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

Pull ext4 updates from Ted Ts'o:
"Improvements to ext4's block allocator performance for very large file
systems, especially when the file system or files which are highly
fragmented. There is a new mount option, prefetch_block_bitmaps which
will pull in the block bitmaps and set up the in-memory buddy bitmaps
when the file system is initially mounted.

Beyond that, a lot of bug fixes and cleanups. In particular, a number
of changes to make ext4 more robust in the face of write errors or
file system corruptions"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (46 commits)
ext4: limit the length of per-inode prealloc list
ext4: reorganize if statement of ext4_mb_release_context()
ext4: add mb_debug logging when there are lost chunks
ext4: Fix comment typo "the the".
jbd2: clean up checksum verification in do_one_pass()
ext4: change to use fallthrough macro
ext4: remove unused parameter of ext4_generic_delete_entry function
mballoc: replace seq_printf with seq_puts
ext4: optimize the implementation of ext4_mb_good_group()
ext4: delete invalid comments near ext4_mb_check_limits()
ext4: fix typos in ext4_mb_regular_allocator() comment
ext4: fix checking of directory entry validity for inline directories
fs: prevent BUG_ON in submit_bh_wbc()
ext4: correctly restore system zone info when remount fails
ext4: handle add_system_zone() failure in ext4_setup_system_zone()
ext4: fold ext4_data_block_valid_rcu() into the caller
ext4: check journal inode extents more carefully
ext4: don't allow overlapping system zones
ext4: handle error of ext4_setup_system_zone() on remount
ext4: delete the invalid BUGON in ext4_mb_load_buddy_gfp()
...

Documentation/admin-guide/ext4.rst

···
         multiple of this tuning parameter if the stripe size is not set in the
         ext4 superblock
 
+  mb_max_inode_prealloc
+        The maximum length of per-inode ext4_prealloc_space list.
+
   mb_max_to_scan
         The maximum number of extents the multiblock allocator will search to
         find the best extent.
···
 Ioctls
 ======
 
-There is some Ext4 specific functionality which can be accessed by applications
-through the system call interfaces. The list of all Ext4 specific ioctls are
-shown in the table below.
+Ext4 implements various ioctls which can be used by applications to access
+ext4-specific functionality. An incomplete list of these ioctls is shown in the
+table below. This list includes truly ext4-specific ioctls (``EXT4_IOC_*``) as
+well as ioctls that may have been ext4-specific originally but are now supported
+by some other filesystem(s) too (``FS_IOC_*``).
 
-Table of Ext4 specific ioctls
+Table of Ext4 ioctls
 
-  EXT4_IOC_GETFLAGS
+  FS_IOC_GETFLAGS
         Get additional attributes associated with inode.  The ioctl argument is
-        an integer bitfield, with bit values described in ext4.h. This ioctl is
-        an alias for FS_IOC_GETFLAGS.
+        an integer bitfield, with bit values described in ext4.h.
 
-  EXT4_IOC_SETFLAGS
+  FS_IOC_SETFLAGS
         Set additional attributes associated with inode.  The ioctl argument is
-        an integer bitfield, with bit values described in ext4.h. This ioctl is
-        an alias for FS_IOC_SETFLAGS.
+        an integer bitfield, with bit values described in ext4.h.
 
   EXT4_IOC_GETVERSION, EXT4_IOC_GETVERSION_OLD
         Get the inode i_generation number stored for each inode. The

Documentation/filesystems/ext4/about.rst

···
 Other References
 ----------------
 
-Also see http://www.nongnu.org/ext2-doc/ for quite a collection of
+Also see https://www.nongnu.org/ext2-doc/ for quite a collection of
 information about ext2/3. Here's another old reference:
 http://wiki.osdev.org/Ext2

fs/buffer.c

···
 	WARN_ON(atomic_read(&bh->b_count) < 1);
 	lock_buffer(bh);
 	if (test_clear_buffer_dirty(bh)) {
+		/*
+		 * The bh should be mapped, but it might not be if the
+		 * device was hot-removed. Not much we can do but fail the I/O.
+		 */
+		if (!buffer_mapped(bh)) {
+			unlock_buffer(bh);
+			return -EIO;
+		}
+
 		get_bh(bh);
 		bh->b_end_io = end_buffer_write_sync;
 		ret = submit_bh(REQ_OP_WRITE, op_flags, bh);

fs/ext4/Kconfig

···
 	  This builds the ext4 KUnit tests.
 
 	  KUnit tests run during boot and output the results to the debug log
-	  in TAP format (http://testanything.org/). Only useful for kernel devs
+	  in TAP format (https://testanything.org/). Only useful for kernel devs
 	  running KUnit test harness and are not for inclusion into a production
 	  build.
 

fs/ext4/balloc.c

···
  * Return buffer_head on success or an ERR_PTR in case of failure.
  */
 struct buffer_head *
-ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
+ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group,
+			      bool ignore_locked)
 {
 	struct ext4_group_desc *desc;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
···
 			     "block_group = %u, block_bitmap = %llu",
 			     block_group, bitmap_blk);
 		return ERR_PTR(-ENOMEM);
+	}
+
+	if (ignore_locked && buffer_locked(bh)) {
+		/* buffer under IO already, return if called for prefetching */
+		put_bh(bh);
+		return NULL;
 	}
 
 	if (bitmap_uptodate(bh))
···
 	 * submit the buffer_head for reading
 	 */
 	set_buffer_new(bh);
-	trace_ext4_read_block_bitmap_load(sb, block_group);
+	trace_ext4_read_block_bitmap_load(sb, block_group, ignore_locked);
 	bh->b_end_io = ext4_end_bitmap_read;
 	get_bh(bh);
-	submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh);
+	submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO |
+		  (ignore_locked ? REQ_RAHEAD : 0), bh);
 	return bh;
 verify:
 	err = ext4_validate_block_bitmap(sb, desc, block_group, bh);
···
 	struct buffer_head *bh;
 	int err;
 
-	bh = ext4_read_block_bitmap_nowait(sb, block_group);
+	bh = ext4_read_block_bitmap_nowait(sb, block_group, false);
 	if (IS_ERR(bh))
 		return bh;
 	err = ext4_wait_block_bitmap(sb, block_group, bh);

fs/ext4/block_validity.c

···
 	struct rb_node	node;
 	ext4_fsblk_t	start_blk;
 	unsigned int	count;
+	u32		ino;
 };
 
 static struct kmem_cache *ext4_system_zone_cachep;
···
 static inline int can_merge(struct ext4_system_zone *entry1,
 		     struct ext4_system_zone *entry2)
 {
-	if ((entry1->start_blk + entry1->count) == entry2->start_blk)
+	if ((entry1->start_blk + entry1->count) == entry2->start_blk &&
+	    entry1->ino == entry2->ino)
 		return 1;
 	return 0;
 }
···
  */
 static int add_system_zone(struct ext4_system_blocks *system_blks,
 			   ext4_fsblk_t start_blk,
-			   unsigned int count)
+			   unsigned int count, u32 ino)
 {
-	struct ext4_system_zone *new_entry = NULL, *entry;
+	struct ext4_system_zone *new_entry, *entry;
 	struct rb_node **n = &system_blks->root.rb_node, *node;
 	struct rb_node *parent = NULL, *new_node = NULL;
 
···
 			n = &(*n)->rb_left;
 		else if (start_blk >= (entry->start_blk + entry->count))
 			n = &(*n)->rb_right;
-		else {
-			if (start_blk + count > (entry->start_blk +
-						 entry->count))
-				entry->count = (start_blk + count -
-						entry->start_blk);
-			new_node = *n;
-			new_entry = rb_entry(new_node, struct ext4_system_zone,
-					     node);
-			break;
-		}
+		else	/* Unexpected overlap of system zones. */
+			return -EFSCORRUPTED;
 	}
 
-	if (!new_entry) {
-		new_entry = kmem_cache_alloc(ext4_system_zone_cachep,
-					     GFP_KERNEL);
-		if (!new_entry)
-			return -ENOMEM;
-		new_entry->start_blk = start_blk;
-		new_entry->count = count;
-		new_node = &new_entry->node;
+	new_entry = kmem_cache_alloc(ext4_system_zone_cachep,
+				     GFP_KERNEL);
+	if (!new_entry)
+		return -ENOMEM;
+	new_entry->start_blk = start_blk;
+	new_entry->count = count;
+	new_entry->ino = ino;
+	new_node = &new_entry->node;
 
-		rb_link_node(new_node, parent, n);
-		rb_insert_color(new_node, &system_blks->root);
-	}
+	rb_link_node(new_node, parent, n);
+	rb_insert_color(new_node, &system_blks->root);
 
 	/* Can we merge to the left? */
 	node = rb_prev(new_node);
···
 	printk(KERN_CONT "\n");
 }
 
-/*
- * Returns 1 if the passed-in block region (start_blk,
- * start_blk+count) is valid; 0 if some part of the block region
- * overlaps with filesystem metadata blocks.
- */
-static int ext4_data_block_valid_rcu(struct ext4_sb_info *sbi,
-				     struct ext4_system_blocks *system_blks,
-				     ext4_fsblk_t start_blk,
-				     unsigned int count)
-{
-	struct ext4_system_zone *entry;
-	struct rb_node *n;
-
-	if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
-	    (start_blk + count < start_blk) ||
-	    (start_blk + count > ext4_blocks_count(sbi->s_es)))
-		return 0;
-
-	if (system_blks == NULL)
-		return 1;
-
-	n = system_blks->root.rb_node;
-	while (n) {
-		entry = rb_entry(n, struct ext4_system_zone, node);
-		if (start_blk + count - 1 < entry->start_blk)
-			n = n->rb_left;
-		else if (start_blk >= (entry->start_blk + entry->count))
-			n = n->rb_right;
-		else
-			return 0;
-	}
-	return 1;
-}
-
 static int ext4_protect_reserved_inode(struct super_block *sb,
 				       struct ext4_system_blocks *system_blks,
 				       u32 ino)
···
 		if (n == 0) {
 			i++;
 		} else {
-			if (!ext4_data_block_valid_rcu(sbi, system_blks,
-						map.m_pblk, n)) {
-				err = -EFSCORRUPTED;
-				__ext4_error(sb, __func__, __LINE__, -err,
-					     map.m_pblk, "blocks %llu-%llu "
-					     "from inode %u overlap system zone",
-					     map.m_pblk,
-					     map.m_pblk + map.m_len - 1, ino);
+			err = add_system_zone(system_blks, map.m_pblk, n, ino);
+			if (err < 0) {
+				if (err == -EFSCORRUPTED) {
+					__ext4_error(sb, __func__, __LINE__,
+						     -err, map.m_pblk,
+						     "blocks %llu-%llu from inode %u overlap system zone",
+						     map.m_pblk,
+						     map.m_pblk + map.m_len - 1,
+						     ino);
+				}
 				break;
 			}
-			err = add_system_zone(system_blks, map.m_pblk, n);
-			if (err < 0)
-				break;
 			i += n;
 		}
 	}
···
 	int flex_size = ext4_flex_bg_size(sbi);
 	int ret;
 
-	if (!test_opt(sb, BLOCK_VALIDITY)) {
-		if (sbi->system_blks)
-			ext4_release_system_zone(sb);
-		return 0;
-	}
-	if (sbi->system_blks)
-		return 0;
-
 	system_blks = kzalloc(sizeof(*system_blks), GFP_KERNEL);
 	if (!system_blks)
 		return -ENOMEM;
···
 	for (i=0; i < ngroups; i++) {
 		cond_resched();
 		if (ext4_bg_has_super(sb, i) &&
-		    ((i < 5) || ((i % flex_size) == 0)))
-			add_system_zone(system_blks,
+		    ((i < 5) || ((i % flex_size) == 0))) {
+			ret = add_system_zone(system_blks,
 					ext4_group_first_block_no(sb, i),
-					ext4_bg_num_gdb(sb, i) + 1);
+					ext4_bg_num_gdb(sb, i) + 1, 0);
+			if (ret)
+				goto err;
+		}
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		ret = add_system_zone(system_blks,
-				ext4_block_bitmap(sb, gdp), 1);
+				ext4_block_bitmap(sb, gdp), 1, 0);
 		if (ret)
 			goto err;
 		ret = add_system_zone(system_blks,
-				ext4_inode_bitmap(sb, gdp), 1);
+				ext4_inode_bitmap(sb, gdp), 1, 0);
 		if (ret)
 			goto err;
 		ret = add_system_zone(system_blks,
 				ext4_inode_table(sb, gdp),
-				sbi->s_itb_per_group);
+				sbi->s_itb_per_group, 0);
 		if (ret)
 			goto err;
 	}
···
 		call_rcu(&system_blks->rcu, ext4_destroy_system_zone);
 }
 
-int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
+/*
+ * Returns 1 if the passed-in block region (start_blk,
+ * start_blk+count) is valid; 0 if some part of the block region
+ * overlaps with some other filesystem metadata blocks.
+ */
+int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
 			  unsigned int count)
 {
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_system_blocks *system_blks;
-	int ret;
+	struct ext4_system_zone *entry;
+	struct rb_node *n;
+	int ret = 1;
+
+	if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
+	    (start_blk + count < start_blk) ||
+	    (start_blk + count > ext4_blocks_count(sbi->s_es)))
+		return 0;
 
 	/*
 	 * Lock the system zone to prevent it being released concurrently
···
 	 */
 	rcu_read_lock();
 	system_blks = rcu_dereference(sbi->system_blks);
-	ret = ext4_data_block_valid_rcu(sbi, system_blks, start_blk,
-					count);
+	if (system_blks == NULL)
+		goto out_rcu;
+
+	n = system_blks->root.rb_node;
+	while (n) {
+		entry = rb_entry(n, struct ext4_system_zone, node);
+		if (start_blk + count - 1 < entry->start_blk)
+			n = n->rb_left;
+		else if (start_blk >= (entry->start_blk + entry->count))
+			n = n->rb_right;
+		else {
+			ret = (entry->ino == inode->i_ino);
+			break;
+		}
+	}
+out_rcu:
 	rcu_read_unlock();
 	return ret;
 }
···
 	while (bref < p+max) {
 		blk = le32_to_cpu(*bref++);
 		if (blk &&
-		    unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
-						    blk, 1))) {
+		    unlikely(!ext4_inode_block_valid(inode, blk, 1))) {
 			ext4_error_inode(inode, function, line, blk,
 					 "invalid block");
 			return -EFSCORRUPTED;

fs/ext4/ext4.h

···
 #define EXT4_CASEFOLD_FL		0x40000000 /* Casefolded directory */
 #define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
 
-#define EXT4_FL_USER_VISIBLE		0x725BDFFF /* User visible flags */
-#define EXT4_FL_USER_MODIFIABLE		0x624BC0FF /* User modifiable flags */
+/* User modifiable flags */
+#define EXT4_FL_USER_MODIFIABLE		(EXT4_SECRM_FL | \
+					 EXT4_UNRM_FL | \
+					 EXT4_COMPR_FL | \
+					 EXT4_SYNC_FL | \
+					 EXT4_IMMUTABLE_FL | \
+					 EXT4_APPEND_FL | \
+					 EXT4_NODUMP_FL | \
+					 EXT4_NOATIME_FL | \
+					 EXT4_JOURNAL_DATA_FL | \
+					 EXT4_NOTAIL_FL | \
+					 EXT4_DIRSYNC_FL | \
+					 EXT4_TOPDIR_FL | \
+					 EXT4_EXTENTS_FL | \
+					 0x00400000 /* EXT4_EOFBLOCKS_FL */ | \
+					 EXT4_DAX_FL | \
+					 EXT4_PROJINHERIT_FL | \
+					 EXT4_CASEFOLD_FL)
 
-/* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */
+/* User visible flags */
+#define EXT4_FL_USER_VISIBLE		(EXT4_FL_USER_MODIFIABLE | \
+					 EXT4_DIRTY_FL | \
+					 EXT4_COMPRBLK_FL | \
+					 EXT4_NOCOMPR_FL | \
+					 EXT4_ENCRYPT_FL | \
+					 EXT4_INDEX_FL | \
+					 EXT4_VERITY_FL | \
+					 EXT4_INLINE_DATA_FL)
+
+/* Flags we can manipulate with through FS_IOC_FSSETXATTR */
 #define EXT4_FL_XFLAG_VISIBLE		(EXT4_SYNC_FL | \
 					 EXT4_IMMUTABLE_FL | \
 					 EXT4_APPEND_FL | \
···
 /*
  * ioctl commands
  */
-#define	EXT4_IOC_GETFLAGS		FS_IOC_GETFLAGS
-#define	EXT4_IOC_SETFLAGS		FS_IOC_SETFLAGS
 #define	EXT4_IOC_GETVERSION		_IOR('f', 3, long)
 #define	EXT4_IOC_SETVERSION		_IOW('f', 4, long)
 #define	EXT4_IOC_GETVERSION_OLD		FS_IOC_GETVERSION
···
 #define EXT4_IOC_RESIZE_FS		_IOW('f', 16, __u64)
 #define EXT4_IOC_SWAP_BOOT		_IO('f', 17)
 #define EXT4_IOC_PRECACHE_EXTENTS	_IO('f', 18)
-#define EXT4_IOC_SET_ENCRYPTION_POLICY	FS_IOC_SET_ENCRYPTION_POLICY
-#define EXT4_IOC_GET_ENCRYPTION_PWSALT	FS_IOC_GET_ENCRYPTION_PWSALT
-#define EXT4_IOC_GET_ENCRYPTION_POLICY	FS_IOC_GET_ENCRYPTION_POLICY
 /* ioctl codes 19--39 are reserved for fscrypt */
 #define EXT4_IOC_CLEAR_ES_CACHE		_IO('f', 40)
 #define EXT4_IOC_GETSTATE		_IOW('f', 41, __u32)
 #define EXT4_IOC_GET_ES_CACHE		_IOWR('f', 42, struct fiemap)
-
-#define EXT4_IOC_FSGETXATTR		FS_IOC_FSGETXATTR
-#define EXT4_IOC_FSSETXATTR		FS_IOC_FSSETXATTR
 
 #define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32)
 
···
 /*
  * ioctl commands in 32 bit emulation
  */
-#define EXT4_IOC32_GETFLAGS		FS_IOC32_GETFLAGS
-#define EXT4_IOC32_SETFLAGS		FS_IOC32_SETFLAGS
 #define EXT4_IOC32_GETVERSION		_IOR('f', 3, int)
 #define EXT4_IOC32_SETVERSION		_IOW('f', 4, int)
 #define EXT4_IOC32_GETRSVSZ		_IOR('f', 5, int)
···
 	struct timespec64 i_crtime;
 
 	/* mballoc */
+	atomic_t i_prealloc_active;
 	struct list_head i_prealloc_list;
 	spinlock_t i_prealloc_lock;
 
···
 #define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
 #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
 #define EXT4_MOUNT_WARN_ON_ERROR	0x2000000 /* Trigger WARN_ON on error */
+#define EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS 0x4000000
 #define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
 #define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
 #define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
···
 	unsigned int s_mb_stats;
 	unsigned int s_mb_order2_reqs;
 	unsigned int s_mb_group_prealloc;
+	unsigned int s_mb_max_inode_prealloc;
 	unsigned int s_max_dir_size_kb;
 	/* where last allocation was done - for stream allocation */
 	unsigned long s_mb_last_group;
 	unsigned long s_mb_last_start;
+	unsigned int s_mb_prefetch;
+	unsigned int s_mb_prefetch_limit;
 
 	/* stats for buddy allocator */
 	atomic_t s_bal_reqs;	/* number of reqs with len > 1 */
···
 	struct ratelimit_state s_err_ratelimit_state;
 	struct ratelimit_state s_warning_ratelimit_state;
 	struct ratelimit_state s_msg_ratelimit_state;
+	atomic_t s_warning_count;
+	atomic_t s_msg_count;
 
 	/* Encryption context for '-o test_dummy_encryption' */
 	struct fscrypt_dummy_context s_dummy_enc_ctx;
···
 #ifdef CONFIG_EXT4_DEBUG
 	unsigned long s_simulate_fail;
 #endif
+	/* Record the errseq of the backing block device */
+	errseq_t s_bdev_wb_err;
+	spinlock_t s_bdev_wb_lock;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
···
 	struct mutex		li_list_mtx;
 };
 
+enum ext4_li_mode {
+	EXT4_LI_MODE_PREFETCH_BBITMAP,
+	EXT4_LI_MODE_ITABLE,
+};
+
 struct ext4_li_request {
 	struct super_block	*lr_super;
-	struct ext4_sb_info	*lr_sbi;
+	enum ext4_li_mode	lr_mode;
+	ext4_group_t		lr_first_not_zeroed;
 	ext4_group_t		lr_next_group;
 	struct list_head	lr_request;
 	unsigned long		lr_next_sched;
···
 extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
 
 extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb,
-						ext4_group_t block_group);
+						ext4_group_t block_group,
+						bool ignore_locked);
 extern int ext4_wait_block_bitmap(struct super_block *sb,
 				  ext4_group_t block_group,
 				  struct buffer_head *bh);
···
 extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
 				struct ext4_allocation_request *, int *);
 extern int ext4_mb_reserve_blocks(struct super_block *, int);
-extern void ext4_discard_preallocations(struct inode *);
+extern void ext4_discard_preallocations(struct inode *, unsigned int);
 extern int __init ext4_init_mballoc(void);
 extern void ext4_exit_mballoc(void);
+extern ext4_group_t ext4_mb_prefetch(struct super_block *sb,
+				     ext4_group_t group,
+				     unsigned int nr, int *cnt);
+extern void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group,
+				  unsigned int nr);
+
 extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			     struct buffer_head *bh, ext4_fsblk_t block,
 			     unsigned long count, int flags);
···
 			   struct ext4_filename *fname,
 			   unsigned int offset,
 			   struct ext4_dir_entry_2 **res_dir);
-extern int ext4_generic_delete_entry(handle_t *handle,
-				     struct inode *dir,
+extern int ext4_generic_delete_entry(struct inode *dir,
 				     struct ext4_dir_entry_2 *de_del,
 				     struct buffer_head *bh,
 				     void *entry_buf,
···
 
 #endif
 
-extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
-					__u32 compat);
-extern int ext4_update_rocompat_feature(handle_t *handle,
-					struct super_block *sb,	__u32 rocompat);
-extern int ext4_update_incompat_feature(handle_t *handle,
-					struct super_block *sb,	__u32 incompat);
 extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
 				      struct ext4_group_desc *bg);
 extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
···
 	(1 << EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT)
 #define EXT4_GROUP_INFO_IBITMAP_CORRUPT		\
 	(1 << EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT)
+#define EXT4_GROUP_INFO_BBITMAP_READ_BIT	4
 
 #define EXT4_MB_GRP_NEED_INIT(grp)	\
 	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
···
 	(set_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
 #define EXT4_MB_GRP_CLEAR_TRIMMED(grp)	\
 	(clear_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
+#define EXT4_MB_GRP_TEST_AND_SET_READ(grp)	\
+	(test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_READ_BIT, &((grp)->bb_state)))
 
 #define EXT4_MAX_CONTENTION		8
 #define EXT4_CONTENTION_THRESHOLD	2
···
 extern int ext4_setup_system_zone(struct super_block *sb);
 extern int __init ext4_init_system_zone(void);
 extern void ext4_exit_system_zone(void);
-extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
-				 ext4_fsblk_t start_blk,
-				 unsigned int count);
+extern int ext4_inode_block_valid(struct inode *inode,
+				  ext4_fsblk_t start_blk,
+				  unsigned int count);
 extern int ext4_check_blockref(const char *, unsigned int,
 			       struct inode *, __le32 *, unsigned int);
 

fs/ext4/ext4_jbd2.c

···
 	jbd2_journal_abort_handle(handle);
 }
 
+static void ext4_check_bdev_write_error(struct super_block *sb)
+{
+	struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int err;
+
+	/*
+	 * If the block device has write error flag, it may have failed to
+	 * async write out metadata buffers in the background. In this case,
+	 * we could read old data from disk and write it out again, which
+	 * may lead to on-disk filesystem inconsistency.
+	 */
+	if (errseq_check(&mapping->wb_err, READ_ONCE(sbi->s_bdev_wb_err))) {
+		spin_lock(&sbi->s_bdev_wb_lock);
+		err = errseq_check_and_advance(&mapping->wb_err, &sbi->s_bdev_wb_err);
+		spin_unlock(&sbi->s_bdev_wb_lock);
+		if (err)
+			ext4_error_err(sb, -err,
+				       "Error while async write back metadata");
+	}
+}
+
 int __ext4_journal_get_write_access(const char *where, unsigned int line,
 				    handle_t *handle, struct buffer_head *bh)
 {
 	int err = 0;
 
 	might_sleep();
+
+	if (bh->b_bdev->bd_super)
+		ext4_check_bdev_write_error(bh->b_bdev->bd_super);
 
 	if (ext4_handle_valid(handle)) {
 		err = jbd2_journal_get_write_access(handle, bh);

fs/ext4/extents.c

···
 	 * i_mutex. So we can safely drop the i_data_sem here.
 	 */
 	BUG_ON(EXT4_JOURNAL(inode) == NULL);
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 	up_write(&EXT4_I(inode)->i_data_sem);
 	*dropped = 1;
 	return 0;
···
 	 */
 	if (lblock + len <= lblock)
 		return 0;
-	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
+	return ext4_inode_block_valid(inode, block, len);
 }
 
 static int ext4_valid_extent_idx(struct inode *inode,
···
 {
 	ext4_fsblk_t block = ext4_idx_pblock(ext_idx);
 
-	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1);
+	return ext4_inode_block_valid(inode, block, 1);
 }
 
 static int ext4_valid_extent_entries(struct inode *inode,
···
 	}
 	if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE))
 		return bh;
-	if (!ext4_has_feature_journal(inode->i_sb) ||
-	    (inode->i_ino !=
-	     le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) {
-		err = __ext4_ext_check(function, line, inode,
-				       ext_block_hdr(bh), depth, pblk);
-		if (err)
-			goto errout;
-	}
+	err = __ext4_ext_check(function, line, inode,
+			       ext_block_hdr(bh), depth, pblk);
+	if (err)
+		goto errout;
 	set_buffer_verified(bh);
 	/*
 	 * If this is a leaf block, cache all of its entries
···
 		return;
 	depth = path->p_depth;
 	for (i = 0; i <= depth; i++, path++) {
-		if (path->p_bh) {
-			brelse(path->p_bh);
-			path->p_bh = NULL;
-		}
+		brelse(path->p_bh);
+		path->p_bh = NULL;
 	}
 }
 
···
 
 /*
  * ext4_ext_insert_extent:
- * tries to merge requsted extent into the existing extent or
+ * tries to merge requested extent into the existing extent or
  * inserts requested extent as new one into the tree,
  * creating new leaf in the no-space case.
  */
···
  *
  *
  * Splits extent [a, b] into two extents [a, @split) and [@split, b], states
- * of which are deterimined by split_flag.
+ * of which are determined by split_flag.
  *
  * There are two cases:
  *  a> the extent are splitted into two extent.
···
 		eof_block = map->m_lblk + map->m_len;
 	/*
 	 * It is safe to convert extent to initialized via explicit
-	 * zeroout only if extent is fully insde i_size or new_size.
+	 * zeroout only if extent is fully inside i_size or new_size.
 	 */
 	depth = ext_depth(inode);
 	ex = path[depth].p_ext;
···
 			 * not a good idea to call discard here directly,
 			 * but otherwise we'd need to call it every free().
 			 */
-			ext4_discard_preallocations(inode);
+			ext4_discard_preallocations(inode, 0);
 			if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
 				fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE;
 			ext4_free_blocks(handle, inode, NULL, newblock,
···
 	}
 
 	/*
-	 * Round up offset. This is not fallocate, we neet to zero out
+	 * Round up offset. This is not fallocate, we need to zero out
 	 * blocks, so convert interior block aligned part of the range to
 	 * unwritten and possibly manually zero out unaligned parts of the
 	 * range.
···
 	}
 
 	down_write(&EXT4_I(inode)->i_data_sem);
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 
 	ret = ext4_es_remove_extent(inode, punch_start,
 				    EXT_MAX_BLOCKS - punch_start);
···
 		up_write(&EXT4_I(inode)->i_data_sem);
 		goto out_stop;
 	}
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 
 	ret = ext4_ext_shift_extents(inode, handle, punch_stop,
 				     punch_stop - punch_start, SHIFT_LEFT);
···
 		goto out_stop;
 
 	down_write(&EXT4_I(inode)->i_data_sem);
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 
 	path = ext4_find_extent(inode, offset_lblk, NULL, 0);
 	if (IS_ERR(path)) {
···
 		}
 		ex1 = path1[path1->p_depth].p_ext;
 		ex2 = path2[path2->p_depth].p_ext;
-		/* Do we have somthing to swap ? */
+		/* Do we have something to swap ? */
 		if (unlikely(!ex2 || !ex1))
 			goto finish;
 

fs/ext4/file.c

···
 	/* if we are the last writer on the inode, drop the block reservation */
 	if ((filp->f_mode & FMODE_WRITE) &&
 			(atomic_read(&inode->i_writecount) == 1) &&
-		        !EXT4_I(inode)->i_reserved_data_blocks)
-	{
+			!EXT4_I(inode)->i_reserved_data_blocks) {
 		down_write(&EXT4_I(inode)->i_data_sem);
-		ext4_discard_preallocations(inode);
+		ext4_discard_preallocations(inode, 0);
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
 	if (is_dx(inode) && filp->private_data)
···
 	 */
 	if (*ilock_shared && (!IS_NOSEC(inode) || *extend ||
 	     !ext4_overwrite_io(inode, offset, count))) {
+		if (iocb->ki_flags & IOCB_NOWAIT) {
+			ret = -EAGAIN;
+			goto out;
+		}
 		inode_unlock_shared(inode);
 		*ilock_shared = false;
 		inode_lock(inode);
···
 	return err;
 }
 
-static int ext4_file_open(struct inode * inode, struct file * filp)
+static int ext4_file_open(struct inode *inode, struct file *filp)
 {
 	int ret;
 

fs/ext4/hash.c

···
 		break;
 	case DX_HASH_HALF_MD4_UNSIGNED:
 		str2hashbuf = str2hashbuf_unsigned;
-		/* fall through */
+		fallthrough;
 	case DX_HASH_HALF_MD4:
 		p = name;
 		while (len > 0) {
···
 		break;
 	case DX_HASH_TEA_UNSIGNED:
 		str2hashbuf = str2hashbuf_unsigned;
-		/* fall through */
+		fallthrough;
 	case DX_HASH_TEA:
 		p = name;
 		while (len > 0) {

fs/ext4/indirect.c

···
 	 * i_mutex. So we can safely drop the i_data_sem here.
 	 */
 	BUG_ON(EXT4_JOURNAL(inode) == NULL);
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 	up_write(&EXT4_I(inode)->i_data_sem);
 	*dropped = 1;
 	return 0;
···
 	else if (ext4_should_journal_data(inode))
 		flags |= EXT4_FREE_BLOCKS_FORGET;
 
-	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free,
-				   count)) {
+	if (!ext4_inode_block_valid(inode, block_to_free, count)) {
 		EXT4_ERROR_INODE(inode, "attempt to clear invalid "
 				 "blocks %llu len %lu",
 				 (unsigned long long) block_to_free, count);
···
 			if (!nr)
 				continue;		/* A hole */
 
-			if (!ext4_data_block_valid(EXT4_SB(inode->i_sb),
-						   nr, 1)) {
+			if (!ext4_inode_block_valid(inode, nr, 1)) {
 				EXT4_ERROR_INODE(inode,
 						 "invalid indirect mapped "
 						 "block %lu (level %d)",
···
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
 			i_data[EXT4_IND_BLOCK] = 0;
 		}
-		/* fall through */
+		fallthrough;
 	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 */
+		fallthrough;
 	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 */
+		fallthrough;
 	case EXT4_TIND_BLOCK:
 		;
 	}
···
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
 			i_data[EXT4_IND_BLOCK] = 0;
 		}
-		/* fall through */
+		fallthrough;
 	case EXT4_IND_BLOCK:
 		if (++n >= n2)
 			break;
···
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
 			i_data[EXT4_DIND_BLOCK] = 0;
 		}
-		/* fall through */
+		fallthrough;
 	case EXT4_DIND_BLOCK:
 		if (++n >= n2)
 			break;
···
 			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
 			i_data[EXT4_TIND_BLOCK] = 0;
 		}
-		/* fall through */
+		fallthrough;
 	case EXT4_TIND_BLOCK:
 		;
 	}

fs/ext4/inline.c

···
 		len = 0;
 	}
 
-	/* Insert the the xttr entry. */
+	/* Insert the xttr entry. */
 	i.value = value;
 	i.value_len = len;
 
···
 	if (err)
 		goto out;
 
-	err = ext4_generic_delete_entry(handle, dir, de_del, bh,
+	err = ext4_generic_delete_entry(dir, de_del, bh,
 					inline_start, inline_size, 0);
 	if (err)
 		goto out;

fs/ext4/inode.c

···
 	 */
 	if ((ei->i_reserved_data_blocks == 0) &&
 	    !inode_is_open_for_write(inode))
-		ext4_discard_preallocations(inode);
+		ext4_discard_preallocations(inode, 0);
 }
 
 static int __check_block_validity(struct inode *inode, const char *func,
···
 	    (inode->i_ino ==
 	     le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum)))
 		return 0;
-	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
-				   map->m_len)) {
+	if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) {
 		ext4_error_inode(inode, func, line, map->m_pblk,
 				 "lblock %lu mapped to illegal pblock %llu "
 				 "(length %d)", (unsigned long) map->m_lblk,
···
 	if (PageChecked(page))
 		return 0;
 	if (journal)
-		return jbd2_journal_try_to_free_buffers(journal, page, wait);
+		return jbd2_journal_try_to_free_buffers(journal, page);
 	else
 		return try_to_free_buffers(page);
 }
···
 	if (stop_block > first_block) {
 
 		down_write(&EXT4_I(inode)->i_data_sem);
-		ext4_discard_preallocations(inode);
+		ext4_discard_preallocations(inode, 0);
 
 		ret = ext4_es_remove_extent(inode, first_block,
 					    stop_block - first_block);
···
 	trace_ext4_truncate_enter(inode);
 
 	if (!ext4_can_truncate(inode))
-		return 0;
+		goto out_trace;
 
 	if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
 		ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
···
 		int has_inline = 1;
 
 		err = ext4_inline_data_truncate(inode, &has_inline);
-		if (err)
-			return err;
-		if (has_inline)
-			return 0;
+		if (err || has_inline)
+			goto out_trace;
 	}
 
 	/* If we zero-out tail of the page, we have to create jinode for jbd2 */
 	if (inode->i_size & (inode->i_sb->s_blocksize - 1)) {
 		if (ext4_inode_attach_jinode(inode) < 0)
-			return 0;
+			goto out_trace;
 	}
 
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
···
 		credits = ext4_blocks_for_truncate(inode);
 
 	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
-	if (IS_ERR(handle))
-		return PTR_ERR(handle);
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		goto out_trace;
+	}
 
 	if (inode->i_size & (inode->i_sb->s_blocksize - 1))
 		ext4_block_truncate_page(handle, mapping, inode->i_size);
···
 
 	down_write(&EXT4_I(inode)->i_data_sem);
 
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		err = ext4_ext_truncate(handle, inode);
···
 		err = err2;
 	ext4_journal_stop(handle);
 
+out_trace:
 	trace_ext4_truncate_exit(inode);
 	return err;
 }
···
 
 	ret = 0;
 	if (ei->i_file_acl &&
-	    !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) {
+	    !ext4_inode_block_valid(inode, ei->i_file_acl, 1)) {
 		ext4_error_inode(inode, function, line, 0,
 				 "iget: bad extended attribute block %llu",
 				 ei->i_file_acl);

fs/ext4/ioctl.c

···
 	reset_inode_seed(inode);
 	reset_inode_seed(inode_bl);
 
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 
 	err = ext4_mark_inode_dirty(handle, inode);
 	if (err < 0) {
···
 	switch (cmd) {
 	case FS_IOC_GETFSMAP:
 		return ext4_ioc_getfsmap(sb, (void __user *)arg);
-	case EXT4_IOC_GETFLAGS:
+	case FS_IOC_GETFLAGS:
 		flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
 		if (S_ISREG(inode->i_mode))
 			flags &= ~EXT4_PROJINHERIT_FL;
 		return put_user(flags, (int __user *) arg);
-	case EXT4_IOC_SETFLAGS: {
+	case FS_IOC_SETFLAGS: {
 		int err;
 
 		if (!inode_owner_or_capable(inode))
···
 	case EXT4_IOC_PRECACHE_EXTENTS:
 		return ext4_ext_precache(inode);
 
-	case EXT4_IOC_SET_ENCRYPTION_POLICY:
+	case FS_IOC_SET_ENCRYPTION_POLICY:
 		if (!ext4_has_feature_encrypt(sb))
 			return -EOPNOTSUPP;
 		return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
 
-	case EXT4_IOC_GET_ENCRYPTION_PWSALT: {
+	case FS_IOC_GET_ENCRYPTION_PWSALT: {
 #ifdef CONFIG_FS_ENCRYPTION
 		int err, err2;
 		struct ext4_sb_info *sbi = EXT4_SB(sb);
···
 		return -EOPNOTSUPP;
 #endif
 	}
-	case EXT4_IOC_GET_ENCRYPTION_POLICY:
+	case FS_IOC_GET_ENCRYPTION_POLICY:
 		if (!ext4_has_feature_encrypt(sb))
 			return -EOPNOTSUPP;
 		return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
···
 	case EXT4_IOC_GET_ES_CACHE:
 		return ext4_ioctl_get_es_cache(filp, arg);
 
-	case EXT4_IOC_FSGETXATTR:
+	case FS_IOC_FSGETXATTR:
 	{
 		struct fsxattr fa;
 
···
 			return -EFAULT;
 		return 0;
 	}
-	case EXT4_IOC_FSSETXATTR:
+	case FS_IOC_FSSETXATTR:
 	{
 		struct fsxattr fa, old_fa;
 		int err;
···
 {
 	/* These are just misnamed, they actually get/put from/to user an int */
 	switch (cmd) {
-	case EXT4_IOC32_GETFLAGS:
-		cmd = EXT4_IOC_GETFLAGS;
+	case FS_IOC32_GETFLAGS:
+		cmd = FS_IOC_GETFLAGS;
 		break;
-	case EXT4_IOC32_SETFLAGS:
-		cmd = EXT4_IOC_SETFLAGS;
+	case FS_IOC32_SETFLAGS:
+		cmd = FS_IOC_SETFLAGS;
 		break;
 	case EXT4_IOC32_GETVERSION:
 		cmd = EXT4_IOC_GETVERSION;
···
 	case EXT4_IOC_RESIZE_FS:
 	case FITRIM:
 	case EXT4_IOC_PRECACHE_EXTENTS:
-	case EXT4_IOC_SET_ENCRYPTION_POLICY:
-	case EXT4_IOC_GET_ENCRYPTION_PWSALT:
-	case EXT4_IOC_GET_ENCRYPTION_POLICY:
+	case FS_IOC_SET_ENCRYPTION_POLICY:
+	case FS_IOC_GET_ENCRYPTION_PWSALT:
+	case FS_IOC_GET_ENCRYPTION_POLICY:
 	case FS_IOC_GET_ENCRYPTION_POLICY_EX:
 	case FS_IOC_ADD_ENCRYPTION_KEY:
 	case FS_IOC_REMOVE_ENCRYPTION_KEY:
···
 	case EXT4_IOC_CLEAR_ES_CACHE:
 	case EXT4_IOC_GETSTATE:
 	case EXT4_IOC_GET_ES_CACHE:
-	case EXT4_IOC_FSGETXATTR:
-	case EXT4_IOC_FSSETXATTR:
+	case FS_IOC_FSGETXATTR:
+	case FS_IOC_FSSETXATTR:
 		break;
 	default:
 		return -ENOIOCTLCMD;

fs/ext4/mballoc.c

···
 			bh[i] = NULL;
 			continue;
 		}
-		bh[i] = ext4_read_block_bitmap_nowait(sb, group);
+		bh[i] = ext4_read_block_bitmap_nowait(sb, group, false);
 		if (IS_ERR(bh[i])) {
 			err = PTR_ERR(bh[i]);
 			bh[i] = NULL;
···
 	/* Pages marked accessed already */
 	e4b->bd_buddy_page = page;
 	e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize);
-
-	BUG_ON(e4b->bd_bitmap_page == NULL);
-	BUG_ON(e4b->bd_buddy_page == NULL);
 
 	return 0;
 
···
 
 }
 
-/*
- * regular allocator, for general purposes allocation
- */
-
 static void ext4_mb_check_limits(struct ext4_allocation_context *ac,
 					struct ext4_buddy *e4b,
 					int finish_group)
···
 
 	BUG_ON(cr < 0 || cr >= 4);
 
-	free = grp->bb_free;
-	if (free == 0)
-		return false;
-	if (cr <= 2 && free < ac->ac_g_ex.fe_len)
+	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp)))
 		return false;
 
-	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp)))
+	free = grp->bb_free;
+	if (free == 0)
 		return false;
 
 	fragments = grp->bb_fragments;
···
 		    ((group % flex_size) == 0))
 			return false;
 
-		if ((ac->ac_2order > ac->ac_sb->s_blocksize_bits+1) ||
-		    (free / fragments) >= ac->ac_g_ex.fe_len)
+		if (free < ac->ac_g_ex.fe_len)
+			return false;
+
+		if (ac->ac_2order > ac->ac_sb->s_blocksize_bits+1)
 			return true;
 
 		if (grp->bb_largest_free_order < ac->ac_2order)
···
 {
 	struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group);
 	struct super_block *sb = ac->ac_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	bool should_lock = ac->ac_flags & EXT4_MB_STRICT_CHECK;
 	ext4_grpblk_t free;
 	int ret = 0;
···
 
 	/* We only do this if the grp has never been initialized */
 	if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
-		ret = ext4_mb_init_group(ac->ac_sb, group, GFP_NOFS);
+		struct ext4_group_desc *gdp =
+			ext4_get_group_desc(sb, group, NULL);
+		int ret;
+
+		/* cr=0/1 is a very optimistic search to find large
+		 * good chunks almost for free.  If buddy data is not
+		 * ready, then this optimization makes no sense.  But
+		 * we never skip the first block group in a flex_bg,
+		 * since this gets used for metadata block allocation,
+		 * and we want to make sure we locate metadata blocks
+		 * in the first block group in the flex_bg if possible.
+		 */
+		if (cr < 2 &&
+		    (!sbi->s_log_groups_per_flex ||
+		     ((group & ((1 << sbi->s_log_groups_per_flex) - 1)) != 0)) &&
+		    !(ext4_has_group_desc_csum(sb) &&
+		      (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))))
+			return 0;
+		ret = ext4_mb_init_group(sb, group, GFP_NOFS);
 		if (ret)
 			return ret;
 	}
···
 	return ret;
 }
 
+/*
+ * Start prefetching @nr block bitmaps starting at @group.
+ * Return the next group which needs to be prefetched.
+ */
+ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group,
+			      unsigned int nr, int *cnt)
+{
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	struct buffer_head *bh;
+	struct blk_plug plug;
+
+	blk_start_plug(&plug);
+	while (nr-- > 0) {
+		struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group,
+								  NULL);
+		struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+
+		/*
+		 * Prefetch block groups with free blocks; but don't
+		 * bother if it is marked uninitialized on disk, since
+		 * it won't require I/O to read.  Also only try to
+		 * prefetch once, so we avoid getblk() call, which can
+		 * be expensive.
+		 */
+		if (!EXT4_MB_GRP_TEST_AND_SET_READ(grp) &&
+		    EXT4_MB_GRP_NEED_INIT(grp) &&
+		    ext4_free_group_clusters(sb, gdp) > 0 &&
+		    !(ext4_has_group_desc_csum(sb) &&
+		      (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) {
+			bh = ext4_read_block_bitmap_nowait(sb, group, true);
+			if (bh && !IS_ERR(bh)) {
+				if (!buffer_uptodate(bh) && cnt)
+					(*cnt)++;
+				brelse(bh);
+			}
+		}
+		if (++group >= ngroups)
+			group = 0;
+	}
+	blk_finish_plug(&plug);
+	return group;
+}
+
+/*
+ * Prefetching reads the block bitmap into the buffer cache; but we
+ * need to make sure that the buddy bitmap in the page cache has been
+ * initialized.  Note that ext4_mb_init_group() will block if the I/O
+ * is not yet completed, or indeed if it was not initiated by
+ * ext4_mb_prefetch did not start the I/O.
+ *
+ * TODO: We should actually kick off the buddy bitmap setup in a work
+ * queue when the buffer I/O is completed, so that we don't block
+ * waiting for the block allocation bitmap read to finish when
+ * ext4_mb_prefetch_fini is called from ext4_mb_regular_allocator().
+ */
+void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group,
+			   unsigned int nr)
+{
+	while (nr-- > 0) {
+		struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group,
+								  NULL);
+		struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+
+		if (!group)
+			group = ext4_get_groups_count(sb);
+		group--;
+		grp = ext4_get_group_info(sb, group);
+
+		if (EXT4_MB_GRP_NEED_INIT(grp) &&
+		    ext4_free_group_clusters(sb, gdp) > 0 &&
+		    !(ext4_has_group_desc_csum(sb) &&
+		      (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) {
+			if (ext4_mb_init_group(sb, group, GFP_NOFS))
+				break;
+		}
+	}
+}
+
 static noinline_for_stack int
 ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 {
-	ext4_group_t ngroups, group, i;
+	ext4_group_t prefetch_grp = 0, ngroups, group, i;
 	int cr = -1;
 	int err = 0, first_err = 0;
+	unsigned int nr = 0, prefetch_ios = 0;
 	struct ext4_sb_info *sbi;
 	struct super_block *sb;
 	struct ext4_buddy e4b;
+	int lost;
 
 	sb = ac->ac_sb;
 	sbi = EXT4_SB(sb);
···
 		goto out;
 
 	/*
-	 * ac->ac2_order is set only if the fe_len is a power of 2
-	 * if ac2_order is set we also set criteria to 0 so that we
+	 * ac->ac_2order is set only if the fe_len is a power of 2
+	 * if ac->ac_2order is set we also set criteria to 0 so that we
 	 * try exact allocation using buddy.
 	 */
 	i = fls(ac->ac_g_ex.fe_len);
···
 		 * from the goal value specified
 		 */
 		group = ac->ac_g_ex.fe_group;
+		prefetch_grp = group;
 
 		for (i = 0; i < ngroups; group++, i++) {
 			int ret = 0;
···
 			 */
 			if (group >= ngroups)
 				group = 0;
+
+			/*
+			 * Batch reads of the block allocation bitmaps
+			 * to get multiple READs in flight; limit
+			 * prefetching at cr=0/1, otherwise mballoc can
+			 * spend a lot of time loading imperfect groups
+			 */
+			if ((prefetch_grp == group) &&
+			    (cr > 1 ||
+			     prefetch_ios < sbi->s_mb_prefetch_limit)) {
+				unsigned int curr_ios = prefetch_ios;
+
+				nr = sbi->s_mb_prefetch;
+				if (ext4_has_feature_flex_bg(sb)) {
+					nr = (group / sbi->s_mb_prefetch) *
+						sbi->s_mb_prefetch;
+					nr = nr + sbi->s_mb_prefetch - group;
+				}
+				prefetch_grp = ext4_mb_prefetch(sb, group,
+							nr, &prefetch_ios);
+				if (prefetch_ios == curr_ios)
+					nr = 0;
+			}
 
 			/* This now checks without needing the buddy page */
 			ret = ext4_mb_good_group_nolock(ac, group, cr);
···
 		 * We've been searching too long. Let's try to allocate
 		 * the best chunk we've found so far
 		 */
-
 		ext4_mb_try_best_found(ac, &e4b);
 		if (ac->ac_status != AC_STATUS_FOUND) {
 			/*
 			 * Someone more lucky has already allocated it.
 			 * The only thing we can do is just take first
 			 * found block(s)
-			printk(KERN_DEBUG "EXT4-fs: someone won our chunk\n");
 			 */
+			lost = atomic_inc_return(&sbi->s_mb_lost_chunks);
+			mb_debug(sb, "lost chunk, group: %u, start: %d, len: %d, lost: %d\n",
+				 ac->ac_b_ex.fe_group, ac->ac_b_ex.fe_start,
+				 ac->ac_b_ex.fe_len, lost);
+
 			ac->ac_b_ex.fe_group = 0;
 			ac->ac_b_ex.fe_start = 0;
 			ac->ac_b_ex.fe_len = 0;
 			ac->ac_status = AC_STATUS_CONTINUE;
 			ac->ac_flags |= EXT4_MB_HINT_FIRST;
 			cr = 3;
-			atomic_inc(&sbi->s_mb_lost_chunks);
 			goto repeat;
 		}
 	}
···
 	mb_debug(sb, "Best len %d, origin len %d, ac_status %u, ac_flags 0x%x, cr %d ret %d\n",
 		 ac->ac_b_ex.fe_len, ac->ac_o_ex.fe_len, ac->ac_status,
 		 ac->ac_flags, cr, err);
+
+	if (nr)
+		ext4_mb_prefetch_fini(sb, prefetch_grp, nr);
+
 	return err;
 }
 
···
 	for (i = 0; i <= 13; i++)
 		seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ?
 				sg.info.bb_counters[i] : 0);
-	seq_printf(seq, " ]\n");
+	seq_puts(seq, " ]\n");
 
 	return 0;
 }
···
 			goto err_freebuddy;
 	}
 
+	if (ext4_has_feature_flex_bg(sb)) {
+		/* a single flex group is supposed to be read by a single IO */
+		sbi->s_mb_prefetch = 1 << sbi->s_es->s_log_groups_per_flex;
+		sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */
+	} else {
+		sbi->s_mb_prefetch = 32;
+	}
+	if (sbi->s_mb_prefetch > ext4_get_groups_count(sb))
+		sbi->s_mb_prefetch = ext4_get_groups_count(sb);
+	/* now many real IOs to prefetch within a single allocation at cr=0
+	 * given cr=0 is an CPU-related optimization we shouldn't try to
+	 * load too many groups, at some point we should start to use what
+	 * we've got in memory.
+	 * with an average random access time 5ms, it'd take a second to get
+	 * 200 groups (* N with flex_bg), so let's make this limit 4
+	 */
+	sbi->s_mb_prefetch_limit = sbi->s_mb_prefetch * 4;
+	if (sbi->s_mb_prefetch_limit > ext4_get_groups_count(sb))
+		sbi->s_mb_prefetch_limit = ext4_get_groups_count(sb);
+
 	return 0;
 
 err_freebuddy:
···
 	sbi->s_mb_stats = MB_DEFAULT_STATS;
 	sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD;
 	sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS;
+	sbi->s_mb_max_inode_prealloc = MB_DEFAULT_MAX_INODE_PREALLOC;
 	/*
 	 * The default group preallocation is 512, which for 4k block
 	 * sizes translates to 2 megabytes.  However for bigalloc file
···
 	block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
 
 	len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
-	if (!ext4_data_block_valid(sbi, block, len)) {
+	if (!ext4_inode_block_valid(ac->ac_inode, block, len)) {
 		ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
 			   "fs metadata", block, block+len);
 		/* File system mounted not to panic on error
···
 	mb_debug(sb, "preallocated %d for group %u\n", preallocated, group);
 }
 
+static void ext4_mb_mark_pa_deleted(struct super_block *sb,
+				    struct ext4_prealloc_space *pa)
+{
+	struct ext4_inode_info *ei;
+
+	if (pa->pa_deleted) {
+		ext4_warning(sb, "deleted pa, type:%d, pblk:%llu, lblk:%u, len:%d\n",
+			     pa->pa_type, pa->pa_pstart, pa->pa_lstart,
+			     pa->pa_len);
+		return;
+	}
+
+	pa->pa_deleted = 1;
+
+	if (pa->pa_type == MB_INODE_PA) {
+		ei = EXT4_I(pa->pa_inode);
+		atomic_dec(&ei->i_prealloc_active);
+	}
+}
+
 static void ext4_mb_pa_callback(struct rcu_head *head)
 {
 	struct ext4_prealloc_space *pa;
···
 		return;
 	}
 
-	pa->pa_deleted = 1;
+	ext4_mb_mark_pa_deleted(sb, pa);
 	spin_unlock(&pa->pa_lock);
 
 	grp_blk = pa->pa_pstart;
···
 	spin_lock(pa->pa_obj_lock);
 	list_add_rcu(&pa->pa_inode_list, &ei->i_prealloc_list);
 	spin_unlock(pa->pa_obj_lock);
+	atomic_inc(&ei->i_prealloc_active);
 }
 
 /*
···
 		}
 
 		/* seems this one can be freed ... */
-		pa->pa_deleted = 1;
+		ext4_mb_mark_pa_deleted(sb, pa);
 
 		/* we can trust pa_free ... */
 		free += pa->pa_free;
···
  *
  * FIXME!! Make sure it is valid at all the call sites
  */
-void ext4_discard_preallocations(struct inode *inode)
+void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct super_block *sb = inode->i_sb;
···
 
 	mb_debug(sb, "discard preallocation for inode %lu\n",
 		 inode->i_ino);
-	trace_ext4_discard_preallocations(inode);
+	trace_ext4_discard_preallocations(inode,
+			atomic_read(&ei->i_prealloc_active), needed);
 
 	INIT_LIST_HEAD(&list);
+
+	if (needed == 0)
+		needed = UINT_MAX;
 
 repeat:
 	/* first, collect all pa's in the inode */
 	spin_lock(&ei->i_prealloc_lock);
-	while (!list_empty(&ei->i_prealloc_list)) {
-		pa = list_entry(ei->i_prealloc_list.next,
+	while (!list_empty(&ei->i_prealloc_list) && needed) {
+		pa = list_entry(ei->i_prealloc_list.prev,
 				struct ext4_prealloc_space, pa_inode_list);
 		BUG_ON(pa->pa_obj_lock != &ei->i_prealloc_lock);
 		spin_lock(&pa->pa_lock);
···
 
 		}
 		if (pa->pa_deleted == 0) {
-			pa->pa_deleted = 1;
+			ext4_mb_mark_pa_deleted(sb, pa);
 			spin_unlock(&pa->pa_lock);
 			list_del_rcu(&pa->pa_inode_list);
 			list_add(&pa->u.pa_tmp_list, &list);
+			needed--;
 			continue;
 		}
 
···
 	ac->ac_g_ex = ac->ac_o_ex;
 	ac->ac_flags = ar->flags;
 
-	/* we have to define context: we'll we work with a file or
+	/* we have to define context: we'll work with a file or
 	 * locality group. this is a policy, actually */
 	ext4_mb_group_or_file(ac);
 
···
 		BUG_ON(pa->pa_type != MB_GROUP_PA);
 
 		/* seems this one can be freed ... */
-		pa->pa_deleted = 1;
+		ext4_mb_mark_pa_deleted(sb, pa);
 		spin_unlock(&pa->pa_lock);
 
 		list_del_rcu(&pa->pa_inode_list);
···
 }
 
 /*
+ * if per-inode prealloc list is too long, trim some PA
+ */
+static void ext4_mb_trim_inode_pa(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	int count, delta;
+
+	count = atomic_read(&ei->i_prealloc_active);
+	delta = (sbi->s_mb_max_inode_prealloc >> 2) + 1;
+	if (count > sbi->s_mb_max_inode_prealloc + delta) {
+		count -= sbi->s_mb_max_inode_prealloc;
+		ext4_discard_preallocations(inode, count);
+	}
+}
+
+/*
  * release all resource we used in allocation
  */
 static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 {
+	struct inode *inode = ac->ac_inode;
+	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_prealloc_space *pa = ac->ac_pa;
 	if (pa) {
···
 			pa->pa_free -= ac->ac_b_ex.fe_len;
 			pa->pa_len -= ac->ac_b_ex.fe_len;
 			spin_unlock(&pa->pa_lock);
+
+			/*
+			 * We want to add the pa to the right bucket.
+			 * Remove it from the list and while adding
+			 * make sure the list to which we are adding
+			 * doesn't grow big.
+			 */
+			if (likely(pa->pa_free)) {
+				spin_lock(pa->pa_obj_lock);
+				list_del_rcu(&pa->pa_inode_list);
+				spin_unlock(pa->pa_obj_lock);
+				ext4_mb_add_n_trim(ac);
+			}
 		}
-	}
-	if (pa) {
-		/*
-		 * We want to add the pa to the right bucket.
-		 * Remove it from the list and while adding
-		 * make sure the list to which we are adding
-		 * doesn't grow big.
-		 */
-		if ((pa->pa_type == MB_GROUP_PA) && likely(pa->pa_free)) {
+
+		if (pa->pa_type == MB_INODE_PA) {
+			/*
+			 * treat per-inode prealloc list as a lru list, then try
+			 * to trim the least recently used PA.
+			 */
 			spin_lock(pa->pa_obj_lock);
-			list_del_rcu(&pa->pa_inode_list);
+			list_move(&pa->pa_inode_list, &ei->i_prealloc_list);
 			spin_unlock(pa->pa_obj_lock);
-			ext4_mb_add_n_trim(ac);
 		}
+
 		ext4_mb_put_pa(ac, ac->ac_sb, pa);
 	}
 	if (ac->ac_bitmap_page)
···
 	if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)
 		mutex_unlock(&ac->ac_lg->lg_mutex);
 	ext4_mb_collect_stats(ac);
+	ext4_mb_trim_inode_pa(inode);
 	return 0;
 }
 
···
 
 	sbi = EXT4_SB(sb);
 	if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
-	    !ext4_data_block_valid(sbi, block, count)) {
+	    !ext4_inode_block_valid(inode, block, count)) {
 		ext4_error(sb, "Freeing blocks not in datazone - "
 			   "block = %llu, count = %lu", block, count);
 		goto error_return;

fs/ext4/mballoc.h

···
  */
 #define MB_DEFAULT_GROUP_PREALLOC	512
 
+/*
+ * maximum length of inode prealloc list
+ */
+#define MB_DEFAULT_MAX_INODE_PREALLOC	512
 
 struct ext4_free_data {
 	/* this links the free block information from sb_info */

fs/ext4/move_extent.c

···
 
 out:
 	if (*moved_len) {
-		ext4_discard_preallocations(orig_inode);
-		ext4_discard_preallocations(donor_inode);
+		ext4_discard_preallocations(orig_inode, 0);
+		ext4_discard_preallocations(donor_inode, 0);
 	}
 
 	ext4_ext_drop_refs(path);

fs/ext4/namei.c

···
 		    ext4_match(dir, fname, de)) {
 			/* found a match - just to be sure, do
 			 * a full check */
-			if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data,
-						 bh->b_size, offset))
+			if (ext4_check_dir_entry(dir, NULL, de, bh, search_buf,
+						 buf_size, offset))
 				return -1;
 			*res_dir = de;
 			return 1;
···
 			     blocksize, hinfo, map);
 	map -= count;
 	dx_sort_map(map, count);
-	/* Split the existing block in the middle, size-wise */
+	/* Ensure that neither split block is over half full */
 	size = 0;
 	move = 0;
 	for (i = count-1; i >= 0; i--) {
···
 		size += map[i].size;
 		move++;
 	}
-	/* map index at which we will split */
-	split = count - move;
+	/*
+	 * map index at which we will split
+	 *
+	 * If the sum of active entries didn't exceed half the block size, just
+	 * split it in half by count; each resulting block will have at least
+	 * half the space free.
+	 */
+	if (i > 0)
+		split = count - move;
+	else
+		split = count/2;
+
 	hash2 = map[split].hash;
 	continued = hash2 == map[split - 1].hash;
 	dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n",
···
  * ext4_generic_delete_entry deletes a directory entry by merging it
  * with the previous entry
  */
-int ext4_generic_delete_entry(handle_t *handle,
-			      struct inode *dir,
+int ext4_generic_delete_entry(struct inode *dir,
 			      struct ext4_dir_entry_2 *de_del,
 			      struct buffer_head *bh,
 			      void *entry_buf,
···
 	de = (struct ext4_dir_entry_2 *)entry_buf;
 	while (i < buf_size - csum_size) {
 		if (ext4_check_dir_entry(dir, NULL, de, bh,
-					 bh->b_data, bh->b_size, i))
+					 entry_buf, buf_size, i))
 			return -EFSCORRUPTED;
 		if (de == de_del)  {
 			if (pde)
···
 	if (unlikely(err))
 		goto out;
 
-	err = ext4_generic_delete_entry(handle, dir, de_del,
-					bh, bh->b_data,
+	err = ext4_generic_delete_entry(dir, de_del, bh, bh->b_data,
 					dir->i_sb->s_blocksize, csum_size);
 	if (err)
 		goto out;
···
 	 * in separate transaction */
 	retval = dquot_initialize(dir);
 	if (retval)
-		return retval;
+		goto out_trace;
 	retval = dquot_initialize(d_inode(dentry));
 	if (retval)
-		return retval;
+		goto out_trace;
 
-	retval = -ENOENT;
 	bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
-	if (IS_ERR(bh))
-		return PTR_ERR(bh);
-	if (!bh)
-		goto end_unlink;
+	if (IS_ERR(bh)) {
+		retval = PTR_ERR(bh);
+		goto out_trace;
+	}
+	if (!bh) {
+		retval = -ENOENT;
+		goto out_trace;
+	}
 
 	inode = d_inode(dentry);
 
-	retval = -EFSCORRUPTED;
-	if (le32_to_cpu(de->inode) != inode->i_ino)
-		goto end_unlink;
+	if (le32_to_cpu(de->inode) != inode->i_ino) {
+		retval = -EFSCORRUPTED;
+		goto out_bh;
+	}
 
 	handle = ext4_journal_start(dir, EXT4_HT_DIR,
 				    EXT4_DATA_TRANS_BLOCKS(dir->i_sb));
 	if (IS_ERR(handle)) {
 		retval = PTR_ERR(handle);
-		handle = NULL;
-		goto end_unlink;
+		goto out_bh;
 	}
 
 	if (IS_DIRSYNC(dir))
···
 
 	retval = ext4_delete_entry(handle, dir, de, bh);
 	if (retval)
-		goto end_unlink;
+		goto out_handle;
 	dir->i_ctime = dir->i_mtime = current_time(dir);
 	ext4_update_dx_flag(dir);
 	retval = ext4_mark_inode_dirty(handle, dir);
 	if (retval)
-		goto end_unlink;
+		goto out_handle;
 	if (inode->i_nlink == 0)
 		ext4_warning_inode(inode, "Deleting file '%.*s' with no links",
 				   dentry->d_name.len, dentry->d_name.name);
···
 		d_invalidate(dentry);
 #endif
 
-end_unlink:
+out_handle:
+	ext4_journal_stop(handle);
+out_bh:
 	brelse(bh);
-	if (handle)
-		ext4_journal_stop(handle);
+out_trace:
 	trace_ext4_unlink_exit(dentry, retval);
 	return retval;
 }

fs/ext4/readpage.c

···
 			return;
 		}
 		ctx->cur_step++;
-		/* fall-through */
+		fallthrough;
 	case STEP_VERITY:
 		if (ctx->enabled_steps & (1 << STEP_VERITY)) {
 			INIT_WORK(&ctx->work, verity_work);
···
 			return;
 		}
 		ctx->cur_step++;
-		/* fall-through */
+		fallthrough;
 	default:
 		__read_end_io(ctx->bio);
 	}

fs/ext4/super.c

···
 			     unsigned long journal_devnum);
 static int ext4_show_options(struct seq_file *seq, struct dentry *root);
 static int ext4_commit_super(struct super_block *sb, int sync);
-static void ext4_mark_recovery_complete(struct super_block *sb,
+static int ext4_mark_recovery_complete(struct super_block *sb,
 					struct ext4_super_block *es);
-static void ext4_clear_journal_err(struct super_block *sb,
-				   struct ext4_super_block *es);
+static int ext4_clear_journal_err(struct super_block *sb,
+				  struct ext4_super_block *es);
 static int ext4_sync_fs(struct super_block *sb, int wait);
 static int ext4_remount(struct super_block *sb, int *flags, char *data);
 static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
···
 	struct va_format vaf;
 	va_list args;
 
+	atomic_inc(&EXT4_SB(sb)->s_msg_count);
 	if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), "EXT4-fs"))
 		return;
 
···
 	va_end(args);
 }
 
-#define ext4_warning_ratelimit(sb)					\
-		___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state),	\
-			     "EXT4-fs warning")
+static int ext4_warning_ratelimit(struct super_block *sb)
+{
+	atomic_inc(&EXT4_SB(sb)->s_warning_count);
+	return ___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state),
+			    "EXT4-fs warning");
+}
 
 void __ext4_warning(struct super_block *sb, const char *function,
 		    unsigned int line, const char *fmt, ...)
···
 	inode_set_iversion(&ei->vfs_inode, 1);
 	spin_lock_init(&ei->i_raw_lock);
 	INIT_LIST_HEAD(&ei->i_prealloc_list);
+	atomic_set(&ei->i_prealloc_active, 0);
 	spin_lock_init(&ei->i_prealloc_lock);
 	ext4_es_init_tree(&ei->i_es_tree);
 	rwlock_init(&ei->i_es_lock);
···
 {
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
-	ext4_discard_preallocations(inode);
+	ext4_discard_preallocations(inode, 0);
 	ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
 	dquot_drop(inode);
 	if (EXT4_I(inode)->jinode) {
···
 	if (!page_has_buffers(page))
 		return 0;
 	if (journal)
-		return jbd2_journal_try_to_free_buffers(journal, page,
-						wait & ~__GFP_DIRECT_RECLAIM);
+		return jbd2_journal_try_to_free_buffers(journal, page);
+
 	return try_to_free_buffers(page);
 }
 
···
 	Opt_dioread_nolock, Opt_dioread_lock,
 	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
 	Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
+	Opt_prefetch_block_bitmaps,
 };
 
 static const match_table_t tokens = {
···
 	{Opt_inlinecrypt, "inlinecrypt"},
 	{Opt_nombcache, "nombcache"},
 	{Opt_nombcache, "no_mbcache"},	/* for backward compatibility */
+	{Opt_prefetch_block_bitmaps, "prefetch_block_bitmaps"},
 	{Opt_removed, "check=none"},	/* mount option from ext2/3 */
 	{Opt_removed, "nocheck"},	/* mount option from ext2/3 */
 	{Opt_removed, "reservation"},	/* mount option from ext2/3 */
···
 	{Opt_max_dir_size_kb, 0, MOPT_GTE0},
 	{Opt_test_dummy_encryption, 0, MOPT_STRING},
 	{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
+	{Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS,
+	 MOPT_SET},
 	{Opt_err, 0, 0}
 };
 
···
 static int ext4_run_li_request(struct ext4_li_request *elr)
 {
 	struct ext4_group_desc *gdp = NULL;
-	ext4_group_t group, ngroups;
-	struct super_block *sb;
+	struct super_block *sb = elr->lr_super;
+	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+	ext4_group_t group = elr->lr_next_group;
 	unsigned long timeout = 0;
+	unsigned int prefetch_ios = 0;
 	int ret = 0;
 
-	sb = elr->lr_super;
-	ngroups = EXT4_SB(sb)->s_groups_count;
+	if (elr->lr_mode == EXT4_LI_MODE_PREFETCH_BBITMAP) {
+		elr->lr_next_group = ext4_mb_prefetch(sb, group,
+				EXT4_SB(sb)->s_mb_prefetch, &prefetch_ios);
+		if (prefetch_ios)
+			ext4_mb_prefetch_fini(sb, elr->lr_next_group,
+					      prefetch_ios);
+		trace_ext4_prefetch_bitmaps(sb, group, elr->lr_next_group,
+					    prefetch_ios);
+		if (group >= elr->lr_next_group) {
+			ret = 1;
+			if (elr->lr_first_not_zeroed != ngroups &&
+			    !sb_rdonly(sb) && test_opt(sb, INIT_INODE_TABLE)) {
+				elr->lr_next_group = elr->lr_first_not_zeroed;
+				elr->lr_mode = EXT4_LI_MODE_ITABLE;
+				ret = 0;
+			}
+		}
+		return ret;
+	}
 
-	for (group = elr->lr_next_group; group < ngroups; group++) {
+	for (; group < ngroups; group++) {
 		gdp = ext4_get_group_desc(sb, group, NULL);
 		if (!gdp) {
 			ret = 1;
···
 		timeout = jiffies;
 		ret = ext4_init_inode_table(sb, group,
 					    elr->lr_timeout ? 0 : 1);
+		trace_ext4_lazy_itable_init(sb, group);
 		if (elr->lr_timeout == 0) {
 			timeout = (jiffies - timeout) *
-				  elr->lr_sbi->s_li_wait_mult;
+				EXT4_SB(elr->lr_super)->s_li_wait_mult;
 			elr->lr_timeout = timeout;
 		}
 		elr->lr_next_sched = jiffies + elr->lr_timeout;
···
  */
 static void ext4_remove_li_request(struct ext4_li_request *elr)
 {
-	struct ext4_sb_info *sbi;
-
 	if (!elr)
 		return;
 
-	sbi = elr->lr_sbi;
-
 	list_del(&elr->lr_request);
-	sbi->s_li_request = NULL;
+	EXT4_SB(elr->lr_super)->s_li_request = NULL;
 	kfree(elr);
 }
 
···
 static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
 					    ext4_group_t start)
 {
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_li_request *elr;
 
 	elr = kzalloc(sizeof(*elr), GFP_KERNEL);
···
 		return NULL;
 
 	elr->lr_super = sb;
-	elr->lr_sbi = sbi;
-	elr->lr_next_group = start;
+	elr->lr_first_not_zeroed = start;
+	if (test_opt(sb, PREFETCH_BLOCK_BITMAPS))
+		elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP;
+	else {
+		elr->lr_mode = EXT4_LI_MODE_ITABLE;
+		elr->lr_next_group = start;
+	}
 
 	/*
 	 * Randomize first schedule time of the request to
···
 		goto out;
 	}
 
-	if (first_not_zeroed == ngroups || sb_rdonly(sb) ||
-	    !test_opt(sb, INIT_INODE_TABLE))
+	if (!test_opt(sb, PREFETCH_BLOCK_BITMAPS) &&
+	    (first_not_zeroed == ngroups || sb_rdonly(sb) ||
+	     !test_opt(sb, INIT_INODE_TABLE)))
 		goto out;
 
 	elr = ext4_li_request_new(sb, first_not_zeroed);
···
 
 	ext4_set_resv_clusters(sb);
 
-	err = ext4_setup_system_zone(sb);
-	if (err) {
-		ext4_msg(sb, KERN_ERR, "failed to initialize system "
-			 "zone (%d)", err);
-		goto failed_mount4a;
+	if (test_opt(sb, BLOCK_VALIDITY)) {
+		err = ext4_setup_system_zone(sb);
+		if (err) {
+			ext4_msg(sb, KERN_ERR, "failed to initialize system "
+				 "zone (%d)", err);
+			goto failed_mount4a;
+		}
 	}
 
 	ext4_ext_init(sb);
···
 	}
 #endif  /* CONFIG_QUOTA */
 
+	/*
+	 * Save the original bdev mapping's wb_err value which could be
+	 * used to detect the metadata async write error.
+	 */
+	spin_lock_init(&sbi->s_bdev_wb_lock);
+	if (!sb_rdonly(sb))
+		errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err,
+					 &sbi->s_bdev_wb_err);
+	sb->s_bdev->bd_super = sb;
 	EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
 	ext4_orphan_cleanup(sb, es);
 	EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
 	if (needs_recovery) {
 		ext4_msg(sb, KERN_INFO, "recovery complete");
-		ext4_mark_recovery_complete(sb, es);
+		err = ext4_mark_recovery_complete(sb, es);
+		if (err)
+			goto failed_mount8;
 	}
 	if (EXT4_SB(sb)->s_journal) {
 		if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
···
 	ratelimit_state_init(&sbi->s_err_ratelimit_state, 5 * HZ, 10);
 	ratelimit_state_init(&sbi->s_warning_ratelimit_state, 5 * HZ, 10);
 	ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10);
+	atomic_set(&sbi->s_warning_count, 0);
+	atomic_set(&sbi->s_msg_count, 0);
 
 	kfree(orig_data);
 	return 0;
···
 		ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
 	goto failed_mount;
 
-#ifdef CONFIG_QUOTA
 failed_mount8:
 	ext4_unregister_sysfs(sb);
-#endif
 failed_mount7:
 	ext4_unregister_li_request(sb);
 failed_mount6:
···
 	struct inode *journal_inode;
 	journal_t *journal;
 
-	BUG_ON(!ext4_has_feature_journal(sb));
+	if (WARN_ON_ONCE(!ext4_has_feature_journal(sb)))
+		return NULL;
 
 	journal_inode = ext4_get_journal_inode(sb, journal_inum);
 	if (!journal_inode)
···
 	struct ext4_super_block *es;
 	struct block_device *bdev;
 
-	BUG_ON(!ext4_has_feature_journal(sb));
+	if (WARN_ON_ONCE(!ext4_has_feature_journal(sb)))
+		return NULL;
 
 	bdev = ext4_blkdev_get(j_dev, sb);
 	if (bdev == NULL)
···
 	dev_t journal_dev;
 	int err = 0;
 	int really_read_only;
+	int journal_dev_ro;
 
-	BUG_ON(!ext4_has_feature_journal(sb));
+	if (WARN_ON_ONCE(!ext4_has_feature_journal(sb)))
+		return -EFSCORRUPTED;
 
 	if (journal_devnum &&
 	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
···
 	} else
 		journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev));
 
-	really_read_only = bdev_read_only(sb->s_bdev);
+	if (journal_inum && journal_dev) {
+		ext4_msg(sb, KERN_ERR,
+			 "filesystem has both journal inode and journal device!");
+		return -EINVAL;
+	}
+
+	if (journal_inum) {
+		journal = ext4_get_journal(sb, journal_inum);
+		if (!journal)
+			return -EINVAL;
+	} else {
+		journal = ext4_get_dev_journal(sb, journal_dev);
+		if (!journal)
+			return -EINVAL;
+	}
+
+	journal_dev_ro = bdev_read_only(journal->j_dev);
+	really_read_only = bdev_read_only(sb->s_bdev) | journal_dev_ro;
+
+	if (journal_dev_ro && !sb_rdonly(sb)) {
+		ext4_msg(sb, KERN_ERR,
+			 "journal device read-only, try mounting with '-o ro'");
+		err = -EROFS;
+		goto err_out;
+	}
 
 	/*
 	 * Are we loading a blank journal or performing recovery after a
···
 				ext4_msg(sb, KERN_ERR, "write access "
 					"unavailable, cannot proceed "
 					"(try mounting with noload)");
-				return -EROFS;
+				err = -EROFS;
+				goto err_out;
 			}
 			ext4_msg(sb, KERN_INFO, "write access will "
 			       "be enabled during recovery");
 		}
-	}
-
-	if (journal_inum && journal_dev) {
-		ext4_msg(sb, KERN_ERR, "filesystem has both journal "
-		       "and inode journals!");
-		return -EINVAL;
-	}
-
-	if (journal_inum) {
-		if (!(journal = ext4_get_journal(sb, journal_inum)))
-			return -EINVAL;
-	} else {
-		if (!(journal = ext4_get_dev_journal(sb, journal_dev)))
-			return -EINVAL;
 	}
 
 	if (!(journal->j_flags & JBD2_BARRIER))
···
 
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "error loading journal");
-		jbd2_journal_destroy(journal);
-		return err;
+		goto err_out;
 	}
 
 	EXT4_SB(sb)->s_journal = journal;
-	ext4_clear_journal_err(sb, es);
+	err = ext4_clear_journal_err(sb, es);
+	if (err) {
+		EXT4_SB(sb)->s_journal = NULL;
+		jbd2_journal_destroy(journal);
+		return err;
+	}
 
 	if (!really_read_only && journal_devnum &&
 	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
···
 	}
 
 	return 0;
+
+err_out:
+	jbd2_journal_destroy(journal);
+	return err;
 }
 
 static int ext4_commit_super(struct super_block *sb, int sync)
···
 	int error = 0;
 
 	if (!sbh || block_device_ejected(sb))
-		return error;
-
-	/*
-	 * The superblock bh should be mapped, but it might not be if the
-	 * device was hot-removed. Not much we can do but fail the I/O.
-	 */
-	if (!buffer_mapped(sbh))
 		return error;
 
 	/*
···
  * remounting) the filesystem readonly, then we will end up with a
  * consistent fs on disk.  Record that fact.
  */
-static void ext4_mark_recovery_complete(struct super_block *sb,
-					struct ext4_super_block *es)
+static int ext4_mark_recovery_complete(struct super_block *sb,
+				       struct ext4_super_block *es)
 {
+	int err;
 	journal_t *journal = EXT4_SB(sb)->s_journal;
 
 	if (!ext4_has_feature_journal(sb)) {
-		BUG_ON(journal != NULL);
-		return;
+		if (journal != NULL) {
+			ext4_error(sb, "Journal got removed while the fs was "
+				   "mounted!");
+			return -EFSCORRUPTED;
+		}
+		return 0;
 	}
 	jbd2_journal_lock_updates(journal);
-	if (jbd2_journal_flush(journal) < 0)
+	err = jbd2_journal_flush(journal);
+	if (err < 0)
 		goto out;
 
 	if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) {
 		ext4_clear_feature_journal_needs_recovery(sb);
 		ext4_commit_super(sb, 1);
 	}
-
 out:
 	jbd2_journal_unlock_updates(journal);
+	return err;
 }
 
 /*
···
  * has recorded an error from a previous lifetime, move that error to the
  * main filesystem now.
  */
-static void ext4_clear_journal_err(struct super_block *sb,
+static int ext4_clear_journal_err(struct super_block *sb,
 				   struct ext4_super_block *es)
 {
 	journal_t *journal;
 	int j_errno;
 	const char *errstr;
 
-	BUG_ON(!ext4_has_feature_journal(sb));
+	if (!ext4_has_feature_journal(sb)) {
+		ext4_error(sb, "Journal got removed while the fs was mounted!");
+		return -EFSCORRUPTED;
+	}
 
 	journal = EXT4_SB(sb)->s_journal;
 
···
 		jbd2_journal_clear_err(journal);
 		jbd2_journal_update_sb_errno(journal);
 	}
+	return 0;
 }
 
 /*
···
 {
 	struct ext4_super_block *es;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	unsigned long old_sb_flags;
+	unsigned long old_sb_flags, vfs_flags;
 	struct ext4_mount_options old_opts;
 	int enable_quota = 0;
 	ext4_group_t g;
···
 #endif
 	if (sbi->s_journal && sbi->s_journal->j_task->io_context)
 		journal_ioprio = sbi->s_journal->j_task->io_context->ioprio;
+
+	/*
+	 * Some options can be enabled by ext4 and/or by VFS mount flag
+	 * either way we need to make sure it matches in both *flags and
+	 * s_flags. Copy those selected flags from *flags to s_flags
+	 */
+	vfs_flags = SB_LAZYTIME | SB_I_VERSION;
+	sb->s_flags = (sb->s_flags & ~vfs_flags) | (*flags & vfs_flags);
 
 	if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) {
 		err = -EINVAL;
···
 		set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
 	}
 
-	if (*flags & SB_LAZYTIME)
-		sb->s_flags |= SB_LAZYTIME;
-
 	if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) {
 		if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
 			err = -EROFS;
···
 			    (sbi->s_mount_state & EXT4_VALID_FS))
 				es->s_state = cpu_to_le16(sbi->s_mount_state);
 
-			if (sbi->s_journal)
+			if (sbi->s_journal) {
+				/*
+				 * We let remount-ro finish even if marking fs
+				 * as clean failed...
+				 */
 				ext4_mark_recovery_complete(sb, es);
+			}
 			if (sbi->s_mmp_tsk)
 				kthread_stop(sbi->s_mmp_tsk);
 		} else {
···
 			}
 
 			/*
+			 * Update the original bdev mapping's wb_err value
+			 * which could be used to detect the metadata async
+			 * write error.
+			 */
+			errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err,
+						 &sbi->s_bdev_wb_err);
+
+			/*
 			 * Mounting a RDONLY partition read-write, so reread
 			 * and store the current valid flag.  (It may have
 			 * been changed by e2fsck since we originally mounted
 			 * the partition.)
 			 */
-			if (sbi->s_journal)
-				ext4_clear_journal_err(sb, es);
+			if (sbi->s_journal) {
+				err = ext4_clear_journal_err(sb, es);
+				if (err)
+					goto restore_opts;
+			}
 			sbi->s_mount_state = le16_to_cpu(es->s_state);
 
 			err = ext4_setup_super(sb, es, 0);
···
 		ext4_register_li_request(sb, first_not_zeroed);
 	}
 
-	ext4_setup_system_zone(sb);
+	/*
+	 * Handle creation of system zone data early because it can fail.
+	 * Releasing of existing data is done when we are sure remount will
+	 * succeed.
+	 */
+	if (test_opt(sb, BLOCK_VALIDITY) && !sbi->system_blks) {
+		err = ext4_setup_system_zone(sb);
+		if (err)
+			goto restore_opts;
+	}
+
 	if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) {
 		err = ext4_commit_super(sb, 1);
 		if (err)
···
 		}
 	}
 #endif
+	if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks)
+		ext4_release_system_zone(sb);
 
-	*flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME);
+	/*
+	 * Some options can be enabled by ext4 and/or by VFS mount flag
+	 * either way we need to make sure it matches in both *flags and
+	 * s_flags. Copy those selected flags from s_flags to *flags
+	 */
+	*flags = (*flags & ~vfs_flags) | (sb->s_flags & vfs_flags);
+
 	ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
 	kfree(orig_data);
 	return 0;
···
 	sbi->s_commit_interval = old_opts.s_commit_interval;
 	sbi->s_min_batch_time = old_opts.s_min_batch_time;
 	sbi->s_max_batch_time = old_opts.s_max_batch_time;
+	if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks)
+		ext4_release_system_zone(sb);
 #ifdef CONFIG_QUOTA
 	sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
 	for (i = 0; i < EXT4_MAXQUOTAS; i++) {

fs/ext4/sysfs.c

···
 #define EXT4_RW_ATTR_SBI_UL(_name,_elname)	\
 	EXT4_ATTR_OFFSET(_name, 0644, pointer_ul, ext4_sb_info, _elname)
 
+#define EXT4_RO_ATTR_SBI_ATOMIC(_name,_elname)	\
+	EXT4_ATTR_OFFSET(_name, 0444, pointer_atomic, ext4_sb_info, _elname)
+
 #define EXT4_ATTR_PTR(_name,_mode,_id,_ptr) \
 static struct ext4_attr ext4_attr_##_name = {			\
 	.attr = {.name = __stringify(_name), .mode = _mode },	\
···
 EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
 EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
 EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
+EXT4_RW_ATTR_SBI_UI(mb_max_inode_prealloc, s_mb_max_inode_prealloc);
 EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb);
 EXT4_ATTR(trigger_fs_error, 0200, trigger_test_error);
 EXT4_RW_ATTR_SBI_UI(err_ratelimit_interval_ms, s_err_ratelimit_state.interval);
···
 #ifdef CONFIG_EXT4_DEBUG
 EXT4_RW_ATTR_SBI_UL(simulate_fail, s_simulate_fail);
 #endif
+EXT4_RO_ATTR_SBI_ATOMIC(warning_count, s_warning_count);
+EXT4_RO_ATTR_SBI_ATOMIC(msg_count, s_msg_count);
 EXT4_RO_ATTR_ES_UI(errors_count, s_error_count);
 EXT4_RO_ATTR_ES_U8(first_error_errcode, s_first_error_errcode);
 EXT4_RO_ATTR_ES_U8(last_error_errcode, s_last_error_errcode);
···
 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);
+EXT4_RW_ATTR_SBI_UI(mb_prefetch, s_mb_prefetch);
+EXT4_RW_ATTR_SBI_UI(mb_prefetch_limit, s_mb_prefetch_limit);
 
 static unsigned int old_bump_val = 128;
 EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val);
···
 	ATTR_LIST(mb_order2_req),
 	ATTR_LIST(mb_stream_req),
 	ATTR_LIST(mb_group_prealloc),
+	ATTR_LIST(mb_max_inode_prealloc),
 	ATTR_LIST(max_writeback_mb_bump),
 	ATTR_LIST(extent_max_zeroout_kb),
 	ATTR_LIST(trigger_fs_error),
···
 	ATTR_LIST(msg_ratelimit_interval_ms),
 	ATTR_LIST(msg_ratelimit_burst),
 	ATTR_LIST(errors_count),
+	ATTR_LIST(warning_count),
+	ATTR_LIST(msg_count),
 	ATTR_LIST(first_error_ino),
 	ATTR_LIST(last_error_ino),
 	ATTR_LIST(first_error_block),
···
 #ifdef CONFIG_EXT4_DEBUG
 	ATTR_LIST(simulate_fail),
 #endif
+	ATTR_LIST(mb_prefetch),
+	ATTR_LIST(mb_prefetch_limit),
 	NULL,
 };
 ATTRIBUTE_GROUPS(ext4);

fs/ext4/xattr.c

···
 
 	block = 0;
 	while (wsize < bufsize) {
-		if (bh != NULL)
-			brelse(bh);
+		brelse(bh);
 		csize = (bufsize - wsize) > blocksize ? blocksize :
 								bufsize - wsize;
 		bh = ext4_getblk(handle, ea_inode, block, 0);

fs/jbd2/journal.c

···
  * superblock as being NULL to prevent the journal destroy from writing
  * back a bogus superblock.
  */
-static void journal_fail_superblock (journal_t *journal)
+static void journal_fail_superblock(journal_t *journal)
 {
 	struct buffer_head *bh = journal->j_sb_buffer;
 	brelse(bh);
···
 	int ret;
 
 	/* Buffer got discarded which means block device got invalidated */
-	if (!buffer_mapped(bh))
+	if (!buffer_mapped(bh)) {
+		unlock_buffer(bh);
 		return -EIO;
+	}
 
 	trace_jbd2_write_superblock(journal, write_flags);
 	if (!(journal->j_flags & JBD2_BARRIER))
···
 
 
 /**
- *int jbd2_journal_check_used_features () - Check if features specified are used.
+ *int jbd2_journal_check_used_features() - Check if features specified are used.
  * @journal: Journal to check.
  * @compat: bitmask of compatible features
  * @ro: bitmask of features that force read-only mount
···
  * features.  Return true (non-zero) if it does.
  **/
 
-int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat,
+int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat,
 				 unsigned long ro, unsigned long incompat)
 {
 	journal_superblock_t *sb;
···
  * all of a given set of features on this journal.  Return true
  * (non-zero) if it can. */
 
-int jbd2_journal_check_available_features (journal_t *journal, unsigned long compat,
+int jbd2_journal_check_available_features(journal_t *journal, unsigned long compat,
 				      unsigned long ro, unsigned long incompat)
 {
 	if (!compat && !ro && !incompat)
···
 }
 
 /**
- * int jbd2_journal_set_features () - Mark a given journal feature in the superblock
+ * int jbd2_journal_set_features() - Mark a given journal feature in the superblock
  * @journal: Journal to act on.
  * @compat: bitmask of compatible features
  * @ro: bitmask of features that force read-only mount
···
  *
  */
 
-int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
+int jbd2_journal_set_features(journal_t *journal, unsigned long compat,
 			  unsigned long ro, unsigned long incompat)
 {
 #define INCOMPAT_FEATURE_ON(f) \

fs/jbd2/recovery.c

···
 			 * number. */
 			if (pass == PASS_SCAN &&
 			    jbd2_has_feature_checksum(journal)) {
-				int chksum_err, chksum_seen;
 				struct commit_header *cbh =
 					(struct commit_header *)bh->b_data;
 				unsigned found_chksum =
 					be32_to_cpu(cbh->h_chksum[0]);
-
-				chksum_err = chksum_seen = 0;
 
 				if (info->end_transaction) {
 					journal->j_failed_commit =
···
 					break;
 				}
 
-				if (crc32_sum == found_chksum &&
-				    cbh->h_chksum_type == JBD2_CRC32_CHKSUM &&
-				    cbh->h_chksum_size ==
-						JBD2_CRC32_CHKSUM_SIZE)
-				       chksum_seen = 1;
-				else if (!(cbh->h_chksum_type == 0 &&
-					     cbh->h_chksum_size == 0 &&
-					     found_chksum == 0 &&
-					     !chksum_seen))
-				/*
-				 * If fs is mounted using an old kernel and then
-				 * kernel with journal_chksum is used then we
-				 * get a situation where the journal flag has
-				 * checksum flag set but checksums are not
-				 * present i.e chksum = 0, in the individual
-				 * commit blocks.
-				 * Hence to avoid checksum failures, in this
-				 * situation, this extra check is added.
-				 */
-						chksum_err = 1;
+				/* Neither checksum match nor unused? */
+				if (!((crc32_sum == found_chksum &&
+				       cbh->h_chksum_type ==
+						JBD2_CRC32_CHKSUM &&
+				       cbh->h_chksum_size ==
+						JBD2_CRC32_CHKSUM_SIZE) ||
+				      (cbh->h_chksum_type == 0 &&
+				       cbh->h_chksum_size == 0 &&
+				       found_chksum == 0)))
+					goto chksum_error;
 
-				if (chksum_err) {
-					info->end_transaction = next_commit_ID;
-
-					if (!jbd2_has_feature_async_commit(journal)) {
-						journal->j_failed_commit =
-							next_commit_ID;
-						brelse(bh);
-						break;
-					}
-				}
 				crc32_sum = ~0;
 			}
 			if (pass == PASS_SCAN &&
 			    !jbd2_commit_block_csum_verify(journal,
 							   bh->b_data)) {
+			chksum_error:
 				info->end_transaction = next_commit_ID;
 
 				if (!jbd2_has_feature_async_commit(journal)) {

fs/jbd2/transaction.c

···
  */
 static void __jbd2_journal_unfile_buffer(struct journal_head *jh)
 {
+	J_ASSERT_JH(jh, jh->b_transaction != NULL);
+	J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
+
 	__jbd2_journal_temp_unlink_buffer(jh);
 	jh->b_transaction = NULL;
 }
···
  * int jbd2_journal_try_to_free_buffers() - try to free page buffers.
  * @journal: journal for operation
  * @page: to try and free
- * @gfp_mask: we use the mask to detect how hard should we try to release
- * buffers. If __GFP_DIRECT_RECLAIM and __GFP_FS is set, we wait for commit
- * code to release the buffers.
- *
  *
  * For all the buffers on this page,
  * if they are fully written out ordered data, move them onto BUF_CLEAN
···
  *
  * Return 0 on failure, 1 on success
  */
-int jbd2_journal_try_to_free_buffers(journal_t *journal,
-				struct page *page, gfp_t gfp_mask)
+int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page)
 {
 	struct buffer_head *head;
 	struct buffer_head *bh;
+	bool has_write_io_error = false;
 	int ret = 0;
 
 	J_ASSERT(PageLocked(page));
···
 		jbd2_journal_put_journal_head(jh);
 		if (buffer_jbd(bh))
 			goto busy;
+
+		/*
+		 * If we free a metadata buffer which has been failed to
+		 * write out, the jbd2 checkpoint procedure will not detect
+		 * this failure and may lead to filesystem inconsistency
+		 * after cleanup journal tail.
+		 */
+		if (buffer_write_io_error(bh)) {
+			pr_err("JBD2: Error while async write back metadata bh %llu.",
+			       (unsigned long long)bh->b_blocknr);
+			has_write_io_error = true;
+		}
 	} while ((bh = bh->b_this_page) != head);
 
 	ret = try_to_free_buffers(page);
 
 busy:
+	if (has_write_io_error)
+		jbd2_journal_abort(journal, -EIO);
+
 	return ret;
 }
 
···
 
 	was_dirty = test_clear_buffer_jbddirty(bh);
 	__jbd2_journal_temp_unlink_buffer(jh);
+
+	/*
+	 * b_transaction must be set, otherwise the new b_transaction won't
+	 * be holding jh reference
+	 */
+	J_ASSERT_JH(jh, jh->b_transaction != NULL);
+
 	/*
 	 * We set b_transaction here because b_next_transaction will inherit
 	 * our jh reference and thus __jbd2_journal_file_buffer() must not

include/linux/jbd2.h

···
 extern int	 jbd2_journal_forget (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_invalidatepage(journal_t *,
 				struct page *, unsigned int, unsigned int);
-extern int	 jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t);
+extern int	 jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page);
 extern int	 jbd2_journal_stop(handle_t *);
 extern int	 jbd2_journal_flush (journal_t *);
 extern void	 jbd2_journal_lock_updates (journal_t *);

include/trace/events/ext4.h

···
 );
 
 TRACE_EVENT(ext4_discard_preallocations,
-	TP_PROTO(struct inode *inode),
+	TP_PROTO(struct inode *inode, unsigned int len, unsigned int needed),
 
-	TP_ARGS(inode),
+	TP_ARGS(inode, len, needed),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
+		__field(	dev_t,		dev		)
+		__field(	ino_t,		ino		)
+		__field(	unsigned int,	len		)
+		__field(	unsigned int,	needed		)
 
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
+		__entry->len	= len;
+		__entry->needed	= needed;
 	),
 
-	TP_printk("dev %d,%d ino %lu",
+	TP_printk("dev %d,%d ino %lu len: %u needed %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  (unsigned long) __entry->ino)
+		  (unsigned long) __entry->ino, __entry->len,
+		  __entry->needed)
 );
 
 TRACE_EVENT(ext4_mb_discard_preallocations,
···
 	TP_ARGS(sb, group)
 );
 
-DEFINE_EVENT(ext4__bitmap_load, ext4_read_block_bitmap_load,
+DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap,
 
 	TP_PROTO(struct super_block *sb, unsigned long group),
 
 	TP_ARGS(sb, group)
 );
 
-DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap,
+TRACE_EVENT(ext4_read_block_bitmap_load,
+	TP_PROTO(struct super_block *sb, unsigned long group, bool prefetch),
 
-	TP_PROTO(struct super_block *sb, unsigned long group),
+	TP_ARGS(sb, group, prefetch),
 
-	TP_ARGS(sb, group)
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	__u32,	group			)
+		__field(	bool,	prefetch		)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->group	= group;
+		__entry->prefetch = prefetch;
+	),
+
+	TP_printk("dev %d,%d group %u prefetch %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->group, __entry->prefetch)
 );
 
 TRACE_EVENT(ext4_direct_IO_enter,
···
 	TP_printk("dev %d,%d function %s line %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->function, __entry->line)
+);
+
+TRACE_EVENT(ext4_prefetch_bitmaps,
+	    TP_PROTO(struct super_block *sb, ext4_group_t group,
+		     ext4_group_t next, unsigned int prefetch_ios),
+
+	TP_ARGS(sb, group, next, prefetch_ios),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	__u32,	group			)
+		__field(	__u32,	next			)
+		__field(	__u32,	ios			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->group	= group;
+		__entry->next	= next;
+		__entry->ios	= prefetch_ios;
+	),
+
+	TP_printk("dev %d,%d group %u next %u ios %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->group, __entry->next, __entry->ios)
+);
+
+TRACE_EVENT(ext4_lazy_itable_init,
+	    TP_PROTO(struct super_block *sb, ext4_group_t group),
+
+	TP_ARGS(sb, group),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	__u32,	group			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->group	= group;
+	),
+
+	TP_printk("dev %d,%d group %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group)
 );
 
 #endif /* _TRACE_EXT4_H */