diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index c549fb2fc3ba..1be76ef117b3 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -1091,6 +1091,40 @@ would need to do so. --- +**mandatory** + +The list of children anchored in parent dentry got turned into hlist now. +Field names got changed (->d_children/->d_sib instead of ->d_subdirs/->d_child +for anchor/entries resp.), so any affected places will be immediately caught +by compiler. + +--- + +**mandatory** + +->d_delete() instances are now called for dentries with ->d_lock held +and refcount equal to 0. They are not permitted to drop/regain ->d_lock. +None of in-tree instances did anything of that sort. Make sure yours do not... + +--- + +**mandatory** + +->d_prune() instances are now called without ->d_lock held on the parent. +->d_lock on dentry itself is still held; if you need per-parent exclusions (none +of the in-tree instances did), use your own spinlock. + +->d_iput() and ->d_release() are called with victim dentry still in the +list of parent's children. It is still unhashed, marked killed, etc., just not +removed from parent's ->d_children yet. + +Anyone iterating through the list of children needs to be aware of the +half-killed dentries that might be seen there; taking ->d_lock on those will +see them negative, unhashed and with negative refcount, which means that most +of the in-kernel users would've done the right thing anyway without any adjustment. + +--- + **recommended** Block device freezing and thawing have been moved to holder operations. diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 10c1320adfd0..030de2b8c145 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -145,10 +145,11 @@ spufs_evict_inode(struct inode *inode) static void spufs_prune_dir(struct dentry *dir) { - struct dentry *dentry, *tmp; + struct dentry *dentry; + struct hlist_node *n; inode_lock(d_inode(dir)); - list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) { + hlist_for_each_entry_safe(dentry, n, &dir->d_children, d_sib) { spin_lock(&dentry->d_lock); if (simple_positive(dentry)) { dget_dlock(dentry); diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index 1f656005018e..2cd40ba601f1 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -373,7 +373,7 @@ error: void afs_dynroot_depopulate(struct super_block *sb) { struct afs_net *net = afs_sb2net(sb); - struct dentry *root = sb->s_root, *subdir, *tmp; + struct dentry *root = sb->s_root, *subdir; /* Prevent more subdirs from being created */ mutex_lock(&net->proc_cells_lock); @@ -382,10 +382,11 @@ void afs_dynroot_depopulate(struct super_block *sb) mutex_unlock(&net->proc_cells_lock); if (root) { + struct hlist_node *n; inode_lock(root->d_inode); /* Remove all the pins for dirs created for manually added cells */ - list_for_each_entry_safe(subdir, tmp, &root->d_subdirs, d_child) { + hlist_for_each_entry_safe(subdir, n, &root->d_children, d_sib) { if (subdir->d_fsdata) { subdir->d_fsdata = NULL; dput(subdir); diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c index 038b3d2d9f57..39d8c84c16f4 100644 --- a/fs/autofs/expire.c +++ b/fs/autofs/expire.c @@ -73,12 +73,9 @@ done: /* p->d_lock held */ static struct dentry *positive_after(struct dentry *p, struct dentry *child) { - if (child) - child = list_next_entry(child, d_child); - else - child = list_first_entry(&p->d_subdirs, struct dentry, d_child); + child = child ? d_next_sibling(child) : d_first_child(p); - list_for_each_entry_from(child, &p->d_subdirs, d_child) { + hlist_for_each_entry_from(child, d_sib) { spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(child)) { dget_dlock(child); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 91709934c8b1..678596684596 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -174,7 +174,7 @@ __dcache_find_get_entry(struct dentry *parent, u64 idx, /* * When possible, we try to satisfy a readdir by peeking at the * dcache. We make this work by carefully ordering dentries on - * d_child when we initially get results back from the MDS, and + * d_children when we initially get results back from the MDS, and * falling back to a "normal" sync readdir if any dentries in the dir * are dropped. * diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index d95eb525519a..02ebfabfc8ee 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2128,7 +2128,7 @@ static bool drop_negative_children(struct dentry *dentry) goto out; spin_lock(&dentry->d_lock); - list_for_each_entry(child, &dentry->d_subdirs, d_child) { + hlist_for_each_entry(child, &dentry->d_children, d_sib) { if (d_really_is_positive(child)) { all_negative = false; break; diff --git a/fs/coda/cache.c b/fs/coda/cache.c index 3b8c4513118f..970f0022ec52 100644 --- a/fs/coda/cache.c +++ b/fs/coda/cache.c @@ -93,13 +93,13 @@ static void coda_flag_children(struct dentry *parent, int flag) struct dentry *de; spin_lock(&parent->d_lock); - list_for_each_entry(de, &parent->d_subdirs, d_child) { + hlist_for_each_entry(de, &parent->d_children, d_sib) { + struct inode *inode = d_inode_rcu(de); /* don't know what to do with negative dentries */ - if (d_inode(de) ) - coda_flag_inode(d_inode(de), flag); + if (inode) + coda_flag_inode(inode, flag); } spin_unlock(&parent->d_lock); - return; } void coda_flag_inode_children(struct inode *inode, int flag) diff --git a/fs/dcache.c b/fs/dcache.c index df49d29ca154..b813528fb147 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -51,8 +51,8 @@ * - 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: @@ -343,7 +343,7 @@ static inline void __d_set_inode_and_type(struct dentry *dentry, 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); } @@ -352,7 +352,7 @@ static inline void __d_clear_type_and_inode(struct dentry *dentry) { 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) @@ -538,7 +538,7 @@ void d_drop(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; /* @@ -546,12 +546,12 @@ static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent) * 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 - @@ -559,29 +559,27 @@ static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent) * 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. @@ -601,9 +599,6 @@ static void __dentry_kill(struct dentry *dentry) } /* 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 @@ -612,80 +607,114 @@ static void __dentry_kill(struct dentry *dentry) 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; } @@ -704,61 +733,12 @@ void d_mark_dontcache(struct inode *inode) } 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! @@ -766,18 +746,9 @@ got_locks: 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); @@ -788,12 +759,12 @@ static inline bool fast_dput(struct dentry *dentry) */ 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; } /* @@ -803,45 +774,18 @@ static inline bool fast_dput(struct dentry *dentry) 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); @@ -851,17 +795,11 @@ static inline bool fast_dput(struct dentry *dentry) * 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; } @@ -894,39 +832,37 @@ static inline bool fast_dput(struct dentry *dentry) */ 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); } } @@ -938,22 +874,10 @@ void dput_to_list(struct dentry *dentry, struct list_head *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; @@ -1003,7 +927,7 @@ static struct dentry * __d_find_any_alias(struct inode *inode) 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; } @@ -1035,7 +959,7 @@ static struct dentry *__d_find_alias(struct inode *inode) 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; } @@ -1102,104 +1026,53 @@ struct dentry *d_find_alias_rcu(struct inode *inode) */ 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); } } @@ -1349,8 +1222,7 @@ enum d_walk_ret { 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; @@ -1372,13 +1244,9 @@ again: 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; @@ -1399,7 +1267,7 @@ resume: 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; @@ -1414,24 +1282,23 @@ resume: 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; @@ -1531,7 +1398,7 @@ out: * 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, @@ -1561,13 +1428,11 @@ static enum d_walk_ret select_collect(void *_data, struct dentry *dentry) 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 @@ -1588,17 +1453,13 @@ static enum d_walk_ret select_collect2(void *_data, struct dentry *dentry) 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 @@ -1636,17 +1497,12 @@ void shrink_dcache_parent(struct dentry *parent) 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)) @@ -1658,7 +1514,7 @@ EXPORT_SYMBOL(shrink_dcache_parent); 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 */ @@ -1708,8 +1564,7 @@ static enum d_walk_ret find_submount(void *_data, struct dentry *dentry) { 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; @@ -1815,9 +1670,9 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) 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) { @@ -1854,9 +1709,8 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) * 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; @@ -1896,9 +1750,15 @@ struct dentry *d_alloc_cursor(struct dentry * parent) */ 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; } @@ -1942,22 +1802,6 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) } 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; @@ -2076,75 +1920,55 @@ struct dentry *d_make_root(struct inode *root_inode) } 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); - if (res) - goto out_iput; + sb = inode->i_sb; - tmp = d_alloc_anon(inode->i_sb); - if (!tmp) { + res = d_find_any_alias(inode); /* existing alias? */ + if (res) + goto out; + + 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); -out_iput: + if (disconnected) + add_flags |= DCACHE_DISCONNECTED; + + 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; } @@ -2728,7 +2552,7 @@ retry: /* 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: @@ -2852,7 +2676,7 @@ struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode) spin_unlock(&alias->d_lock); alias = NULL; } else { - __dget_dlock(alias); + dget_dlock(alias); __d_rehash(alias); spin_unlock(&alias->d_lock); } @@ -2994,11 +2818,15 @@ static void __d_move(struct dentry *dentry, struct dentry *target, } 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); @@ -3081,8 +2909,7 @@ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2) * 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; @@ -3163,7 +2990,7 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) 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); @@ -3234,10 +3061,7 @@ static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry) 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; } diff --git a/fs/file_table.c b/fs/file_table.c index c5ac2cc05135..b991f90571b4 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -316,9 +316,6 @@ struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, const char *name, int flags, const struct file_operations *fops) { - static const struct dentry_operations anon_ops = { - .d_dname = simple_dname - }; struct qstr this = QSTR_INIT(name, strlen(name)); struct path path; struct file *file; @@ -326,8 +323,6 @@ struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, path.dentry = d_alloc_pseudo(mnt->mnt_sb, &this); if (!path.dentry) return ERR_PTR(-ENOMEM); - if (!mnt->mnt_sb->s_d_op) - d_set_d_op(path.dentry, &anon_ops); path.mnt = mntget(mnt); d_instantiate(path.dentry, inode); file = alloc_file(&path, flags, fops); diff --git a/fs/internal.h b/fs/internal.h index 93cdeeb858cb..b67406435fc0 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -214,6 +214,11 @@ extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *) extern char *simple_dname(struct dentry *, char *, int); extern void dput_to_list(struct dentry *, struct list_head *); extern void shrink_dentry_list(struct list_head *); +extern void shrink_dcache_for_umount(struct super_block *); +extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *); +extern struct dentry *__d_lookup_rcu(const struct dentry *parent, + const struct qstr *name, unsigned *seq); +extern void d_genocide(struct dentry *); /* * pipe.c diff --git a/fs/libfs.c b/fs/libfs.c index c2aa6fd4795c..eec6031b0155 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -104,15 +104,16 @@ EXPORT_SYMBOL(dcache_dir_close); * If no such element exists, NULL is returned. */ static struct dentry *scan_positives(struct dentry *cursor, - struct list_head *p, + struct hlist_node **p, loff_t count, struct dentry *last) { struct dentry *dentry = cursor->d_parent, *found = NULL; spin_lock(&dentry->d_lock); - while ((p = p->next) != &dentry->d_subdirs) { - struct dentry *d = list_entry(p, struct dentry, d_child); + while (*p) { + struct dentry *d = hlist_entry(*p, struct dentry, d_sib); + p = &d->d_sib.next; // we must at least skip cursors, to avoid livelocks if (d->d_flags & DCACHE_DENTRY_CURSOR) continue; @@ -126,8 +127,10 @@ static struct dentry *scan_positives(struct dentry *cursor, count = 1; } if (need_resched()) { - list_move(&cursor->d_child, p); - p = &cursor->d_child; + if (!hlist_unhashed(&cursor->d_sib)) + __hlist_del(&cursor->d_sib); + hlist_add_behind(&cursor->d_sib, &d->d_sib); + p = &cursor->d_sib.next; spin_unlock(&dentry->d_lock); cond_resched(); spin_lock(&dentry->d_lock); @@ -159,13 +162,12 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) inode_lock_shared(dentry->d_inode); if (offset > 2) - to = scan_positives(cursor, &dentry->d_subdirs, + to = scan_positives(cursor, &dentry->d_children.first, offset - 2, NULL); spin_lock(&dentry->d_lock); + hlist_del_init(&cursor->d_sib); if (to) - list_move(&cursor->d_child, &to->d_child); - else - list_del_init(&cursor->d_child); + hlist_add_behind(&cursor->d_sib, &to->d_sib); spin_unlock(&dentry->d_lock); dput(to); @@ -187,19 +189,16 @@ int dcache_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct dentry *cursor = file->private_data; - struct list_head *anchor = &dentry->d_subdirs; struct dentry *next = NULL; - struct list_head *p; + struct hlist_node **p; if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos == 2) - p = anchor; - else if (!list_empty(&cursor->d_child)) - p = &cursor->d_child; + p = &dentry->d_children.first; else - return 0; + p = &cursor->d_sib.next; while ((next = scan_positives(cursor, p, 1, next)) != NULL) { if (!dir_emit(ctx, next->d_name.name, next->d_name.len, @@ -207,13 +206,12 @@ int dcache_readdir(struct file *file, struct dir_context *ctx) fs_umode_to_dtype(d_inode(next)->i_mode))) break; ctx->pos++; - p = &next->d_child; + p = &next->d_sib.next; } spin_lock(&dentry->d_lock); + hlist_del_init(&cursor->d_sib); if (next) - list_move_tail(&cursor->d_child, &next->d_child); - else - list_del_init(&cursor->d_child); + hlist_add_before(&cursor->d_sib, &next->d_sib); spin_unlock(&dentry->d_lock); dput(next); @@ -500,12 +498,11 @@ const struct file_operations simple_offset_dir_operations = { static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev) { - struct dentry *child = NULL; - struct list_head *p = prev ? &prev->d_child : &parent->d_subdirs; + struct dentry *child = NULL, *d; spin_lock(&parent->d_lock); - while ((p = p->next) != &parent->d_subdirs) { - struct dentry *d = container_of(p, struct dentry, d_child); + d = prev ? d_next_sibling(prev) : d_first_child(parent); + hlist_for_each_entry_from(d, d_sib) { if (simple_positive(d)) { spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(d)) @@ -666,7 +663,7 @@ int simple_empty(struct dentry *dentry) int ret = 0; spin_lock(&dentry->d_lock); - list_for_each_entry(child, &dentry->d_subdirs, d_child) { + hlist_for_each_entry(child, &dentry->d_children, d_sib) { spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(child)) { spin_unlock(&child->d_lock); @@ -920,7 +917,6 @@ int simple_fill_super(struct super_block *s, unsigned long magic, const struct tree_descr *files) { struct inode *inode; - struct dentry *root; struct dentry *dentry; int i; @@ -943,8 +939,8 @@ int simple_fill_super(struct super_block *s, unsigned long magic, inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; set_nlink(inode, 2); - root = d_make_root(inode); - if (!root) + s->s_root = d_make_root(inode); + if (!s->s_root) return -ENOMEM; for (i = 0; !files->name || files->name[0]; i++, files++) { if (!files->name) @@ -956,13 +952,13 @@ int simple_fill_super(struct super_block *s, unsigned long magic, "with an index of 1!\n", __func__, s->s_type->name); - dentry = d_alloc_name(root, files->name); + dentry = d_alloc_name(s->s_root, files->name); if (!dentry) - goto out; + return -ENOMEM; inode = new_inode(s); if (!inode) { dput(dentry); - goto out; + return -ENOMEM; } inode->i_mode = S_IFREG | files->mode; simple_inode_init_ts(inode); @@ -970,13 +966,7 @@ int simple_fill_super(struct super_block *s, unsigned long magic, inode->i_ino = i; d_add(dentry, inode); } - s->s_root = root; return 0; -out: - d_genocide(root); - shrink_dcache_parent(root); - dput(root); - return -ENOMEM; } EXPORT_SYMBOL(simple_fill_super); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 8e6dbe9e0b65..c9f9590f056b 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1242,63 +1242,34 @@ static inline void _nfsd_symlink(struct dentry *parent, const char *name, #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); @@ -1317,8 +1288,9 @@ static int nfsdfs_create_files(struct dentry *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) @@ -1327,7 +1299,6 @@ static int nfsdfs_create_files(struct dentry *root, inode_unlock(dir); return 0; out: - nfsdfs_remove_files(root); inode_unlock(dir); return -ENOMEM; } @@ -1347,7 +1318,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn, 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; @@ -1358,20 +1329,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn, /* 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) diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 7974e91ffe13..8bfd690e9f10 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -124,7 +124,7 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode) * d_flags to indicate parental interest (their parent is the * original inode) */ spin_lock(&alias->d_lock); - list_for_each_entry(child, &alias->d_subdirs, d_child) { + hlist_for_each_entry(child, &alias->d_children, d_sib) { if (!child->d_inode) continue; diff --git a/fs/nsfs.c b/fs/nsfs.c index 9a4b228d42fa..34e1e3e36733 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -90,12 +90,9 @@ slow: inode->i_fop = &ns_file_operations; inode->i_private = ns; - dentry = d_alloc_anon(mnt->mnt_sb); - if (!dentry) { - iput(inode); + dentry = d_make_root(inode); /* not the normal use, but... */ + if (!dentry) return -ENOMEM; - } - d_instantiate(dentry, inode); dentry->d_fsdata = (void *)ns->ops; d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry); if (d) { diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 6909c4a5da56..063409069f56 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -289,7 +289,6 @@ static struct dentry *ovl_obtain_alias(struct super_block *sb, { struct dentry *lower = lowerpath ? lowerpath->dentry : NULL; struct dentry *upper = upper_alias ?: index; - struct dentry *dentry; struct inode *inode = NULL; struct ovl_entry *oe; struct ovl_inode_params oip = { @@ -320,27 +319,7 @@ static struct dentry *ovl_obtain_alias(struct super_block *sb, if (upper) ovl_set_flag(OVL_UPPERDATA, inode); - dentry = d_find_any_alias(inode); - if (dentry) - goto out_iput; - - dentry = d_alloc_anon(inode->i_sb); - if (unlikely(!dentry)) - goto nomem; - - if (upper_alias) - ovl_dentry_set_upper_alias(dentry); - - ovl_dentry_init_reval(dentry, upper, OVL_I_E(inode)); - - return d_instantiate_anon(dentry, inode); - -nomem: - dput(dentry); - dentry = ERR_PTR(-ENOMEM); -out_iput: - iput(inode); - return dentry; + return d_obtain_alias(inode); } /* Get the upper or lower dentry in stack whose on layer @idx */ diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index bc86ffdb103b..ad20e6af938d 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -199,21 +199,17 @@ static void change_gid(struct dentry *dentry, kgid_t gid) */ static void set_gid(struct dentry *parent, kgid_t gid) { - struct dentry *this_parent; - struct list_head *next; + struct dentry *this_parent, *dentry; this_parent = parent; spin_lock(&this_parent->d_lock); change_gid(this_parent, gid); repeat: - next = this_parent->d_subdirs.next; + dentry = d_first_child(this_parent); resume: - while (next != &this_parent->d_subdirs) { + hlist_for_each_entry_from(dentry, d_sib) { struct tracefs_inode *ti; - struct list_head *tmp = next; - struct dentry *dentry = list_entry(tmp, struct dentry, d_child); - next = tmp->next; /* Note, getdents() can add a cursor dentry with no inode */ if (!dentry->d_inode) @@ -228,7 +224,7 @@ resume: if (ti && (ti->flags & TRACEFS_EVENT_INODE)) eventfs_update_gid(dentry, gid); - 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; @@ -243,21 +239,20 @@ resume: 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); /* 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; } rcu_read_unlock(); spin_unlock(&this_parent->d_lock); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 3da2f0545d5d..1666c387861f 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -68,12 +68,12 @@ extern const struct qstr dotdot_name; * large memory footprint increase). */ #ifdef CONFIG_64BIT -# define DNAME_INLINE_LEN 32 /* 192 bytes */ +# define DNAME_INLINE_LEN 40 /* 192 bytes */ #else # ifdef CONFIG_SMP -# define DNAME_INLINE_LEN 36 /* 128 bytes */ -# else # define DNAME_INLINE_LEN 40 /* 128 bytes */ +# else +# define DNAME_INLINE_LEN 44 /* 128 bytes */ # endif #endif @@ -101,8 +101,8 @@ struct dentry { struct list_head d_lru; /* LRU list */ wait_queue_head_t *d_wait; /* in-lookup ones only */ }; - struct list_head d_child; /* child of parent list */ - struct list_head d_subdirs; /* our children */ + struct hlist_node d_sib; /* child of parent list */ + struct hlist_head d_children; /* our children */ /* * d_alias and d_rcu can share memory */ @@ -111,7 +111,7 @@ struct dentry { struct hlist_bl_node d_in_lookup_hash; /* only for in-lookup ones */ struct rcu_head d_rcu; } d_u; -} __randomize_layout; +}; /* * dentry->d_lock spinlock nesting subclasses: @@ -151,13 +151,13 @@ struct dentry_operations { */ /* d_flags entries */ -#define DCACHE_OP_HASH 0x00000001 -#define DCACHE_OP_COMPARE 0x00000002 -#define DCACHE_OP_REVALIDATE 0x00000004 -#define DCACHE_OP_DELETE 0x00000008 -#define DCACHE_OP_PRUNE 0x00000010 +#define DCACHE_OP_HASH BIT(0) +#define DCACHE_OP_COMPARE BIT(1) +#define DCACHE_OP_REVALIDATE BIT(2) +#define DCACHE_OP_DELETE BIT(3) +#define DCACHE_OP_PRUNE BIT(4) -#define DCACHE_DISCONNECTED 0x00000020 +#define DCACHE_DISCONNECTED BIT(5) /* This dentry is possibly not currently connected to the dcache tree, in * which case its parent will either be itself, or will have this flag as * well. nfsd will not use a dentry with this bit set, but will first @@ -168,50 +168,46 @@ struct dentry_operations { * dentry into place and return that dentry rather than the passed one, * typically using d_splice_alias. */ -#define DCACHE_REFERENCED 0x00000040 /* Recently used, don't discard. */ +#define DCACHE_REFERENCED BIT(6) /* Recently used, don't discard. */ -#define DCACHE_DONTCACHE 0x00000080 /* Purge from memory on final dput() */ +#define DCACHE_DONTCACHE BIT(7) /* Purge from memory on final dput() */ -#define DCACHE_CANT_MOUNT 0x00000100 -#define DCACHE_GENOCIDE 0x00000200 -#define DCACHE_SHRINK_LIST 0x00000400 +#define DCACHE_CANT_MOUNT BIT(8) +#define DCACHE_SHRINK_LIST BIT(10) -#define DCACHE_OP_WEAK_REVALIDATE 0x00000800 +#define DCACHE_OP_WEAK_REVALIDATE BIT(11) -#define DCACHE_NFSFS_RENAMED 0x00001000 +#define DCACHE_NFSFS_RENAMED BIT(12) /* this dentry has been "silly renamed" and has to be deleted on the last * dput() */ -#define DCACHE_COOKIE 0x00002000 /* For use by dcookie subsystem */ -#define DCACHE_FSNOTIFY_PARENT_WATCHED 0x00004000 +#define DCACHE_FSNOTIFY_PARENT_WATCHED BIT(14) /* Parent inode is watched by some fsnotify listener */ -#define DCACHE_DENTRY_KILLED 0x00008000 +#define DCACHE_DENTRY_KILLED BIT(15) -#define DCACHE_MOUNTED 0x00010000 /* is a mountpoint */ -#define DCACHE_NEED_AUTOMOUNT 0x00020000 /* handle automount on this dir */ -#define DCACHE_MANAGE_TRANSIT 0x00040000 /* manage transit from this dirent */ +#define DCACHE_MOUNTED BIT(16) /* is a mountpoint */ +#define DCACHE_NEED_AUTOMOUNT BIT(17) /* handle automount on this dir */ +#define DCACHE_MANAGE_TRANSIT BIT(18) /* manage transit from this dirent */ #define DCACHE_MANAGED_DENTRY \ (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT) -#define DCACHE_LRU_LIST 0x00080000 +#define DCACHE_LRU_LIST BIT(19) -#define DCACHE_ENTRY_TYPE 0x00700000 -#define DCACHE_MISS_TYPE 0x00000000 /* Negative dentry (maybe fallthru to nowhere) */ -#define DCACHE_WHITEOUT_TYPE 0x00100000 /* Whiteout dentry (stop pathwalk) */ -#define DCACHE_DIRECTORY_TYPE 0x00200000 /* Normal directory */ -#define DCACHE_AUTODIR_TYPE 0x00300000 /* Lookupless directory (presumed automount) */ -#define DCACHE_REGULAR_TYPE 0x00400000 /* Regular file type (or fallthru to such) */ -#define DCACHE_SPECIAL_TYPE 0x00500000 /* Other file type (or fallthru to such) */ -#define DCACHE_SYMLINK_TYPE 0x00600000 /* Symlink (or fallthru to such) */ +#define DCACHE_ENTRY_TYPE (7 << 20) /* bits 20..22 are for storing type: */ +#define DCACHE_MISS_TYPE (0 << 20) /* Negative dentry */ +#define DCACHE_WHITEOUT_TYPE (1 << 20) /* Whiteout dentry (stop pathwalk) */ +#define DCACHE_DIRECTORY_TYPE (2 << 20) /* Normal directory */ +#define DCACHE_AUTODIR_TYPE (3 << 20) /* Lookupless directory (presumed automount) */ +#define DCACHE_REGULAR_TYPE (4 << 20) /* Regular file type */ +#define DCACHE_SPECIAL_TYPE (5 << 20) /* Other file type */ +#define DCACHE_SYMLINK_TYPE (6 << 20) /* Symlink */ -#define DCACHE_MAY_FREE 0x00800000 -#define DCACHE_FALLTHRU 0x01000000 /* Fall through to lower layer */ -#define DCACHE_NOKEY_NAME 0x02000000 /* Encrypted name encoded without key */ -#define DCACHE_OP_REAL 0x04000000 +#define DCACHE_NOKEY_NAME BIT(25) /* Encrypted name encoded without key */ +#define DCACHE_OP_REAL BIT(26) -#define DCACHE_PAR_LOOKUP 0x10000000 /* being looked up (with parent locked shared) */ -#define DCACHE_DENTRY_CURSOR 0x20000000 -#define DCACHE_NORCU 0x40000000 /* No RCU delay for freeing */ +#define DCACHE_PAR_LOOKUP BIT(28) /* being looked up (with parent locked shared) */ +#define DCACHE_DENTRY_CURSOR BIT(29) +#define DCACHE_NORCU BIT(30) /* No RCU delay for freeing */ extern seqlock_t rename_lock; @@ -220,8 +216,6 @@ extern seqlock_t rename_lock; */ extern void d_instantiate(struct dentry *, struct inode *); extern void d_instantiate_new(struct dentry *, struct inode *); -extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *); -extern struct dentry * d_instantiate_anon(struct dentry *, struct inode *); extern void __d_drop(struct dentry *dentry); extern void d_drop(struct dentry *dentry); extern void d_delete(struct dentry *); @@ -242,15 +236,11 @@ extern struct dentry * d_obtain_alias(struct inode *); extern struct dentry * d_obtain_root(struct inode *); extern void shrink_dcache_sb(struct super_block *); extern void shrink_dcache_parent(struct dentry *); -extern void shrink_dcache_for_umount(struct super_block *); extern void d_invalidate(struct dentry *); /* only used at mount-time */ extern struct dentry * d_make_root(struct inode *); -/* - the ramfs-type tree */ -extern void d_genocide(struct dentry *); - extern void d_mark_tmpfile(struct file *, struct inode *); extern void d_tmpfile(struct file *, struct inode *); @@ -274,12 +264,8 @@ extern void d_move(struct dentry *, struct dentry *); extern void d_exchange(struct dentry *, struct dentry *); extern struct dentry *d_ancestor(struct dentry *, struct dentry *); -/* appendix may either be NULL or be used for transname suffixes */ extern struct dentry *d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); -extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *); -extern struct dentry *__d_lookup_rcu(const struct dentry *parent, - const struct qstr *name, unsigned *seq); static inline unsigned d_count(const struct dentry *dentry) { @@ -301,20 +287,40 @@ extern char *dentry_path(const struct dentry *, char *, int); /* Allocation counts.. */ /** - * dget, dget_dlock - get a reference to a dentry - * @dentry: dentry to get a reference to + * dget_dlock - get a reference to a dentry + * @dentry: dentry to get a reference to * - * Given a dentry or %NULL pointer increment the reference count - * if appropriate and return the dentry. A dentry will not be - * destroyed when it has references. + * Given a live dentry, increment the reference count and return the dentry. + * Caller must hold @dentry->d_lock. Making sure that dentry is alive is + * caller's resonsibility. There are many conditions sufficient to guarantee + * that; e.g. anything with non-negative refcount is alive, so's anything + * hashed, anything positive, anyone's parent, etc. */ static inline struct dentry *dget_dlock(struct dentry *dentry) { - if (dentry) - dentry->d_lockref.count++; + dentry->d_lockref.count++; return dentry; } + +/** + * dget - get a reference to a dentry + * @dentry: dentry to get a reference to + * + * Given a dentry or %NULL pointer increment the reference count + * if appropriate and return the dentry. A dentry will not be + * destroyed when it has references. Conversely, a dentry with + * no references can disappear for any number of reasons, starting + * with memory pressure. In other words, that primitive is + * used to clone an existing reference; using it on something with + * zero refcount is a bug. + * + * NOTE: it will spin if @dentry->d_lock is held. From the deadlock + * avoidance point of view it is equivalent to spin_lock()/increment + * refcount/spin_unlock(), so calling it under @dentry->d_lock is + * always a bug; so's calling it under ->d_lock on any of its descendents. + * + */ static inline struct dentry *dget(struct dentry *dentry) { if (dentry) @@ -325,12 +331,11 @@ static inline struct dentry *dget(struct dentry *dentry) extern struct dentry *dget_parent(struct dentry *dentry); /** - * d_unhashed - is dentry hashed - * @dentry: entry to check + * d_unhashed - is dentry hashed + * @dentry: entry to check * - * Returns true if the dentry passed is not currently hashed. + * Returns true if the dentry passed is not currently hashed. */ - static inline int d_unhashed(const struct dentry *dentry) { return hlist_bl_unhashed(&dentry->d_hash); @@ -490,14 +495,6 @@ static inline int simple_positive(const struct dentry *dentry) return d_really_is_positive(dentry) && !d_unhashed(dentry); } -extern void d_set_fallthru(struct dentry *dentry); - -static inline bool d_is_fallthru(const struct dentry *dentry) -{ - return dentry->d_flags & DCACHE_FALLTHRU; -} - - extern int sysctl_vfs_cache_pressure; static inline unsigned long vfs_pressure_ratio(unsigned long val) @@ -546,21 +543,6 @@ static inline struct inode *d_backing_inode(const struct dentry *upper) return inode; } -/** - * d_backing_dentry - Get upper or lower dentry we should be using - * @upper: The upper layer - * - * This is the helper that should be used to get the dentry of the inode that - * will be used if this dentry were opened as a file. It may be the upper - * dentry or it may be a lower dentry pinned by the upper. - * - * Normal filesystems should not use this to access their own dentries. - */ -static inline struct dentry *d_backing_dentry(struct dentry *upper) -{ - return upper; -} - /** * d_real - Return the real dentry * @dentry: the dentry to query @@ -600,4 +582,14 @@ struct name_snapshot { void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); void release_dentry_name_snapshot(struct name_snapshot *); +static inline struct dentry *d_first_child(const struct dentry *dentry) +{ + return hlist_entry_safe(dentry->d_children.first, struct dentry, d_sib); +} + +static inline struct dentry *d_next_sibling(const struct dentry *dentry) +{ + return hlist_entry_safe(dentry->d_sib.next, struct dentry, d_sib); +} + #endif /* __LINUX_DCACHE_H */