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:
  ext4: extent macros cleanup
  Fix compilation with EXT_DEBUG, also fix leXX_to_cpu conversions.
  ext4: remove extra IS_RDONLY() check
  ext4: Use is_power_of_2()
  Use zero_user_page() in ext4 where possible
  ext4: Remove 65000 subdirectory limit
  ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields 
  ext4: Add nanosecond timestamps
  jbd2: Move jbd2-debug file to debugfs
  jbd2: Fix CONFIG_JBD_DEBUG ifdef to be CONFIG_JBD2_DEBUG
  ext4: Set the journal JBD2_FEATURE_INCOMPAT_64BIT on large devices
  ext4: Make extents code sanely handle on-disk corruption
  ext4: copy i_flags to inode flags on write
  ext4: Enable extents by default
  Change on-disk format to support 2^15 uninitialized extents
  write support for preallocated blocks
  fallocate support in ext4
  sys_fallocate() implementation on i386, x86_64 and powerpc

12 files changed, 168 insertions, 11 deletions

diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h
index e84ace1ec8bf..9b15545eb9b5 100644
--- a/include/asm-i386/unistd.h
+++ b/include/asm-i386/unistd.h
@@ -329,10 +329,11 @@
 #define __NR_signalfd		321
 #define __NR_timerfd		322
 #define __NR_eventfd		323
+#define __NR_fallocate		324
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 324
+#define NR_syscalls 325
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
diff --git a/include/asm-powerpc/systbl.h b/include/asm-powerpc/systbl.h
index 1cc3f9cb6f4e..cc6d87228258 100644
--- a/include/asm-powerpc/systbl.h
+++ b/include/asm-powerpc/systbl.h
@@ -308,6 +308,7 @@ COMPAT_SYS_SPU(move_pages)
 SYSCALL_SPU(getcpu)
 COMPAT_SYS(epoll_pwait)
 COMPAT_SYS_SPU(utimensat)
+COMPAT_SYS(fallocate)
 COMPAT_SYS_SPU(signalfd)
 COMPAT_SYS_SPU(timerfd)
 SYSCALL_SPU(eventfd)
diff --git a/include/asm-powerpc/unistd.h b/include/asm-powerpc/unistd.h
index f71c6061f1ec..97d82b6a9406 100644
--- a/include/asm-powerpc/unistd.h
+++ b/include/asm-powerpc/unistd.h
@@ -331,10 +331,11 @@
 #define __NR_timerfd		306
 #define __NR_eventfd		307
 #define __NR_sync_file_range2	308
+#define __NR_fallocate		309
 
 #ifdef __KERNEL__
 
-#define __NR_syscalls		309
+#define __NR_syscalls		310
 
 #define __NR__exit __NR_exit
 #define NR_syscalls	__NR_syscalls
diff --git a/include/asm-x86_64/unistd.h b/include/asm-x86_64/unistd.h
index 8696f8ad401e..fc4e73f5f1fa 100644
--- a/include/asm-x86_64/unistd.h
+++ b/include/asm-x86_64/unistd.h
@@ -630,6 +630,8 @@ __SYSCALL(__NR_signalfd, sys_signalfd)
 __SYSCALL(__NR_timerfd, sys_timerfd)
 #define __NR_eventfd		284
 __SYSCALL(__NR_eventfd, sys_eventfd)
+#define __NR_fallocate		285
+__SYSCALL(__NR_fallocate, sys_fallocate)
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR
diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h
index de1f9f78625a..cdee7aaa57aa 100644
--- a/include/linux/ext4_fs.h
+++ b/include/linux/ext4_fs.h
@@ -71,7 +71,7 @@
 /*
  * Maximal count of links to a file
  */
-#define EXT4_LINK_MAX		32000
+#define EXT4_LINK_MAX		65000
 
 /*
  * Macro-instructions used to manage several block sizes
@@ -102,6 +102,7 @@
 				 EXT4_GOOD_OLD_FIRST_INO : \
 				 (s)->s_first_ino)
 #endif
+#define EXT4_BLOCK_ALIGN(size, blkbits)		ALIGN((size), (1 << (blkbits)))
 
 /*
  * Macro-instructions used to manage fragments
@@ -201,6 +202,7 @@ struct ext4_group_desc
 #define EXT4_STATE_JDATA		0x00000001 /* journaled data exists */
 #define EXT4_STATE_NEW			0x00000002 /* inode is newly created */
 #define EXT4_STATE_XATTR		0x00000004 /* has in-inode xattrs */
+#define EXT4_STATE_NO_EXPAND		0x00000008 /* No space for expansion */
 
 /* Used to pass group descriptor data when online resize is done */
 struct ext4_new_group_input {
@@ -225,6 +227,11 @@ struct ext4_new_group_data {
 	__u32 free_blocks_count;
 };
 
+/*
+ * Following is used by preallocation code to tell get_blocks() that we
+ * want uninitialzed extents.
+ */
+#define EXT4_CREATE_UNINITIALIZED_EXT		2
 
 /*
  * ioctl commands
@@ -237,7 +244,7 @@ struct ext4_new_group_data {
 #define EXT4_IOC_GROUP_ADD		_IOW('f', 8,struct ext4_new_group_input)
 #define	EXT4_IOC_GETVERSION_OLD		FS_IOC_GETVERSION
 #define	EXT4_IOC_SETVERSION_OLD		FS_IOC_SETVERSION
-#ifdef CONFIG_JBD_DEBUG
+#ifdef CONFIG_JBD2_DEBUG
 #define EXT4_IOC_WAIT_FOR_READONLY	_IOR('f', 99, long)
 #endif
 #define EXT4_IOC_GETRSVSZ		_IOR('f', 5, long)
@@ -253,7 +260,7 @@ struct ext4_new_group_data {
 #define EXT4_IOC32_GETRSVSZ		_IOR('f', 5, int)
 #define EXT4_IOC32_SETRSVSZ		_IOW('f', 6, int)
 #define EXT4_IOC32_GROUP_EXTEND		_IOW('f', 7, unsigned int)
-#ifdef CONFIG_JBD_DEBUG
+#ifdef CONFIG_JBD2_DEBUG
 #define EXT4_IOC32_WAIT_FOR_READONLY	_IOR('f', 99, int)
 #endif
 #define EXT4_IOC32_GETVERSION_OLD	FS_IOC32_GETVERSION
@@ -282,7 +289,7 @@ struct ext4_inode {
 	__le16	i_uid;		/* Low 16 bits of Owner Uid */
 	__le32	i_size;		/* Size in bytes */
 	__le32	i_atime;	/* Access time */
-	__le32	i_ctime;	/* Creation time */
+	__le32	i_ctime;	/* Inode Change time */
 	__le32	i_mtime;	/* Modification time */
 	__le32	i_dtime;	/* Deletion Time */
 	__le16	i_gid;		/* Low 16 bits of Group Id */
@@ -331,10 +338,85 @@ struct ext4_inode {
 	} osd2;				/* OS dependent 2 */
 	__le16	i_extra_isize;
 	__le16	i_pad1;
+	__le32  i_ctime_extra;  /* extra Change time      (nsec << 2 | epoch) */
+	__le32  i_mtime_extra;  /* extra Modification time(nsec << 2 | epoch) */
+	__le32  i_atime_extra;  /* extra Access time      (nsec << 2 | epoch) */
+	__le32  i_crtime;       /* File Creation time */
+	__le32  i_crtime_extra; /* extra FileCreationtime (nsec << 2 | epoch) */
 };
 
 #define i_size_high	i_dir_acl
 
+#define EXT4_EPOCH_BITS 2
+#define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1)
+#define EXT4_NSEC_MASK  (~0UL << EXT4_EPOCH_BITS)
+
+/*
+ * Extended fields will fit into an inode if the filesystem was formatted
+ * with large inodes (-I 256 or larger) and there are not currently any EAs
+ * consuming all of the available space. For new inodes we always reserve
+ * enough space for the kernel's known extended fields, but for inodes
+ * created with an old kernel this might not have been the case. None of
+ * the extended inode fields is critical for correct filesystem operation.
+ * This macro checks if a certain field fits in the inode. Note that
+ * inode-size = GOOD_OLD_INODE_SIZE + i_extra_isize
+ */
+#define EXT4_FITS_IN_INODE(ext4_inode, einode, field)	\
+	((offsetof(typeof(*ext4_inode), field) +	\
+	  sizeof((ext4_inode)->field))			\
+	<= (EXT4_GOOD_OLD_INODE_SIZE +			\
+	    (einode)->i_extra_isize))			\
+
+static inline __le32 ext4_encode_extra_time(struct timespec *time)
+{
+       return cpu_to_le32((sizeof(time->tv_sec) > 4 ?
+			   time->tv_sec >> 32 : 0) |
+			   ((time->tv_nsec << 2) & EXT4_NSEC_MASK));
+}
+
+static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
+{
+       if (sizeof(time->tv_sec) > 4)
+	       time->tv_sec |= (__u64)(le32_to_cpu(extra) & EXT4_EPOCH_MASK)
+			       << 32;
+       time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> 2;
+}
+
+#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode)			       \
+do {									       \
+	(raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec);	       \
+	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra))     \
+		(raw_inode)->xtime ## _extra =				       \
+				ext4_encode_extra_time(&(inode)->xtime);       \
+} while (0)
+
+#define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode)			       \
+do {									       \
+	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime))		       \
+		(raw_inode)->xtime = cpu_to_le32((einode)->xtime.tv_sec);      \
+	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra))	       \
+		(raw_inode)->xtime ## _extra =				       \
+				ext4_encode_extra_time(&(einode)->xtime);      \
+} while (0)
+
+#define EXT4_INODE_GET_XTIME(xtime, inode, raw_inode)			       \
+do {									       \
+	(inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime);       \
+	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra))     \
+		ext4_decode_extra_time(&(inode)->xtime,			       \
+				       raw_inode->xtime ## _extra);	       \
+} while (0)
+
+#define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode)			       \
+do {									       \
+	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime))		       \
+		(einode)->xtime.tv_sec = 				       \
+			(signed)le32_to_cpu((raw_inode)->xtime);	       \
+	if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra))	       \
+		ext4_decode_extra_time(&(einode)->xtime,		       \
+				       raw_inode->xtime ## _extra);	       \
+} while (0)
+
 #if defined(__KERNEL__) || defined(__linux__)
 #define i_reserved1	osd1.linux1.l_i_reserved1
 #define i_frag		osd2.linux2.l_i_frag
@@ -533,6 +615,13 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
 	return container_of(inode, struct ext4_inode_info, vfs_inode);
 }
 
+static inline struct timespec ext4_current_time(struct inode *inode)
+{
+	return (inode->i_sb->s_time_gran < NSEC_PER_SEC) ?
+		current_fs_time(inode->i_sb) : CURRENT_TIME_SEC;
+}
+
+
 static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 {
 	return ino == EXT4_ROOT_INO ||
@@ -603,6 +692,8 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 #define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
 #define EXT4_FEATURE_RO_COMPAT_LARGE_FILE	0x0002
 #define EXT4_FEATURE_RO_COMPAT_BTREE_DIR	0x0004
+#define EXT4_FEATURE_RO_COMPAT_DIR_NLINK	0x0020
+#define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE	0x0040
 
 #define EXT4_FEATURE_INCOMPAT_COMPRESSION	0x0001
 #define EXT4_FEATURE_INCOMPAT_FILETYPE		0x0002
@@ -620,6 +711,8 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 					 EXT4_FEATURE_INCOMPAT_64BIT)
 #define EXT4_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
 					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
+					 EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
+					 EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
 					 EXT4_FEATURE_RO_COMPAT_BTREE_DIR)
 
 /*
@@ -862,6 +955,7 @@ extern int ext4_change_inode_journal_flag(struct inode *, int);
 extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
 extern void ext4_truncate (struct inode *);
 extern void ext4_set_inode_flags(struct inode *);
+extern void ext4_get_inode_flags(struct ext4_inode_info *);
 extern void ext4_set_aops(struct inode *inode);
 extern int ext4_writepage_trans_blocks(struct inode *);
 extern int ext4_block_truncate_page(handle_t *handle, struct page *page,
@@ -983,6 +1077,8 @@ extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 extern void ext4_ext_truncate(struct inode *, struct page *);
 extern void ext4_ext_init(struct super_block *);
 extern void ext4_ext_release(struct super_block *);
+extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
+			  loff_t len);
 static inline int
 ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
 			unsigned long max_blocks, struct buffer_head *bh,
diff --git a/include/linux/ext4_fs_extents.h b/include/linux/ext4_fs_extents.h
index acfe59740b03..81406f3655d4 100644
--- a/include/linux/ext4_fs_extents.h
+++ b/include/linux/ext4_fs_extents.h
@@ -141,7 +141,25 @@ typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *,
 
 #define EXT_MAX_BLOCK	0xffffffff
 
-#define EXT_MAX_LEN	((1UL << 15) - 1)
+/*
+ * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an
+ * initialized extent. This is 2^15 and not (2^16 - 1), since we use the
+ * MSB of ee_len field in the extent datastructure to signify if this
+ * particular extent is an initialized extent or an uninitialized (i.e.
+ * preallocated).
+ * EXT_UNINIT_MAX_LEN is the maximum number of blocks we can have in an
+ * uninitialized extent.
+ * If ee_len is <= 0x8000, it is an initialized extent. Otherwise, it is an
+ * uninitialized one. In other words, if MSB of ee_len is set, it is an
+ * uninitialized extent with only one special scenario when ee_len = 0x8000.
+ * In this case we can not have an uninitialized extent of zero length and
+ * thus we make it as a special case of initialized extent with 0x8000 length.
+ * This way we get better extent-to-group alignment for initialized extents.
+ * Hence, the maximum number of blocks we can have in an *initialized*
+ * extent is 2^15 (32768) and in an *uninitialized* extent is 2^15-1 (32767).
+ */
+#define EXT_INIT_MAX_LEN	(1UL << 15)
+#define EXT_UNINIT_MAX_LEN	(EXT_INIT_MAX_LEN - 1)
 
 
 #define EXT_FIRST_EXTENT(__hdr__) \
@@ -188,8 +206,31 @@ ext4_ext_invalidate_cache(struct inode *inode)
 	EXT4_I(inode)->i_cached_extent.ec_type = EXT4_EXT_CACHE_NO;
 }
 
+static inline void ext4_ext_mark_uninitialized(struct ext4_extent *ext)
+{
+	/* We can not have an uninitialized extent of zero length! */
+	BUG_ON((le16_to_cpu(ext->ee_len) & ~EXT_INIT_MAX_LEN) == 0);
+	ext->ee_len |= cpu_to_le16(EXT_INIT_MAX_LEN);
+}
+
+static inline int ext4_ext_is_uninitialized(struct ext4_extent *ext)
+{
+	/* Extent with ee_len of 0x8000 is treated as an initialized extent */
+	return (le16_to_cpu(ext->ee_len) > EXT_INIT_MAX_LEN);
+}
+
+static inline int ext4_ext_get_actual_len(struct ext4_extent *ext)
+{
+	return (le16_to_cpu(ext->ee_len) <= EXT_INIT_MAX_LEN ?
+		le16_to_cpu(ext->ee_len) :
+		(le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN));
+}
+
 extern int ext4_extent_tree_init(handle_t *, struct inode *);
 extern int ext4_ext_calc_credits_for_insert(struct inode *, struct ext4_ext_path *);
+extern int ext4_ext_try_to_merge(struct inode *inode,
+				 struct ext4_ext_path *path,
+				 struct ext4_extent *);
 extern unsigned int ext4_ext_check_overlap(struct inode *, struct ext4_extent *, struct ext4_ext_path *);
 extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *);
 extern int ext4_ext_walk_space(struct inode *, unsigned long, unsigned long, ext_prepare_callback, void *);
diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h
index 9de494406995..1a511e9905aa 100644
--- a/include/linux/ext4_fs_i.h
+++ b/include/linux/ext4_fs_i.h
@@ -153,6 +153,11 @@ struct ext4_inode_info {
 
 	unsigned long i_ext_generation;
 	struct ext4_ext_cache i_cached_extent;
+	/*
+	 * File creation time. Its function is same as that of
+	 * struct timespec i_{a,c,m}time in the generic inode.
+	 */
+	struct timespec i_crtime;
 };
 
 #endif	/* _LINUX_EXT4_FS_I */
diff --git a/include/linux/ext4_fs_sb.h b/include/linux/ext4_fs_sb.h
index 2347557a327a..1b2ffee12be9 100644
--- a/include/linux/ext4_fs_sb.h
+++ b/include/linux/ext4_fs_sb.h
@@ -73,7 +73,7 @@ struct ext4_sb_info {
 	struct list_head s_orphan;
 	unsigned long s_commit_interval;
 	struct block_device *journal_bdev;
-#ifdef CONFIG_JBD_DEBUG
+#ifdef CONFIG_JBD2_DEBUG
 	struct timer_list turn_ro_timer;	/* For turning read-only (crash simulation) */
 	wait_queue_head_t ro_wait_queue;	/* For people waiting for the fs to go read-only */
 #endif
@@ -81,6 +81,7 @@ struct ext4_sb_info {
 	char *s_qf_names[MAXQUOTAS];		/* Names of quota files with journalled quota */
 	int s_jquota_fmt;			/* Format of quota to use */
 #endif
+	unsigned int s_want_extra_isize; /* New inodes should reserve # bytes */
 
 #ifdef EXTENTS_STATS
 	/* ext4 extents stats */
diff --git a/include/linux/falloc.h b/include/linux/falloc.h
new file mode 100644
index 000000000000..8e912ab6a072
--- /dev/null
+++ b/include/linux/falloc.h
@@ -0,0 +1,6 @@
+#ifndef _FALLOC_H_
+#define _FALLOC_H_
+
+#define FALLOC_FL_KEEP_SIZE	0x01 /* default is extend size */
+
+#endif /* _FALLOC_H_ */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 98205f680476..0b806c5e32eb 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1147,6 +1147,8 @@ struct inode_operations {
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*removexattr) (struct dentry *, const char *);
 	void (*truncate_range)(struct inode *, loff_t, loff_t);
+	long (*fallocate)(struct inode *inode, int mode, loff_t offset,
+			  loff_t len);
 };
 
 struct seq_file;
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 0e0fedd2039a..260d6d76c5f3 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -50,14 +50,14 @@
  */
 #define JBD_DEFAULT_MAX_COMMIT_AGE 5
 
-#ifdef CONFIG_JBD_DEBUG
+#ifdef CONFIG_JBD2_DEBUG
 /*
  * Define JBD_EXPENSIVE_CHECKING to enable more expensive internal
  * consistency checks.  By default we don't do this unless
- * CONFIG_JBD_DEBUG is on.
+ * CONFIG_JBD2_DEBUG is on.
  */
 #define JBD_EXPENSIVE_CHECKING
-extern int jbd2_journal_enable_debug;
+extern u8 jbd2_journal_enable_debug;
 
 #define jbd_debug(n, f, a...)						\
 	do {								\
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 83d0ec11235e..7a8b1e3322e0 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -610,6 +610,7 @@ asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemas
 asmlinkage long sys_timerfd(int ufd, int clockid, int flags,
 			    const struct itimerspec __user *utmr);
 asmlinkage long sys_eventfd(unsigned int count);
+asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len);
 
 int kernel_execve(const char *filename, char *const argv[], char *const envp[]);