#endif
-static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl)
+static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl,
+ gfp_t gfp)
{
unsigned int i, size;
#if defined(CONFIG_PROVE_LOCKING)
if (sizeof(spinlock_t) != 0) {
#ifdef CONFIG_NUMA
- if (size * sizeof(spinlock_t) > PAGE_SIZE)
+ if (size * sizeof(spinlock_t) > PAGE_SIZE &&
+ gfp == GFP_KERNEL)
tbl->locks = vmalloc(size * sizeof(spinlock_t));
else
#endif
tbl->locks = kmalloc_array(size, sizeof(spinlock_t),
- GFP_KERNEL);
+ gfp);
if (!tbl->locks)
return -ENOMEM;
for (i = 0; i < size; i++)
}
static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
- size_t nbuckets)
+ size_t nbuckets,
+ gfp_t gfp)
{
struct bucket_table *tbl = NULL;
size_t size;
int i;
size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]);
- if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
- tbl = kzalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
- if (tbl == NULL)
+ if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER) ||
+ gfp != GFP_KERNEL)
+ tbl = kzalloc(size, gfp | __GFP_NOWARN | __GFP_NORETRY);
+ if (tbl == NULL && gfp == GFP_KERNEL)
tbl = vzalloc(size);
if (tbl == NULL)
return NULL;
tbl->size = nbuckets;
- if (alloc_bucket_locks(ht, tbl) < 0) {
+ if (alloc_bucket_locks(ht, tbl, gfp) < 0) {
bucket_table_free(tbl);
return NULL;
}
return tbl;
}
-static int rhashtable_rehash_one(struct rhashtable *ht, unsigned old_hash)
+static struct bucket_table *rhashtable_last_table(struct rhashtable *ht,
+ struct bucket_table *tbl)
+{
+ struct bucket_table *new_tbl;
+
+ do {
+ new_tbl = tbl;
+ tbl = rht_dereference_rcu(tbl->future_tbl, ht);
+ } while (tbl);
+
+ return new_tbl;
+}
+
+static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash)
{
struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
- struct bucket_table *new_tbl =
- rht_dereference(old_tbl->future_tbl, ht) ?: old_tbl;
+ struct bucket_table *new_tbl = rhashtable_last_table(ht,
+ rht_dereference_rcu(old_tbl->future_tbl, ht));
struct rhash_head __rcu **pprev = &old_tbl->buckets[old_hash];
int err = -ENOENT;
struct rhash_head *head, *next, *entry;
spinlock_t *new_bucket_lock;
- unsigned new_hash;
+ unsigned int new_hash;
rht_for_each(entry, old_tbl, old_hash) {
err = 0;
return err;
}
-static void rhashtable_rehash_chain(struct rhashtable *ht, unsigned old_hash)
+static void rhashtable_rehash_chain(struct rhashtable *ht,
+ unsigned int old_hash)
{
struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
spinlock_t *old_bucket_lock;
spin_unlock_bh(old_bucket_lock);
}
-static void rhashtable_rehash(struct rhashtable *ht,
- struct bucket_table *new_tbl)
+static int rhashtable_rehash_attach(struct rhashtable *ht,
+ struct bucket_table *old_tbl,
+ struct bucket_table *new_tbl)
{
- struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
- struct rhashtable_walker *walker;
- unsigned old_hash;
+ /* Protect future_tbl using the first bucket lock. */
+ spin_lock_bh(old_tbl->locks);
+
+ /* Did somebody beat us to it? */
+ if (rcu_access_pointer(old_tbl->future_tbl)) {
+ spin_unlock_bh(old_tbl->locks);
+ return -EEXIST;
+ }
/* Make insertions go into the new, empty table right away. Deletions
* and lookups will be attempted in both tables until we synchronize.
/* Ensure the new table is visible to readers. */
smp_wmb();
+ spin_unlock_bh(old_tbl->locks);
+
+ return 0;
+}
+
+static int rhashtable_rehash_table(struct rhashtable *ht)
+{
+ struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
+ struct bucket_table *new_tbl;
+ struct rhashtable_walker *walker;
+ unsigned int old_hash;
+
+ new_tbl = rht_dereference(old_tbl->future_tbl, ht);
+ if (!new_tbl)
+ return 0;
+
for (old_hash = 0; old_hash < old_tbl->size; old_hash++)
rhashtable_rehash_chain(ht, old_hash);
/* Publish the new table pointer. */
rcu_assign_pointer(ht->tbl, new_tbl);
+ spin_lock(&ht->lock);
list_for_each_entry(walker, &old_tbl->walkers, list)
walker->tbl = NULL;
+ spin_unlock(&ht->lock);
/* Wait for readers. All new readers will see the new
* table, and thus no references to the old table will
* remain.
*/
call_rcu(&old_tbl->rcu, bucket_table_free_rcu);
+
+ return rht_dereference(new_tbl->future_tbl, ht) ? -EAGAIN : 0;
}
/**
* It is valid to have concurrent insertions and deletions protected by per
* bucket locks or concurrent RCU protected lookups and traversals.
*/
-int rhashtable_expand(struct rhashtable *ht)
+static int rhashtable_expand(struct rhashtable *ht)
{
struct bucket_table *new_tbl, *old_tbl = rht_dereference(ht->tbl, ht);
+ int err;
ASSERT_RHT_MUTEX(ht);
- new_tbl = bucket_table_alloc(ht, old_tbl->size * 2);
+ old_tbl = rhashtable_last_table(ht, old_tbl);
+
+ new_tbl = bucket_table_alloc(ht, old_tbl->size * 2, GFP_KERNEL);
if (new_tbl == NULL)
return -ENOMEM;
- rhashtable_rehash(ht, new_tbl);
- return 0;
+ err = rhashtable_rehash_attach(ht, old_tbl, new_tbl);
+ if (err)
+ bucket_table_free(new_tbl);
+
+ return err;
}
-EXPORT_SYMBOL_GPL(rhashtable_expand);
/**
* rhashtable_shrink - Shrink hash table while allowing concurrent lookups
* @ht: the hash table to shrink
*
- * This function may only be called in a context where it is safe to call
- * synchronize_rcu(), e.g. not within a rcu_read_lock() section.
+ * This function shrinks the hash table to fit, i.e., the smallest
+ * size would not cause it to expand right away automatically.
*
* The caller must ensure that no concurrent resizing occurs by holding
* ht->mutex.
* It is valid to have concurrent insertions and deletions protected by per
* bucket locks or concurrent RCU protected lookups and traversals.
*/
-int rhashtable_shrink(struct rhashtable *ht)
+static int rhashtable_shrink(struct rhashtable *ht)
{
struct bucket_table *new_tbl, *old_tbl = rht_dereference(ht->tbl, ht);
+ unsigned int size;
+ int err;
ASSERT_RHT_MUTEX(ht);
- new_tbl = bucket_table_alloc(ht, old_tbl->size / 2);
+ size = roundup_pow_of_two(atomic_read(&ht->nelems) * 3 / 2);
+ if (size < ht->p.min_size)
+ size = ht->p.min_size;
+
+ if (old_tbl->size <= size)
+ return 0;
+
+ if (rht_dereference(old_tbl->future_tbl, ht))
+ return -EEXIST;
+
+ new_tbl = bucket_table_alloc(ht, size, GFP_KERNEL);
if (new_tbl == NULL)
return -ENOMEM;
- rhashtable_rehash(ht, new_tbl);
- return 0;
+ err = rhashtable_rehash_attach(ht, old_tbl, new_tbl);
+ if (err)
+ bucket_table_free(new_tbl);
+
+ return err;
}
-EXPORT_SYMBOL_GPL(rhashtable_shrink);
static void rht_deferred_worker(struct work_struct *work)
{
struct rhashtable *ht;
struct bucket_table *tbl;
+ int err = 0;
ht = container_of(work, struct rhashtable, run_work);
mutex_lock(&ht->mutex);
- if (ht->being_destroyed)
- goto unlock;
tbl = rht_dereference(ht->tbl, ht);
+ tbl = rhashtable_last_table(ht, tbl);
if (rht_grow_above_75(ht, tbl))
rhashtable_expand(ht);
- else if (rht_shrink_below_30(ht, tbl))
+ else if (ht->p.automatic_shrinking && rht_shrink_below_30(ht, tbl))
rhashtable_shrink(ht);
-unlock:
+
+ err = rhashtable_rehash_table(ht);
+
mutex_unlock(&ht->mutex);
+
+ if (err)
+ schedule_work(&ht->run_work);
+}
+
+static bool rhashtable_check_elasticity(struct rhashtable *ht,
+ struct bucket_table *tbl,
+ unsigned int hash)
+{
+ unsigned int elasticity = ht->elasticity;
+ struct rhash_head *head;
+
+ rht_for_each(head, tbl, hash)
+ if (!--elasticity)
+ return true;
+
+ return false;
}
+int rhashtable_insert_rehash(struct rhashtable *ht)
+{
+ struct bucket_table *old_tbl;
+ struct bucket_table *new_tbl;
+ struct bucket_table *tbl;
+ unsigned int size;
+ int err;
+
+ old_tbl = rht_dereference_rcu(ht->tbl, ht);
+ tbl = rhashtable_last_table(ht, old_tbl);
+
+ size = tbl->size;
+
+ if (rht_grow_above_75(ht, tbl))
+ size *= 2;
+ /* More than two rehashes (not resizes) detected. */
+ else if (WARN_ON(old_tbl != tbl && old_tbl->size == size))
+ return -EBUSY;
+
+ new_tbl = bucket_table_alloc(ht, size, GFP_ATOMIC);
+ if (new_tbl == NULL)
+ return -ENOMEM;
+
+ err = rhashtable_rehash_attach(ht, tbl, new_tbl);
+ if (err) {
+ bucket_table_free(new_tbl);
+ if (err == -EEXIST)
+ err = 0;
+ } else
+ schedule_work(&ht->run_work);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(rhashtable_insert_rehash);
+
int rhashtable_insert_slow(struct rhashtable *ht, const void *key,
struct rhash_head *obj,
struct bucket_table *tbl)
{
struct rhash_head *head;
- unsigned hash;
- int err = -EEXIST;
+ unsigned int hash;
+ int err;
+ tbl = rhashtable_last_table(ht, tbl);
hash = head_hashfn(ht, tbl, obj);
spin_lock_nested(rht_bucket_lock(tbl, hash), SINGLE_DEPTH_NESTING);
+ err = -EEXIST;
if (key && rhashtable_lookup_fast(ht, key, ht->p))
goto exit;
+ err = -EAGAIN;
+ if (rhashtable_check_elasticity(ht, tbl, hash) ||
+ rht_grow_above_100(ht, tbl))
+ goto exit;
+
err = 0;
head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash);
iter->skip = 0;
}
+ /* Ensure we see any new tables. */
+ smp_rmb();
+
iter->walker->tbl = rht_dereference_rcu(tbl->future_tbl, ht);
if (iter->walker->tbl) {
iter->slot = 0;
ht = iter->ht;
- mutex_lock(&ht->mutex);
+ spin_lock(&ht->lock);
if (tbl->rehash < tbl->size)
list_add(&iter->walker->list, &tbl->walkers);
else
iter->walker->tbl = NULL;
- mutex_unlock(&ht->mutex);
+ spin_unlock(&ht->lock);
iter->p = NULL;
(unsigned long)params->min_size);
}
+static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed)
+{
+ return jhash2(key, length, seed);
+}
+
/**
* rhashtable_init - initialize a new hash table
* @ht: hash table to be initialized
* struct rhash_head node;
* };
*
- * u32 my_hash_fn(const void *data, u32 seed)
+ * u32 my_hash_fn(const void *data, u32 len, u32 seed)
* {
* struct test_obj *obj = data;
*
size = HASH_DEFAULT_SIZE;
- if ((!(params->key_len && params->hashfn) && !params->obj_hashfn) ||
+ if ((!params->key_len && !params->obj_hashfn) ||
(params->obj_hashfn && !params->obj_cmpfn))
return -EINVAL;
memset(ht, 0, sizeof(*ht));
mutex_init(&ht->mutex);
+ spin_lock_init(&ht->lock);
memcpy(&ht->p, params, sizeof(*params));
if (params->min_size)
ht->p.min_size = max(ht->p.min_size, HASH_MIN_SIZE);
+ /* The maximum (not average) chain length grows with the
+ * size of the hash table, at a rate of (log N)/(log log N).
+ * The value of 16 is selected so that even if the hash
+ * table grew to 2^32 you would not expect the maximum
+ * chain length to exceed it unless we are under attack
+ * (or extremely unlucky).
+ *
+ * As this limit is only to detect attacks, we don't need
+ * to set it to a lower value as you'd need the chain
+ * length to vastly exceed 16 to have any real effect
+ * on the system.
+ */
+ if (!params->insecure_elasticity)
+ ht->elasticity = 16;
+
if (params->locks_mul)
ht->p.locks_mul = roundup_pow_of_two(params->locks_mul);
else
ht->p.locks_mul = BUCKET_LOCKS_PER_CPU;
- tbl = bucket_table_alloc(ht, size);
+ ht->key_len = ht->p.key_len;
+ if (!params->hashfn) {
+ ht->p.hashfn = jhash;
+
+ if (!(ht->key_len & (sizeof(u32) - 1))) {
+ ht->key_len /= sizeof(u32);
+ ht->p.hashfn = rhashtable_jhash2;
+ }
+ }
+
+ tbl = bucket_table_alloc(ht, size, GFP_KERNEL);
if (tbl == NULL)
return -ENOMEM;
EXPORT_SYMBOL_GPL(rhashtable_init);
/**
- * rhashtable_destroy - destroy hash table
+ * rhashtable_free_and_destroy - free elements and destroy hash table
* @ht: the hash table to destroy
+ * @free_fn: callback to release resources of element
+ * @arg: pointer passed to free_fn
*
- * Frees the bucket array. This function is not rcu safe, therefore the caller
- * has to make sure that no resizing may happen by unpublishing the hashtable
- * and waiting for the quiescent cycle before releasing the bucket array.
+ * Stops an eventual async resize. If defined, invokes free_fn for each
+ * element to releasal resources. Please note that RCU protected
+ * readers may still be accessing the elements. Releasing of resources
+ * must occur in a compatible manner. Then frees the bucket array.
+ *
+ * This function will eventually sleep to wait for an async resize
+ * to complete. The caller is responsible that no further write operations
+ * occurs in parallel.
*/
-void rhashtable_destroy(struct rhashtable *ht)
+void rhashtable_free_and_destroy(struct rhashtable *ht,
+ void (*free_fn)(void *ptr, void *arg),
+ void *arg)
{
- ht->being_destroyed = true;
+ const struct bucket_table *tbl;
+ unsigned int i;
cancel_work_sync(&ht->run_work);
mutex_lock(&ht->mutex);
- bucket_table_free(rht_dereference(ht->tbl, ht));
+ tbl = rht_dereference(ht->tbl, ht);
+ if (free_fn) {
+ for (i = 0; i < tbl->size; i++) {
+ struct rhash_head *pos, *next;
+
+ for (pos = rht_dereference(tbl->buckets[i], ht),
+ next = !rht_is_a_nulls(pos) ?
+ rht_dereference(pos->next, ht) : NULL;
+ !rht_is_a_nulls(pos);
+ pos = next,
+ next = !rht_is_a_nulls(pos) ?
+ rht_dereference(pos->next, ht) : NULL)
+ free_fn(rht_obj(ht, pos), arg);
+ }
+ }
+
+ bucket_table_free(tbl);
mutex_unlock(&ht->mutex);
}
+EXPORT_SYMBOL_GPL(rhashtable_free_and_destroy);
+
+void rhashtable_destroy(struct rhashtable *ht)
+{
+ return rhashtable_free_and_destroy(ht, NULL, NULL);
+}
EXPORT_SYMBOL_GPL(rhashtable_destroy);