-/*-
- * BSD LICENSE
- *
- * Copyright(c) 2010-2015 Intel Corporation. All rights reserved.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2016 Intel Corporation
*/
#include <string.h>
#include <rte_memcpy.h>
#include <rte_prefetch.h>
#include <rte_branch_prediction.h>
-#include <rte_memzone.h>
#include <rte_malloc.h>
#include <rte_eal.h>
#include <rte_eal_memconfig.h>
#include <rte_errno.h>
#include <rte_string_fns.h>
#include <rte_cpuflags.h>
-#include <rte_log.h>
#include <rte_rwlock.h>
#include <rte_spinlock.h>
#include <rte_ring.h>
#include <rte_compat.h>
+#include <rte_pause.h>
#include "rte_hash.h"
-#if defined(RTE_ARCH_X86_64) || defined(RTE_ARCH_I686) || defined(RTE_ARCH_X86_X32)
-#include "rte_cmp_x86.h"
-#endif
+#include "rte_cuckoo_hash.h"
-#if defined(RTE_ARCH_ARM64)
-#include "rte_cmp_arm64.h"
-#endif
TAILQ_HEAD(rte_hash_list, rte_tailq_entry);
};
EAL_REGISTER_TAILQ(rte_hash_tailq)
-/* Macro to enable/disable run-time checking of function parameters */
-#if defined(RTE_LIBRTE_HASH_DEBUG)
-#define RETURN_IF_TRUE(cond, retval) do { \
- if (cond) \
- return retval; \
-} while (0)
-#else
-#define RETURN_IF_TRUE(cond, retval)
-#endif
-
-/* Hash function used if none is specified */
-#if defined(RTE_MACHINE_CPUFLAG_SSE4_2) || defined(RTE_MACHINE_CPUFLAG_CRC32)
-#include <rte_hash_crc.h>
-#define DEFAULT_HASH_FUNC rte_hash_crc
-#else
-#include <rte_jhash.h>
-#define DEFAULT_HASH_FUNC rte_jhash
-#endif
-
-/** Number of items per bucket. */
-#define RTE_HASH_BUCKET_ENTRIES 4
-
-#define NULL_SIGNATURE 0
-
-#define KEY_ALIGNMENT 16
-
-#define LCORE_CACHE_SIZE 8
-
-struct lcore_cache {
- unsigned len; /**< Cache len */
- void *objs[LCORE_CACHE_SIZE]; /**< Cache objects */
-} __rte_cache_aligned;
-
-/** A hash table structure. */
-struct rte_hash {
- char name[RTE_HASH_NAMESIZE]; /**< Name of the hash. */
- uint32_t entries; /**< Total table entries. */
- uint32_t num_buckets; /**< Number of buckets in table. */
- uint32_t key_len; /**< Length of hash key. */
- rte_hash_function hash_func; /**< Function used to calculate hash. */
- uint32_t hash_func_init_val; /**< Init value used by hash_func. */
- rte_hash_cmp_eq_t rte_hash_cmp_eq; /**< Function used to compare keys. */
- uint32_t bucket_bitmask; /**< Bitmask for getting bucket index
- from hash signature. */
- uint32_t key_entry_size; /**< Size of each key entry. */
-
- struct rte_ring *free_slots; /**< Ring that stores all indexes
- of the free slots in the key table */
- void *key_store; /**< Table storing all keys and data */
- struct rte_hash_bucket *buckets; /**< Table with buckets storing all the
- hash values and key indexes
- to the key table*/
- uint8_t hw_trans_mem_support; /**< Hardware transactional
- memory support */
- struct lcore_cache *local_free_slots;
- /**< Local cache per lcore, storing some indexes of the free slots */
-} __rte_cache_aligned;
-
-/* Structure storing both primary and secondary hashes */
-struct rte_hash_signatures {
- union {
- struct {
- hash_sig_t current;
- hash_sig_t alt;
- };
- uint64_t sig;
- };
-};
-
-/* Structure that stores key-value pair */
-struct rte_hash_key {
- union {
- uintptr_t idata;
- void *pdata;
- };
- /* Variable key size */
- char key[0];
-} __attribute__((aligned(KEY_ALIGNMENT)));
-
-/** Bucket structure */
-struct rte_hash_bucket {
- struct rte_hash_signatures signatures[RTE_HASH_BUCKET_ENTRIES];
- /* Includes dummy key index that always contains index 0 */
- uint32_t key_idx[RTE_HASH_BUCKET_ENTRIES + 1];
- uint8_t flag[RTE_HASH_BUCKET_ENTRIES];
-} __rte_cache_aligned;
-
struct rte_hash *
rte_hash_find_existing(const char *name)
{
void rte_hash_set_cmp_func(struct rte_hash *h, rte_hash_cmp_eq_t func)
{
- h->rte_hash_cmp_eq = func;
+ h->cmp_jump_table_idx = KEY_CUSTOM;
+ h->rte_hash_custom_cmp_eq = func;
+}
+
+static inline int
+rte_hash_cmp_eq(const void *key1, const void *key2, const struct rte_hash *h)
+{
+ if (h->cmp_jump_table_idx == KEY_CUSTOM)
+ return h->rte_hash_custom_cmp_eq(key1, key2, h->key_len);
+ else
+ return cmp_jump_table[h->cmp_jump_table_idx](key1, key2, h->key_len);
}
struct rte_hash *
void *buckets = NULL;
char ring_name[RTE_RING_NAMESIZE];
unsigned num_key_slots;
- unsigned hw_trans_mem_support = 0;
unsigned i;
+ unsigned int hw_trans_mem_support = 0, multi_writer_support = 0;
+ unsigned int readwrite_concur_support = 0;
+
+ rte_hash_function default_hash_func = (rte_hash_function)rte_jhash;
hash_list = RTE_TAILQ_CAST(rte_hash_tailq.head, rte_hash_list);
/* Check for valid parameters */
if ((params->entries > RTE_HASH_ENTRIES_MAX) ||
(params->entries < RTE_HASH_BUCKET_ENTRIES) ||
- !rte_is_power_of_2(RTE_HASH_BUCKET_ENTRIES) ||
(params->key_len == 0)) {
rte_errno = EINVAL;
RTE_LOG(ERR, HASH, "rte_hash_create has invalid parameters\n");
if (params->extra_flag & RTE_HASH_EXTRA_FLAGS_TRANS_MEM_SUPPORT)
hw_trans_mem_support = 1;
+ if (params->extra_flag & RTE_HASH_EXTRA_FLAGS_MULTI_WRITER_ADD)
+ multi_writer_support = 1;
+
+ if (params->extra_flag & RTE_HASH_EXTRA_FLAGS_RW_CONCURRENCY) {
+ readwrite_concur_support = 1;
+ multi_writer_support = 1;
+ }
+
+ /* Store all keys and leave the first entry as a dummy entry for lookup_bulk */
+ if (multi_writer_support)
+ /*
+ * Increase number of slots by total number of indices
+ * that can be stored in the lcore caches
+ * except for the first cache
+ */
+ num_key_slots = params->entries + (RTE_MAX_LCORE - 1) *
+ (LCORE_CACHE_SIZE - 1) + 1;
+ else
+ num_key_slots = params->entries + 1;
+
+ snprintf(ring_name, sizeof(ring_name), "HT_%s", params->name);
+ /* Create ring (Dummy slot index is not enqueued) */
+ r = rte_ring_create(ring_name, rte_align32pow2(num_key_slots),
+ params->socket_id, 0);
+ if (r == NULL) {
+ RTE_LOG(ERR, HASH, "memory allocation failed\n");
+ goto err;
+ }
+
snprintf(hash_name, sizeof(hash_name), "HT_%s", params->name);
- /* Guarantee there's no existing */
- h = rte_hash_find_existing(params->name);
- if (h != NULL)
- return h;
+ rte_rwlock_write_lock(RTE_EAL_TAILQ_RWLOCK);
+
+ /* guarantee there's no existing: this is normally already checked
+ * by ring creation above */
+ TAILQ_FOREACH(te, hash_list, next) {
+ h = (struct rte_hash *) te->data;
+ if (strncmp(params->name, h->name, RTE_HASH_NAMESIZE) == 0)
+ break;
+ }
+ h = NULL;
+ if (te != NULL) {
+ rte_errno = EEXIST;
+ te = NULL;
+ goto err_unlock;
+ }
te = rte_zmalloc("HASH_TAILQ_ENTRY", sizeof(*te), 0);
if (te == NULL) {
RTE_LOG(ERR, HASH, "tailq entry allocation failed\n");
- goto err;
+ goto err_unlock;
}
h = (struct rte_hash *)rte_zmalloc_socket(hash_name, sizeof(struct rte_hash),
if (h == NULL) {
RTE_LOG(ERR, HASH, "memory allocation failed\n");
- goto err;
+ goto err_unlock;
}
const uint32_t num_buckets = rte_align32pow2(params->entries)
if (buckets == NULL) {
RTE_LOG(ERR, HASH, "memory allocation failed\n");
- goto err;
+ goto err_unlock;
}
const uint32_t key_entry_size = sizeof(struct rte_hash_key) + params->key_len;
-
- /* Store all keys and leave the first entry as a dummy entry for lookup_bulk */
- if (hw_trans_mem_support)
- /*
- * Increase number of slots by total number of indices
- * that can be stored in the lcore caches
- * except for the first cache
- */
- num_key_slots = params->entries + (RTE_MAX_LCORE - 1) *
- LCORE_CACHE_SIZE + 1;
- else
- num_key_slots = params->entries + 1;
-
const uint64_t key_tbl_size = (uint64_t) key_entry_size * num_key_slots;
k = rte_zmalloc_socket(NULL, key_tbl_size,
if (k == NULL) {
RTE_LOG(ERR, HASH, "memory allocation failed\n");
- goto err;
+ goto err_unlock;
}
/*
* If x86 architecture is used, select appropriate compare function,
- * which may use x86 instrinsics, otherwise use memcmp
+ * which may use x86 intrinsics, otherwise use memcmp
*/
-#if defined(RTE_ARCH_X86_64) || defined(RTE_ARCH_I686) ||\
- defined(RTE_ARCH_X86_X32) || defined(RTE_ARCH_ARM64)
+#if defined(RTE_ARCH_X86) || defined(RTE_ARCH_ARM64)
/* Select function to compare keys */
switch (params->key_len) {
case 16:
- h->rte_hash_cmp_eq = rte_hash_k16_cmp_eq;
+ h->cmp_jump_table_idx = KEY_16_BYTES;
break;
case 32:
- h->rte_hash_cmp_eq = rte_hash_k32_cmp_eq;
+ h->cmp_jump_table_idx = KEY_32_BYTES;
break;
case 48:
- h->rte_hash_cmp_eq = rte_hash_k48_cmp_eq;
+ h->cmp_jump_table_idx = KEY_48_BYTES;
break;
case 64:
- h->rte_hash_cmp_eq = rte_hash_k64_cmp_eq;
+ h->cmp_jump_table_idx = KEY_64_BYTES;
break;
case 80:
- h->rte_hash_cmp_eq = rte_hash_k80_cmp_eq;
+ h->cmp_jump_table_idx = KEY_80_BYTES;
break;
case 96:
- h->rte_hash_cmp_eq = rte_hash_k96_cmp_eq;
+ h->cmp_jump_table_idx = KEY_96_BYTES;
break;
case 112:
- h->rte_hash_cmp_eq = rte_hash_k112_cmp_eq;
+ h->cmp_jump_table_idx = KEY_112_BYTES;
break;
case 128:
- h->rte_hash_cmp_eq = rte_hash_k128_cmp_eq;
+ h->cmp_jump_table_idx = KEY_128_BYTES;
break;
default:
/* If key is not multiple of 16, use generic memcmp */
- h->rte_hash_cmp_eq = memcmp;
+ h->cmp_jump_table_idx = KEY_OTHER_BYTES;
}
#else
- h->rte_hash_cmp_eq = memcmp;
+ h->cmp_jump_table_idx = KEY_OTHER_BYTES;
#endif
- snprintf(ring_name, sizeof(ring_name), "HT_%s", params->name);
- r = rte_ring_create(ring_name, rte_align32pow2(num_key_slots),
- params->socket_id, 0);
- if (r == NULL) {
- RTE_LOG(ERR, HASH, "memory allocation failed\n");
- goto err;
- }
-
- if (hw_trans_mem_support) {
+ if (multi_writer_support) {
h->local_free_slots = rte_zmalloc_socket(NULL,
sizeof(struct lcore_cache) * RTE_MAX_LCORE,
RTE_CACHE_LINE_SIZE, params->socket_id);
}
+ /* Default hash function */
+#if defined(RTE_ARCH_X86)
+ default_hash_func = (rte_hash_function)rte_hash_crc;
+#elif defined(RTE_ARCH_ARM64)
+ if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_CRC32))
+ default_hash_func = (rte_hash_function)rte_hash_crc;
+#endif
/* Setup hash context */
snprintf(h->name, sizeof(h->name), "%s", params->name);
h->entries = params->entries;
h->bucket_bitmask = h->num_buckets - 1;
h->buckets = buckets;
h->hash_func = (params->hash_func == NULL) ?
- DEFAULT_HASH_FUNC : params->hash_func;
+ default_hash_func : params->hash_func;
h->key_store = k;
h->free_slots = r;
h->hw_trans_mem_support = hw_trans_mem_support;
+ h->multi_writer_support = multi_writer_support;
+ h->readwrite_concur_support = readwrite_concur_support;
+
+#if defined(RTE_ARCH_X86)
+ if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2))
+ h->sig_cmp_fn = RTE_HASH_COMPARE_AVX2;
+ else if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_SSE2))
+ h->sig_cmp_fn = RTE_HASH_COMPARE_SSE;
+ else
+#endif
+ h->sig_cmp_fn = RTE_HASH_COMPARE_SCALAR;
- /* populate the free slots ring. Entry zero is reserved for key misses */
- for (i = 1; i < params->entries + 1; i++)
+ /* Turn on multi-writer only with explicit flag from user and TM
+ * support.
+ */
+ if (h->multi_writer_support) {
+ h->readwrite_lock = rte_malloc(NULL, sizeof(rte_rwlock_t),
+ RTE_CACHE_LINE_SIZE);
+ if (h->readwrite_lock == NULL)
+ goto err_unlock;
+
+ rte_rwlock_init(h->readwrite_lock);
+ }
+
+ /* Populate free slots ring. Entry zero is reserved for key misses. */
+ for (i = 1; i < num_key_slots; i++)
rte_ring_sp_enqueue(r, (void *)((uintptr_t) i));
- rte_rwlock_write_lock(RTE_EAL_TAILQ_RWLOCK);
te->data = (void *) h;
TAILQ_INSERT_TAIL(hash_list, te, next);
rte_rwlock_write_unlock(RTE_EAL_TAILQ_RWLOCK);
return h;
+err_unlock:
+ rte_rwlock_write_unlock(RTE_EAL_TAILQ_RWLOCK);
err:
+ rte_ring_free(r);
rte_free(te);
rte_free(h);
rte_free(buckets);
rte_rwlock_write_unlock(RTE_EAL_TAILQ_RWLOCK);
- if (h->hw_trans_mem_support)
+ if (h->multi_writer_support) {
rte_free(h->local_free_slots);
-
+ rte_free(h->readwrite_lock);
+ }
rte_ring_free(h->free_slots);
rte_free(h->key_store);
rte_free(h->buckets);
uint32_t tag = primary_hash >> all_bits_shift;
- return (primary_hash ^ ((tag + 1) * alt_bits_xor));
+ return primary_hash ^ ((tag + 1) * alt_bits_xor);
+}
+
+int32_t
+rte_hash_count(const struct rte_hash *h)
+{
+ uint32_t tot_ring_cnt, cached_cnt = 0;
+ uint32_t i, ret;
+
+ if (h == NULL)
+ return -EINVAL;
+
+ if (h->multi_writer_support) {
+ tot_ring_cnt = h->entries + (RTE_MAX_LCORE - 1) *
+ (LCORE_CACHE_SIZE - 1);
+ for (i = 0; i < RTE_MAX_LCORE; i++)
+ cached_cnt += h->local_free_slots[i].len;
+
+ ret = tot_ring_cnt - rte_ring_count(h->free_slots) -
+ cached_cnt;
+ } else {
+ tot_ring_cnt = h->entries;
+ ret = tot_ring_cnt - rte_ring_count(h->free_slots);
+ }
+ return ret;
+}
+
+/* Read write locks implemented using rte_rwlock */
+static inline void
+__hash_rw_writer_lock(const struct rte_hash *h)
+{
+ if (h->multi_writer_support && h->hw_trans_mem_support)
+ rte_rwlock_write_lock_tm(h->readwrite_lock);
+ else if (h->multi_writer_support)
+ rte_rwlock_write_lock(h->readwrite_lock);
+}
+
+
+static inline void
+__hash_rw_reader_lock(const struct rte_hash *h)
+{
+ if (h->readwrite_concur_support && h->hw_trans_mem_support)
+ rte_rwlock_read_lock_tm(h->readwrite_lock);
+ else if (h->readwrite_concur_support)
+ rte_rwlock_read_lock(h->readwrite_lock);
+}
+
+static inline void
+__hash_rw_writer_unlock(const struct rte_hash *h)
+{
+ if (h->multi_writer_support && h->hw_trans_mem_support)
+ rte_rwlock_write_unlock_tm(h->readwrite_lock);
+ else if (h->multi_writer_support)
+ rte_rwlock_write_unlock(h->readwrite_lock);
+}
+
+static inline void
+__hash_rw_reader_unlock(const struct rte_hash *h)
+{
+ if (h->readwrite_concur_support && h->hw_trans_mem_support)
+ rte_rwlock_read_unlock_tm(h->readwrite_lock);
+ else if (h->readwrite_concur_support)
+ rte_rwlock_read_unlock(h->readwrite_lock);
}
void
rte_hash_reset(struct rte_hash *h)
{
void *ptr;
- unsigned i;
+ uint32_t tot_ring_cnt, i;
if (h == NULL)
return;
+ __hash_rw_writer_lock(h);
memset(h->buckets, 0, h->num_buckets * sizeof(struct rte_hash_bucket));
memset(h->key_store, 0, h->key_entry_size * (h->entries + 1));
rte_pause();
/* Repopulate the free slots ring. Entry zero is reserved for key misses */
- for (i = 1; i < h->entries + 1; i++)
+ if (h->multi_writer_support)
+ tot_ring_cnt = h->entries + (RTE_MAX_LCORE - 1) *
+ (LCORE_CACHE_SIZE - 1);
+ else
+ tot_ring_cnt = h->entries;
+
+ for (i = 1; i < tot_ring_cnt + 1; i++)
rte_ring_sp_enqueue(h->free_slots, (void *)((uintptr_t) i));
- if (h->hw_trans_mem_support) {
+ if (h->multi_writer_support) {
/* Reset local caches per lcore */
for (i = 0; i < RTE_MAX_LCORE; i++)
h->local_free_slots[i].len = 0;
}
+ __hash_rw_writer_unlock(h);
}
-/* Search for an entry that can be pushed to its alternative location */
-static inline int
-make_space_bucket(const struct rte_hash *h, struct rte_hash_bucket *bkt)
+/*
+ * Function called to enqueue back an index in the cache/ring,
+ * as slot has not being used and it can be used in the
+ * next addition attempt.
+ */
+static inline void
+enqueue_slot_back(const struct rte_hash *h,
+ struct lcore_cache *cached_free_slots,
+ void *slot_id)
{
- unsigned i, j;
- int ret;
- uint32_t next_bucket_idx;
- struct rte_hash_bucket *next_bkt[RTE_HASH_BUCKET_ENTRIES];
+ if (h->multi_writer_support) {
+ cached_free_slots->objs[cached_free_slots->len] = slot_id;
+ cached_free_slots->len++;
+ } else
+ rte_ring_sp_enqueue(h->free_slots, slot_id);
+}
+
+/* Search a key from bucket and update its data */
+static inline int32_t
+search_and_update(const struct rte_hash *h, void *data, const void *key,
+ struct rte_hash_bucket *bkt, hash_sig_t sig, hash_sig_t alt_hash)
+{
+ int i;
+ struct rte_hash_key *k, *keys = h->key_store;
- /*
- * Push existing item (search for bucket with space in
- * alternative locations) to its alternative location
- */
for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
- /* Search for space in alternative locations */
- next_bucket_idx = bkt->signatures[i].alt & h->bucket_bitmask;
- next_bkt[i] = &h->buckets[next_bucket_idx];
- for (j = 0; j < RTE_HASH_BUCKET_ENTRIES; j++) {
- if (next_bkt[i]->signatures[j].sig == NULL_SIGNATURE)
- break;
+ if (bkt->sig_current[i] == sig &&
+ bkt->sig_alt[i] == alt_hash) {
+ k = (struct rte_hash_key *) ((char *)keys +
+ bkt->key_idx[i] * h->key_entry_size);
+ if (rte_hash_cmp_eq(key, k->key, h) == 0) {
+ /* Update data */
+ k->pdata = data;
+ /*
+ * Return index where key is stored,
+ * subtracting the first dummy index
+ */
+ return bkt->key_idx[i] - 1;
+ }
}
-
- if (j != RTE_HASH_BUCKET_ENTRIES)
- break;
}
+ return -1;
+}
+
+/* Only tries to insert at one bucket (@prim_bkt) without trying to push
+ * buckets around.
+ * return 1 if matching existing key, return 0 if succeeds, return -1 for no
+ * empty entry.
+ */
+static inline int32_t
+rte_hash_cuckoo_insert_mw(const struct rte_hash *h,
+ struct rte_hash_bucket *prim_bkt,
+ struct rte_hash_bucket *sec_bkt,
+ const struct rte_hash_key *key, void *data,
+ hash_sig_t sig, hash_sig_t alt_hash, uint32_t new_idx,
+ int32_t *ret_val)
+{
+ unsigned int i;
+ struct rte_hash_bucket *cur_bkt = prim_bkt;
+ int32_t ret;
- /* Alternative location has spare room (end of recursive function) */
- if (i != RTE_HASH_BUCKET_ENTRIES) {
- next_bkt[i]->signatures[j].alt = bkt->signatures[i].current;
- next_bkt[i]->signatures[j].current = bkt->signatures[i].alt;
- next_bkt[i]->key_idx[j] = bkt->key_idx[i];
- return i;
+ __hash_rw_writer_lock(h);
+ /* Check if key was inserted after last check but before this
+ * protected region in case of inserting duplicated keys.
+ */
+ ret = search_and_update(h, data, key, cur_bkt, sig, alt_hash);
+ if (ret != -1) {
+ __hash_rw_writer_unlock(h);
+ *ret_val = ret;
+ return 1;
+ }
+ ret = search_and_update(h, data, key, sec_bkt, alt_hash, sig);
+ if (ret != -1) {
+ __hash_rw_writer_unlock(h);
+ *ret_val = ret;
+ return 1;
}
- /* Pick entry that has not been pushed yet */
- for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++)
- if (bkt->flag[i] == 0)
+ /* Insert new entry if there is room in the primary
+ * bucket.
+ */
+ for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
+ /* Check if slot is available */
+ if (likely(prim_bkt->key_idx[i] == EMPTY_SLOT)) {
+ prim_bkt->sig_current[i] = sig;
+ prim_bkt->sig_alt[i] = alt_hash;
+ prim_bkt->key_idx[i] = new_idx;
break;
+ }
+ }
+ __hash_rw_writer_unlock(h);
+
+ if (i != RTE_HASH_BUCKET_ENTRIES)
+ return 0;
- /* All entries have been pushed, so entry cannot be added */
- if (i == RTE_HASH_BUCKET_ENTRIES)
- return -ENOSPC;
+ /* no empty entry */
+ return -1;
+}
- /* Set flag to indicate that this entry is going to be pushed */
- bkt->flag[i] = 1;
- /* Need room in alternative bucket to insert the pushed entry */
- ret = make_space_bucket(h, next_bkt[i]);
- /*
- * After recursive function.
- * Clear flags and insert the pushed entry
- * in its alternative location if successful,
- * or return error
+/* Shift buckets along provided cuckoo_path (@leaf and @leaf_slot) and fill
+ * the path head with new entry (sig, alt_hash, new_idx)
+ * return 1 if matched key found, return -1 if cuckoo path invalided and fail,
+ * return 0 if succeeds.
+ */
+static inline int
+rte_hash_cuckoo_move_insert_mw(const struct rte_hash *h,
+ struct rte_hash_bucket *bkt,
+ struct rte_hash_bucket *alt_bkt,
+ const struct rte_hash_key *key, void *data,
+ struct queue_node *leaf, uint32_t leaf_slot,
+ hash_sig_t sig, hash_sig_t alt_hash, uint32_t new_idx,
+ int32_t *ret_val)
+{
+ uint32_t prev_alt_bkt_idx;
+ struct rte_hash_bucket *cur_bkt = bkt;
+ struct queue_node *prev_node, *curr_node = leaf;
+ struct rte_hash_bucket *prev_bkt, *curr_bkt = leaf->bkt;
+ uint32_t prev_slot, curr_slot = leaf_slot;
+ int32_t ret;
+
+ __hash_rw_writer_lock(h);
+
+ /* In case empty slot was gone before entering protected region */
+ if (curr_bkt->key_idx[curr_slot] != EMPTY_SLOT) {
+ __hash_rw_writer_unlock(h);
+ return -1;
+ }
+
+ /* Check if key was inserted after last check but before this
+ * protected region.
*/
- bkt->flag[i] = 0;
- if (ret >= 0) {
- next_bkt[i]->signatures[ret].alt = bkt->signatures[i].current;
- next_bkt[i]->signatures[ret].current = bkt->signatures[i].alt;
- next_bkt[i]->key_idx[ret] = bkt->key_idx[i];
- return i;
- } else
- return ret;
+ ret = search_and_update(h, data, key, cur_bkt, sig, alt_hash);
+ if (ret != -1) {
+ __hash_rw_writer_unlock(h);
+ *ret_val = ret;
+ return 1;
+ }
+
+ ret = search_and_update(h, data, key, alt_bkt, alt_hash, sig);
+ if (ret != -1) {
+ __hash_rw_writer_unlock(h);
+ *ret_val = ret;
+ return 1;
+ }
+
+ while (likely(curr_node->prev != NULL)) {
+ prev_node = curr_node->prev;
+ prev_bkt = prev_node->bkt;
+ prev_slot = curr_node->prev_slot;
+
+ prev_alt_bkt_idx =
+ prev_bkt->sig_alt[prev_slot] & h->bucket_bitmask;
+
+ if (unlikely(&h->buckets[prev_alt_bkt_idx]
+ != curr_bkt)) {
+ /* revert it to empty, otherwise duplicated keys */
+ curr_bkt->key_idx[curr_slot] = EMPTY_SLOT;
+ __hash_rw_writer_unlock(h);
+ return -1;
+ }
+
+ /* Need to swap current/alt sig to allow later
+ * Cuckoo insert to move elements back to its
+ * primary bucket if available
+ */
+ curr_bkt->sig_alt[curr_slot] =
+ prev_bkt->sig_current[prev_slot];
+ curr_bkt->sig_current[curr_slot] =
+ prev_bkt->sig_alt[prev_slot];
+ curr_bkt->key_idx[curr_slot] =
+ prev_bkt->key_idx[prev_slot];
+
+ curr_slot = prev_slot;
+ curr_node = prev_node;
+ curr_bkt = curr_node->bkt;
+ }
+
+ curr_bkt->sig_current[curr_slot] = sig;
+ curr_bkt->sig_alt[curr_slot] = alt_hash;
+ curr_bkt->key_idx[curr_slot] = new_idx;
+
+ __hash_rw_writer_unlock(h);
+
+ return 0;
}
/*
- * Function called to enqueue back an index in the cache/ring,
- * as slot has not being used and it can be used in the
- * next addition attempt.
+ * Make space for new key, using bfs Cuckoo Search and Multi-Writer safe
+ * Cuckoo
*/
-static inline void
-enqueue_slot_back(const struct rte_hash *h,
- struct lcore_cache *cached_free_slots,
- void *slot_id)
+static inline int
+rte_hash_cuckoo_make_space_mw(const struct rte_hash *h,
+ struct rte_hash_bucket *bkt,
+ struct rte_hash_bucket *sec_bkt,
+ const struct rte_hash_key *key, void *data,
+ hash_sig_t sig, hash_sig_t alt_hash,
+ uint32_t new_idx, int32_t *ret_val)
{
- if (h->hw_trans_mem_support) {
- cached_free_slots->objs[cached_free_slots->len] = slot_id;
- cached_free_slots->len++;
- } else
- rte_ring_sp_enqueue(h->free_slots, slot_id);
+ unsigned int i;
+ struct queue_node queue[RTE_HASH_BFS_QUEUE_MAX_LEN];
+ struct queue_node *tail, *head;
+ struct rte_hash_bucket *curr_bkt, *alt_bkt;
+
+ tail = queue;
+ head = queue + 1;
+ tail->bkt = bkt;
+ tail->prev = NULL;
+ tail->prev_slot = -1;
+
+ /* Cuckoo bfs Search */
+ while (likely(tail != head && head <
+ queue + RTE_HASH_BFS_QUEUE_MAX_LEN -
+ RTE_HASH_BUCKET_ENTRIES)) {
+ curr_bkt = tail->bkt;
+ for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
+ if (curr_bkt->key_idx[i] == EMPTY_SLOT) {
+ int32_t ret = rte_hash_cuckoo_move_insert_mw(h,
+ bkt, sec_bkt, key, data,
+ tail, i, sig, alt_hash,
+ new_idx, ret_val);
+ if (likely(ret != -1))
+ return ret;
+ }
+
+ /* Enqueue new node and keep prev node info */
+ alt_bkt = &(h->buckets[curr_bkt->sig_alt[i]
+ & h->bucket_bitmask]);
+ head->bkt = alt_bkt;
+ head->prev = tail;
+ head->prev_slot = i;
+ head++;
+ }
+ tail++;
+ }
+
+ return -ENOSPC;
}
static inline int32_t
{
hash_sig_t alt_hash;
uint32_t prim_bucket_idx, sec_bucket_idx;
- unsigned i;
struct rte_hash_bucket *prim_bkt, *sec_bkt;
- struct rte_hash_key *new_k, *k, *keys = h->key_store;
+ struct rte_hash_key *new_k, *keys = h->key_store;
void *slot_id = NULL;
uint32_t new_idx;
int ret;
unsigned n_slots;
unsigned lcore_id;
struct lcore_cache *cached_free_slots = NULL;
+ int32_t ret_val;
prim_bucket_idx = sig & h->bucket_bitmask;
prim_bkt = &h->buckets[prim_bucket_idx];
sec_bkt = &h->buckets[sec_bucket_idx];
rte_prefetch0(sec_bkt);
- /* Get a new slot for storing the new key */
- if (h->hw_trans_mem_support) {
+ /* Check if key is already inserted in primary location */
+ __hash_rw_writer_lock(h);
+ ret = search_and_update(h, data, key, prim_bkt, sig, alt_hash);
+ if (ret != -1) {
+ __hash_rw_writer_unlock(h);
+ return ret;
+ }
+
+ /* Check if key is already inserted in secondary location */
+ ret = search_and_update(h, data, key, sec_bkt, alt_hash, sig);
+ if (ret != -1) {
+ __hash_rw_writer_unlock(h);
+ return ret;
+ }
+ __hash_rw_writer_unlock(h);
+
+ /* Did not find a match, so get a new slot for storing the new key */
+ if (h->multi_writer_support) {
lcore_id = rte_lcore_id();
cached_free_slots = &h->local_free_slots[lcore_id];
/* Try to get a free slot from the local cache */
if (cached_free_slots->len == 0) {
/* Need to get another burst of free slots from global ring */
n_slots = rte_ring_mc_dequeue_burst(h->free_slots,
- cached_free_slots->objs, LCORE_CACHE_SIZE);
- if (n_slots == 0)
+ cached_free_slots->objs,
+ LCORE_CACHE_SIZE, NULL);
+ if (n_slots == 0) {
return -ENOSPC;
+ }
cached_free_slots->len += n_slots;
}
cached_free_slots->len--;
slot_id = cached_free_slots->objs[cached_free_slots->len];
} else {
- if (rte_ring_sc_dequeue(h->free_slots, &slot_id) != 0)
+ if (rte_ring_sc_dequeue(h->free_slots, &slot_id) != 0) {
return -ENOSPC;
+ }
}
new_k = RTE_PTR_ADD(keys, (uintptr_t)slot_id * h->key_entry_size);
- rte_prefetch0(new_k);
new_idx = (uint32_t)((uintptr_t) slot_id);
-
- /* Check if key is already inserted in primary location */
- for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
- if (prim_bkt->signatures[i].current == sig &&
- prim_bkt->signatures[i].alt == alt_hash) {
- k = (struct rte_hash_key *) ((char *)keys +
- prim_bkt->key_idx[i] * h->key_entry_size);
- if (h->rte_hash_cmp_eq(key, k->key, h->key_len) == 0) {
- /* Enqueue index of free slot back in the ring. */
- enqueue_slot_back(h, cached_free_slots, slot_id);
- /* Update data */
- k->pdata = data;
- /*
- * Return index where key is stored,
- * substracting the first dummy index
- */
- return (prim_bkt->key_idx[i] - 1);
- }
- }
- }
-
- /* Check if key is already inserted in secondary location */
- for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
- if (sec_bkt->signatures[i].alt == sig &&
- sec_bkt->signatures[i].current == alt_hash) {
- k = (struct rte_hash_key *) ((char *)keys +
- sec_bkt->key_idx[i] * h->key_entry_size);
- if (h->rte_hash_cmp_eq(key, k->key, h->key_len) == 0) {
- /* Enqueue index of free slot back in the ring. */
- enqueue_slot_back(h, cached_free_slots, slot_id);
- /* Update data */
- k->pdata = data;
- /*
- * Return index where key is stored,
- * substracting the first dummy index
- */
- return (sec_bkt->key_idx[i] - 1);
- }
- }
- }
-
/* Copy key */
rte_memcpy(new_k->key, key, h->key_len);
new_k->pdata = data;
- /* Insert new entry is there is room in the primary bucket */
- for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
- /* Check if slot is available */
- if (likely(prim_bkt->signatures[i].sig == NULL_SIGNATURE)) {
- prim_bkt->signatures[i].current = sig;
- prim_bkt->signatures[i].alt = alt_hash;
- prim_bkt->key_idx[i] = new_idx;
- return new_idx - 1;
- }
+
+ /* Find an empty slot and insert */
+ ret = rte_hash_cuckoo_insert_mw(h, prim_bkt, sec_bkt, key, data,
+ sig, alt_hash, new_idx, &ret_val);
+ if (ret == 0)
+ return new_idx - 1;
+ else if (ret == 1) {
+ enqueue_slot_back(h, cached_free_slots, slot_id);
+ return ret_val;
}
- /* Primary bucket is full, so we need to make space for new entry */
- ret = make_space_bucket(h, prim_bkt);
- /*
- * After recursive function.
- * Insert the new entry in the position of the pushed entry
- * if successful or return error and
- * store the new slot back in the ring
- */
- if (ret >= 0) {
- prim_bkt->signatures[ret].current = sig;
- prim_bkt->signatures[ret].alt = alt_hash;
- prim_bkt->key_idx[ret] = new_idx;
- return (new_idx - 1);
+ /* Primary bucket full, need to make space for new entry */
+ ret = rte_hash_cuckoo_make_space_mw(h, prim_bkt, sec_bkt, key, data,
+ sig, alt_hash, new_idx, &ret_val);
+ if (ret == 0)
+ return new_idx - 1;
+ else if (ret == 1) {
+ enqueue_slot_back(h, cached_free_slots, slot_id);
+ return ret_val;
}
- /* Error in addition, store new slot back in the ring and return error */
- enqueue_slot_back(h, cached_free_slots, (void *)((uintptr_t) new_idx));
+ /* Also search secondary bucket to get better occupancy */
+ ret = rte_hash_cuckoo_make_space_mw(h, sec_bkt, prim_bkt, key, data,
+ alt_hash, sig, new_idx, &ret_val);
- return ret;
+ if (ret == 0)
+ return new_idx - 1;
+ else if (ret == 1) {
+ enqueue_slot_back(h, cached_free_slots, slot_id);
+ return ret_val;
+ } else {
+ enqueue_slot_back(h, cached_free_slots, slot_id);
+ return ret;
+ }
}
int32_t
else
return ret;
}
+
+/* Search one bucket to find the match key */
static inline int32_t
-__rte_hash_lookup_with_hash(const struct rte_hash *h, const void *key,
- hash_sig_t sig, void **data)
+search_one_bucket(const struct rte_hash *h, const void *key, hash_sig_t sig,
+ void **data, const struct rte_hash_bucket *bkt)
{
- uint32_t bucket_idx;
- hash_sig_t alt_hash;
- unsigned i;
- struct rte_hash_bucket *bkt;
+ int i;
struct rte_hash_key *k, *keys = h->key_store;
- bucket_idx = sig & h->bucket_bitmask;
- bkt = &h->buckets[bucket_idx];
-
- /* Check if key is in primary location */
for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
- if (bkt->signatures[i].current == sig &&
- bkt->signatures[i].sig != NULL_SIGNATURE) {
+ if (bkt->sig_current[i] == sig &&
+ bkt->key_idx[i] != EMPTY_SLOT) {
k = (struct rte_hash_key *) ((char *)keys +
bkt->key_idx[i] * h->key_entry_size);
- if (h->rte_hash_cmp_eq(key, k->key, h->key_len) == 0) {
+ if (rte_hash_cmp_eq(key, k->key, h) == 0) {
if (data != NULL)
*data = k->pdata;
/*
* Return index where key is stored,
- * substracting the first dummy index
+ * subtracting the first dummy index
*/
- return (bkt->key_idx[i] - 1);
+ return bkt->key_idx[i] - 1;
}
}
}
+ return -1;
+}
+static inline int32_t
+__rte_hash_lookup_with_hash(const struct rte_hash *h, const void *key,
+ hash_sig_t sig, void **data)
+{
+ uint32_t bucket_idx;
+ hash_sig_t alt_hash;
+ struct rte_hash_bucket *bkt;
+ int ret;
+
+ bucket_idx = sig & h->bucket_bitmask;
+ bkt = &h->buckets[bucket_idx];
+
+ __hash_rw_reader_lock(h);
+
+ /* Check if key is in primary location */
+ ret = search_one_bucket(h, key, sig, data, bkt);
+ if (ret != -1) {
+ __hash_rw_reader_unlock(h);
+ return ret;
+ }
/* Calculate secondary hash */
alt_hash = rte_hash_secondary_hash(sig);
bucket_idx = alt_hash & h->bucket_bitmask;
bkt = &h->buckets[bucket_idx];
/* Check if key is in secondary location */
- for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
- if (bkt->signatures[i].current == alt_hash &&
- bkt->signatures[i].alt == sig) {
- k = (struct rte_hash_key *) ((char *)keys +
- bkt->key_idx[i] * h->key_entry_size);
- if (h->rte_hash_cmp_eq(key, k->key, h->key_len) == 0) {
- if (data != NULL)
- *data = k->pdata;
- /*
- * Return index where key is stored,
- * substracting the first dummy index
- */
- return (bkt->key_idx[i] - 1);
- }
- }
+ ret = search_one_bucket(h, key, alt_hash, data, bkt);
+ if (ret != -1) {
+ __hash_rw_reader_unlock(h);
+ return ret;
}
-
+ __hash_rw_reader_unlock(h);
return -ENOENT;
}
unsigned lcore_id, n_slots;
struct lcore_cache *cached_free_slots;
- bkt->signatures[i].sig = NULL_SIGNATURE;
- if (h->hw_trans_mem_support) {
+ bkt->sig_current[i] = NULL_SIGNATURE;
+ bkt->sig_alt[i] = NULL_SIGNATURE;
+ if (h->multi_writer_support) {
lcore_id = rte_lcore_id();
cached_free_slots = &h->local_free_slots[lcore_id];
/* Cache full, need to free it. */
/* Need to enqueue the free slots in global ring. */
n_slots = rte_ring_mp_enqueue_burst(h->free_slots,
cached_free_slots->objs,
- LCORE_CACHE_SIZE);
+ LCORE_CACHE_SIZE, NULL);
cached_free_slots->len -= n_slots;
}
/* Put index of new free slot in cache. */
}
}
+/* Search one bucket and remove the matched key */
static inline int32_t
-__rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
- hash_sig_t sig)
+search_and_remove(const struct rte_hash *h, const void *key,
+ struct rte_hash_bucket *bkt, hash_sig_t sig)
{
- uint32_t bucket_idx;
- hash_sig_t alt_hash;
- unsigned i;
- struct rte_hash_bucket *bkt;
struct rte_hash_key *k, *keys = h->key_store;
-
- bucket_idx = sig & h->bucket_bitmask;
- bkt = &h->buckets[bucket_idx];
+ unsigned int i;
+ int32_t ret;
/* Check if key is in primary location */
for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
- if (bkt->signatures[i].current == sig &&
- bkt->signatures[i].sig != NULL_SIGNATURE) {
+ if (bkt->sig_current[i] == sig &&
+ bkt->key_idx[i] != EMPTY_SLOT) {
k = (struct rte_hash_key *) ((char *)keys +
bkt->key_idx[i] * h->key_entry_size);
- if (h->rte_hash_cmp_eq(key, k->key, h->key_len) == 0) {
+ if (rte_hash_cmp_eq(key, k->key, h) == 0) {
remove_entry(h, bkt, i);
/*
* Return index where key is stored,
- * substracting the first dummy index
+ * subtracting the first dummy index
*/
- return (bkt->key_idx[i] - 1);
+ ret = bkt->key_idx[i] - 1;
+ bkt->key_idx[i] = EMPTY_SLOT;
+ return ret;
}
}
}
+ return -1;
+}
+
+static inline int32_t
+__rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
+ hash_sig_t sig)
+{
+ uint32_t bucket_idx;
+ hash_sig_t alt_hash;
+ struct rte_hash_bucket *bkt;
+ int32_t ret;
+
+ bucket_idx = sig & h->bucket_bitmask;
+ bkt = &h->buckets[bucket_idx];
+
+ __hash_rw_writer_lock(h);
+ /* look for key in primary bucket */
+ ret = search_and_remove(h, key, bkt, sig);
+ if (ret != -1) {
+ __hash_rw_writer_unlock(h);
+ return ret;
+ }
/* Calculate secondary hash */
alt_hash = rte_hash_secondary_hash(sig);
bucket_idx = alt_hash & h->bucket_bitmask;
bkt = &h->buckets[bucket_idx];
- /* Check if key is in secondary location */
- for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
- if (bkt->signatures[i].current == alt_hash &&
- bkt->signatures[i].sig != NULL_SIGNATURE) {
- k = (struct rte_hash_key *) ((char *)keys +
- bkt->key_idx[i] * h->key_entry_size);
- if (h->rte_hash_cmp_eq(key, k->key, h->key_len) == 0) {
- remove_entry(h, bkt, i);
-
- /*
- * Return index where key is stored,
- * substracting the first dummy index
- */
- return (bkt->key_idx[i] - 1);
- }
- }
+ /* look for key in secondary bucket */
+ ret = search_and_remove(h, key, bkt, alt_hash);
+ if (ret != -1) {
+ __hash_rw_writer_unlock(h);
+ return ret;
}
+ __hash_rw_writer_unlock(h);
return -ENOENT;
}
return __rte_hash_del_key_with_hash(h, key, rte_hash_hash(h, key));
}
-/* Lookup bulk stage 0: Prefetch input key */
-static inline void
-lookup_stage0(unsigned *idx, uint64_t *lookup_mask,
- const void * const *keys)
+int
+rte_hash_get_key_with_position(const struct rte_hash *h, const int32_t position,
+ void **key)
{
- *idx = __builtin_ctzl(*lookup_mask);
- if (*lookup_mask == 0)
- *idx = 0;
+ RETURN_IF_TRUE(((h == NULL) || (key == NULL)), -EINVAL);
+
+ struct rte_hash_key *k, *keys = h->key_store;
+ k = (struct rte_hash_key *) ((char *) keys + (position + 1) *
+ h->key_entry_size);
+ *key = k->key;
- rte_prefetch0(keys[*idx]);
- *lookup_mask &= ~(1llu << *idx);
+ if (position !=
+ __rte_hash_lookup_with_hash(h, *key, rte_hash_hash(h, *key),
+ NULL)) {
+ return -ENOENT;
+ }
+
+ return 0;
}
-/*
- * Lookup bulk stage 1: Calculate primary/secondary hashes
- * and prefetch primary/secondary buckets
- */
static inline void
-lookup_stage1(unsigned idx, hash_sig_t *prim_hash, hash_sig_t *sec_hash,
- const struct rte_hash_bucket **primary_bkt,
- const struct rte_hash_bucket **secondary_bkt,
- hash_sig_t *hash_vals, const void * const *keys,
- const struct rte_hash *h)
+compare_signatures(uint32_t *prim_hash_matches, uint32_t *sec_hash_matches,
+ const struct rte_hash_bucket *prim_bkt,
+ const struct rte_hash_bucket *sec_bkt,
+ hash_sig_t prim_hash, hash_sig_t sec_hash,
+ enum rte_hash_sig_compare_function sig_cmp_fn)
{
- *prim_hash = rte_hash_hash(h, keys[idx]);
- hash_vals[idx] = *prim_hash;
- *sec_hash = rte_hash_secondary_hash(*prim_hash);
-
- *primary_bkt = &h->buckets[*prim_hash & h->bucket_bitmask];
- *secondary_bkt = &h->buckets[*sec_hash & h->bucket_bitmask];
+ unsigned int i;
+
+ switch (sig_cmp_fn) {
+#ifdef RTE_MACHINE_CPUFLAG_AVX2
+ case RTE_HASH_COMPARE_AVX2:
+ *prim_hash_matches = _mm256_movemask_ps((__m256)_mm256_cmpeq_epi32(
+ _mm256_load_si256(
+ (__m256i const *)prim_bkt->sig_current),
+ _mm256_set1_epi32(prim_hash)));
+ *sec_hash_matches = _mm256_movemask_ps((__m256)_mm256_cmpeq_epi32(
+ _mm256_load_si256(
+ (__m256i const *)sec_bkt->sig_current),
+ _mm256_set1_epi32(sec_hash)));
+ break;
+#endif
+#ifdef RTE_MACHINE_CPUFLAG_SSE2
+ case RTE_HASH_COMPARE_SSE:
+ /* Compare the first 4 signatures in the bucket */
+ *prim_hash_matches = _mm_movemask_ps((__m128)_mm_cmpeq_epi16(
+ _mm_load_si128(
+ (__m128i const *)prim_bkt->sig_current),
+ _mm_set1_epi32(prim_hash)));
+ *prim_hash_matches |= (_mm_movemask_ps((__m128)_mm_cmpeq_epi16(
+ _mm_load_si128(
+ (__m128i const *)&prim_bkt->sig_current[4]),
+ _mm_set1_epi32(prim_hash)))) << 4;
+ /* Compare the first 4 signatures in the bucket */
+ *sec_hash_matches = _mm_movemask_ps((__m128)_mm_cmpeq_epi16(
+ _mm_load_si128(
+ (__m128i const *)sec_bkt->sig_current),
+ _mm_set1_epi32(sec_hash)));
+ *sec_hash_matches |= (_mm_movemask_ps((__m128)_mm_cmpeq_epi16(
+ _mm_load_si128(
+ (__m128i const *)&sec_bkt->sig_current[4]),
+ _mm_set1_epi32(sec_hash)))) << 4;
+ break;
+#endif
+ default:
+ for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
+ *prim_hash_matches |=
+ ((prim_hash == prim_bkt->sig_current[i]) << i);
+ *sec_hash_matches |=
+ ((sec_hash == sec_bkt->sig_current[i]) << i);
+ }
+ }
- rte_prefetch0(*primary_bkt);
- rte_prefetch0(*secondary_bkt);
}
-/*
- * Lookup bulk stage 2: Search for match hashes in primary/secondary locations
- * and prefetch first key slot
- */
+#define PREFETCH_OFFSET 4
static inline void
-lookup_stage2(unsigned idx, hash_sig_t prim_hash, hash_sig_t sec_hash,
- const struct rte_hash_bucket *prim_bkt,
- const struct rte_hash_bucket *sec_bkt,
- const struct rte_hash_key **key_slot, int32_t *positions,
- uint64_t *extra_hits_mask, const void *keys,
- const struct rte_hash *h)
+__rte_hash_lookup_bulk(const struct rte_hash *h, const void **keys,
+ int32_t num_keys, int32_t *positions,
+ uint64_t *hit_mask, void *data[])
{
- unsigned prim_hash_matches, sec_hash_matches, key_idx, i;
- unsigned total_hash_matches;
+ uint64_t hits = 0;
+ int32_t i;
+ uint32_t prim_hash[RTE_HASH_LOOKUP_BULK_MAX];
+ uint32_t sec_hash[RTE_HASH_LOOKUP_BULK_MAX];
+ const struct rte_hash_bucket *primary_bkt[RTE_HASH_LOOKUP_BULK_MAX];
+ const struct rte_hash_bucket *secondary_bkt[RTE_HASH_LOOKUP_BULK_MAX];
+ uint32_t prim_hitmask[RTE_HASH_LOOKUP_BULK_MAX] = {0};
+ uint32_t sec_hitmask[RTE_HASH_LOOKUP_BULK_MAX] = {0};
+
+ /* Prefetch first keys */
+ for (i = 0; i < PREFETCH_OFFSET && i < num_keys; i++)
+ rte_prefetch0(keys[i]);
- prim_hash_matches = 1 << RTE_HASH_BUCKET_ENTRIES;
- sec_hash_matches = 1 << RTE_HASH_BUCKET_ENTRIES;
- for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
- prim_hash_matches |= ((prim_hash == prim_bkt->signatures[i].current) << i);
- sec_hash_matches |= ((sec_hash == sec_bkt->signatures[i].current) << i);
+ /*
+ * Prefetch rest of the keys, calculate primary and
+ * secondary bucket and prefetch them
+ */
+ for (i = 0; i < (num_keys - PREFETCH_OFFSET); i++) {
+ rte_prefetch0(keys[i + PREFETCH_OFFSET]);
+
+ prim_hash[i] = rte_hash_hash(h, keys[i]);
+ sec_hash[i] = rte_hash_secondary_hash(prim_hash[i]);
+
+ primary_bkt[i] = &h->buckets[prim_hash[i] & h->bucket_bitmask];
+ secondary_bkt[i] = &h->buckets[sec_hash[i] & h->bucket_bitmask];
+
+ rte_prefetch0(primary_bkt[i]);
+ rte_prefetch0(secondary_bkt[i]);
}
- key_idx = prim_bkt->key_idx[__builtin_ctzl(prim_hash_matches)];
- if (key_idx == 0)
- key_idx = sec_bkt->key_idx[__builtin_ctzl(sec_hash_matches)];
+ /* Calculate and prefetch rest of the buckets */
+ for (; i < num_keys; i++) {
+ prim_hash[i] = rte_hash_hash(h, keys[i]);
+ sec_hash[i] = rte_hash_secondary_hash(prim_hash[i]);
- total_hash_matches = (prim_hash_matches |
- (sec_hash_matches << (RTE_HASH_BUCKET_ENTRIES + 1)));
- *key_slot = (const struct rte_hash_key *) ((const char *)keys +
- key_idx * h->key_entry_size);
+ primary_bkt[i] = &h->buckets[prim_hash[i] & h->bucket_bitmask];
+ secondary_bkt[i] = &h->buckets[sec_hash[i] & h->bucket_bitmask];
- rte_prefetch0(*key_slot);
- /*
- * Return index where key is stored,
- * substracting the first dummy index
- */
- positions[idx] = (key_idx - 1);
+ rte_prefetch0(primary_bkt[i]);
+ rte_prefetch0(secondary_bkt[i]);
+ }
- *extra_hits_mask |= (uint64_t)(__builtin_popcount(total_hash_matches) > 3) << idx;
+ __hash_rw_reader_lock(h);
+ /* Compare signatures and prefetch key slot of first hit */
+ for (i = 0; i < num_keys; i++) {
+ compare_signatures(&prim_hitmask[i], &sec_hitmask[i],
+ primary_bkt[i], secondary_bkt[i],
+ prim_hash[i], sec_hash[i], h->sig_cmp_fn);
+
+ if (prim_hitmask[i]) {
+ uint32_t first_hit = __builtin_ctzl(prim_hitmask[i]);
+ uint32_t key_idx = primary_bkt[i]->key_idx[first_hit];
+ const struct rte_hash_key *key_slot =
+ (const struct rte_hash_key *)(
+ (const char *)h->key_store +
+ key_idx * h->key_entry_size);
+ rte_prefetch0(key_slot);
+ continue;
+ }
-}
+ if (sec_hitmask[i]) {
+ uint32_t first_hit = __builtin_ctzl(sec_hitmask[i]);
+ uint32_t key_idx = secondary_bkt[i]->key_idx[first_hit];
+ const struct rte_hash_key *key_slot =
+ (const struct rte_hash_key *)(
+ (const char *)h->key_store +
+ key_idx * h->key_entry_size);
+ rte_prefetch0(key_slot);
+ }
+ }
+ /* Compare keys, first hits in primary first */
+ for (i = 0; i < num_keys; i++) {
+ positions[i] = -ENOENT;
+ while (prim_hitmask[i]) {
+ uint32_t hit_index = __builtin_ctzl(prim_hitmask[i]);
+
+ uint32_t key_idx = primary_bkt[i]->key_idx[hit_index];
+ const struct rte_hash_key *key_slot =
+ (const struct rte_hash_key *)(
+ (const char *)h->key_store +
+ key_idx * h->key_entry_size);
+ /*
+ * If key index is 0, do not compare key,
+ * as it is checking the dummy slot
+ */
+ if (!!key_idx & !rte_hash_cmp_eq(key_slot->key, keys[i], h)) {
+ if (data != NULL)
+ data[i] = key_slot->pdata;
-/* Lookup bulk stage 3: Check if key matches, update hit mask and return data */
-static inline void
-lookup_stage3(unsigned idx, const struct rte_hash_key *key_slot, const void * const *keys,
- const int32_t *positions, void *data[], uint64_t *hits,
- const struct rte_hash *h)
-{
- unsigned hit;
- unsigned key_idx;
+ hits |= 1ULL << i;
+ positions[i] = key_idx - 1;
+ goto next_key;
+ }
+ prim_hitmask[i] &= ~(1 << (hit_index));
+ }
- hit = !h->rte_hash_cmp_eq(key_slot->key, keys[idx], h->key_len);
- if (data != NULL)
- data[idx] = key_slot->pdata;
+ while (sec_hitmask[i]) {
+ uint32_t hit_index = __builtin_ctzl(sec_hitmask[i]);
- key_idx = positions[idx] + 1;
- /*
- * If key index is 0, force hit to be 0, in case key to be looked up
- * is all zero (as in the dummy slot), which would result in a wrong hit
- */
- *hits |= (uint64_t)(hit && !!key_idx) << idx;
-}
+ uint32_t key_idx = secondary_bkt[i]->key_idx[hit_index];
+ const struct rte_hash_key *key_slot =
+ (const struct rte_hash_key *)(
+ (const char *)h->key_store +
+ key_idx * h->key_entry_size);
+ /*
+ * If key index is 0, do not compare key,
+ * as it is checking the dummy slot
+ */
-static inline void
-__rte_hash_lookup_bulk(const struct rte_hash *h, const void **keys,
- uint32_t num_keys, int32_t *positions,
- uint64_t *hit_mask, void *data[])
-{
- uint64_t hits = 0;
- uint64_t extra_hits_mask = 0;
- uint64_t lookup_mask, miss_mask;
- unsigned idx;
- const void *key_store = h->key_store;
- int ret;
- hash_sig_t hash_vals[RTE_HASH_LOOKUP_BULK_MAX];
-
- unsigned idx00, idx01, idx10, idx11, idx20, idx21, idx30, idx31;
- const struct rte_hash_bucket *primary_bkt10, *primary_bkt11;
- const struct rte_hash_bucket *secondary_bkt10, *secondary_bkt11;
- const struct rte_hash_bucket *primary_bkt20, *primary_bkt21;
- const struct rte_hash_bucket *secondary_bkt20, *secondary_bkt21;
- const struct rte_hash_key *k_slot20, *k_slot21, *k_slot30, *k_slot31;
- hash_sig_t primary_hash10, primary_hash11;
- hash_sig_t secondary_hash10, secondary_hash11;
- hash_sig_t primary_hash20, primary_hash21;
- hash_sig_t secondary_hash20, secondary_hash21;
-
- lookup_mask = (uint64_t) -1 >> (64 - num_keys);
- miss_mask = lookup_mask;
-
- lookup_stage0(&idx00, &lookup_mask, keys);
- lookup_stage0(&idx01, &lookup_mask, keys);
-
- idx10 = idx00, idx11 = idx01;
-
- lookup_stage0(&idx00, &lookup_mask, keys);
- lookup_stage0(&idx01, &lookup_mask, keys);
- lookup_stage1(idx10, &primary_hash10, &secondary_hash10,
- &primary_bkt10, &secondary_bkt10, hash_vals, keys, h);
- lookup_stage1(idx11, &primary_hash11, &secondary_hash11,
- &primary_bkt11, &secondary_bkt11, hash_vals, keys, h);
-
- primary_bkt20 = primary_bkt10;
- primary_bkt21 = primary_bkt11;
- secondary_bkt20 = secondary_bkt10;
- secondary_bkt21 = secondary_bkt11;
- primary_hash20 = primary_hash10;
- primary_hash21 = primary_hash11;
- secondary_hash20 = secondary_hash10;
- secondary_hash21 = secondary_hash11;
- idx20 = idx10, idx21 = idx11;
- idx10 = idx00, idx11 = idx01;
-
- lookup_stage0(&idx00, &lookup_mask, keys);
- lookup_stage0(&idx01, &lookup_mask, keys);
- lookup_stage1(idx10, &primary_hash10, &secondary_hash10,
- &primary_bkt10, &secondary_bkt10, hash_vals, keys, h);
- lookup_stage1(idx11, &primary_hash11, &secondary_hash11,
- &primary_bkt11, &secondary_bkt11, hash_vals, keys, h);
- lookup_stage2(idx20, primary_hash20, secondary_hash20, primary_bkt20,
- secondary_bkt20, &k_slot20, positions, &extra_hits_mask,
- key_store, h);
- lookup_stage2(idx21, primary_hash21, secondary_hash21, primary_bkt21,
- secondary_bkt21, &k_slot21, positions, &extra_hits_mask,
- key_store, h);
-
- while (lookup_mask) {
- k_slot30 = k_slot20, k_slot31 = k_slot21;
- idx30 = idx20, idx31 = idx21;
- primary_bkt20 = primary_bkt10;
- primary_bkt21 = primary_bkt11;
- secondary_bkt20 = secondary_bkt10;
- secondary_bkt21 = secondary_bkt11;
- primary_hash20 = primary_hash10;
- primary_hash21 = primary_hash11;
- secondary_hash20 = secondary_hash10;
- secondary_hash21 = secondary_hash11;
- idx20 = idx10, idx21 = idx11;
- idx10 = idx00, idx11 = idx01;
-
- lookup_stage0(&idx00, &lookup_mask, keys);
- lookup_stage0(&idx01, &lookup_mask, keys);
- lookup_stage1(idx10, &primary_hash10, &secondary_hash10,
- &primary_bkt10, &secondary_bkt10, hash_vals, keys, h);
- lookup_stage1(idx11, &primary_hash11, &secondary_hash11,
- &primary_bkt11, &secondary_bkt11, hash_vals, keys, h);
- lookup_stage2(idx20, primary_hash20, secondary_hash20,
- primary_bkt20, secondary_bkt20, &k_slot20, positions,
- &extra_hits_mask, key_store, h);
- lookup_stage2(idx21, primary_hash21, secondary_hash21,
- primary_bkt21, secondary_bkt21, &k_slot21, positions,
- &extra_hits_mask, key_store, h);
- lookup_stage3(idx30, k_slot30, keys, positions, data, &hits, h);
- lookup_stage3(idx31, k_slot31, keys, positions, data, &hits, h);
- }
+ if (!!key_idx & !rte_hash_cmp_eq(key_slot->key, keys[i], h)) {
+ if (data != NULL)
+ data[i] = key_slot->pdata;
- k_slot30 = k_slot20, k_slot31 = k_slot21;
- idx30 = idx20, idx31 = idx21;
- primary_bkt20 = primary_bkt10;
- primary_bkt21 = primary_bkt11;
- secondary_bkt20 = secondary_bkt10;
- secondary_bkt21 = secondary_bkt11;
- primary_hash20 = primary_hash10;
- primary_hash21 = primary_hash11;
- secondary_hash20 = secondary_hash10;
- secondary_hash21 = secondary_hash11;
- idx20 = idx10, idx21 = idx11;
- idx10 = idx00, idx11 = idx01;
-
- lookup_stage1(idx10, &primary_hash10, &secondary_hash10,
- &primary_bkt10, &secondary_bkt10, hash_vals, keys, h);
- lookup_stage1(idx11, &primary_hash11, &secondary_hash11,
- &primary_bkt11, &secondary_bkt11, hash_vals, keys, h);
- lookup_stage2(idx20, primary_hash20, secondary_hash20, primary_bkt20,
- secondary_bkt20, &k_slot20, positions, &extra_hits_mask,
- key_store, h);
- lookup_stage2(idx21, primary_hash21, secondary_hash21, primary_bkt21,
- secondary_bkt21, &k_slot21, positions, &extra_hits_mask,
- key_store, h);
- lookup_stage3(idx30, k_slot30, keys, positions, data, &hits, h);
- lookup_stage3(idx31, k_slot31, keys, positions, data, &hits, h);
-
- k_slot30 = k_slot20, k_slot31 = k_slot21;
- idx30 = idx20, idx31 = idx21;
- primary_bkt20 = primary_bkt10;
- primary_bkt21 = primary_bkt11;
- secondary_bkt20 = secondary_bkt10;
- secondary_bkt21 = secondary_bkt11;
- primary_hash20 = primary_hash10;
- primary_hash21 = primary_hash11;
- secondary_hash20 = secondary_hash10;
- secondary_hash21 = secondary_hash11;
- idx20 = idx10, idx21 = idx11;
-
- lookup_stage2(idx20, primary_hash20, secondary_hash20, primary_bkt20,
- secondary_bkt20, &k_slot20, positions, &extra_hits_mask,
- key_store, h);
- lookup_stage2(idx21, primary_hash21, secondary_hash21, primary_bkt21,
- secondary_bkt21, &k_slot21, positions, &extra_hits_mask,
- key_store, h);
- lookup_stage3(idx30, k_slot30, keys, positions, data, &hits, h);
- lookup_stage3(idx31, k_slot31, keys, positions, data, &hits, h);
-
- k_slot30 = k_slot20, k_slot31 = k_slot21;
- idx30 = idx20, idx31 = idx21;
-
- lookup_stage3(idx30, k_slot30, keys, positions, data, &hits, h);
- lookup_stage3(idx31, k_slot31, keys, positions, data, &hits, h);
-
- /* ignore any items we have already found */
- extra_hits_mask &= ~hits;
-
- if (unlikely(extra_hits_mask)) {
- /* run a single search for each remaining item */
- do {
- idx = __builtin_ctzl(extra_hits_mask);
- if (data != NULL) {
- ret = rte_hash_lookup_with_hash_data(h,
- keys[idx], hash_vals[idx], &data[idx]);
- if (ret >= 0)
- hits |= 1ULL << idx;
- } else {
- positions[idx] = rte_hash_lookup_with_hash(h,
- keys[idx], hash_vals[idx]);
- if (positions[idx] >= 0)
- hits |= 1llu << idx;
+ hits |= 1ULL << i;
+ positions[i] = key_idx - 1;
+ goto next_key;
}
- extra_hits_mask &= ~(1llu << idx);
- } while (extra_hits_mask);
- }
+ sec_hitmask[i] &= ~(1 << (hit_index));
+ }
- miss_mask &= ~hits;
- if (unlikely(miss_mask)) {
- do {
- idx = __builtin_ctzl(miss_mask);
- positions[idx] = -ENOENT;
- miss_mask &= ~(1llu << idx);
- } while (miss_mask);
+next_key:
+ continue;
}
+ __hash_rw_reader_unlock(h);
+
if (hit_mask != NULL)
*hit_mask = hits;
}
idx = *next % RTE_HASH_BUCKET_ENTRIES;
/* If current position is empty, go to the next one */
- while (h->buckets[bucket_idx].signatures[idx].sig == NULL_SIGNATURE) {
+ while (h->buckets[bucket_idx].key_idx[idx] == EMPTY_SLOT) {
(*next)++;
/* End of table */
if (*next == total_entries)
bucket_idx = *next / RTE_HASH_BUCKET_ENTRIES;
idx = *next % RTE_HASH_BUCKET_ENTRIES;
}
-
+ __hash_rw_reader_lock(h);
/* Get position of entry in key table */
position = h->buckets[bucket_idx].key_idx[idx];
next_key = (struct rte_hash_key *) ((char *)h->key_store +
*key = next_key->key;
*data = next_key->pdata;
+ __hash_rw_reader_unlock(h);
+
/* Increment iterator */
(*next)++;
- return (position - 1);
+ return position - 1;
}
git.droids-corp.org / dpdk.git / blobdiff