*/
#define _LGPL_SOURCE
+#define _GNU_SOURCE
#include <stdlib.h>
#include <errno.h>
#include <assert.h>
#include <stdio.h>
#include <stdint.h>
#include <string.h>
+#include <sched.h>
#include "config.h"
#include <urcu.h>
*/
#define REMOVED_FLAG (1UL << 0)
#define BUCKET_FLAG (1UL << 1)
-#define FLAGS_MASK ((1UL << 2) - 1)
+#define REMOVAL_OWNER_FLAG (1UL << 2)
+#define FLAGS_MASK ((1UL << 3) - 1)
/* Value of the end pointer. Should not interact with flags. */
#define END_VALUE NULL
unsigned long start, unsigned long len);
};
-static
-void _cds_lfht_add(struct cds_lfht *ht,
- cds_lfht_match_fct match,
- const void *key,
- unsigned long size,
- struct cds_lfht_node *node,
- struct cds_lfht_iter *unique_ret,
- int bucket);
-
/*
* Algorithm to reverse bits in a word by lookup table, extended to
* 64-bit words.
}
#endif
-unsigned int fls_ulong(unsigned long x)
+unsigned int cds_lfht_fls_ulong(unsigned long x)
{
#if (CAA_BITS_PER_LONG == 32)
return fls_u32(x);
* Return the minimum order for which x <= (1UL << order).
* Return -1 if x is 0.
*/
-int get_count_order_u32(uint32_t x)
+int cds_lfht_get_count_order_u32(uint32_t x)
{
if (!x)
return -1;
* Return the minimum order for which x <= (1UL << order).
* Return -1 if x is 0.
*/
-int get_count_order_ulong(unsigned long x)
+int cds_lfht_get_count_order_ulong(unsigned long x)
{
if (!x)
return -1;
- return fls_ulong(x - 1);
+ return cds_lfht_fls_ulong(x - 1);
}
static
* round up number of CPUs to next power of two, so we
* can use & for modulo.
*/
- maxcpus = 1UL << get_count_order_ulong(maxcpus);
+ maxcpus = 1UL << cds_lfht_get_count_order_ulong(maxcpus);
nr_cpus_mask = maxcpus - 1;
}
#else /* #if defined(HAVE_SYSCONF) */
dbg_printf("add split count %lu\n", split_count);
count = uatomic_add_return(&ht->count,
1UL << COUNT_COMMIT_ORDER);
- if (likely(count & (count - 1)))
+ if (caa_likely(count & (count - 1)))
return;
/* Only if global count is power of 2 */
dbg_printf("del split count %lu\n", split_count);
count = uatomic_add_return(&ht->count,
-(1UL << COUNT_COMMIT_ORDER));
- if (likely(count & (count - 1)))
+ if (caa_likely(count & (count - 1)))
return;
/* Only if global count is power of 2 */
chain_len);
if (chain_len >= CHAIN_LEN_RESIZE_THRESHOLD)
cds_lfht_resize_lazy_grow(ht, size,
- get_count_order_u32(chain_len - (CHAIN_LEN_TARGET - 1)));
+ cds_lfht_get_count_order_u32(chain_len - (CHAIN_LEN_TARGET - 1)));
}
static
return (struct cds_lfht_node *) (((unsigned long) node) | BUCKET_FLAG);
}
+static
+int is_removal_owner(struct cds_lfht_node *node)
+{
+ return ((unsigned long) node) & REMOVAL_OWNER_FLAG;
+}
+
+static
+struct cds_lfht_node *flag_removal_owner(struct cds_lfht_node *node)
+{
+ return (struct cds_lfht_node *) (((unsigned long) node) | REMOVAL_OWNER_FLAG);
+}
+
static
struct cds_lfht_node *get_end(void)
{
new_next = clear_flag(next);
(void) uatomic_cmpxchg(&iter_prev->next, iter, new_next);
}
- return;
}
static
*/
return -ENOENT;
}
- assert(!is_bucket(old_next));
- assert(new_node != clear_flag(old_next));
- new_node->next = clear_flag(old_next);
+ assert(old_next == clear_flag(old_next));
+ assert(new_node != old_next);
+ new_node->next = old_next;
/*
* Here is the whole trick for lock-free replace: we add
* the replacement node _after_ the node we want to
* next pointer, they will either skip the old node due
* to the removal flag and see the new node, or use
* the old node, but will not see the new one.
+ * This is a replacement of a node with another node
+ * that has the same value: we are therefore not
+ * removing a value from the hash table.
*/
ret_next = uatomic_cmpxchg(&old_node->next,
old_next, flag_removed(new_node));
*/
static
void _cds_lfht_add(struct cds_lfht *ht,
+ unsigned long hash,
cds_lfht_match_fct match,
const void *key,
unsigned long size,
assert(!is_bucket(node));
assert(!is_removed(node));
- bucket = lookup_bucket(ht, size, bit_reverse_ulong(node->reverse_hash));
+ bucket = lookup_bucket(ht, size, hash);
for (;;) {
uint32_t chain_len = 0;
static
int _cds_lfht_del(struct cds_lfht *ht, unsigned long size,
- struct cds_lfht_node *node,
- int bucket_removal)
+ struct cds_lfht_node *node)
{
- struct cds_lfht_node *bucket, *next, *old;
+ struct cds_lfht_node *bucket, *next;
if (!node) /* Return -ENOENT if asked to delete NULL node */
return -ENOENT;
/* logically delete the node */
assert(!is_bucket(node));
assert(!is_removed(node));
- old = rcu_dereference(node->next);
- do {
- struct cds_lfht_node *new_next;
+ assert(!is_removal_owner(node));
- next = old;
- if (caa_unlikely(is_removed(next)))
- return -ENOENT;
- if (bucket_removal)
- assert(is_bucket(next));
- else
- assert(!is_bucket(next));
- new_next = flag_removed(next);
- old = uatomic_cmpxchg(&node->next, next, new_next);
- } while (old != next);
+ /*
+ * We are first checking if the node had previously been
+ * logically removed (this check is not atomic with setting the
+ * logical removal flag). Return -ENOENT if the node had
+ * previously been removed.
+ */
+ next = rcu_dereference(node->next);
+ if (caa_unlikely(is_removed(next)))
+ return -ENOENT;
+ assert(!is_bucket(next));
+ /*
+ * We set the REMOVED_FLAG unconditionally. Note that there may
+ * be more than one concurrent thread setting this flag.
+ * Knowing which wins the race will be known after the garbage
+ * collection phase, stay tuned!
+ */
+ uatomic_or(&node->next, REMOVED_FLAG);
/* We performed the (logical) deletion. */
/*
_cds_lfht_gc_bucket(bucket, node);
assert(is_removed(rcu_dereference(node->next)));
- return 0;
+ /*
+ * Last phase: atomically exchange node->next with a version
+ * having "REMOVAL_OWNER_FLAG" set. If the returned node->next
+ * pointer did _not_ have "REMOVAL_OWNER_FLAG" set, we now own
+ * the node and win the removal race.
+ * It is interesting to note that all "add" paths are forbidden
+ * to change the next pointer starting from the point where the
+ * REMOVED_FLAG is set, so here using a read, followed by a
+ * xchg() suffice to guarantee that the xchg() will ever only
+ * set the "REMOVAL_OWNER_FLAG" (or change nothing if the flag
+ * was already set).
+ */
+ if (!is_removal_owner(uatomic_xchg(&node->next,
+ flag_removal_owner(node->next))))
+ return 0;
+ else
+ return -ENOENT;
}
static
} else {
nr_threads = 1;
}
- partition_len = len >> get_count_order_ulong(nr_threads);
+ partition_len = len >> cds_lfht_get_count_order_ulong(nr_threads);
work = calloc(nr_threads, sizeof(*work));
assert(work);
for (thread = 0; thread < nr_threads; thread++) {
dbg_printf("init populate: order %lu index %lu hash %lu\n",
i, j, j);
new_node->reverse_hash = bit_reverse_ulong(j);
- _cds_lfht_add(ht, NULL, NULL, size, new_node, NULL, 1);
+ _cds_lfht_add(ht, j, NULL, NULL, size, new_node, NULL, 1);
}
ht->flavor->read_unlock();
}
assert(i > MIN_TABLE_ORDER);
ht->flavor->read_lock();
for (j = size + start; j < size + start + len; j++) {
- struct cds_lfht_node *fini_node = bucket_at(ht, j);
+ struct cds_lfht_node *fini_bucket = bucket_at(ht, j);
+ struct cds_lfht_node *parent_bucket = bucket_at(ht, j - size);
assert(j >= size && j < (size << 1));
dbg_printf("remove entry: order %lu index %lu hash %lu\n",
i, j, j);
- fini_node->reverse_hash = bit_reverse_ulong(j);
- (void) _cds_lfht_del(ht, size, fini_node, 1);
+ /* Set the REMOVED_FLAG to freeze the ->next for gc */
+ uatomic_or(&fini_bucket->next, REMOVED_FLAG);
+ _cds_lfht_gc_bucket(parent_bucket, fini_bucket);
}
ht->flavor->read_unlock();
}
partition_resize_helper(ht, i, len, remove_table_partition);
}
+/*
+ * fini_table() is never called for first_order == 0, which is why
+ * free_by_rcu_order == 0 can be used as criterion to know if free must
+ * be called.
+ */
static
void fini_table(struct cds_lfht *ht,
unsigned long first_order, unsigned long last_order)
node->next = flag_bucket(get_end());
node->reverse_hash = 0;
- for (order = 1; order < get_count_order_ulong(size) + 1; order++) {
+ for (order = 1; order < cds_lfht_get_count_order_ulong(size) + 1; order++) {
len = 1UL << (order - 1);
cds_lfht_alloc_bucket_table(ht, order);
if (!init_size || (init_size & (init_size - 1)))
return NULL;
+ /*
+ * Memory management plugin default.
+ */
+ if (!mm) {
+ if (CAA_BITS_PER_LONG > 32
+ && max_nr_buckets
+ && max_nr_buckets <= (1ULL << 32)) {
+ /*
+ * For 64-bit architectures, with max number of
+ * buckets small enough not to use the entire
+ * 64-bit memory mapping space (and allowing a
+ * fair number of hash table instances), use the
+ * mmap allocator, which is faster than the
+ * order allocator.
+ */
+ mm = &cds_lfht_mm_mmap;
+ } else {
+ /*
+ * The fallback is to use the order allocator.
+ */
+ mm = &cds_lfht_mm_order;
+ }
+ }
+
/* max_nr_buckets == 0 for order based mm means infinite */
if (mm == &cds_lfht_mm_order && !max_nr_buckets)
max_nr_buckets = 1UL << (MAX_TABLE_ORDER - 1);
alloc_split_items_count(ht);
/* this mutex should not nest in read-side C.S. */
pthread_mutex_init(&ht->resize_mutex, NULL);
- order = get_count_order_ulong(init_size);
+ order = cds_lfht_get_count_order_ulong(init_size);
ht->resize_target = 1UL << order;
cds_lfht_create_bucket(ht, 1UL << order);
ht->size = 1UL << order;
{
unsigned long size;
- node->reverse_hash = bit_reverse_ulong((unsigned long) hash);
+ node->reverse_hash = bit_reverse_ulong(hash);
size = rcu_dereference(ht->size);
- _cds_lfht_add(ht, NULL, NULL, size, node, NULL, 0);
+ _cds_lfht_add(ht, hash, NULL, NULL, size, node, NULL, 0);
ht_count_add(ht, size, hash);
}
unsigned long size;
struct cds_lfht_iter iter;
- node->reverse_hash = bit_reverse_ulong((unsigned long) hash);
+ node->reverse_hash = bit_reverse_ulong(hash);
size = rcu_dereference(ht->size);
- _cds_lfht_add(ht, match, key, size, node, &iter, 0);
+ _cds_lfht_add(ht, hash, match, key, size, node, &iter, 0);
if (iter.node == node)
ht_count_add(ht, size, hash);
return iter.node;
unsigned long size;
struct cds_lfht_iter iter;
- node->reverse_hash = bit_reverse_ulong((unsigned long) hash);
+ node->reverse_hash = bit_reverse_ulong(hash);
size = rcu_dereference(ht->size);
for (;;) {
- _cds_lfht_add(ht, match, key, size, node, &iter, 0);
+ _cds_lfht_add(ht, hash, match, key, size, node, &iter, 0);
if (iter.node == node) {
ht_count_add(ht, size, hash);
return NULL;
}
}
-int cds_lfht_replace(struct cds_lfht *ht, struct cds_lfht_iter *old_iter,
+int cds_lfht_replace(struct cds_lfht *ht,
+ struct cds_lfht_iter *old_iter,
+ unsigned long hash,
+ cds_lfht_match_fct match,
+ const void *key,
struct cds_lfht_node *new_node)
{
unsigned long size;
+ new_node->reverse_hash = bit_reverse_ulong(hash);
+ if (!old_iter->node)
+ return -ENOENT;
+ if (caa_unlikely(old_iter->node->reverse_hash != new_node->reverse_hash))
+ return -EINVAL;
+ if (caa_unlikely(!match(old_iter->node, key)))
+ return -EINVAL;
size = rcu_dereference(ht->size);
return _cds_lfht_replace(ht, size, old_iter->node, old_iter->next,
new_node);
}
-int cds_lfht_del(struct cds_lfht *ht, struct cds_lfht_iter *iter)
+int cds_lfht_del(struct cds_lfht *ht, struct cds_lfht_node *node)
{
unsigned long size, hash;
int ret;
size = rcu_dereference(ht->size);
- ret = _cds_lfht_del(ht, size, iter->node, 0);
+ ret = _cds_lfht_del(ht, size, node);
if (!ret) {
- hash = bit_reverse_ulong(iter->node->reverse_hash);
+ hash = bit_reverse_ulong(node->reverse_hash);
ht_count_del(ht, size, hash);
}
return ret;
}
+int cds_lfht_is_node_deleted(struct cds_lfht_node *node)
+{
+ return is_removed(rcu_dereference(node->next));
+}
+
static
int cds_lfht_delete_bucket(struct cds_lfht *ht)
{
assert(is_bucket(node->next));
}
- for (order = get_count_order_ulong(size); (long)order >= 0; order--)
+ for (order = cds_lfht_get_count_order_ulong(size); (long)order >= 0; order--)
cds_lfht_free_bucket_table(ht, order);
return 0;
void cds_lfht_count_nodes(struct cds_lfht *ht,
long *approx_before,
unsigned long *count,
- unsigned long *removed,
long *approx_after)
{
struct cds_lfht_node *node, *next;
- unsigned long nr_bucket = 0;
+ unsigned long nr_bucket = 0, nr_removed = 0;
*approx_before = 0;
if (ht->split_count) {
}
*count = 0;
- *removed = 0;
/* Count non-bucket nodes in the table */
node = bucket_at(ht, 0);
next = rcu_dereference(node->next);
if (is_removed(next)) {
if (!is_bucket(next))
- (*removed)++;
+ (nr_removed)++;
else
(nr_bucket)++;
} else if (!is_bucket(next))
(nr_bucket)++;
node = clear_flag(next);
} while (!is_end(node));
+ dbg_printf("number of logically removed nodes: %lu\n", nr_removed);
dbg_printf("number of bucket nodes: %lu\n", nr_bucket);
*approx_after = 0;
if (ht->split_count) {
{
unsigned long old_order, new_order;
- old_order = get_count_order_ulong(old_size);
- new_order = get_count_order_ulong(new_size);
+ old_order = cds_lfht_get_count_order_ulong(old_size);
+ new_order = cds_lfht_get_count_order_ulong(new_size);
dbg_printf("resize from %lu (order %lu) to %lu (order %lu) buckets\n",
old_size, old_order, new_size, new_order);
assert(new_size > old_size);
unsigned long old_order, new_order;
new_size = max(new_size, MIN_TABLE_SIZE);
- old_order = get_count_order_ulong(old_size);
- new_order = get_count_order_ulong(new_size);
+ old_order = cds_lfht_get_count_order_ulong(old_size);
+ new_order = cds_lfht_get_count_order_ulong(new_size);
dbg_printf("resize from %lu (order %lu) to %lu (order %lu) buckets\n",
old_size, old_order, new_size, new_order);
assert(new_size < old_size);