Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kern…

…el/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" <[email protected]>
+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);