#include <linux/pagemap.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
+#include <linux/time.h>
+#include <linux/quotaops.h>
#define MLOG_MASK_PREFIX ML_DLM_GLUE
#include <cluster/masklog.h>
#include "slot_map.h"
#include "super.h"
#include "uptodate.h"
+#include "quota.h"
+#include "refcounttree.h"
#include "buffer_head_io.h"
struct completion mw_complete;
unsigned long mw_mask;
unsigned long mw_goal;
+#ifdef CONFIG_OCFS2_FS_STATS
+ unsigned long long mw_lock_start;
+#endif
};
static struct ocfs2_super *ocfs2_get_dentry_osb(struct ocfs2_lock_res *lockres);
static struct ocfs2_super *ocfs2_get_inode_osb(struct ocfs2_lock_res *lockres);
static struct ocfs2_super *ocfs2_get_file_osb(struct ocfs2_lock_res *lockres);
+static struct ocfs2_super *ocfs2_get_qinfo_osb(struct ocfs2_lock_res *lockres);
/*
* Return value from ->downconvert_worker functions.
enum ocfs2_unblock_action unblock_action;
};
+/* Lockdep class keys */
+struct lock_class_key lockdep_keys[OCFS2_NUM_LOCK_TYPES];
+
static int ocfs2_check_meta_downconvert(struct ocfs2_lock_res *lockres,
int new_level);
static void ocfs2_set_meta_lvb(struct ocfs2_lock_res *lockres);
static void ocfs2_dentry_post_unlock(struct ocfs2_super *osb,
struct ocfs2_lock_res *lockres);
+static void ocfs2_set_qinfo_lvb(struct ocfs2_lock_res *lockres);
+
+static int ocfs2_check_refcount_downconvert(struct ocfs2_lock_res *lockres,
+ int new_level);
+static int ocfs2_refcount_convert_worker(struct ocfs2_lock_res *lockres,
+ int blocking);
#define mlog_meta_lvb(__level, __lockres) ocfs2_dump_meta_lvb_info(__level, __PRETTY_FUNCTION__, __LINE__, __lockres)
unsigned int line,
struct ocfs2_lock_res *lockres)
{
- struct ocfs2_meta_lvb *lvb =
- (struct ocfs2_meta_lvb *)ocfs2_dlm_lvb(&lockres->l_lksb);
+ struct ocfs2_meta_lvb *lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
mlog(level, "LVB information for %s (called from %s:%u):\n",
lockres->l_name, function, line);
.flags = 0,
};
+static struct ocfs2_lock_res_ops ocfs2_nfs_sync_lops = {
+ .flags = 0,
+};
+
+static struct ocfs2_lock_res_ops ocfs2_orphan_scan_lops = {
+ .flags = LOCK_TYPE_REQUIRES_REFRESH|LOCK_TYPE_USES_LVB,
+};
+
static struct ocfs2_lock_res_ops ocfs2_dentry_lops = {
.get_osb = ocfs2_get_dentry_osb,
.post_unlock = ocfs2_dentry_post_unlock,
.flags = 0,
};
+static struct ocfs2_lock_res_ops ocfs2_qinfo_lops = {
+ .set_lvb = ocfs2_set_qinfo_lvb,
+ .get_osb = ocfs2_get_qinfo_osb,
+ .flags = LOCK_TYPE_REQUIRES_REFRESH | LOCK_TYPE_USES_LVB,
+};
+
+static struct ocfs2_lock_res_ops ocfs2_refcount_block_lops = {
+ .check_downconvert = ocfs2_check_refcount_downconvert,
+ .downconvert_worker = ocfs2_refcount_convert_worker,
+ .flags = 0,
+};
+
static inline int ocfs2_is_inode_lock(struct ocfs2_lock_res *lockres)
{
return lockres->l_type == OCFS2_LOCK_TYPE_META ||
return (struct ocfs2_dentry_lock *)lockres->l_priv;
}
+static inline struct ocfs2_mem_dqinfo *ocfs2_lock_res_qinfo(struct ocfs2_lock_res *lockres)
+{
+ BUG_ON(lockres->l_type != OCFS2_LOCK_TYPE_QINFO);
+
+ return (struct ocfs2_mem_dqinfo *)lockres->l_priv;
+}
+
+static inline struct ocfs2_refcount_tree *
+ocfs2_lock_res_refcount_tree(struct ocfs2_lock_res *res)
+{
+ return container_of(res, struct ocfs2_refcount_tree, rf_lockres);
+}
+
static inline struct ocfs2_super *ocfs2_get_lockres_osb(struct ocfs2_lock_res *lockres)
{
if (lockres->l_ops->get_osb)
u32 dlm_flags);
static inline int ocfs2_may_continue_on_blocked_lock(struct ocfs2_lock_res *lockres,
int wanted);
-static void ocfs2_cluster_unlock(struct ocfs2_super *osb,
- struct ocfs2_lock_res *lockres,
- int level);
+static void __ocfs2_cluster_unlock(struct ocfs2_super *osb,
+ struct ocfs2_lock_res *lockres,
+ int level, unsigned long caller_ip);
+static inline void ocfs2_cluster_unlock(struct ocfs2_super *osb,
+ struct ocfs2_lock_res *lockres,
+ int level)
+{
+ __ocfs2_cluster_unlock(osb, lockres, level, _RET_IP_);
+}
+
static inline void ocfs2_generic_handle_downconvert_action(struct ocfs2_lock_res *lockres);
static inline void ocfs2_generic_handle_convert_action(struct ocfs2_lock_res *lockres);
static inline void ocfs2_generic_handle_attach_action(struct ocfs2_lock_res *lockres);
struct ocfs2_lock_res *lockres);
static inline void ocfs2_recover_from_dlm_error(struct ocfs2_lock_res *lockres,
int convert);
-#define ocfs2_log_dlm_error(_func, _err, _lockres) do { \
- mlog(ML_ERROR, "DLM error %d while calling %s on resource %s\n", \
- _err, _func, _lockres->l_name); \
+#define ocfs2_log_dlm_error(_func, _err, _lockres) do { \
+ if ((_lockres)->l_type != OCFS2_LOCK_TYPE_DENTRY) \
+ mlog(ML_ERROR, "DLM error %d while calling %s on resource %s\n", \
+ _err, _func, _lockres->l_name); \
+ else \
+ mlog(ML_ERROR, "DLM error %d while calling %s on resource %.*s%08x\n", \
+ _err, _func, OCFS2_DENTRY_LOCK_INO_START - 1, (_lockres)->l_name, \
+ (unsigned int)ocfs2_get_dentry_lock_ino(_lockres)); \
} while (0)
static int ocfs2_downconvert_thread(void *arg);
static void ocfs2_downconvert_on_unlock(struct ocfs2_super *osb,
struct buffer_head **bh);
static void ocfs2_drop_osb_locks(struct ocfs2_super *osb);
static inline int ocfs2_highest_compat_lock_level(int level);
-static void ocfs2_prepare_downconvert(struct ocfs2_lock_res *lockres,
- int new_level);
+static unsigned int ocfs2_prepare_downconvert(struct ocfs2_lock_res *lockres,
+ int new_level);
static int ocfs2_downconvert_lock(struct ocfs2_super *osb,
struct ocfs2_lock_res *lockres,
int new_level,
- int lvb);
+ int lvb,
+ unsigned int generation);
static int ocfs2_prepare_cancel_convert(struct ocfs2_super *osb,
struct ocfs2_lock_res *lockres);
static int ocfs2_cancel_convert(struct ocfs2_super *osb,
spin_unlock(&ocfs2_dlm_tracking_lock);
}
+#ifdef CONFIG_OCFS2_FS_STATS
+static void ocfs2_init_lock_stats(struct ocfs2_lock_res *res)
+{
+ res->l_lock_num_prmode = 0;
+ res->l_lock_num_prmode_failed = 0;
+ res->l_lock_total_prmode = 0;
+ res->l_lock_max_prmode = 0;
+ res->l_lock_num_exmode = 0;
+ res->l_lock_num_exmode_failed = 0;
+ res->l_lock_total_exmode = 0;
+ res->l_lock_max_exmode = 0;
+ res->l_lock_refresh = 0;
+}
+
+static void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, int level,
+ struct ocfs2_mask_waiter *mw, int ret)
+{
+ unsigned long long *num, *sum;
+ unsigned int *max, *failed;
+ struct timespec ts = current_kernel_time();
+ unsigned long long time = timespec_to_ns(&ts) - mw->mw_lock_start;
+
+ if (level == LKM_PRMODE) {
+ num = &res->l_lock_num_prmode;
+ sum = &res->l_lock_total_prmode;
+ max = &res->l_lock_max_prmode;
+ failed = &res->l_lock_num_prmode_failed;
+ } else if (level == LKM_EXMODE) {
+ num = &res->l_lock_num_exmode;
+ sum = &res->l_lock_total_exmode;
+ max = &res->l_lock_max_exmode;
+ failed = &res->l_lock_num_exmode_failed;
+ } else
+ return;
+
+ (*num)++;
+ (*sum) += time;
+ if (time > *max)
+ *max = time;
+ if (ret)
+ (*failed)++;
+}
+
+static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres)
+{
+ lockres->l_lock_refresh++;
+}
+
+static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw)
+{
+ struct timespec ts = current_kernel_time();
+ mw->mw_lock_start = timespec_to_ns(&ts);
+}
+#else
+static inline void ocfs2_init_lock_stats(struct ocfs2_lock_res *res)
+{
+}
+static inline void ocfs2_update_lock_stats(struct ocfs2_lock_res *res,
+ int level, struct ocfs2_mask_waiter *mw, int ret)
+{
+}
+static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres)
+{
+}
+static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw)
+{
+}
+#endif
+
static void ocfs2_lock_res_init_common(struct ocfs2_super *osb,
struct ocfs2_lock_res *res,
enum ocfs2_lock_type type,
res->l_flags = OCFS2_LOCK_INITIALIZED;
ocfs2_add_lockres_tracking(res, osb->osb_dlm_debug);
+
+ ocfs2_init_lock_stats(res);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ if (type != OCFS2_LOCK_TYPE_OPEN)
+ lockdep_init_map(&res->l_lockdep_map, ocfs2_lock_type_strings[type],
+ &lockdep_keys[type], 0);
+ else
+ res->l_lockdep_map.key = NULL;
+#endif
}
void ocfs2_lock_res_init_once(struct ocfs2_lock_res *res)
return OCFS2_SB(inode->i_sb);
}
+static struct ocfs2_super *ocfs2_get_qinfo_osb(struct ocfs2_lock_res *lockres)
+{
+ struct ocfs2_mem_dqinfo *info = lockres->l_priv;
+
+ return OCFS2_SB(info->dqi_gi.dqi_sb);
+}
+
static struct ocfs2_super *ocfs2_get_file_osb(struct ocfs2_lock_res *lockres)
{
struct ocfs2_file_private *fp = lockres->l_priv;
&ocfs2_rename_lops, osb);
}
+static void ocfs2_nfs_sync_lock_res_init(struct ocfs2_lock_res *res,
+ struct ocfs2_super *osb)
+{
+ /* nfs_sync lockres doesn't come from a slab so we call init
+ * once on it manually. */
+ ocfs2_lock_res_init_once(res);
+ ocfs2_build_lock_name(OCFS2_LOCK_TYPE_NFS_SYNC, 0, 0, res->l_name);
+ ocfs2_lock_res_init_common(osb, res, OCFS2_LOCK_TYPE_NFS_SYNC,
+ &ocfs2_nfs_sync_lops, osb);
+}
+
+static void ocfs2_orphan_scan_lock_res_init(struct ocfs2_lock_res *res,
+ struct ocfs2_super *osb)
+{
+ ocfs2_lock_res_init_once(res);
+ ocfs2_build_lock_name(OCFS2_LOCK_TYPE_ORPHAN_SCAN, 0, 0, res->l_name);
+ ocfs2_lock_res_init_common(osb, res, OCFS2_LOCK_TYPE_ORPHAN_SCAN,
+ &ocfs2_orphan_scan_lops, osb);
+}
+
void ocfs2_file_lock_res_init(struct ocfs2_lock_res *lockres,
struct ocfs2_file_private *fp)
{
lockres->l_flags |= OCFS2_LOCK_NOCACHE;
}
+void ocfs2_qinfo_lock_res_init(struct ocfs2_lock_res *lockres,
+ struct ocfs2_mem_dqinfo *info)
+{
+ ocfs2_lock_res_init_once(lockres);
+ ocfs2_build_lock_name(OCFS2_LOCK_TYPE_QINFO, info->dqi_gi.dqi_type,
+ 0, lockres->l_name);
+ ocfs2_lock_res_init_common(OCFS2_SB(info->dqi_gi.dqi_sb), lockres,
+ OCFS2_LOCK_TYPE_QINFO, &ocfs2_qinfo_lops,
+ info);
+}
+
+void ocfs2_refcount_lock_res_init(struct ocfs2_lock_res *lockres,
+ struct ocfs2_super *osb, u64 ref_blkno,
+ unsigned int generation)
+{
+ ocfs2_lock_res_init_once(lockres);
+ ocfs2_build_lock_name(OCFS2_LOCK_TYPE_REFCOUNT, ref_blkno,
+ generation, lockres->l_name);
+ ocfs2_lock_res_init_common(osb, lockres, OCFS2_LOCK_TYPE_REFCOUNT,
+ &ocfs2_refcount_block_lops, osb);
+}
+
void ocfs2_lock_res_free(struct ocfs2_lock_res *res)
{
mlog_entry_void();
assert_spin_locked(&lockres->l_lock);
- lockres_or_flags(lockres, OCFS2_LOCK_BLOCKED);
-
if (level > lockres->l_blocking) {
/* only schedule a downconvert if we haven't already scheduled
* one that goes low enough to satisfy the level we're
lockres->l_blocking = level;
}
+ if (needs_downconvert)
+ lockres_or_flags(lockres, OCFS2_LOCK_BLOCKED);
+
mlog_exit(needs_downconvert);
return needs_downconvert;
}
+/*
+ * OCFS2_LOCK_PENDING and l_pending_gen.
+ *
+ * Why does OCFS2_LOCK_PENDING exist? To close a race between setting
+ * OCFS2_LOCK_BUSY and calling ocfs2_dlm_lock(). See ocfs2_unblock_lock()
+ * for more details on the race.
+ *
+ * OCFS2_LOCK_PENDING closes the race quite nicely. However, it introduces
+ * a race on itself. In o2dlm, we can get the ast before ocfs2_dlm_lock()
+ * returns. The ast clears OCFS2_LOCK_BUSY, and must therefore clear
+ * OCFS2_LOCK_PENDING at the same time. When ocfs2_dlm_lock() returns,
+ * the caller is going to try to clear PENDING again. If nothing else is
+ * happening, __lockres_clear_pending() sees PENDING is unset and does
+ * nothing.
+ *
+ * But what if another path (eg downconvert thread) has just started a
+ * new locking action? The other path has re-set PENDING. Our path
+ * cannot clear PENDING, because that will re-open the original race
+ * window.
+ *
+ * [Example]
+ *
+ * ocfs2_meta_lock()
+ * ocfs2_cluster_lock()
+ * set BUSY
+ * set PENDING
+ * drop l_lock
+ * ocfs2_dlm_lock()
+ * ocfs2_locking_ast() ocfs2_downconvert_thread()
+ * clear PENDING ocfs2_unblock_lock()
+ * take_l_lock
+ * !BUSY
+ * ocfs2_prepare_downconvert()
+ * set BUSY
+ * set PENDING
+ * drop l_lock
+ * take l_lock
+ * clear PENDING
+ * drop l_lock
+ * <window>
+ * ocfs2_dlm_lock()
+ *
+ * So as you can see, we now have a window where l_lock is not held,
+ * PENDING is not set, and ocfs2_dlm_lock() has not been called.
+ *
+ * The core problem is that ocfs2_cluster_lock() has cleared the PENDING
+ * set by ocfs2_prepare_downconvert(). That wasn't nice.
+ *
+ * To solve this we introduce l_pending_gen. A call to
+ * lockres_clear_pending() will only do so when it is passed a generation
+ * number that matches the lockres. lockres_set_pending() will return the
+ * current generation number. When ocfs2_cluster_lock() goes to clear
+ * PENDING, it passes the generation it got from set_pending(). In our
+ * example above, the generation numbers will *not* match. Thus,
+ * ocfs2_cluster_lock() will not clear the PENDING set by
+ * ocfs2_prepare_downconvert().
+ */
+
+/* Unlocked version for ocfs2_locking_ast() */
+static void __lockres_clear_pending(struct ocfs2_lock_res *lockres,
+ unsigned int generation,
+ struct ocfs2_super *osb)
+{
+ assert_spin_locked(&lockres->l_lock);
+
+ /*
+ * The ast and locking functions can race us here. The winner
+ * will clear pending, the loser will not.
+ */
+ if (!(lockres->l_flags & OCFS2_LOCK_PENDING) ||
+ (lockres->l_pending_gen != generation))
+ return;
+
+ lockres_clear_flags(lockres, OCFS2_LOCK_PENDING);
+ lockres->l_pending_gen++;
+
+ /*
+ * The downconvert thread may have skipped us because we
+ * were PENDING. Wake it up.
+ */
+ if (lockres->l_flags & OCFS2_LOCK_BLOCKED)
+ ocfs2_wake_downconvert_thread(osb);
+}
+
+/* Locked version for callers of ocfs2_dlm_lock() */
+static void lockres_clear_pending(struct ocfs2_lock_res *lockres,
+ unsigned int generation,
+ struct ocfs2_super *osb)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&lockres->l_lock, flags);
+ __lockres_clear_pending(lockres, generation, osb);
+ spin_unlock_irqrestore(&lockres->l_lock, flags);
+}
+
+static unsigned int lockres_set_pending(struct ocfs2_lock_res *lockres)
+{
+ assert_spin_locked(&lockres->l_lock);
+ BUG_ON(!(lockres->l_flags & OCFS2_LOCK_BUSY));
+
+ lockres_or_flags(lockres, OCFS2_LOCK_PENDING);
+
+ return lockres->l_pending_gen;
+}
+
+
static void ocfs2_blocking_ast(void *opaque, int level)
{
struct ocfs2_lock_res *lockres = opaque;
static void ocfs2_locking_ast(void *opaque)
{
struct ocfs2_lock_res *lockres = opaque;
+ struct ocfs2_super *osb = ocfs2_get_lockres_osb(lockres);
unsigned long flags;
+ int status;
spin_lock_irqsave(&lockres->l_lock, flags);
- if (ocfs2_dlm_lock_status(&lockres->l_lksb)) {
+ status = ocfs2_dlm_lock_status(&lockres->l_lksb);
+
+ if (status == -EAGAIN) {
+ lockres_clear_flags(lockres, OCFS2_LOCK_BUSY);
+ goto out;
+ }
+
+ if (status) {
mlog(ML_ERROR, "lockres %s: lksb status value of %d!\n",
- lockres->l_name,
- ocfs2_dlm_lock_status(&lockres->l_lksb));
+ lockres->l_name, status);
spin_unlock_irqrestore(&lockres->l_lock, flags);
return;
}
lockres->l_unlock_action);
BUG();
}
-
+out:
/* set it to something invalid so if we get called again we
* can catch it. */
lockres->l_action = OCFS2_AST_INVALID;
+ /* Did we try to cancel this lock? Clear that state */
+ if (lockres->l_unlock_action == OCFS2_UNLOCK_CANCEL_CONVERT)
+ lockres->l_unlock_action = OCFS2_UNLOCK_INVALID;
+
+ /*
+ * We may have beaten the locking functions here. We certainly
+ * know that dlm_lock() has been called :-)
+ * Because we can't have two lock calls in flight at once, we
+ * can use lockres->l_pending_gen.
+ */
+ __lockres_clear_pending(lockres, lockres->l_pending_gen, osb);
+
wake_up(&lockres->l_event);
spin_unlock_irqrestore(&lockres->l_lock, flags);
}
{
int ret = 0;
unsigned long flags;
+ unsigned int gen;
mlog_entry_void();
lockres->l_action = OCFS2_AST_ATTACH;
lockres->l_requested = level;
lockres_or_flags(lockres, OCFS2_LOCK_BUSY);
+ gen = lockres_set_pending(lockres);
spin_unlock_irqrestore(&lockres->l_lock, flags);
ret = ocfs2_dlm_lock(osb->cconn,
lockres->l_name,
OCFS2_LOCK_ID_MAX_LEN - 1,
lockres);
+ lockres_clear_pending(lockres, gen, osb);
if (ret) {
ocfs2_log_dlm_error("ocfs2_dlm_lock", ret, lockres);
ocfs2_recover_from_dlm_error(lockres, 1);
{
INIT_LIST_HEAD(&mw->mw_item);
init_completion(&mw->mw_complete);
+ ocfs2_init_start_time(mw);
}
static int ocfs2_wait_for_mask(struct ocfs2_mask_waiter *mw)
return ret;
}
-static int ocfs2_cluster_lock(struct ocfs2_super *osb,
- struct ocfs2_lock_res *lockres,
- int level,
- u32 lkm_flags,
- int arg_flags)
+static int __ocfs2_cluster_lock(struct ocfs2_super *osb,
+ struct ocfs2_lock_res *lockres,
+ int level,
+ u32 lkm_flags,
+ int arg_flags,
+ int l_subclass,
+ unsigned long caller_ip)
{
struct ocfs2_mask_waiter mw;
int wait, catch_signals = !(osb->s_mount_opt & OCFS2_MOUNT_NOINTR);
int ret = 0; /* gcc doesn't realize wait = 1 guarantees ret is set */
unsigned long flags;
+ unsigned int gen;
+ int noqueue_attempted = 0;
mlog_entry_void();
}
if (level > lockres->l_level) {
+ if (noqueue_attempted > 0) {
+ ret = -EAGAIN;
+ goto unlock;
+ }
+ if (lkm_flags & DLM_LKF_NOQUEUE)
+ noqueue_attempted = 1;
+
if (lockres->l_action != OCFS2_AST_INVALID)
mlog(ML_ERROR, "lockres %s has action %u pending\n",
lockres->l_name, lockres->l_action);
lockres->l_requested = level;
lockres_or_flags(lockres, OCFS2_LOCK_BUSY);
+ gen = lockres_set_pending(lockres);
spin_unlock_irqrestore(&lockres->l_lock, flags);
BUG_ON(level == DLM_LOCK_IV);
lockres->l_name,
OCFS2_LOCK_ID_MAX_LEN - 1,
lockres);
+ lockres_clear_pending(lockres, gen, osb);
if (ret) {
if (!(lkm_flags & DLM_LKF_NOQUEUE) ||
(ret != -EAGAIN)) {
goto out;
}
- mlog(0, "lock %s, successfull return from ocfs2_dlm_lock\n",
+ mlog(0, "lock %s, successful return from ocfs2_dlm_lock\n",
lockres->l_name);
/* At this point we've gone inside the dlm and need to
goto again;
mlog_errno(ret);
}
+ ocfs2_update_lock_stats(lockres, level, &mw, ret);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ if (!ret && lockres->l_lockdep_map.key != NULL) {
+ if (level == DLM_LOCK_PR)
+ rwsem_acquire_read(&lockres->l_lockdep_map, l_subclass,
+ !!(arg_flags & OCFS2_META_LOCK_NOQUEUE),
+ caller_ip);
+ else
+ rwsem_acquire(&lockres->l_lockdep_map, l_subclass,
+ !!(arg_flags & OCFS2_META_LOCK_NOQUEUE),
+ caller_ip);
+ }
+#endif
mlog_exit(ret);
return ret;
}
-static void ocfs2_cluster_unlock(struct ocfs2_super *osb,
- struct ocfs2_lock_res *lockres,
- int level)
+static inline int ocfs2_cluster_lock(struct ocfs2_super *osb,
+ struct ocfs2_lock_res *lockres,
+ int level,
+ u32 lkm_flags,
+ int arg_flags)
+{
+ return __ocfs2_cluster_lock(osb, lockres, level, lkm_flags, arg_flags,
+ 0, _RET_IP_);
+}
+
+
+static void __ocfs2_cluster_unlock(struct ocfs2_super *osb,
+ struct ocfs2_lock_res *lockres,
+ int level,
+ unsigned long caller_ip)
{
unsigned long flags;
ocfs2_dec_holders(lockres, level);
ocfs2_downconvert_on_unlock(osb, lockres);
spin_unlock_irqrestore(&lockres->l_lock, flags);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ if (lockres->l_lockdep_map.key != NULL)
+ rwsem_release(&lockres->l_lockdep_map, 1, caller_ip);
+#endif
mlog_exit_void();
}
(unsigned long long)OCFS2_I(inode)->ip_blkno,
write ? "EXMODE" : "PRMODE");
- if (ocfs2_mount_local(osb))
+ if (ocfs2_mount_local(osb)) {
+ mlog_exit(0);
return 0;
+ }
lockres = &OCFS2_I(inode)->ip_rw_lockres;
*/
int ocfs2_file_lock(struct file *file, int ex, int trylock)
{
- int ret, level = ex ? LKM_EXMODE : LKM_PRMODE;
- unsigned int lkm_flags = trylock ? LKM_NOQUEUE : 0;
+ int ret, level = ex ? DLM_LOCK_EX : DLM_LOCK_PR;
+ unsigned int lkm_flags = trylock ? DLM_LKF_NOQUEUE : 0;
unsigned long flags;
struct ocfs2_file_private *fp = file->private_data;
struct ocfs2_lock_res *lockres = &fp->fp_flock;
* Get the lock at NLMODE to start - that way we
* can cancel the upconvert request if need be.
*/
- ret = ocfs2_lock_create(osb, lockres, LKM_NLMODE, 0);
+ ret = ocfs2_lock_create(osb, lockres, DLM_LOCK_NL, 0);
if (ret < 0) {
mlog_errno(ret);
goto out;
}
lockres->l_action = OCFS2_AST_CONVERT;
- lkm_flags |= LKM_CONVERT;
+ lkm_flags |= DLM_LKF_CONVERT;
lockres->l_requested = level;
lockres_or_flags(lockres, OCFS2_LOCK_BUSY);
* outstanding lock request, so a cancel convert is
* required. We intentionally overwrite 'ret' - if the
* cancel fails and the lock was granted, it's easier
- * to just bubble sucess back up to the user.
+ * to just bubble success back up to the user.
*/
ret = ocfs2_flock_handle_signal(lockres, level);
+ } else if (!ret && (level > lockres->l_level)) {
+ /* Trylock failed asynchronously */
+ BUG_ON(!trylock);
+ ret = -EAGAIN;
}
out:
void ocfs2_file_unlock(struct file *file)
{
int ret;
+ unsigned int gen;
unsigned long flags;
struct ocfs2_file_private *fp = file->private_data;
struct ocfs2_lock_res *lockres = &fp->fp_flock;
if (!(lockres->l_flags & OCFS2_LOCK_ATTACHED))
return;
- if (lockres->l_level == LKM_NLMODE)
+ if (lockres->l_level == DLM_LOCK_NL)
return;
mlog(0, "Unlock: \"%s\" flags: 0x%lx, level: %d, act: %d\n",
lockres_or_flags(lockres, OCFS2_LOCK_BLOCKED);
lockres->l_blocking = DLM_LOCK_EX;
- ocfs2_prepare_downconvert(lockres, LKM_NLMODE);
+ gen = ocfs2_prepare_downconvert(lockres, DLM_LOCK_NL);
lockres_add_mask_waiter(lockres, &mw, OCFS2_LOCK_BUSY, 0);
spin_unlock_irqrestore(&lockres->l_lock, flags);
- ret = ocfs2_downconvert_lock(osb, lockres, LKM_NLMODE, 0);
+ ret = ocfs2_downconvert_lock(osb, lockres, DLM_LOCK_NL, 0, gen);
if (ret) {
mlog_errno(ret);
return;
mlog_entry_void();
- lvb = (struct ocfs2_meta_lvb *)ocfs2_dlm_lvb(&lockres->l_lksb);
+ lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
/*
* Invalidate the LVB of a deleted inode - this way other
mlog_meta_lvb(0, lockres);
- lvb = (struct ocfs2_meta_lvb *)ocfs2_dlm_lvb(&lockres->l_lksb);
+ lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
/* We're safe here without the lockres lock... */
spin_lock(&oi->ip_lock);
static inline int ocfs2_meta_lvb_is_trustable(struct inode *inode,
struct ocfs2_lock_res *lockres)
{
- struct ocfs2_meta_lvb *lvb =
- (struct ocfs2_meta_lvb *)ocfs2_dlm_lvb(&lockres->l_lksb);
+ struct ocfs2_meta_lvb *lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
- if (lvb->lvb_version == OCFS2_LVB_VERSION
+ if (ocfs2_dlm_lvb_valid(&lockres->l_lksb)
+ && lvb->lvb_version == OCFS2_LVB_VERSION
&& be32_to_cpu(lvb->lvb_igeneration) == inode->i_generation)
return 1;
return 0;
/* This will discard any caching information we might have had
* for the inode metadata. */
- ocfs2_metadata_cache_purge(inode);
+ ocfs2_metadata_cache_purge(INODE_CACHE(inode));
ocfs2_extent_map_trunc(inode, 0);
} else {
/* Boo, we have to go to disk. */
/* read bh, cast, ocfs2_refresh_inode */
- status = ocfs2_read_block(OCFS2_SB(inode->i_sb), oi->ip_blkno,
- bh, OCFS2_BH_CACHED, inode);
+ status = ocfs2_read_inode_block(inode, bh);
if (status < 0) {
mlog_errno(status);
goto bail_refresh;
fe = (struct ocfs2_dinode *) (*bh)->b_data;
/* This is a good chance to make sure we're not
- * locking an invalid object.
+ * locking an invalid object. ocfs2_read_inode_block()
+ * already checked that the inode block is sane.
*
* We bug on a stale inode here because we checked
* above whether it was wiped from disk. The wiping
* node provides a guarantee that we receive that
* message and can mark the inode before dropping any
* locks associated with it. */
- if (!OCFS2_IS_VALID_DINODE(fe)) {
- OCFS2_RO_ON_INVALID_DINODE(inode->i_sb, fe);
- status = -EIO;
- goto bail_refresh;
- }
mlog_bug_on_msg(inode->i_generation !=
le32_to_cpu(fe->i_generation),
"Invalid dinode %llu disk generation: %u "
le32_to_cpu(fe->i_flags));
ocfs2_refresh_inode(inode, fe);
+ ocfs2_track_lock_refresh(lockres);
}
status = 0;
return 0;
}
- status = ocfs2_read_block(OCFS2_SB(inode->i_sb),
- OCFS2_I(inode)->ip_blkno,
- ret_bh,
- OCFS2_BH_CACHED,
- inode);
+ status = ocfs2_read_inode_block(inode, ret_bh);
if (status < 0)
mlog_errno(status);
* returns < 0 error if the callback will never be called, otherwise
* the result of the lock will be communicated via the callback.
*/
-int ocfs2_inode_lock_full(struct inode *inode,
- struct buffer_head **ret_bh,
- int ex,
- int arg_flags)
+int ocfs2_inode_lock_full_nested(struct inode *inode,
+ struct buffer_head **ret_bh,
+ int ex,
+ int arg_flags,
+ int subclass)
{
int status, level, acquired;
u32 dlm_flags;
if (arg_flags & OCFS2_META_LOCK_NOQUEUE)
dlm_flags |= DLM_LKF_NOQUEUE;
- status = ocfs2_cluster_lock(osb, lockres, level, dlm_flags, arg_flags);
+ status = __ocfs2_cluster_lock(osb, lockres, level, dlm_flags,
+ arg_flags, subclass, _RET_IP_);
if (status < 0) {
if (status != -EAGAIN && status != -EIOCBRETRY)
mlog_errno(status);
mlog_exit_void();
}
+int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno)
+{
+ struct ocfs2_lock_res *lockres;
+ struct ocfs2_orphan_scan_lvb *lvb;
+ int status = 0;
+
+ if (ocfs2_is_hard_readonly(osb))
+ return -EROFS;
+
+ if (ocfs2_mount_local(osb))
+ return 0;
+
+ lockres = &osb->osb_orphan_scan.os_lockres;
+ status = ocfs2_cluster_lock(osb, lockres, DLM_LOCK_EX, 0, 0);
+ if (status < 0)
+ return status;
+
+ lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
+ if (ocfs2_dlm_lvb_valid(&lockres->l_lksb) &&
+ lvb->lvb_version == OCFS2_ORPHAN_LVB_VERSION)
+ *seqno = be32_to_cpu(lvb->lvb_os_seqno);
+ else
+ *seqno = osb->osb_orphan_scan.os_seqno + 1;
+
+ return status;
+}
+
+void ocfs2_orphan_scan_unlock(struct ocfs2_super *osb, u32 seqno)
+{
+ struct ocfs2_lock_res *lockres;
+ struct ocfs2_orphan_scan_lvb *lvb;
+
+ if (!ocfs2_is_hard_readonly(osb) && !ocfs2_mount_local(osb)) {
+ lockres = &osb->osb_orphan_scan.os_lockres;
+ lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
+ lvb->lvb_version = OCFS2_ORPHAN_LVB_VERSION;
+ lvb->lvb_os_seqno = cpu_to_be32(seqno);
+ ocfs2_cluster_unlock(osb, lockres, DLM_LOCK_EX);
+ }
+}
+
int ocfs2_super_lock(struct ocfs2_super *osb,
int ex)
{
if (status < 0)
mlog_errno(status);
+ ocfs2_track_lock_refresh(lockres);
}
bail:
mlog_exit(status);
ocfs2_cluster_unlock(osb, lockres, DLM_LOCK_EX);
}
+int ocfs2_nfs_sync_lock(struct ocfs2_super *osb, int ex)
+{
+ int status;
+ struct ocfs2_lock_res *lockres = &osb->osb_nfs_sync_lockres;
+
+ if (ocfs2_is_hard_readonly(osb))
+ return -EROFS;
+
+ if (ocfs2_mount_local(osb))
+ return 0;
+
+ status = ocfs2_cluster_lock(osb, lockres, ex ? LKM_EXMODE : LKM_PRMODE,
+ 0, 0);
+ if (status < 0)
+ mlog(ML_ERROR, "lock on nfs sync lock failed %d\n", status);
+
+ return status;
+}
+
+void ocfs2_nfs_sync_unlock(struct ocfs2_super *osb, int ex)
+{
+ struct ocfs2_lock_res *lockres = &osb->osb_nfs_sync_lockres;
+
+ if (!ocfs2_mount_local(osb))
+ ocfs2_cluster_unlock(osb, lockres,
+ ex ? LKM_EXMODE : LKM_PRMODE);
+}
+
int ocfs2_dentry_lock(struct dentry *dentry, int ex)
{
int ret;
}
/* So that debugfs.ocfs2 can determine which format is being used */
-#define OCFS2_DLM_DEBUG_STR_VERSION 1
+#define OCFS2_DLM_DEBUG_STR_VERSION 2
static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
{
int i;
for(i = 0; i < DLM_LVB_LEN; i++)
seq_printf(m, "0x%x\t", lvb[i]);
+#ifdef CONFIG_OCFS2_FS_STATS
+# define lock_num_prmode(_l) (_l)->l_lock_num_prmode
+# define lock_num_exmode(_l) (_l)->l_lock_num_exmode
+# define lock_num_prmode_failed(_l) (_l)->l_lock_num_prmode_failed
+# define lock_num_exmode_failed(_l) (_l)->l_lock_num_exmode_failed
+# define lock_total_prmode(_l) (_l)->l_lock_total_prmode
+# define lock_total_exmode(_l) (_l)->l_lock_total_exmode
+# define lock_max_prmode(_l) (_l)->l_lock_max_prmode
+# define lock_max_exmode(_l) (_l)->l_lock_max_exmode
+# define lock_refresh(_l) (_l)->l_lock_refresh
+#else
+# define lock_num_prmode(_l) (0ULL)
+# define lock_num_exmode(_l) (0ULL)
+# define lock_num_prmode_failed(_l) (0)
+# define lock_num_exmode_failed(_l) (0)
+# define lock_total_prmode(_l) (0ULL)
+# define lock_total_exmode(_l) (0ULL)
+# define lock_max_prmode(_l) (0)
+# define lock_max_exmode(_l) (0)
+# define lock_refresh(_l) (0)
+#endif
+ /* The following seq_print was added in version 2 of this output */
+ seq_printf(m, "%llu\t"
+ "%llu\t"
+ "%u\t"
+ "%u\t"
+ "%llu\t"
+ "%llu\t"
+ "%u\t"
+ "%u\t"
+ "%u\t",
+ lock_num_prmode(lockres),
+ lock_num_exmode(lockres),
+ lock_num_prmode_failed(lockres),
+ lock_num_exmode_failed(lockres),
+ lock_total_prmode(lockres),
+ lock_total_exmode(lockres),
+ lock_max_prmode(lockres),
+ lock_max_exmode(lockres),
+ lock_refresh(lockres));
+
/* End the line */
seq_printf(m, "\n");
return 0;
}
/* for now, uuid == domain */
- status = ocfs2_cluster_connect(osb->uuid_str,
+ status = ocfs2_cluster_connect(osb->osb_cluster_stack,
+ osb->uuid_str,
strlen(osb->uuid_str),
ocfs2_do_node_down, osb,
&conn);
mlog_errno(status);
mlog(ML_ERROR,
"could not find this host's node number\n");
- ocfs2_cluster_disconnect(conn);
+ ocfs2_cluster_disconnect(conn, 0);
goto bail;
}
local:
ocfs2_super_lock_res_init(&osb->osb_super_lockres, osb);
ocfs2_rename_lock_res_init(&osb->osb_rename_lockres, osb);
+ ocfs2_nfs_sync_lock_res_init(&osb->osb_nfs_sync_lockres, osb);
+ ocfs2_orphan_scan_lock_res_init(&osb->osb_orphan_scan.os_lockres, osb);
osb->cconn = conn;
return status;
}
-void ocfs2_dlm_shutdown(struct ocfs2_super *osb)
+void ocfs2_dlm_shutdown(struct ocfs2_super *osb,
+ int hangup_pending)
{
mlog_entry_void();
ocfs2_lock_res_free(&osb->osb_super_lockres);
ocfs2_lock_res_free(&osb->osb_rename_lockres);
+ ocfs2_lock_res_free(&osb->osb_nfs_sync_lockres);
+ ocfs2_lock_res_free(&osb->osb_orphan_scan.os_lockres);
- ocfs2_cluster_disconnect(osb->cconn);
+ ocfs2_cluster_disconnect(osb->cconn, hangup_pending);
osb->cconn = NULL;
ocfs2_dlm_shutdown_debug(osb);
lockres->l_unlock_action);
spin_lock_irqsave(&lockres->l_lock, flags);
- /* We tried to cancel a convert request, but it was already
- * granted. All we want to do here is clear our unlock
- * state. The wake_up call done at the bottom is redundant
- * (ocfs2_prepare_cancel_convert doesn't sleep on this) but doesn't
- * hurt anything anyway */
- if (error == -DLM_ECANCEL &&
- lockres->l_unlock_action == OCFS2_UNLOCK_CANCEL_CONVERT) {
- mlog(0, "Got cancelgrant for %s\n", lockres->l_name);
-
- /* We don't clear the busy flag in this case as it
- * should have been cleared by the ast which the dlm
- * has called. */
- goto complete_unlock;
- }
-
- /* DLM_EUNLOCK is the success code for unlock */
- if (error != -DLM_EUNLOCK) {
+ if (error) {
mlog(ML_ERROR, "Dlm passes error %d for lock %s, "
"unlock_action %d\n", error, lockres->l_name,
lockres->l_unlock_action);
spin_unlock_irqrestore(&lockres->l_lock, flags);
+ mlog_exit_void();
return;
}
case OCFS2_UNLOCK_CANCEL_CONVERT:
mlog(0, "Cancel convert success for %s\n", lockres->l_name);
lockres->l_action = OCFS2_AST_INVALID;
+ /* Downconvert thread may have requeued this lock, we
+ * need to wake it. */
+ if (lockres->l_flags & OCFS2_LOCK_BLOCKED)
+ ocfs2_wake_downconvert_thread(ocfs2_get_lockres_osb(lockres));
break;
case OCFS2_UNLOCK_DROP_LOCK:
lockres->l_level = DLM_LOCK_IV;
}
lockres_clear_flags(lockres, OCFS2_LOCK_BUSY);
-complete_unlock:
lockres->l_unlock_action = OCFS2_UNLOCK_INVALID;
- spin_unlock_irqrestore(&lockres->l_lock, flags);
-
wake_up(&lockres->l_event);
+ spin_unlock_irqrestore(&lockres->l_lock, flags);
mlog_exit_void();
}
if (ret) {
ocfs2_log_dlm_error("ocfs2_dlm_unlock", ret, lockres);
mlog(ML_ERROR, "lockres flags: %lu\n", lockres->l_flags);
- /* XXX Need to abstract this */
- dlm_print_one_lock(lockres->l_lksb.lksb_o2dlm.lockid);
+ ocfs2_dlm_dump_lksb(&lockres->l_lksb);
BUG();
}
- mlog(0, "lock %s, successfull return from ocfs2_dlm_unlock\n",
+ mlog(0, "lock %s, successful return from ocfs2_dlm_unlock\n",
lockres->l_name);
ocfs2_wait_on_busy_lock(lockres);
/* Mark the lockres as being dropped. It will no longer be
* queued if blocking, but we still may have to wait on it
* being dequeued from the downconvert thread before we can consider
- * it safe to drop.
+ * it safe to drop.
*
* You can *not* attempt to call cluster_lock on this lockres anymore. */
void ocfs2_mark_lockres_freeing(struct ocfs2_lock_res *lockres)
{
ocfs2_simple_drop_lockres(osb, &osb->osb_super_lockres);
ocfs2_simple_drop_lockres(osb, &osb->osb_rename_lockres);
+ ocfs2_simple_drop_lockres(osb, &osb->osb_nfs_sync_lockres);
+ ocfs2_simple_drop_lockres(osb, &osb->osb_orphan_scan.os_lockres);
}
int ocfs2_drop_inode_locks(struct inode *inode)
return status;
}
-static void ocfs2_prepare_downconvert(struct ocfs2_lock_res *lockres,
- int new_level)
+static unsigned int ocfs2_prepare_downconvert(struct ocfs2_lock_res *lockres,
+ int new_level)
{
assert_spin_locked(&lockres->l_lock);
lockres->l_action = OCFS2_AST_DOWNCONVERT;
lockres->l_requested = new_level;
lockres_or_flags(lockres, OCFS2_LOCK_BUSY);
+ return lockres_set_pending(lockres);
}
static int ocfs2_downconvert_lock(struct ocfs2_super *osb,
struct ocfs2_lock_res *lockres,
int new_level,
- int lvb)
+ int lvb,
+ unsigned int generation)
{
int ret;
u32 dlm_flags = DLM_LKF_CONVERT;
lockres->l_name,
OCFS2_LOCK_ID_MAX_LEN - 1,
lockres);
+ lockres_clear_pending(lockres, generation, osb);
if (ret) {
ocfs2_log_dlm_error("ocfs2_dlm_lock", ret, lockres);
ocfs2_recover_from_dlm_error(lockres, 1);
int new_level;
int ret = 0;
int set_lvb = 0;
+ unsigned int gen;
mlog_entry_void();
recheck:
if (lockres->l_flags & OCFS2_LOCK_BUSY) {
+ /* XXX
+ * This is a *big* race. The OCFS2_LOCK_PENDING flag
+ * exists entirely for one reason - another thread has set
+ * OCFS2_LOCK_BUSY, but has *NOT* yet called dlm_lock().
+ *
+ * If we do ocfs2_cancel_convert() before the other thread
+ * calls dlm_lock(), our cancel will do nothing. We will
+ * get no ast, and we will have no way of knowing the
+ * cancel failed. Meanwhile, the other thread will call
+ * into dlm_lock() and wait...forever.
+ *
+ * Why forever? Because another node has asked for the
+ * lock first; that's why we're here in unblock_lock().
+ *
+ * The solution is OCFS2_LOCK_PENDING. When PENDING is
+ * set, we just requeue the unblock. Only when the other
+ * thread has called dlm_lock() and cleared PENDING will
+ * we then cancel their request.
+ *
+ * All callers of dlm_lock() must set OCFS2_DLM_PENDING
+ * at the same time they set OCFS2_DLM_BUSY. They must
+ * clear OCFS2_DLM_PENDING after dlm_lock() returns.
+ */
+ if (lockres->l_flags & OCFS2_LOCK_PENDING)
+ goto leave_requeue;
+
ctl->requeue = 1;
ret = ocfs2_prepare_cancel_convert(osb, lockres);
spin_unlock_irqrestore(&lockres->l_lock, flags);
lockres->l_ops->set_lvb(lockres);
}
- ocfs2_prepare_downconvert(lockres, new_level);
+ gen = ocfs2_prepare_downconvert(lockres, new_level);
spin_unlock_irqrestore(&lockres->l_lock, flags);
- ret = ocfs2_downconvert_lock(osb, lockres, new_level, set_lvb);
+ ret = ocfs2_downconvert_lock(osb, lockres, new_level, set_lvb,
+ gen);
+
leave:
mlog_exit(ret);
return ret;
return UNBLOCK_CONTINUE;
}
-static int ocfs2_check_meta_downconvert(struct ocfs2_lock_res *lockres,
- int new_level)
+static int ocfs2_ci_checkpointed(struct ocfs2_caching_info *ci,
+ struct ocfs2_lock_res *lockres,
+ int new_level)
{
- struct inode *inode = ocfs2_lock_res_inode(lockres);
- int checkpointed = ocfs2_inode_fully_checkpointed(inode);
+ int checkpointed = ocfs2_ci_fully_checkpointed(ci);
BUG_ON(new_level != DLM_LOCK_NL && new_level != DLM_LOCK_PR);
BUG_ON(lockres->l_level != DLM_LOCK_EX && !checkpointed);
if (checkpointed)
return 1;
- ocfs2_start_checkpoint(OCFS2_SB(inode->i_sb));
+ ocfs2_start_checkpoint(OCFS2_SB(ocfs2_metadata_cache_get_super(ci)));
return 0;
}
+static int ocfs2_check_meta_downconvert(struct ocfs2_lock_res *lockres,
+ int new_level)
+{
+ struct inode *inode = ocfs2_lock_res_inode(lockres);
+
+ return ocfs2_ci_checkpointed(INODE_CACHE(inode), lockres, new_level);
+}
+
static void ocfs2_set_meta_lvb(struct ocfs2_lock_res *lockres)
{
struct inode *inode = ocfs2_lock_res_inode(lockres);
return UNBLOCK_CONTINUE_POST;
}
+static int ocfs2_check_refcount_downconvert(struct ocfs2_lock_res *lockres,
+ int new_level)
+{
+ struct ocfs2_refcount_tree *tree =
+ ocfs2_lock_res_refcount_tree(lockres);
+
+ return ocfs2_ci_checkpointed(&tree->rf_ci, lockres, new_level);
+}
+
+static int ocfs2_refcount_convert_worker(struct ocfs2_lock_res *lockres,
+ int blocking)
+{
+ struct ocfs2_refcount_tree *tree =
+ ocfs2_lock_res_refcount_tree(lockres);
+
+ ocfs2_metadata_cache_purge(&tree->rf_ci);
+
+ return UNBLOCK_CONTINUE;
+}
+
+static void ocfs2_set_qinfo_lvb(struct ocfs2_lock_res *lockres)
+{
+ struct ocfs2_qinfo_lvb *lvb;
+ struct ocfs2_mem_dqinfo *oinfo = ocfs2_lock_res_qinfo(lockres);
+ struct mem_dqinfo *info = sb_dqinfo(oinfo->dqi_gi.dqi_sb,
+ oinfo->dqi_gi.dqi_type);
+
+ mlog_entry_void();
+
+ lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
+ lvb->lvb_version = OCFS2_QINFO_LVB_VERSION;
+ lvb->lvb_bgrace = cpu_to_be32(info->dqi_bgrace);
+ lvb->lvb_igrace = cpu_to_be32(info->dqi_igrace);
+ lvb->lvb_syncms = cpu_to_be32(oinfo->dqi_syncms);
+ lvb->lvb_blocks = cpu_to_be32(oinfo->dqi_gi.dqi_blocks);
+ lvb->lvb_free_blk = cpu_to_be32(oinfo->dqi_gi.dqi_free_blk);
+ lvb->lvb_free_entry = cpu_to_be32(oinfo->dqi_gi.dqi_free_entry);
+
+ mlog_exit_void();
+}
+
+void ocfs2_qinfo_unlock(struct ocfs2_mem_dqinfo *oinfo, int ex)
+{
+ struct ocfs2_lock_res *lockres = &oinfo->dqi_gqlock;
+ struct ocfs2_super *osb = OCFS2_SB(oinfo->dqi_gi.dqi_sb);
+ int level = ex ? DLM_LOCK_EX : DLM_LOCK_PR;
+
+ mlog_entry_void();
+ if (!ocfs2_is_hard_readonly(osb) && !ocfs2_mount_local(osb))
+ ocfs2_cluster_unlock(osb, lockres, level);
+ mlog_exit_void();
+}
+
+static int ocfs2_refresh_qinfo(struct ocfs2_mem_dqinfo *oinfo)
+{
+ struct mem_dqinfo *info = sb_dqinfo(oinfo->dqi_gi.dqi_sb,
+ oinfo->dqi_gi.dqi_type);
+ struct ocfs2_lock_res *lockres = &oinfo->dqi_gqlock;
+ struct ocfs2_qinfo_lvb *lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
+ struct buffer_head *bh = NULL;
+ struct ocfs2_global_disk_dqinfo *gdinfo;
+ int status = 0;
+
+ if (ocfs2_dlm_lvb_valid(&lockres->l_lksb) &&
+ lvb->lvb_version == OCFS2_QINFO_LVB_VERSION) {
+ info->dqi_bgrace = be32_to_cpu(lvb->lvb_bgrace);
+ info->dqi_igrace = be32_to_cpu(lvb->lvb_igrace);
+ oinfo->dqi_syncms = be32_to_cpu(lvb->lvb_syncms);
+ oinfo->dqi_gi.dqi_blocks = be32_to_cpu(lvb->lvb_blocks);
+ oinfo->dqi_gi.dqi_free_blk = be32_to_cpu(lvb->lvb_free_blk);
+ oinfo->dqi_gi.dqi_free_entry =
+ be32_to_cpu(lvb->lvb_free_entry);
+ } else {
+ status = ocfs2_read_quota_block(oinfo->dqi_gqinode, 0, &bh);
+ if (status) {
+ mlog_errno(status);
+ goto bail;
+ }
+ gdinfo = (struct ocfs2_global_disk_dqinfo *)
+ (bh->b_data + OCFS2_GLOBAL_INFO_OFF);
+ info->dqi_bgrace = le32_to_cpu(gdinfo->dqi_bgrace);
+ info->dqi_igrace = le32_to_cpu(gdinfo->dqi_igrace);
+ oinfo->dqi_syncms = le32_to_cpu(gdinfo->dqi_syncms);
+ oinfo->dqi_gi.dqi_blocks = le32_to_cpu(gdinfo->dqi_blocks);
+ oinfo->dqi_gi.dqi_free_blk = le32_to_cpu(gdinfo->dqi_free_blk);
+ oinfo->dqi_gi.dqi_free_entry =
+ le32_to_cpu(gdinfo->dqi_free_entry);
+ brelse(bh);
+ ocfs2_track_lock_refresh(lockres);
+ }
+
+bail:
+ return status;
+}
+
+/* Lock quota info, this function expects at least shared lock on the quota file
+ * so that we can safely refresh quota info from disk. */
+int ocfs2_qinfo_lock(struct ocfs2_mem_dqinfo *oinfo, int ex)
+{
+ struct ocfs2_lock_res *lockres = &oinfo->dqi_gqlock;
+ struct ocfs2_super *osb = OCFS2_SB(oinfo->dqi_gi.dqi_sb);
+ int level = ex ? DLM_LOCK_EX : DLM_LOCK_PR;
+ int status = 0;
+
+ mlog_entry_void();
+
+ /* On RO devices, locking really isn't needed... */
+ if (ocfs2_is_hard_readonly(osb)) {
+ if (ex)
+ status = -EROFS;
+ goto bail;
+ }
+ if (ocfs2_mount_local(osb))
+ goto bail;
+
+ status = ocfs2_cluster_lock(osb, lockres, level, 0, 0);
+ if (status < 0) {
+ mlog_errno(status);
+ goto bail;
+ }
+ if (!ocfs2_should_refresh_lock_res(lockres))
+ goto bail;
+ /* OK, we have the lock but we need to refresh the quota info */
+ status = ocfs2_refresh_qinfo(oinfo);
+ if (status)
+ ocfs2_qinfo_unlock(oinfo, ex);
+ ocfs2_complete_lock_res_refresh(lockres, status);
+bail:
+ mlog_exit(status);
+ return status;
+}
+
+int ocfs2_refcount_lock(struct ocfs2_refcount_tree *ref_tree, int ex)
+{
+ int status;
+ int level = ex ? DLM_LOCK_EX : DLM_LOCK_PR;
+ struct ocfs2_lock_res *lockres = &ref_tree->rf_lockres;
+ struct ocfs2_super *osb = lockres->l_priv;
+
+
+ if (ocfs2_is_hard_readonly(osb))
+ return -EROFS;
+
+ if (ocfs2_mount_local(osb))
+ return 0;
+
+ status = ocfs2_cluster_lock(osb, lockres, level, 0, 0);
+ if (status < 0)
+ mlog_errno(status);
+
+ return status;
+}
+
+void ocfs2_refcount_unlock(struct ocfs2_refcount_tree *ref_tree, int ex)
+{
+ int level = ex ? DLM_LOCK_EX : DLM_LOCK_PR;
+ struct ocfs2_lock_res *lockres = &ref_tree->rf_lockres;
+ struct ocfs2_super *osb = lockres->l_priv;
+
+ if (!ocfs2_mount_local(osb))
+ ocfs2_cluster_unlock(osb, lockres, level);
+}
+
/*
* This is the filesystem locking protocol. It provides the lock handling
* hooks for the underlying DLM. It has a maximum version number.
.lp_unlock_ast = ocfs2_unlock_ast,
};
-/* This interface isn't the final one, hence the less-than-perfect names */
-void dlmglue_init_stack(void)
+void ocfs2_set_locking_protocol(void)
{
- o2cb_get_stack(&lproto);
+ ocfs2_stack_glue_set_locking_protocol(&lproto);
}
-void dlmglue_exit_stack(void)
-{
- o2cb_put_stack();
-}
static void ocfs2_process_blocked_lock(struct ocfs2_super *osb,
struct ocfs2_lock_res *lockres)
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff