* - d_lru
* - d_count
* - d_unhashed()
- * - d_parent and d_subdirs
- * - childrens' d_child and d_parent
+ * - d_parent and d_chilren
+ * - childrens' d_sib and d_parent
* - d_u.d_alias, d_inode
*
* Ordering:
.mode = 0444,
.proc_handler = proc_nr_dentry,
},
- { }
};
static int __init init_fs_dcache_sysctls(void)
dentry->d_inode = inode;
flags = READ_ONCE(dentry->d_flags);
- flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
+ flags &= ~DCACHE_ENTRY_TYPE;
flags |= type_flags;
smp_store_release(&dentry->d_flags, flags);
}
{
unsigned flags = READ_ONCE(dentry->d_flags);
- flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU);
+ flags &= ~DCACHE_ENTRY_TYPE;
WRITE_ONCE(dentry->d_flags, flags);
dentry->d_inode = NULL;
if (dentry->d_flags & DCACHE_LRU_LIST)
this_cpu_inc(nr_dentry_unused);
if (d_is_negative(dentry))
this_cpu_inc(nr_dentry_negative);
- WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
+ WARN_ON_ONCE(!list_lru_add_obj(
+ &dentry->d_sb->s_dentry_lru, &dentry->d_lru));
}
static void d_lru_del(struct dentry *dentry)
this_cpu_dec(nr_dentry_unused);
if (d_is_negative(dentry))
this_cpu_dec(nr_dentry_negative);
- WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
+ WARN_ON_ONCE(!list_lru_del_obj(
+ &dentry->d_sb->s_dentry_lru, &dentry->d_lru));
}
static void d_shrink_del(struct dentry *dentry)
}
EXPORT_SYMBOL(d_drop);
- static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent)
+ static inline void dentry_unlist(struct dentry *dentry)
{
struct dentry *next;
/*
* attached to the dentry tree
*/
dentry->d_flags |= DCACHE_DENTRY_KILLED;
- if (unlikely(list_empty(&dentry->d_child)))
+ if (unlikely(hlist_unhashed(&dentry->d_sib)))
return;
- __list_del_entry(&dentry->d_child);
+ __hlist_del(&dentry->d_sib);
/*
* Cursors can move around the list of children. While we'd been
- * a normal list member, it didn't matter - ->d_child.next would've
+ * a normal list member, it didn't matter - ->d_sib.next would've
* been updated. However, from now on it won't be and for the
* things like d_walk() it might end up with a nasty surprise.
* Normally d_walk() doesn't care about cursors moving around -
* of its own, we get through it without ever unlocking the parent.
* There is one exception, though - if we ascend from a child that
* gets killed as soon as we unlock it, the next sibling is found
- * using the value left in its ->d_child.next. And if _that_
+ * using the value left in its ->d_sib.next. And if _that_
* pointed to a cursor, and cursor got moved (e.g. by lseek())
* before d_walk() regains parent->d_lock, we'll end up skipping
* everything the cursor had been moved past.
*
- * Solution: make sure that the pointer left behind in ->d_child.next
+ * Solution: make sure that the pointer left behind in ->d_sib.next
* points to something that won't be moving around. I.e. skip the
* cursors.
*/
- while (dentry->d_child.next != &parent->d_subdirs) {
- next = list_entry(dentry->d_child.next, struct dentry, d_child);
+ while (dentry->d_sib.next) {
+ next = hlist_entry(dentry->d_sib.next, struct dentry, d_sib);
if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR)))
break;
- dentry->d_child.next = next->d_child.next;
+ dentry->d_sib.next = next->d_sib.next;
}
}
- static void __dentry_kill(struct dentry *dentry)
+ static struct dentry *__dentry_kill(struct dentry *dentry)
{
struct dentry *parent = NULL;
bool can_free = true;
- if (!IS_ROOT(dentry))
- parent = dentry->d_parent;
/*
* The dentry is now unrecoverably dead to the world.
}
/* if it was on the hash then remove it */
__d_drop(dentry);
- dentry_unlist(dentry, parent);
- if (parent)
- spin_unlock(&parent->d_lock);
if (dentry->d_inode)
dentry_unlink_inode(dentry);
else
if (dentry->d_op && dentry->d_op->d_release)
dentry->d_op->d_release(dentry);
- spin_lock(&dentry->d_lock);
- if (dentry->d_flags & DCACHE_SHRINK_LIST) {
- dentry->d_flags |= DCACHE_MAY_FREE;
- can_free = false;
+ cond_resched();
+ /* now that it's negative, ->d_parent is stable */
+ if (!IS_ROOT(dentry)) {
+ parent = dentry->d_parent;
+ spin_lock(&parent->d_lock);
}
+ spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+ dentry_unlist(dentry);
+ if (dentry->d_flags & DCACHE_SHRINK_LIST)
+ can_free = false;
spin_unlock(&dentry->d_lock);
if (likely(can_free))
dentry_free(dentry);
- cond_resched();
- }
-
- static struct dentry *__lock_parent(struct dentry *dentry)
- {
- struct dentry *parent;
- rcu_read_lock();
- spin_unlock(&dentry->d_lock);
- again:
- parent = READ_ONCE(dentry->d_parent);
- spin_lock(&parent->d_lock);
- /*
- * We can't blindly lock dentry until we are sure
- * that we won't violate the locking order.
- * Any changes of dentry->d_parent must have
- * been done with parent->d_lock held, so
- * spin_lock() above is enough of a barrier
- * for checking if it's still our child.
- */
- if (unlikely(parent != dentry->d_parent)) {
+ if (parent && --parent->d_lockref.count) {
spin_unlock(&parent->d_lock);
- goto again;
+ return NULL;
}
- rcu_read_unlock();
- if (parent != dentry)
- spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
- else
- parent = NULL;
return parent;
}
- static inline struct dentry *lock_parent(struct dentry *dentry)
+ /*
+ * Lock a dentry for feeding it to __dentry_kill().
+ * Called under rcu_read_lock() and dentry->d_lock; the former
+ * guarantees that nothing we access will be freed under us.
+ * Note that dentry is *not* protected from concurrent dentry_kill(),
+ * d_delete(), etc.
+ *
+ * Return false if dentry is busy. Otherwise, return true and have
+ * that dentry's inode locked.
+ */
+
+ static bool lock_for_kill(struct dentry *dentry)
{
- struct dentry *parent = dentry->d_parent;
- if (IS_ROOT(dentry))
- return NULL;
- if (likely(spin_trylock(&parent->d_lock)))
- return parent;
- return __lock_parent(dentry);
+ struct inode *inode = dentry->d_inode;
+
+ if (unlikely(dentry->d_lockref.count))
+ return false;
+
+ if (!inode || likely(spin_trylock(&inode->i_lock)))
+ return true;
+
+ do {
+ spin_unlock(&dentry->d_lock);
+ spin_lock(&inode->i_lock);
+ spin_lock(&dentry->d_lock);
+ if (likely(inode == dentry->d_inode))
+ break;
+ spin_unlock(&inode->i_lock);
+ inode = dentry->d_inode;
+ } while (inode);
+ if (likely(!dentry->d_lockref.count))
+ return true;
+ if (inode)
+ spin_unlock(&inode->i_lock);
+ return false;
}
- static inline bool retain_dentry(struct dentry *dentry)
+ /*
+ * Decide if dentry is worth retaining. Usually this is called with dentry
+ * locked; if not locked, we are more limited and might not be able to tell
+ * without a lock. False in this case means "punt to locked path and recheck".
+ *
+ * In case we aren't locked, these predicates are not "stable". However, it is
+ * sufficient that at some point after we dropped the reference the dentry was
+ * hashed and the flags had the proper value. Other dentry users may have
+ * re-gotten a reference to the dentry and change that, but our work is done -
+ * we can leave the dentry around with a zero refcount.
+ */
+ static inline bool retain_dentry(struct dentry *dentry, bool locked)
{
- WARN_ON(d_in_lookup(dentry));
+ unsigned int d_flags;
- /* Unreachable? Get rid of it */
+ smp_rmb();
+ d_flags = READ_ONCE(dentry->d_flags);
+
+ // Unreachable? Nobody would be able to look it up, no point retaining
if (unlikely(d_unhashed(dentry)))
return false;
- if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED))
+ // Same if it's disconnected
+ if (unlikely(d_flags & DCACHE_DISCONNECTED))
return false;
- if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) {
- if (dentry->d_op->d_delete(dentry))
+ // ->d_delete() might tell us not to bother, but that requires
+ // ->d_lock; can't decide without it
+ if (unlikely(d_flags & DCACHE_OP_DELETE)) {
+ if (!locked || dentry->d_op->d_delete(dentry))
return false;
}
- if (unlikely(dentry->d_flags & DCACHE_DONTCACHE))
+ // Explicitly told not to bother
+ if (unlikely(d_flags & DCACHE_DONTCACHE))
return false;
- /* retain; LRU fodder */
- dentry->d_lockref.count--;
- if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST)))
+ // At this point it looks like we ought to keep it. We also might
+ // need to do something - put it on LRU if it wasn't there already
+ // and mark it referenced if it was on LRU, but not marked yet.
+ // Unfortunately, both actions require ->d_lock, so in lockless
+ // case we'd have to punt rather than doing those.
+ if (unlikely(!(d_flags & DCACHE_LRU_LIST))) {
+ if (!locked)
+ return false;
d_lru_add(dentry);
- else if (unlikely(!(dentry->d_flags & DCACHE_REFERENCED)))
+ } else if (unlikely(!(d_flags & DCACHE_REFERENCED))) {
+ if (!locked)
+ return false;
dentry->d_flags |= DCACHE_REFERENCED;
+ }
return true;
}
}
EXPORT_SYMBOL(d_mark_dontcache);
- /*
- * Finish off a dentry we've decided to kill.
- * dentry->d_lock must be held, returns with it unlocked.
- * Returns dentry requiring refcount drop, or NULL if we're done.
- */
- static struct dentry *dentry_kill(struct dentry *dentry)
- __releases(dentry->d_lock)
- {
- struct inode *inode = dentry->d_inode;
- struct dentry *parent = NULL;
-
- if (inode && unlikely(!spin_trylock(&inode->i_lock)))
- goto slow_positive;
-
- if (!IS_ROOT(dentry)) {
- parent = dentry->d_parent;
- if (unlikely(!spin_trylock(&parent->d_lock))) {
- parent = __lock_parent(dentry);
- if (likely(inode || !dentry->d_inode))
- goto got_locks;
- /* negative that became positive */
- if (parent)
- spin_unlock(&parent->d_lock);
- inode = dentry->d_inode;
- goto slow_positive;
- }
- }
- __dentry_kill(dentry);
- return parent;
-
- slow_positive:
- spin_unlock(&dentry->d_lock);
- spin_lock(&inode->i_lock);
- spin_lock(&dentry->d_lock);
- parent = lock_parent(dentry);
- got_locks:
- if (unlikely(dentry->d_lockref.count != 1)) {
- dentry->d_lockref.count--;
- } else if (likely(!retain_dentry(dentry))) {
- __dentry_kill(dentry);
- return parent;
- }
- /* we are keeping it, after all */
- if (inode)
- spin_unlock(&inode->i_lock);
- if (parent)
- spin_unlock(&parent->d_lock);
- spin_unlock(&dentry->d_lock);
- return NULL;
- }
-
/*
* Try to do a lockless dput(), and return whether that was successful.
*
* If unsuccessful, we return false, having already taken the dentry lock.
+ * In that case refcount is guaranteed to be zero and we have already
+ * decided that it's not worth keeping around.
*
* The caller needs to hold the RCU read lock, so that the dentry is
* guaranteed to stay around even if the refcount goes down to zero!
static inline bool fast_dput(struct dentry *dentry)
{
int ret;
- unsigned int d_flags;
-
- /*
- * If we have a d_op->d_delete() operation, we sould not
- * let the dentry count go to zero, so use "put_or_lock".
- */
- if (unlikely(dentry->d_flags & DCACHE_OP_DELETE))
- return lockref_put_or_lock(&dentry->d_lockref);
/*
- * .. otherwise, we can try to just decrement the
- * lockref optimistically.
+ * try to decrement the lockref optimistically.
*/
ret = lockref_put_return(&dentry->d_lockref);
*/
if (unlikely(ret < 0)) {
spin_lock(&dentry->d_lock);
- if (dentry->d_lockref.count > 1) {
- dentry->d_lockref.count--;
+ if (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) {
spin_unlock(&dentry->d_lock);
return true;
}
- return false;
+ dentry->d_lockref.count--;
+ goto locked;
}
/*
return true;
/*
- * Careful, careful. The reference count went down
- * to zero, but we don't hold the dentry lock, so
- * somebody else could get it again, and do another
- * dput(), and we need to not race with that.
- *
- * However, there is a very special and common case
- * where we don't care, because there is nothing to
- * do: the dentry is still hashed, it does not have
- * a 'delete' op, and it's referenced and already on
- * the LRU list.
- *
- * NOTE! Since we aren't locked, these values are
- * not "stable". However, it is sufficient that at
- * some point after we dropped the reference the
- * dentry was hashed and the flags had the proper
- * value. Other dentry users may have re-gotten
- * a reference to the dentry and change that, but
- * our work is done - we can leave the dentry
- * around with a zero refcount.
- *
- * Nevertheless, there are two cases that we should kill
- * the dentry anyway.
- * 1. free disconnected dentries as soon as their refcount
- * reached zero.
- * 2. free dentries if they should not be cached.
+ * Can we decide that decrement of refcount is all we needed without
+ * taking the lock? There's a very common case when it's all we need -
+ * dentry looks like it ought to be retained and there's nothing else
+ * to do.
*/
- smp_rmb();
- d_flags = READ_ONCE(dentry->d_flags);
- d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST |
- DCACHE_DISCONNECTED | DCACHE_DONTCACHE;
-
- /* Nothing to do? Dropping the reference was all we needed? */
- if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry))
+ if (retain_dentry(dentry, false))
return true;
/*
- * Not the fast normal case? Get the lock. We've already decremented
- * the refcount, but we'll need to re-check the situation after
- * getting the lock.
+ * Either not worth retaining or we can't tell without the lock.
+ * Get the lock, then. We've already decremented the refcount to 0,
+ * but we'll need to re-check the situation after getting the lock.
*/
spin_lock(&dentry->d_lock);
* else could have killed it and marked it dead. Either way, we
* don't need to do anything else.
*/
- if (dentry->d_lockref.count) {
+ locked:
+ if (dentry->d_lockref.count || retain_dentry(dentry, true)) {
spin_unlock(&dentry->d_lock);
return true;
}
-
- /*
- * Re-get the reference we optimistically dropped. We hold the
- * lock, and we just tested that it was zero, so we can just
- * set it to 1.
- */
- dentry->d_lockref.count = 1;
return false;
}
*/
void dput(struct dentry *dentry)
{
- while (dentry) {
- might_sleep();
-
- rcu_read_lock();
- if (likely(fast_dput(dentry))) {
- rcu_read_unlock();
- return;
- }
-
- /* Slow case: now with the dentry lock held */
+ if (!dentry)
+ return;
+ might_sleep();
+ rcu_read_lock();
+ if (likely(fast_dput(dentry))) {
rcu_read_unlock();
-
- if (likely(retain_dentry(dentry))) {
+ return;
+ }
+ while (lock_for_kill(dentry)) {
+ rcu_read_unlock();
+ dentry = __dentry_kill(dentry);
+ if (!dentry)
+ return;
+ if (retain_dentry(dentry, true)) {
spin_unlock(&dentry->d_lock);
return;
}
-
- dentry = dentry_kill(dentry);
+ rcu_read_lock();
}
+ rcu_read_unlock();
+ spin_unlock(&dentry->d_lock);
}
EXPORT_SYMBOL(dput);
- static void __dput_to_list(struct dentry *dentry, struct list_head *list)
+ static void to_shrink_list(struct dentry *dentry, struct list_head *list)
__must_hold(&dentry->d_lock)
{
- if (dentry->d_flags & DCACHE_SHRINK_LIST) {
- /* let the owner of the list it's on deal with it */
- --dentry->d_lockref.count;
- } else {
+ if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
if (dentry->d_flags & DCACHE_LRU_LIST)
d_lru_del(dentry);
- if (!--dentry->d_lockref.count)
- d_shrink_add(dentry, list);
+ d_shrink_add(dentry, list);
}
}
return;
}
rcu_read_unlock();
- if (!retain_dentry(dentry))
- __dput_to_list(dentry, list);
+ to_shrink_list(dentry, list);
spin_unlock(&dentry->d_lock);
}
- /* This must be called with d_lock held */
- static inline void __dget_dlock(struct dentry *dentry)
- {
- dentry->d_lockref.count++;
- }
-
- static inline void __dget(struct dentry *dentry)
- {
- lockref_get(&dentry->d_lockref);
- }
-
struct dentry *dget_parent(struct dentry *dentry)
{
int gotref;
if (hlist_empty(&inode->i_dentry))
return NULL;
alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
- __dget(alias);
+ lockref_get(&alias->d_lockref);
return alias;
}
hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
spin_lock(&alias->d_lock);
if (!d_unhashed(alias)) {
- __dget_dlock(alias);
+ dget_dlock(alias);
spin_unlock(&alias->d_lock);
return alias;
}
*/
void d_prune_aliases(struct inode *inode)
{
+ LIST_HEAD(dispose);
struct dentry *dentry;
- restart:
+
spin_lock(&inode->i_lock);
hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
spin_lock(&dentry->d_lock);
- if (!dentry->d_lockref.count) {
- struct dentry *parent = lock_parent(dentry);
- if (likely(!dentry->d_lockref.count)) {
- __dentry_kill(dentry);
- dput(parent);
- goto restart;
- }
- if (parent)
- spin_unlock(&parent->d_lock);
- }
+ if (!dentry->d_lockref.count)
+ to_shrink_list(dentry, &dispose);
spin_unlock(&dentry->d_lock);
}
spin_unlock(&inode->i_lock);
+ shrink_dentry_list(&dispose);
}
EXPORT_SYMBOL(d_prune_aliases);
- /*
- * Lock a dentry from shrink list.
- * Called under rcu_read_lock() and dentry->d_lock; the former
- * guarantees that nothing we access will be freed under us.
- * Note that dentry is *not* protected from concurrent dentry_kill(),
- * d_delete(), etc.
- *
- * Return false if dentry has been disrupted or grabbed, leaving
- * the caller to kick it off-list. Otherwise, return true and have
- * that dentry's inode and parent both locked.
- */
- static bool shrink_lock_dentry(struct dentry *dentry)
+ static inline void shrink_kill(struct dentry *victim)
{
- struct inode *inode;
- struct dentry *parent;
-
- if (dentry->d_lockref.count)
- return false;
-
- inode = dentry->d_inode;
- if (inode && unlikely(!spin_trylock(&inode->i_lock))) {
- spin_unlock(&dentry->d_lock);
- spin_lock(&inode->i_lock);
- spin_lock(&dentry->d_lock);
- if (unlikely(dentry->d_lockref.count))
- goto out;
- /* changed inode means that somebody had grabbed it */
- if (unlikely(inode != dentry->d_inode))
- goto out;
- }
-
- parent = dentry->d_parent;
- if (IS_ROOT(dentry) || likely(spin_trylock(&parent->d_lock)))
- return true;
-
- spin_unlock(&dentry->d_lock);
- spin_lock(&parent->d_lock);
- if (unlikely(parent != dentry->d_parent)) {
- spin_unlock(&parent->d_lock);
- spin_lock(&dentry->d_lock);
- goto out;
- }
- spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
- if (likely(!dentry->d_lockref.count))
- return true;
- spin_unlock(&parent->d_lock);
- out:
- if (inode)
- spin_unlock(&inode->i_lock);
- return false;
+ do {
+ rcu_read_unlock();
+ victim = __dentry_kill(victim);
+ rcu_read_lock();
+ } while (victim && lock_for_kill(victim));
+ rcu_read_unlock();
+ if (victim)
+ spin_unlock(&victim->d_lock);
}
void shrink_dentry_list(struct list_head *list)
{
while (!list_empty(list)) {
- struct dentry *dentry, *parent;
+ struct dentry *dentry;
dentry = list_entry(list->prev, struct dentry, d_lru);
spin_lock(&dentry->d_lock);
rcu_read_lock();
- if (!shrink_lock_dentry(dentry)) {
- bool can_free = false;
+ if (!lock_for_kill(dentry)) {
+ bool can_free;
rcu_read_unlock();
d_shrink_del(dentry);
- if (dentry->d_lockref.count < 0)
- can_free = dentry->d_flags & DCACHE_MAY_FREE;
+ can_free = dentry->d_flags & DCACHE_DENTRY_KILLED;
spin_unlock(&dentry->d_lock);
if (can_free)
dentry_free(dentry);
continue;
}
- rcu_read_unlock();
d_shrink_del(dentry);
- parent = dentry->d_parent;
- if (parent != dentry)
- __dput_to_list(parent, list);
- __dentry_kill(dentry);
+ shrink_kill(dentry);
}
}
*
* This is guaranteed by the fact that all LRU management
* functions are intermediated by the LRU API calls like
- * list_lru_add and list_lru_del. List movement in this file
+ * list_lru_add_obj and list_lru_del_obj. List movement in this file
* only ever occur through this functions or through callbacks
* like this one, that are called from the LRU API.
*
static void d_walk(struct dentry *parent, void *data,
enum d_walk_ret (*enter)(void *, struct dentry *))
{
- struct dentry *this_parent;
- struct list_head *next;
+ struct dentry *this_parent, *dentry;
unsigned seq = 0;
enum d_walk_ret ret;
bool retry = true;
break;
}
repeat:
- next = this_parent->d_subdirs.next;
+ dentry = d_first_child(this_parent);
resume:
- while (next != &this_parent->d_subdirs) {
- struct list_head *tmp = next;
- struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
- next = tmp->next;
-
+ hlist_for_each_entry_from(dentry, d_sib) {
if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR))
continue;
continue;
}
- if (!list_empty(&dentry->d_subdirs)) {
+ if (!hlist_empty(&dentry->d_children)) {
spin_unlock(&this_parent->d_lock);
spin_release(&dentry->d_lock.dep_map, _RET_IP_);
this_parent = dentry;
rcu_read_lock();
ascend:
if (this_parent != parent) {
- struct dentry *child = this_parent;
- this_parent = child->d_parent;
+ dentry = this_parent;
+ this_parent = dentry->d_parent;
- spin_unlock(&child->d_lock);
+ spin_unlock(&dentry->d_lock);
spin_lock(&this_parent->d_lock);
/* might go back up the wrong parent if we have had a rename. */
if (need_seqretry(&rename_lock, seq))
goto rename_retry;
/* go into the first sibling still alive */
- do {
- next = child->d_child.next;
- if (next == &this_parent->d_subdirs)
- goto ascend;
- child = list_entry(next, struct dentry, d_child);
- } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
- rcu_read_unlock();
- goto resume;
+ hlist_for_each_entry_continue(dentry, d_sib) {
+ if (likely(!(dentry->d_flags & DCACHE_DENTRY_KILLED))) {
+ rcu_read_unlock();
+ goto resume;
+ }
+ }
+ goto ascend;
}
if (need_seqretry(&rename_lock, seq))
goto rename_retry;
* Search the dentry child list of the specified parent,
* and move any unused dentries to the end of the unused
* list for prune_dcache(). We descend to the next level
- * whenever the d_subdirs list is non-empty and continue
+ * whenever the d_children list is non-empty and continue
* searching.
*
* It returns zero iff there are no unused children,
if (dentry->d_flags & DCACHE_SHRINK_LIST) {
data->found++;
- } else {
- if (dentry->d_flags & DCACHE_LRU_LIST)
- d_lru_del(dentry);
- if (!dentry->d_lockref.count) {
- d_shrink_add(dentry, &data->dispose);
- data->found++;
- }
+ } else if (!dentry->d_lockref.count) {
+ to_shrink_list(dentry, &data->dispose);
+ data->found++;
+ } else if (dentry->d_lockref.count < 0) {
+ data->found++;
}
/*
* We can return to the caller if we have found some (this
if (data->start == dentry)
goto out;
- if (dentry->d_flags & DCACHE_SHRINK_LIST) {
- if (!dentry->d_lockref.count) {
+ if (!dentry->d_lockref.count) {
+ if (dentry->d_flags & DCACHE_SHRINK_LIST) {
rcu_read_lock();
data->victim = dentry;
return D_WALK_QUIT;
}
- } else {
- if (dentry->d_flags & DCACHE_LRU_LIST)
- d_lru_del(dentry);
- if (!dentry->d_lockref.count)
- d_shrink_add(dentry, &data->dispose);
+ to_shrink_list(dentry, &data->dispose);
}
/*
* We can return to the caller if we have found some (this
data.victim = NULL;
d_walk(parent, &data, select_collect2);
if (data.victim) {
- struct dentry *parent;
spin_lock(&data.victim->d_lock);
- if (!shrink_lock_dentry(data.victim)) {
+ if (!lock_for_kill(data.victim)) {
spin_unlock(&data.victim->d_lock);
rcu_read_unlock();
} else {
- rcu_read_unlock();
- parent = data.victim->d_parent;
- if (parent != data.victim)
- __dput_to_list(parent, &data.dispose);
- __dentry_kill(data.victim);
+ shrink_kill(data.victim);
}
}
if (!list_empty(&data.dispose))
static enum d_walk_ret umount_check(void *_data, struct dentry *dentry)
{
/* it has busy descendents; complain about those instead */
- if (!list_empty(&dentry->d_subdirs))
+ if (!hlist_empty(&dentry->d_children))
return D_WALK_CONTINUE;
/* root with refcount 1 is fine */
{
struct dentry **victim = _data;
if (d_mountpoint(dentry)) {
- __dget_dlock(dentry);
- *victim = dentry;
+ *victim = dget_dlock(dentry);
return D_WALK_QUIT;
}
return D_WALK_CONTINUE;
dentry->d_fsdata = NULL;
INIT_HLIST_BL_NODE(&dentry->d_hash);
INIT_LIST_HEAD(&dentry->d_lru);
- INIT_LIST_HEAD(&dentry->d_subdirs);
+ INIT_HLIST_HEAD(&dentry->d_children);
INIT_HLIST_NODE(&dentry->d_u.d_alias);
- INIT_LIST_HEAD(&dentry->d_child);
+ INIT_HLIST_NODE(&dentry->d_sib);
d_set_d_op(dentry, dentry->d_sb->s_d_op);
if (dentry->d_op && dentry->d_op->d_init) {
* don't need child lock because it is not subject
* to concurrency here
*/
- __dget_dlock(parent);
- dentry->d_parent = parent;
- list_add(&dentry->d_child, &parent->d_subdirs);
+ dentry->d_parent = dget_dlock(parent);
+ hlist_add_head(&dentry->d_sib, &parent->d_children);
spin_unlock(&parent->d_lock);
return dentry;
*/
struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name)
{
+ static const struct dentry_operations anon_ops = {
+ .d_dname = simple_dname
+ };
struct dentry *dentry = __d_alloc(sb, name);
- if (likely(dentry))
+ if (likely(dentry)) {
dentry->d_flags |= DCACHE_NORCU;
+ if (!sb->s_d_op)
+ d_set_d_op(dentry, &anon_ops);
+ }
return dentry;
}
}
EXPORT_SYMBOL(d_set_d_op);
-
- /*
- * d_set_fallthru - Mark a dentry as falling through to a lower layer
- * @dentry - The dentry to mark
- *
- * Mark a dentry as falling through to the lower layer (as set with
- * d_pin_lower()). This flag may be recorded on the medium.
- */
- void d_set_fallthru(struct dentry *dentry)
- {
- spin_lock(&dentry->d_lock);
- dentry->d_flags |= DCACHE_FALLTHRU;
- spin_unlock(&dentry->d_lock);
- }
- EXPORT_SYMBOL(d_set_fallthru);
-
static unsigned d_flags_for_inode(struct inode *inode)
{
unsigned add_flags = DCACHE_REGULAR_TYPE;
}
EXPORT_SYMBOL(d_make_root);
- static struct dentry *__d_instantiate_anon(struct dentry *dentry,
- struct inode *inode,
- bool disconnected)
- {
- struct dentry *res;
- unsigned add_flags;
-
- security_d_instantiate(dentry, inode);
- spin_lock(&inode->i_lock);
- res = __d_find_any_alias(inode);
- if (res) {
- spin_unlock(&inode->i_lock);
- dput(dentry);
- goto out_iput;
- }
-
- /* attach a disconnected dentry */
- add_flags = d_flags_for_inode(inode);
-
- if (disconnected)
- add_flags |= DCACHE_DISCONNECTED;
-
- spin_lock(&dentry->d_lock);
- __d_set_inode_and_type(dentry, inode, add_flags);
- hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
- if (!disconnected) {
- hlist_bl_lock(&dentry->d_sb->s_roots);
- hlist_bl_add_head(&dentry->d_hash, &dentry->d_sb->s_roots);
- hlist_bl_unlock(&dentry->d_sb->s_roots);
- }
- spin_unlock(&dentry->d_lock);
- spin_unlock(&inode->i_lock);
-
- return dentry;
-
- out_iput:
- iput(inode);
- return res;
- }
-
- struct dentry *d_instantiate_anon(struct dentry *dentry, struct inode *inode)
- {
- return __d_instantiate_anon(dentry, inode, true);
- }
- EXPORT_SYMBOL(d_instantiate_anon);
-
static struct dentry *__d_obtain_alias(struct inode *inode, bool disconnected)
{
- struct dentry *tmp;
- struct dentry *res;
+ struct super_block *sb;
+ struct dentry *new, *res;
if (!inode)
return ERR_PTR(-ESTALE);
if (IS_ERR(inode))
return ERR_CAST(inode);
- res = d_find_any_alias(inode);
+ sb = inode->i_sb;
+
+ res = d_find_any_alias(inode); /* existing alias? */
if (res)
- goto out_iput;
+ goto out;
- tmp = d_alloc_anon(inode->i_sb);
- if (!tmp) {
+ new = d_alloc_anon(sb);
+ if (!new) {
res = ERR_PTR(-ENOMEM);
- goto out_iput;
+ goto out;
}
- return __d_instantiate_anon(tmp, inode, disconnected);
+ security_d_instantiate(new, inode);
+ spin_lock(&inode->i_lock);
+ res = __d_find_any_alias(inode); /* recheck under lock */
+ if (likely(!res)) { /* still no alias, attach a disconnected dentry */
+ unsigned add_flags = d_flags_for_inode(inode);
+
+ if (disconnected)
+ add_flags |= DCACHE_DISCONNECTED;
- out_iput:
+ spin_lock(&new->d_lock);
+ __d_set_inode_and_type(new, inode, add_flags);
+ hlist_add_head(&new->d_u.d_alias, &inode->i_dentry);
+ if (!disconnected) {
+ hlist_bl_lock(&sb->s_roots);
+ hlist_bl_add_head(&new->d_hash, &sb->s_roots);
+ hlist_bl_unlock(&sb->s_roots);
+ }
+ spin_unlock(&new->d_lock);
+ spin_unlock(&inode->i_lock);
+ inode = NULL; /* consumed by new->d_inode */
+ res = new;
+ } else {
+ spin_unlock(&inode->i_lock);
+ dput(new);
+ }
+
+ out:
iput(inode);
return res;
}
/* we can't take ->d_lock here; it's OK, though. */
new->d_flags |= DCACHE_PAR_LOOKUP;
new->d_wait = wq;
- hlist_bl_add_head_rcu(&new->d_u.d_in_lookup_hash, b);
+ hlist_bl_add_head(&new->d_u.d_in_lookup_hash, b);
hlist_bl_unlock(b);
return new;
mismatch:
spin_unlock(&alias->d_lock);
alias = NULL;
} else {
- __dget_dlock(alias);
+ dget_dlock(alias);
__d_rehash(alias);
spin_unlock(&alias->d_lock);
}
} else {
target->d_parent = old_parent;
swap_names(dentry, target);
- list_move(&target->d_child, &target->d_parent->d_subdirs);
+ if (!hlist_unhashed(&target->d_sib))
+ __hlist_del(&target->d_sib);
+ hlist_add_head(&target->d_sib, &target->d_parent->d_children);
__d_rehash(target);
fsnotify_update_flags(target);
}
- list_move(&dentry->d_child, &dentry->d_parent->d_subdirs);
+ if (!hlist_unhashed(&dentry->d_sib))
+ __hlist_del(&dentry->d_sib);
+ hlist_add_head(&dentry->d_sib, &dentry->d_parent->d_children);
__d_rehash(dentry);
fsnotify_update_flags(dentry);
fscrypt_handle_d_move(dentry);
* Note: If ever the locking in lock_rename() changes, then please
* remember to update this too...
*/
- static int __d_unalias(struct inode *inode,
- struct dentry *dentry, struct dentry *alias)
+ static int __d_unalias(struct dentry *dentry, struct dentry *alias)
{
struct mutex *m1 = NULL;
struct rw_semaphore *m2 = NULL;
inode->i_sb->s_id);
} else if (!IS_ROOT(new)) {
struct dentry *old_parent = dget(new->d_parent);
- int err = __d_unalias(inode, dentry, new);
+ int err = __d_unalias(dentry, new);
write_sequnlock(&rename_lock);
if (err) {
dput(new);
if (d_unhashed(dentry) || !dentry->d_inode)
return D_WALK_SKIP;
- if (!(dentry->d_flags & DCACHE_GENOCIDE)) {
- dentry->d_flags |= DCACHE_GENOCIDE;
- dentry->d_lockref.count--;
- }
+ dentry->d_lockref.count--;
}
return D_WALK_CONTINUE;
}
#ifdef CONFIG_NFSD_V4
static ssize_t write_leasetime(struct file *file, char *buf, size_t size);
static ssize_t write_gracetime(struct file *file, char *buf, size_t size);
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
static ssize_t write_recoverydir(struct file *file, char *buf, size_t size);
+#endif
static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size);
#endif
#ifdef CONFIG_NFSD_V4
[NFSD_Leasetime] = write_leasetime,
[NFSD_Gracetime] = write_gracetime,
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
[NFSD_RecoveryDir] = write_recoverydir,
+#endif
[NFSD_V4EndGrace] = write_v4_end_grace,
#endif
};
.open = nfsd_pool_stats_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = nfsd_pool_stats_release,
+ .release = seq_release,
};
DEFINE_SHOW_ATTRIBUTE(nfsd_reply_cache_stats);
char *mesg = buf;
int fd, err;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct svc_serv *serv;
err = get_int(&mesg, &fd);
if (err != 0 || fd < 0)
if (err != 0)
return err;
- err = svc_addsock(nn->nfsd_serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
+ serv = nn->nfsd_serv;
+ err = svc_addsock(serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
- if (err >= 0 &&
- !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
- svc_get(nn->nfsd_serv);
+ if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
+ nfsd_destroy_serv(net);
- nfsd_put(net);
return err;
}
struct svc_xprt *xprt;
int port, err;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct svc_serv *serv;
if (sscanf(buf, "%15s %5u", transport, &port) != 2)
return -EINVAL;
if (err != 0)
return err;
- err = svc_xprt_create(nn->nfsd_serv, transport, net,
+ serv = nn->nfsd_serv;
+ err = svc_xprt_create(serv, transport, net,
PF_INET, port, SVC_SOCK_ANONYMOUS, cred);
if (err < 0)
goto out_err;
- err = svc_xprt_create(nn->nfsd_serv, transport, net,
+ err = svc_xprt_create(serv, transport, net,
PF_INET6, port, SVC_SOCK_ANONYMOUS, cred);
if (err < 0 && err != -EAFNOSUPPORT)
goto out_close;
- if (!nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
- svc_get(nn->nfsd_serv);
-
- nfsd_put(net);
return 0;
out_close:
- xprt = svc_find_xprt(nn->nfsd_serv, transport, net, PF_INET, port);
+ xprt = svc_find_xprt(serv, transport, net, PF_INET, port);
if (xprt != NULL) {
svc_xprt_close(xprt);
svc_xprt_put(xprt);
}
out_err:
- nfsd_put(net);
+ if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
+ nfsd_destroy_serv(net);
+
return err;
}
return nfsd4_write_time(file, buf, size, &nn->nfsd4_grace, nn);
}
+#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size,
struct nfsd_net *nn)
{
mutex_unlock(&nfsd_mutex);
return rv;
}
+#endif
/*
* write_v4_end_grace - release grace period for nfsd's v4.x lock manager
#endif
- static void clear_ncl(struct inode *inode)
+ static void clear_ncl(struct dentry *dentry)
{
+ struct inode *inode = d_inode(dentry);
struct nfsdfs_client *ncl = inode->i_private;
+ spin_lock(&inode->i_lock);
inode->i_private = NULL;
+ spin_unlock(&inode->i_lock);
kref_put(&ncl->cl_ref, ncl->cl_release);
}
- static struct nfsdfs_client *__get_nfsdfs_client(struct inode *inode)
- {
- struct nfsdfs_client *nc = inode->i_private;
-
- if (nc)
- kref_get(&nc->cl_ref);
- return nc;
- }
-
struct nfsdfs_client *get_nfsdfs_client(struct inode *inode)
{
struct nfsdfs_client *nc;
- inode_lock_shared(inode);
- nc = __get_nfsdfs_client(inode);
- inode_unlock_shared(inode);
+ spin_lock(&inode->i_lock);
+ nc = inode->i_private;
+ if (nc)
+ kref_get(&nc->cl_ref);
+ spin_unlock(&inode->i_lock);
return nc;
}
- /* from __rpc_unlink */
- static void nfsdfs_remove_file(struct inode *dir, struct dentry *dentry)
- {
- int ret;
-
- clear_ncl(d_inode(dentry));
- dget(dentry);
- ret = simple_unlink(dir, dentry);
- d_drop(dentry);
- fsnotify_unlink(dir, dentry);
- dput(dentry);
- WARN_ON_ONCE(ret);
- }
-
- static void nfsdfs_remove_files(struct dentry *root)
- {
- struct dentry *dentry, *tmp;
-
- list_for_each_entry_safe(dentry, tmp, &root->d_subdirs, d_child) {
- if (!simple_positive(dentry)) {
- WARN_ON_ONCE(1); /* I think this can't happen? */
- continue;
- }
- nfsdfs_remove_file(d_inode(root), dentry);
- }
- }
/* XXX: cut'n'paste from simple_fill_super; figure out if we could share
* code instead. */
static int nfsdfs_create_files(struct dentry *root,
const struct tree_descr *files,
+ struct nfsdfs_client *ncl,
struct dentry **fdentries)
{
struct inode *dir = d_inode(root);
dput(dentry);
goto out;
}
+ kref_get(&ncl->cl_ref);
inode->i_fop = files->ops;
- inode->i_private = __get_nfsdfs_client(dir);
+ inode->i_private = ncl;
d_add(dentry, inode);
fsnotify_create(dir, dentry);
if (fdentries)
inode_unlock(dir);
return 0;
out:
- nfsdfs_remove_files(root);
inode_unlock(dir);
return -ENOMEM;
}
dentry = nfsd_mkdir(nn->nfsd_client_dir, ncl, name);
if (IS_ERR(dentry)) /* XXX: tossing errors? */
return NULL;
- ret = nfsdfs_create_files(dentry, files, fdentries);
+ ret = nfsdfs_create_files(dentry, files, ncl, fdentries);
if (ret) {
nfsd_client_rmdir(dentry);
return NULL;
/* Taken from __rpc_rmdir: */
void nfsd_client_rmdir(struct dentry *dentry)
{
- struct inode *dir = d_inode(dentry->d_parent);
- struct inode *inode = d_inode(dentry);
- int ret;
-
- inode_lock(dir);
- nfsdfs_remove_files(dentry);
- clear_ncl(inode);
- dget(dentry);
- ret = simple_rmdir(dir, dentry);
- WARN_ON_ONCE(ret);
- d_drop(dentry);
- fsnotify_rmdir(dir, dentry);
- dput(dentry);
- inode_unlock(dir);
+ simple_recursive_removal(dentry, clear_ncl);
}
static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc)
int ret = -ENODEV;
mutex_lock(&nfsd_mutex);
- if (nn->nfsd_serv) {
- svc_get(nn->nfsd_serv);
+ if (nn->nfsd_serv)
ret = 0;
- }
- mutex_unlock(&nfsd_mutex);
+ else
+ mutex_unlock(&nfsd_mutex);
return ret;
}
*/
int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb)
{
- mutex_lock(&nfsd_mutex);
- nfsd_put(sock_net(cb->skb->sk));
mutex_unlock(&nfsd_mutex);
return 0;
projects / linux.git / commitdiff