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

Pull ext4 updates from Ted Ts'o:
 "A large number of bug fixes and cleanups.

  One new feature to allow users to more easily find the jbd2 journal
  thread for a particular ext4 file system"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (25 commits)
  jbd2: jbd2_get_transaction does not need to return a value
  jbd2: fix invalid descriptor block checksum
  ext4: fix bigalloc cluster freeing when hole punching under load
  ext4: add sysfs attr /sys/fs/ext4/<disk>/journal_task
  ext4: Change debugging support help prefix from EXT4 to Ext4
  ext4: fix compile error when using BUFFER_TRACE
  jbd2: fix compile warning when using JBUFFER_TRACE
  ext4: fix some error pointer dereferences
  ext4: annotate more implicit fall throughs
  ext4: annotate implicit fall throughs
  ext4: don't update s_rev_level if not required
  jbd2: fold jbd2_superblock_csum_{verify,set} into their callers
  jbd2: fix race when writing superblock
  ext4: fix crash during online resizing
  ext4: disallow files with EXT4_JOURNAL_DATA_FL from EXT4_IOC_SWAP_BOOT
  ext4: add mask of ext4 flags to swap
  ext4: update quota information while swapping boot loader inode
  ext4: cleanup pagecache before swap i_data
  ext4: fix check of inode in swap_inode_boot_loader
  ext4: unlock unused_pages timely when doing writeback
  ...

Documentation/ABI/testing/sysfs-fs-ext4

@@ -109,3 +109,10 @@ Description:
 		write operation (since a 4k random write might turn
 		into a much larger write due to the zeroout
 		operation).
+
+What:		/sys/fs/ext4/<disk>/journal_task
+Date:		February 2019
+Contact:	"Theodore Ts'o" <tytso@mit.edu>
+Description:
+		This file is read-only and shows the pid of journal thread in
+		current pid-namespace or 0 if task is unreachable.

fs/ext4/Kconfig

@@ -97,7 +97,7 @@ config EXT4_FS_SECURITY
 	  extended attributes for file security labels, say N.
 
 config EXT4_DEBUG
-	bool "EXT4 debugging support"
+	bool "Ext4 debugging support"
 	depends on EXT4_FS
 	help
 	  Enables run-time debugging support for the ext4 filesystem.

fs/ext4/ext4.h

@@ -425,6 +425,9 @@ struct flex_groups {
 /* Flags that are appropriate for non-directories/regular files. */
 #define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL)
 
+/* The only flags that should be swapped */
+#define EXT4_FL_SHOULD_SWAP (EXT4_HUGE_FILE_FL | EXT4_EXTENTS_FL)
+
 /* Mask out flags that are inappropriate for the given type of inode. */
 static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
 {
@@ -1661,6 +1664,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 #define EXT4_FEATURE_INCOMPAT_INLINE_DATA	0x8000 /* data in inode */
 #define EXT4_FEATURE_INCOMPAT_ENCRYPT		0x10000
 
+extern void ext4_update_dynamic_rev(struct super_block *sb);
+
 #define EXT4_FEATURE_COMPAT_FUNCS(name, flagname) \
 static inline bool ext4_has_feature_##name(struct super_block *sb) \
 { \
@@ -1669,6 +1674,7 @@ static inline bool ext4_has_feature_##name(struct super_block *sb) \
 } \
 static inline void ext4_set_feature_##name(struct super_block *sb) \
 { \
+	ext4_update_dynamic_rev(sb); \
 	EXT4_SB(sb)->s_es->s_feature_compat |= \
 		cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname); \
 } \
@@ -1686,6 +1692,7 @@ static inline bool ext4_has_feature_##name(struct super_block *sb) \
 } \
 static inline void ext4_set_feature_##name(struct super_block *sb) \
 { \
+	ext4_update_dynamic_rev(sb); \
 	EXT4_SB(sb)->s_es->s_feature_ro_compat |= \
 		cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname); \
 } \
@@ -1703,6 +1710,7 @@ static inline bool ext4_has_feature_##name(struct super_block *sb) \
 } \
 static inline void ext4_set_feature_##name(struct super_block *sb) \
 { \
+	ext4_update_dynamic_rev(sb); \
 	EXT4_SB(sb)->s_es->s_feature_incompat |= \
 		cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname); \
 } \
@@ -2666,7 +2674,6 @@ do {									\
 
 #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);
 extern int ext4_update_rocompat_feature(handle_t *handle,

fs/ext4/extents.c

@@ -2956,14 +2956,17 @@ int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
 			if (err < 0)
 				goto out;
 
-		} else if (sbi->s_cluster_ratio > 1 && end >= ex_end) {
+		} else if (sbi->s_cluster_ratio > 1 && end >= ex_end &&
+			   partial.state == initial) {
 			/*
-			 * If there's an extent to the right its first cluster
-			 * contains the immediate right boundary of the
-			 * truncated/punched region.  Set partial_cluster to
-			 * its negative value so it won't be freed if shared
-			 * with the current extent.  The end < ee_block case
-			 * is handled in ext4_ext_rm_leaf().
+			 * If we're punching, there's an extent to the right.
+			 * If the partial cluster hasn't been set, set it to
+			 * that extent's first cluster and its state to nofree
+			 * so it won't be freed should it contain blocks to be
+			 * removed. If it's already set (tofree/nofree), we're
+			 * retrying and keep the original partial cluster info
+			 * so a cluster marked tofree as a result of earlier
+			 * extent removal is not lost.
 			 */
 			lblk = ex_end + 1;
 			err = ext4_ext_search_right(inode, path, &lblk, &pblk,
@@ -4048,18 +4051,8 @@ ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
 	} else
 		allocated = ret;
 	map->m_flags |= EXT4_MAP_NEW;
-	/*
-	 * if we allocated more blocks than requested
-	 * we need to make sure we unmap the extra block
-	 * allocated. The actual needed block will get
-	 * unmapped later when we find the buffer_head marked
-	 * new.
-	 */
-	if (allocated > map->m_len) {
-		clean_bdev_aliases(inode->i_sb->s_bdev, newblock + map->m_len,
-				   allocated - map->m_len);
+	if (allocated > map->m_len)
 		allocated = map->m_len;
-	}
 	map->m_len = allocated;
 
 map_out:

fs/ext4/hash.c

@@ -231,6 +231,7 @@ int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 		break;
 	case DX_HASH_HALF_MD4_UNSIGNED:
 		str2hashbuf = str2hashbuf_unsigned;
+		/* fall through */
 	case DX_HASH_HALF_MD4:
 		p = name;
 		while (len > 0) {
@@ -244,6 +245,7 @@ int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
 		break;
 	case DX_HASH_TEA_UNSIGNED:
 		str2hashbuf = str2hashbuf_unsigned;
+		/* fall through */
 	case DX_HASH_TEA:
 		p = name;
 		while (len > 0) {

fs/ext4/indirect.c

@@ -1183,18 +1183,21 @@ void ext4_ind_truncate(handle_t *handle, struct inode *inode)
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
 			i_data[EXT4_IND_BLOCK] = 0;
 		}
+		/* fall through */
 	case EXT4_IND_BLOCK:
 		nr = i_data[EXT4_DIND_BLOCK];
 		if (nr) {
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
 			i_data[EXT4_DIND_BLOCK] = 0;
 		}
+		/* fall through */
 	case EXT4_DIND_BLOCK:
 		nr = i_data[EXT4_TIND_BLOCK];
 		if (nr) {
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
 			i_data[EXT4_TIND_BLOCK] = 0;
 		}
+		/* fall through */
 	case EXT4_TIND_BLOCK:
 		;
 	}
@@ -1433,6 +1436,7 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
 			i_data[EXT4_IND_BLOCK] = 0;
 		}
+		/* fall through */
 	case EXT4_IND_BLOCK:
 		if (++n >= n2)
 			return 0;
@@ -1441,6 +1445,7 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
 			i_data[EXT4_DIND_BLOCK] = 0;
 		}
+		/* fall through */
 	case EXT4_DIND_BLOCK:
 		if (++n >= n2)
 			return 0;
@@ -1449,6 +1454,7 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
 			i_data[EXT4_TIND_BLOCK] = 0;
 		}
+		/* fall through */
 	case EXT4_TIND_BLOCK:
 		;
 	}

fs/ext4/inode.c

@@ -391,7 +391,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
 	 * inode's preallocations.
 	 */
 	if ((ei->i_reserved_data_blocks == 0) &&
-	    (atomic_read(&inode->i_writecount) == 0))
+	    !inode_is_open_for_write(inode))
 		ext4_discard_preallocations(inode);
 }
 
@@ -678,8 +678,6 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		if (flags & EXT4_GET_BLOCKS_ZERO &&
 		    map->m_flags & EXT4_MAP_MAPPED &&
 		    map->m_flags & EXT4_MAP_NEW) {
-			clean_bdev_aliases(inode->i_sb->s_bdev, map->m_pblk,
-					   map->m_len);
 			ret = ext4_issue_zeroout(inode, map->m_lblk,
 						 map->m_pblk, map->m_len);
 			if (ret) {
@@ -1194,7 +1192,6 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len,
 			if (err)
 				break;
 			if (buffer_new(bh)) {
-				clean_bdev_bh_alias(bh);
 				if (PageUptodate(page)) {
 					clear_buffer_new(bh);
 					set_buffer_uptodate(bh);
@@ -2489,10 +2486,6 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
 	}
 
 	BUG_ON(map->m_len == 0);
-	if (map->m_flags & EXT4_MAP_NEW) {
-		clean_bdev_aliases(inode->i_sb->s_bdev, map->m_pblk,
-				   map->m_len);
-	}
 	return 0;
 }
 
@@ -2835,12 +2828,12 @@ static int ext4_writepages(struct address_space *mapping,
 		goto unplug;
 	}
 	ret = mpage_prepare_extent_to_map(&mpd);
+	/* Unlock pages we didn't use */
+	mpage_release_unused_pages(&mpd, false);
 	/* Submit prepared bio */
 	ext4_io_submit(&mpd.io_submit);
 	ext4_put_io_end_defer(mpd.io_submit.io_end);
 	mpd.io_submit.io_end = NULL;
-	/* Unlock pages we didn't use */
-	mpage_release_unused_pages(&mpd, false);
 	if (ret < 0)
 		goto unplug;
 
@@ -2908,10 +2901,11 @@ static int ext4_writepages(struct address_space *mapping,
 			handle = NULL;
 			mpd.do_map = 0;
 		}
-		/* Submit prepared bio */
-		ext4_io_submit(&mpd.io_submit);
 		/* Unlock pages we didn't use */
 		mpage_release_unused_pages(&mpd, give_up_on_write);
+		/* Submit prepared bio */
+		ext4_io_submit(&mpd.io_submit);
+
 		/*
 		 * Drop our io_end reference we got from init. We have
 		 * to be careful and use deferred io_end finishing if
@@ -5349,7 +5343,6 @@ static int ext4_do_update_inode(handle_t *handle,
 		err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
 		if (err)
 			goto out_brelse;
-		ext4_update_dynamic_rev(sb);
 		ext4_set_feature_large_file(sb);
 		ext4_handle_sync(handle);
 		err = ext4_handle_dirty_super(handle, sb);
@@ -6000,7 +5993,7 @@ int ext4_expand_extra_isize(struct inode *inode,
 
 	ext4_write_lock_xattr(inode, &no_expand);
 
-	BUFFER_TRACE(iloc.bh, "get_write_access");
+	BUFFER_TRACE(iloc->bh, "get_write_access");
 	error = ext4_journal_get_write_access(handle, iloc->bh);
 	if (error) {
 		brelse(iloc->bh);

fs/ext4/ioctl.c

@@ -63,18 +63,20 @@ static void swap_inode_data(struct inode *inode1, struct inode *inode2)
 	loff_t isize;
 	struct ext4_inode_info *ei1;
 	struct ext4_inode_info *ei2;
+	unsigned long tmp;
 
 	ei1 = EXT4_I(inode1);
 	ei2 = EXT4_I(inode2);
 
 	swap(inode1->i_version, inode2->i_version);
-	swap(inode1->i_blocks, inode2->i_blocks);
-	swap(inode1->i_bytes, inode2->i_bytes);
 	swap(inode1->i_atime, inode2->i_atime);
 	swap(inode1->i_mtime, inode2->i_mtime);
 
 	memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data));
-	swap(ei1->i_flags, ei2->i_flags);
+	tmp = ei1->i_flags & EXT4_FL_SHOULD_SWAP;
+	ei1->i_flags = (ei2->i_flags & EXT4_FL_SHOULD_SWAP) |
+		(ei1->i_flags & ~EXT4_FL_SHOULD_SWAP);
+	ei2->i_flags = tmp | (ei2->i_flags & ~EXT4_FL_SHOULD_SWAP);
 	swap(ei1->i_disksize, ei2->i_disksize);
 	ext4_es_remove_extent(inode1, 0, EXT_MAX_BLOCKS);
 	ext4_es_remove_extent(inode2, 0, EXT_MAX_BLOCKS);
@@ -115,28 +117,42 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	int err;
 	struct inode *inode_bl;
 	struct ext4_inode_info *ei_bl;
-
-	if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode) ||
-	    IS_SWAPFILE(inode) || IS_ENCRYPTED(inode) ||
-	    ext4_has_inline_data(inode))
-		return -EINVAL;
-
-	if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) ||
-	    !inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN))
-		return -EPERM;
+	qsize_t size, size_bl, diff;
+	blkcnt_t blocks;
+	unsigned short bytes;
 
 	inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO, EXT4_IGET_SPECIAL);
 	if (IS_ERR(inode_bl))
 		return PTR_ERR(inode_bl);
 	ei_bl = EXT4_I(inode_bl);
 
-	filemap_flush(inode->i_mapping);
-	filemap_flush(inode_bl->i_mapping);
-
 	/* Protect orig inodes against a truncate and make sure,
 	 * that only 1 swap_inode_boot_loader is running. */
 	lock_two_nondirectories(inode, inode_bl);
 
+	if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode) ||
+	    IS_SWAPFILE(inode) || IS_ENCRYPTED(inode) ||
+	    (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) ||
+	    ext4_has_inline_data(inode)) {
+		err = -EINVAL;
+		goto journal_err_out;
+	}
+
+	if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) ||
+	    !inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) {
+		err = -EPERM;
+		goto journal_err_out;
+	}
+
+	down_write(&EXT4_I(inode)->i_mmap_sem);
+	err = filemap_write_and_wait(inode->i_mapping);
+	if (err)
+		goto err_out;
+
+	err = filemap_write_and_wait(inode_bl->i_mapping);
+	if (err)
+		goto err_out;
+
 	/* Wait for all existing dio workers */
 	inode_dio_wait(inode);
 	inode_dio_wait(inode_bl);
@@ -147,7 +163,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
 	if (IS_ERR(handle)) {
 		err = -EINVAL;
-		goto journal_err_out;
+		goto err_out;
 	}
 
 	/* Protect extent tree against block allocations via delalloc */
@@ -170,6 +186,13 @@ static long swap_inode_boot_loader(struct super_block *sb,
 			memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data));
 	}
 
+	err = dquot_initialize(inode);
+	if (err)
+		goto err_out1;
+
+	size = (qsize_t)(inode->i_blocks) * (1 << 9) + inode->i_bytes;
+	size_bl = (qsize_t)(inode_bl->i_blocks) * (1 << 9) + inode_bl->i_bytes;
+	diff = size - size_bl;
 	swap_inode_data(inode, inode_bl);
 
 	inode->i_ctime = inode_bl->i_ctime = current_time(inode);
@@ -183,27 +206,51 @@ static long swap_inode_boot_loader(struct super_block *sb,
 
 	err = ext4_mark_inode_dirty(handle, inode);
 	if (err < 0) {
+		/* No need to update quota information. */
 		ext4_warning(inode->i_sb,
 			"couldn't mark inode #%lu dirty (err %d)",
 			inode->i_ino, err);
 		/* Revert all changes: */
 		swap_inode_data(inode, inode_bl);
 		ext4_mark_inode_dirty(handle, inode);
-	} else {
+		goto err_out1;
+	}
+
+	blocks = inode_bl->i_blocks;
+	bytes = inode_bl->i_bytes;
+	inode_bl->i_blocks = inode->i_blocks;
+	inode_bl->i_bytes = inode->i_bytes;
 	err = ext4_mark_inode_dirty(handle, inode_bl);
 	if (err < 0) {
+		/* No need to update quota information. */
 		ext4_warning(inode_bl->i_sb,
 			"couldn't mark inode #%lu dirty (err %d)",
 			inode_bl->i_ino, err);
+		goto revert;
+	}
+
+	/* Bootloader inode should not be counted into quota information. */
+	if (diff > 0)
+		dquot_free_space(inode, diff);
+	else
+		err = dquot_alloc_space(inode, -1 * diff);
+
+	if (err < 0) {
+revert:
 		/* Revert all changes: */
+		inode_bl->i_blocks = blocks;
+		inode_bl->i_bytes = bytes;
 		swap_inode_data(inode, inode_bl);
 		ext4_mark_inode_dirty(handle, inode);
 		ext4_mark_inode_dirty(handle, inode_bl);
 	}
-	}
+
+err_out1:
 	ext4_journal_stop(handle);
 	ext4_double_up_write_data_sem(inode, inode_bl);
 
+err_out:
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 journal_err_out:
 	unlock_two_nondirectories(inode, inode_bl);
 	iput(inode_bl);

fs/ext4/mballoc.c

@@ -4176,9 +4176,8 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
 	isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1)
 		>> bsbits;
 
-	if ((size == isize) &&
-	    !ext4_fs_is_busy(sbi) &&
-	    (atomic_read(&ac->ac_inode->i_writecount) == 0)) {
+	if ((size == isize) && !ext4_fs_is_busy(sbi) &&
+	    !inode_is_open_for_write(ac->ac_inode)) {
 		ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC;
 		return;
 	}
@@ -4258,7 +4257,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac,
 			(unsigned) ar->goal, ac->ac_flags, ac->ac_2order,
 			(unsigned) ar->lleft, (unsigned) ar->pleft,
 			(unsigned) ar->lright, (unsigned) ar->pright,
-			atomic_read(&ar->inode->i_writecount) ? "" : "non-");
+			inode_is_open_for_write(ar->inode) ? "" : "non-");
 	return 0;
 
 }

fs/ext4/page-io.c

@@ -468,10 +468,8 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 				ext4_io_submit(io);
 			continue;
 		}
-		if (buffer_new(bh)) {
+		if (buffer_new(bh))
 			clear_buffer_new(bh);
-			clean_bdev_bh_alias(bh);
-		}
 		set_buffer_async_write(bh);
 		nr_to_submit++;
 	} while ((bh = bh->b_this_page) != head);

fs/ext4/resize.c

@@ -1960,7 +1960,8 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
 				le16_to_cpu(es->s_reserved_gdt_blocks);
 			n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb);
 			n_blocks_count = (ext4_fsblk_t)n_group *
-				EXT4_BLOCKS_PER_GROUP(sb);
+				EXT4_BLOCKS_PER_GROUP(sb) +
+				le32_to_cpu(es->s_first_data_block);
 			n_group--; /* set to last group number */
 		}
 

fs/ext4/super.c

@@ -2249,7 +2249,6 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 		es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
 	le16_add_cpu(&es->s_mnt_count, 1);
 	ext4_update_tstamp(es, s_mtime);
-	ext4_update_dynamic_rev(sb);
 	if (sbi->s_journal)
 		ext4_set_feature_journal_needs_recovery(sb);
 

fs/ext4/sysfs.c

@@ -30,6 +30,7 @@ typedef enum {
 	attr_feature,
 	attr_pointer_ui,
 	attr_pointer_atomic,
+	attr_journal_task,
 } attr_id_t;
 
 typedef enum {
@@ -125,6 +126,14 @@ static ssize_t trigger_test_error(struct ext4_sb_info *sbi,
 	return count;
 }
 
+static ssize_t journal_task_show(struct ext4_sb_info *sbi, char *buf)
+{
+	if (!sbi->s_journal)
+		return snprintf(buf, PAGE_SIZE, "<none>\n");
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+			task_pid_vnr(sbi->s_journal->j_task));
+}
+
 #define EXT4_ATTR(_name,_mode,_id)					\
 static struct ext4_attr ext4_attr_##_name = {				\
 	.attr = {.name = __stringify(_name), .mode = _mode },		\
@@ -188,6 +197,7 @@ EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst);
 EXT4_RO_ATTR_ES_UI(errors_count, s_error_count);
 EXT4_ATTR(first_error_time, 0444, first_error_time);
 EXT4_ATTR(last_error_time, 0444, last_error_time);
+EXT4_ATTR(journal_task, 0444, journal_task);
 
 static unsigned int old_bump_val = 128;
 EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val);
@@ -217,6 +227,7 @@ static struct attribute *ext4_attrs[] = {
 	ATTR_LIST(errors_count),
 	ATTR_LIST(first_error_time),
 	ATTR_LIST(last_error_time),
+	ATTR_LIST(journal_task),
 	NULL,
 };
 
@@ -304,6 +315,8 @@ static ssize_t ext4_attr_show(struct kobject *kobj,
 		return print_tstamp(buf, sbi->s_es, s_first_error_time);
 	case attr_last_error_time:
 		return print_tstamp(buf, sbi->s_es, s_last_error_time);
+	case attr_journal_task:
+		return journal_task_show(sbi, buf);
 	}
 
 	return 0;

fs/ext4/xattr.c

@@ -829,6 +829,7 @@ int ext4_get_inode_usage(struct inode *inode, qsize_t *usage)
 		bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO);
 		if (IS_ERR(bh)) {
 			ret = PTR_ERR(bh);
+			bh = NULL;
 			goto out;
 		}
 
@@ -2903,6 +2904,7 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
 			if (error == -EIO)
 				EXT4_ERROR_INODE(inode, "block %llu read error",
 						 EXT4_I(inode)->i_file_acl);
+			bh = NULL;
 			goto cleanup;
 		}
 		error = ext4_xattr_check_block(inode, bh);
@@ -3059,6 +3061,7 @@ ext4_xattr_block_cache_find(struct inode *inode,
 		if (IS_ERR(bh)) {
 			if (PTR_ERR(bh) == -ENOMEM)
 				return NULL;
+			bh = NULL;
 			EXT4_ERROR_INODE(inode, "block %lu read error",
 					 (unsigned long)ce->e_value);
 		} else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) {

fs/jbd2/checkpoint.c

@@ -113,7 +113,7 @@ void __jbd2_log_wait_for_space(journal_t *journal)
 	nblocks = jbd2_space_needed(journal);
 	while (jbd2_log_space_left(journal) < nblocks) {
 		write_unlock(&journal->j_state_lock);
-		mutex_lock(&journal->j_checkpoint_mutex);
+		mutex_lock_io(&journal->j_checkpoint_mutex);
 
 		/*
 		 * Test again, another process may have checkpointed while we
@@ -276,9 +276,22 @@ int jbd2_log_do_checkpoint(journal_t *journal)
 		"JBD2: %s: Waiting for Godot: block %llu\n",
 		journal->j_devname, (unsigned long long) bh->b_blocknr);
 
+			if (batch_count)
+				__flush_batch(journal, &batch_count);
 			jbd2_log_start_commit(journal, tid);
+			/*
+			 * jbd2_journal_commit_transaction() may want
+			 * to take the checkpoint_mutex if JBD2_FLUSHED
+			 * is set, jbd2_update_log_tail() called by
+			 * jbd2_journal_commit_transaction() may also take
+			 * checkpoint_mutex.  So we need to temporarily
+			 * drop it.
+			 */
+			mutex_unlock(&journal->j_checkpoint_mutex);
 			jbd2_log_wait_commit(journal, tid);
-			goto retry;
+			mutex_lock_io(&journal->j_checkpoint_mutex);
+			spin_lock(&journal->j_list_lock);
+			goto restart;
 		}
 		if (!buffer_dirty(bh)) {
 			if (unlikely(buffer_write_io_error(bh)) && !result)

fs/jbd2/commit.c

@@ -694,9 +694,11 @@ void jbd2_journal_commit_transaction(journal_t *journal)
                            the last tag we set up. */
 
 			tag->t_flags |= cpu_to_be16(JBD2_FLAG_LAST_TAG);
-
-			jbd2_descriptor_block_csum_set(journal, descriptor);
 start_journal_io:
+			if (descriptor)
+				jbd2_descriptor_block_csum_set(journal,
+							descriptor);
+
 			for (i = 0; i < bufs; i++) {
 				struct buffer_head *bh = wbuf[i];
 				/*

fs/jbd2/journal.c

@@ -142,22 +142,6 @@ static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb)
 	return cpu_to_be32(csum);
 }
 
-static int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
-{
-	if (!jbd2_journal_has_csum_v2or3(j))
-		return 1;
-
-	return sb->s_checksum == jbd2_superblock_csum(j, sb);
-}
-
-static void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb)
-{
-	if (!jbd2_journal_has_csum_v2or3(j))
-		return;
-
-	sb->s_checksum = jbd2_superblock_csum(j, sb);
-}
-
 /*
  * Helper function used to manage commit timeouts
  */
@@ -1356,6 +1340,10 @@ static int journal_reset(journal_t *journal)
 	return jbd2_journal_start_thread(journal);
 }
 
+/*
+ * This function expects that the caller will have locked the journal
+ * buffer head, and will return with it unlocked
+ */
 static int jbd2_write_superblock(journal_t *journal, int write_flags)
 {
 	struct buffer_head *bh = journal->j_sb_buffer;
@@ -1365,7 +1353,6 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags)
 	trace_jbd2_write_superblock(journal, write_flags);
 	if (!(journal->j_flags & JBD2_BARRIER))
 		write_flags &= ~(REQ_FUA | REQ_PREFLUSH);
-	lock_buffer(bh);
 	if (buffer_write_io_error(bh)) {
 		/*
 		 * Oh, dear.  A previous attempt to write the journal
@@ -1381,7 +1368,8 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags)
 		clear_buffer_write_io_error(bh);
 		set_buffer_uptodate(bh);
 	}
-	jbd2_superblock_csum_set(journal, sb);
+	if (jbd2_journal_has_csum_v2or3(journal))
+		sb->s_checksum = jbd2_superblock_csum(journal, sb);
 	get_bh(bh);
 	bh->b_end_io = end_buffer_write_sync;
 	ret = submit_bh(REQ_OP_WRITE, write_flags, bh);
@@ -1424,6 +1412,7 @@ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
 	jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n",
 		  tail_block, tail_tid);
 
+	lock_buffer(journal->j_sb_buffer);
 	sb->s_sequence = cpu_to_be32(tail_tid);
 	sb->s_start    = cpu_to_be32(tail_block);
 
@@ -1454,18 +1443,17 @@ static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
 	journal_superblock_t *sb = journal->j_superblock;
 
 	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
-	read_lock(&journal->j_state_lock);
-	/* Is it already empty? */
-	if (sb->s_start == 0) {
-		read_unlock(&journal->j_state_lock);
+	lock_buffer(journal->j_sb_buffer);
+	if (sb->s_start == 0) {		/* Is it already empty? */
+		unlock_buffer(journal->j_sb_buffer);
 		return;
 	}
+
 	jbd_debug(1, "JBD2: Marking journal as empty (seq %d)\n",
 		  journal->j_tail_sequence);
 
 	sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
 	sb->s_start    = cpu_to_be32(0);
-	read_unlock(&journal->j_state_lock);
 
 	jbd2_write_superblock(journal, write_op);
 
@@ -1488,9 +1476,8 @@ void jbd2_journal_update_sb_errno(journal_t *journal)
 	journal_superblock_t *sb = journal->j_superblock;
 	int errcode;
 
-	read_lock(&journal->j_state_lock);
+	lock_buffer(journal->j_sb_buffer);
 	errcode = journal->j_errno;
-	read_unlock(&journal->j_state_lock);
 	if (errcode == -ESHUTDOWN)
 		errcode = 0;
 	jbd_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode);
@@ -1595,17 +1582,18 @@ static int journal_get_superblock(journal_t *journal)
 		}
 	}
 
+	if (jbd2_journal_has_csum_v2or3(journal)) {
 		/* Check superblock checksum */
-	if (!jbd2_superblock_csum_verify(journal, sb)) {
+		if (sb->s_checksum != jbd2_superblock_csum(journal, sb)) {
 			printk(KERN_ERR "JBD2: journal checksum error\n");
 			err = -EFSBADCRC;
 			goto out;
 		}
 
 		/* Precompute checksum seed for all metadata */
-	if (jbd2_journal_has_csum_v2or3(journal))
 		journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid,
 						   sizeof(sb->s_uuid));
+	}
 
 	set_buffer_verified(bh);
 
@@ -1894,28 +1882,27 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 
 	sb = journal->j_superblock;
 
-	/* If enabling v3 checksums, update superblock */
-	if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
-		sb->s_checksum_type = JBD2_CRC32C_CHKSUM;
-		sb->s_feature_compat &=
-			~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM);
-
-		/* Load the checksum driver */
-		if (journal->j_chksum_driver == NULL) {
-			journal->j_chksum_driver = crypto_alloc_shash("crc32c",
-								      0, 0);
+	/* Load the checksum driver if necessary */
+	if ((journal->j_chksum_driver == NULL) &&
+	    INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
+		journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
 		if (IS_ERR(journal->j_chksum_driver)) {
-				printk(KERN_ERR "JBD2: Cannot load crc32c "
-				       "driver.\n");
+			printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n");
 			journal->j_chksum_driver = NULL;
 			return 0;
 		}
-
 		/* Precompute checksum seed for all metadata */
-			journal->j_csum_seed = jbd2_chksum(journal, ~0,
-							   sb->s_uuid,
+		journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid,
 						   sizeof(sb->s_uuid));
 	}
+
+	lock_buffer(journal->j_sb_buffer);
+
+	/* If enabling v3 checksums, update superblock */
+	if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
+		sb->s_checksum_type = JBD2_CRC32C_CHKSUM;
+		sb->s_feature_compat &=
+			~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM);
 	}
 
 	/* If enabling v1 checksums, downgrade superblock */
@@ -1927,6 +1914,7 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 	sb->s_feature_compat    |= cpu_to_be32(compat);
 	sb->s_feature_ro_compat |= cpu_to_be32(ro);
 	sb->s_feature_incompat  |= cpu_to_be32(incompat);
+	unlock_buffer(journal->j_sb_buffer);
 
 	return 1;
 #undef COMPAT_FEATURE_ON
@@ -2067,7 +2055,7 @@ int jbd2_journal_wipe(journal_t *journal, int write)
 	err = jbd2_journal_skip_recovery(journal);
 	if (write) {
 		/* Lock to make assertions happy... */
-		mutex_lock(&journal->j_checkpoint_mutex);
+		mutex_lock_io(&journal->j_checkpoint_mutex);
 		jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 	}

fs/jbd2/transaction.c

@@ -63,7 +63,7 @@ void jbd2_journal_free_transaction(transaction_t *transaction)
 /*
  * jbd2_get_transaction: obtain a new transaction_t object.
  *
- * Simply allocate and initialise a new transaction.  Create it in
+ * Simply initialise a new transaction. Initialize it in
  * RUNNING state and add it to the current journal (which should not
  * have an existing running transaction: we only make a new transaction
  * once we have started to commit the old one).
@@ -75,8 +75,8 @@ void jbd2_journal_free_transaction(transaction_t *transaction)
  *
  */
 
-static transaction_t *
-jbd2_get_transaction(journal_t *journal, transaction_t *transaction)
+static void jbd2_get_transaction(journal_t *journal,
+				transaction_t *transaction)
 {
 	transaction->t_journal = journal;
 	transaction->t_state = T_RUNNING;
@@ -100,8 +100,6 @@ jbd2_get_transaction(journal_t *journal, transaction_t *transaction)
 	transaction->t_max_wait = 0;
 	transaction->t_start = jiffies;
 	transaction->t_requested = 0;
-
-	return transaction;
 }
 
 /*
@@ -1252,11 +1250,12 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
 	struct journal_head *jh;
 	char *committed_data = NULL;
 
-	JBUFFER_TRACE(jh, "entry");
 	if (jbd2_write_access_granted(handle, bh, true))
 		return 0;
 
 	jh = jbd2_journal_add_journal_head(bh);
+	JBUFFER_TRACE(jh, "entry");
+
 	/*
 	 * Do this first --- it can drop the journal lock, so we want to
 	 * make sure that obtaining the committed_data is done
@@ -1367,15 +1366,17 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 
 	if (is_handle_aborted(handle))
 		return -EROFS;
-	if (!buffer_jbd(bh)) {
-		ret = -EUCLEAN;
-		goto out;
-	}
+	if (!buffer_jbd(bh))
+		return -EUCLEAN;
+
 	/*
 	 * We don't grab jh reference here since the buffer must be part
 	 * of the running transaction.
 	 */
 	jh = bh2jh(bh);
+	jbd_debug(5, "journal_head %p\n", jh);
+	JBUFFER_TRACE(jh, "entry");
+
 	/*
 	 * This and the following assertions are unreliable since we may see jh
 	 * in inconsistent state unless we grab bh_state lock. But this is
@@ -1409,9 +1410,6 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 	}
 
 	journal = transaction->t_journal;
-	jbd_debug(5, "journal_head %p\n", jh);
-	JBUFFER_TRACE(jh, "entry");
-
 	jbd_lock_bh_state(bh);
 
 	if (jh->b_modified == 0) {
@@ -1597,9 +1595,7 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
 			__jbd2_journal_unfile_buffer(jh);
 			if (!buffer_jbd(bh)) {
 				spin_unlock(&journal->j_list_lock);
-				jbd_unlock_bh_state(bh);
-				__bforget(bh);
-				goto drop;
+				goto not_jbd;
 			}
 		}
 		spin_unlock(&journal->j_list_lock);
@@ -1609,14 +1605,21 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
 		/* However, if the buffer is still owned by a prior
 		 * (committing) transaction, we can't drop it yet... */
 		JBUFFER_TRACE(jh, "belongs to older transaction");
-		/* ... but we CAN drop it from the new transaction if we
-		 * have also modified it since the original commit. */
+		/* ... but we CAN drop it from the new transaction through
+		 * marking the buffer as freed and set j_next_transaction to
+		 * the new transaction, so that not only the commit code
+		 * knows it should clear dirty bits when it is done with the
+		 * buffer, but also the buffer can be checkpointed only
+		 * after the new transaction commits. */
 
-		if (jh->b_next_transaction) {
-			J_ASSERT(jh->b_next_transaction == transaction);
+		set_buffer_freed(bh);
+
+		if (!jh->b_next_transaction) {
 			spin_lock(&journal->j_list_lock);
-			jh->b_next_transaction = NULL;
+			jh->b_next_transaction = transaction;
 			spin_unlock(&journal->j_list_lock);
+		} else {
+			J_ASSERT(jh->b_next_transaction == transaction);
 
 			/*
 			 * only drop a reference if this transaction modified
@@ -1625,9 +1628,40 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
 			if (was_modified)
 				drop_reserve = 1;
 		}
+	} else {
+		/*
+		 * Finally, if the buffer is not belongs to any
+		 * transaction, we can just drop it now if it has no
+		 * checkpoint.
+		 */
+		spin_lock(&journal->j_list_lock);
+		if (!jh->b_cp_transaction) {
+			JBUFFER_TRACE(jh, "belongs to none transaction");
+			spin_unlock(&journal->j_list_lock);
+			goto not_jbd;
+		}
+
+		/*
+		 * Otherwise, if the buffer has been written to disk,
+		 * it is safe to remove the checkpoint and drop it.
+		 */
+		if (!buffer_dirty(bh)) {
+			__jbd2_journal_remove_checkpoint(jh);
+			spin_unlock(&journal->j_list_lock);
+			goto not_jbd;
+		}
+
+		/*
+		 * The buffer is still not written to disk, we should
+		 * attach this buffer to current transaction so that the
+		 * buffer can be checkpointed only after the current
+		 * transaction commits.
+		 */
+		clear_buffer_dirty(bh);
+		__jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
+		spin_unlock(&journal->j_list_lock);
 	}
 
-not_jbd:
 	jbd_unlock_bh_state(bh);
 	__brelse(bh);
 drop:
@@ -1636,6 +1670,11 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
 		handle->h_buffer_credits++;
 	}
 	return err;
+
+not_jbd:
+	jbd_unlock_bh_state(bh);
+	__bforget(bh);
+	goto drop;
 }
 
 /**