/*
* Resizable, Scalable, Concurrent Hash Table
*
- * Copyright (c) 2014 Thomas Graf <tgraf@suug.ch>
+ * Copyright (c) 2014-2015 Thomas Graf <tgraf@suug.ch>
* Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net>
*
* Based on the following paper:
#include <linux/jhash.h>
#include <linux/random.h>
#include <linux/rhashtable.h>
+#include <linux/err.h>
#define HASH_DEFAULT_SIZE 64UL
#define HASH_MIN_SIZE 4UL
enum {
RHT_LOCK_NORMAL,
RHT_LOCK_NESTED,
- RHT_LOCK_NESTED2,
};
/* The bucket lock is selected based on the hash and protects mutations
* on a group of hash buckets.
*
+ * A maximum of tbl->size/2 bucket locks is allocated. This ensures that
+ * a single lock always covers both buckets which may both contains
+ * entries which link to the same bucket of the old table during resizing.
+ * This allows to simplify the locking as locking the bucket in both
+ * tables during resize always guarantee protection.
+ *
* IMPORTANT: When holding the bucket lock of both the old and new table
* during expansions and shrinking, the old bucket lock must always be
* acquired first.
return &tbl->locks[hash & tbl->locks_mask];
}
-#define ASSERT_RHT_MUTEX(HT) BUG_ON(!lockdep_rht_mutex_is_held(HT))
-#define ASSERT_BUCKET_LOCK(TBL, HASH) \
- BUG_ON(!lockdep_rht_bucket_is_held(TBL, HASH))
-
-#ifdef CONFIG_PROVE_LOCKING
-int lockdep_rht_mutex_is_held(struct rhashtable *ht)
-{
- return (debug_locks) ? lockdep_is_held(&ht->mutex) : 1;
-}
-EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held);
-
-int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash)
-{
- spinlock_t *lock = bucket_lock(tbl, hash);
-
- return (debug_locks) ? lockdep_is_held(lock) : 1;
-}
-EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held);
-#endif
-
static void *rht_obj(const struct rhashtable *ht, const struct rhash_head *he)
{
return (void *) he - ht->p.head_offset;
static u32 key_hashfn(struct rhashtable *ht, const void *key, u32 len)
{
- struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
- u32 hash;
-
- hash = ht->p.hashfn(key, len, ht->p.hash_rnd);
- hash >>= HASH_RESERVED_SPACE;
-
- return rht_bucket_index(tbl, hash);
+ return ht->p.hashfn(key, len, ht->p.hash_rnd) >> HASH_RESERVED_SPACE;
}
static u32 head_hashfn(const struct rhashtable *ht,
return rht_bucket_index(tbl, obj_raw_hashfn(ht, rht_obj(ht, he)));
}
+#ifdef CONFIG_PROVE_LOCKING
+static void debug_dump_buckets(const struct rhashtable *ht,
+ const struct bucket_table *tbl)
+{
+ struct rhash_head *he;
+ unsigned int i, hash;
+
+ for (i = 0; i < tbl->size; i++) {
+ pr_warn(" [Bucket %d] ", i);
+ rht_for_each_rcu(he, tbl, i) {
+ hash = head_hashfn(ht, tbl, he);
+ pr_cont("[hash = %#x, lock = %p] ",
+ hash, bucket_lock(tbl, hash));
+ }
+ pr_cont("\n");
+ }
+
+}
+
+static void debug_dump_table(struct rhashtable *ht,
+ const struct bucket_table *tbl,
+ unsigned int hash)
+{
+ struct bucket_table *old_tbl, *future_tbl;
+
+ pr_emerg("BUG: lock for hash %#x in table %p not held\n",
+ hash, tbl);
+
+ rcu_read_lock();
+ future_tbl = rht_dereference_rcu(ht->future_tbl, ht);
+ old_tbl = rht_dereference_rcu(ht->tbl, ht);
+ if (future_tbl != old_tbl) {
+ pr_warn("Future table %p (size: %zd)\n",
+ future_tbl, future_tbl->size);
+ debug_dump_buckets(ht, future_tbl);
+ }
+
+ pr_warn("Table %p (size: %zd)\n", old_tbl, old_tbl->size);
+ debug_dump_buckets(ht, old_tbl);
+
+ rcu_read_unlock();
+}
+
+#define ASSERT_RHT_MUTEX(HT) BUG_ON(!lockdep_rht_mutex_is_held(HT))
+#define ASSERT_BUCKET_LOCK(HT, TBL, HASH) \
+ do { \
+ if (unlikely(!lockdep_rht_bucket_is_held(TBL, HASH))) { \
+ debug_dump_table(HT, TBL, HASH); \
+ BUG(); \
+ } \
+ } while (0)
+
+int lockdep_rht_mutex_is_held(struct rhashtable *ht)
+{
+ return (debug_locks) ? lockdep_is_held(&ht->mutex) : 1;
+}
+EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held);
+
+int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash)
+{
+ spinlock_t *lock = bucket_lock(tbl, hash);
+
+ return (debug_locks) ? lockdep_is_held(lock) : 1;
+}
+EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held);
+#else
+#define ASSERT_RHT_MUTEX(HT)
+#define ASSERT_BUCKET_LOCK(HT, TBL, HASH)
+#endif
+
+
static struct rhash_head __rcu **bucket_tail(struct bucket_table *tbl, u32 n)
{
struct rhash_head __rcu **pprev;
nr_pcpus = min_t(unsigned int, nr_pcpus, 32UL);
size = roundup_pow_of_two(nr_pcpus * ht->p.locks_mul);
- /* Never allocate more than one lock per bucket */
- size = min_t(unsigned int, size, tbl->size);
+ /* Never allocate more than 0.5 locks per bucket */
+ size = min_t(unsigned int, size, tbl->size >> 1);
if (sizeof(spinlock_t) != 0) {
#ifdef CONFIG_NUMA
}
EXPORT_SYMBOL_GPL(rht_shrink_below_30);
-static void hashtable_chain_unzip(const struct rhashtable *ht,
+static void lock_buckets(struct bucket_table *new_tbl,
+ struct bucket_table *old_tbl, unsigned int hash)
+ __acquires(old_bucket_lock)
+{
+ spin_lock_bh(bucket_lock(old_tbl, hash));
+ if (new_tbl != old_tbl)
+ spin_lock_bh_nested(bucket_lock(new_tbl, hash),
+ RHT_LOCK_NESTED);
+}
+
+static void unlock_buckets(struct bucket_table *new_tbl,
+ struct bucket_table *old_tbl, unsigned int hash)
+ __releases(old_bucket_lock)
+{
+ if (new_tbl != old_tbl)
+ spin_unlock_bh(bucket_lock(new_tbl, hash));
+ spin_unlock_bh(bucket_lock(old_tbl, hash));
+}
+
+/**
+ * Unlink entries on bucket which hash to different bucket.
+ *
+ * Returns true if no more work needs to be performed on the bucket.
+ */
+static bool hashtable_chain_unzip(struct rhashtable *ht,
const struct bucket_table *new_tbl,
struct bucket_table *old_tbl,
size_t old_hash)
{
struct rhash_head *he, *p, *next;
- spinlock_t *new_bucket_lock, *new_bucket_lock2 = NULL;
unsigned int new_hash, new_hash2;
- ASSERT_BUCKET_LOCK(old_tbl, old_hash);
+ ASSERT_BUCKET_LOCK(ht, old_tbl, old_hash);
/* Old bucket empty, no work needed. */
p = rht_dereference_bucket(old_tbl->buckets[old_hash], old_tbl,
old_hash);
if (rht_is_a_nulls(p))
- return;
+ return false;
- new_hash = new_hash2 = head_hashfn(ht, new_tbl, p);
- new_bucket_lock = bucket_lock(new_tbl, new_hash);
+ new_hash = head_hashfn(ht, new_tbl, p);
+ ASSERT_BUCKET_LOCK(ht, new_tbl, new_hash);
/* Advance the old bucket pointer one or more times until it
* reaches a node that doesn't hash to the same bucket as the
*/
rht_for_each_continue(he, p->next, old_tbl, old_hash) {
new_hash2 = head_hashfn(ht, new_tbl, he);
+ ASSERT_BUCKET_LOCK(ht, new_tbl, new_hash2);
+
if (new_hash != new_hash2)
break;
p = he;
}
rcu_assign_pointer(old_tbl->buckets[old_hash], p->next);
- spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED);
-
- /* If we have encountered an entry that maps to a different bucket in
- * the new table, lock down that bucket as well as we might cut off
- * the end of the chain.
- */
- new_bucket_lock2 = bucket_lock(new_tbl, new_hash);
- if (new_bucket_lock != new_bucket_lock2)
- spin_lock_bh_nested(new_bucket_lock2, RHT_LOCK_NESTED2);
-
/* Find the subsequent node which does hash to the same
* bucket as node P, or NULL if no such node exists.
*/
*/
rcu_assign_pointer(p->next, next);
- if (new_bucket_lock != new_bucket_lock2)
- spin_unlock_bh(new_bucket_lock2);
- spin_unlock_bh(new_bucket_lock);
+ p = rht_dereference_bucket(old_tbl->buckets[old_hash], old_tbl,
+ old_hash);
+
+ return !rht_is_a_nulls(p);
}
-static void link_old_to_new(struct bucket_table *new_tbl,
+static void link_old_to_new(struct rhashtable *ht, struct bucket_table *new_tbl,
unsigned int new_hash, struct rhash_head *entry)
{
- spinlock_t *new_bucket_lock;
+ ASSERT_BUCKET_LOCK(ht, new_tbl, new_hash);
- new_bucket_lock = bucket_lock(new_tbl, new_hash);
-
- spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED);
rcu_assign_pointer(*bucket_tail(new_tbl, new_hash), entry);
- spin_unlock_bh(new_bucket_lock);
}
/**
{
struct bucket_table *new_tbl, *old_tbl = rht_dereference(ht->tbl, ht);
struct rhash_head *he;
- spinlock_t *old_bucket_lock;
unsigned int new_hash, old_hash;
bool complete = false;
*/
for (new_hash = 0; new_hash < new_tbl->size; new_hash++) {
old_hash = rht_bucket_index(old_tbl, new_hash);
- old_bucket_lock = bucket_lock(old_tbl, old_hash);
-
- spin_lock_bh(old_bucket_lock);
+ lock_buckets(new_tbl, old_tbl, new_hash);
rht_for_each(he, old_tbl, old_hash) {
if (head_hashfn(ht, new_tbl, he) == new_hash) {
- link_old_to_new(new_tbl, new_hash, he);
+ link_old_to_new(ht, new_tbl, new_hash, he);
break;
}
}
- spin_unlock_bh(old_bucket_lock);
+ unlock_buckets(new_tbl, old_tbl, new_hash);
}
- /* Publish the new table pointer. Lookups may now traverse
- * the new table, but they will not benefit from any
- * additional efficiency until later steps unzip the buckets.
- */
- rcu_assign_pointer(ht->tbl, new_tbl);
-
/* Unzip interleaved hash chains */
while (!complete && !ht->being_destroyed) {
/* Wait for readers. All new readers will see the new
*/
complete = true;
for (old_hash = 0; old_hash < old_tbl->size; old_hash++) {
- struct rhash_head *head;
+ lock_buckets(new_tbl, old_tbl, old_hash);
- old_bucket_lock = bucket_lock(old_tbl, old_hash);
- spin_lock_bh(old_bucket_lock);
-
- hashtable_chain_unzip(ht, new_tbl, old_tbl, old_hash);
- head = rht_dereference_bucket(old_tbl->buckets[old_hash],
- old_tbl, old_hash);
- if (!rht_is_a_nulls(head))
+ if (hashtable_chain_unzip(ht, new_tbl, old_tbl,
+ old_hash))
complete = false;
- spin_unlock_bh(old_bucket_lock);
+ unlock_buckets(new_tbl, old_tbl, old_hash);
}
}
+ rcu_assign_pointer(ht->tbl, new_tbl);
+ synchronize_rcu();
+
bucket_table_free(old_tbl);
return 0;
}
int rhashtable_shrink(struct rhashtable *ht)
{
struct bucket_table *new_tbl, *tbl = rht_dereference(ht->tbl, ht);
- spinlock_t *new_bucket_lock, *old_bucket_lock1, *old_bucket_lock2;
unsigned int new_hash;
ASSERT_RHT_MUTEX(ht);
* always divide the size in half when shrinking, each bucket
* in the new table maps to exactly two buckets in the old
* table.
- *
- * As removals can occur concurrently on the old table, we need
- * to lock down both matching buckets in the old table.
*/
for (new_hash = 0; new_hash < new_tbl->size; new_hash++) {
- old_bucket_lock1 = bucket_lock(tbl, new_hash);
- old_bucket_lock2 = bucket_lock(tbl, new_hash + new_tbl->size);
- new_bucket_lock = bucket_lock(new_tbl, new_hash);
-
- spin_lock_bh(old_bucket_lock1);
-
- /* Depending on the lock per buckets mapping, the bucket in
- * the lower and upper region may map to the same lock.
- */
- if (old_bucket_lock1 != old_bucket_lock2) {
- spin_lock_bh_nested(old_bucket_lock2, RHT_LOCK_NESTED);
- spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED2);
- } else {
- spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED);
- }
+ lock_buckets(new_tbl, tbl, new_hash);
rcu_assign_pointer(*bucket_tail(new_tbl, new_hash),
tbl->buckets[new_hash]);
+ ASSERT_BUCKET_LOCK(ht, tbl, new_hash + new_tbl->size);
rcu_assign_pointer(*bucket_tail(new_tbl, new_hash),
tbl->buckets[new_hash + new_tbl->size]);
- spin_unlock_bh(new_bucket_lock);
- if (old_bucket_lock1 != old_bucket_lock2)
- spin_unlock_bh(old_bucket_lock2);
- spin_unlock_bh(old_bucket_lock1);
+ unlock_buckets(new_tbl, tbl, new_hash);
}
/* Publish the new, valid hash table */
{
struct rhashtable *ht;
struct bucket_table *tbl;
+ struct rhashtable_walker *walker;
ht = container_of(work, struct rhashtable, run_work);
mutex_lock(&ht->mutex);
+ if (ht->being_destroyed)
+ goto unlock;
+
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))
rhashtable_shrink(ht);
+unlock:
mutex_unlock(&ht->mutex);
}
static void __rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj,
struct bucket_table *tbl, u32 hash)
{
- struct rhash_head *head = rht_dereference_bucket(tbl->buckets[hash],
- tbl, hash);
+ struct rhash_head *head;
+
+ hash = rht_bucket_index(tbl, hash);
+ head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash);
+
+ ASSERT_BUCKET_LOCK(ht, tbl, hash);
if (rht_is_a_nulls(head))
INIT_RHT_NULLS_HEAD(obj->next, ht, hash);
*/
void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj)
{
- struct bucket_table *tbl;
- spinlock_t *lock;
+ struct bucket_table *tbl, *old_tbl;
unsigned hash;
rcu_read_lock();
tbl = rht_dereference_rcu(ht->future_tbl, ht);
- hash = head_hashfn(ht, tbl, obj);
- lock = bucket_lock(tbl, hash);
+ old_tbl = rht_dereference_rcu(ht->tbl, ht);
+ hash = obj_raw_hashfn(ht, rht_obj(ht, obj));
- spin_lock_bh(lock);
+ lock_buckets(tbl, old_tbl, hash);
__rhashtable_insert(ht, obj, tbl, hash);
- spin_unlock_bh(lock);
+ unlock_buckets(tbl, old_tbl, hash);
rcu_read_unlock();
}
*/
bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *obj)
{
- struct bucket_table *tbl;
+ struct bucket_table *tbl, *new_tbl, *old_tbl;
struct rhash_head __rcu **pprev;
- struct rhash_head *he;
- spinlock_t *lock;
- unsigned int hash;
+ struct rhash_head *he, *he2;
+ unsigned int hash, new_hash;
bool ret = false;
rcu_read_lock();
- tbl = rht_dereference_rcu(ht->tbl, ht);
- hash = head_hashfn(ht, tbl, obj);
-
- lock = bucket_lock(tbl, hash);
- spin_lock_bh(lock);
+ old_tbl = rht_dereference_rcu(ht->tbl, ht);
+ tbl = new_tbl = rht_dereference_rcu(ht->future_tbl, ht);
+ new_hash = obj_raw_hashfn(ht, rht_obj(ht, obj));
+ lock_buckets(new_tbl, old_tbl, new_hash);
restart:
+ hash = rht_bucket_index(tbl, new_hash);
pprev = &tbl->buckets[hash];
rht_for_each(he, tbl, hash) {
if (he != obj) {
continue;
}
- rcu_assign_pointer(*pprev, obj->next);
+ ASSERT_BUCKET_LOCK(ht, tbl, hash);
+
+ if (old_tbl->size > new_tbl->size && tbl == old_tbl &&
+ !rht_is_a_nulls(obj->next) &&
+ head_hashfn(ht, tbl, obj->next) != hash) {
+ rcu_assign_pointer(*pprev, (struct rhash_head *) rht_marker(ht, hash));
+ } else if (unlikely(old_tbl->size < new_tbl->size && tbl == new_tbl)) {
+ rht_for_each_continue(he2, obj->next, tbl, hash) {
+ if (head_hashfn(ht, tbl, he2) == hash) {
+ rcu_assign_pointer(*pprev, he2);
+ goto found;
+ }
+ }
+
+ rcu_assign_pointer(*pprev, (struct rhash_head *) rht_marker(ht, hash));
+ } else {
+ rcu_assign_pointer(*pprev, obj->next);
+ }
+found:
ret = true;
break;
}
* resizing. Thus traversing both is fine and the added cost is
* very rare.
*/
- if (tbl != rht_dereference_rcu(ht->future_tbl, ht)) {
- spin_unlock_bh(lock);
-
- tbl = rht_dereference_rcu(ht->future_tbl, ht);
- hash = head_hashfn(ht, tbl, obj);
-
- lock = bucket_lock(tbl, hash);
- spin_lock_bh(lock);
+ if (tbl != old_tbl) {
+ tbl = old_tbl;
goto restart;
}
- spin_unlock_bh(lock);
+ unlock_buckets(new_tbl, old_tbl, new_hash);
if (ret) {
atomic_dec(&ht->nelems);
void *arg)
{
struct bucket_table *new_tbl, *old_tbl;
- spinlock_t *new_bucket_lock, *old_bucket_lock;
- u32 new_hash, old_hash;
+ u32 new_hash;
bool success = true;
BUG_ON(!ht->p.key_len);
rcu_read_lock();
-
old_tbl = rht_dereference_rcu(ht->tbl, ht);
- old_hash = head_hashfn(ht, old_tbl, obj);
- old_bucket_lock = bucket_lock(old_tbl, old_hash);
- spin_lock_bh(old_bucket_lock);
-
new_tbl = rht_dereference_rcu(ht->future_tbl, ht);
- new_hash = head_hashfn(ht, new_tbl, obj);
- new_bucket_lock = bucket_lock(new_tbl, new_hash);
- if (unlikely(old_tbl != new_tbl))
- spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED);
+ new_hash = obj_raw_hashfn(ht, rht_obj(ht, obj));
+
+ lock_buckets(new_tbl, old_tbl, new_hash);
if (rhashtable_lookup_compare(ht, rht_obj(ht, obj) + ht->p.key_offset,
compare, arg)) {
__rhashtable_insert(ht, obj, new_tbl, new_hash);
exit:
- if (unlikely(old_tbl != new_tbl))
- spin_unlock_bh(new_bucket_lock);
- spin_unlock_bh(old_bucket_lock);
-
+ unlock_buckets(new_tbl, old_tbl, new_hash);
rcu_read_unlock();
return success;
}
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),
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);