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

Pull ext4 updates from Ted Ts'o:
 "The usual collection of bug fixes and optimizations.  Perhaps of
  greatest note is a speed up for parallel, non-allocating DIO writes,
  since we no longer take the i_mutex lock in that case.

  For bug fixes, we fix an incorrect overhead calculation which caused
  slightly incorrect results for df(1) and statfs(2).  We also fixed
  bugs in the metadata checksum feature."

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (23 commits)
  ext4: undo ext4_calc_metadata_amount if we fail to claim space
  ext4: don't let i_reserved_meta_blocks go negative
  ext4: fix hole punch failure when depth is greater than 0
  ext4: remove unnecessary argument from __ext4_handle_dirty_metadata()
  ext4: weed out ext4_write_super
  ext4: remove unnecessary superblock dirtying
  ext4: convert last user of ext4_mark_super_dirty() to ext4_handle_dirty_super()
  ext4: remove useless marking of superblock dirty
  ext4: fix ext4 mismerge back in January
  ext4: remove dynamic array size in ext4_chksum()
  ext4: remove unused variable in ext4_update_super()
  ext4: make quota as first class supported feature
  ext4: don't take the i_mutex lock when doing DIO overwrites
  ext4: add a new nolock flag in ext4_map_blocks
  ext4: split ext4_file_write into buffered IO and direct IO
  ext4: remove an unused statement in ext4_mb_get_buddy_page_lock()
  ext4: fix out-of-date comments in extents.c
  ext4: use s_csum_seed instead of i_csum_seed for xattr block
  ext4: use proper csum calculation in ext4_rename
  ext4: fix overhead calculation used by ext4_statfs()
  ...

fs/ext4/balloc.c

@@ -609,7 +609,8 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb)
 		if (bitmap_bh == NULL)
 			continue;
 
-		x = ext4_count_free(bitmap_bh, sb->s_blocksize);
+		x = ext4_count_free(bitmap_bh->b_data,
+				    EXT4_BLOCKS_PER_GROUP(sb) / 8);
 		printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n",
 			i, ext4_free_group_clusters(sb, gdp), x);
 		bitmap_count += x;

fs/ext4/bitmap.c

@@ -11,24 +11,18 @@
 #include <linux/jbd2.h>
 #include "ext4.h"
 
-#ifdef EXT4FS_DEBUG
-
 static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
 
-unsigned int ext4_count_free(struct buffer_head *map, unsigned int numchars)
+unsigned int ext4_count_free(char *bitmap, unsigned int numchars)
 {
 	unsigned int i, sum = 0;
 
-	if (!map)
-		return 0;
 	for (i = 0; i < numchars; i++)
-		sum += nibblemap[map->b_data[i] & 0xf] +
-			nibblemap[(map->b_data[i] >> 4) & 0xf];
+		sum += nibblemap[bitmap[i] & 0xf] +
+			nibblemap[(bitmap[i] >> 4) & 0xf];
 	return sum;
 }
 
-#endif  /*  EXT4FS_DEBUG  */
-
 int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group,
 				  struct ext4_group_desc *gdp,
 				  struct buffer_head *bh, int sz)

fs/ext4/ext4.h

@@ -571,6 +571,8 @@ enum {
 #define EXT4_GET_BLOCKS_NO_NORMALIZE		0x0040
 	/* Request will not result in inode size update (user for fallocate) */
 #define EXT4_GET_BLOCKS_KEEP_SIZE		0x0080
+	/* Do not take i_data_sem locking in ext4_map_blocks */
+#define EXT4_GET_BLOCKS_NO_LOCK			0x0100
 
 /*
  * Flags used by ext4_free_blocks
@@ -1161,8 +1163,7 @@ struct ext4_sb_info {
 	unsigned long s_desc_per_block;	/* Number of group descriptors per block */
 	ext4_group_t s_groups_count;	/* Number of groups in the fs */
 	ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
-	unsigned long s_overhead_last;  /* Last calculated overhead */
-	unsigned long s_blocks_last;    /* Last seen block count */
+	unsigned long s_overhead;  /* # of fs overhead clusters */
 	unsigned int s_cluster_ratio;	/* Number of blocks per cluster */
 	unsigned int s_cluster_bits;	/* log2 of s_cluster_ratio */
 	loff_t s_bitmap_maxbytes;	/* max bytes for bitmap files */
@@ -1314,6 +1315,8 @@ static inline struct timespec ext4_current_time(struct inode *inode)
 static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 {
 	return ino == EXT4_ROOT_INO ||
+		ino == EXT4_USR_QUOTA_INO ||
+		ino == EXT4_GRP_QUOTA_INO ||
 		ino == EXT4_JOURNAL_INO ||
 		ino == EXT4_RESIZE_INO ||
 		(ino >= EXT4_FIRST_INO(sb) &&
@@ -1496,7 +1499,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
 					 EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\
 					 EXT4_FEATURE_RO_COMPAT_BIGALLOC |\
-					 EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)
+					 EXT4_FEATURE_RO_COMPAT_METADATA_CSUM|\
+					 EXT4_FEATURE_RO_COMPAT_QUOTA)
 
 /*
  * Default values for user and/or group using reserved blocks
@@ -1663,10 +1667,12 @@ static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc,
 {
 	struct {
 		struct shash_desc shash;
-		char ctx[crypto_shash_descsize(sbi->s_chksum_driver)];
+		char ctx[4];
 	} desc;
 	int err;
 
+	BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx));
+
 	desc.shash.tfm = sbi->s_chksum_driver;
 	desc.shash.flags = 0;
 	*(u32 *)desc.ctx = crc;
@@ -1852,7 +1858,7 @@ struct mmpd_data {
 # define NORET_AND	noreturn,
 
 /* bitmap.c */
-extern unsigned int ext4_count_free(struct buffer_head *, unsigned);
+extern unsigned int ext4_count_free(char *bitmap, unsigned numchars);
 void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group,
 				struct ext4_group_desc *gdp,
 				struct buffer_head *bh, int sz);
@@ -2037,6 +2043,7 @@ extern int ext4_group_extend(struct super_block *sb,
 extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count);
 
 /* super.c */
+extern int ext4_calculate_overhead(struct super_block *sb);
 extern int ext4_superblock_csum_verify(struct super_block *sb,
 				       struct ext4_super_block *es);
 extern void ext4_superblock_csum_set(struct super_block *sb,
@@ -2321,15 +2328,6 @@ static inline void ext4_unlock_group(struct super_block *sb,
 	spin_unlock(ext4_group_lock_ptr(sb, group));
 }
 
-static inline void ext4_mark_super_dirty(struct super_block *sb)
-{
-	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
-
-	ext4_superblock_csum_set(sb, es);
-	if (EXT4_SB(sb)->s_journal == NULL)
-		sb->s_dirt =1;
-}
-
 /*
  * Block validity checking
  */

fs/ext4/ext4_jbd2.c

@@ -138,8 +138,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 }
 
 int __ext4_handle_dirty_super(const char *where, unsigned int line,
-			      handle_t *handle, struct super_block *sb,
-			      int now)
+			      handle_t *handle, struct super_block *sb)
 {
 	struct buffer_head *bh = EXT4_SB(sb)->s_sbh;
 	int err = 0;
@@ -151,11 +150,10 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line,
 		if (err)
 			ext4_journal_abort_handle(where, line, __func__,
 						  bh, handle, err);
-	} else if (now) {
+	} else {
 		ext4_superblock_csum_set(sb,
 				(struct ext4_super_block *)bh->b_data);
 		mark_buffer_dirty(bh);
-	} else
-		sb->s_dirt = 1;
+	}
 	return err;
 }

fs/ext4/ext4_jbd2.h

@@ -87,14 +87,20 @@
 #ifdef CONFIG_QUOTA
 /* Amount of blocks needed for quota update - we know that the structure was
  * allocated so we need to update only data block */
-#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 1 : 0)
+#define EXT4_QUOTA_TRANS_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
+		EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\
+		1 : 0)
 /* Amount of blocks needed for quota insert/delete - we do some block writes
  * but inode, sb and group updates are done only once */
-#define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\
-		(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0)
-
-#define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\
-		(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0)
+#define EXT4_QUOTA_INIT_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
+		EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\
+		(DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\
+		 +3+DQUOT_INIT_REWRITE) : 0)
+
+#define EXT4_QUOTA_DEL_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
+		EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\
+		(DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\
+		 +3+DQUOT_DEL_REWRITE) : 0)
 #else
 #define EXT4_QUOTA_TRANS_BLOCKS(sb) 0
 #define EXT4_QUOTA_INIT_BLOCKS(sb) 0
@@ -213,8 +219,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 				 struct buffer_head *bh);
 
 int __ext4_handle_dirty_super(const char *where, unsigned int line,
-			      handle_t *handle, struct super_block *sb,
-			      int now);
+			      handle_t *handle, struct super_block *sb);
 
 #define ext4_journal_get_write_access(handle, bh) \
 	__ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh))
@@ -226,10 +231,8 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line,
 #define ext4_handle_dirty_metadata(handle, inode, bh) \
 	__ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \
 				     (bh))
-#define ext4_handle_dirty_super_now(handle, sb) \
-	__ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb), 1)
 #define ext4_handle_dirty_super(handle, sb) \
-	__ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb), 0)
+	__ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb))
 
 handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks);
 int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle);

fs/ext4/extents.c

@@ -1891,11 +1891,10 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 	nearex->ee_len = newext->ee_len;
 
 merge:
-	/* try to merge extents to the right */
+	/* try to merge extents */
 	if (!(flag & EXT4_GET_BLOCKS_PRE_IO))
 		ext4_ext_try_to_merge(inode, path, nearex);
 
-	/* try to merge extents to the left */
 
 	/* time to correct all indexes above */
 	err = ext4_ext_correct_indexes(handle, inode, path);
@@ -2570,10 +2569,10 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
 {
 	struct super_block *sb = inode->i_sb;
 	int depth = ext_depth(inode);
-	struct ext4_ext_path *path;
+	struct ext4_ext_path *path = NULL;
 	ext4_fsblk_t partial_cluster = 0;
 	handle_t *handle;
-	int i, err;
+	int i = 0, err;
 
 	ext_debug("truncate since %u to %u\n", start, end);
 
@@ -2606,8 +2605,12 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
 		}
 		depth = ext_depth(inode);
 		ex = path[depth].p_ext;
-		if (!ex)
+		if (!ex) {
+			ext4_ext_drop_refs(path);
+			kfree(path);
+			path = NULL;
 			goto cont;
+		}
 
 		ee_block = le32_to_cpu(ex->ee_block);
 
@@ -2637,8 +2640,6 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
 			if (err < 0)
 				goto out;
 		}
-		ext4_ext_drop_refs(path);
-		kfree(path);
 	}
 cont:
 
@@ -2647,19 +2648,27 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
 	 * after i_size and walking into the tree depth-wise.
 	 */
 	depth = ext_depth(inode);
-	path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_NOFS);
-	if (path == NULL) {
-		ext4_journal_stop(handle);
-		return -ENOMEM;
-	}
-	path[0].p_depth = depth;
-	path[0].p_hdr = ext_inode_hdr(inode);
+	if (path) {
+		int k = i = depth;
+		while (--k > 0)
+			path[k].p_block =
+				le16_to_cpu(path[k].p_hdr->eh_entries)+1;
+	} else {
+		path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1),
+			       GFP_NOFS);
+		if (path == NULL) {
+			ext4_journal_stop(handle);
+			return -ENOMEM;
+		}
+		path[0].p_depth = depth;
+		path[0].p_hdr = ext_inode_hdr(inode);
 
-	if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
-		err = -EIO;
-		goto out;
+		if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
+			err = -EIO;
+			goto out;
+		}
 	}
-	i = err = 0;
+	err = 0;
 
 	while (i >= 0 && err == 0) {
 		if (i == depth) {
@@ -2773,8 +2782,10 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
 out:
 	ext4_ext_drop_refs(path);
 	kfree(path);
-	if (err == -EAGAIN)
+	if (err == -EAGAIN) {
+		path = NULL;
 		goto again;
+	}
 	ext4_journal_stop(handle);
 
 	return err;
@@ -4420,6 +4431,8 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 		ext4_falloc_update_inode(inode, mode, new_size,
 					 (map.m_flags & EXT4_MAP_NEW));
 		ext4_mark_inode_dirty(handle, inode);
+		if ((file->f_flags & O_SYNC) && ret >= max_blocks)
+			ext4_handle_sync(handle);
 		ret2 = ext4_journal_stop(handle);
 		if (ret2)
 			break;

fs/ext4/file.c

@@ -89,12 +89,92 @@ ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
 	return 0;
 }
 
+static ssize_t
+ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
+		    unsigned long nr_segs, loff_t pos)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	struct blk_plug plug;
+	int unaligned_aio = 0;
+	ssize_t ret;
+	int overwrite = 0;
+	size_t length = iov_length(iov, nr_segs);
+
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
+	    !is_sync_kiocb(iocb))
+		unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
+
+	/* Unaligned direct AIO must be serialized; see comment above */
+	if (unaligned_aio) {
+		static unsigned long unaligned_warn_time;
+
+		/* Warn about this once per day */
+		if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
+			ext4_msg(inode->i_sb, KERN_WARNING,
+				 "Unaligned AIO/DIO on inode %ld by %s; "
+				 "performance will be poor.",
+				 inode->i_ino, current->comm);
+		mutex_lock(ext4_aio_mutex(inode));
+		ext4_aiodio_wait(inode);
+	}
+
+	BUG_ON(iocb->ki_pos != pos);
+
+	mutex_lock(&inode->i_mutex);
+	blk_start_plug(&plug);
+
+	iocb->private = &overwrite;
+
+	/* check whether we do a DIO overwrite or not */
+	if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
+	    !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
+		struct ext4_map_blocks map;
+		unsigned int blkbits = inode->i_blkbits;
+		int err, len;
+
+		map.m_lblk = pos >> blkbits;
+		map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
+			- map.m_lblk;
+		len = map.m_len;
+
+		err = ext4_map_blocks(NULL, inode, &map, 0);
+		/*
+		 * 'err==len' means that all of blocks has been preallocated no
+		 * matter they are initialized or not.  For excluding
+		 * uninitialized extents, we need to check m_flags.  There are
+		 * two conditions that indicate for initialized extents.
+		 * 1) If we hit extent cache, EXT4_MAP_MAPPED flag is returned;
+		 * 2) If we do a real lookup, non-flags are returned.
+		 * So we should check these two conditions.
+		 */
+		if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
+			overwrite = 1;
+	}
+
+	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+	mutex_unlock(&inode->i_mutex);
+
+	if (ret > 0 || ret == -EIOCBQUEUED) {
+		ssize_t err;
+
+		err = generic_write_sync(file, pos, ret);
+		if (err < 0 && ret > 0)
+			ret = err;
+	}
+	blk_finish_plug(&plug);
+
+	if (unaligned_aio)
+		mutex_unlock(ext4_aio_mutex(inode));
+
+	return ret;
+}
+
 static ssize_t
 ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
 		unsigned long nr_segs, loff_t pos)
 {
 	struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
-	int unaligned_aio = 0;
 	ssize_t ret;
 
 	/*
@@ -114,29 +194,12 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
 			nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
 					      sbi->s_bitmap_maxbytes - pos);
 		}
-	} else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) &&
-		   !is_sync_kiocb(iocb))) {
-		unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
 	}
 
-	/* Unaligned direct AIO must be serialized; see comment above */
-	if (unaligned_aio) {
-		static unsigned long unaligned_warn_time;
-
-		/* Warn about this once per day */
-		if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
-			ext4_msg(inode->i_sb, KERN_WARNING,
-				 "Unaligned AIO/DIO on inode %ld by %s; "
-				 "performance will be poor.",
-				 inode->i_ino, current->comm);
-		mutex_lock(ext4_aio_mutex(inode));
-		ext4_aiodio_wait(inode);
-	}
-
-	ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
-
-	if (unaligned_aio)
-		mutex_unlock(ext4_aio_mutex(inode));
+	if (unlikely(iocb->ki_filp->f_flags & O_DIRECT))
+		ret = ext4_file_dio_write(iocb, iov, nr_segs, pos);
+	else
+		ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
 
 	return ret;
 }
@@ -181,9 +244,21 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 		path.dentry = mnt->mnt_root;
 		cp = d_path(&path, buf, sizeof(buf));
 		if (!IS_ERR(cp)) {
+			handle_t *handle;
+			int err;
+
+			handle = ext4_journal_start_sb(sb, 1);
+			if (IS_ERR(handle))
+				return PTR_ERR(handle);
+			err = ext4_journal_get_write_access(handle, sbi->s_sbh);
+			if (err) {
+				ext4_journal_stop(handle);
+				return err;
+			}
 			strlcpy(sbi->s_es->s_last_mounted, cp,
 				sizeof(sbi->s_es->s_last_mounted));
-			ext4_mark_super_dirty(sb);
+			ext4_handle_dirty_super(handle, sb);
+			ext4_journal_stop(handle);
 		}
 	}
 	/*

fs/ext4/ialloc.c

@@ -315,7 +315,6 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 		err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
 		if (!fatal)
 			fatal = err;
-		ext4_mark_super_dirty(sb);
 	} else
 		ext4_error(sb, "bit already cleared for inode %lu", ino);
 
@@ -830,7 +829,6 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, umode_t mode,
 	percpu_counter_dec(&sbi->s_freeinodes_counter);
 	if (S_ISDIR(mode))
 		percpu_counter_inc(&sbi->s_dirs_counter);
-	ext4_mark_super_dirty(sb);
 
 	if (sbi->s_log_groups_per_flex) {
 		flex_group = ext4_flex_group(sbi, group);
@@ -1054,7 +1052,8 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
 		if (!bitmap_bh)
 			continue;
 
-		x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
+		x = ext4_count_free(bitmap_bh->b_data,
+				    EXT4_INODES_PER_GROUP(sb) / 8);
 		printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
 			(unsigned long) i, ext4_free_inodes_count(sb, gdp), x);
 		bitmap_count += x;

fs/ext4/inode.c

@@ -346,6 +346,15 @@ void ext4_da_update_reserve_space(struct inode *inode,
 		used = ei->i_reserved_data_blocks;
 	}
 
+	if (unlikely(ei->i_allocated_meta_blocks > ei->i_reserved_meta_blocks)) {
+		ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, allocated %d "
+			 "with only %d reserved metadata blocks\n", __func__,
+			 inode->i_ino, ei->i_allocated_meta_blocks,
+			 ei->i_reserved_meta_blocks);
+		WARN_ON(1);
+		ei->i_allocated_meta_blocks = ei->i_reserved_meta_blocks;
+	}
+
 	/* Update per-inode reservations */
 	ei->i_reserved_data_blocks -= used;
 	ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
@@ -544,7 +553,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 	 * Try to see if we can get the block without requesting a new
 	 * file system block.
 	 */
-	down_read((&EXT4_I(inode)->i_data_sem));
+	if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
+		down_read((&EXT4_I(inode)->i_data_sem));
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
 		retval = ext4_ext_map_blocks(handle, inode, map, flags &
 					     EXT4_GET_BLOCKS_KEEP_SIZE);
@@ -552,7 +562,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 		retval = ext4_ind_map_blocks(handle, inode, map, flags &
 					     EXT4_GET_BLOCKS_KEEP_SIZE);
 	}
-	up_read((&EXT4_I(inode)->i_data_sem));
+	if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
+		up_read((&EXT4_I(inode)->i_data_sem));
 
 	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
 		int ret = check_block_validity(inode, map);
@@ -1171,6 +1182,17 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	unsigned int md_needed;
 	int ret;
+	ext4_lblk_t save_last_lblock;
+	int save_len;
+
+	/*
+	 * We will charge metadata quota at writeout time; this saves
+	 * us from metadata over-estimation, though we may go over by
+	 * a small amount in the end.  Here we just reserve for data.
+	 */
+	ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1));
+	if (ret)
+		return ret;
 
 	/*
 	 * recalculate the amount of metadata blocks to reserve
@@ -1179,32 +1201,31 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
 	 */
 repeat:
 	spin_lock(&ei->i_block_reservation_lock);
+	/*
+	 * ext4_calc_metadata_amount() has side effects, which we have
+	 * to be prepared undo if we fail to claim space.
+	 */
+	save_len = ei->i_da_metadata_calc_len;
+	save_last_lblock = ei->i_da_metadata_calc_last_lblock;
 	md_needed = EXT4_NUM_B2C(sbi,
 				 ext4_calc_metadata_amount(inode, lblock));
 	trace_ext4_da_reserve_space(inode, md_needed);
-	spin_unlock(&ei->i_block_reservation_lock);
 
-	/*
-	 * We will charge metadata quota at writeout time; this saves
-	 * us from metadata over-estimation, though we may go over by
-	 * a small amount in the end.  Here we just reserve for data.
-	 */
-	ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1));
-	if (ret)
-		return ret;
 	/*
 	 * We do still charge estimated metadata to the sb though;
 	 * we cannot afford to run out of free blocks.
 	 */
 	if (ext4_claim_free_clusters(sbi, md_needed + 1, 0)) {
-		dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
+		ei->i_da_metadata_calc_len = save_len;
+		ei->i_da_metadata_calc_last_lblock = save_last_lblock;
+		spin_unlock(&ei->i_block_reservation_lock);
 		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
 			yield();
 			goto repeat;
 		}
+		dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
 		return -ENOSPC;
 	}
-	spin_lock(&ei->i_block_reservation_lock);
 	ei->i_reserved_data_blocks++;
 	ei->i_reserved_meta_blocks += md_needed;
 	spin_unlock(&ei->i_block_reservation_lock);
@@ -2818,6 +2839,32 @@ static int ext4_get_block_write(struct inode *inode, sector_t iblock,
 			       EXT4_GET_BLOCKS_IO_CREATE_EXT);
 }
 
+static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock,
+		   struct buffer_head *bh_result, int flags)
+{
+	handle_t *handle = ext4_journal_current_handle();
+	struct ext4_map_blocks map;
+	int ret = 0;
+
+	ext4_debug("ext4_get_block_write_nolock: inode %lu, flag %d\n",
+		   inode->i_ino, flags);
+
+	flags = EXT4_GET_BLOCKS_NO_LOCK;
+
+	map.m_lblk = iblock;
+	map.m_len = bh_result->b_size >> inode->i_blkbits;
+
+	ret = ext4_map_blocks(handle, inode, &map, flags);
+	if (ret > 0) {
+		map_bh(bh_result, inode->i_sb, map.m_pblk);
+		bh_result->b_state = (bh_result->b_state & ~EXT4_MAP_FLAGS) |
+					map.m_flags;
+		bh_result->b_size = inode->i_sb->s_blocksize * map.m_len;
+		ret = 0;
+	}
+	return ret;
+}
+
 static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 			    ssize_t size, void *private, int ret,
 			    bool is_async)
@@ -2966,6 +3013,18 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 
 	loff_t final_size = offset + count;
 	if (rw == WRITE && final_size <= inode->i_size) {
+		int overwrite = 0;
+
+		BUG_ON(iocb->private == NULL);
+
+		/* If we do a overwrite dio, i_mutex locking can be released */
+		overwrite = *((int *)iocb->private);
+
+		if (overwrite) {
+			down_read(&EXT4_I(inode)->i_data_sem);
+			mutex_unlock(&inode->i_mutex);
+		}
+
 		/*
  		 * We could direct write to holes and fallocate.
 		 *
@@ -2991,8 +3050,10 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 		if (!is_sync_kiocb(iocb)) {
 			ext4_io_end_t *io_end =
 				ext4_init_io_end(inode, GFP_NOFS);
-			if (!io_end)
-				return -ENOMEM;
+			if (!io_end) {
+				ret = -ENOMEM;
+				goto retake_lock;
+			}
 			io_end->flag |= EXT4_IO_END_DIRECT;
 			iocb->private = io_end;
 			/*
@@ -3005,13 +3066,22 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 			EXT4_I(inode)->cur_aio_dio = iocb->private;
 		}
 
-		ret = __blockdev_direct_IO(rw, iocb, inode,
-					 inode->i_sb->s_bdev, iov,
-					 offset, nr_segs,
-					 ext4_get_block_write,
-					 ext4_end_io_dio,
-					 NULL,
-					 DIO_LOCKING);
+		if (overwrite)
+			ret = __blockdev_direct_IO(rw, iocb, inode,
+						 inode->i_sb->s_bdev, iov,
+						 offset, nr_segs,
+						 ext4_get_block_write_nolock,
+						 ext4_end_io_dio,
+						 NULL,
+						 0);
+		else
+			ret = __blockdev_direct_IO(rw, iocb, inode,
+						 inode->i_sb->s_bdev, iov,
+						 offset, nr_segs,
+						 ext4_get_block_write,
+						 ext4_end_io_dio,
+						 NULL,
+						 DIO_LOCKING);
 		if (iocb->private)
 			EXT4_I(inode)->cur_aio_dio = NULL;
 		/*
@@ -3031,7 +3101,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 		if (ret != -EIOCBQUEUED && ret <= 0 && iocb->private) {
 			ext4_free_io_end(iocb->private);
 			iocb->private = NULL;
-		} else if (ret > 0 && ext4_test_inode_state(inode,
+		} else if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
 						EXT4_STATE_DIO_UNWRITTEN)) {
 			int err;
 			/*
@@ -3044,6 +3114,14 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 				ret = err;
 			ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
 		}
+
+	retake_lock:
+		/* take i_mutex locking again if we do a ovewrite dio */
+		if (overwrite) {
+			up_read(&EXT4_I(inode)->i_data_sem);
+			mutex_lock(&inode->i_mutex);
+		}
+
 		return ret;
 	}
 
@@ -4034,7 +4112,7 @@ static int ext4_do_update_inode(handle_t *handle,
 			EXT4_SET_RO_COMPAT_FEATURE(sb,
 					EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
 			ext4_handle_sync(handle);
-			err = ext4_handle_dirty_super_now(handle, sb);
+			err = ext4_handle_dirty_super(handle, sb);
 		}
 	}
 	raw_inode->i_generation = cpu_to_le32(inode->i_generation);

fs/ext4/mballoc.c

@@ -969,7 +969,6 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
 
 	block++;
 	pnum = block / blocks_per_page;
-	poff = block % blocks_per_page;
 	page = find_or_create_page(inode->i_mapping, pnum, GFP_NOFS);
 	if (!page)
 		return -EIO;
@@ -2077,8 +2076,9 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 	struct super_block *sb = seq->private;
 	ext4_group_t group = (ext4_group_t) ((unsigned long) v);
 	int i;
-	int err;
+	int err, buddy_loaded = 0;
 	struct ext4_buddy e4b;
+	struct ext4_group_info *grinfo;
 	struct sg {
 		struct ext4_group_info info;
 		ext4_grpblk_t counters[16];
@@ -2095,15 +2095,21 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 
 	i = (sb->s_blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) +
 		sizeof(struct ext4_group_info);
-	err = ext4_mb_load_buddy(sb, group, &e4b);
-	if (err) {
-		seq_printf(seq, "#%-5u: I/O error\n", group);
-		return 0;
+	grinfo = ext4_get_group_info(sb, group);
+	/* Load the group info in memory only if not already loaded. */
+	if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) {
+		err = ext4_mb_load_buddy(sb, group, &e4b);
+		if (err) {
+			seq_printf(seq, "#%-5u: I/O error\n", group);
+			return 0;
+		}
+		buddy_loaded = 1;
 	}
-	ext4_lock_group(sb, group);
+
 	memcpy(&sg, ext4_get_group_info(sb, group), i);
-	ext4_unlock_group(sb, group);
-	ext4_mb_unload_buddy(&e4b);
+
+	if (buddy_loaded)
+		ext4_mb_unload_buddy(&e4b);
 
 	seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free,
 			sg.info.bb_fragments, sg.info.bb_first_free);
@@ -2825,7 +2831,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh);
 
 out_err:
-	ext4_mark_super_dirty(sb);
 	brelse(bitmap_bh);
 	return err;
 }
@@ -4694,7 +4699,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 		put_bh(bitmap_bh);
 		goto do_more;
 	}
-	ext4_mark_super_dirty(sb);
 error_return:
 	brelse(bitmap_bh);
 	ext4_std_error(sb, err);

fs/ext4/namei.c

@@ -2397,7 +2397,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 	/* Insert this inode at the head of the on-disk orphan list... */
 	NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan);
 	EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
-	err = ext4_handle_dirty_super_now(handle, sb);
+	err = ext4_handle_dirty_super(handle, sb);
 	rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
 	if (!err)
 		err = rc;
@@ -2470,7 +2470,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
 		if (err)
 			goto out_brelse;
 		sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
-		err = ext4_handle_dirty_super_now(handle, inode->i_sb);
+		err = ext4_handle_dirty_super(handle, inode->i_sb);
 	} else {
 		struct ext4_iloc iloc2;
 		struct inode *i_prev =
@@ -2918,8 +2918,15 @@ 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_dirent_node(handle, old_inode,
-						       dir_bh);
+		if (is_dx(old_inode)) {
+			retval = ext4_handle_dirty_dx_node(handle,
+							   old_inode,
+							   dir_bh);
+		} else {
+			retval = ext4_handle_dirty_dirent_node(handle,
+							       old_inode,
+							       dir_bh);
+		}
 		if (retval) {
 			ext4_std_error(old_dir->i_sb, retval);
 			goto end_rename;

fs/ext4/resize.c

@@ -798,7 +798,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 	ext4_kvfree(o_group_desc);
 
 	le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
-	err = ext4_handle_dirty_super_now(handle, sb);
+	err = ext4_handle_dirty_super(handle, sb);
 	if (err)
 		ext4_std_error(sb, err);
 
@@ -1272,6 +1272,11 @@ static void ext4_update_super(struct super_block *sb,
 			   &sbi->s_flex_groups[flex_group].free_inodes);
 	}
 
+	/*
+	 * Update the fs overhead information
+	 */
+	ext4_calculate_overhead(sb);
+
 	if (test_opt(sb, DEBUG))
 		printk(KERN_DEBUG "EXT4-fs: added group %u:"
 		       "%llu blocks(%llu free %llu reserved)\n", flex_gd->count,

fs/ext4/xattr.c

@@ -127,19 +127,16 @@ static __le32 ext4_xattr_block_csum(struct inode *inode,
 				    struct ext4_xattr_header *hdr)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	struct ext4_inode_info *ei = EXT4_I(inode);
 	__u32 csum, old;
 
 	old = hdr->h_checksum;
 	hdr->h_checksum = 0;
-	if (le32_to_cpu(hdr->h_refcount) != 1) {
-		block_nr = cpu_to_le64(block_nr);
-		csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&block_nr,
-				   sizeof(block_nr));
-	} else
-		csum = ei->i_csum_seed;
+	block_nr = cpu_to_le64(block_nr);
+	csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&block_nr,
+			   sizeof(block_nr));
 	csum = ext4_chksum(sbi, csum, (__u8 *)hdr,
 			   EXT4_BLOCK_SIZE(inode->i_sb));
+
 	hdr->h_checksum = old;
 	return cpu_to_le32(csum);
 }