h->free_slots = r;
h->hw_trans_mem_support = hw_trans_mem_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;
+
/* Turn on multi-writer only with explicit flat from user and TM
* support.
*/
static inline int
make_space_bucket(const struct rte_hash *h, struct rte_hash_bucket *bkt)
{
+ static unsigned int nr_pushes;
unsigned i, j;
int ret;
uint32_t next_bucket_idx;
break;
/* All entries have been pushed, so entry cannot be added */
- if (i == RTE_HASH_BUCKET_ENTRIES)
+ if (i == RTE_HASH_BUCKET_ENTRIES || nr_pushes > RTE_HASH_MAX_PUSHES)
return -ENOSPC;
/* Set flag to indicate that this entry is going to be pushed */
bkt->flag[i] = 1;
+
+ nr_pushes++;
/* Need room in alternative bucket to insert the pushed entry */
ret = make_space_bucket(h, next_bkt[i]);
/*
* or return error
*/
bkt->flag[i] = 0;
+ nr_pushes = 0;
if (ret >= 0) {
next_bkt[i]->sig_alt[ret] = bkt->sig_current[i];
next_bkt[i]->sig_current[ret] = bkt->sig_alt[i];
/* 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. */
return 0;
}
-/* Lookup bulk stage 0: Prefetch input key */
static inline void
-lookup_stage0(unsigned *idx, uint64_t *lookup_mask,
- const void * const *keys)
+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)
{
- *idx = __builtin_ctzl(*lookup_mask);
- if (*lookup_mask == 0)
- *idx = 0;
+ 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(keys[*idx]);
- *lookup_mask &= ~(1llu << *idx);
}
-/*
- * Lookup bulk stage 1: Calculate primary/secondary hashes
- * and prefetch primary/secondary buckets
- */
+#define PREFETCH_OFFSET 4
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)
+__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[])
{
- *prim_hash = rte_hash_hash(h, keys[idx]);
- hash_vals[idx] = *prim_hash;
- *sec_hash = rte_hash_secondary_hash(*prim_hash);
+ 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]);
- *primary_bkt = &h->buckets[*prim_hash & h->bucket_bitmask];
- *secondary_bkt = &h->buckets[*sec_hash & h->bucket_bitmask];
+ /*
+ * 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]);
- rte_prefetch0(*primary_bkt);
- rte_prefetch0(*secondary_bkt);
-}
+ prim_hash[i] = rte_hash_hash(h, keys[i]);
+ sec_hash[i] = rte_hash_secondary_hash(prim_hash[i]);
-/*
- * Lookup bulk stage 2: Search for match hashes in primary/secondary locations
- * and prefetch first key slot
- */
-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)
-{
- unsigned prim_hash_matches, sec_hash_matches, key_idx, i;
- unsigned total_hash_matches;
+ primary_bkt[i] = &h->buckets[prim_hash[i] & h->bucket_bitmask];
+ secondary_bkt[i] = &h->buckets[sec_hash[i] & h->bucket_bitmask];
- 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->sig_current[i]) << i);
- sec_hash_matches |= ((sec_hash == sec_bkt->sig_current[i]) << i);
+ 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;
+ /* 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 = !rte_hash_cmp_eq(key_slot->key, keys[idx], h);
- 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;
}
if (hit_mask != NULL)
git.droids-corp.org / dpdk.git / blobdiff