#define OCFS2_EXTENT_BLOCK_SIGNATURE "EXBLK01"
#define OCFS2_GROUP_DESC_SIGNATURE "GROUP01"
#define OCFS2_XATTR_BLOCK_SIGNATURE "XATTR01"
+#define OCFS2_DIR_TRAILER_SIGNATURE "DIRTRL1"
+#define OCFS2_DX_ROOT_SIGNATURE "DXDIR01"
+#define OCFS2_DX_LEAF_SIGNATURE "DXLEAF1"
+#define OCFS2_REFCOUNT_BLOCK_SIGNATURE "REFCNT1"
/* Compatibility flags */
#define OCFS2_HAS_COMPAT_FEATURE(sb,mask) \
| OCFS2_FEATURE_INCOMPAT_INLINE_DATA \
| OCFS2_FEATURE_INCOMPAT_EXTENDED_SLOT_MAP \
| OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK \
- | OCFS2_FEATURE_INCOMPAT_XATTR)
-#define OCFS2_FEATURE_RO_COMPAT_SUPP (OCFS2_FEATURE_RO_COMPAT_UNWRITTEN)
+ | OCFS2_FEATURE_INCOMPAT_XATTR \
+ | OCFS2_FEATURE_INCOMPAT_META_ECC \
+ | OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS \
+ | OCFS2_FEATURE_INCOMPAT_REFCOUNT_TREE)
+#define OCFS2_FEATURE_RO_COMPAT_SUPP (OCFS2_FEATURE_RO_COMPAT_UNWRITTEN \
+ | OCFS2_FEATURE_RO_COMPAT_USRQUOTA \
+ | OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)
/*
* Heartbeat-only devices are missing journals and other files. The
/* Support for extended attributes */
#define OCFS2_FEATURE_INCOMPAT_XATTR 0x0200
+/* Support for indexed directores */
+#define OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS 0x0400
+
+/* Metadata checksum and error correction */
+#define OCFS2_FEATURE_INCOMPAT_META_ECC 0x0800
+
+/* Refcount tree support */
+#define OCFS2_FEATURE_INCOMPAT_REFCOUNT_TREE 0x1000
+
/*
* backup superblock flag is used to indicate that this volume
* has backup superblocks.
#define OCFS2_HAS_XATTR_FL (0x0002)
#define OCFS2_INLINE_XATTR_FL (0x0004)
#define OCFS2_INDEXED_DIR_FL (0x0008)
+#define OCFS2_HAS_REFCOUNT_FL (0x0010)
/* Inode attributes, keep in sync with EXT2 */
#define OCFS2_SECRM_FL (0x00000001) /* Secure deletion */
/*
* Extent record flags (e_node.leaf.flags)
*/
-#define OCFS2_EXT_UNWRITTEN (0x01) /* Extent is allocated but
- * unwritten */
-
-/*
- * ioctl commands
- */
-#define OCFS2_IOC_GETFLAGS _IOR('f', 1, long)
-#define OCFS2_IOC_SETFLAGS _IOW('f', 2, long)
-#define OCFS2_IOC32_GETFLAGS _IOR('f', 1, int)
-#define OCFS2_IOC32_SETFLAGS _IOW('f', 2, int)
-
-/*
- * Space reservation / allocation / free ioctls and argument structure
- * are designed to be compatible with XFS.
- *
- * ALLOCSP* and FREESP* are not and will never be supported, but are
- * included here for completeness.
- */
-struct ocfs2_space_resv {
- __s16 l_type;
- __s16 l_whence;
- __s64 l_start;
- __s64 l_len; /* len == 0 means until end of file */
- __s32 l_sysid;
- __u32 l_pid;
- __s32 l_pad[4]; /* reserve area */
-};
-
-#define OCFS2_IOC_ALLOCSP _IOW ('X', 10, struct ocfs2_space_resv)
-#define OCFS2_IOC_FREESP _IOW ('X', 11, struct ocfs2_space_resv)
-#define OCFS2_IOC_RESVSP _IOW ('X', 40, struct ocfs2_space_resv)
-#define OCFS2_IOC_UNRESVSP _IOW ('X', 41, struct ocfs2_space_resv)
-#define OCFS2_IOC_ALLOCSP64 _IOW ('X', 36, struct ocfs2_space_resv)
-#define OCFS2_IOC_FREESP64 _IOW ('X', 37, struct ocfs2_space_resv)
-#define OCFS2_IOC_RESVSP64 _IOW ('X', 42, struct ocfs2_space_resv)
-#define OCFS2_IOC_UNRESVSP64 _IOW ('X', 43, struct ocfs2_space_resv)
-
-/* Used to pass group descriptor data when online resize is done */
-struct ocfs2_new_group_input {
- __u64 group; /* Group descriptor's blkno. */
- __u32 clusters; /* Total number of clusters in this group */
- __u32 frees; /* Total free clusters in this group */
- __u16 chain; /* Chain for this group */
- __u16 reserved1;
- __u32 reserved2;
-};
-
-#define OCFS2_IOC_GROUP_EXTEND _IOW('o', 1, int)
-#define OCFS2_IOC_GROUP_ADD _IOW('o', 2,struct ocfs2_new_group_input)
-#define OCFS2_IOC_GROUP_ADD64 _IOW('o', 3,struct ocfs2_new_group_input)
+#define OCFS2_EXT_UNWRITTEN (0x01) /* Extent is allocated but
+ * unwritten */
+#define OCFS2_EXT_REFCOUNTED (0x02) /* Extent is reference
+ * counted in an associated
+ * refcount tree */
/*
* Journal Flags (ocfs2_dinode.id1.journal1.i_flags)
#define OCFS2_DIR_REC_LEN(name_len) (((name_len) + OCFS2_DIR_MEMBER_LEN + \
OCFS2_DIR_ROUND) & \
~OCFS2_DIR_ROUND)
+#define OCFS2_DIR_MIN_REC_LEN OCFS2_DIR_REC_LEN(1)
#define OCFS2_LINK_MAX 32000
+#define OCFS2_DX_LINK_MAX ((1U << 31) - 1U)
+#define OCFS2_LINKS_HI_SHIFT 16
+#define OCFS2_DX_ENTRIES_MAX (0xffffffffU)
#define S_SHIFT 12
static unsigned char ocfs2_type_by_mode[S_IFMT >> S_SHIFT] = {
#define OCFS2_RAW_SB(dinode) (&((dinode)->id2.i_super))
/*
+ * Block checking structure. This is used in metadata to validate the
+ * contents. If OCFS2_FEATURE_INCOMPAT_META_ECC is not set, it is all
+ * zeros.
+ */
+struct ocfs2_block_check {
+/*00*/ __le32 bc_crc32e; /* 802.3 Ethernet II CRC32 */
+ __le16 bc_ecc; /* Single-error-correction parity vector.
+ This is a simple Hamming code dependant
+ on the blocksize. OCFS2's maximum
+ blocksize, 4K, requires 16 parity bits,
+ so we fit in __le16. */
+ __le16 bc_reserved1;
+/*08*/
+};
+
+/*
* On disk extent record for OCFS2
* It describes a range of clusters on disk.
*
struct ocfs2_extent_block
{
/*00*/ __u8 h_signature[8]; /* Signature for verification */
- __le64 h_reserved1;
+ struct ocfs2_block_check h_check; /* Error checking */
/*10*/ __le16 h_suballoc_slot; /* Slot suballocator this
extent_header belongs to */
__le16 h_suballoc_bit; /* Bit offset in suballocator
/*B8*/ __le16 s_xattr_inline_size; /* extended attribute inline size
for this fs*/
__le16 s_reserved0;
- __le32 s_reserved1;
-/*C0*/ __le64 s_reserved2[16]; /* Fill out superblock */
+ __le32 s_dx_seed[3]; /* seed[0-2] for dx dir hash.
+ * s_uuid_hash serves as seed[3]. */
+/*C0*/ __le64 s_reserved2[15]; /* Fill out superblock */
/*140*/
/*
belongs to */
__le16 i_suballoc_bit; /* Bit offset in suballocator
block group */
-/*10*/ __le16 i_reserved0;
+/*10*/ __le16 i_links_count_hi; /* High 16 bits of links count */
__le16 i_xattr_inline_size;
__le32 i_clusters; /* Cluster count */
__le32 i_uid; /* Owner UID */
was set in i_flags */
__le16 i_dyn_features;
__le64 i_xattr_loc;
-/*80*/ __le64 i_reserved2[7];
+/*80*/ struct ocfs2_block_check i_check; /* Error checking */
+/*88*/ __le64 i_dx_root; /* Pointer to dir index root block */
+/*90*/ __le64 i_refcount_loc;
+ __le64 i_reserved2[4];
/*B8*/ union {
__le64 i_pad1; /* Generic way to refer to this
64bit union */
} __attribute__ ((packed));
/*
+ * Per-block record for the unindexed directory btree. This is carefully
+ * crafted so that the rec_len and name_len records of an ocfs2_dir_entry are
+ * mirrored. That way, the directory manipulation code needs a minimal amount
+ * of update.
+ *
+ * NOTE: Keep this structure aligned to a multiple of 4 bytes.
+ */
+struct ocfs2_dir_block_trailer {
+/*00*/ __le64 db_compat_inode; /* Always zero. Was inode */
+
+ __le16 db_compat_rec_len; /* Backwards compatible with
+ * ocfs2_dir_entry. */
+ __u8 db_compat_name_len; /* Always zero. Was name_len */
+ __u8 db_reserved0;
+ __le16 db_reserved1;
+ __le16 db_free_rec_len; /* Size of largest empty hole
+ * in this block. (unused) */
+/*10*/ __u8 db_signature[8]; /* Signature for verification */
+ __le64 db_reserved2;
+ __le64 db_free_next; /* Next block in list (unused) */
+/*20*/ __le64 db_blkno; /* Offset on disk, in blocks */
+ __le64 db_parent_dinode; /* dinode which owns me, in
+ blocks */
+/*30*/ struct ocfs2_block_check db_check; /* Error checking */
+/*40*/
+};
+
+ /*
+ * A directory entry in the indexed tree. We don't store the full name here,
+ * but instead provide a pointer to the full dirent in the unindexed tree.
+ *
+ * We also store name_len here so as to reduce the number of leaf blocks we
+ * need to search in case of collisions.
+ */
+struct ocfs2_dx_entry {
+ __le32 dx_major_hash; /* Used to find logical
+ * cluster in index */
+ __le32 dx_minor_hash; /* Lower bits used to find
+ * block in cluster */
+ __le64 dx_dirent_blk; /* Physical block in unindexed
+ * tree holding this dirent. */
+};
+
+struct ocfs2_dx_entry_list {
+ __le32 de_reserved;
+ __le16 de_count; /* Maximum number of entries
+ * possible in de_entries */
+ __le16 de_num_used; /* Current number of
+ * de_entries entries */
+ struct ocfs2_dx_entry de_entries[0]; /* Indexed dir entries
+ * in a packed array of
+ * length de_num_used */
+};
+
+#define OCFS2_DX_FLAG_INLINE 0x01
+
+/*
+ * A directory indexing block. Each indexed directory has one of these,
+ * pointed to by ocfs2_dinode.
+ *
+ * This block stores an indexed btree root, and a set of free space
+ * start-of-list pointers.
+ */
+struct ocfs2_dx_root_block {
+ __u8 dr_signature[8]; /* Signature for verification */
+ struct ocfs2_block_check dr_check; /* Error checking */
+ __le16 dr_suballoc_slot; /* Slot suballocator this
+ * block belongs to. */
+ __le16 dr_suballoc_bit; /* Bit offset in suballocator
+ * block group */
+ __le32 dr_fs_generation; /* Must match super block */
+ __le64 dr_blkno; /* Offset on disk, in blocks */
+ __le64 dr_last_eb_blk; /* Pointer to last
+ * extent block */
+ __le32 dr_clusters; /* Clusters allocated
+ * to the indexed tree. */
+ __u8 dr_flags; /* OCFS2_DX_FLAG_* flags */
+ __u8 dr_reserved0;
+ __le16 dr_reserved1;
+ __le64 dr_dir_blkno; /* Pointer to parent inode */
+ __le32 dr_num_entries; /* Total number of
+ * names stored in
+ * this directory.*/
+ __le32 dr_reserved2;
+ __le64 dr_free_blk; /* Pointer to head of free
+ * unindexed block list. */
+ __le64 dr_reserved3[15];
+ union {
+ struct ocfs2_extent_list dr_list; /* Keep this aligned to 128
+ * bits for maximum space
+ * efficiency. */
+ struct ocfs2_dx_entry_list dr_entries; /* In-root-block list of
+ * entries. We grow out
+ * to extents if this
+ * gets too big. */
+ };
+};
+
+/*
+ * The header of a leaf block in the indexed tree.
+ */
+struct ocfs2_dx_leaf {
+ __u8 dl_signature[8];/* Signature for verification */
+ struct ocfs2_block_check dl_check; /* Error checking */
+ __le64 dl_blkno; /* Offset on disk, in blocks */
+ __le32 dl_fs_generation;/* Must match super block */
+ __le32 dl_reserved0;
+ __le64 dl_reserved1;
+ struct ocfs2_dx_entry_list dl_list;
+};
+
+/*
* On disk allocator group structure for OCFS2
*/
struct ocfs2_group_desc
/*20*/ __le64 bg_parent_dinode; /* dinode which owns me, in
blocks */
__le64 bg_blkno; /* Offset on disk, in blocks */
-/*30*/ __le64 bg_reserved2[2];
+/*30*/ struct ocfs2_block_check bg_check; /* Error checking */
+ __le64 bg_reserved2;
/*40*/ __u8 bg_bitmap[0];
};
+struct ocfs2_refcount_rec {
+/*00*/ __le64 r_cpos; /* Physical offset, in clusters */
+ __le32 r_clusters; /* Clusters covered by this extent */
+ __le32 r_refcount; /* Reference count of this extent */
+/*10*/
+};
+#define OCFS2_32BIT_POS_MASK (0xffffffffULL)
+
+#define OCFS2_REFCOUNT_LEAF_FL (0x00000001)
+#define OCFS2_REFCOUNT_TREE_FL (0x00000002)
+
+struct ocfs2_refcount_list {
+/*00*/ __le16 rl_count; /* Maximum number of entries possible
+ in rl_records */
+ __le16 rl_used; /* Current number of used records */
+ __le32 rl_reserved2;
+ __le64 rl_reserved1; /* Pad to sizeof(ocfs2_refcount_record) */
+/*10*/ struct ocfs2_refcount_rec rl_recs[0]; /* Refcount records */
+};
+
+
+struct ocfs2_refcount_block {
+/*00*/ __u8 rf_signature[8]; /* Signature for verification */
+ __le16 rf_suballoc_slot; /* Slot suballocator this block
+ belongs to */
+ __le16 rf_suballoc_bit; /* Bit offset in suballocator
+ block group */
+ __le32 rf_fs_generation; /* Must match superblock */
+/*10*/ __le64 rf_blkno; /* Offset on disk, in blocks */
+ __le64 rf_parent; /* Parent block, only valid if
+ OCFS2_REFCOUNT_LEAF_FL is set in
+ rf_flags */
+/*20*/ struct ocfs2_block_check rf_check; /* Error checking */
+ __le64 rf_last_eb_blk; /* Pointer to last extent block */
+/*30*/ __le32 rf_count; /* Number of inodes sharing this
+ refcount tree */
+ __le32 rf_flags; /* See the flags above */
+ __le32 rf_clusters; /* clusters covered by refcount tree. */
+ __le32 rf_cpos; /* cluster offset in refcount tree.*/
+/*40*/ __le32 rf_generation; /* generation number. all be the same
+ * for the same refcount tree. */
+ __le32 rf_reserved0;
+ __le64 rf_reserved1[7];
+/*80*/ union {
+ struct ocfs2_refcount_list rf_records; /* List of refcount
+ records */
+ struct ocfs2_extent_list rf_list; /* Extent record list,
+ only valid if
+ OCFS2_REFCOUNT_TREE_FL
+ is set in rf_flags */
+ };
+/* Actual on-disk size is one block */
+};
+
/*
* On disk extended attribute structure for OCFS2.
*/
in this extent record,
only valid in the first
bucket. */
- __le64 xh_csum;
+ struct ocfs2_block_check xh_check; /* Error checking
+ (Note, this is only
+ used for xattr
+ buckets. A block uses
+ xb_check and sets
+ this field to zero.) */
struct ocfs2_xattr_entry xh_entries[0]; /* xattr entry list. */
};
block group */
__le32 xb_fs_generation; /* Must match super block */
/*10*/ __le64 xb_blkno; /* Offset on disk, in blocks */
- __le64 xb_csum;
+ struct ocfs2_block_check xb_check; /* Error checking */
/*20*/ __le16 xb_flags; /* Indicates whether this block contains
real xattr or a xattr tree. */
__le16 xb_reserved0;
/* Header of one chunk of a quota file */
struct ocfs2_local_disk_chunk {
__le32 dqc_free; /* Number of free entries in the bitmap */
- u8 dqc_bitmap[0]; /* Bitmap of entries in the corresponding
+ __u8 dqc_bitmap[0]; /* Bitmap of entries in the corresponding
* chunk of quota file */
};
/*10*/ __le64 dqb_inodemod; /* Change in the amount of used inodes */
};
+
+/*
+ * The quota trailer lives at the end of each quota block.
+ */
+
+struct ocfs2_disk_dqtrailer {
+/*00*/ struct ocfs2_block_check dq_check; /* Error checking */
+/*08*/ /* Cannot be larger than OCFS2_QBLK_RESERVED_SPACE */
+};
+
+static inline struct ocfs2_disk_dqtrailer *ocfs2_block_dqtrailer(int blocksize,
+ void *buf)
+{
+ char *ptr = buf;
+ ptr += blocksize - OCFS2_QBLK_RESERVED_SPACE;
+
+ return (struct ocfs2_disk_dqtrailer *)ptr;
+}
+
#ifdef __KERNEL__
static inline int ocfs2_fast_symlink_chars(struct super_block *sb)
{
offsetof(struct ocfs2_dinode, id2.i_symlink);
}
-static inline int ocfs2_max_inline_data(struct super_block *sb)
-{
- return sb->s_blocksize -
- offsetof(struct ocfs2_dinode, id2.i_data.id_data);
-}
-
static inline int ocfs2_max_inline_data_with_xattr(struct super_block *sb,
struct ocfs2_dinode *di)
{
return size / sizeof(struct ocfs2_extent_rec);
}
+static inline int ocfs2_extent_recs_per_dx_root(struct super_block *sb)
+{
+ int size;
+
+ size = sb->s_blocksize -
+ offsetof(struct ocfs2_dx_root_block, dr_list.l_recs);
+
+ return size / sizeof(struct ocfs2_extent_rec);
+}
+
static inline int ocfs2_chain_recs_per_inode(struct super_block *sb)
{
int size;
return size / sizeof(struct ocfs2_extent_rec);
}
+static inline int ocfs2_dx_entries_per_leaf(struct super_block *sb)
+{
+ int size;
+
+ size = sb->s_blocksize -
+ offsetof(struct ocfs2_dx_leaf, dl_list.de_entries);
+
+ return size / sizeof(struct ocfs2_dx_entry);
+}
+
+static inline int ocfs2_dx_entries_per_root(struct super_block *sb)
+{
+ int size;
+
+ size = sb->s_blocksize -
+ offsetof(struct ocfs2_dx_root_block, dr_entries.de_entries);
+
+ return size / sizeof(struct ocfs2_dx_entry);
+}
+
static inline u16 ocfs2_local_alloc_size(struct super_block *sb)
{
u16 size;
return size / sizeof(struct ocfs2_extent_rec);
}
+
+static inline u16 ocfs2_extent_recs_per_rb(struct super_block *sb)
+{
+ int size;
+
+ size = sb->s_blocksize -
+ offsetof(struct ocfs2_refcount_block, rf_list.l_recs);
+
+ return size / sizeof(struct ocfs2_extent_rec);
+}
+
+static inline u16 ocfs2_refcount_recs_per_rb(struct super_block *sb)
+{
+ int size;
+
+ size = sb->s_blocksize -
+ offsetof(struct ocfs2_refcount_block, rf_records.rl_recs);
+
+ return size / sizeof(struct ocfs2_refcount_rec);
+}
+
+static inline u32
+ocfs2_get_ref_rec_low_cpos(const struct ocfs2_refcount_rec *rec)
+{
+ return le64_to_cpu(rec->r_cpos) & OCFS2_32BIT_POS_MASK;
+}
#else
static inline int ocfs2_fast_symlink_chars(int blocksize)
{
return blocksize - offsetof(struct ocfs2_dinode, id2.i_symlink);
}
-static inline int ocfs2_max_inline_data(int blocksize)
+static inline int ocfs2_max_inline_data_with_xattr(int blocksize,
+ struct ocfs2_dinode *di)
{
- return blocksize - offsetof(struct ocfs2_dinode, id2.i_data.id_data);
+ if (di && (di->i_dyn_features & OCFS2_INLINE_XATTR_FL))
+ return blocksize -
+ offsetof(struct ocfs2_dinode, id2.i_data.id_data) -
+ di->i_xattr_inline_size;
+ else
+ return blocksize -
+ offsetof(struct ocfs2_dinode, id2.i_data.id_data);
}
static inline int ocfs2_extent_recs_per_inode(int blocksize)
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff