Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (60 commits)
  ext4: prevent memory leaks from ext4_mb_init_backend() on error path
  ext4: use EXT4_BAD_INO for buddy cache to avoid colliding with valid inode #
  ext4: use ext4_msg() instead of printk in mballoc
  ext4: use ext4_kvzalloc()/ext4_kvmalloc() for s_group_desc and s_group_info
  ext4: introduce ext4_kvmalloc(), ext4_kzalloc(), and ext4_kvfree()
  ext4: use the correct error exit path in ext4_init_inode_table()
  ext4: add missing kfree() on error return path in add_new_gdb()
  ext4: change umode_t in tracepoint headers to be an explicit __u16
  ext4: fix races in ext4_sync_parent()
  ext4: Fix overflow caused by missing cast in ext4_fallocate()
  ext4: add action of moving index in ext4_ext_rm_idx for Punch Hole
  ext4: simplify parameters of reserve_backup_gdb()
  ext4: simplify parameters of add_new_gdb()
  ext4: remove lock_buffer in bclean() and setup_new_group_blocks()
  ext4: simplify journal handling in setup_new_group_blocks()
  ext4: let setup_new_group_blocks() set multiple bits at a time
  ext4: fix a typo in ext4_group_extend()
  ext4: let ext4_group_add_blocks() handle 0 blocks quickly
  ext4: let ext4_group_add_blocks() return an error code
  ext4: rename ext4_add_groupblocks() to ext4_group_add_blocks()
  ...

Fix up conflict in fs/ext4/inode.c: commit aacfc19c ("fs: simplify
the blockdev_direct_IO prototype") had changed the ext4_ind_direct_IO()
function for the new simplified calling convention, while commit
dae1e52c ("ext4: move ext4_ind_* functions from inode.c to
indirect.c") moved the function to another file.

fs/ext4/Makefile

@@ -7,7 +7,7 @@ obj-$(CONFIG_EXT4_FS) += ext4.o
 ext4-y	:= balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \
 		ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
 		ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \
-		mmp.o
+		mmp.o indirect.o
 
 ext4-$(CONFIG_EXT4_FS_XATTR)		+= xattr.o xattr_user.o xattr_trusted.o
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o

fs/ext4/balloc.c

@@ -620,3 +620,51 @@ unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group)
 
 }
 
+/**
+ *	ext4_inode_to_goal_block - return a hint for block allocation
+ *	@inode: inode for block allocation
+ *
+ *	Return the ideal location to start allocating blocks for a
+ *	newly created inode.
+ */
+ext4_fsblk_t ext4_inode_to_goal_block(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	ext4_group_t block_group;
+	ext4_grpblk_t colour;
+	int flex_size = ext4_flex_bg_size(EXT4_SB(inode->i_sb));
+	ext4_fsblk_t bg_start;
+	ext4_fsblk_t last_block;
+
+	block_group = ei->i_block_group;
+	if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) {
+		/*
+		 * If there are at least EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME
+		 * block groups per flexgroup, reserve the first block
+		 * group for directories and special files.  Regular
+		 * files will start at the second block group.  This
+		 * tends to speed up directory access and improves
+		 * fsck times.
+		 */
+		block_group &= ~(flex_size-1);
+		if (S_ISREG(inode->i_mode))
+			block_group++;
+	}
+	bg_start = ext4_group_first_block_no(inode->i_sb, block_group);
+	last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
+
+	/*
+	 * If we are doing delayed allocation, we don't need take
+	 * colour into account.
+	 */
+	if (test_opt(inode->i_sb, DELALLOC))
+		return bg_start;
+
+	if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
+		colour = (current->pid % 16) *
+			(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
+	else
+		colour = (current->pid % 16) * ((last_block - bg_start) / 16);
+	return bg_start + colour;
+}
+

fs/ext4/block_validity.c

@@ -246,3 +246,24 @@ int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
 	return 1;
 }
 
+int ext4_check_blockref(const char *function, unsigned int line,
+			struct inode *inode, __le32 *p, unsigned int max)
+{
+	struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
+	__le32 *bref = p;
+	unsigned int blk;
+
+	while (bref < p+max) {
+		blk = le32_to_cpu(*bref++);
+		if (blk &&
+		    unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
+						    blk, 1))) {
+			es->s_last_error_block = cpu_to_le64(blk);
+			ext4_error_inode(inode, function, line, blk,
+					 "invalid block");
+			return -EIO;
+		}
+	}
+	return 0;
+}
+

fs/ext4/ext4.h

@@ -526,6 +526,7 @@ struct ext4_new_group_data {
 #define EXT4_FREE_BLOCKS_METADATA	0x0001
 #define EXT4_FREE_BLOCKS_FORGET		0x0002
 #define EXT4_FREE_BLOCKS_VALIDATED	0x0004
+#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE	0x0008
 
 /*
  * ioctl commands
@@ -939,6 +940,8 @@ struct ext4_inode_info {
 #define ext4_find_next_zero_bit		find_next_zero_bit_le
 #define ext4_find_next_bit		find_next_bit_le
 
+extern void ext4_set_bits(void *bm, int cur, int len);
+
 /*
  * Maximal mount counts between two filesystem checks
  */
@@ -1126,7 +1129,8 @@ struct ext4_sb_info {
 	struct journal_s *s_journal;
 	struct list_head s_orphan;
 	struct mutex s_orphan_lock;
-	struct mutex s_resize_lock;
+	unsigned long s_resize_flags;		/* Flags indicating if there
+						   is a resizer */
 	unsigned long s_commit_interval;
 	u32 s_max_batch_time;
 	u32 s_min_batch_time;
@@ -1214,6 +1218,9 @@ struct ext4_sb_info {
 
 	/* Kernel thread for multiple mount protection */
 	struct task_struct *s_mmp_tsk;
+
+	/* record the last minlen when FITRIM is called. */
+	atomic_t s_last_trim_minblks;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1743,6 +1750,7 @@ extern unsigned ext4_init_block_bitmap(struct super_block *sb,
 				       struct ext4_group_desc *desc);
 #define ext4_free_blocks_after_init(sb, group, desc)			\
 		ext4_init_block_bitmap(sb, NULL, group, desc)
+ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
 
 /* dir.c */
 extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
@@ -1793,7 +1801,7 @@ extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			     unsigned long count, int flags);
 extern int ext4_mb_add_groupinfo(struct super_block *sb,
 		ext4_group_t i, struct ext4_group_desc *desc);
-extern void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
+extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 				ext4_fsblk_t block, unsigned long count);
 extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
 
@@ -1834,6 +1842,17 @@ extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 extern qsize_t *ext4_get_reserved_space(struct inode *inode);
 extern void ext4_da_update_reserve_space(struct inode *inode,
 					int used, int quota_claim);
+
+/* indirect.c */
+extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
+				struct ext4_map_blocks *map, int flags);
+extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
+				const struct iovec *iov, loff_t offset,
+				unsigned long nr_segs);
+extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
+extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk);
+extern void ext4_ind_truncate(struct inode *inode);
+
 /* ioctl.c */
 extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
 extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
@@ -1855,6 +1874,9 @@ extern int ext4_group_extend(struct super_block *sb,
 				ext4_fsblk_t n_blocks_count);
 
 /* super.c */
+extern void *ext4_kvmalloc(size_t size, gfp_t flags);
+extern void *ext4_kvzalloc(size_t size, gfp_t flags);
+extern void ext4_kvfree(void *ptr);
 extern void __ext4_error(struct super_block *, const char *, unsigned int,
 			 const char *, ...)
 	__attribute__ ((format (printf, 4, 5)));
@@ -2067,11 +2089,19 @@ struct ext4_group_info {
 					 * 5 free 8-block regions. */
 };
 
-#define EXT4_GROUP_INFO_NEED_INIT_BIT	0
+#define EXT4_GROUP_INFO_NEED_INIT_BIT		0
+#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT		1
 
 #define EXT4_MB_GRP_NEED_INIT(grp)	\
 	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
 
+#define EXT4_MB_GRP_WAS_TRIMMED(grp)	\
+	(test_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
+#define EXT4_MB_GRP_SET_TRIMMED(grp)	\
+	(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_MAX_CONTENTION		8
 #define EXT4_CONTENTION_THRESHOLD	2
 
@@ -2122,6 +2152,19 @@ static inline void ext4_mark_super_dirty(struct super_block *sb)
 		sb->s_dirt =1;
 }
 
+/*
+ * Block validity checking
+ */
+#define ext4_check_indirect_blockref(inode, bh)				\
+	ext4_check_blockref(__func__, __LINE__, inode,			\
+			    (__le32 *)(bh)->b_data,			\
+			    EXT4_ADDR_PER_BLOCK((inode)->i_sb))
+
+#define ext4_ind_check_inode(inode)					\
+	ext4_check_blockref(__func__, __LINE__, inode,			\
+			    EXT4_I(inode)->i_data,			\
+			    EXT4_NDIR_BLOCKS)
+
 /*
  * Inodes and files operations
  */
@@ -2151,6 +2194,8 @@ 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_check_blockref(const char *, unsigned int,
+			       struct inode *, __le32 *, unsigned int);
 
 /* extents.c */
 extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
@@ -2230,6 +2275,10 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh)
 extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
 extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
 
+#define EXT4_RESIZING	0
+extern int ext4_resize_begin(struct super_block *sb);
+extern void ext4_resize_end(struct super_block *sb);
+
 #endif	/* __KERNEL__ */
 
 #endif	/* _EXT4_H */

fs/ext4/extents.c

@@ -114,12 +114,6 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
 			      struct ext4_ext_path *path,
 			      ext4_lblk_t block)
 {
-	struct ext4_inode_info *ei = EXT4_I(inode);
-	ext4_fsblk_t bg_start;
-	ext4_fsblk_t last_block;
-	ext4_grpblk_t colour;
-	ext4_group_t block_group;
-	int flex_size = ext4_flex_bg_size(EXT4_SB(inode->i_sb));
 	int depth;
 
 	if (path) {
@@ -161,36 +155,7 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
 	}
 
 	/* OK. use inode's group */
-	block_group = ei->i_block_group;
-	if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) {
-		/*
-		 * If there are at least EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME
-		 * block groups per flexgroup, reserve the first block
-		 * group for directories and special files.  Regular
-		 * files will start at the second block group.  This
-		 * tends to speed up directory access and improves
-		 * fsck times.
-		 */
-		block_group &= ~(flex_size-1);
-		if (S_ISREG(inode->i_mode))
-			block_group++;
-	}
-	bg_start = ext4_group_first_block_no(inode->i_sb, block_group);
-	last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
-
-	/*
-	 * If we are doing delayed allocation, we don't need take
-	 * colour into account.
-	 */
-	if (test_opt(inode->i_sb, DELALLOC))
-		return bg_start;
-
-	if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
-		colour = (current->pid % 16) *
-			(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
-	else
-		colour = (current->pid % 16) * ((last_block - bg_start) / 16);
-	return bg_start + colour + block;
+	return ext4_inode_to_goal_block(inode);
 }
 
 /*
@@ -776,6 +741,16 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
 				 logical, le32_to_cpu(curp->p_idx->ei_block));
 		return -EIO;
 	}
+
+	if (unlikely(le16_to_cpu(curp->p_hdr->eh_entries)
+			     >= le16_to_cpu(curp->p_hdr->eh_max))) {
+		EXT4_ERROR_INODE(inode,
+				 "eh_entries %d >= eh_max %d!",
+				 le16_to_cpu(curp->p_hdr->eh_entries),
+				 le16_to_cpu(curp->p_hdr->eh_max));
+		return -EIO;
+	}
+
 	len = EXT_MAX_INDEX(curp->p_hdr) - curp->p_idx;
 	if (logical > le32_to_cpu(curp->p_idx->ei_block)) {
 		/* insert after */
@@ -805,13 +780,6 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
 	ext4_idx_store_pblock(ix, ptr);
 	le16_add_cpu(&curp->p_hdr->eh_entries, 1);
 
-	if (unlikely(le16_to_cpu(curp->p_hdr->eh_entries)
-			     > le16_to_cpu(curp->p_hdr->eh_max))) {
-		EXT4_ERROR_INODE(inode,
-				 "logical %d == ei_block %d!",
-				 logical, le32_to_cpu(curp->p_idx->ei_block));
-		return -EIO;
-	}
 	if (unlikely(ix > EXT_LAST_INDEX(curp->p_hdr))) {
 		EXT4_ERROR_INODE(inode, "ix > EXT_LAST_INDEX!");
 		return -EIO;
@@ -1446,8 +1414,7 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path)
  * ext4_ext_next_leaf_block:
  * returns first allocated block from next leaf or EXT_MAX_BLOCKS
  */
-static ext4_lblk_t ext4_ext_next_leaf_block(struct inode *inode,
-					struct ext4_ext_path *path)
+static ext4_lblk_t ext4_ext_next_leaf_block(struct ext4_ext_path *path)
 {
 	int depth;
 
@@ -1757,7 +1724,6 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 		goto merge;
 	}
 
-repeat:
 	depth = ext_depth(inode);
 	eh = path[depth].p_hdr;
 	if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max))
@@ -1765,9 +1731,10 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 
 	/* probably next leaf has space for us? */
 	fex = EXT_LAST_EXTENT(eh);
-	next = ext4_ext_next_leaf_block(inode, path);
-	if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block)
-	    && next != EXT_MAX_BLOCKS) {
+	next = EXT_MAX_BLOCKS;
+	if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block))
+		next = ext4_ext_next_leaf_block(path);
+	if (next != EXT_MAX_BLOCKS) {
 		ext_debug("next leaf block - %d\n", next);
 		BUG_ON(npath != NULL);
 		npath = ext4_ext_find_extent(inode, next, NULL);
@@ -1779,7 +1746,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 			ext_debug("next leaf isn't full(%d)\n",
 				  le16_to_cpu(eh->eh_entries));
 			path = npath;
-			goto repeat;
+			goto has_space;
 		}
 		ext_debug("next leaf has no free space(%d,%d)\n",
 			  le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max));
@@ -1839,7 +1806,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 				ext4_ext_pblock(newext),
 				ext4_ext_is_uninitialized(newext),
 				ext4_ext_get_actual_len(newext),
-				nearex, len, nearex + 1, nearex + 2);
+				nearex, len, nearex, nearex + 1);
 		memmove(nearex + 1, nearex, len);
 		path[depth].p_ext = nearex;
 	}
@@ -2052,7 +2019,7 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
 }
 
 /*
- * ext4_ext_in_cache()
+ * ext4_ext_check_cache()
  * Checks to see if the given block is in the cache.
  * If it is, the cached extent is stored in the given
  * cache extent pointer.  If the cached extent is a hole,
@@ -2134,8 +2101,6 @@ ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
 /*
  * ext4_ext_rm_idx:
  * removes index from the index block.
- * It's used in truncate case only, thus all requests are for
- * last index in the block only.
  */
 static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
 			struct ext4_ext_path *path)
@@ -2153,6 +2118,13 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
 	err = ext4_ext_get_access(handle, inode, path);
 	if (err)
 		return err;
+
+	if (path->p_idx != EXT_LAST_INDEX(path->p_hdr)) {
+		int len = EXT_LAST_INDEX(path->p_hdr) - path->p_idx;
+		len *= sizeof(struct ext4_extent_idx);
+		memmove(path->p_idx, path->p_idx + 1, len);
+	}
+
 	le16_add_cpu(&path->p_hdr->eh_entries, -1);
 	err = ext4_ext_dirty(handle, inode, path);
 	if (err)
@@ -2534,8 +2506,7 @@ ext4_ext_more_to_rm(struct ext4_ext_path *path)
 	return 1;
 }
 
-static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
-				ext4_lblk_t end)
+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);
@@ -2575,7 +2546,7 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
 		if (i == depth) {
 			/* this is leaf block */
 			err = ext4_ext_rm_leaf(handle, inode, path,
-					start, end);
+					start, EXT_MAX_BLOCKS - 1);
 			/* root level has p_bh == NULL, brelse() eats this */
 			brelse(path[i].p_bh);
 			path[i].p_bh = NULL;
@@ -3107,12 +3078,10 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle,
 					      struct ext4_ext_path *path)
 {
 	struct ext4_extent *ex;
-	struct ext4_extent_header *eh;
 	int depth;
 	int err = 0;
 
 	depth = ext_depth(inode);
-	eh = path[depth].p_hdr;
 	ex = path[depth].p_ext;
 
 	ext_debug("ext4_convert_unwritten_extents_endio: inode %lu, logical"
@@ -3357,8 +3326,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
 
 	/* check in cache */
-	if (ext4_ext_in_cache(inode, map->m_lblk, &newex) &&
-		((flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) == 0)) {
+	if (!(flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) &&
+		ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
 		if (!newex.ee_start_lo && !newex.ee_start_hi) {
 			if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
 				/*
@@ -3497,8 +3466,27 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 
 			ext4_ext_mark_uninitialized(ex);
 
-			err = ext4_ext_remove_space(inode, map->m_lblk,
-				map->m_lblk + punched_out);
+			ext4_ext_invalidate_cache(inode);
+
+			err = ext4_ext_rm_leaf(handle, inode, path,
+				map->m_lblk, map->m_lblk + punched_out);
+
+			if (!err && path->p_hdr->eh_entries == 0) {
+				/*
+				 * Punch hole freed all of this sub tree,
+				 * so we need to correct eh_depth
+				 */
+				err = ext4_ext_get_access(handle, inode, path);
+				if (err == 0) {
+					ext_inode_hdr(inode)->eh_depth = 0;
+					ext_inode_hdr(inode)->eh_max =
+					cpu_to_le16(ext4_ext_space_root(
+						inode, 0));
+
+					err = ext4_ext_dirty(
+						handle, inode, path);
+				}
+			}
 
 			goto out2;
 		}
@@ -3596,17 +3584,18 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	}
 
 	err = check_eofblocks_fl(handle, inode, map->m_lblk, path, ar.len);
-	if (err)
-		goto out2;
-
-	err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
+	if (!err)
+		err = ext4_ext_insert_extent(handle, inode, path,
+					     &newex, flags);
 	if (err) {
+		int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ?
+			EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0;
 		/* free data blocks we just allocated */
 		/* not a good idea to call discard here directly,
 		 * but otherwise we'd need to call it every free() */
 		ext4_discard_preallocations(inode);
 		ext4_free_blocks(handle, inode, NULL, ext4_ext_pblock(&newex),
-				 ext4_ext_get_actual_len(&newex), 0);
+				 ext4_ext_get_actual_len(&newex), fb_flags);
 		goto out2;
 	}
 
@@ -3699,7 +3688,7 @@ void ext4_ext_truncate(struct inode *inode)
 
 	last_block = (inode->i_size + sb->s_blocksize - 1)
 			>> EXT4_BLOCK_SIZE_BITS(sb);
-	err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
+	err = ext4_ext_remove_space(inode, last_block);
 
 	/* In a multi-transaction truncate, we only make the final
 	 * transaction synchronous.
@@ -3835,7 +3824,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 						blkbits) >> blkbits))
 			new_size = offset + len;
 		else
-			new_size = (map.m_lblk + ret) << blkbits;
+			new_size = ((loff_t) map.m_lblk + ret) << blkbits;
 
 		ext4_falloc_update_inode(inode, mode, new_size,
 					 (map.m_flags & EXT4_MAP_NEW));

fs/ext4/fsync.c

@@ -129,15 +129,30 @@ static int ext4_sync_parent(struct inode *inode)
 {
 	struct writeback_control wbc;
 	struct dentry *dentry = NULL;
+	struct inode *next;
 	int ret = 0;
 
-	while (inode && ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
+	if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY))
+		return 0;
+	inode = igrab(inode);
+	while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
 		ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
-		dentry = list_entry(inode->i_dentry.next,
-				    struct dentry, d_alias);
-		if (!dentry || !dentry->d_parent || !dentry->d_parent->d_inode)
+		dentry = NULL;
+		spin_lock(&inode->i_lock);
+		if (!list_empty(&inode->i_dentry)) {
+			dentry = list_first_entry(&inode->i_dentry,
+						  struct dentry, d_alias);
+			dget(dentry);
+		}
+		spin_unlock(&inode->i_lock);
+		if (!dentry)
 			break;
-		inode = dentry->d_parent->d_inode;
+		next = igrab(dentry->d_parent->d_inode);
+		dput(dentry);
+		if (!next)
+			break;
+		iput(inode);
+		inode = next;
 		ret = sync_mapping_buffers(inode->i_mapping);
 		if (ret)
 			break;
@@ -148,6 +163,7 @@ static int ext4_sync_parent(struct inode *inode)
 		if (ret)
 			break;
 	}
+	iput(inode);
 	return ret;
 }
 

fs/ext4/ialloc.c

@@ -1287,7 +1287,7 @@ extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
 			   group, used_blks,
 			   ext4_itable_unused_count(sb, gdp));
 		ret = 1;
-		goto out;
+		goto err_out;
 	}
 
 	blk = ext4_inode_table(sb, gdp) + used_blks;

fs/ext4/ioctl.c

@@ -202,8 +202,9 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		struct super_block *sb = inode->i_sb;
 		int err, err2=0;
 
-		if (!capable(CAP_SYS_RESOURCE))
-			return -EPERM;
+		err = ext4_resize_begin(sb);
+		if (err)
+			return err;
 
 		if (get_user(n_blocks_count, (__u32 __user *)arg))
 			return -EFAULT;
@@ -221,6 +222,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (err == 0)
 			err = err2;
 		mnt_drop_write(filp->f_path.mnt);
+		ext4_resize_end(sb);
 
 		return err;
 	}
@@ -271,8 +273,9 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		struct super_block *sb = inode->i_sb;
 		int err, err2=0;
 
-		if (!capable(CAP_SYS_RESOURCE))
-			return -EPERM;
+		err = ext4_resize_begin(sb);
+		if (err)
+			return err;
 
 		if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
 				sizeof(input)))
@@ -291,6 +294,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (err == 0)
 			err = err2;
 		mnt_drop_write(filp->f_path.mnt);
+		ext4_resize_end(sb);
 
 		return err;
 	}

fs/ext4/mballoc.h

@@ -187,7 +187,6 @@ struct ext4_allocation_context {
 	__u16 ac_flags;		/* allocation hints */
 	__u8 ac_status;
 	__u8 ac_criteria;
-	__u8 ac_repeats;
 	__u8 ac_2order;		/* if request is to allocate 2^N blocks and
 				 * N > 0, the field stores N, otherwise 0 */
 	__u8 ac_op;		/* operation, for history only */

fs/ext4/namei.c

@@ -289,7 +289,7 @@ static struct stats dx_show_leaf(struct dx_hash_info *hinfo, struct ext4_dir_ent
 				while (len--) printk("%c", *name++);
 				ext4fs_dirhash(de->name, de->name_len, &h);
 				printk(":%x.%u ", h.hash,
-				       ((char *) de - base));
+				       (unsigned) ((char *) de - base));
 			}
 			space += EXT4_DIR_REC_LEN(de->name_len);
 			names++;
@@ -1013,7 +1013,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct q
 
 	*err = -ENOENT;
 errout:
-	dxtrace(printk(KERN_DEBUG "%s not found\n", name));
+	dxtrace(printk(KERN_DEBUG "%s not found\n", d_name->name));
 	dx_release (frames);
 	return NULL;
 }
@@ -1985,18 +1985,11 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 	if (!list_empty(&EXT4_I(inode)->i_orphan))
 		goto out_unlock;
 
-	/* Orphan handling is only valid for files with data blocks
-	 * being truncated, or files being unlinked. */
-
-	/* @@@ FIXME: Observation from aviro:
-	 * I think I can trigger J_ASSERT in ext4_orphan_add().  We block
-	 * here (on s_orphan_lock), so race with ext4_link() which might bump
-	 * ->i_nlink. For, say it, character device. Not a regular file,
-	 * not a directory, not a symlink and ->i_nlink > 0.
-	 *
-	 * tytso, 4/25/2009: I'm not sure how that could happen;
-	 * shouldn't the fs core protect us from these sort of
-	 * unlink()/link() races?
+	/*
+	 * Orphan handling is only valid for files with data blocks
+	 * being truncated, or files being unlinked. Note that we either
+	 * hold i_mutex, or the inode can not be referenced from outside,
+	 * so i_nlink should not be bumped due to race
 	 */
 	J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
 		  S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);

fs/ext4/page-io.c

@@ -285,11 +285,7 @@ static int io_submit_init(struct ext4_io_submit *io,
 	io_end = ext4_init_io_end(inode, GFP_NOFS);
 	if (!io_end)
 		return -ENOMEM;
-	do {
-		bio = bio_alloc(GFP_NOIO, nvecs);
-		nvecs >>= 1;
-	} while (bio == NULL);
-
+	bio = bio_alloc(GFP_NOIO, min(nvecs, BIO_MAX_PAGES));
 	bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
 	bio->bi_bdev = bh->b_bdev;
 	bio->bi_private = io->io_end = io_end;

fs/ext4/super.c

@@ -110,6 +110,35 @@ static struct file_system_type ext3_fs_type = {
 #define IS_EXT3_SB(sb) (0)
 #endif
 
+void *ext4_kvmalloc(size_t size, gfp_t flags)
+{
+	void *ret;
+
+	ret = kmalloc(size, flags);
+	if (!ret)
+		ret = __vmalloc(size, flags, PAGE_KERNEL);
+	return ret;
+}
+
+void *ext4_kvzalloc(size_t size, gfp_t flags)
+{
+	void *ret;
+
+	ret = kmalloc(size, flags);
+	if (!ret)
+		ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL);
+	return ret;
+}
+
+void ext4_kvfree(void *ptr)
+{
+	if (is_vmalloc_addr(ptr))
+		vfree(ptr);
+	else
+		kfree(ptr);
+
+}
+
 ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
 			       struct ext4_group_desc *bg)
 {
@@ -269,6 +298,7 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
 	journal_t *journal;
 	handle_t  *handle;
 
+	trace_ext4_journal_start(sb, nblocks, _RET_IP_);
 	if (sb->s_flags & MS_RDONLY)
 		return ERR_PTR(-EROFS);
 
@@ -789,11 +819,8 @@ static void ext4_put_super(struct super_block *sb)
 
 	for (i = 0; i < sbi->s_gdb_count; i++)
 		brelse(sbi->s_group_desc[i]);
-	kfree(sbi->s_group_desc);
-	if (is_vmalloc_addr(sbi->s_flex_groups))
-		vfree(sbi->s_flex_groups);
-	else
-		kfree(sbi->s_flex_groups);
+	ext4_kvfree(sbi->s_group_desc);
+	ext4_kvfree(sbi->s_flex_groups);
 	percpu_counter_destroy(&sbi->s_freeblocks_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
@@ -1976,15 +2003,11 @@ static int ext4_fill_flex_info(struct super_block *sb)
 			((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) <<
 			      EXT4_DESC_PER_BLOCK_BITS(sb))) / groups_per_flex;
 	size = flex_group_count * sizeof(struct flex_groups);
-	sbi->s_flex_groups = kzalloc(size, GFP_KERNEL);
+	sbi->s_flex_groups = ext4_kvzalloc(size, GFP_KERNEL);
 	if (sbi->s_flex_groups == NULL) {
-		sbi->s_flex_groups = vzalloc(size);
-		if (sbi->s_flex_groups == NULL) {
-			ext4_msg(sb, KERN_ERR,
-				 "not enough memory for %u flex groups",
-				 flex_group_count);
-			goto failed;
-		}
+		ext4_msg(sb, KERN_ERR, "not enough memory for %u flex groups",
+			 flex_group_count);
+		goto failed;
 	}
 
 	for (i = 0; i < sbi->s_groups_count; i++) {
@@ -2383,17 +2406,25 @@ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi)
 	unsigned long stride = le16_to_cpu(sbi->s_es->s_raid_stride);
 	unsigned long stripe_width =
 			le32_to_cpu(sbi->s_es->s_raid_stripe_width);
+	int ret;
 
 	if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group)
-		return sbi->s_stripe;
-
-	if (stripe_width <= sbi->s_blocks_per_group)
-		return stripe_width;
+		ret = sbi->s_stripe;
+	else if (stripe_width <= sbi->s_blocks_per_group)
+		ret = stripe_width;
+	else if (stride <= sbi->s_blocks_per_group)
+		ret = stride;
+	else
+		ret = 0;
 
-	if (stride <= sbi->s_blocks_per_group)
-		return stride;
+	/*
+	 * If the stripe width is 1, this makes no sense and
+	 * we set it to 0 to turn off stripe handling code.
+	 */
+	if (ret <= 1)
+		ret = 0;
 
-	return 0;
+	return ret;
 }
 
 /* sysfs supprt */
@@ -3408,8 +3439,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
 	db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
 		   EXT4_DESC_PER_BLOCK(sb);
-	sbi->s_group_desc = kmalloc(db_count * sizeof(struct buffer_head *),
-				    GFP_KERNEL);
+	sbi->s_group_desc = ext4_kvmalloc(db_count *
+					  sizeof(struct buffer_head *),
+					  GFP_KERNEL);
 	if (sbi->s_group_desc == NULL) {
 		ext4_msg(sb, KERN_ERR, "not enough memory");
 		goto failed_mount;
@@ -3491,7 +3523,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
 	mutex_init(&sbi->s_orphan_lock);
-	mutex_init(&sbi->s_resize_lock);
+	sbi->s_resize_flags = 0;
 
 	sb->s_root = NULL;
 
@@ -3741,12 +3773,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 failed_mount3:
 	del_timer(&sbi->s_err_report);
-	if (sbi->s_flex_groups) {
-		if (is_vmalloc_addr(sbi->s_flex_groups))
-			vfree(sbi->s_flex_groups);
-		else
-			kfree(sbi->s_flex_groups);
-	}
+	if (sbi->s_flex_groups)
+		ext4_kvfree(sbi->s_flex_groups);
 	percpu_counter_destroy(&sbi->s_freeblocks_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
@@ -3756,7 +3784,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 failed_mount2:
 	for (i = 0; i < db_count; i++)
 		brelse(sbi->s_group_desc[i]);
-	kfree(sbi->s_group_desc);
+	ext4_kvfree(sbi->s_group_desc);
 failed_mount:
 	if (sbi->s_proc) {
 		remove_proc_entry(sb->s_id, ext4_proc_root);

fs/ext4/truncate.h

+/*
+ * linux/fs/ext4/truncate.h
+ *
+ * Common inline functions needed for truncate support
+ */
+
+/*
+ * Truncate blocks that were not used by write. We have to truncate the
+ * pagecache as well so that corresponding buffers get properly unmapped.
+ */
+static inline void ext4_truncate_failed_write(struct inode *inode)
+{
+	truncate_inode_pages(inode->i_mapping, inode->i_size);
+	ext4_truncate(inode);
+}
+
+/*
+ * Work out how many blocks we need to proceed with the next chunk of a
+ * truncate transaction.
+ */
+static inline unsigned long ext4_blocks_for_truncate(struct inode *inode)
+{
+	ext4_lblk_t needed;
+
+	needed = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9);
+
+	/* Give ourselves just enough room to cope with inodes in which
+	 * i_blocks is corrupt: we've seen disk corruptions in the past
+	 * which resulted in random data in an inode which looked enough
+	 * like a regular file for ext4 to try to delete it.  Things
+	 * will go a bit crazy if that happens, but at least we should
+	 * try not to panic the whole kernel. */
+	if (needed < 2)
+		needed = 2;
+
+	/* But we need to bound the transaction so we don't overflow the
+	 * journal. */
+	if (needed > EXT4_MAX_TRANS_DATA)
+		needed = EXT4_MAX_TRANS_DATA;
+
+	return EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + needed;
+}
+

fs/jbd2/checkpoint.c

@@ -257,9 +257,12 @@ static void
 __flush_batch(journal_t *journal, int *batch_count)
 {
 	int i;
+	struct blk_plug plug;
 
+	blk_start_plug(&plug);
 	for (i = 0; i < *batch_count; i++)
-		write_dirty_buffer(journal->j_chkpt_bhs[i], WRITE);
+		write_dirty_buffer(journal->j_chkpt_bhs[i], WRITE_SYNC);
+	blk_finish_plug(&plug);
 
 	for (i = 0; i < *batch_count; i++) {
 		struct buffer_head *bh = journal->j_chkpt_bhs[i];

include/linux/jbd2.h

@@ -1329,12 +1329,6 @@ extern int jbd_blocks_per_page(struct inode *inode);
 #define BUFFER_TRACE2(bh, bh2, info)	do {} while (0)
 #define JBUFFER_TRACE(jh, info)	do {} while (0)
 
-/* 
- * jbd2_dev_to_name is a utility function used by the jbd2 and ext4 
- * tracing infrastructure to map a dev_t to a device name.
- */
-extern const char *jbd2_dev_to_name(dev_t device);
-
 #endif	/* __KERNEL__ */
 
 #endif	/* _LINUX_JBD2_H */