int length);
 static int afs_releasepage(struct page *page, gfp_t gfp_flags);
 static int afs_launder_page(struct page *page);
 
@@ -310,16 +311,17 @@ static int afs_launder_page(struct page *page)
  * - release a page and clean up its private data if offset is 0 (indicating
  *   the entire page)
  */
-static void afs_invalidatepage(struct page *page, unsigned long offset)
+static void afs_invalidatepage(struct page *page, unsigned int offset,
+			       unsigned int length)
 {
 	struct afs_writeback *wb = (struct afs_writeback *) page_private(page);
 
-	_enter("{%lu},%lu", page->index, offset);
+	_enter("{%lu},%u,%u", page->index, offset, length);
 
 	BUG_ON(!PageLocked(page));
 
 	/* we clean up only if the entire page is being invalidated */
-	if (offset == 0) {
+	if (offset == 0 && length == PAGE_CACHE_SIZE) {
 #ifdef CONFIG_AFS_FSCACHE
 		if (PageFsCache(page)) {
 			struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b8b60b660c8..b0292b3ead5 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1013,7 +1013,8 @@ static int btree_releasepage(struct page *page, gfp_t gfp_flags)
 	return try_release_extent_buffer(page);
 }
 
-static void btree_invalidatepage(struct page *page, unsigned long offset)
+static void btree_invalidatepage(struct page *page, unsigned int offset,
+				 unsigned int length)
 {
 	struct extent_io_tree *tree;
 	tree = &BTRFS_I(page->mapping->host)->io_tree;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e7e7afb4a87..6bca9472f31 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2957,7 +2957,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	pg_offset = i_size & (PAGE_CACHE_SIZE - 1);
 	if (page->index > end_index ||
 	   (page->index == end_index && !pg_offset)) {
-		page->mapping->a_ops->invalidatepage(page, 0);
+		page->mapping->a_ops->invalidatepage(page, 0, PAGE_CACHE_SIZE);
 		unlock_page(page);
 		return 0;
 	}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a46b656d08d..4f9d16b70d3 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7493,7 +7493,8 @@ static int btrfs_releasepage(struct page *page, gfp_t gfp_flags)
 	return __btrfs_releasepage(page, gfp_flags & GFP_NOFS);
 }
 
-static void btrfs_invalidatepage(struct page *page, unsigned long offset)
+static void btrfs_invalidatepage(struct page *page, unsigned int offset,
+				 unsigned int length)
 {
 	struct inode *inode = page->mapping->host;
 	struct extent_io_tree *tree;
diff --git a/fs/buffer.c b/fs/buffer.c
index d2a4d1bb2d5..f93392e2df1 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1454,7 +1454,8 @@ static void discard_buffer(struct buffer_head * bh)
  * block_invalidatepage - invalidate part or all of a buffer-backed page
  *
  * @page: the page which is affected
- * @offset: the index of the truncation point
+ * @offset: start of the range to invalidate
+ * @length: length of the range to invalidate
  *
  * block_invalidatepage() is called when all or part of the page has become
  * invalidated by a truncate operation.
@@ -1465,15 +1466,22 @@ static void discard_buffer(struct buffer_head * bh)
  * point.  Because the caller is about to free (and possibly reuse) those
  * blocks on-disk.
  */
-void block_invalidatepage(struct page *page, unsigned long offset)
+void block_invalidatepage(struct page *page, unsigned int offset,
+			  unsigned int length)
 {
 	struct buffer_head *head, *bh, *next;
 	unsigned int curr_off = 0;
+	unsigned int stop = length + offset;
 
 	BUG_ON(!PageLocked(page));
 	if (!page_has_buffers(page))
 		goto out;
 
+	/*
+	 * Check for overflow
+	 */
+	BUG_ON(stop > PAGE_CACHE_SIZE || stop < length);
+
 	head = page_buffers(page);
 	bh = head;
 	do {
@@ -1481,6 +1489,12 @@ void block_invalidatepage(struct page *page, unsigned long offset)
 		next = bh->b_this_page;
 
 		/*
+		 * Are we still fully in range ?
+		 */
+		if (next_off > stop)
+			goto out;
+
+		/*
 		 * is this block fully invalidated?
 		 */
 		if (offset <= curr_off)
@@ -1501,6 +1515,7 @@ out:
 }
 EXPORT_SYMBOL(block_invalidatepage);
 
+
 /*
  * We attach and possibly dirty the buffers atomically wrt
  * __set_page_dirty_buffers() via private_lock.  try_to_free_buffers
@@ -2841,7 +2856,7 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block,
 		 * they may have been added in ext3_writepage().  Make them
 		 * freeable here, so the page does not leak.
 		 */
-		do_invalidatepage(page, 0);
+		do_invalidatepage(page, 0, PAGE_CACHE_SIZE);
 		unlock_page(page);
 		return 0; /* don't care */
 	}
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 3e68ac10104..38b5c1bc677 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -143,7 +143,8 @@ static int ceph_set_page_dirty(struct page *page)
  * dirty page counters appropriately.  Only called if there is private
  * data on the page.
  */
-static void ceph_invalidatepage(struct page *page, unsigned long offset)
+static void ceph_invalidatepage(struct page *page, unsigned int offset,
+				unsigned int length)
 {
 	struct inode *inode;
 	struct ceph_inode_info *ci;
@@ -163,20 +164,20 @@ static void ceph_invalidatepage(struct page *page, unsigned long offset)
 	if (!PageDirty(page))
 		pr_err("%p invalidatepage %p page not dirty\n", inode, page);
 
-	if (offset == 0)
+	if (offset == 0 && length == PAGE_CACHE_SIZE)
 		ClearPageChecked(page);
 
 	ci = ceph_inode(inode);
-	if (offset == 0) {
-		dout("%p invalidatepage %p idx %lu full dirty page %lu\n",
-		     inode, page, page->index, offset);
+	if (offset == 0 && length == PAGE_CACHE_SIZE) {
+		dout("%p invalidatepage %p idx %lu full dirty page\n",
+		     inode, page, page->index);
 		ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
 		ceph_put_snap_context(snapc);
 		page->private = 0;
 		ClearPagePrivate(page);
 	} else {
-		dout("%p invalidatepage %p idx %lu partial dirty page\n",
-		     inode, page, page->index);
+		dout("%p invalidatepage %p idx %lu partial dirty page %u(%u)\n",
+		     inode, page, page->index, offset, length);
 	}
 }
 
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 48b29d24c9f..4d8ba8d491e 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3546,11 +3546,12 @@ static int cifs_release_page(struct page *page, gfp_t gfp)
 	return cifs_fscache_release_page(page, gfp);
 }
 
-static void cifs_invalidate_page(struct page *page, unsigned long offset)
+static void cifs_invalidate_page(struct page *page, unsigned int offset,
+				 unsigned int length)
 {
 	struct cifsInodeInfo *cifsi = CIFS_I(page->mapping->host);
 
-	if (offset == 0)
+	if (offset == 0 && length == PAGE_CACHE_SIZE)
 		cifs_fscache_invalidate_page(page, &cifsi->vfs_inode);
 }
 
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index d1f80abd882..2ec8eb1ab26 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -953,9 +953,11 @@ static int exofs_releasepage(struct page *page, gfp_t gfp)
 	return 0;
 }
 
-static void exofs_invalidatepage(struct page *page, unsigned long offset)
+static void exofs_invalidatepage(struct page *page, unsigned int offset,
+				 unsigned int length)
 {
-	EXOFS_DBGMSG("page 0x%lx offset 0x%lx\n", page->index, offset);
+	EXOFS_DBGMSG("page 0x%lx offset 0x%x length 0x%x\n",
+		     page->index, offset, length);
 	WARN_ON(1);
 }
 
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 23c71282564..f67668f724b 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1825,19 +1825,20 @@ ext3_readpages(struct file *file, struct address_space *mapping,
 	return mpage_readpages(mapping, pages, nr_pages, ext3_get_block);
 }
 
-static void ext3_invalidatepage(struct page *page, unsigned long offset)
+static void ext3_invalidatepage(struct page *page, unsigned int offset,
+				unsigned int length)
 {
 	journal_t *journal = EXT3_JOURNAL(page->mapping->host);
 
-	trace_ext3_invalidatepage(page, offset);
+	trace_ext3_invalidatepage(page, offset, length);
 
 	/*
 	 * If it's a full truncate we just forget about the pending dirtying
 	 */
-	if (offset == 0)
+	if (offset == 0 && length == PAGE_CACHE_SIZE)
 		ClearPageChecked(page);
 
-	journal_invalidatepage(journal, page, offset);
+	journal_invalidatepage(journal, page, offset, length);
 }
 
 static int ext3_releasepage(struct page *page, gfp_t wait)
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 692de13e359..cea8ecf3e76 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -576,11 +576,8 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 		if (!ext3_check_dir_entry("htree_dirblock_to_tree", dir, de, bh,
 					(block<<EXT3_BLOCK_SIZE_BITS(dir->i_sb))
 						+((char *)de - bh->b_data))) {
-			/* On error, skip the f_pos to the next block. */
-			dir_file->f_pos = (dir_file->f_pos |
-					(dir->i_sb->s_blocksize - 1)) + 1;
-			brelse (bh);
-			return count;
+			/* silently ignore the rest of the block */
+			break;
 		}
 		ext3fs_dirhash(de->name, de->name_len, hinfo);
 		if ((hinfo->hash < start_hash) ||
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index d0f13eada0e..58339393fa6 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -682,11 +682,15 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb)
 
 static inline int test_root(ext4_group_t a, int b)
 {
-	int num = b;
-
-	while (a > num)
-		num *= b;
-	return num == a;
+	while (1) {
+		if (a < b)
+			return 0;
+		if (a == b)
+			return 1;
+		if ((a % b) != 0)
+			return 0;
+		a = a / b;
+	}
 }
 
 static int ext4_group_sparse(ext4_group_t group)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 4af03ea84aa..b577e45425b 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 unwritt