/*
* 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
bool rht_grow_above_75(const struct rhashtable *ht, size_t new_size)
{
/* Expand table when exceeding 75% load */
- return atomic_read(&ht->nelems) > (new_size / 4 * 3);
+ return atomic_read(&ht->nelems) > (new_size / 4 * 3) &&
+ (ht->p.max_shift && atomic_read(&ht->shift) < ht->p.max_shift);
}
EXPORT_SYMBOL_GPL(rht_grow_above_75);
bool rht_shrink_below_30(const struct rhashtable *ht, size_t new_size)
{
/* Shrink table beneath 30% load */
- return atomic_read(&ht->nelems) < (new_size * 3 / 10);
+ return atomic_read(&ht->nelems) < (new_size * 3 / 10) &&
+ (atomic_read(&ht->shift) > ht->p.min_shift);
}
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;
-
- new_bucket_lock = bucket_lock(new_tbl, new_hash);
+ ASSERT_BUCKET_LOCK(ht, 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;
ASSERT_RHT_MUTEX(ht);
- if (ht->p.max_shift && ht->shift >= ht->p.max_shift)
- return 0;
-
new_tbl = bucket_table_alloc(ht, old_tbl->size * 2);
if (new_tbl == NULL)
return -ENOMEM;
- ht->shift++;
+ atomic_inc(&ht->shift);
/* Make insertions go into the new, empty table right away. Deletions
* and lookups will be attempted in both tables until we synchronize.
*/
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);
- if (ht->shift <= ht->p.min_shift)
- return 0;
-
new_tbl = bucket_table_alloc(ht, tbl->size / 2);
if (new_tbl == NULL)
return -ENOMEM;
* 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);
- spin_lock_bh_nested(old_bucket_lock2, RHT_LOCK_NESTED);
- spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED2);
+ 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);
- 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 */
rcu_assign_pointer(ht->tbl, new_tbl);
- ht->shift--;
+ atomic_dec(&ht->shift);
/* Wait for readers. No new readers will have references to the
* old hash table.
{
struct rhashtable *ht;
struct bucket_table *tbl;
+ struct rhashtable_walker *walker;
- ht = container_of(work, struct rhashtable, run_work.work);
+ 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);
}
if (tbl == new_tbl &&
((ht->p.grow_decision && ht->p.grow_decision(ht, size)) ||
(ht->p.shrink_decision && ht->p.shrink_decision(ht, size))))
- schedule_delayed_work(&ht->run_work, 0);
+ schedule_work(&ht->run_work);
+}
+
+static void __rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj,
+ struct bucket_table *tbl, u32 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);
+ else
+ RCU_INIT_POINTER(obj->next, head);
+
+ rcu_assign_pointer(tbl->buckets[hash], obj);
+
+ atomic_inc(&ht->nelems);
+
+ rhashtable_wakeup_worker(ht);
}
/**
- * rhashtable_insert - insert object into hash hash table
+ * rhashtable_insert - insert object into hash table
* @ht: hash table
* @obj: pointer to hash head inside object
*
*/
void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj)
{
- struct bucket_table *tbl;
- struct rhash_head *head;
- 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);
-
- spin_lock_bh(lock);
- head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash);
- if (rht_is_a_nulls(head))
- INIT_RHT_NULLS_HEAD(obj->next, ht, hash);
- else
- RCU_INIT_POINTER(obj->next, head);
-
- rcu_assign_pointer(tbl->buckets[hash], obj);
- spin_unlock_bh(lock);
-
- atomic_inc(&ht->nelems);
+ old_tbl = rht_dereference_rcu(ht->tbl, ht);
+ hash = obj_raw_hashfn(ht, rht_obj(ht, obj));
- rhashtable_wakeup_worker(ht);
+ lock_buckets(tbl, old_tbl, hash);
+ __rhashtable_insert(ht, obj, tbl, hash);
+ unlock_buckets(tbl, old_tbl, hash);
rcu_read_unlock();
}
* walk the bucket chain upon removal. The removal operation is thus
* considerable slow if the hash table is not correctly sized.
*
- * Will automatically shrink the table via rhashtable_expand() if the the
+ * Will automatically shrink the table via rhashtable_expand() if the
* shrink_decision function specified at rhashtable_init() returns true.
*
* The caller must ensure that no concurrent table mutations occur. It is
*/
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);
- atomic_dec(&ht->nelems);
-
- spin_unlock_bh(lock);
-
- rhashtable_wakeup_worker(ht);
+ 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_read_unlock();
+ rcu_assign_pointer(*pprev, (struct rhash_head *) rht_marker(ht, hash));
+ } else {
+ rcu_assign_pointer(*pprev, obj->next);
+ }
- return true;
+found:
+ ret = true;
+ break;
}
- if (tbl != rht_dereference_rcu(ht->tbl, ht)) {
- spin_unlock_bh(lock);
+ /* The entry may be linked in either 'tbl', 'future_tbl', or both.
+ * 'future_tbl' only exists for a short period of time during
+ * resizing. Thus traversing both is fine and the added cost is
+ * very rare.
+ */
+ if (tbl != old_tbl) {
+ tbl = old_tbl;
+ goto restart;
+ }
- tbl = rht_dereference_rcu(ht->tbl, ht);
- hash = head_hashfn(ht, tbl, obj);
+ unlock_buckets(new_tbl, old_tbl, new_hash);
- lock = bucket_lock(tbl, hash);
- spin_lock_bh(lock);
- goto restart;
+ if (ret) {
+ atomic_dec(&ht->nelems);
+ rhashtable_wakeup_worker(ht);
}
- spin_unlock_bh(lock);
rcu_read_unlock();
- return false;
+ return ret;
}
EXPORT_SYMBOL_GPL(rhashtable_remove);
* for a entry with an identical key. The first matching entry is returned.
*
* This lookup function may only be used for fixed key hash table (key_len
- * paramter set). It will BUG() if used inappropriately.
+ * parameter set). It will BUG() if used inappropriately.
*
* Lookups may occur in parallel with hashtable mutations and resizing.
*/
}
EXPORT_SYMBOL_GPL(rhashtable_lookup_compare);
+/**
+ * rhashtable_lookup_insert - lookup and insert object into hash table
+ * @ht: hash table
+ * @obj: pointer to hash head inside object
+ *
+ * Locks down the bucket chain in both the old and new table if a resize
+ * is in progress to ensure that writers can't remove from the old table
+ * and can't insert to the new table during the atomic operation of search
+ * and insertion. Searches for duplicates in both the old and new table if
+ * a resize is in progress.
+ *
+ * This lookup function may only be used for fixed key hash table (key_len
+ * parameter set). It will BUG() if used inappropriately.
+ *
+ * It is safe to call this function from atomic context.
+ *
+ * Will trigger an automatic deferred table resizing if the size grows
+ * beyond the watermark indicated by grow_decision() which can be passed
+ * to rhashtable_init().
+ */
+bool rhashtable_lookup_insert(struct rhashtable *ht, struct rhash_head *obj)
+{
+ struct rhashtable_compare_arg arg = {
+ .ht = ht,
+ .key = rht_obj(ht, obj) + ht->p.key_offset,
+ };
+
+ BUG_ON(!ht->p.key_len);
+
+ return rhashtable_lookup_compare_insert(ht, obj, &rhashtable_compare,
+ &arg);
+}
+EXPORT_SYMBOL_GPL(rhashtable_lookup_insert);
+
+/**
+ * rhashtable_lookup_compare_insert - search and insert object to hash table
+ * with compare function
+ * @ht: hash table
+ * @obj: pointer to hash head inside object
+ * @compare: compare function, must return true on match
+ * @arg: argument passed on to compare function
+ *
+ * Locks down the bucket chain in both the old and new table if a resize
+ * is in progress to ensure that writers can't remove from the old table
+ * and can't insert to the new table during the atomic operation of search
+ * and insertion. Searches for duplicates in both the old and new table if
+ * a resize is in progress.
+ *
+ * Lookups may occur in parallel with hashtable mutations and resizing.
+ *
+ * Will trigger an automatic deferred table resizing if the size grows
+ * beyond the watermark indicated by grow_decision() which can be passed
+ * to rhashtable_init().
+ */
+bool rhashtable_lookup_compare_insert(struct rhashtable *ht,
+ struct rhash_head *obj,
+ bool (*compare)(void *, void *),
+ void *arg)
+{
+ struct bucket_table *new_tbl, *old_tbl;
+ u32 new_hash;
+ bool success = true;
+
+ BUG_ON(!ht->p.key_len);
+
+ rcu_read_lock();
+ old_tbl = rht_dereference_rcu(ht->tbl, ht);
+ 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);
+
+ if (rhashtable_lookup_compare(ht, rht_obj(ht, obj) + ht->p.key_offset,
+ compare, arg)) {
+ success = false;
+ goto exit;
+ }
+
+ __rhashtable_insert(ht, obj, new_tbl, new_hash);
+
+exit:
+ 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);
if (tbl == NULL)
return -ENOMEM;
- ht->shift = ilog2(tbl->size);
+ atomic_set(&ht->nelems, 0);
+ atomic_set(&ht->shift, ilog2(tbl->size));
RCU_INIT_POINTER(ht->tbl, tbl);
RCU_INIT_POINTER(ht->future_tbl, tbl);
get_random_bytes(&ht->p.hash_rnd, sizeof(ht->p.hash_rnd));
if (ht->p.grow_decision || ht->p.shrink_decision)
- INIT_DEFERRABLE_WORK(&ht->run_work, rht_deferred_worker);
+ INIT_WORK(&ht->run_work, rht_deferred_worker);
return 0;
}
{
ht->being_destroyed = true;
- mutex_lock(&ht->mutex);
+ if (ht->p.grow_decision || ht->p.shrink_decision)
+ cancel_work_sync(&ht->run_work);
- cancel_delayed_work(&ht->run_work);
+ mutex_lock(&ht->mutex);
bucket_table_free(rht_dereference(ht->tbl, ht));
-
mutex_unlock(&ht->mutex);
}
EXPORT_SYMBOL_GPL(rhashtable_destroy);
-
-/**************************************************************************
- * Self Test
- **************************************************************************/
-
-#ifdef CONFIG_TEST_RHASHTABLE
-
-#define TEST_HT_SIZE 8
-#define TEST_ENTRIES 2048
-#define TEST_PTR ((void *) 0xdeadbeef)
-#define TEST_NEXPANDS 4
-
-struct test_obj {
- void *ptr;
- int value;
- struct rhash_head node;
-};
-
-static int __init test_rht_lookup(struct rhashtable *ht)
-{
- unsigned int i;
-
- for (i = 0; i < TEST_ENTRIES * 2; i++) {
- struct test_obj *obj;
- bool expected = !(i % 2);
- u32 key = i;
-
- obj = rhashtable_lookup(ht, &key);
-
- if (expected && !obj) {
- pr_warn("Test failed: Could not find key %u\n", key);
- return -ENOENT;
- } else if (!expected && obj) {
- pr_warn("Test failed: Unexpected entry found for key %u\n",
- key);
- return -EEXIST;
- } else if (expected && obj) {
- if (obj->ptr != TEST_PTR || obj->value != i) {
- pr_warn("Test failed: Lookup value mismatch %p!=%p, %u!=%u\n",
- obj->ptr, TEST_PTR, obj->value, i);
- return -EINVAL;
- }
- }
- }
-
- return 0;
-}
-
-static void test_bucket_stats(struct rhashtable *ht, bool quiet)
-{
- unsigned int cnt, rcu_cnt, i, total = 0;
- struct rhash_head *pos;
- struct test_obj *obj;
- struct bucket_table *tbl;
-
- tbl = rht_dereference_rcu(ht->tbl, ht);
- for (i = 0; i < tbl->size; i++) {
- rcu_cnt = cnt = 0;
-
- if (!quiet)
- pr_info(" [%#4x/%zu]", i, tbl->size);
-
- rht_for_each_entry_rcu(obj, pos, tbl, i, node) {
- cnt++;
- total++;
- if (!quiet)
- pr_cont(" [%p],", obj);
- }
-
- rht_for_each_entry_rcu(obj, pos, tbl, i, node)
- rcu_cnt++;
-
- if (rcu_cnt != cnt)
- pr_warn("Test failed: Chain count mismach %d != %d",
- cnt, rcu_cnt);
-
- if (!quiet)
- pr_cont("\n [%#x] first element: %p, chain length: %u\n",
- i, tbl->buckets[i], cnt);
- }
-
- pr_info(" Traversal complete: counted=%u, nelems=%u, entries=%d\n",
- total, atomic_read(&ht->nelems), TEST_ENTRIES);
-
- if (total != atomic_read(&ht->nelems) || total != TEST_ENTRIES)
- pr_warn("Test failed: Total count mismatch ^^^");
-}
-
-static int __init test_rhashtable(struct rhashtable *ht)
-{
- struct bucket_table *tbl;
- struct test_obj *obj;
- struct rhash_head *pos, *next;
- int err;
- unsigned int i;
-
- /*
- * Insertion Test:
- * Insert TEST_ENTRIES into table with all keys even numbers
- */
- pr_info(" Adding %d keys\n", TEST_ENTRIES);
- for (i = 0; i < TEST_ENTRIES; i++) {
- struct test_obj *obj;
-
- obj = kzalloc(sizeof(*obj), GFP_KERNEL);
- if (!obj) {
- err = -ENOMEM;
- goto error;
- }
-
- obj->ptr = TEST_PTR;
- obj->value = i * 2;
-
- rhashtable_insert(ht, &obj->node);
- }
-
- rcu_read_lock();
- test_bucket_stats(ht, true);
- test_rht_lookup(ht);
- rcu_read_unlock();
-
- for (i = 0; i < TEST_NEXPANDS; i++) {
- pr_info(" Table expansion iteration %u...\n", i);
- mutex_lock(&ht->mutex);
- rhashtable_expand(ht);
- mutex_unlock(&ht->mutex);
-
- rcu_read_lock();
- pr_info(" Verifying lookups...\n");
- test_rht_lookup(ht);
- rcu_read_unlock();
- }
-
- for (i = 0; i < TEST_NEXPANDS; i++) {
- pr_info(" Table shrinkage iteration %u...\n", i);
- mutex_lock(&ht->mutex);
- rhashtable_shrink(ht);
- mutex_unlock(&ht->mutex);
-
- rcu_read_lock();
- pr_info(" Verifying lookups...\n");
- test_rht_lookup(ht);
- rcu_read_unlock();
- }
-
- rcu_read_lock();
- test_bucket_stats(ht, true);
- rcu_read_unlock();
-
- pr_info(" Deleting %d keys\n", TEST_ENTRIES);
- for (i = 0; i < TEST_ENTRIES; i++) {
- u32 key = i * 2;
-
- obj = rhashtable_lookup(ht, &key);
- BUG_ON(!obj);
-
- rhashtable_remove(ht, &obj->node);
- kfree(obj);
- }
-
- return 0;
-
-error:
- tbl = rht_dereference_rcu(ht->tbl, ht);
- for (i = 0; i < tbl->size; i++)
- rht_for_each_entry_safe(obj, pos, next, tbl, i, node)
- kfree(obj);
-
- return err;
-}
-
-static int __init test_rht_init(void)
-{
- struct rhashtable ht;
- struct rhashtable_params params = {
- .nelem_hint = TEST_HT_SIZE,
- .head_offset = offsetof(struct test_obj, node),
- .key_offset = offsetof(struct test_obj, value),
- .key_len = sizeof(int),
- .hashfn = jhash,
- .nulls_base = (3U << RHT_BASE_SHIFT),
- .grow_decision = rht_grow_above_75,
- .shrink_decision = rht_shrink_below_30,
- };
- int err;
-
- pr_info("Running resizable hashtable tests...\n");
-
- err = rhashtable_init(&ht, ¶ms);
- if (err < 0) {
- pr_warn("Test failed: Unable to initialize hashtable: %d\n",
- err);
- return err;
- }
-
- err = test_rhashtable(&ht);
-
- rhashtable_destroy(&ht);
-
- return err;
-}
-
-subsys_initcall(test_rht_init);
-
-#endif /* CONFIG_TEST_RHASHTABLE */
projects / karo-tx-linux.git / blobdiff