X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_hash%2Frte_cuckoo_hash.c;h=e3cc3a7ce23e0ba0ed058eb0b98964d8ef849c81;hb=99c12dcca65d;hp=5cf4af69883ae4d8ba7248b18f90dec378a51c26;hpb=9cd270a67856eb8d4ae43e5c84ff5390c6cb4eed;p=dpdk.git

diff --git a/lib/librte_hash/rte_cuckoo_hash.c b/lib/librte_hash/rte_cuckoo_hash.c
index 5cf4af6988..e3cc3a7ce2 100644
--- a/lib/librte_hash/rte_cuckoo_hash.c
+++ b/lib/librte_hash/rte_cuckoo_hash.c
@@ -1,7 +1,7 @@
 /*-
  *   BSD LICENSE
  *
- *   Copyright(c) 2010-2015 Intel Corporation. All rights reserved.
+ *   Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
  *   All rights reserved.
  *
  *   Redistribution and use in source and binary forms, with or without
@@ -59,8 +59,10 @@
 #include <rte_compat.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"
+#include "rte_cuckoo_hash.h"
+
+#if defined(RTE_ARCH_X86)
+#include "rte_cuckoo_hash_x86.h"
 #endif
 
 TAILQ_HEAD(rte_hash_list, rte_tailq_entry);
@@ -70,84 +72,6 @@ static struct rte_tailq_elem rte_hash_tailq = {
 };
 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 */
-#ifdef RTE_MACHINE_CPUFLAG_SSE4_2
-#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
-
-typedef int (*rte_hash_cmp_eq_t)(const void *key1, const void *key2, size_t key_len);
-
-/** 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*/
-} __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)
 {
@@ -172,6 +96,20 @@ rte_hash_find_existing(const char *name)
 	return h;
 }
 
+void rte_hash_set_cmp_func(struct rte_hash *h, rte_hash_cmp_eq_t func)
+{
+	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 *
 rte_hash_create(const struct rte_hash_parameters *params)
 {
@@ -180,9 +118,11 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	struct rte_hash_list *hash_list;
 	struct rte_ring *r = NULL;
 	char hash_name[RTE_HASH_NAMESIZE];
-	void *ptr, *k = NULL;
+	void *k = NULL;
 	void *buckets = NULL;
 	char ring_name[RTE_RING_NAMESIZE];
+	unsigned num_key_slots;
+	unsigned hw_trans_mem_support = 0;
 	unsigned i;
 
 	hash_list = RTE_TAILQ_CAST(rte_hash_tailq.head, rte_hash_list);
@@ -202,17 +142,52 @@ rte_hash_create(const struct rte_hash_parameters *params)
 		return NULL;
 	}
 
+	/* Check extra flags field to check extra options. */
+	if (params->extra_flag & RTE_HASH_EXTRA_FLAGS_TRANS_MEM_SUPPORT)
+		hw_trans_mem_support = 1;
+
+	/* 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;
+
+	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;
+	}
+
 	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),
@@ -220,7 +195,7 @@ rte_hash_create(const struct rte_hash_parameters *params)
 
 	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)
@@ -232,73 +207,63 @@ rte_hash_create(const struct rte_hash_parameters *params)
 
 	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 */
-	const uint64_t key_tbl_size = key_entry_size * (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,
 			RTE_CACHE_LINE_SIZE, params->socket_id);
 
 	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)
+#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_lookup(ring_name);
-	if (r != NULL) {
-		/* clear the free ring */
-		while (rte_ring_dequeue(r, &ptr) == 0)
-			rte_pause();
-	} else
-		r = rte_ring_create(ring_name, rte_align32pow2(params->entries + 1),
-				params->socket_id, 0);
-	if (r == NULL) {
-		RTE_LOG(ERR, HASH, "memory allocation failed\n");
-		goto err;
+	if (hw_trans_mem_support) {
+		h->local_free_slots = rte_zmalloc_socket(NULL,
+				sizeof(struct lcore_cache) * RTE_MAX_LCORE,
+				RTE_CACHE_LINE_SIZE, params->socket_id);
 	}
 
 	/* Setup hash context */
@@ -313,21 +278,39 @@ rte_hash_create(const struct rte_hash_parameters *params)
 	h->buckets = buckets;
 	h->hash_func = (params->hash_func == NULL) ?
 		DEFAULT_HASH_FUNC : params->hash_func;
-
 	h->key_store = k;
 	h->free_slots = r;
+	h->hw_trans_mem_support = hw_trans_mem_support;
+
+	/* Turn on multi-writer only with explicit flat from user and TM
+	 * support.
+	 */
+	if (params->extra_flag & RTE_HASH_EXTRA_FLAGS_MULTI_WRITER_ADD) {
+		if (h->hw_trans_mem_support) {
+			h->add_key = ADD_KEY_MULTIWRITER_TM;
+		} else {
+			h->add_key = ADD_KEY_MULTIWRITER;
+			h->multiwriter_lock = rte_malloc(NULL,
+							sizeof(rte_spinlock_t),
+							LCORE_CACHE_SIZE);
+			rte_spinlock_init(h->multiwriter_lock);
+		}
+	} else
+		h->add_key = ADD_KEY_SINGLEWRITER;
 
-	/* populate the free slots ring. Entry zero is reserved for key misses */
+	/* Populate free slots ring. Entry zero is reserved for key misses. */
 	for (i = 1; i < params->entries + 1; 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);
@@ -363,6 +346,12 @@ rte_hash_free(struct rte_hash *h)
 
 	rte_rwlock_write_unlock(RTE_EAL_TAILQ_RWLOCK);
 
+	if (h->hw_trans_mem_support)
+		rte_free(h->local_free_slots);
+
+	if (h->add_key == ADD_KEY_MULTIWRITER)
+		rte_free(h->multiwriter_lock);
+	rte_ring_free(h->free_slots);
 	rte_free(h->key_store);
 	rte_free(h->buckets);
 	rte_free(h);
@@ -385,7 +374,7 @@ rte_hash_secondary_hash(const hash_sig_t primary_hash)
 
 	uint32_t tag = primary_hash >> all_bits_shift;
 
-	return (primary_hash ^ ((tag + 1) * alt_bits_xor));
+	return primary_hash ^ ((tag + 1) * alt_bits_xor);
 }
 
 void
@@ -407,6 +396,12 @@ rte_hash_reset(struct rte_hash *h)
 	/* Repopulate the free slots ring. Entry zero is reserved for key misses */
 	for (i = 1; i < h->entries + 1; i++)
 		rte_ring_sp_enqueue(h->free_slots, (void *)((uintptr_t) i));
+
+	if (h->hw_trans_mem_support) {
+		/* Reset local caches per lcore */
+		for (i = 0; i < RTE_MAX_LCORE; i++)
+			h->local_free_slots[i].len = 0;
+	}
 }
 
 /* Search for an entry that can be pushed to its alternative location */
@@ -473,6 +468,23 @@ 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)
+{
+	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);
+}
+
 static inline int32_t
 __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 						hash_sig_t sig, void *data)
@@ -482,9 +494,15 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 	unsigned i;
 	struct rte_hash_bucket *prim_bkt, *sec_bkt;
 	struct rte_hash_key *new_k, *k, *keys = h->key_store;
-	void *slot_id;
+	void *slot_id = NULL;
 	uint32_t new_idx;
 	int ret;
+	unsigned n_slots;
+	unsigned lcore_id;
+	struct lcore_cache *cached_free_slots = NULL;
+
+	if (h->add_key == ADD_KEY_MULTIWRITER)
+		rte_spinlock_lock(h->multiwriter_lock);
 
 	prim_bucket_idx = sig & h->bucket_bitmask;
 	prim_bkt = &h->buckets[prim_bucket_idx];
@@ -496,8 +514,28 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 	rte_prefetch0(sec_bkt);
 
 	/* Get a new slot for storing the new key */
-	if (rte_ring_sc_dequeue(h->free_slots, &slot_id) != 0)
-		return -ENOSPC;
+	if (h->hw_trans_mem_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)
+				return -ENOSPC;
+
+			cached_free_slots->len += n_slots;
+		}
+
+		/* Get a free slot from the local cache */
+		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)
+			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);
@@ -505,18 +543,19 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 	/* 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)  {
+				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) {
-				rte_ring_sp_enqueue(h->free_slots, &slot_id);
+			if (rte_hash_cmp_eq(key, k->key, h) == 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);
+				return prim_bkt->key_idx[i] - 1;
 			}
 		}
 	}
@@ -524,18 +563,19 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *key,
 	/* 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)  {
+				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) {
-				rte_ring_sp_enqueue(h->free_slots, &slot_id);
+			if (rte_hash_cmp_eq(key, k->key, h) == 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);
+				return sec_bkt->key_idx[i] - 1;
 			}
 		}
 	}
@@ -544,37 +584,68 @@ __rte_hash_add_key_with_hash(const struct rte_hash *h, const void *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;
+#if defined(RTE_ARCH_X86) /* currently only x86 support HTM */
+	if (h->add_key == ADD_KEY_MULTIWRITER_TM) {
+		ret = rte_hash_cuckoo_insert_mw_tm(prim_bkt,
+				sig, alt_hash, new_idx);
+		if (ret >= 0)
+			return new_idx - 1;
+
+		/* Primary bucket full, need to make space for new entry */
+		ret = rte_hash_cuckoo_make_space_mw_tm(h, prim_bkt, sig,
+							alt_hash, new_idx);
+
+		if (ret >= 0)
+			return new_idx - 1;
+
+		/* Also search secondary bucket to get better occupancy */
+		ret = rte_hash_cuckoo_make_space_mw_tm(h, sec_bkt, sig,
+							alt_hash, new_idx);
+
+		if (ret >= 0)
+			return new_idx - 1;
+	} else {
+#endif
+		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;
+				break;
+			}
+		}
+
+		if (i != RTE_HASH_BUCKET_ENTRIES) {
+			if (h->add_key == ADD_KEY_MULTIWRITER)
+				rte_spinlock_unlock(h->multiwriter_lock);
 			return new_idx - 1;
 		}
-	}
 
-	/* 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
+		 * 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
+		 */
+		ret = make_space_bucket(h, prim_bkt);
+		if (ret >= 0) {
+			prim_bkt->signatures[ret].current = sig;
+			prim_bkt->signatures[ret].alt = alt_hash;
+			prim_bkt->key_idx[ret] = new_idx;
+			if (h->add_key == ADD_KEY_MULTIWRITER)
+				rte_spinlock_unlock(h->multiwriter_lock);
+			return new_idx - 1;
+		}
+#if defined(RTE_ARCH_X86)
 	}
-
+#endif
 	/* Error in addition, store new slot back in the ring and return error */
-	rte_ring_sp_enqueue(h->free_slots,
-		(void *)((uintptr_t) new_idx));
-	return ret;
+	enqueue_slot_back(h, cached_free_slots, (void *)((uintptr_t) new_idx));
 
+	if (h->add_key == ADD_KEY_MULTIWRITER)
+		rte_spinlock_unlock(h->multiwriter_lock);
+	return ret;
 }
 
 int32_t
@@ -638,14 +709,14 @@ __rte_hash_lookup_with_hash(const struct rte_hash *h, const void *key,
 				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) {
+			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
 				 */
-				return (bkt->key_idx[i] - 1);
+				return bkt->key_idx[i] - 1;
 			}
 		}
 	}
@@ -661,14 +732,14 @@ __rte_hash_lookup_with_hash(const struct rte_hash *h, const void *key,
 				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 (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
 				 */
-				return (bkt->key_idx[i] - 1);
+				return bkt->key_idx[i] - 1;
 			}
 		}
 	}
@@ -706,6 +777,34 @@ rte_hash_lookup_data(const struct rte_hash *h, const void *key, void **data)
 	return __rte_hash_lookup_with_hash(h, key, rte_hash_hash(h, key), data);
 }
 
+static inline void
+remove_entry(const struct rte_hash *h, struct rte_hash_bucket *bkt, unsigned i)
+{
+	unsigned lcore_id, n_slots;
+	struct lcore_cache *cached_free_slots;
+
+	bkt->signatures[i].sig = NULL_SIGNATURE;
+	if (h->hw_trans_mem_support) {
+		lcore_id = rte_lcore_id();
+		cached_free_slots = &h->local_free_slots[lcore_id];
+		/* Cache full, need to free it. */
+		if (cached_free_slots->len == LCORE_CACHE_SIZE) {
+			/* 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);
+			cached_free_slots->len -= n_slots;
+		}
+		/* Put index of new free slot in cache. */
+		cached_free_slots->objs[cached_free_slots->len] =
+				(void *)((uintptr_t)bkt->key_idx[i]);
+		cached_free_slots->len++;
+	} else {
+		rte_ring_sp_enqueue(h->free_slots,
+				(void *)((uintptr_t)bkt->key_idx[i]));
+	}
+}
+
 static inline int32_t
 __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 						hash_sig_t sig)
@@ -725,15 +824,14 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 				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) {
-				bkt->signatures[i].sig = NULL_SIGNATURE;
-				rte_ring_sp_enqueue(h->free_slots,
-						(void *)((uintptr_t)bkt->key_idx[i]));
+			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
 				 */
-				return (bkt->key_idx[i] - 1);
+				return bkt->key_idx[i] - 1;
 			}
 		}
 	}
@@ -749,15 +847,14 @@ __rte_hash_del_key_with_hash(const struct rte_hash *h, const void *key,
 				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) {
-				bkt->signatures[i].sig = NULL_SIGNATURE;
-				rte_ring_sp_enqueue(h->free_slots,
-						(void *)((uintptr_t)bkt->key_idx[i]));
+			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
 				 */
-				return (bkt->key_idx[i] - 1);
+				return bkt->key_idx[i] - 1;
 			}
 		}
 	}
@@ -861,15 +958,22 @@ lookup_stage2(unsigned idx, hash_sig_t prim_hash, hash_sig_t sec_hash,
 /* 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,
-		void *data[], uint64_t *hits, const struct rte_hash *h)
+		const int32_t *positions, void *data[], uint64_t *hits,
+		const struct rte_hash *h)
 {
 	unsigned hit;
+	unsigned key_idx;
 
-	hit = !h->rte_hash_cmp_eq(key_slot->key, keys[idx], h->key_len);
+	hit = !rte_hash_cmp_eq(key_slot->key, keys[idx], h);
 	if (data != NULL)
 		data[idx] = key_slot->pdata;
 
-	*hits |= (uint64_t)(hit) << idx;
+	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;
 }
 
 static inline void
@@ -961,8 +1065,8 @@ __rte_hash_lookup_bulk(const struct rte_hash *h, const void **keys,
 		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, data, &hits, h);
-		lookup_stage3(idx31, k_slot31, keys, data, &hits, 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;
@@ -988,8 +1092,8 @@ __rte_hash_lookup_bulk(const struct rte_hash *h, const void **keys,
 	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, data, &hits, h);
-	lookup_stage3(idx31, k_slot31, keys, data, &hits, 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;
@@ -1009,14 +1113,14 @@ __rte_hash_lookup_bulk(const struct rte_hash *h, const void **keys,
 	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, data, &hits, h);
-	lookup_stage3(idx31, k_slot31, keys, data, &hits, 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, data, &hits, h);
-	lookup_stage3(idx31, k_slot31, keys, data, &hits, h);
+	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;
@@ -1119,5 +1223,5 @@ rte_hash_iterate(const struct rte_hash *h, const void **key, void **data, uint32
 	/* Increment iterator */
 	(*next)++;
 
-	return (position - 1);
+	return position - 1;
 }