#include <linux/workqueue.h>
#include <linux/kref.h>
#include <linux/mutex.h>
-#include <linux/jbd.h>
+#include <linux/lockdep.h>
+#include <linux/jbd2.h>
/* For union ocfs2_dlm_lksb */
#include "stackglue.h"
#include "ocfs2_fs.h"
#include "ocfs2_lockid.h"
+#include "ocfs2_ioctl.h"
+
+/* For struct ocfs2_blockcheck_stats */
+#include "blockcheck.h"
+
+
+/* Caching of metadata buffers */
/* Most user visible OCFS2 inodes will have very few pieces of
* metadata, but larger files (including bitmaps, etc) must be taken
* into account when designing an access scheme. We allow a small
* amount of inlined blocks to be stored on an array and grow the
* structure into a rb tree when necessary. */
-#define OCFS2_INODE_MAX_CACHE_ARRAY 2
+#define OCFS2_CACHE_INFO_MAX_ARRAY 2
+
+/* Flags for ocfs2_caching_info */
+enum ocfs2_caching_info_flags {
+ /* Indicates that the metadata cache is using the inline array */
+ OCFS2_CACHE_FL_INLINE = 1<<1,
+};
+
+struct ocfs2_caching_operations;
struct ocfs2_caching_info {
+ /*
+ * The parent structure provides the locks, but because the
+ * parent structure can differ, it provides locking operations
+ * to struct ocfs2_caching_info.
+ */
+ const struct ocfs2_caching_operations *ci_ops;
+
+ /* next two are protected by trans_inc_lock */
+ /* which transaction were we created on? Zero if none. */
+ unsigned long ci_created_trans;
+ /* last transaction we were a part of. */
+ unsigned long ci_last_trans;
+
+ /* Cache structures */
+ unsigned int ci_flags;
unsigned int ci_num_cached;
union {
- sector_t ci_array[OCFS2_INODE_MAX_CACHE_ARRAY];
+ sector_t ci_array[OCFS2_CACHE_INFO_MAX_ARRAY];
struct rb_root ci_tree;
} ci_cache;
};
+/*
+ * Need this prototype here instead of in uptodate.h because journal.h
+ * uses it.
+ */
+struct super_block *ocfs2_metadata_cache_get_super(struct ocfs2_caching_info *ci);
/* this limits us to 256 nodes
* if we need more, we can do a kmalloc for the map */
};
/* ocfs2_lock_res->l_flags flags. */
-#define OCFS2_LOCK_ATTACHED (0x00000001) /* have we initialized
+#define OCFS2_LOCK_ATTACHED (0x00000001) /* we have initialized
* the lvb */
#define OCFS2_LOCK_BUSY (0x00000002) /* we are currently in
* dlm_lock */
#define OCFS2_LOCK_PENDING (0x00000400) /* This lockres is pending a
call to dlm_lock. Only
exists with BUSY set. */
+#define OCFS2_LOCK_UPCONVERT_FINISHING (0x00000800) /* blocks the dc thread
+ * from downconverting
+ * before the upconvert
+ * has completed */
struct ocfs2_lock_res_ops;
int l_level;
unsigned int l_ro_holders;
unsigned int l_ex_holders;
- union ocfs2_dlm_lksb l_lksb;
+ struct ocfs2_dlm_lksb l_lksb;
/* used from AST/BAST funcs. */
enum ocfs2_ast_action l_action;
unsigned int l_lock_max_exmode; /* Max wait for EX */
unsigned int l_lock_refresh; /* Disk refreshes */
#endif
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ struct lockdep_map l_lockdep_map;
+#endif
+};
+
+enum ocfs2_orphan_scan_state {
+ ORPHAN_SCAN_ACTIVE,
+ ORPHAN_SCAN_INACTIVE
+};
+
+struct ocfs2_orphan_scan {
+ struct mutex os_lock;
+ struct ocfs2_super *os_osb;
+ struct ocfs2_lock_res os_lockres; /* lock to synchronize scans */
+ struct delayed_work os_orphan_scan_work;
+ struct timespec os_scantime; /* time this node ran the scan */
+ u32 os_count; /* tracks node specific scans */
+ u32 os_seqno; /* tracks cluster wide scans */
+ atomic_t os_state; /* ACTIVE or INACTIVE */
};
struct ocfs2_dlm_debug {
{
VOLUME_INIT = 0,
VOLUME_MOUNTED,
+ VOLUME_MOUNTED_QUOTAS,
VOLUME_DISMOUNTED,
VOLUME_DISABLED
};
OCFS2_MOUNT_DATA_WRITEBACK = 1 << 4, /* No data ordering */
OCFS2_MOUNT_LOCALFLOCKS = 1 << 5, /* No cluster aware user file locks */
OCFS2_MOUNT_NOUSERXATTR = 1 << 6, /* No user xattr */
+ OCFS2_MOUNT_INODE64 = 1 << 7, /* Allow inode numbers > 2^32 */
+ OCFS2_MOUNT_POSIX_ACL = 1 << 8, /* Force POSIX access control lists */
+ OCFS2_MOUNT_NO_POSIX_ACL = 1 << 9, /* Disable POSIX access
+ control lists */
+ OCFS2_MOUNT_USRQUOTA = 1 << 10, /* We support user quotas */
+ OCFS2_MOUNT_GRPQUOTA = 1 << 11, /* We support group quotas */
};
-#define OCFS2_OSB_SOFT_RO 0x0001
-#define OCFS2_OSB_HARD_RO 0x0002
-#define OCFS2_OSB_ERROR_FS 0x0004
-#define OCFS2_DEFAULT_ATIME_QUANTUM 60
+#define OCFS2_OSB_SOFT_RO 0x0001
+#define OCFS2_OSB_HARD_RO 0x0002
+#define OCFS2_OSB_ERROR_FS 0x0004
+#define OCFS2_OSB_DROP_DENTRY_LOCK_IMMED 0x0008
+
+#define OCFS2_DEFAULT_ATIME_QUANTUM 60
struct ocfs2_journal;
struct ocfs2_slot_info;
struct ocfs2_recovery_map;
+struct ocfs2_replay_map;
+struct ocfs2_quota_recovery;
+struct ocfs2_dentry_lock;
struct ocfs2_super
{
struct task_struct *commit_task;
u32 s_next_generation;
unsigned long osb_flags;
s16 s_inode_steal_slot;
+ s16 s_meta_steal_slot;
atomic_t s_num_inodes_stolen;
+ atomic_t s_num_meta_stolen;
unsigned long s_mount_opt;
unsigned int s_atime_quantum;
atomic_t vol_state;
struct mutex recovery_lock;
struct ocfs2_recovery_map *recovery_map;
+ struct ocfs2_replay_map *replay_map;
struct task_struct *recovery_thread_task;
int disable_recovery;
wait_queue_head_t checkpoint_event;
u64 la_last_gd;
-#ifdef CONFIG_OCFS2_FS_STATS
- struct dentry *local_alloc_debug;
- char *local_alloc_debug_buf;
-#endif
-
- /* Next two fields are for local node slot recovery during
+ /* Next three fields are for local node slot recovery during
* mount. */
int dirty;
struct ocfs2_dinode *local_alloc_copy;
+ struct ocfs2_quota_recovery *quota_rec;
+ struct ocfs2_blockcheck_stats osb_ecc_stats;
struct ocfs2_alloc_stats alloc_stats;
char dev_str[20]; /* "major,minor" of the device */
struct ocfs2_cluster_connection *cconn;
struct ocfs2_lock_res osb_super_lockres;
struct ocfs2_lock_res osb_rename_lockres;
+ struct ocfs2_lock_res osb_nfs_sync_lockres;
struct ocfs2_dlm_debug *osb_dlm_debug;
struct dentry *osb_debug_root;
+ struct dentry *osb_ctxt;
wait_queue_head_t recovery_event;
struct list_head blocked_lock_list;
unsigned long blocked_lock_count;
+ /* List of dentry locks to release. Anyone can add locks to
+ * the list, ocfs2_wq processes the list */
+ struct ocfs2_dentry_lock *dentry_lock_list;
+ struct work_struct dentry_lock_work;
+
wait_queue_head_t osb_mount_event;
/* Truncate log info */
struct ocfs2_node_map osb_recovering_orphan_dirs;
unsigned int *osb_orphan_wipes;
wait_queue_head_t osb_wipe_event;
+
+ struct ocfs2_orphan_scan osb_orphan_scan;
+
+ /* used to protect metaecc calculation check of xattr. */
+ spinlock_t osb_xattr_lock;
+
+ unsigned int osb_dx_mask;
+ u32 osb_dx_seed[4];
+
+ /* the group we used to allocate inodes. */
+ u64 osb_inode_alloc_group;
+
+ /* rb tree root for refcount lock. */
+ struct rb_root osb_rf_lock_tree;
+ struct ocfs2_refcount_tree *osb_ref_tree_lru;
};
#define OCFS2_SB(sb) ((struct ocfs2_super *)(sb)->s_fs_info)
+/* Useful typedef for passing around journal access functions */
+typedef int (*ocfs2_journal_access_func)(handle_t *handle,
+ struct ocfs2_caching_info *ci,
+ struct buffer_head *bh, int type);
+
static inline int ocfs2_should_order_data(struct inode *inode)
{
if (!S_ISREG(inode->i_mode))
return 0;
}
+static inline int ocfs2_supports_xattr(struct ocfs2_super *osb)
+{
+ if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_XATTR)
+ return 1;
+ return 0;
+}
+
+static inline int ocfs2_meta_ecc(struct ocfs2_super *osb)
+{
+ if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_META_ECC)
+ return 1;
+ return 0;
+}
+
+static inline int ocfs2_supports_indexed_dirs(struct ocfs2_super *osb)
+{
+ if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS)
+ return 1;
+ return 0;
+}
+
+static inline unsigned int ocfs2_link_max(struct ocfs2_super *osb)
+{
+ if (ocfs2_supports_indexed_dirs(osb))
+ return OCFS2_DX_LINK_MAX;
+ return OCFS2_LINK_MAX;
+}
+
+static inline unsigned int ocfs2_read_links_count(struct ocfs2_dinode *di)
+{
+ u32 nlink = le16_to_cpu(di->i_links_count);
+ u32 hi = le16_to_cpu(di->i_links_count_hi);
+
+ if (di->i_dyn_features & cpu_to_le16(OCFS2_INDEXED_DIR_FL))
+ nlink |= (hi << OCFS2_LINKS_HI_SHIFT);
+
+ return nlink;
+}
+
+static inline void ocfs2_set_links_count(struct ocfs2_dinode *di, u32 nlink)
+{
+ u16 lo, hi;
+
+ lo = nlink;
+ hi = nlink >> OCFS2_LINKS_HI_SHIFT;
+
+ di->i_links_count = cpu_to_le16(lo);
+ di->i_links_count_hi = cpu_to_le16(hi);
+}
+
+static inline void ocfs2_add_links_count(struct ocfs2_dinode *di, int n)
+{
+ u32 links = ocfs2_read_links_count(di);
+
+ links += n;
+
+ ocfs2_set_links_count(di, links);
+}
+
+static inline int ocfs2_refcount_tree(struct ocfs2_super *osb)
+{
+ if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_REFCOUNT_TREE)
+ return 1;
+ return 0;
+}
+
/* set / clear functions because cluster events can make these happen
* in parallel so we want the transitions to be atomic. this also
* means that any future flags osb_flags must be protected by spinlock
spin_unlock(&osb->osb_lock);
}
+
+static inline unsigned long ocfs2_test_osb_flag(struct ocfs2_super *osb,
+ unsigned long flag)
+{
+ unsigned long ret;
+
+ spin_lock(&osb->osb_lock);
+ ret = osb->osb_flags & flag;
+ spin_unlock(&osb->osb_lock);
+ return ret;
+}
+
static inline void ocfs2_set_ro_flag(struct ocfs2_super *osb,
int hard)
{
#define OCFS2_IS_VALID_DINODE(ptr) \
(!strcmp((ptr)->i_signature, OCFS2_INODE_SIGNATURE))
-#define OCFS2_RO_ON_INVALID_DINODE(__sb, __di) do { \
- typeof(__di) ____di = (__di); \
- ocfs2_error((__sb), \
- "Dinode # %llu has bad signature %.*s", \
- (unsigned long long)le64_to_cpu((____di)->i_blkno), 7, \
- (____di)->i_signature); \
-} while (0)
-
#define OCFS2_IS_VALID_EXTENT_BLOCK(ptr) \
(!strcmp((ptr)->h_signature, OCFS2_EXTENT_BLOCK_SIGNATURE))
-#define OCFS2_RO_ON_INVALID_EXTENT_BLOCK(__sb, __eb) do { \
- typeof(__eb) ____eb = (__eb); \
- ocfs2_error((__sb), \
- "Extent Block # %llu has bad signature %.*s", \
- (unsigned long long)le64_to_cpu((____eb)->h_blkno), 7, \
- (____eb)->h_signature); \
-} while (0)
-
#define OCFS2_IS_VALID_GROUP_DESC(ptr) \
(!strcmp((ptr)->bg_signature, OCFS2_GROUP_DESC_SIGNATURE))
-#define OCFS2_RO_ON_INVALID_GROUP_DESC(__sb, __gd) do { \
- typeof(__gd) ____gd = (__gd); \
- ocfs2_error((__sb), \
- "Group Descriptor # %llu has bad signature %.*s", \
- (unsigned long long)le64_to_cpu((____gd)->bg_blkno), 7, \
- (____gd)->bg_signature); \
-} while (0)
+
+#define OCFS2_IS_VALID_XATTR_BLOCK(ptr) \
+ (!strcmp((ptr)->xb_signature, OCFS2_XATTR_BLOCK_SIGNATURE))
+
+#define OCFS2_IS_VALID_DIR_TRAILER(ptr) \
+ (!strcmp((ptr)->db_signature, OCFS2_DIR_TRAILER_SIGNATURE))
+
+#define OCFS2_IS_VALID_DX_ROOT(ptr) \
+ (!strcmp((ptr)->dr_signature, OCFS2_DX_ROOT_SIGNATURE))
+
+#define OCFS2_IS_VALID_DX_LEAF(ptr) \
+ (!strcmp((ptr)->dl_signature, OCFS2_DX_LEAF_SIGNATURE))
+
+#define OCFS2_IS_VALID_REFCOUNT_BLOCK(ptr) \
+ (!strcmp((ptr)->rf_signature, OCFS2_REFCOUNT_BLOCK_SIGNATURE))
static inline unsigned long ino_from_blkno(struct super_block *sb,
u64 blkno)
return (u64)clusters << OCFS2_SB(sb)->s_clustersize_bits;
}
+static inline u64 ocfs2_block_to_cluster_start(struct super_block *sb,
+ u64 blocks)
+{
+ int bits = OCFS2_SB(sb)->s_clustersize_bits - sb->s_blocksize_bits;
+ unsigned int clusters;
+
+ clusters = ocfs2_blocks_to_clusters(sb, blocks);
+ return (u64)clusters << bits;
+}
+
static inline u64 ocfs2_align_bytes_to_clusters(struct super_block *sb,
u64 bytes)
{
return megs << (20 - OCFS2_SB(sb)->s_clustersize_bits);
}
-static inline void ocfs2_init_inode_steal_slot(struct ocfs2_super *osb)
-{
- spin_lock(&osb->osb_lock);
- osb->s_inode_steal_slot = OCFS2_INVALID_SLOT;
- spin_unlock(&osb->osb_lock);
- atomic_set(&osb->s_num_inodes_stolen, 0);
-}
-
-static inline void ocfs2_set_inode_steal_slot(struct ocfs2_super *osb,
- s16 slot)
+static inline void _ocfs2_set_bit(unsigned int bit, unsigned long *bitmap)
{
- spin_lock(&osb->osb_lock);
- osb->s_inode_steal_slot = slot;
- spin_unlock(&osb->osb_lock);
+ ext2_set_bit(bit, bitmap);
}
+#define ocfs2_set_bit(bit, addr) _ocfs2_set_bit((bit), (unsigned long *)(addr))
-static inline s16 ocfs2_get_inode_steal_slot(struct ocfs2_super *osb)
+static inline void _ocfs2_clear_bit(unsigned int bit, unsigned long *bitmap)
{
- s16 slot;
-
- spin_lock(&osb->osb_lock);
- slot = osb->s_inode_steal_slot;
- spin_unlock(&osb->osb_lock);
-
- return slot;
+ ext2_clear_bit(bit, bitmap);
}
+#define ocfs2_clear_bit(bit, addr) _ocfs2_clear_bit((bit), (unsigned long *)(addr))
-#define ocfs2_set_bit ext2_set_bit
-#define ocfs2_clear_bit ext2_clear_bit
#define ocfs2_test_bit ext2_test_bit
#define ocfs2_find_next_zero_bit ext2_find_next_zero_bit
+#define ocfs2_find_next_bit ext2_find_next_bit
#endif /* OCFS2_H */