diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index e0337844358e..58851275fed9 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -18,6 +18,7 @@ #ifndef _LINUX_RHASHTABLE_H #define _LINUX_RHASHTABLE_H +#include #include #include #include @@ -111,6 +112,7 @@ struct rhashtable_params { * @p: Configuration parameters * @run_work: Deferred worker to expand/shrink asynchronously * @mutex: Mutex to protect current/future table swapping + * @walkers: List of active walkers * @being_destroyed: True if table is set up for destruction */ struct rhashtable { @@ -121,9 +123,36 @@ struct rhashtable { struct rhashtable_params p; struct work_struct run_work; struct mutex mutex; + struct list_head walkers; bool being_destroyed; }; +/** + * struct rhashtable_walker - Hash table walker + * @list: List entry on list of walkers + * @resize: Resize event occured + */ +struct rhashtable_walker { + struct list_head list; + bool resize; +}; + +/** + * struct rhashtable_iter - Hash table iterator, fits into netlink cb + * @ht: Table to iterate through + * @p: Current pointer + * @walker: Associated rhashtable walker + * @slot: Current slot + * @skip: Number of entries to skip in slot + */ +struct rhashtable_iter { + struct rhashtable *ht; + struct rhash_head *p; + struct rhashtable_walker *walker; + unsigned int slot; + unsigned int skip; +}; + static inline unsigned long rht_marker(const struct rhashtable *ht, u32 hash) { return NULLS_MARKER(ht->p.nulls_base + hash); @@ -179,6 +208,12 @@ bool rhashtable_lookup_compare_insert(struct rhashtable *ht, bool (*compare)(void *, void *), void *arg); +int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter); +void rhashtable_walk_exit(struct rhashtable_iter *iter); +int rhashtable_walk_start(struct rhashtable_iter *iter) __acquires(RCU); +void *rhashtable_walk_next(struct rhashtable_iter *iter); +void rhashtable_walk_stop(struct rhashtable_iter *iter) __releases(RCU); + void rhashtable_destroy(struct rhashtable *ht); #define rht_dereference(p, ht) \ diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 904b419b72f5..057919164e23 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -484,6 +484,7 @@ static void rht_deferred_worker(struct work_struct *work) { struct rhashtable *ht; struct bucket_table *tbl; + struct rhashtable_walker *walker; ht = container_of(work, struct rhashtable, run_work); mutex_lock(&ht->mutex); @@ -492,6 +493,9 @@ static void rht_deferred_worker(struct work_struct *work) tbl = rht_dereference(ht->tbl, ht); + list_for_each_entry(walker, &ht->walkers, list) + walker->resize = true; + if (ht->p.grow_decision && ht->p.grow_decision(ht, tbl->size)) rhashtable_expand(ht); else if (ht->p.shrink_decision && ht->p.shrink_decision(ht, tbl->size)) @@ -822,6 +826,164 @@ exit: } EXPORT_SYMBOL_GPL(rhashtable_lookup_compare_insert); +/** + * rhashtable_walk_init - Initialise an iterator + * @ht: Table to walk over + * @iter: Hash table Iterator + * + * This function prepares a hash table walk. + * + * Note that if you restart a walk after rhashtable_walk_stop you + * may see the same object twice. Also, you may miss objects if + * there are removals in between rhashtable_walk_stop and the next + * call to rhashtable_walk_start. + * + * For a completely stable walk you should construct your own data + * structure outside the hash table. + * + * This function may sleep so you must not call it from interrupt + * context or with spin locks held. + * + * You must call rhashtable_walk_exit if this function returns + * successfully. + */ +int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter) +{ + iter->ht = ht; + iter->p = NULL; + iter->slot = 0; + iter->skip = 0; + + iter->walker = kmalloc(sizeof(*iter->walker), GFP_KERNEL); + if (!iter->walker) + return -ENOMEM; + + mutex_lock(&ht->mutex); + list_add(&iter->walker->list, &ht->walkers); + mutex_unlock(&ht->mutex); + + return 0; +} +EXPORT_SYMBOL_GPL(rhashtable_walk_init); + +/** + * rhashtable_walk_exit - Free an iterator + * @iter: Hash table Iterator + * + * This function frees resources allocated by rhashtable_walk_init. + */ +void rhashtable_walk_exit(struct rhashtable_iter *iter) +{ + mutex_lock(&iter->ht->mutex); + list_del(&iter->walker->list); + mutex_unlock(&iter->ht->mutex); + kfree(iter->walker); +} +EXPORT_SYMBOL_GPL(rhashtable_walk_exit); + +/** + * rhashtable_walk_start - Start a hash table walk + * @iter: Hash table iterator + * + * Start a hash table walk. Note that we take the RCU lock in all + * cases including when we return an error. So you must always call + * rhashtable_walk_stop to clean up. + * + * Returns zero if successful. + * + * Returns -EAGAIN if resize event occured. Note that the iterator + * will rewind back to the beginning and you may use it immediately + * by calling rhashtable_walk_next. + */ +int rhashtable_walk_start(struct rhashtable_iter *iter) +{ + rcu_read_lock(); + + if (iter->walker->resize) { + iter->slot = 0; + iter->skip = 0; + iter->walker->resize = false; + return -EAGAIN; + } + + return 0; +} +EXPORT_SYMBOL_GPL(rhashtable_walk_start); + +/** + * rhashtable_walk_next - Return the next object and advance the iterator + * @iter: Hash table iterator + * + * Note that you must call rhashtable_walk_stop when you are finished + * with the walk. + * + * Returns the next object or NULL when the end of the table is reached. + * + * Returns -EAGAIN if resize event occured. Note that the iterator + * will rewind back to the beginning and you may continue to use it. + */ +void *rhashtable_walk_next(struct rhashtable_iter *iter) +{ + const struct bucket_table *tbl; + struct rhashtable *ht = iter->ht; + struct rhash_head *p = iter->p; + void *obj = NULL; + + tbl = rht_dereference_rcu(ht->tbl, ht); + + if (p) { + p = rht_dereference_bucket_rcu(p->next, tbl, iter->slot); + goto next; + } + + for (; iter->slot < tbl->size; iter->slot++) { + int skip = iter->skip; + + rht_for_each_rcu(p, tbl, iter->slot) { + if (!skip) + break; + skip--; + } + +next: + if (!rht_is_a_nulls(p)) { + iter->skip++; + iter->p = p; + obj = rht_obj(ht, p); + goto out; + } + + iter->skip = 0; + } + + iter->p = NULL; + +out: + if (iter->walker->resize) { + iter->p = NULL; + iter->slot = 0; + iter->skip = 0; + iter->walker->resize = false; + return ERR_PTR(-EAGAIN); + } + + return obj; +} +EXPORT_SYMBOL_GPL(rhashtable_walk_next); + +/** + * rhashtable_walk_stop - Finish a hash table walk + * @iter: Hash table iterator + * + * Finish a hash table walk. + */ +void rhashtable_walk_stop(struct rhashtable_iter *iter) +{ + rcu_read_unlock(); + iter->p = NULL; +} +EXPORT_SYMBOL_GPL(rhashtable_walk_stop); + static size_t rounded_hashtable_size(struct rhashtable_params *params) { return max(roundup_pow_of_two(params->nelem_hint * 4 / 3), @@ -894,6 +1056,7 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params) memset(ht, 0, sizeof(*ht)); mutex_init(&ht->mutex); memcpy(&ht->p, params, sizeof(*params)); + INIT_LIST_HEAD(&ht->walkers); if (params->locks_mul) ht->p.locks_mul = roundup_pow_of_two(params->locks_mul);