Merge tag 'v3.18-rc4' into patchwork

Needed due to some important regression fixes at RC core.

* commit 'v3.18-rc4': (587 commits)
  Linux 3.18-rc4
  ARM: dts: zynq: Enable PL clocks for Parallella
  tiny: rename ENABLE_DEV_COREDUMP to ALLOW_DEV_COREDUMP
  tiny: reverse logic for DISABLE_DEV_COREDUMP
  i2c: core: Dispose OF IRQ mapping at client removal time
  i2c: at91: don't account as iowait
  i2c: remove FSF address
  USB: Update default usb-storage delay_use value in kernel-parameters.txt
  sysfs: driver core: Fix glue dir race condition by gdp_mutex
  MIPS: Fix build with binutils 2.24.51+
  xfs: track bulkstat progress by agino
  xfs: bulkstat error handling is broken
  xfs: bulkstat main loop logic is a mess
  xfs: bulkstat chunk-formatter has issues
  xfs: bulkstat chunk formatting cursor is broken
  xfs: bulkstat btree walk doesn't terminate
  mm: Fix comment before truncate_setsize()
  USB: cdc-acm: add quirk for control-line state requests
  tty: Fix pty master poll() after slave closes v2
  MIPS: R3000: Fix debug output for Virtual page number
  ...

Conflicts:
	drivers/media/rc/rc-main.c

30 files changed, 273 insertions, 367 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index cc9d4114cda0..1d9c9f3754f8 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1585,7 +1585,7 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 }
 EXPORT_SYMBOL_GPL(blkdev_write_iter);
 
-static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
+ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *bd_inode = file->f_mapping->host;
@@ -1599,6 +1599,7 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	iov_iter_truncate(to, size);
 	return generic_file_read_iter(iocb, to);
 }
+EXPORT_SYMBOL_GPL(blkdev_read_iter);
 
 /*
  * Try to release a page associated with block device when the system
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index d557264ee974..fe69edda11fb 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3276,7 +3276,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root, unsigned long count);
 int btrfs_async_run_delayed_refs(struct btrfs_root *root,
 				 unsigned long count, int wait);
-int btrfs_lookup_extent(struct btrfs_root *root, u64 start, u64 len);
+int btrfs_lookup_data_extent(struct btrfs_root *root, u64 start, u64 len);
 int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root, u64 bytenr,
 			     u64 offset, int metadata, u64 *refs, u64 *flags);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1ad0f47ac850..1bf9f897065d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3817,19 +3817,19 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 	struct btrfs_super_block *sb = fs_info->super_copy;
 	int ret = 0;
 
-	if (sb->root_level > BTRFS_MAX_LEVEL) {
-		printk(KERN_ERR "BTRFS: tree_root level too big: %d > %d\n",
-				sb->root_level, BTRFS_MAX_LEVEL);
+	if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
+		printk(KERN_ERR "BTRFS: tree_root level too big: %d >= %d\n",
+				btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);
 		ret = -EINVAL;
 	}
-	if (sb->chunk_root_level > BTRFS_MAX_LEVEL) {
-		printk(KERN_ERR "BTRFS: chunk_root level too big: %d > %d\n",
-				sb->chunk_root_level, BTRFS_MAX_LEVEL);
+	if (btrfs_super_chunk_root_level(sb) >= BTRFS_MAX_LEVEL) {
+		printk(KERN_ERR "BTRFS: chunk_root level too big: %d >= %d\n",
+				btrfs_super_chunk_root_level(sb), BTRFS_MAX_LEVEL);
 		ret = -EINVAL;
 	}
-	if (sb->log_root_level > BTRFS_MAX_LEVEL) {
-		printk(KERN_ERR "BTRFS: log_root level too big: %d > %d\n",
-				sb->log_root_level, BTRFS_MAX_LEVEL);
+	if (btrfs_super_log_root_level(sb) >= BTRFS_MAX_LEVEL) {
+		printk(KERN_ERR "BTRFS: log_root level too big: %d >= %d\n",
+				btrfs_super_log_root_level(sb), BTRFS_MAX_LEVEL);
 		ret = -EINVAL;
 	}
 
@@ -3837,15 +3837,15 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 	 * The common minimum, we don't know if we can trust the nodesize/sectorsize
 	 * items yet, they'll be verified later. Issue just a warning.
 	 */
-	if (!IS_ALIGNED(sb->root, 4096))
+	if (!IS_ALIGNED(btrfs_super_root(sb), 4096))
 		printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
 				sb->root);
-	if (!IS_ALIGNED(sb->chunk_root, 4096))
+	if (!IS_ALIGNED(btrfs_super_chunk_root(sb), 4096))
 		printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
 				sb->chunk_root);
-	if (!IS_ALIGNED(sb->log_root, 4096))
+	if (!IS_ALIGNED(btrfs_super_log_root(sb), 4096))
 		printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
-				sb->log_root);
+				btrfs_super_log_root(sb));
 
 	if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_UUID_SIZE) != 0) {
 		printk(KERN_ERR "BTRFS: dev_item UUID does not match fsid: %pU != %pU\n",
@@ -3857,13 +3857,13 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 	 * Hint to catch really bogus numbers, bitflips or so, more exact checks are
 	 * done later
 	 */
-	if (sb->num_devices > (1UL << 31))
+	if (btrfs_super_num_devices(sb) > (1UL << 31))
 		printk(KERN_WARNING "BTRFS: suspicious number of devices: %llu\n",
-				sb->num_devices);
+				btrfs_super_num_devices(sb));
 
-	if (sb->bytenr != BTRFS_SUPER_INFO_OFFSET) {
+	if (btrfs_super_bytenr(sb) != BTRFS_SUPER_INFO_OFFSET) {
 		printk(KERN_ERR "BTRFS: super offset mismatch %llu != %u\n",
-				sb->bytenr, BTRFS_SUPER_INFO_OFFSET);
+				btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET);
 		ret = -EINVAL;
 	}
 
@@ -3871,14 +3871,15 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 	 * The generation is a global counter, we'll trust it more than the others
 	 * but it's still possible that it's the one that's wrong.
 	 */
-	if (sb->generation < sb->chunk_root_generation)
+	if (btrfs_super_generation(sb) < btrfs_super_chunk_root_generation(sb))
 		printk(KERN_WARNING
 			"BTRFS: suspicious: generation < chunk_root_generation: %llu < %llu\n",
-			sb->generation, sb->chunk_root_generation);
-	if (sb->generation < sb->cache_generation && sb->cache_generation != (u64)-1)
+			btrfs_super_generation(sb), btrfs_super_chunk_root_generation(sb));
+	if (btrfs_super_generation(sb) < btrfs_super_cache_generation(sb)
+	    && btrfs_super_cache_generation(sb) != (u64)-1)
 		printk(KERN_WARNING
 			"BTRFS: suspicious: generation < cache_generation: %llu < %llu\n",
-			sb->generation, sb->cache_generation);
+			btrfs_super_generation(sb), btrfs_super_cache_generation(sb));
 
 	return ret;
 }
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d56589571012..47c1ba141082 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -710,8 +710,8 @@ void btrfs_clear_space_info_full(struct btrfs_fs_info *info)
 	rcu_read_unlock();
 }
 
-/* simple helper to search for an existing extent at a given offset */
-int btrfs_lookup_extent(struct btrfs_root *root, u64 start, u64 len)
+/* simple helper to search for an existing data extent at a given offset */
+int btrfs_lookup_data_extent(struct btrfs_root *root, u64 start, u64 len)
 {
 	int ret;
 	struct btrfs_key key;
@@ -726,12 +726,6 @@ int btrfs_lookup_extent(struct btrfs_root *root, u64 start, u64 len)
 	key.type = BTRFS_EXTENT_ITEM_KEY;
 	ret = btrfs_search_slot(NULL, root->fs_info->extent_root, &key, path,
 				0, 0);
-	if (ret > 0) {
-		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
-		if (key.objectid == start &&
-		    key.type == BTRFS_METADATA_ITEM_KEY)
-			ret = 0;
-	}
 	btrfs_free_path(path);
 	return ret;
 }
@@ -786,7 +780,6 @@ search_again:
 	else
 		key.type = BTRFS_EXTENT_ITEM_KEY;
 
-again:
 	ret = btrfs_search_slot(trans, root->fs_info->extent_root,
 				&key, path, 0, 0);
 	if (ret < 0)
@@ -802,13 +795,6 @@ again:
 			    key.offset == root->nodesize)
 				ret = 0;
 		}
-		if (ret) {
-			key.objectid = bytenr;
-			key.type = BTRFS_EXTENT_ITEM_KEY;
-			key.offset = root->nodesize;
-			btrfs_release_path(path);
-			goto again;
-		}
 	}
 
 	if (ret == 0) {
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 783a94355efd..84a2d1868271 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -413,7 +413,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 	ret = 0;
 fail:
 	while (ret < 0 && !list_empty(&tmplist)) {
-		sums = list_entry(&tmplist, struct btrfs_ordered_sum, list);
+		sums = list_entry(tmplist.next, struct btrfs_ordered_sum, list);
 		list_del(&sums->list);
 		kfree(sums);
 	}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index a2b97ef10317..54bd91ece35b 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2151,6 +2151,7 @@ static void __exit exit_btrfs_fs(void)
 	extent_map_exit();
 	extent_io_exit();
 	btrfs_interface_exit();
+	btrfs_end_io_wq_exit();
 	unregister_filesystem(&btrfs_fs_type);
 	btrfs_exit_sysfs();
 	btrfs_cleanup_fs_uuids();
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 1475979e5718..286213cec861 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -672,7 +672,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 			 * is this extent already allocated in the extent
 			 * allocation tree?  If so, just add a reference
 			 */
-			ret = btrfs_lookup_extent(root, ins.objectid,
+			ret = btrfs_lookup_data_extent(root, ins.objectid,
 						ins.offset);
 			if (ret == 0) {
 				ret = btrfs_inc_extent_ref(trans, root,
diff --git a/fs/buffer.c b/fs/buffer.c
index 6c48f20eddd4..20805db2c987 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -128,21 +128,15 @@ __clear_page_buffers(struct page *page)
 	page_cache_release(page);
 }
 
-
-static int quiet_error(struct buffer_head *bh)
-{
-	if (!test_bit(BH_Quiet, &bh->b_state) && printk_ratelimit())
-		return 0;
-	return 1;
-}
-
-
-static void buffer_io_error(struct buffer_head *bh)
+static void buffer_io_error(struct buffer_head *bh, char *msg)
 {
 	char b[BDEVNAME_SIZE];
-	printk(KERN_ERR "Buffer I/O error on device %s, logical block %Lu\n",
+
+	if (!test_bit(BH_Quiet, &bh->b_state))
+		printk_ratelimited(KERN_ERR
+			"Buffer I/O error on dev %s, logical block %llu%s\n",
 			bdevname(bh->b_bdev, b),
-			(unsigned long long)bh->b_blocknr);
+			(unsigned long long)bh->b_blocknr, msg);
 }
 
 /*
@@ -177,17 +171,10 @@ EXPORT_SYMBOL(end_buffer_read_sync);
 
 void end_buffer_write_sync(struct buffer_head *bh, int uptodate)
 {
-	char b[BDEVNAME_SIZE];
-
 	if (uptodate) {
 		set_buffer_uptodate(bh);
 	} else {
-		if (!quiet_error(bh)) {
-			buffer_io_error(bh);
-			printk(KERN_WARNING "lost page write due to "
-					"I/O error on %s\n",
-				       bdevname(bh->b_bdev, b));
-		}
+		buffer_io_error(bh, ", lost sync page write");
 		set_buffer_write_io_error(bh);
 		clear_buffer_uptodate(bh);
 	}
@@ -304,8 +291,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 		set_buffer_uptodate(bh);
 	} else {
 		clear_buffer_uptodate(bh);
-		if (!quiet_error(bh))
-			buffer_io_error(bh);
+		buffer_io_error(bh, ", async page read");
 		SetPageError(page);
 	}
 
@@ -353,7 +339,6 @@ still_busy:
  */
 void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 {
-	char b[BDEVNAME_SIZE];
 	unsigned long flags;
 	struct buffer_head *first;
 	struct buffer_head *tmp;
@@ -365,12 +350,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 	if (uptodate) {
 		set_buffer_uptodate(bh);
 	} else {
-		if (!quiet_error(bh)) {
-			buffer_io_error(bh);
-			printk(KERN_WARNING "lost page write due to "
-					"I/O error on %s\n",
-			       bdevname(bh->b_bdev, b));
-		}
+		buffer_io_error(bh, ", lost async page write");
 		set_bit(AS_EIO, &page->mapping->flags);
 		set_buffer_write_io_error(bh);
 		clear_buffer_uptodate(bh);
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 7015db0bafd1..eb742d0e67ff 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -1354,13 +1354,6 @@ set_qf_format:
 					"not specified.");
 			return 0;
 		}
-	} else {
-		if (sbi->s_jquota_fmt) {
-			ext3_msg(sb, KERN_ERR, "error: journaled quota format "
-					"specified with no journaling "
-					"enabled.");
-			return 0;
-		}
 	}
 #endif
 	return 1;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 37043d0b2be8..0b16fb4c06d3 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3603,11 +3603,10 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		}
 	}
 
-	allocated = ext4_split_extent(handle, inode, ppath,
-				      &split_map, split_flag, flags);
-	if (allocated < 0)
-		err = allocated;
-
+	err = ext4_split_extent(handle, inode, ppath, &split_map, split_flag,
+				flags);
+	if (err > 0)
+		err = 0;
 out:
 	/* If we have gotten a failure, don't zero out status tree */
 	if (!err)
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index aca7b24a4432..8131be8c0af3 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -137,10 +137,10 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			iov_iter_truncate(from, sbi->s_bitmap_maxbytes - pos);
 	}
 
+	iocb->private = &overwrite;
 	if (o_direct) {
 		blk_start_plug(&plug);
 
-		iocb->private = &overwrite;
 
 		/* check whether we do a DIO overwrite or not */
 		if (ext4_should_dioread_nolock(inode) && !aio_mutex &&
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 8012a5daf401..ac644c31ca67 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -887,6 +887,10 @@ got:
 		struct buffer_head *block_bitmap_bh;
 
 		block_bitmap_bh = ext4_read_block_bitmap(sb, group);
+		if (!block_bitmap_bh) {
+			err = -EIO;
+			goto out;
+		}
 		BUFFER_TRACE(block_bitmap_bh, "get block bitmap access");
 		err = ext4_journal_get_write_access(handle, block_bitmap_bh);
 		if (err) {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index e9777f93cf05..3356ab5395f4 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4959,7 +4959,12 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	if (val)
 		ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
 	else {
-		jbd2_journal_flush(journal);
+		err = jbd2_journal_flush(journal);
+		if (err < 0) {
+			jbd2_journal_unlock_updates(journal);
+			ext4_inode_resume_unlocked_dio(inode);
+			return err;
+		}
 		ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
 	}
 	ext4_set_aops(inode);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 123798c5ac31..426211882f72 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1816,31 +1816,39 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 		hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
 	hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
 	ext4fs_dirhash(name, namelen, &hinfo);
+	memset(frames, 0, sizeof(frames));
 	frame = frames;
 	frame->entries = entries;
 	frame->at = entries;
 	frame->bh = bh;
 	bh = bh2;
 
-	ext4_handle_dirty_dx_node(handle, dir, frame->bh);
-	ext4_handle_dirty_dirent_node(handle, dir, bh);
+	retval = ext4_handle_dirty_dx_node(handle, dir, frame->bh);
+	if (retval)
+		goto out_frames;	
+	retval = ext4_handle_dirty_dirent_node(handle, dir, bh);
+	if (retval)
+		goto out_frames;	
 
 	de = do_split(handle,dir, &bh, frame, &hinfo);
 	if (IS_ERR(de)) {
-		/*
-		 * Even if the block split failed, we have to properly write
-		 * out all the changes we did so far. Otherwise we can end up
-		 * with corrupted filesystem.
-		 */
-		ext4_mark_inode_dirty(handle, dir);
-		dx_release(frames);
-		return PTR_ERR(de);
+		retval = PTR_ERR(de);
+		goto out_frames;
 	}
 	dx_release(frames);
 
 	retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
 	brelse(bh);
 	return retval;
+out_frames:
+	/*
+	 * Even if the block split failed, we have to properly write
+	 * out all the changes we did so far. Otherwise we can end up
+	 * with corrupted filesystem.
+	 */
+	ext4_mark_inode_dirty(handle, dir);
+	dx_release(frames);
+	return retval;
 }
 
 /*
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index f298c60f907d..ca4588388fc3 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1081,7 +1081,7 @@ static void update_backups(struct super_block *sb, int blk_off, char *data,
 			break;
 
 		if (meta_bg == 0)
-			backup_block = group * bpg + blk_off;
+			backup_block = ((ext4_fsblk_t)group) * bpg + blk_off;
 		else
 			backup_block = (ext4_group_first_block_no(sb, group) +
 					ext4_bg_has_super(sb, group));
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 1eda6ab0ef9d..2c9e6864abd9 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3526,6 +3526,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 	set_opt(sb, POSIX_ACL);
 #endif
+	/* don't forget to enable journal_csum when metadata_csum is enabled. */
+	if (ext4_has_metadata_csum(sb))
+		set_opt(sb, JOURNAL_CHECKSUM);
+
 	if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
 		set_opt(sb, JOURNAL_DATA);
 	else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
@@ -3943,7 +3947,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_MMP) &&
 	    !(sb->s_flags & MS_RDONLY))
 		if (ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)))
-			goto failed_mount3;
+			goto failed_mount3a;
 
 	/*
 	 * The first inode we look at is the journal inode.  Don't try
@@ -3952,7 +3956,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if (!test_opt(sb, NOLOAD) &&
 	    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
 		if (ext4_load_journal(sb, es, journal_devnum))
-			goto failed_mount3;
+			goto failed_mount3a;
 	} else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
 	      EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
 		ext4_msg(sb, KERN_ERR, "required journal recovery "
@@ -4240,6 +4244,7 @@ failed_mount_wq:
 		jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
 	}
+failed_mount3a:
 	ext4_es_unregister_shrinker(sbi);
 failed_mount3:
 	del_timer_sync(&sbi->s_err_report);
@@ -4841,6 +4846,14 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		goto restore_opts;
 	}
 
+	if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^
+	    test_opt(sb, JOURNAL_CHECKSUM)) {
+		ext4_msg(sb, KERN_ERR, "changing journal_checksum "
+			 "during remount not supported");
+		err = -EINVAL;
+		goto restore_opts;
+	}
+
 	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
 		if (test_opt2(sb, EXPLICIT_DELALLOC)) {
 			ext4_msg(sb, KERN_ERR, "can't mount with "
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 881b3bd0143f..fe839b915116 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -29,13 +29,9 @@
 #define BEQUIET
 
 static int isofs_hashi(const struct dentry *parent, struct qstr *qstr);
-static int isofs_hash(const struct dentry *parent, struct qstr *qstr);
 static int isofs_dentry_cmpi(const struct dentry *parent,
 		const struct dentry *dentry,
 		unsigned int len, const char *str, const struct qstr *name);
-static int isofs_dentry_cmp(const struct dentry *parent,
-		const struct dentry *dentry,
-		unsigned int len, const char *str, const struct qstr *name);
 
 #ifdef CONFIG_JOLIET
 static int isofs_hashi_ms(const struct dentry *parent, struct qstr *qstr);
@@ -135,10 +131,6 @@ static const struct super_operations isofs_sops = {
 
 static const struct dentry_operations isofs_dentry_ops[] = {
 	{
-		.d_hash		= isofs_hash,
-		.d_compare	= isofs_dentry_cmp,
-	},
-	{
 		.d_hash		= isofs_hashi,
 		.d_compare	= isofs_dentry_cmpi,
 	},
@@ -258,25 +250,12 @@ static int isofs_dentry_cmp_common(
 }
 
 static int
-isofs_hash(const struct dentry *dentry, struct qstr *qstr)
-{
-	return isofs_hash_common(qstr, 0);
-}
-
-static int
 isofs_hashi(const struct dentry *dentry, struct qstr *qstr)
 {
 	return isofs_hashi_common(qstr, 0);
 }
 
 static int
-isofs_dentry_cmp(const struct dentry *parent, const struct dentry *dentry,
-		unsigned int len, const char *str, const struct qstr *name)
-{
-	return isofs_dentry_cmp_common(len, str, name, 0, 0);
-}
-
-static int
 isofs_dentry_cmpi(const struct dentry *parent, const struct dentry *dentry,
 		unsigned int len, const char *str, const struct qstr *name)
 {
@@ -930,7 +909,8 @@ root_found:
 	if (opt.check == 'r')
 		table++;
 
-	s->s_d_op = &isofs_dentry_ops[table];
+	if (table)
+		s->s_d_op = &isofs_dentry_ops[table - 1];
 
 	/* get the root dentry */
 	s->s_root = d_make_root(inode);
diff --git a/fs/isofs/namei.c b/fs/isofs/namei.c
index 95295640d9c8..7b543e6b6526 100644
--- a/fs/isofs/namei.c
+++ b/fs/isofs/namei.c
@@ -18,25 +18,10 @@ static int
 isofs_cmp(struct dentry *dentry, const char *compare, int dlen)
 {
 	struct qstr qstr;
-
-	if (!compare)
-		return 1;
-
-	/* check special "." and ".." files */
-	if (dlen == 1) {
-		/* "." */
-		if (compare[0] == 0) {
-			if (!dentry->d_name.len)
-				return 0;
-			compare = ".";
-		} else if (compare[0] == 1) {
-			compare = "..";
-			dlen = 2;
-		}
-	}
-
 	qstr.name = compare;
 	qstr.len = dlen;
+	if (likely(!dentry->d_op))
+		return dentry->d_name.len != dlen || memcmp(dentry->d_name.name, compare, dlen);
 	return dentry->d_op->d_compare(NULL, NULL, dentry->d_name.len, dentry->d_name.name, &qstr);
 }
 
@@ -146,7 +131,8 @@ isofs_find_entry(struct inode *dir, struct dentry *dentry,
 				(!(de->flags[-sbi->s_high_sierra] & 1))) &&
 			(sbi->s_showassoc ||
 				(!(de->flags[-sbi->s_high_sierra] & 4)))) {
-			match = (isofs_cmp(dentry, dpnt, dlen) == 0);
+			if (dpnt && (dlen > 1 || dpnt[0] > 1))
+				match = (isofs_cmp(dentry, dpnt, dlen) == 0);
 		}
 		if (match) {
 			isofs_normalize_block_and_offset(de,
diff --git a/fs/jbd/revoke.c b/fs/jbd/revoke.c
index 8898bbd2b61e..dcead636c33b 100644
--- a/fs/jbd/revoke.c
+++ b/fs/jbd/revoke.c
@@ -93,6 +93,7 @@
 #include <linux/bio.h>
 #endif
 #include <linux/log2.h>
+#include <linux/hash.h>
 
 static struct kmem_cache *revoke_record_cache;
 static struct kmem_cache *revoke_table_cache;
@@ -129,15 +130,11 @@ static void flush_descriptor(journal_t *, struct journal_head *, int, int);
 
 /* Utility functions to maintain the revoke table */
 
-/* Borrowed from buffer.c: this is a tried and tested block hash function */
 static inline int hash(journal_t *journal, unsigned int block)
 {
 	struct jbd_revoke_table_s *table = journal->j_revoke;
-	int hash_shift = table->hash_shift;
 
-	return ((block << (hash_shift - 6)) ^
-		(block >> 13) ^
-		(block << (hash_shift - 12))) & (table->hash_size - 1);
+	return hash_32(block, table->hash_shift);
 }
 
 static int insert_revoke_hash(journal_t *journal, unsigned int blocknr,
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index d5e95a175c92..c6cbaef2bda1 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -92,6 +92,7 @@
 #include <linux/init.h>
 #include <linux/bio.h>
 #include <linux/log2.h>
+#include <linux/hash.h>
 #endif
 
 static struct kmem_cache *jbd2_revoke_record_cache;
@@ -130,16 +131,9 @@ static void flush_descriptor(journal_t *, struct buffer_head *, int, int);
 
 /* Utility functions to maintain the revoke table */
 
-/* Borrowed from buffer.c: this is a tried and tested block hash function */
 static inline int hash(journal_t *journal, unsigned long long block)
 {
-	struct jbd2_revoke_table_s *table = journal->j_revoke;
-	int hash_shift = table->hash_shift;
-	int hash = (int)block ^ (int)((block >> 31) >> 1);
-
-	return ((hash << (hash_shift - 6)) ^
-		(hash >> 13) ^
-		(hash << (hash_shift - 12))) & (table->hash_size - 1);
+	return hash_64(block, journal->j_revoke->hash_shift);
 }
 
 static int insert_revoke_hash(journal_t *journal, unsigned long long blocknr,
diff --git a/fs/namei.c b/fs/namei.c
index 42df664e95e5..db5fe86319e6 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2497,7 +2497,7 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
 	}
 
 	mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
-	mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD);
+	mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT2);
 	return NULL;
 }
 EXPORT_SYMBOL(lock_rename);
@@ -3154,7 +3154,8 @@ static int do_tmpfile(int dfd, struct filename *pathname,
 	if (error)
 		goto out2;
 	audit_inode(pathname, nd->path.dentry, 0);
-	error = may_open(&nd->path, op->acc_mode, op->open_flag);
+	/* Don't check for other permissions, the inode was just created */
+	error = may_open(&nd->path, MAY_OPEN, op->open_flag);
 	if (error)
 		goto out2;
 	file->f_path.mnt = nd->path.mnt;
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index cdeb3cfd6f32..0beb023f25ac 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1272,7 +1272,8 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp)
 	 */
 	if (argp->opcnt == resp->opcnt)
 		return false;
-
+	if (next->opnum == OP_ILLEGAL)
+		return false;
 	nextd = OPDESC(next);
 	/*
 	 * Rest of 2.6.3.1.1: certain operations will return WRONGSEC
@@ -1589,7 +1590,8 @@ static inline u32 nfsd4_rename_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op
 static inline u32 nfsd4_sequence_rsize(struct svc_rqst *rqstp,
 				       struct nfsd4_op *op)
 {
-	return NFS4_MAX_SESSIONID_LEN + 20;
+	return (op_encode_hdr_size
+		+ XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5) * sizeof(__be32);
 }
 
 static inline u32 nfsd4_setattr_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
@@ -1893,6 +1895,7 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_func = (nfsd4op_func)nfsd4_sequence,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
 		.op_name = "OP_SEQUENCE",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_sequence_rsize,
 	},
 	[OP_DESTROY_CLIENTID] = {
 		.op_func = (nfsd4op_func)nfsd4_destroy_clientid,
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index 9ce062218de9..e8497144b323 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -288,20 +288,25 @@ void fsnotify_unmount_inodes(struct list_head *list)
 		spin_unlock(&inode->i_lock);
 
 		/* In case the dropping of a reference would nuke next_i. */
-		if ((&next_i->i_sb_list != list) &&
-		    atomic_read(&next_i->i_count)) {
+		while (&next_i->i_sb_list != list) {
 			spin_lock(&next_i->i_lock);
-			if (!(next_i->i_state & (I_FREEING | I_WILL_FREE))) {
+			if (!(next_i->i_state & (I_FREEING | I_WILL_FREE)) &&
+						atomic_read(&next_i->i_count)) {
 				__iget(next_i);
 				need_iput = next_i;
+				spin_unlock(&next_i->i_lock);
+				break;
 			}
 			spin_unlock(&next_i->i_lock);
+			next_i = list_entry(next_i->i_sb_list.next,
+						struct inode, i_sb_list);
 		}
 
 		/*
-		 * We can safely drop inode_sb_list_lock here because we hold
-		 * references on both inode and next_i.  Also no new inodes
-		 * will be added since the umount has begun.
+		 * We can safely drop inode_sb_list_lock here because either
+		 * we actually hold references on both inode and next_i or
+		 * end of list.  Also no new inodes will be added since the
+		 * umount has begun.
 		 */
 		spin_unlock(&inode_sb_list_lock);
 
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 97de0fbd9f78..a96044004064 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -925,7 +925,7 @@ static int o2net_send_tcp_msg(struct socket *sock, struct kvec *vec,
 			      size_t veclen, size_t total)
 {
 	int ret;
-	struct msghdr msg;
+	struct msghdr msg = {.msg_flags = 0,};
 
 	if (sock == NULL) {
 		ret = -EINVAL;
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 8add6f1030d7..b931e04e3388 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -158,7 +158,7 @@ bail_add:
 		 * NOTE: This dentry already has ->d_op set from
 		 * ocfs2_get_parent() and ocfs2_get_dentry()
 		 */
-		if (ret)
+		if (!IS_ERR_OR_NULL(ret))
 			dentry = ret;
 
 		status = ocfs2_dentry_attach_lock(dentry, inode,
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 910553f37aca..2a7ef4f8e2a6 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -21,9 +21,10 @@ struct ovl_cache_entry {
 	unsigned int len;
 	unsigned int type;
 	u64 ino;
-	bool is_whiteout;
 	struct list_head l_node;
 	struct rb_node node;
+	bool is_whiteout;
+	bool is_cursor;
 	char name[];
 };
 
@@ -92,6 +93,7 @@ static struct ovl_cache_entry *ovl_cache_entry_new(const char *name, int len,
 		p->type = d_type;
 		p->ino = ino;
 		p->is_whiteout = false;
+		p->is_cursor = false;
 	}
 
 	return p;
@@ -166,7 +168,7 @@ static void ovl_cache_put(struct ovl_dir_file *od, struct dentry *dentry)
 {
 	struct ovl_dir_cache *cache = od->cache;
 
-	list_del(&od->cursor.l_node);
+	list_del_init(&od->cursor.l_node);
 	WARN_ON(cache->refcount <= 0);
 	cache->refcount--;
 	if (!cache->refcount) {
@@ -251,7 +253,7 @@ static int ovl_dir_mark_whiteouts(struct dentry *dir,
 
 	mutex_lock(&dir->d_inode->i_mutex);
 	list_for_each_entry(p, rdd->list, l_node) {
-		if (!p->name)
+		if (p->is_cursor)
 			continue;
 
 		if (p->type != DT_CHR)
@@ -307,7 +309,6 @@ static inline int ovl_dir_read_merged(struct path *upperpath,
 	}
 out:
 	return err;
-
 }
 
 static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos)
@@ -316,7 +317,7 @@ static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos)
 	loff_t off = 0;
 
 	list_for_each_entry(p, &od->cache->entries, l_node) {
-		if (!p->name)
+		if (p->is_cursor)
 			continue;
 		if (off >= pos)
 			break;
@@ -389,7 +390,7 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx)
 
 		p = list_entry(od->cursor.l_node.next, struct ovl_cache_entry, l_node);
 		/* Skip cursors */
-		if (p->name) {
+		if (!p->is_cursor) {
 			if (!p->is_whiteout) {
 				if (!dir_emit(ctx, p->name, p->len, p->ino, p->type))
 					break;
@@ -454,12 +455,13 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
 	if (!od->is_upper && ovl_path_type(dentry) == OVL_PATH_MERGE) {
 		struct inode *inode = file_inode(file);
 
-		realfile = od->upperfile;
+		realfile =lockless_dereference(od->upperfile);
 		if (!realfile) {
 			struct path upperpath;
 
 			ovl_path_upper(dentry, &upperpath);
 			realfile = ovl_path_open(&upperpath, O_RDONLY);
+			smp_mb__before_spinlock();
 			mutex_lock(&inode->i_mutex);
 			if (!od->upperfile) {
 				if (IS_ERR(realfile)) {
@@ -518,6 +520,7 @@ static int ovl_dir_open(struct inode *inode, struct file *file)
 	od->realfile = realfile;
 	od->is_real = (type != OVL_PATH_MERGE);
 	od->is_upper = (type != OVL_PATH_LOWER);
+	od->cursor.is_cursor = true;
 	file->private_data = od;
 
 	return 0;
@@ -569,7 +572,7 @@ void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list)
 {
 	struct ovl_cache_entry *p;
 
-	mutex_lock_nested(&upper->d_inode->i_mutex, I_MUTEX_PARENT);
+	mutex_lock_nested(&upper->d_inode->i_mutex, I_MUTEX_CHILD);
 	list_for_each_entry(p, list, l_node) {
 		struct dentry *dentry;
 
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 8b663b2d9562..6b4527216a7f 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -634,7 +634,7 @@ int dquot_writeback_dquots(struct super_block *sb, int type)
 			dqstats_inc(DQST_LOOKUPS);
 			err = sb->dq_op->write_dquot(dquot);
 			if (!ret && err)
-				err = ret;
+				ret = err;
 			dqput(dquot);
 			spin_lock(&dq_list_lock);
 		}
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 92e8f99a5857..281002689d64 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1338,7 +1338,10 @@ xfs_free_file_space(
 	goto out;
 }
 
-
+/*
+ * Preallocate and zero a range of a file. This mechanism has the allocation
+ * semantics of fallocate and in addition converts data in the range to zeroes.
+ */
 int
 xfs_zero_file_space(
 	struct xfs_inode	*ip,
@@ -1346,65 +1349,30 @@ xfs_zero_file_space(
 	xfs_off_t		len)
 {
 	struct xfs_mount	*mp = ip->i_mount;
-	uint			granularity;
-	xfs_off_t		start_boundary;
-	xfs_off_t		end_boundary;
+	uint			blksize;
 	int			error;
 
 	trace_xfs_zero_file_space(ip);
 
-	granularity = max_t(uint, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
+	blksize = 1 << mp->m_sb.sb_blocklog;
 
 	/*
-	 * Round the range of extents we are going to convert inwards.  If the
-	 * offset is aligned, then it doesn't get changed so we zero from the
-	 * start of the block offset points to.
+	 * Punch a hole and prealloc the range. We use hole punch rather than
+	 * unwritten extent conversion for two reasons:
+	 *
+	 * 1.) Hole punch handles partial block zeroing for us.
+	 *
+	 * 2.) If prealloc returns ENOSPC, the file range is still zero-valued
+	 * by virtue of the hole punch.
 	 */
-	start_boundary = round_up(offset, granularity);
-	end_boundary = round_down(offset + len, granularity);
-
-	ASSERT(start_boundary >= offset);
-	ASSERT(end_boundary <= offset + len);
-
-	if (start_boundary < end_boundary - 1) {
-		/*
-		 * Writeback the range to ensure any inode size updates due to
-		 * appending writes make it to disk (otherwise we could just
-		 * punch out the delalloc blocks).
-		 */
-		error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
-				start_boundary, end_boundary - 1);
-		if (error)
-			goto out;
-		truncate_pagecache_range(VFS_I(ip), start_boundary,
-					 end_boundary - 1);
-
-		/* convert the blocks */
-		error = xfs_alloc_file_space(ip, start_boundary,
-					end_boundary - start_boundary - 1,
-					XFS_BMAPI_PREALLOC | XFS_BMAPI_CONVERT);
-		if (error)
-			goto out;
-
-		/* We've handled the interior of the range, now for the edges */
-		if (start_boundary != offset) {
-			error = xfs_iozero(ip, offset, start_boundary - offset);
-			if (error)
-				goto out;
-		}
-
-		if (end_boundary != offset + len)
-			error = xfs_iozero(ip, end_boundary,
-					   offset + len - end_boundary);
-
-	} else {
-		/*
-		 * It's either a sub-granularity range or the range spanned lies
-		 * partially across two adjacent blocks.
-		 */
-		error = xfs_iozero(ip, offset, len);
-	}
+	error = xfs_free_file_space(ip, offset, len);
+	if (error)
+		goto out;
 
+	error = xfs_alloc_file_space(ip, round_down(offset, blksize),
+				     round_up(offset + len, blksize) -
+				     round_down(offset, blksize),
+				     XFS_BMAPI_PREALLOC);
 out:
 	return error;
 
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index f1deb961a296..894924a5129b 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -236,8 +236,10 @@ xfs_bulkstat_grab_ichunk(
 	XFS_WANT_CORRUPTED_RETURN(stat == 1);
 
 	/* Check if the record contains the inode in request */
-	if (irec->ir_startino + XFS_INODES_PER_CHUNK <= agino)
-		return -EINVAL;
+	if (irec->ir_startino + XFS_INODES_PER_CHUNK <= agino) {
+		*icount = 0;
+		return 0;
+	}
 
 	idx = agino - irec->ir_startino + 1;
 	if (idx < XFS_INODES_PER_CHUNK &&
@@ -262,75 +264,76 @@ xfs_bulkstat_grab_ichunk(
 
 #define XFS_BULKSTAT_UBLEFT(ubleft)	((ubleft) >= statstruct_size)
 
+struct xfs_bulkstat_agichunk {
+	char		__user **ac_ubuffer;/* pointer into user's buffer */
+	int		ac_ubleft;	/* bytes left in user's buffer */
+	int		ac_ubelem;	/* spaces used in user's buffer */
+};
+
 /*
  * Process inodes in chunk with a pointer to a formatter function
  * that will iget the inode and fill in the appropriate structure.
  */
-int
+static int
 xfs_bulkstat_ag_ichunk(
 	struct xfs_mount		*mp,
 	xfs_agnumber_t			agno,
 	struct xfs_inobt_rec_incore	*irbp,
 	bulkstat_one_pf			formatter,
 	size_t				statstruct_size,
-	struct xfs_bulkstat_agichunk	*acp)
+	struct xfs_bulkstat_agichunk	*acp,
+	xfs_agino_t			*last_agino)
 {
-	xfs_ino_t			lastino = acp->ac_lastino;
 	char				__user **ubufp = acp->ac_ubuffer;
-	int				ubleft = acp->ac_ubleft;
-	int				ubelem = acp->ac_ubelem;
-	int				chunkidx, clustidx;
+	int				chunkidx;
 	int				error = 0;
-	xfs_agino_t			agino;
+	xfs_agino_t			agino = irbp->ir_startino;
 
-	for (agino = irbp->ir_startino, chunkidx = clustidx = 0;
-	     XFS_BULKSTAT_UBLEFT(ubleft) &&
-	     irbp->ir_freecount < XFS_INODES_PER_CHUNK;
-	     chunkidx++, clustidx++, agino++) {
-		int		fmterror;	/* bulkstat formatter result */
+	for (chunkidx = 0; chunkidx < XFS_INODES_PER_CHUNK;
+	     chunkidx++, agino++) {
+		int		fmterror;
 		int		ubused;
-		xfs_ino_t	ino = XFS_AGINO_TO_INO(mp, agno, agino);
 
-		ASSERT(chunkidx < XFS_INODES_PER_CHUNK);
+		/* inode won't fit in buffer, we are done */
+		if (acp->ac_ubleft < statstruct_size)
+			break;
 
 		/* Skip if this inode is free */
-		if (XFS_INOBT_MASK(chunkidx) & irbp->ir_free) {
-			lastino = ino;
+		if (XFS_INOBT_MASK(chunkidx) & irbp->ir_free)
 			continue;
-		}
-
-		/*
-		 * Count used inodes as free so we can tell when the
-		 * chunk is used up.
-		 */
-		irbp->ir_freecount++;
 
 		/* Get the inode and fill in a single buffer */
 		ubused = statstruct_size;
-		error = formatter(mp, ino, *ubufp, ubleft, &ubused, &fmterror);
-		if (fmterror == BULKSTAT_RV_NOTHING) {
-			if (error && error != -ENOENT && error != -EINVAL) {
-				ubleft = 0;
-				break;
-			}
-			lastino = ino;
-			continue;
-		}
-		if (fmterror == BULKSTAT_RV_GIVEUP) {
-			ubleft = 0;
+		error = formatter(mp, XFS_AGINO_TO_INO(mp, agno, agino),
+				  *ubufp, acp->ac_ubleft, &ubused, &fmterror);
+
+		if (fmterror == BULKSTAT_RV_GIVEUP ||
+		    (error && error != -ENOENT && error != -EINVAL)) {
+			acp->ac_ubleft = 0;
 			ASSERT(error);
 			break;
 		}
-		if (*ubufp)
-			*ubufp += ubused;
-		ubleft -= ubused;
-		ubelem++;
-		lastino = ino;
+
+		/* be careful not to leak error if at end of chunk */
+		if (fmterror == BULKSTAT_RV_NOTHING || error) {
+			error = 0;
+			continue;
+		}
+
+		*ubufp += ubused;
+		acp->ac_ubleft -= ubused;
+		acp->ac_ubelem++;
 	}
 
-	acp->ac_lastino = lastino;
-	acp->ac_ubleft = ubleft;
-	acp->ac_ubelem = ubelem;
+	/*
+	 * Post-update *last_agino. At this point, agino will always point one
+	 * inode past the last inode we processed successfully. Hence we
+	 * substract that inode when setting the *last_agino cursor so that we
+	 * return the correct cookie to userspace. On the next bulkstat call,
+	 * the inode under the lastino cookie will be skipped as we have already
+	 * processed it here.
+	 */
+	*last_agino = agino - 1;
 
 	return error;
 }
@@ -353,45 +356,33 @@ xfs_bulkstat(
 	xfs_agino_t		agino;	/* inode # in allocation group */
 	xfs_agnumber_t		agno;	/* allocation group number */
 	xfs_btree_cur_t		*cur;	/* btree cursor for ialloc btree */
-	int			end_of_ag; /* set if we've seen the ag end */
-	int			error;	/* error code */
-	int                     fmterror;/* bulkstat formatter result */
-	int			i;	/* loop index */
-	int			icount;	/* count of inodes good in irbuf */
 	size_t			irbsize; /* size of irec buffer in bytes */
-	xfs_ino_t		ino;	/* inode number (filesystem) */
-	xfs_inobt_rec_incore_t	*irbp;	/* current irec buffer pointer */
 	xfs_inobt_rec_incore_t	*irbuf;	/* start of irec buffer */
-	xfs_inobt_rec_incore_t	*irbufend; /* end of good irec buffer entries */
-	xfs_ino_t		lastino; /* last inode number returned */
 	int			nirbuf;	/* size of irbuf */
-	int			rval;	/* return value error code */
-	int			tmp;	/* result value from btree calls */
 	int			ubcount; /* size of user's buffer */
-	int			ubleft;	/* bytes left in user's buffer */
-	char			__user *ubufp;	/* pointer into user's buffer */
-	int			ubelem;	/* spaces used in user's buffer */
+	struct xfs_bulkstat_agichunk ac;
+	int			error = 0;
 
 	/*
 	 * Get the last inode value, see if there's nothing to do.
 	 */
-	ino = (xfs_ino_t)*lastinop;
-	lastino = ino;
-	agno = XFS_INO_TO_AGNO(mp, ino);
-	agino = XFS_INO_TO_AGINO(mp, ino);
+	agno = XFS_INO_TO_AGNO(mp, *lastinop);
+	agino = XFS_INO_TO_AGINO(mp, *lastinop);
 	if (agno >= mp->m_sb.sb_agcount ||
-	    ino != XFS_AGINO_TO_INO(mp, agno, agino)) {
+	    *lastinop != XFS_AGINO_TO_INO(mp, agno, agino)) {
 		*done = 1;
 		*ubcountp = 0;
 		return 0;
 	}
 
 	ubcount = *ubcountp; /* statstruct's */
-	ubleft = ubcount * statstruct_size; /* bytes */
-	*ubcountp = ubelem = 0;
+	ac.ac_ubuffer = &ubuffer;
+	ac.ac_ubleft = ubcount * statstruct_size; /* bytes */;
+	ac.ac_ubelem = 0;
+
+	*ubcountp = 0;
 	*done = 0;
-	fmterror = 0;
-	ubufp = ubuffer;
+
 	irbuf = kmem_zalloc_greedy(&irbsize, PAGE_SIZE, PAGE_SIZE * 4);
 	if (!irbuf)
 		return -ENOMEM;
@@ -402,9 +393,13 @@ xfs_bulkstat(
 	 * Loop over the allocation groups, starting from the last
 	 * inode returned; 0 means start of the allocation group.
 	 */
-	rval = 0;
-	while (XFS_BULKSTAT_UBLEFT(ubleft) && agno < mp->m_sb.sb_agcount) {
-		cond_resched();
+	while (agno < mp->m_sb.sb_agcount) {
+		struct xfs_inobt_rec_incore	*irbp = irbuf;
+		struct xfs_inobt_rec_incore	*irbufend = irbuf + nirbuf;
+		bool				end_of_ag = false;
+		int				icount = 0;
+		int				stat;
+
 		error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp);
 		if (error)
 			break;
@@ -414,10 +409,6 @@ xfs_bulkstat(
 		 */
 		cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno,
 					    XFS_BTNUM_INO);
-		irbp = irbuf;
-		irbufend = irbuf + nirbuf;
-		end_of_ag = 0;
-		icount = 0;
 		if (agino > 0) {
 			/*
 			 * In the middle of an allocation group, we need to get
@@ -427,22 +418,23 @@ xfs_bulkstat(
 
 			error = xfs_bulkstat_grab_ichunk(cur, agino, &icount, &r);
 			if (error)
-				break;
+				goto del_cursor;
 			if (icount) {
 				irbp->ir_startino = r.ir_startino;
 				irbp->ir_freecount = r.ir_freecount;
 				irbp->ir_free = r.ir_free;
 				irbp++;
-				agino = r.ir_startino + XFS_INODES_PER_CHUNK;
 			}
 			/* Increment to the next record */
-			error = xfs_btree_increment(cur, 0, &tmp);
+			error = xfs_btree_increment(cur, 0, &stat);
 		} else {
 			/* Start of ag.  Lookup the first inode chunk */
-			error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &tmp);
+			error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &stat);
+		}
+		if (error || stat == 0) {
+			end_of_ag = true;
+			goto del_cursor;
 		}
-		if (error)
-			break;
 
 		/*
 		 * Loop through inode btree records in this ag,
@@ -451,10 +443,10 @@ xfs_bulkstat(
 		while (irbp < irbufend && icount < ubcount) {
 			struct xfs_inobt_rec_incore	r;
 
-			error = xfs_inobt_get_rec(cur, &r, &i);
-			if (error || i == 0) {
-				end_of_ag = 1;
-				break;
+			error = xfs_inobt_get_rec(cur, &r, &stat);
+			if (error || stat == 0) {
+				end_of_ag = true;
+				goto del_cursor;
 			}
 
 			/*
@@ -469,77 +461,79 @@ xfs_bulkstat(
 				irbp++;
 				icount += XFS_INODES_PER_CHUNK - r.ir_freecount;
 			}
-			/*
-			 * Set agino to after this chunk and bump the cursor.
-			 */
-			agino = r.ir_startino + XFS_INODES_PER_CHUNK;
-			error = xfs_btree_increment(cur, 0, &tmp);
+			error = xfs_btree_increment(cur, 0, &stat);
+			if (error || stat == 0) {
+				end_of_ag = true;
+				goto del_cursor;
+			}
 			cond_resched();
 		}
+
 		/*
-		 * Drop the btree buffers and the agi buffer.
-		 * We can't hold any of the locks these represent
-		 * when calling iget.
+		 * Drop the btree buffers and the agi buffer as we can't hold any
+		 * of the locks these represent when calling iget. If there is a
+		 * pending error, then we are done.
 		 */
+del_cursor:
 		xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 		xfs_buf_relse(agbp);
+		if (error)
+			break;
 		/*
-		 * Now format all the good inodes into the user's buffer.
+		 * Now format all the good inodes into the user's buffer. The
+		 * call to xfs_bulkstat_ag_ichunk() sets up the agino pointer
+		 * for the next loop iteration.
 		 */
 		irbufend = irbp;
 		for (irbp = irbuf;
-		     irbp < irbufend && XFS_BULKSTAT_UBLEFT(ubleft); irbp++) {
-			struct xfs_bulkstat_agichunk ac;
-
-			ac.ac_lastino = lastino;
-			ac.ac_ubuffer = &ubuffer;
-			ac.ac_ubleft = ubleft;
-			ac.ac_ubelem = ubelem;
+		     irbp < irbufend && ac.ac_ubleft >= statstruct_size;
+		     irbp++) {
 			error = xfs_bulkstat_ag_ichunk(mp, agno, irbp,
-					formatter, statstruct_size, &ac);
+					formatter, statstruct_size, &ac,
+					&agino);
 			if (error)
-				rval = error;
-
-			lastino = ac.ac_lastino;
-			ubleft = ac.ac_ubleft;
-			ubelem = ac.ac_ubelem;
+				break;
 
 			cond_resched();
 		}
+
 		/*
-		 * Set up for the next loop iteration.
+		 * If we've run out of space or had a formatting error, we
+		 * are now done
 		 */
-		if (XFS_BULKSTAT_UBLEFT(ubleft)) {
-			if (end_of_ag) {
-				agno++;
-				agino = 0;
-			} else
-				agino = XFS_INO_TO_AGINO(mp, lastino);
-		} else
+		if (ac.ac_ubleft < statstruct_size || error)
 			break;
+
+		if (end_of_ag) {
+			agno++;
+			agino = 0;
+		}
 	}
 	/*
 	 * Done, we're either out of filesystem or space to put the data.
 	 */
 	kmem_free(irbuf);
-	*ubcountp = ubelem;
+	*ubcountp = ac.ac_ubelem;
+
 	/*
-	 * Found some inodes, return them now and return the error next time.
+	 * We found some inodes, so clear the error status and return them.
+	 * The lastino pointer will point directly at the inode that triggered
+	 * any error that occurred, so on the next call the error will be
+	 * triggered again and propagated to userspace as there will be no
+	 * formatted inodes in the buffer.
 	 */
-	if (ubelem)
-		rval = 0;
-	if (agno >= mp->m_sb.sb_agcount) {
-		/*
-		 * If we ran out of filesystem, mark lastino as off
-		 * the end of the filesystem, so the next call
-		 * will return immediately.
-		 */
-		*lastinop = (xfs_ino_t)XFS_AGINO_TO_INO(mp, agno, 0);
+	if (ac.ac_ubelem)
+		error = 0;
+
+	/*
+	 * If we ran out of filesystem, lastino will point off the end of
+	 * the filesystem so the next call will return immediately.
+	 */
+	*lastinop = XFS_AGINO_TO_INO(mp, agno, agino);
+	if (agno >= mp->m_sb.sb_agcount)
 		*done = 1;
-	} else
-		*lastinop = (xfs_ino_t)lastino;
 
-	return rval;
+	return error;
 }
 
 int
diff --git a/fs/xfs/xfs_itable.h b/fs/xfs/xfs_itable.h
index aaed08022eb9..6ea8b3912fa4 100644
--- a/fs/xfs/xfs_itable.h
+++ b/fs/xfs/xfs_itable.h
@@ -30,22 +30,6 @@ typedef int (*bulkstat_one_pf)(struct xfs_mount	*mp,
 			       int		*ubused,
 			       int		*stat);
 
-struct xfs_bulkstat_agichunk {
-	xfs_ino_t	ac_lastino;	/* last inode returned */
-	char		__user **ac_ubuffer;/* pointer into user's buffer */
-	int		ac_ubleft;	/* bytes left in user's buffer */
-	int		ac_ubelem;	/* spaces used in user's buffer */
-};
-
-int
-xfs_bulkstat_ag_ichunk(
-	struct xfs_mount		*mp,
-	xfs_agnumber_t			agno,
-	struct xfs_inobt_rec_incore	*irbp,
-	bulkstat_one_pf			formatter,
-	size_t				statstruct_size,
-	struct xfs_bulkstat_agichunk	*acp);
-
 /*
  * Values for stat return value.
  */