8 files changed, 118 insertions, 69 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 354619a..1a34c1c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -175,6 +175,7 @@ struct mpage_da_data {
  */
 #define	EXT4_IO_END_UNWRITTEN	0x0001
 #define EXT4_IO_END_ERROR	0x0002
+#define EXT4_IO_END_QUEUED	0x0004
 
 struct ext4_io_page {
 	struct page	*p_page;
@@ -357,8 +358,7 @@ struct flex_groups {
 
 /* Flags that should be inherited by new inodes from their parent. */
 #define EXT4_FL_INHERITED (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_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
 			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
 			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL)
 
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 5802fa1..95af6f8 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -261,43 +261,45 @@ static inline void ext4_update_inode_fsync_trans(handle_t *handle,
 /* super.c */
 int ext4_force_commit(struct super_block *sb);
 
-static inline int ext4_should_journal_data(struct inode *inode)
+/*
+ * Ext4 inode journal modes
+ */
+#define EXT4_INODE_JOURNAL_DATA_MODE	0x01 /* journal data mode */
+#define EXT4_INODE_ORDERED_DATA_MODE	0x02 /* ordered data mode */
+#define EXT4_INODE_WRITEBACK_DATA_MODE	0x04 /* writeback data mode */
+
+static inline int ext4_inode_journal_mode(struct inode *inode)
 {
 	if (EXT4_JOURNAL(inode) == NULL)
-		return 0;
-	if (!S_ISREG(inode->i_mode))
-		return 1;
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
-		return 1;
-	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
-		return 1;
-	return 0;
+		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
+	/* We do not support data journalling with delayed allocation */
+	if (!S_ISREG(inode->i_mode) ||
+	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
+	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
+	    !test_opt(inode->i_sb, DELALLOC))
+		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+		return EXT4_INODE_ORDERED_DATA_MODE;	/* ordered */
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
+	else
+		BUG();
+}
+
+static inline int ext4_should_journal_data(struct inode *inode)
+{
+	return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE;
 }
 
 static inline int ext4_should_order_data(struct inode *inode)
 {
-	if (EXT4_JOURNAL(inode) == NULL)
-		return 0;
-	if (!S_ISREG(inode->i_mode))
-		return 0;
-	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
-		return 0;
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
-		return 1;
-	return 0;
+	return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE;
 }
 
 static inline int ext4_should_writeback_data(struct inode *inode)
 {
-	if (EXT4_JOURNAL(inode) == NULL)
-		return 1;
-	if (!S_ISREG(inode->i_mode))
-		return 0;
-	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
-		return 0;
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
-		return 1;
-	return 0;
+	return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE;
 }
 
 /*
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index f3aacb3..7fc10ed 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -341,6 +341,8 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
 	ext4_fsblk_t block = ext4_ext_pblock(ext);
 	int len = ext4_ext_get_actual_len(ext);
 
+	if (len == 0)
+		return 0;
 	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
 }
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c94774c..c1e6a72 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -190,9 +190,6 @@ void ext4_evict_inode(struct inode *inode)
 
 	trace_ext4_evict_inode(inode);
 
-	mutex_lock(&inode->i_mutex);
-	ext4_flush_completed_IO(inode);
-	mutex_unlock(&inode->i_mutex);
 	ext4_ioend_wait(inode);
 
 	if (inode->i_nlink) {
@@ -2129,8 +2126,11 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
 					clear_buffer_unwritten(bh);
 				}
 
-				/* skip page if block allocation undone */
-				if (buffer_delay(bh) || buffer_unwritten(bh))
+				/*
+				 * skip page if block allocation undone and
+				 * block is dirty
+				 */
+				if (ext4_bh_delay_or_unwritten(NULL, bh))
 					skip_page = 1;
 				bh = bh->b_this_page;
 				block_start += bh->b_size;
@@ -3212,13 +3212,14 @@ static int ext4_da_write_end(struct file *file,
 	int write_mode = (int)(unsigned long)fsdata;
 
 	if (write_mode == FALL_BACK_TO_NONDELALLOC) {
-		if (ext4_should_order_data(inode)) {
+		switch (ext4_inode_journal_mode(inode)) {
+		case EXT4_INODE_ORDERED_DATA_MODE:
 			return ext4_ordered_write_end(file, mapping, pos,
 					len, copied, page, fsdata);
-		} else if (ext4_should_writeback_data(inode)) {
+		case EXT4_INODE_WRITEBACK_DATA_MODE:
 			return ext4_writeback_write_end(file, mapping, pos,
 					len, copied, page, fsdata);
-		} else {
+		default:
 			BUG();
 		}
 	}
@@ -3234,7 +3235,7 @@ static int ext4_da_write_end(struct file *file,
 	 */
 
 	new_i_size = pos + copied;
-	if (new_i_size > EXT4_I(inode)->i_disksize) {
+	if (copied && new_i_size > EXT4_I(inode)->i_disksize) {
 		if (ext4_da_should_update_i_disksize(page, end)) {
 			down_write(&EXT4_I(inode)->i_data_sem);
 			if (new_i_size > EXT4_I(inode)->i_disksize) {
@@ -3510,12 +3511,17 @@ static ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 	}
 
 retry:
-	if (rw == READ && ext4_should_dioread_nolock(inode))
+	if (rw == READ && ext4_should_dioread_nolock(inode)) {
+		if (unlikely(!list_empty(&ei->i_completed_io_list))) {
+			mutex_lock(&inode->i_mutex);
+			ext4_flush_completed_IO(inode);
+			mutex_unlock(&inode->i_mutex);
+		}
 		ret = __blockdev_direct_IO(rw, iocb, inode,
 				 inode->i_sb->s_bdev, iov,
 				 offset, nr_segs,
 				 ext4_get_block, NULL, NULL, 0);
-	else {
+	} else {
 		ret = blockdev_direct_IO(rw, iocb, inode,
 				 inode->i_sb->s_bdev, iov,
 				 offset, nr_segs,
@@ -3913,18 +3919,25 @@ static const struct address_space_operations ext4_da_aops = {
 
 void ext4_set_aops(struct inode *inode)
 {
-	if (ext4_should_order_data(inode) &&
-		test_opt(inode->i_sb, DELALLOC))
-		inode->i_mapping->a_ops = &ext4_da_aops;
-	else if (ext4_should_order_data(inode))
-		inode->i_mapping->a_ops = &ext4_ordered_aops;
-	else if (ext4_should_writeback_data(inode) &&
-		 test_opt(inode->i_sb, DELALLOC))
-		inode->i_mapping->a_ops = &ext4_da_aops;
-	else if (ext4_should_writeback_data(inode))
-		inode->i_mapping->a_ops = &ext4_writeback_aops;
-	else
+	switch (ext4_inode_journal_mode(inode)) {
+	case EXT4_INODE_ORDERED_DATA_MODE:
+		if (test_opt(inode->i_sb, DELALLOC))
+			inode->i_mapping->a_ops = &ext4_da_aops;
+		else
+			inode->i_mapping->a_ops = &ext4_ordered_aops;
+		break;
+	case EXT4_INODE_WRITEBACK_DATA_MODE:
+		if (test_opt(inode->i_sb, DELALLOC))
+			inode->i_mapping->a_ops = &ext4_da_aops;
+		else
+			inode->i_mapping->a_ops = &ext4_writeback_aops;
+		break;
+	case EXT4_INODE_JOURNAL_DATA_MODE:
 		inode->i_mapping->a_ops = &ext4_journalled_aops;
+		break;
+	default:
+		BUG();
+	}
 }
 
 /*
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 458a394..3d36d5a 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1589,7 +1589,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			dxtrace(dx_show_index("node", frames[1].entries));
 			dxtrace(dx_show_index("node",
 			       ((struct dx_node *) bh2->b_data)->entries));
-			err = ext4_handle_dirty_metadata(handle, inode, bh2);
+			err = ext4_handle_dirty_metadata(handle, dir, bh2);
 			if (err)
 				goto journal_error;
 			brelse (bh2);
@@ -1615,7 +1615,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			if (err)
 				goto journal_error;
 		}
-		err = ext4_handle_dirty_metadata(handle, inode, frames[0].bh);
+		err = ext4_handle_dirty_metadata(handle, dir, frames[0].bh);
 		if (err) {
 			ext4_std_error(inode->i_sb, err);
 			goto cleanup;
@@ -1866,7 +1866,7 @@ retry:
 	ext4_set_de_type(dir->i_sb, de, S_IFDIR);
 	inode->i_nlink = 2;
 	BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
-	err = ext4_handle_dirty_metadata(handle, dir, dir_block);
+	err = ext4_handle_dirty_metadata(handle, inode, dir_block);
 	if (err)
 		goto out_clear_inode;
 	err = ext4_mark_inode_dirty(handle, inode);
@@ -2540,7 +2540,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) =
 						cpu_to_le32(new_dir->i_ino);
 		BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
-		retval = ext4_handle_dirty_metadata(handle, old_dir, dir_bh);
+		retval = ext4_handle_dirty_metadata(handle, old_inode, dir_bh);
 		if (retval) {
 			ext4_std_error(old_dir->i_sb, retval);
 			goto end_rename;
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 97e5e98..d99d74a 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -142,7 +142,23 @@ static void ext4_end_io_work(struct work_struct *work)
 	unsigned long		flags;
 	int			ret;
 
-	mutex_lock(&inode->i_mutex);
+	if (!mutex_trylock(&inode->i_mutex)) {
+		/*
+		 * Requeue the work instead of waiting so that the work
+		 * items queued after this can be processed.
+		 */
+		queue_work(EXT4_SB(inode->i_sb)->dio_unwritten_wq, &io->work);
+		/*
+		 * To prevent the ext4-dio-unwritten thread from keeping
+		 * requeueing end_io requests and occupying cpu for too long,
+		 * yield the cpu if it sees an end_io request that has already
+		 * been requeued.
+		 */
+		if (io->flag & EXT4_IO_END_QUEUED)
+			yield();
+		io->flag |= EXT4_IO_END_QUEUED;
+		return;
+	}
 	ret = ext4_end_io_nolock(io);
 	if (ret < 0) {
 		mutex_unlock(&inode->i_mutex);
@@ -389,6 +405,18 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 
 		block_end = block_start + blocksize;
 		if (block_start >= len) {
+			/*
+			 * Comments copied from block_write_full_page_endio:
+			 *
+			 * The page straddles i_size.  It must be zeroed out on
+			 * each and every writepage invocation because it may
+			 * be mmapped.  "A file is mapped in multiples of the
+			 * page size.  For a file that is not a multiple of
+			 * the  page size, the remaining memory is zeroed when
+			 * mapped, and writes to that region are not written
+			 * out to the file."
+			 */
+			zero_user_segment(page, block_start, block_end);
 			clear_buffer_dirty(bh);
 			set_buffer_uptodate(bh);
 			continue;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 111ed9d..df121b2 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1113,9 +1113,9 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",block_validity");
 
 	if (!test_opt(sb, INIT_INODE_TABLE))
-		seq_puts(seq, ",noinit_inode_table");
+		seq_puts(seq, ",noinit_itable");
 	else if (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)
-		seq_printf(seq, ",init_inode_table=%u",
+		seq_printf(seq, ",init_itable=%u",
 			   (unsigned) sbi->s_li_wait_mult);
 
 	ext4_show_quota_options(seq, sb);
@@ -1291,8 +1291,7 @@ enum {
 	Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
 	Opt_inode_readahead_blks, Opt_journal_ioprio,
 	Opt_dioread_nolock, Opt_dioread_lock,
-	Opt_discard, Opt_nodiscard,
-	Opt_init_inode_table, Opt_noinit_inode_table,
+	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
 };
 
 static const match_table_t tokens = {
@@ -1365,9 +1364,9 @@ static const match_table_t tokens = {
 	{Opt_dioread_lock, "dioread_lock"},
 	{Opt_discard, "discard"},
 	{Opt_nodiscard, "nodiscard"},
-	{Opt_init_inode_table, "init_itable=%u"},
-	{Opt_init_inode_table, "init_itable"},
-	{Opt_noinit_inode_table, "noinit_itable"},
+	{Opt_init_itable, "init_itable=%u"},
+	{Opt_init_itable, "init_itable"},
+	{Opt_noinit_itable, "noinit_itable"},
 	{Opt_err, NULL},
 };
 
@@ -1844,7 +1843,7 @@ set_qf_format:
 		case Opt_dioread_lock:
 			clear_opt(sb, DIOREAD_NOLOCK);
 			break;
-		case Opt_init_inode_table:
+		case Opt_init_itable:
 			set_opt(sb, INIT_INODE_TABLE);
 			if (args[0].from) {
 				if (match_int(&args[0], &option))
@@ -1855,7 +1854,7 @@ set_qf_format:
 				return 0;
 			sbi->s_li_wait_mult = option;
 			break;
-		case Opt_noinit_inode_table:
+		case Opt_noinit_itable:
 			clear_opt(sb, INIT_INODE_TABLE);
 			break;
 		default:
@@ -1958,17 +1957,16 @@ static int ext4_fill_flex_info(struct super_block *sb)
 	struct ext4_group_desc *gdp = NULL;
 	ext4_group_t flex_group_count;
 	ext4_group_t flex_group;
-	int groups_per_flex = 0;
+	unsigned int groups_per_flex = 0;
 	size_t size;
 	int i;
 
 	sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
-	groups_per_flex = 1 << sbi->s_log_groups_per_flex;
-
-	if (groups_per_flex < 2) {
+	if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) {
 		sbi->s_log_groups_per_flex = 0;
 		return 1;
 	}
+	groups_per_flex = 1 << sbi->s_log_groups_per_flex;
 
 	/* We allocate both existing and potentially added groups */
 	flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index c757adc..19fe4e3 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -820,8 +820,14 @@ inserted:
 			if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 				goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
 
+			/*
+			 * take i_data_sem because we will test
+			 * i_delalloc_reserved_flag in ext4_mb_new_blocks
+			 */
+			down_read((&EXT4_I(inode)->i_data_sem));
 			block = ext4_new_meta_blocks(handle, inode, goal, 0,
 						     NULL, &error);
+			up_read((&EXT4_I(inode)->i_data_sem));
 			if (error)
 				goto cleanup;