* @block: start physical block to free
* @count: number of blocks to free
*/
-void ext2_free_blocks (struct inode * inode, unsigned long block,
- unsigned long count)
+void ext2_free_blocks(struct inode * inode, ext2_fsblk_t block,
+ unsigned long count)
{
struct buffer_head *bitmap_bh = NULL;
struct buffer_head * bh2;
}
/**
- * find_next_reservable_window():
- * find a reservable space within the given range.
- * It does not allocate the reservation window for now:
- * alloc_new_reservation() will do the work later.
+ * find_next_reservable_window - Find a reservable space within the given range.
+ * @search_head: The list to search.
+ * @my_rsv: The reservation we're currently using.
+ * @sb: The super block.
+ * @start_block: The first block we consider to start the real search from
+ * @last_block: The maximum block number that our goal reservable space
+ * could start from.
*
- * @search_head: the head of the searching list;
- * This is not necessarily the list head of the whole filesystem
+ * It does not allocate the reservation window: alloc_new_reservation()
+ * will do the work later.
*
- * We have both head and start_block to assist the search
- * for the reservable space. The list starts from head,
- * but we will shift to the place where start_block is,
- * then start from there, when looking for a reservable space.
+ * We search the given range, rather than the whole reservation double
+ * linked list, (start_block, last_block) to find a free region that is
+ * of my size and has not been reserved.
*
- * @sb: the super block.
+ * @search_head is not necessarily the list head of the whole filesystem.
+ * We have both head and @start_block to assist the search for the
+ * reservable space. The list starts from head, but we will shift to
+ * the place where start_block is, then start from there, when looking
+ * for a reservable space.
*
- * @start_block: the first block we consider to start the real search from
- *
- * @last_block:
- * the maximum block number that our goal reservable space
- * could start from. This is normally the last block in this
- * group. The search will end when we found the start of next
- * possible reservable space is out of this boundary.
- * This could handle the cross boundary reservation window
- * request.
- *
- * basically we search from the given range, rather than the whole
- * reservation double linked list, (start_block, last_block)
- * to find a free region that is of my size and has not
- * been reserved.
+ * @last_block is normally the last block in this group. The search will end
+ * when we found the start of next possible reservable space is out
+ * of this boundary. This could handle the cross boundary reservation
+ * window request.
*
+ * Return: -1 if we could not find a range of sufficient size. If we could,
+ * return 0 and fill in @my_rsv with the range information.
*/
static int find_next_reservable_window(
struct ext2_reserve_window_node *search_head,
}
/**
- * alloc_new_reservation()--allocate a new reservation window
- *
- * To make a new reservation, we search part of the filesystem
- * reservation list (the list that inside the group). We try to
- * allocate a new reservation window near the allocation goal,
- * or the beginning of the group, if there is no goal.
- *
- * We first find a reservable space after the goal, then from
- * there, we check the bitmap for the first free block after
- * it. If there is no free block until the end of group, then the
- * whole group is full, we failed. Otherwise, check if the free
- * block is inside the expected reservable space, if so, we
- * succeed.
- * If the first free block is outside the reservable space, then
- * start from the first free block, we search for next available
- * space, and go on.
+ * alloc_new_reservation - Allocate a new reservation window.
+ * @my_rsv: The reservation we're currently using.
+ * @grp_goal: The goal block relative to the start of the group.
+ * @sb: The super block.
+ * @group: The group we are trying to allocate in.
+ * @bitmap_bh: The block group block bitmap.
*
- * on succeed, a new reservation will be found and inserted into the list
- * It contains at least one free block, and it does not overlap with other
- * reservation windows.
+ * To make a new reservation, we search part of the filesystem reservation
+ * list (the list inside the group). We try to allocate a new
+ * reservation window near @grp_goal, or the beginning of the
+ * group, if @grp_goal is negative.
*
- * failed: we failed to find a reservation window in this group
+ * We first find a reservable space after the goal, then from there,
+ * we check the bitmap for the first free block after it. If there is
+ * no free block until the end of group, then the whole group is full,
+ * we failed. Otherwise, check if the free block is inside the expected
+ * reservable space, if so, we succeed.
*
- * @my_rsv: the reservation
+ * If the first free block is outside the reservable space, then start
+ * from the first free block, we search for next available space, and
+ * go on.
*
- * @grp_goal: The goal (group-relative). It is where the search for a
- * free reservable space should start from.
- * if we have a goal(goal >0 ), then start from there,
- * no goal(goal = -1), we start from the first block
- * of the group.
- *
- * @sb: the super block
- * @group: the group we are trying to allocate in
- * @bitmap_bh: the block group block bitmap
+ * on succeed, a new reservation will be found and inserted into the
+ * list. It contains at least one free block, and it does not overlap
+ * with other reservation windows.
*
+ * Return: 0 on success, -1 if we failed to find a reservation window
+ * in this group
*/
static int alloc_new_reservation(struct ext2_reserve_window_node *my_rsv,
ext2_grpblk_t grp_goal, struct super_block *sb,
if ((my_rsv->rsv_start > group_last_block) ||
(my_rsv->rsv_end < group_first_block)) {
+ ext2_error(sb, __func__,
+ "Reservation out of group %u range goal %d fsb[%lu,%lu] rsv[%lu, %lu]",
+ group, grp_goal, group_first_block,
+ group_last_block, my_rsv->rsv_start,
+ my_rsv->rsv_end);
rsv_window_dump(&EXT2_SB(sb)->s_rsv_window_root, 1);
- BUG();
+ return -1;
}
ret = ext2_try_to_allocate(sb, group, bitmap_bh, grp_goal,
&num, &my_rsv->rsv_window);
* @goal: given target block(filesystem wide)
* @count: target number of blocks to allocate
* @errp: error code
+ * @flags: allocate flags
*
* ext2_new_blocks uses a goal block to assist allocation. If the goal is
* free, or there is a free block within 32 blocks of the goal, that block
* This function also updates quota and i_blocks field.
*/
ext2_fsblk_t ext2_new_blocks(struct inode *inode, ext2_fsblk_t goal,
- unsigned long *count, int *errp)
+ unsigned long *count, int *errp, unsigned int flags)
{
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *gdp_bh;
es = EXT2_SB(sb)->s_es;
ext2_debug("goal=%lu.\n", goal);
/*
- * Allocate a block from reservation only when
- * filesystem is mounted with reservation(default,-o reservation), and
- * it's a regular file, and
- * the desired window size is greater than 0 (One could use ioctl
- * command EXT2_IOC_SETRSVSZ to set the window size to 0 to turn off
- * reservation on that particular file)
+ * Allocate a block from reservation only when the filesystem is
+ * mounted with reservation(default,-o reservation), and it's a regular
+ * file, and the desired window size is greater than 0 (One could use
+ * ioctl command EXT2_IOC_SETRSVSZ to set the window size to 0 to turn
+ * off reservation on that particular file). Also do not use the
+ * reservation window if the caller asked us not to do it.
*/
block_i = EXT2_I(inode)->i_block_alloc_info;
- if (block_i) {
+ if (!(flags & EXT2_ALLOC_NORESERVE) && block_i) {
windowsz = block_i->rsv_window_node.rsv_goal_size;
if (windowsz > 0)
my_rsv = &block_i->rsv_window_node;
return 0;
}
-ext2_fsblk_t ext2_new_block(struct inode *inode, unsigned long goal, int *errp)
-{
- unsigned long count = 1;
-
- return ext2_new_blocks(inode, goal, &count, errp);
-}
-
#ifdef EXT2FS_DEBUG
unsigned long ext2_count_free(struct buffer_head *map, unsigned int numchars)
/*
* Dquot List Management:
- * The quota code uses four lists for dquot management: the inuse_list,
- * free_dquots, dqi_dirty_list, and dquot_hash[] array. A single dquot
- * structure may be on some of those lists, depending on its current state.
+ * The quota code uses five lists for dquot management: the inuse_list,
+ * releasing_dquots, free_dquots, dqi_dirty_list, and dquot_hash[] array.
+ * A single dquot structure may be on some of those lists, depending on
+ * its current state.
*
* All dquots are placed to the end of inuse_list when first created, and this
* list is used for invalidate operation, which must look at every dquot.
*
+ * When the last reference of a dquot will be dropped, the dquot will be
+ * added to releasing_dquots. We'd then queue work item which would call
+ * synchronize_srcu() and after that perform the final cleanup of all the
+ * dquots on the list. Both releasing_dquots and free_dquots use the
+ * dq_free list_head in the dquot struct. When a dquot is removed from
+ * releasing_dquots, a reference count is always subtracted, and if
+ * dq_count == 0 at that point, the dquot will be added to the free_dquots.
+ *
* Unused dquots (dq_count == 0) are added to the free_dquots list when freed,
* and this list is searched whenever we need an available dquot. Dquots are
* removed from the list as soon as they are used again, and
static LIST_HEAD(inuse_list);
static LIST_HEAD(free_dquots);
+static LIST_HEAD(releasing_dquots);
static unsigned int dq_hash_bits, dq_hash_mask;
static struct hlist_head *dquot_hash;
static qsize_t __inode_get_rsv_space(struct inode *inode);
static int __dquot_initialize(struct inode *inode, int type);
+static void quota_release_workfn(struct work_struct *work);
+static DECLARE_DELAYED_WORK(quota_release_work, quota_release_workfn);
+
static inline unsigned int
hashfn(const struct super_block *sb, struct kqid qid)
{
dqstats_inc(DQST_FREE_DQUOTS);
}
+static inline void put_releasing_dquots(struct dquot *dquot)
+{
+ list_add_tail(&dquot->dq_free, &releasing_dquots);
+}
+
static inline void remove_free_dquot(struct dquot *dquot)
{
if (list_empty(&dquot->dq_free))
return;
list_del_init(&dquot->dq_free);
- dqstats_dec(DQST_FREE_DQUOTS);
+ if (!atomic_read(&dquot->dq_count))
+ dqstats_dec(DQST_FREE_DQUOTS);
}
static inline void put_inuse(struct dquot *dquot)
mutex_unlock(&dquot->dq_lock);
}
+static inline int dquot_active(struct dquot *dquot)
+{
+ return test_bit(DQ_ACTIVE_B, &dquot->dq_flags);
+}
+
static inline int dquot_dirty(struct dquot *dquot)
{
return test_bit(DQ_MOD_B, &dquot->dq_flags);
{
int ret = 1;
- if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags))
+ if (!dquot_active(dquot))
return 0;
if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NOLIST_DIRTY)
return test_and_set_bit(DQ_MOD_B, &dquot->dq_flags);
/* If quota is dirty already, we don't have to acquire dq_list_lock */
- if (test_bit(DQ_MOD_B, &dquot->dq_flags))
+ if (dquot_dirty(dquot))
return 1;
spin_lock(&dq_list_lock);
smp_mb__before_atomic();
set_bit(DQ_READ_B, &dquot->dq_flags);
/* Instantiate dquot if needed */
- if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags) && !dquot->dq_off) {
+ if (!dquot_active(dquot) && !dquot->dq_off) {
ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot);
/* Write the info if needed */
if (info_dirty(&dqopt->info[dquot->dq_id.type])) {
goto out_lock;
/* Inactive dquot can be only if there was error during read/init
* => we have better not writing it */
- if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags))
+ if (dquot_active(dquot))
ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot);
else
ret = -EIO;
struct dquot *dquot, *tmp;
restart:
+ flush_delayed_work("a_release_work);
+
spin_lock(&dq_list_lock);
list_for_each_entry_safe(dquot, tmp, &inuse_list, dq_inuse) {
if (dquot->dq_sb != sb)
continue;
/* Wait for dquot users */
if (atomic_read(&dquot->dq_count)) {
+ /* dquot in releasing_dquots, flush and retry */
+ if (!list_empty(&dquot->dq_free)) {
+ spin_unlock(&dq_list_lock);
+ goto restart;
+ }
+
atomic_inc(&dquot->dq_count);
spin_unlock(&dq_list_lock);
/*
spin_lock(&dq_list_lock);
list_for_each_entry(dquot, &inuse_list, dq_inuse) {
- if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags))
+ if (!dquot_active(dquot))
continue;
if (dquot->dq_sb != sb)
continue;
* outstanding call and recheck the DQ_ACTIVE_B after that.
*/
wait_on_dquot(dquot);
- if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
+ if (dquot_active(dquot)) {
ret = fn(dquot, priv);
if (ret < 0)
goto out;
}
EXPORT_SYMBOL(dquot_scan_active);
+static inline int dquot_write_dquot(struct dquot *dquot)
+{
+ int ret = dquot->dq_sb->dq_op->write_dquot(dquot);
+ if (ret < 0) {
+ quota_error(dquot->dq_sb, "Can't write quota structure "
+ "(error %d). Quota may get out of sync!", ret);
+ /* Clear dirty bit anyway to avoid infinite loop. */
+ clear_dquot_dirty(dquot);
+ }
+ return ret;
+}
+
/* Write all dquot structures to quota files */
int dquot_writeback_dquots(struct super_block *sb, int type)
{
dquot = list_first_entry(&dirty, struct dquot,
dq_dirty);
- WARN_ON(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags));
+ WARN_ON(!dquot_active(dquot));
/* Now we have active dquot from which someone is
* holding reference so we can safely just increase
* use count */
dqgrab(dquot);
spin_unlock(&dq_list_lock);
- err = sb->dq_op->write_dquot(dquot);
- if (err) {
- /*
- * Clear dirty bit anyway to avoid infinite
- * loop here.
- */
- clear_dquot_dirty(dquot);
- if (!ret)
- ret = err;
- }
+ err = dquot_write_dquot(dquot);
+ if (err && !ret)
+ ret = err;
dqput(dquot);
spin_lock(&dq_list_lock);
}
.seeks = DEFAULT_SEEKS,
};
+/*
+ * Safely release dquot and put reference to dquot.
+ */
+static void quota_release_workfn(struct work_struct *work)
+{
+ struct dquot *dquot;
+ struct list_head rls_head;
+
+ spin_lock(&dq_list_lock);
+ /* Exchange the list head to avoid livelock. */
+ list_replace_init(&releasing_dquots, &rls_head);
+ spin_unlock(&dq_list_lock);
+
+restart:
+ synchronize_srcu(&dquot_srcu);
+ spin_lock(&dq_list_lock);
+ while (!list_empty(&rls_head)) {
+ dquot = list_first_entry(&rls_head, struct dquot, dq_free);
+ /* Dquot got used again? */
+ if (atomic_read(&dquot->dq_count) > 1) {
+ remove_free_dquot(dquot);
+ atomic_dec(&dquot->dq_count);
+ continue;
+ }
+ if (dquot_dirty(dquot)) {
+ spin_unlock(&dq_list_lock);
+ /* Commit dquot before releasing */
+ dquot_write_dquot(dquot);
+ goto restart;
+ }
+ if (dquot_active(dquot)) {
+ spin_unlock(&dq_list_lock);
+ dquot->dq_sb->dq_op->release_dquot(dquot);
+ goto restart;
+ }
+ /* Dquot is inactive and clean, now move it to free list */
+ remove_free_dquot(dquot);
+ atomic_dec(&dquot->dq_count);
+ put_dquot_last(dquot);
+ }
+ spin_unlock(&dq_list_lock);
+}
+
/*
* Put reference to dquot
*/
void dqput(struct dquot *dquot)
{
- int ret;
-
if (!dquot)
return;
#ifdef CONFIG_QUOTA_DEBUG
}
#endif
dqstats_inc(DQST_DROPS);
-we_slept:
+
spin_lock(&dq_list_lock);
if (atomic_read(&dquot->dq_count) > 1) {
/* We have more than one user... nothing to do */
spin_unlock(&dq_list_lock);
return;
}
+
/* Need to release dquot? */
- if (dquot_dirty(dquot)) {
- spin_unlock(&dq_list_lock);
- /* Commit dquot before releasing */
- ret = dquot->dq_sb->dq_op->write_dquot(dquot);
- if (ret < 0) {
- quota_error(dquot->dq_sb, "Can't write quota structure"
- " (error %d). Quota may get out of sync!",
- ret);
- /*
- * We clear dirty bit anyway, so that we avoid
- * infinite loop here
- */
- clear_dquot_dirty(dquot);
- }
- goto we_slept;
- }
- if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
- spin_unlock(&dq_list_lock);
- dquot->dq_sb->dq_op->release_dquot(dquot);
- goto we_slept;
- }
- atomic_dec(&dquot->dq_count);
#ifdef CONFIG_QUOTA_DEBUG
/* sanity check */
BUG_ON(!list_empty(&dquot->dq_free));
#endif
- put_dquot_last(dquot);
+ put_releasing_dquots(dquot);
spin_unlock(&dq_list_lock);
+ queue_delayed_work(system_unbound_wq, "a_release_work, 1);
}
EXPORT_SYMBOL(dqput);
* already finished or it will be canceled due to dq_count > 1 test */
wait_on_dquot(dquot);
/* Read the dquot / allocate space in quota file */
- if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
+ if (!dquot_active(dquot)) {
int err;
err = sb->dq_op->acquire_dquot(dquot);
return err;
}
-/*
- * Remove references to dquots from inode and add dquot to list for freeing
- * if we have the last reference to dquot
- */
-static void remove_inode_dquot_ref(struct inode *inode, int type,
- struct list_head *tofree_head)
-{
- struct dquot **dquots = i_dquot(inode);
- struct dquot *dquot = dquots[type];
-
- if (!dquot)
- return;
-
- dquots[type] = NULL;
- if (list_empty(&dquot->dq_free)) {
- /*
- * The inode still has reference to dquot so it can't be in the
- * free list
- */
- spin_lock(&dq_list_lock);
- list_add(&dquot->dq_free, tofree_head);
- spin_unlock(&dq_list_lock);
- } else {
- /*
- * Dquot is already in a list to put so we won't drop the last
- * reference here.
- */
- dqput(dquot);
- }
-}
-
-/*
- * Free list of dquots
- * Dquots are removed from inodes and no new references can be got so we are
- * the only ones holding reference
- */
-static void put_dquot_list(struct list_head *tofree_head)
-{
- struct list_head *act_head;
- struct dquot *dquot;
-
- act_head = tofree_head->next;
- while (act_head != tofree_head) {
- dquot = list_entry(act_head, struct dquot, dq_free);
- act_head = act_head->next;
- /* Remove dquot from the list so we won't have problems... */
- list_del_init(&dquot->dq_free);
- dqput(dquot);
- }
-}
-
-static void remove_dquot_ref(struct super_block *sb, int type,
- struct list_head *tofree_head)
+static void remove_dquot_ref(struct super_block *sb, int type)
{
struct inode *inode;
#ifdef CONFIG_QUOTA_DEBUG
*/
spin_lock(&dq_data_lock);
if (!IS_NOQUOTA(inode)) {
+ struct dquot **dquots = i_dquot(inode);
+ struct dquot *dquot = dquots[type];
+
#ifdef CONFIG_QUOTA_DEBUG
if (unlikely(inode_get_rsv_space(inode) > 0))
reserved = 1;
#endif
- remove_inode_dquot_ref(inode, type, tofree_head);
+ dquots[type] = NULL;
+ if (dquot)
+ dqput(dquot);
}
spin_unlock(&dq_data_lock);
}
/* Gather all references from inodes and drop them */
static void drop_dquot_ref(struct super_block *sb, int type)
{
- LIST_HEAD(tofree_head);
-
- if (sb->dq_op) {
- remove_dquot_ref(sb, type, &tofree_head);
- synchronize_srcu(&dquot_srcu);
- put_dquot_list(&tofree_head);
- }
+ if (sb->dq_op)
+ remove_dquot_ref(sb, type);
}
static inline
return QUOTA_NL_NOWARN;
}
-static int dquot_active(const struct inode *inode)
+static int inode_quota_active(const struct inode *inode)
{
struct super_block *sb = inode->i_sb;
qsize_t rsv;
int ret = 0;
- if (!dquot_active(inode))
+ if (!inode_quota_active(inode))
return 0;
dquots = i_dquot(inode);
struct dquot **dquots;
int i;
- if (!dquot_active(inode))
+ if (!inode_quota_active(inode))
return false;
dquots = i_dquot(inode);
int reserve = flags & DQUOT_SPACE_RESERVE;
struct dquot **dquots;
- if (!dquot_active(inode)) {
+ if (!inode_quota_active(inode)) {
if (reserve) {
spin_lock(&inode->i_lock);
*inode_reserved_space(inode) += number;
struct dquot_warn warn[MAXQUOTAS];
struct dquot * const *dquots;
- if (!dquot_active(inode))
+ if (!inode_quota_active(inode))
return 0;
for (cnt = 0; cnt < MAXQUOTAS; cnt++)
warn[cnt].w_type = QUOTA_NL_NOWARN;
struct dquot **dquots;
int cnt, index;
- if (!dquot_active(inode)) {
+ if (!inode_quota_active(inode)) {
spin_lock(&inode->i_lock);
*inode_reserved_space(inode) -= number;
__inode_add_bytes(inode, number);
struct dquot **dquots;
int cnt, index;
- if (!dquot_active(inode)) {
+ if (!inode_quota_active(inode)) {
spin_lock(&inode->i_lock);
*inode_reserved_space(inode) += number;
__inode_sub_bytes(inode, number);
struct dquot **dquots;
int reserve = flags & DQUOT_SPACE_RESERVE, index;
- if (!dquot_active(inode)) {
+ if (!inode_quota_active(inode)) {
if (reserve) {
spin_lock(&inode->i_lock);
*inode_reserved_space(inode) -= number;
struct dquot * const *dquots;
int index;
- if (!dquot_active(inode))
+ if (!inode_quota_active(inode))
return;
dquots = i_dquot(inode);
struct super_block *sb = inode->i_sb;
int ret;
- if (!dquot_active(inode))
+ if (!inode_quota_active(inode))
return 0;
if (i_uid_needs_update(idmap, iattr, inode)) {
struct quota_info *dqopt = sb_dqopt(sb);
int error;
+ lockdep_assert_held_write(&sb->s_umount);
+
/* Just unsuspend quotas? */
BUG_ON(flags & DQUOT_SUSPENDED);
- /* s_umount should be held in exclusive mode */
- if (WARN_ON_ONCE(down_read_trylock(&sb->s_umount)))
- up_read(&sb->s_umount);
if (!fmt)
return -ESRCH;
projects / linux-2.6-microblaze.git / commitdiff