14 files changed, 395 insertions, 82 deletions

diff --git a/include/asm-arm/bitops.h b/include/asm-arm/bitops.h
index 47a6b086eee2..5c60bfc1a84d 100644
--- a/include/asm-arm/bitops.h
+++ b/include/asm-arm/bitops.h
@@ -310,6 +310,8 @@ static inline int constant_fls(int x)
                 _find_first_zero_bit_le(p,sz)
 #define ext2_find_next_zero_bit(p,sz,off)       \
                 _find_next_zero_bit_le(p,sz,off)
+#define ext2_find_next_bit(p, sz, off) \
+                _find_next_bit_le(p, sz, off)
 
 /*
  * Minix is defined to use little-endian byte ordering.
diff --git a/include/asm-generic/bitops/ext2-non-atomic.h b/include/asm-generic/bitops/ext2-non-atomic.h
index 1697404afa05..63cf822431a2 100644
--- a/include/asm-generic/bitops/ext2-non-atomic.h
+++ b/include/asm-generic/bitops/ext2-non-atomic.h
@@ -14,5 +14,7 @@
         generic_find_first_zero_le_bit((unsigned long *)(addr), (size))
 #define ext2_find_next_zero_bit(addr, size, off) \
         generic_find_next_zero_le_bit((unsigned long *)(addr), (size), (off))
+#define ext2_find_next_bit(addr, size, off) \
+        generic_find_next_le_bit((unsigned long *)(addr), (size), (off))
 
 #endif /* _ASM_GENERIC_BITOPS_EXT2_NON_ATOMIC_H_ */
diff --git a/include/asm-generic/bitops/le.h b/include/asm-generic/bitops/le.h
index b9c7e5d2d2ad..80e3bf13b2b9 100644
--- a/include/asm-generic/bitops/le.h
+++ b/include/asm-generic/bitops/le.h
@@ -20,6 +20,8 @@
 #define generic___test_and_clear_le_bit(nr, addr) __test_and_clear_bit(nr, addr)
 
 #define generic_find_next_zero_le_bit(addr, size, offset) find_next_zero_bit(addr, size, offset)
+#define generic_find_next_le_bit(addr, size, offset) \
+                        find_next_bit(addr, size, offset)
 
 #elif defined(__BIG_ENDIAN)
 
@@ -42,6 +44,8 @@
 
 extern unsigned long generic_find_next_zero_le_bit(const unsigned long *addr,
                 unsigned long size, unsigned long offset);
+extern unsigned long generic_find_next_le_bit(const unsigned long *addr,
+                unsigned long size, unsigned long offset);
 
 #else
 #error "Please fix <asm/byteorder.h>"
diff --git a/include/asm-m68k/bitops.h b/include/asm-m68k/bitops.h
index 2976b5d68e96..83d1f286230b 100644
--- a/include/asm-m68k/bitops.h
+++ b/include/asm-m68k/bitops.h
@@ -410,6 +410,8 @@ static inline int ext2_find_next_zero_bit(const void *vaddr, unsigned size,
         res = ext2_find_first_zero_bit (p, size - 32 * (p - addr));
         return (p - addr) * 32 + res;
 }
+#define ext2_find_next_bit(addr, size, off) \
+        generic_find_next_le_bit((unsigned long *)(addr), (size), (off))
 
 #endif /* __KERNEL__ */
 
diff --git a/include/asm-m68knommu/bitops.h b/include/asm-m68knommu/bitops.h
index f8dfb7ba2e25..f43afe1fc3b3 100644
--- a/include/asm-m68knommu/bitops.h
+++ b/include/asm-m68knommu/bitops.h
@@ -294,6 +294,8 @@ found_middle:
         return result + ffz(__swab32(tmp));
 }
 
+#define ext2_find_next_bit(addr, size, off) \
+        generic_find_next_le_bit((unsigned long *)(addr), (size), (off))
 #include <asm-generic/bitops/minix.h>
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-powerpc/bitops.h b/include/asm-powerpc/bitops.h
index 733b4af7f4f1..220d9a781ab9 100644
--- a/include/asm-powerpc/bitops.h
+++ b/include/asm-powerpc/bitops.h
@@ -359,6 +359,8 @@ static __inline__ int test_le_bit(unsigned long nr,
 unsigned long generic_find_next_zero_le_bit(const unsigned long *addr,
                                     unsigned long size, unsigned long offset);
 
+unsigned long generic_find_next_le_bit(const unsigned long *addr,
+                                    unsigned long size, unsigned long offset);
 /* Bitmap functions for the ext2 filesystem */
 
 #define ext2_set_bit(nr,addr) \
@@ -378,6 +380,8 @@ unsigned long generic_find_next_zero_le_bit(const unsigned long *addr,
 #define ext2_find_next_zero_bit(addr, size, off) \
         generic_find_next_zero_le_bit((unsigned long*)addr, size, off)
 
+#define ext2_find_next_bit(addr, size, off) \
+        generic_find_next_le_bit((unsigned long *)addr, size, off)
 /* Bitmap functions for the minix filesystem.  */
 
 #define minix_test_and_set_bit(nr,addr) \
diff --git a/include/asm-s390/bitops.h b/include/asm-s390/bitops.h
index 34d9a6357c38..dba6fecad0be 100644
--- a/include/asm-s390/bitops.h
+++ b/include/asm-s390/bitops.h
@@ -772,6 +772,8 @@ static inline int sched_find_first_bit(unsigned long *b)
         test_and_clear_bit((nr)^(__BITOPS_WORDSIZE - 8), (unsigned long *)addr)
 #define ext2_test_bit(nr, addr)      \
         test_bit((nr)^(__BITOPS_WORDSIZE - 8), (unsigned long *)addr)
+#define ext2_find_next_bit(addr, size, off) \
+        generic_find_next_le_bit((unsigned long *)(addr), (size), (off))
 
 #ifndef __s390x__
 
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index da0d83fbadc0..e98801f06dcc 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -192,6 +192,8 @@ int sync_dirty_buffer(struct buffer_head *bh);
 int submit_bh(int, struct buffer_head *);
 void write_boundary_block(struct block_device *bdev,
                         sector_t bblock, unsigned blocksize);
+int bh_uptodate_or_lock(struct buffer_head *bh);
+int bh_submit_read(struct buffer_head *bh);
 
 extern int buffer_heads_over_limit;
 
diff --git a/include/linux/ext4_fs.h b/include/linux/ext4_fs.h
index 97dd409d5f4a..1852313fc7c7 100644
--- a/include/linux/ext4_fs.h
+++ b/include/linux/ext4_fs.h
@@ -20,6 +20,8 @@
 #include <linux/blkdev.h>
 #include <linux/magic.h>
 
+#include <linux/ext4_fs_i.h>
+
 /*
  * The second extended filesystem constants/structures
  */
@@ -51,6 +53,50 @@
 #define ext4_debug(f, a...)     do {} while (0)
 #endif
 
+#define EXT4_MULTIBLOCK_ALLOCATOR       1
+
+/* prefer goal again. length */
+#define EXT4_MB_HINT_MERGE              1
+/* blocks already reserved */
+#define EXT4_MB_HINT_RESERVED           2
+/* metadata is being allocated */
+#define EXT4_MB_HINT_METADATA           4
+/* first blocks in the file */
+#define EXT4_MB_HINT_FIRST              8
+/* search for the best chunk */
+#define EXT4_MB_HINT_BEST               16
+/* data is being allocated */
+#define EXT4_MB_HINT_DATA               32
+/* don't preallocate (for tails) */
+#define EXT4_MB_HINT_NOPREALLOC         64
+/* allocate for locality group */
+#define EXT4_MB_HINT_GROUP_ALLOC        128
+/* allocate goal blocks or none */
+#define EXT4_MB_HINT_GOAL_ONLY          256
+/* goal is meaningful */
+#define EXT4_MB_HINT_TRY_GOAL           512
+
+struct ext4_allocation_request {
+        /* target inode for block we're allocating */
+        struct inode *inode;
+        /* logical block in target inode */
+        ext4_lblk_t logical;
+        /* phys. target (a hint) */
+        ext4_fsblk_t goal;
+        /* the closest logical allocated block to the left */
+        ext4_lblk_t lleft;
+        /* phys. block for ^^^ */
+        ext4_fsblk_t pleft;
+        /* the closest logical allocated block to the right */
+        ext4_lblk_t lright;
+        /* phys. block for ^^^ */
+        ext4_fsblk_t pright;
+        /* how many blocks we want to allocate */
+        unsigned long len;
+        /* flags. see above EXT4_MB_HINT_* */
+        unsigned long flags;
+};
+
 /*
  * Special inodes numbers
  */
@@ -73,8 +119,8 @@
  * Macro-instructions used to manage several block sizes
  */
 #define EXT4_MIN_BLOCK_SIZE             1024
-#define EXT4_MAX_BLOCK_SIZE             4096
-#define EXT4_MIN_BLOCK_LOG_SIZE           10
+#define EXT4_MAX_BLOCK_SIZE             65536
+#define EXT4_MIN_BLOCK_LOG_SIZE         10
 #ifdef __KERNEL__
 # define EXT4_BLOCK_SIZE(s)             ((s)->s_blocksize)
 #else
@@ -118,6 +164,11 @@ struct ext4_group_desc
         __le32  bg_block_bitmap_hi;     /* Blocks bitmap block MSB */
         __le32  bg_inode_bitmap_hi;     /* Inodes bitmap block MSB */
         __le32  bg_inode_table_hi;      /* Inodes table block MSB */
+        __le16  bg_free_blocks_count_hi;/* Free blocks count MSB */
+        __le16  bg_free_inodes_count_hi;/* Free inodes count MSB */
+        __le16  bg_used_dirs_count_hi;  /* Directories count MSB */
+        __le16  bg_itable_unused_hi;    /* Unused inodes count MSB */
+        __u32   bg_reserved2[3];
 };
 
 #define EXT4_BG_INODE_UNINIT    0x0001 /* Inode table/bitmap not in use */
@@ -178,8 +229,9 @@ struct ext4_group_desc
 #define EXT4_NOTAIL_FL                  0x00008000 /* file tail should not be merged */
 #define EXT4_DIRSYNC_FL                 0x00010000 /* dirsync behaviour (directories only) */
 #define EXT4_TOPDIR_FL                  0x00020000 /* Top of directory hierarchies*/
-#define EXT4_RESERVED_FL                0x80000000 /* reserved for ext4 lib */
+#define EXT4_HUGE_FILE_FL               0x00040000 /* Set to each huge file */
 #define EXT4_EXTENTS_FL                 0x00080000 /* Inode uses extents */
+#define EXT4_RESERVED_FL                0x80000000 /* reserved for ext4 lib */
 
 #define EXT4_FL_USER_VISIBLE            0x000BDFFF /* User visible flags */
 #define EXT4_FL_USER_MODIFIABLE         0x000380FF /* User modifiable flags */
@@ -237,6 +289,7 @@ struct ext4_new_group_data {
 #endif
 #define EXT4_IOC_GETRSVSZ               _IOR('f', 5, long)
 #define EXT4_IOC_SETRSVSZ               _IOW('f', 6, long)
+#define EXT4_IOC_MIGRATE                _IO('f', 7)
 
 /*
  * ioctl commands in 32 bit emulation
@@ -275,18 +328,18 @@ struct ext4_mount_options {
 struct ext4_inode {
         __le16  i_mode;         /* File mode */
         __le16  i_uid;          /* Low 16 bits of Owner Uid */
-        __le32  i_size;         /* Size in bytes */
+        __le32  i_size_lo;      /* Size in bytes */
         __le32  i_atime;        /* Access 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 */
         __le16  i_links_count;  /* Links count */
-        __le32  i_blocks;       /* Blocks count */
+        __le32  i_blocks_lo;    /* Blocks count */
         __le32  i_flags;        /* File flags */
         union {
                 struct {
-                        __u32  l_i_reserved1;
+                        __le32  l_i_version;
                 } linux1;
                 struct {
                         __u32  h_i_translator;
@@ -297,12 +350,12 @@ struct ext4_inode {
         } osd1;                         /* OS dependent 1 */
         __le32  i_block[EXT4_N_BLOCKS];/* Pointers to blocks */
         __le32  i_generation;   /* File version (for NFS) */
-        __le32  i_file_acl;     /* File ACL */
-        __le32  i_dir_acl;      /* Directory ACL */
+        __le32  i_file_acl_lo;  /* File ACL */
+        __le32  i_size_high;
         __le32  i_obso_faddr;   /* Obsoleted fragment address */
         union {
                 struct {
-                        __le16  l_i_reserved1;  /* Obsoleted fragment number/size which are removed in ext4 */
+                        __le16  l_i_blocks_high; /* were l_i_reserved1 */
                         __le16  l_i_file_acl_high;
                         __le16  l_i_uid_high;   /* these 2 fields */
                         __le16  l_i_gid_high;   /* were reserved2[0] */
@@ -328,9 +381,9 @@ struct ext4_inode {
         __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) */
+        __le32  i_version_hi;   /* high 32 bits for 64-bit version */
 };
 
-#define i_size_high     i_dir_acl
 
 #define EXT4_EPOCH_BITS 2
 #define EXT4_EPOCH_MASK ((1 << EXT4_EPOCH_BITS) - 1)
@@ -402,9 +455,12 @@ do {									       \
                                        raw_inode->xtime ## _extra);            \
 } while (0)
 
+#define i_disk_version osd1.linux1.l_i_version
+
 #if defined(__KERNEL__) || defined(__linux__)
 #define i_reserved1     osd1.linux1.l_i_reserved1
 #define i_file_acl_high osd2.linux2.l_i_file_acl_high
+#define i_blocks_high   osd2.linux2.l_i_blocks_high
 #define i_uid_low       i_uid
 #define i_gid_low       i_gid
 #define i_uid_high      osd2.linux2.l_i_uid_high
@@ -461,7 +517,10 @@ do {									       \
 #define EXT4_MOUNT_USRQUOTA             0x100000 /* "old" user quota */
 #define EXT4_MOUNT_GRPQUOTA             0x200000 /* "old" group quota */
 #define EXT4_MOUNT_EXTENTS              0x400000 /* Extents support */
-
+#define EXT4_MOUNT_JOURNAL_CHECKSUM     0x800000 /* Journal checksums */
+#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
+#define EXT4_MOUNT_I_VERSION            0x2000000 /* i_version support */
+#define EXT4_MOUNT_MBALLOC              0x4000000 /* Buddy allocation support */
 /* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */
 #ifndef _LINUX_EXT2_FS_H
 #define clear_opt(o, opt)               o &= ~EXT4_MOUNT_##opt
@@ -481,6 +540,7 @@ do {									       \
 #define ext4_test_bit                   ext2_test_bit
 #define ext4_find_first_zero_bit        ext2_find_first_zero_bit
 #define ext4_find_next_zero_bit         ext2_find_next_zero_bit
+#define ext4_find_next_bit              ext2_find_next_bit
 
 /*
  * Maximal mount counts between two filesystem checks
@@ -671,6 +731,7 @@ 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_HUGE_FILE        0x0008
 #define EXT4_FEATURE_RO_COMPAT_GDT_CSUM         0x0010
 #define EXT4_FEATURE_RO_COMPAT_DIR_NLINK        0x0020
 #define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE      0x0040
@@ -682,6 +743,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 #define EXT4_FEATURE_INCOMPAT_META_BG           0x0010
 #define EXT4_FEATURE_INCOMPAT_EXTENTS           0x0040 /* extents support */
 #define EXT4_FEATURE_INCOMPAT_64BIT             0x0080
+#define EXT4_FEATURE_INCOMPAT_MMP               0x0100
 #define EXT4_FEATURE_INCOMPAT_FLEX_BG           0x0200
 
 #define EXT4_FEATURE_COMPAT_SUPP        EXT2_FEATURE_COMPAT_EXT_ATTR
@@ -696,7 +758,8 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
                                          EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
                                          EXT4_FEATURE_RO_COMPAT_DIR_NLINK | \
                                          EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \
-                                         EXT4_FEATURE_RO_COMPAT_BTREE_DIR)
+                                         EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\
+                                         EXT4_FEATURE_RO_COMPAT_HUGE_FILE)
 
 /*
  * Default values for user and/or group using reserved blocks
@@ -767,6 +830,26 @@ struct ext4_dir_entry_2 {
 #define EXT4_DIR_ROUND                  (EXT4_DIR_PAD - 1)
 #define EXT4_DIR_REC_LEN(name_len)      (((name_len) + 8 + EXT4_DIR_ROUND) & \
                                          ~EXT4_DIR_ROUND)
+#define EXT4_MAX_REC_LEN                ((1<<16)-1)
+
+static inline unsigned ext4_rec_len_from_disk(__le16 dlen)
+{
+        unsigned len = le16_to_cpu(dlen);
+
+        if (len == EXT4_MAX_REC_LEN)
+                return 1 << 16;
+        return len;
+}
+
+static inline __le16 ext4_rec_len_to_disk(unsigned len)
+{
+        if (len == (1 << 16))
+                return cpu_to_le16(EXT4_MAX_REC_LEN);
+        else if (len > (1 << 16))
+                BUG();
+        return cpu_to_le16(len);
+}
+
 /*
  * Hash Tree Directory indexing
  * (c) Daniel Phillips, 2001
@@ -810,7 +893,7 @@ struct ext4_iloc
 {
         struct buffer_head *bh;
         unsigned long offset;
-        unsigned long block_group;
+        ext4_group_t block_group;
 };
 
 static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
@@ -835,7 +918,7 @@ struct dir_private_info {
 
 /* calculate the first block number of the group */
 static inline ext4_fsblk_t
-ext4_group_first_block_no(struct super_block *sb, unsigned long group_no)
+ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
 {
         return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
                 le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
@@ -866,21 +949,24 @@ extern unsigned int ext4_block_group(struct super_block *sb,
                         ext4_fsblk_t blocknr);
 extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb,
                         ext4_fsblk_t blocknr);
-extern int ext4_bg_has_super(struct super_block *sb, int group);
-extern unsigned long ext4_bg_num_gdb(struct super_block *sb, int group);
+extern int ext4_bg_has_super(struct super_block *sb, ext4_group_t group);
+extern unsigned long ext4_bg_num_gdb(struct super_block *sb,
+                        ext4_group_t group);
 extern ext4_fsblk_t ext4_new_block (handle_t *handle, struct inode *inode,
                         ext4_fsblk_t goal, int *errp);
 extern ext4_fsblk_t ext4_new_blocks (handle_t *handle, struct inode *inode,
                         ext4_fsblk_t goal, unsigned long *count, int *errp);
+extern ext4_fsblk_t ext4_new_blocks_old(handle_t *handle, struct inode *inode,
+                        ext4_fsblk_t goal, unsigned long *count, int *errp);
 extern void ext4_free_blocks (handle_t *handle, struct inode *inode,
-                        ext4_fsblk_t block, unsigned long count);
+                        ext4_fsblk_t block, unsigned long count, int metadata);
 extern void ext4_free_blocks_sb (handle_t *handle, struct super_block *sb,
                                  ext4_fsblk_t block, unsigned long count,
                                 unsigned long *pdquot_freed_blocks);
 extern ext4_fsblk_t ext4_count_free_blocks (struct super_block *);
 extern void ext4_check_blocks_bitmap (struct super_block *);
 extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
-                                                    unsigned int block_group,
+                                                    ext4_group_t block_group,
                                                     struct buffer_head ** bh);
 extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
 extern void ext4_init_block_alloc_info(struct inode *);
@@ -911,15 +997,32 @@ extern unsigned long ext4_count_dirs (struct super_block *);
 extern void ext4_check_inodes_bitmap (struct super_block *);
 extern unsigned long ext4_count_free (struct buffer_head *, unsigned);
 
+/* mballoc.c */
+extern long ext4_mb_stats;
+extern long ext4_mb_max_to_scan;
+extern int ext4_mb_init(struct super_block *, int);
+extern int ext4_mb_release(struct super_block *);
+extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
+                                struct ext4_allocation_request *, int *);
+extern int ext4_mb_reserve_blocks(struct super_block *, int);
+extern void ext4_mb_discard_inode_preallocations(struct inode *);
+extern int __init init_ext4_mballoc(void);
+extern void exit_ext4_mballoc(void);
+extern void ext4_mb_free_blocks(handle_t *, struct inode *,
+                unsigned long, unsigned long, int, unsigned long *);
+
 
 /* inode.c */
 int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
                 struct buffer_head *bh, ext4_fsblk_t blocknr);
-struct buffer_head * ext4_getblk (handle_t *, struct inode *, long, int, int *);
-struct buffer_head * ext4_bread (handle_t *, struct inode *, int, int, int *);
+struct buffer_head *ext4_getblk(handle_t *, struct inode *,
+                                                ext4_lblk_t, int, int *);
+struct buffer_head *ext4_bread(handle_t *, struct inode *,
+                                                ext4_lblk_t, int, int *);
 int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
-        sector_t iblock, unsigned long maxblocks, struct buffer_head *bh_result,
-        int create, int extend_disksize);
+                                ext4_lblk_t iblock, unsigned long maxblocks,
+                                struct buffer_head *bh_result,
+                                int create, int extend_disksize);
 
 extern void ext4_read_inode (struct inode *);
 extern int  ext4_write_inode (struct inode *, int);
@@ -943,6 +1046,9 @@ extern int ext4_ioctl (struct inode *, struct file *, unsigned int,
                        unsigned long);
 extern long ext4_compat_ioctl (struct file *, unsigned int, unsigned long);
 
+/* migrate.c */
+extern int ext4_ext_migrate(struct inode *, struct file *, unsigned int,
+                       unsigned long);
 /* namei.c */
 extern int ext4_orphan_add(handle_t *, struct inode *);
 extern int ext4_orphan_del(handle_t *, struct inode *);
@@ -965,6 +1071,12 @@ extern void ext4_abort (struct super_block *, const char *, const char *, ...)
 extern void ext4_warning (struct super_block *, const char *, const char *, ...)
         __attribute__ ((format (printf, 3, 4)));
 extern void ext4_update_dynamic_rev (struct super_block *sb);
+extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
+                                        __u32 compat);
+extern int ext4_update_rocompat_feature(handle_t *handle,
+                                        struct super_block *sb, __u32 rocompat);
+extern int ext4_update_incompat_feature(handle_t *handle,
+                                        struct super_block *sb, __u32 incompat);
 extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
                                       struct ext4_group_desc *bg);
 extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
@@ -1017,6 +1129,29 @@ static inline void ext4_r_blocks_count_set(struct ext4_super_block *es,
         es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32);
 }
 
+static inline loff_t ext4_isize(struct ext4_inode *raw_inode)
+{
+        return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
+                le32_to_cpu(raw_inode->i_size_lo);
+}
+
+static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size)
+{
+        raw_inode->i_size_lo = cpu_to_le32(i_size);
+        raw_inode->i_size_high = cpu_to_le32(i_size >> 32);
+}
+
+static inline
+struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
+                                                        ext4_group_t group)
+{
+         struct ext4_group_info ***grp_info;
+         long indexv, indexh;
+         grp_info = EXT4_SB(sb)->s_group_info;
+         indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
+         indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
+         return grp_info[indexv][indexh];
+}
 
 
 #define ext4_std_error(sb, errno)                               \
@@ -1048,7 +1183,7 @@ extern const struct inode_operations ext4_fast_symlink_inode_operations;
 extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
 extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
 extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
-                        ext4_fsblk_t iblock,
+                        ext4_lblk_t iblock,
                         unsigned long max_blocks, struct buffer_head *bh_result,
                         int create, int extend_disksize);
 extern void ext4_ext_truncate(struct inode *, struct page *);
@@ -1056,19 +1191,10 @@ 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,
-                        int create, int extend_disksize)
-{
-        if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
-                return ext4_ext_get_blocks(handle, inode, block, max_blocks,
-                                        bh, create, extend_disksize);
-        return ext4_get_blocks_handle(handle, inode, block, max_blocks, bh,
-                                        create, extend_disksize);
-}
-
-
+extern int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode,
+                        sector_t block, unsigned long max_blocks,
+                        struct buffer_head *bh, int create,
+                        int extend_disksize);
 #endif  /* __KERNEL__ */
 
 #endif  /* _LINUX_EXT4_FS_H */
diff --git a/include/linux/ext4_fs_extents.h b/include/linux/ext4_fs_extents.h
index d2045a26195d..697da4bce6c5 100644
--- a/include/linux/ext4_fs_extents.h
+++ b/include/linux/ext4_fs_extents.h
@@ -124,20 +124,6 @@ struct ext4_ext_path {
 #define EXT4_EXT_CACHE_GAP      1
 #define EXT4_EXT_CACHE_EXTENT   2
 
-/*
- * to be called by ext4_ext_walk_space()
- * negative retcode - error
- * positive retcode - signal for ext4_ext_walk_space(), see below
- * callback must return valid extent (passed or newly created)
- */
-typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *,
-                                        struct ext4_ext_cache *,
-                                        void *);
-
-#define EXT_CONTINUE    0
-#define EXT_BREAK       1
-#define EXT_REPEAT      2
-
 
 #define EXT_MAX_BLOCK   0xffffffff
 
@@ -226,6 +212,8 @@ static inline int ext4_ext_get_actual_len(struct ext4_extent *ext)
                 (le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN));
 }
 
+extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *);
+extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t);
 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,
@@ -233,8 +221,11 @@ extern int ext4_ext_try_to_merge(struct inode *inode,
                                  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 *);
-extern struct ext4_ext_path * ext4_ext_find_extent(struct inode *, int, struct ext4_ext_path *);
-
+extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
+                                                        struct ext4_ext_path *);
+extern int ext4_ext_search_left(struct inode *, struct ext4_ext_path *,
+                                                ext4_lblk_t *, ext4_fsblk_t *);
+extern int ext4_ext_search_right(struct inode *, struct ext4_ext_path *,
+                                                ext4_lblk_t *, ext4_fsblk_t *);
 #endif /* _LINUX_EXT4_EXTENTS */
 
diff --git a/include/linux/ext4_fs_i.h b/include/linux/ext4_fs_i.h
index 86ddfe2089f3..d5508d3cf290 100644
--- a/include/linux/ext4_fs_i.h
+++ b/include/linux/ext4_fs_i.h
@@ -27,6 +27,12 @@ typedef int ext4_grpblk_t;
 /* data type for filesystem-wide blocks number */
 typedef unsigned long long ext4_fsblk_t;
 
+/* data type for file logical block number */
+typedef __u32 ext4_lblk_t;
+
+/* data type for block group number */
+typedef unsigned long ext4_group_t;
+
 struct ext4_reserve_window {
         ext4_fsblk_t    _rsv_start;     /* First byte reserved */
         ext4_fsblk_t    _rsv_end;       /* Last byte reserved or 0 */
@@ -48,7 +54,7 @@ struct ext4_block_alloc_info {
          * most-recently-allocated block in this file.
          * We use this for detecting linearly ascending allocation requests.
          */
-        __u32 last_alloc_logical_block;
+        ext4_lblk_t last_alloc_logical_block;
         /*
          * Was i_next_alloc_goal in ext4_inode_info
          * is the *physical* companion to i_next_alloc_block.
@@ -67,7 +73,7 @@ struct ext4_block_alloc_info {
  */
 struct ext4_ext_cache {
         ext4_fsblk_t    ec_start;
-        __u32           ec_block;
+        ext4_lblk_t     ec_block;
         __u32           ec_len; /* must be 32bit to return holes */
         __u32           ec_type;
 };
@@ -79,7 +85,6 @@ struct ext4_inode_info {
         __le32  i_data[15];     /* unconverted */
         __u32   i_flags;
         ext4_fsblk_t    i_file_acl;
-        __u32   i_dir_acl;
         __u32   i_dtime;
 
         /*
@@ -89,13 +94,13 @@ struct ext4_inode_info {
          * place a file's data blocks near its inode block, and new inodes
          * near to their parent directory's inode.
          */
-        __u32   i_block_group;
+        ext4_group_t    i_block_group;
         __u32   i_state;                /* Dynamic state flags for ext4 */
 
         /* block reservation info */
         struct ext4_block_alloc_info *i_block_alloc_info;
 
-        __u32   i_dir_start_lookup;
+        ext4_lblk_t             i_dir_start_lookup;
 #ifdef CONFIG_EXT4DEV_FS_XATTR
         /*
          * Extended attributes can be read independently of the main file
@@ -134,16 +139,16 @@ struct ext4_inode_info {
         __u16 i_extra_isize;
 
         /*
-         * truncate_mutex is for serialising ext4_truncate() against
+         * i_data_sem is for serialising ext4_truncate() against
          * ext4_getblock().  In the 2.4 ext2 design, great chunks of inode's
          * data tree are chopped off during truncate. We can't do that in
          * ext4 because whenever we perform intermediate commits during
          * truncate, the inode and all the metadata blocks *must* be in a
          * consistent state which allows truncation of the orphans to restart
          * during recovery.  Hence we must fix the get_block-vs-truncate race
-         * by other means, so we have truncate_mutex.
+         * by other means, so we have i_data_sem.
          */
-        struct mutex truncate_mutex;
+        struct rw_semaphore i_data_sem;
         struct inode vfs_inode;
 
         unsigned long i_ext_generation;
@@ -153,6 +158,10 @@ struct ext4_inode_info {
          * struct timespec i_{a,c,m}time in the generic inode.
          */
         struct timespec i_crtime;
+
+        /* mballoc */
+        struct list_head i_prealloc_list;
+        spinlock_t i_prealloc_lock;
 };
 
 #endif  /* _LINUX_EXT4_FS_I */
diff --git a/include/linux/ext4_fs_sb.h b/include/linux/ext4_fs_sb.h
index b40e827cd495..abaae2c8cccf 100644
--- a/include/linux/ext4_fs_sb.h
+++ b/include/linux/ext4_fs_sb.h
@@ -35,9 +35,10 @@ struct ext4_sb_info {
         unsigned long s_itb_per_group;  /* Number of inode table blocks per group */
         unsigned long s_gdb_count;      /* Number of group descriptor blocks */
         unsigned long s_desc_per_block; /* Number of group descriptors per block */
-        unsigned long s_groups_count;   /* Number of groups in the fs */
+        ext4_group_t s_groups_count;    /* Number of groups in the fs */
         unsigned long s_overhead_last;  /* Last calculated overhead */
         unsigned long s_blocks_last;    /* Last seen block count */
+        loff_t s_bitmap_maxbytes;       /* max bytes for bitmap files */
         struct buffer_head * s_sbh;     /* Buffer containing the super block */
         struct ext4_super_block * s_es; /* Pointer to the super block in the buffer */
         struct buffer_head ** s_group_desc;
@@ -90,6 +91,58 @@ struct ext4_sb_info {
         unsigned long s_ext_blocks;
         unsigned long s_ext_extents;
 #endif
+
+        /* for buddy allocator */
+        struct ext4_group_info ***s_group_info;
+        struct inode *s_buddy_cache;
+        long s_blocks_reserved;
+        spinlock_t s_reserve_lock;
+        struct list_head s_active_transaction;
+        struct list_head s_closed_transaction;
+        struct list_head s_committed_transaction;
+        spinlock_t s_md_lock;
+        tid_t s_last_transaction;
+        unsigned short *s_mb_offsets, *s_mb_maxs;
+
+        /* tunables */
+        unsigned long s_stripe;
+        unsigned long s_mb_stream_request;
+        unsigned long s_mb_max_to_scan;
+        unsigned long s_mb_min_to_scan;
+        unsigned long s_mb_stats;
+        unsigned long s_mb_order2_reqs;
+        unsigned long s_mb_group_prealloc;
+        /* where last allocation was done - for stream allocation */
+        unsigned long s_mb_last_group;
+        unsigned long s_mb_last_start;
+
+        /* history to debug policy */
+        struct ext4_mb_history *s_mb_history;
+        int s_mb_history_cur;
+        int s_mb_history_max;
+        int s_mb_history_num;
+        struct proc_dir_entry *s_mb_proc;
+        spinlock_t s_mb_history_lock;
+        int s_mb_history_filter;
+
+        /* stats for buddy allocator */
+        spinlock_t s_mb_pa_lock;
+        atomic_t s_bal_reqs;    /* number of reqs with len > 1 */
+        atomic_t s_bal_success; /* we found long enough chunks */
+        atomic_t s_bal_allocated;       /* in blocks */
+        atomic_t s_bal_ex_scanned;      /* total extents scanned */
+        atomic_t s_bal_goals;   /* goal hits */
+        atomic_t s_bal_breaks;  /* too long searches */
+        atomic_t s_bal_2orders; /* 2^order hits */
+        spinlock_t s_bal_lock;
+        unsigned long s_mb_buddies_generated;
+        unsigned long long s_mb_generation_time;
+        atomic_t s_mb_lost_chunks;
+        atomic_t s_mb_preallocated;
+        atomic_t s_mb_discarded;
+
+        /* locality groups */
+        struct ext4_locality_group *s_locality_groups;
 };
 
 #endif  /* _LINUX_EXT4_FS_SB */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 21398a5d688d..a516b6716870 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -124,6 +124,7 @@ extern int dir_notify_enable;
 #define MS_SHARED       (1<<20) /* change to shared */
 #define MS_RELATIME     (1<<21) /* Update atime relative to mtime/ctime. */
 #define MS_KERNMOUNT    (1<<22) /* this is a kern_mount call */
+#define MS_I_VERSION    (1<<23) /* Update inode I_version field */
 #define MS_ACTIVE       (1<<30)
 #define MS_NOUSER       (1<<31)
 
@@ -173,6 +174,7 @@ extern int dir_notify_enable;
                                         ((inode)->i_flags & (S_SYNC|S_DIRSYNC)))
 #define IS_MANDLOCK(inode)      __IS_FLG(inode, MS_MANDLOCK)
 #define IS_NOATIME(inode)   __IS_FLG(inode, MS_RDONLY|MS_NOATIME)
+#define IS_I_VERSION(inode)   __IS_FLG(inode, MS_I_VERSION)
 
 #define IS_NOQUOTA(inode)       ((inode)->i_flags & S_NOQUOTA)
 #define IS_APPEND(inode)        ((inode)->i_flags & S_APPEND)
@@ -599,7 +601,7 @@ struct inode {
         uid_t                   i_uid;
         gid_t                   i_gid;
         dev_t                   i_rdev;
-        unsigned long           i_version;
+        u64                     i_version;
         loff_t                  i_size;
 #ifdef __NEED_I_SIZE_ORDERED
         seqcount_t              i_size_seqcount;
@@ -1394,6 +1396,21 @@ static inline void inode_dec_link_count(struct inode *inode)
         mark_inode_dirty(inode);
 }
 
+/**
+ * inode_inc_iversion - increments i_version
+ * @inode: inode that need to be updated
+ *
+ * Every time the inode is modified, the i_version field will be incremented.
+ * The filesystem has to be mounted with i_version flag
+ */
+
+static inline void inode_inc_iversion(struct inode *inode)
+{
+       spin_lock(&inode->i_lock);
+       inode->i_version++;
+       spin_unlock(&inode->i_lock);
+}
+
 extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry);
 static inline void file_accessed(struct file *file)
 {
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 06ef11457051..2cbf6fdb1799 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -149,6 +149,28 @@ typedef struct journal_header_s
         __be32          h_sequence;
 } journal_header_t;
 
+/*
+ * Checksum types.
+ */
+#define JBD2_CRC32_CHKSUM   1
+#define JBD2_MD5_CHKSUM     2
+#define JBD2_SHA1_CHKSUM    3
+
+#define JBD2_CRC32_CHKSUM_SIZE 4
+
+#define JBD2_CHECKSUM_BYTES (32 / sizeof(u32))
+/*
+ * Commit block header for storing transactional checksums:
+ */
+struct commit_header {
+        __be32          h_magic;
+        __be32          h_blocktype;
+        __be32          h_sequence;
+        unsigned char   h_chksum_type;
+        unsigned char   h_chksum_size;
+        unsigned char   h_padding[2];
+        __be32          h_chksum[JBD2_CHECKSUM_BYTES];
+};
 
 /*
  * The block tag: used to describe a single buffer in the journal.
@@ -242,31 +264,25 @@ typedef struct journal_superblock_s
         ((j)->j_format_version >= 2 &&                                  \
          ((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask))))
 
-#define JBD2_FEATURE_INCOMPAT_REVOKE    0x00000001
-#define JBD2_FEATURE_INCOMPAT_64BIT     0x00000002
+#define JBD2_FEATURE_COMPAT_CHECKSUM    0x00000001
+
+#define JBD2_FEATURE_INCOMPAT_REVOKE            0x00000001
+#define JBD2_FEATURE_INCOMPAT_64BIT             0x00000002
+#define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT      0x00000004
 
 /* Features known to this kernel version: */
-#define JBD2_KNOWN_COMPAT_FEATURES      0
+#define JBD2_KNOWN_COMPAT_FEATURES      JBD2_FEATURE_COMPAT_CHECKSUM
 #define JBD2_KNOWN_ROCOMPAT_FEATURES    0
 #define JBD2_KNOWN_INCOMPAT_FEATURES    (JBD2_FEATURE_INCOMPAT_REVOKE | \
-                                         JBD2_FEATURE_INCOMPAT_64BIT)
+                                        JBD2_FEATURE_INCOMPAT_64BIT | \
+                                        JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)
 
 #ifdef __KERNEL__
 
 #include <linux/fs.h>
 #include <linux/sched.h>
 
-#define JBD2_ASSERTIONS
-#ifdef JBD2_ASSERTIONS
-#define J_ASSERT(assert)                                                \
-do {                                                                    \
-        if (!(assert)) {                                                \
-                printk (KERN_EMERG                                      \
-                        "Assertion failure in %s() at %s:%d: \"%s\"\n", \
-                        __FUNCTION__, __FILE__, __LINE__, # assert);    \
-                BUG();                                                  \
-        }                                                               \
-} while (0)
+#define J_ASSERT(assert)        BUG_ON(!(assert))
 
 #if defined(CONFIG_BUFFER_DEBUG)
 void buffer_assertion_failure(struct buffer_head *bh);
@@ -282,10 +298,6 @@ void buffer_assertion_failure(struct buffer_head *bh);
 #define J_ASSERT_JH(jh, expr)   J_ASSERT(expr)
 #endif
 
-#else
-#define J_ASSERT(assert)        do { } while (0)
-#endif          /* JBD2_ASSERTIONS */
-
 #if defined(JBD2_PARANOID_IOFAIL)
 #define J_EXPECT(expr, why...)          J_ASSERT(expr)
 #define J_EXPECT_BH(bh, expr, why...)   J_ASSERT_BH(bh, expr)
@@ -406,9 +418,23 @@ struct handle_s
         unsigned int    h_sync:         1;      /* sync-on-close */
         unsigned int    h_jdata:        1;      /* force data journaling */
         unsigned int    h_aborted:      1;      /* fatal error on handle */
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+        struct lockdep_map      h_lockdep_map;
+#endif
 };
 
 
+/*
+ * Some stats for checkpoint phase
+ */
+struct transaction_chp_stats_s {
+        unsigned long           cs_chp_time;
+        unsigned long           cs_forced_to_close;
+        unsigned long           cs_written;
+        unsigned long           cs_dropped;
+};
+
 /* The transaction_t type is the guts of the journaling mechanism.  It
  * tracks a compound transaction through its various states:
  *
@@ -456,6 +482,8 @@ struct transaction_s
         /*
          * Transaction's current state
          * [no locking - only kjournald2 alters this]
+         * [j_list_lock] guards transition of a transaction into T_FINISHED
+         * state and subsequent call of __jbd2_journal_drop_transaction()
          * FIXME: needs barriers
          * KLUDGE: [use j_state_lock]
          */
@@ -544,6 +572,21 @@ struct transaction_s
         spinlock_t              t_handle_lock;
 
         /*
+         * Longest time some handle had to wait for running transaction
+         */
+        unsigned long           t_max_wait;
+
+        /*
+         * When transaction started
+         */
+        unsigned long           t_start;
+
+        /*
+         * Checkpointing stats [j_checkpoint_sem]
+         */
+        struct transaction_chp_stats_s t_chp_stats;
+
+        /*
          * Number of outstanding updates running on this transaction
          * [t_handle_lock]
          */
@@ -574,6 +617,39 @@ struct transaction_s
 
 };
 
+struct transaction_run_stats_s {
+        unsigned long           rs_wait;
+        unsigned long           rs_running;
+        unsigned long           rs_locked;
+        unsigned long           rs_flushing;
+        unsigned long           rs_logging;
+
+        unsigned long           rs_handle_count;
+        unsigned long           rs_blocks;
+        unsigned long           rs_blocks_logged;
+};
+
+struct transaction_stats_s {
+        int                     ts_type;
+        unsigned long           ts_tid;
+        union {
+                struct transaction_run_stats_s run;
+                struct transaction_chp_stats_s chp;
+        } u;
+};
+
+#define JBD2_STATS_RUN          1
+#define JBD2_STATS_CHECKPOINT   2
+
+static inline unsigned long
+jbd2_time_diff(unsigned long start, unsigned long end)
+{
+        if (end >= start)
+                return end - start;
+
+        return end + (MAX_JIFFY_OFFSET - start);
+}
+
 /**
  * struct journal_s - The journal_s type is the concrete type associated with
  *     journal_t.
@@ -635,6 +711,12 @@ struct transaction_s
  * @j_wbufsize: maximum number of buffer_heads allowed in j_wbuf, the
  *      number that will fit in j_blocksize
  * @j_last_sync_writer: most recent pid which did a synchronous write
+ * @j_history: Buffer storing the transactions statistics history
+ * @j_history_max: Maximum number of transactions in the statistics history
+ * @j_history_cur: Current number of transactions in the statistics history
+ * @j_history_lock: Protect the transactions statistics history
+ * @j_proc_entry: procfs entry for the jbd statistics directory
+ * @j_stats: Overall statistics
  * @j_private: An opaque pointer to fs-private information.
  */
 
@@ -827,6 +909,19 @@ struct journal_s
         pid_t                   j_last_sync_writer;
 
         /*
+         * Journal statistics
+         */
+        struct transaction_stats_s *j_history;
+        int                     j_history_max;
+        int                     j_history_cur;
+        /*
+         * Protect the transactions statistics history
+         */
+        spinlock_t              j_history_lock;
+        struct proc_dir_entry   *j_proc_entry;
+        struct transaction_stats_s j_stats;
+
+        /*
          * An opaque pointer to fs-private information.  ext3 puts its
          * superblock pointer here
          */
@@ -932,6 +1027,8 @@ extern int	   jbd2_journal_check_available_features
                    (journal_t *, unsigned long, unsigned long, unsigned long);
 extern int         jbd2_journal_set_features
                    (journal_t *, unsigned long, unsigned long, unsigned long);
+extern void        jbd2_journal_clear_features
+                   (journal_t *, unsigned long, unsigned long, unsigned long);
 extern int         jbd2_journal_create     (journal_t *);
 extern int         jbd2_journal_load       (journal_t *journal);
 extern void        jbd2_journal_destroy    (journal_t *);