[PATCH v10 1/4] hash: pack the hitmask for hash in bulk lookup

[Yoan Picchi <yoan.picchi@arm.com>]

Current hitmask includes padding due to Intel's SIMD
implementation detail. This patch allows non Intel SIMD
implementations to benefit from a dense hitmask.
In addition, the new dense hitmask interweave the primary
and secondary matches which allow a better cache usage and
enable future improvements for the SIMD implementations
The default non SIMD path now use this dense mask.

Signed-off-by: Yoan Picchi <yoan.picchi@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Nathan Brown <nathan.brown@arm.com>
---
 .mailmap                                  |   1 +
 lib/hash/compare_signatures_arm_pvt.h     |  60 +++++++
 lib/hash/compare_signatures_generic_pvt.h |  37 +++++
 lib/hash/compare_signatures_x86_pvt.h     |  49 ++++++
 lib/hash/hash_sig_cmp_func_pvt.h          |  20 +++
 lib/hash/rte_cuckoo_hash.c                | 190 +++++++++++-----------
 lib/hash/rte_cuckoo_hash.h                |  10 +-
 7 files changed, 267 insertions(+), 100 deletions(-)
 create mode 100644 lib/hash/compare_signatures_arm_pvt.h
 create mode 100644 lib/hash/compare_signatures_generic_pvt.h
 create mode 100644 lib/hash/compare_signatures_x86_pvt.h
 create mode 100644 lib/hash/hash_sig_cmp_func_pvt.h

diff --git a/.mailmap b/.mailmap
index f76037213d..ec525981fe 100644
--- a/.mailmap
+++ b/.mailmap
@@ -1661,6 +1661,7 @@ Yixue Wang <yixue.wang@intel.com>
 Yi Yang <yangyi01@inspur.com> <yi.y.yang@intel.com>
 Yi Zhang <zhang.yi75@zte.com.cn>
 Yoann Desmouceaux <ydesmouc@cisco.com>
+Yoan Picchi <yoan.picchi@arm.com>
 Yogesh Jangra <yogesh.jangra@intel.com>
 Yogev Chaimovich <yogev@cgstowernetworks.com>
 Yongjie Gu <yongjiex.gu@intel.com>
diff --git a/lib/hash/compare_signatures_arm_pvt.h b/lib/hash/compare_signatures_arm_pvt.h
new file mode 100644
index 0000000000..e83bae9912
--- /dev/null
+++ b/lib/hash/compare_signatures_arm_pvt.h
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2016 Intel Corporation
+ * Copyright(c) 2018-2024 Arm Limited
+ */
+
+/*
+ * Arm's version uses a densely packed hitmask buffer:
+ * Every bit is in use.
+ */
+
+#include <inttypes.h>
+#include <rte_common.h>
+#include <rte_vect.h>
+
+#include "rte_cuckoo_hash.h"
+#include "hash_sig_cmp_func_pvt.h"
+
+#define DENSE_HASH_BULK_LOOKUP 1
+
+static inline void
+compare_signatures_dense(uint16_t *hitmask_buffer,
+			const uint16_t *prim_bucket_sigs,
+			const uint16_t *sec_bucket_sigs,
+			uint16_t sig,
+			enum rte_hash_sig_compare_function sig_cmp_fn)
+{
+
+	static_assert(sizeof(*hitmask_buffer) >= 2 * (RTE_HASH_BUCKET_ENTRIES / 8),
+		"hitmask_buffer must be wide enough to fit a dense hitmask");
+
+	/* For match mask every bits indicates the match */
+	switch (sig_cmp_fn) {
+#if RTE_HASH_BUCKET_ENTRIES <= 8
+	case RTE_HASH_COMPARE_NEON: {
+		uint16x8_t vmat, vsig, x;
+		int16x8_t shift = {0, 1, 2, 3, 4, 5, 6, 7};
+		uint16_t low, high;
+
+		vsig = vld1q_dup_u16((uint16_t const *)&sig);
+		/* Compare all signatures in the primary bucket */
+		vmat = vceqq_u16(vsig, vld1q_u16((uint16_t const *)prim_bucket_sigs));
+		x = vshlq_u16(vandq_u16(vmat, vdupq_n_u16(0x0001)), shift);
+		low = (uint16_t)(vaddvq_u16(x));
+		/* Compare all signatures in the secondary bucket */
+		vmat = vceqq_u16(vsig, vld1q_u16((uint16_t const *)sec_bucket_sigs));
+		x = vshlq_u16(vandq_u16(vmat, vdupq_n_u16(0x0001)), shift);
+		high = (uint16_t)(vaddvq_u16(x));
+		*hitmask_buffer = low | high << RTE_HASH_BUCKET_ENTRIES;
+
+		}
+		break;
+#endif
+	default:
+		for (unsigned int i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
+			*hitmask_buffer |= (sig == prim_bucket_sigs[i]) << i;
+			*hitmask_buffer |=
+				((sig == sec_bucket_sigs[i]) << i) << RTE_HASH_BUCKET_ENTRIES;
+		}
+	}
+}
diff --git a/lib/hash/compare_signatures_generic_pvt.h b/lib/hash/compare_signatures_generic_pvt.h
new file mode 100644
index 0000000000..18c2f651c4
--- /dev/null
+++ b/lib/hash/compare_signatures_generic_pvt.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2016 Intel Corporation
+ * Copyright(c) 2018-2024 Arm Limited
+ */
+
+/*
+ * The generic version could use either a dense or sparsely packed hitmask buffer,
+ * but the dense one is slightly faster.
+ */
+
+#include <inttypes.h>
+#include <rte_common.h>
+#include <rte_vect.h>
+
+#include "rte_cuckoo_hash.h"
+#include "hash_sig_cmp_func_pvt.h"
+
+#define DENSE_HASH_BULK_LOOKUP 1
+
+static inline void
+compare_signatures_dense(uint16_t *hitmask_buffer,
+			const uint16_t *prim_bucket_sigs,
+			const uint16_t *sec_bucket_sigs,
+			uint16_t sig,
+			__rte_unused enum rte_hash_sig_compare_function sig_cmp_fn)
+{
+
+	static_assert(sizeof(*hitmask_buffer) >= 2 * (RTE_HASH_BUCKET_ENTRIES / 8),
+			"hitmask_buffer must be wide enough to fit a dense hitmask");
+
+	/* For match mask every bits indicates the match */
+	for (unsigned int i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
+		*hitmask_buffer |= (sig == prim_bucket_sigs[i]) << i;
+		*hitmask_buffer |= ((sig == sec_bucket_sigs[i]) << i) << RTE_HASH_BUCKET_ENTRIES;
+	}
+
+}
diff --git a/lib/hash/compare_signatures_x86_pvt.h b/lib/hash/compare_signatures_x86_pvt.h
new file mode 100644
index 0000000000..932912ba19
--- /dev/null
+++ b/lib/hash/compare_signatures_x86_pvt.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2016 Intel Corporation
+ * Copyright(c) 2018-2024 Arm Limited
+ */
+
+/*
+ * x86's version uses a sparsely packed hitmask buffer:
+ * Every other bit is padding.
+ */
+
+#include <inttypes.h>
+#include <rte_common.h>
+#include <rte_vect.h>
+
+#include "rte_cuckoo_hash.h"
+#include "hash_sig_cmp_func_pvt.h"
+
+#define DENSE_HASH_BULK_LOOKUP 0
+
+static inline void
+compare_signatures_sparse(uint32_t *prim_hash_matches, uint32_t *sec_hash_matches,
+			const struct rte_hash_bucket *prim_bkt,
+			const struct rte_hash_bucket *sec_bkt,
+			uint16_t sig,
+			enum rte_hash_sig_compare_function sig_cmp_fn)
+{
+	/* For match mask the first bit of every two bits indicates the match */
+	switch (sig_cmp_fn) {
+#if defined(__SSE2__) && RTE_HASH_BUCKET_ENTRIES <= 8
+	case RTE_HASH_COMPARE_SSE:
+		/* Compare all signatures in the bucket */
+		*prim_hash_matches = _mm_movemask_epi8(_mm_cmpeq_epi16(_mm_load_si128(
+			(__m128i const *)prim_bkt->sig_current), _mm_set1_epi16(sig)));
+		/* Extract the even-index bits only */
+		*prim_hash_matches &= 0x5555;
+		/* Compare all signatures in the bucket */
+		*sec_hash_matches = _mm_movemask_epi8(_mm_cmpeq_epi16(_mm_load_si128(
+			(__m128i const *)sec_bkt->sig_current), _mm_set1_epi16(sig)));
+		/* Extract the even-index bits only */
+		*sec_hash_matches &= 0x5555;
+		break;
+#endif /* defined(__SSE2__) */
+	default:
+		for (unsigned int i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
+			*prim_hash_matches |= (sig == prim_bkt->sig_current[i]) << (i << 1);
+			*sec_hash_matches |= (sig == sec_bkt->sig_current[i]) << (i << 1);
+		}
+	}
+}
diff --git a/lib/hash/hash_sig_cmp_func_pvt.h b/lib/hash/hash_sig_cmp_func_pvt.h
new file mode 100644
index 0000000000..d8d2fbffaf
--- /dev/null
+++ b/lib/hash/hash_sig_cmp_func_pvt.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2024 Arm Limited
+ */
+
+#ifndef _SIG_CMP_FUNC_H_
+#define _SIG_CMP_FUNC_H_
+
+/** Enum used to select the implementation of the signature comparison function to use
+ * eg: A system supporting SVE might want to use a NEON implementation.
+ * Those may change and are for internal use only
+ */
+enum rte_hash_sig_compare_function {
+	RTE_HASH_COMPARE_SCALAR = 0,
+	RTE_HASH_COMPARE_SSE,
+	RTE_HASH_COMPARE_NEON,
+	RTE_HASH_COMPARE_SVE,
+	RTE_HASH_COMPARE_NUM
+};
+
+#endif
diff --git a/lib/hash/rte_cuckoo_hash.c b/lib/hash/rte_cuckoo_hash.c
index d87aa52b5b..61cc12d83b 100644
--- a/lib/hash/rte_cuckoo_hash.c
+++ b/lib/hash/rte_cuckoo_hash.c
@@ -32,6 +32,15 @@ RTE_LOG_REGISTER_DEFAULT(hash_logtype, INFO);
 	RTE_LOG_LINE(level, HASH, "" __VA_ARGS__)
 
 #include "rte_cuckoo_hash.h"
+#include "hash_sig_cmp_func_pvt.h"
+
+#if defined(__ARM_NEON)
+#include "compare_signatures_arm_pvt.h"
+#elif defined(__SSE2__)
+#include "compare_signatures_x86_pvt.h"
+#else
+#include "compare_signatures_generic_pvt.h"
+#endif
 
 /* Mask of all flags supported by this version */
 #define RTE_HASH_EXTRA_FLAGS_MASK (RTE_HASH_EXTRA_FLAGS_TRANS_MEM_SUPPORT | \
@@ -1880,63 +1889,6 @@ rte_hash_free_key_with_position(const struct rte_hash *h,
 
 }
 
-static inline void
-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,
-			uint16_t sig,
-			enum rte_hash_sig_compare_function sig_cmp_fn)
-{
-	unsigned int i;
-
-	/* For match mask the first bit of every two bits indicates the match */
-	switch (sig_cmp_fn) {
-#if defined(__SSE2__)
-	case RTE_HASH_COMPARE_SSE:
-		/* Compare all signatures in the bucket */
-		*prim_hash_matches = _mm_movemask_epi8(_mm_cmpeq_epi16(
-				_mm_load_si128(
-					(__m128i const *)prim_bkt->sig_current),
-				_mm_set1_epi16(sig)));
-		/* Extract the even-index bits only */
-		*prim_hash_matches &= 0x5555;
-		/* Compare all signatures in the bucket */
-		*sec_hash_matches = _mm_movemask_epi8(_mm_cmpeq_epi16(
-				_mm_load_si128(
-					(__m128i const *)sec_bkt->sig_current),
-				_mm_set1_epi16(sig)));
-		/* Extract the even-index bits only */
-		*sec_hash_matches &= 0x5555;
-		break;
-#elif defined(__ARM_NEON)
-	case RTE_HASH_COMPARE_NEON: {
-		uint16x8_t vmat, vsig, x;
-		int16x8_t shift = {-15, -13, -11, -9, -7, -5, -3, -1};
-
-		vsig = vld1q_dup_u16((uint16_t const *)&sig);
-		/* Compare all signatures in the primary bucket */
-		vmat = vceqq_u16(vsig,
-			vld1q_u16((uint16_t const *)prim_bkt->sig_current));
-		x = vshlq_u16(vandq_u16(vmat, vdupq_n_u16(0x8000)), shift);
-		*prim_hash_matches = (uint32_t)(vaddvq_u16(x));
-		/* Compare all signatures in the secondary bucket */
-		vmat = vceqq_u16(vsig,
-			vld1q_u16((uint16_t const *)sec_bkt->sig_current));
-		x = vshlq_u16(vandq_u16(vmat, vdupq_n_u16(0x8000)), shift);
-		*sec_hash_matches = (uint32_t)(vaddvq_u16(x));
-		}
-		break;
-#endif
-	default:
-		for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
-			*prim_hash_matches |=
-				((sig == prim_bkt->sig_current[i]) << (i << 1));
-			*sec_hash_matches |=
-				((sig == sec_bkt->sig_current[i]) << (i << 1));
-		}
-	}
-}
-
 static inline void
 __bulk_lookup_l(const struct rte_hash *h, const void **keys,
 		const struct rte_hash_bucket **primary_bkt,
@@ -1947,22 +1899,41 @@ __bulk_lookup_l(const struct rte_hash *h, const void **keys,
 	uint64_t hits = 0;
 	int32_t i;
 	int32_t ret;
-	uint32_t prim_hitmask[RTE_HASH_LOOKUP_BULK_MAX] = {0};
-	uint32_t sec_hitmask[RTE_HASH_LOOKUP_BULK_MAX] = {0};
 	struct rte_hash_bucket *cur_bkt, *next_bkt;
 
+#if DENSE_HASH_BULK_LOOKUP
+	const int hitmask_padding = 0;
+	uint16_t hitmask_buffer[RTE_HASH_LOOKUP_BULK_MAX] = {0};
+#else
+	const int hitmask_padding = 1;
+	uint32_t prim_hitmask_buffer[RTE_HASH_LOOKUP_BULK_MAX] = {0};
+	uint32_t sec_hitmask_buffer[RTE_HASH_LOOKUP_BULK_MAX] = {0};
+#endif
+
 	__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],
+#if DENSE_HASH_BULK_LOOKUP
+		uint16_t *hitmask = &hitmask_buffer[i];
+		compare_signatures_dense(hitmask,
+			primary_bkt[i]->sig_current,
+			secondary_bkt[i]->sig_current,
+			sig[i], h->sig_cmp_fn);
+		const unsigned int prim_hitmask = *(uint8_t *)(hitmask);
+		const unsigned int sec_hitmask = *((uint8_t *)(hitmask)+1);
+#else
+		compare_signatures_sparse(&prim_hitmask_buffer[i], &sec_hitmask_buffer[i],
 			primary_bkt[i], secondary_bkt[i],
 			sig[i], h->sig_cmp_fn);
+		const unsigned int prim_hitmask = prim_hitmask_buffer[i];
+		const unsigned int sec_hitmask = sec_hitmask_buffer[i];
+#endif
 
-		if (prim_hitmask[i]) {
+		if (prim_hitmask) {
 			uint32_t first_hit =
-					rte_ctz32(prim_hitmask[i])
-					>> 1;
+					rte_ctz32(prim_hitmask)
+					>> hitmask_padding;
 			uint32_t key_idx =
 				primary_bkt[i]->key_idx[first_hit];
 			const struct rte_hash_key *key_slot =
@@ -1973,10 +1944,10 @@ __bulk_lookup_l(const struct rte_hash *h, const void **keys,
 			continue;
 		}
 
-		if (sec_hitmask[i]) {
+		if (sec_hitmask) {
 			uint32_t first_hit =
-					rte_ctz32(sec_hitmask[i])
-					>> 1;
+					rte_ctz32(sec_hitmask)
+					>> hitmask_padding;
 			uint32_t key_idx =
 				secondary_bkt[i]->key_idx[first_hit];
 			const struct rte_hash_key *key_slot =
@@ -1990,10 +1961,18 @@ __bulk_lookup_l(const struct rte_hash *h, const void **keys,
 	/* Compare keys, first hits in primary first */
 	for (i = 0; i < num_keys; i++) {
 		positions[i] = -ENOENT;
-		while (prim_hitmask[i]) {
+#if DENSE_HASH_BULK_LOOKUP
+		uint16_t *hitmask = &hitmask_buffer[i];
+		unsigned int prim_hitmask = *(uint8_t *)(hitmask);
+		unsigned int sec_hitmask = *((uint8_t *)(hitmask)+1);
+#else
+		unsigned int prim_hitmask = prim_hitmask_buffer[i];
+		unsigned int sec_hitmask = sec_hitmask_buffer[i];
+#endif
+		while (prim_hitmask) {
 			uint32_t hit_index =
-					rte_ctz32(prim_hitmask[i])
-					>> 1;
+					rte_ctz32(prim_hitmask)
+					>> hitmask_padding;
 			uint32_t key_idx =
 				primary_bkt[i]->key_idx[hit_index];
 			const struct rte_hash_key *key_slot =
@@ -2015,13 +1994,13 @@ __bulk_lookup_l(const struct rte_hash *h, const void **keys,
 				positions[i] = key_idx - 1;
 				goto next_key;
 			}
-			prim_hitmask[i] &= ~(3ULL << (hit_index << 1));
+			prim_hitmask &= ~(1 << (hit_index << hitmask_padding));
 		}
 
-		while (sec_hitmask[i]) {
+		while (sec_hitmask) {
 			uint32_t hit_index =
-					rte_ctz32(sec_hitmask[i])
-					>> 1;
+					rte_ctz32(sec_hitmask)
+					>> hitmask_padding;
 			uint32_t key_idx =
 				secondary_bkt[i]->key_idx[hit_index];
 			const struct rte_hash_key *key_slot =
@@ -2044,7 +2023,7 @@ __bulk_lookup_l(const struct rte_hash *h, const void **keys,
 				positions[i] = key_idx - 1;
 				goto next_key;
 			}
-			sec_hitmask[i] &= ~(3ULL << (hit_index << 1));
+			sec_hitmask &= ~(1 << (hit_index << hitmask_padding));
 		}
 next_key:
 		continue;
@@ -2094,11 +2073,20 @@ __bulk_lookup_lf(const struct rte_hash *h, const void **keys,
 	uint64_t hits = 0;
 	int32_t i;
 	int32_t ret;
-	uint32_t prim_hitmask[RTE_HASH_LOOKUP_BULK_MAX] = {0};
-	uint32_t sec_hitmask[RTE_HASH_LOOKUP_BULK_MAX] = {0};
 	struct rte_hash_bucket *cur_bkt, *next_bkt;
 	uint32_t cnt_b, cnt_a;
 
+#if DENSE_HASH_BULK_LOOKUP
+	const int hitmask_padding = 0;
+	uint16_t hitmask_buffer[RTE_HASH_LOOKUP_BULK_MAX] = {0};
+	static_assert(sizeof(*hitmask_buffer)*8/2 == RTE_HASH_BUCKET_ENTRIES,
+	"The hitmask must be exactly wide enough to accept the whole hitmask chen it is dense");
+#else
+	const int hitmask_padding = 1;
+	uint32_t prim_hitmask_buffer[RTE_HASH_LOOKUP_BULK_MAX] = {0};
+	uint32_t sec_hitmask_buffer[RTE_HASH_LOOKUP_BULK_MAX] = {0};
+#endif
+
 	for (i = 0; i < num_keys; i++)
 		positions[i] = -ENOENT;
 
@@ -2112,14 +2100,26 @@ __bulk_lookup_lf(const struct rte_hash *h, const void **keys,
 
 		/* Compare signatures and prefetch key slot of first hit */
 		for (i = 0; i < num_keys; i++) {
-			compare_signatures(&prim_hitmask[i], &sec_hitmask[i],
+#if DENSE_HASH_BULK_LOOKUP
+			uint16_t *hitmask = &hitmask_buffer[i];
+			compare_signatures_dense(hitmask,
+				primary_bkt[i]->sig_current,
+				secondary_bkt[i]->sig_current,
+				sig[i], h->sig_cmp_fn);
+			const unsigned int prim_hitmask = *(uint8_t *)(hitmask);
+			const unsigned int sec_hitmask = *((uint8_t *)(hitmask)+1);
+#else
+			compare_signatures_sparse(&prim_hitmask_buffer[i], &sec_hitmask_buffer[i],
 				primary_bkt[i], secondary_bkt[i],
 				sig[i], h->sig_cmp_fn);
+			const unsigned int prim_hitmask = prim_hitmask_buffer[i];
+			const unsigned int sec_hitmask = sec_hitmask_buffer[i];
+#endif
 
-			if (prim_hitmask[i]) {
+			if (prim_hitmask) {
 				uint32_t first_hit =
-						rte_ctz32(prim_hitmask[i])
-						>> 1;
+						rte_ctz32(prim_hitmask)
+						>> hitmask_padding;
 				uint32_t key_idx =
 					primary_bkt[i]->key_idx[first_hit];
 				const struct rte_hash_key *key_slot =
@@ -2130,10 +2130,10 @@ __bulk_lookup_lf(const struct rte_hash *h, const void **keys,
 				continue;
 			}
 
-			if (sec_hitmask[i]) {
+			if (sec_hitmask) {
 				uint32_t first_hit =
-						rte_ctz32(sec_hitmask[i])
-						>> 1;
+						rte_ctz32(sec_hitmask)
+						>> hitmask_padding;
 				uint32_t key_idx =
 					secondary_bkt[i]->key_idx[first_hit];
 				const struct rte_hash_key *key_slot =
@@ -2146,10 +2146,18 @@ __bulk_lookup_lf(const struct rte_hash *h, const void **keys,
 
 		/* Compare keys, first hits in primary first */
 		for (i = 0; i < num_keys; i++) {
-			while (prim_hitmask[i]) {
+#if DENSE_HASH_BULK_LOOKUP
+			uint16_t *hitmask = &hitmask_buffer[i];
+			unsigned int prim_hitmask = *(uint8_t *)(hitmask);
+			unsigned int sec_hitmask = *((uint8_t *)(hitmask)+1);
+#else
+			unsigned int prim_hitmask = prim_hitmask_buffer[i];
+			unsigned int sec_hitmask = sec_hitmask_buffer[i];
+#endif
+			while (prim_hitmask) {
 				uint32_t hit_index =
-						rte_ctz32(prim_hitmask[i])
-						>> 1;
+						rte_ctz32(prim_hitmask)
+						>> hitmask_padding;
 				uint32_t key_idx =
 				rte_atomic_load_explicit(
 					&primary_bkt[i]->key_idx[hit_index],
@@ -2175,13 +2183,13 @@ __bulk_lookup_lf(const struct rte_hash *h, const void **keys,
 					positions[i] = key_idx - 1;
 					goto next_key;
 				}
-				prim_hitmask[i] &= ~(3ULL << (hit_index << 1));
+				prim_hitmask &= ~(1 << (hit_index << hitmask_padding));
 			}
 
-			while (sec_hitmask[i]) {
+			while (sec_hitmask) {
 				uint32_t hit_index =
-						rte_ctz32(sec_hitmask[i])
-						>> 1;
+						rte_ctz32(sec_hitmask)
+						>> hitmask_padding;
 				uint32_t key_idx =
 				rte_atomic_load_explicit(
 					&secondary_bkt[i]->key_idx[hit_index],
@@ -2208,7 +2216,7 @@ __bulk_lookup_lf(const struct rte_hash *h, const void **keys,
 					positions[i] = key_idx - 1;
 					goto next_key;
 				}
-				sec_hitmask[i] &= ~(3ULL << (hit_index << 1));
+				sec_hitmask &= ~(1 << (hit_index << hitmask_padding));
 			}
 next_key:
 			continue;
diff --git a/lib/hash/rte_cuckoo_hash.h b/lib/hash/rte_cuckoo_hash.h
index a528f1d1a0..26a992419a 100644
--- a/lib/hash/rte_cuckoo_hash.h
+++ b/lib/hash/rte_cuckoo_hash.h
@@ -134,14 +134,6 @@ struct rte_hash_key {
 	char key[0];
 };
 
-/* All different signature compare functions */
-enum rte_hash_sig_compare_function {
-	RTE_HASH_COMPARE_SCALAR = 0,
-	RTE_HASH_COMPARE_SSE,
-	RTE_HASH_COMPARE_NEON,
-	RTE_HASH_COMPARE_NUM
-};
-
 /** Bucket structure */
 struct __rte_cache_aligned rte_hash_bucket {
 	uint16_t sig_current[RTE_HASH_BUCKET_ENTRIES];
@@ -199,7 +191,7 @@ struct __rte_cache_aligned rte_hash {
 	/**< Custom function used to compare keys. */
 	enum cmp_jump_table_case cmp_jump_table_idx;
 	/**< Indicates which compare function to use. */
-	enum rte_hash_sig_compare_function sig_cmp_fn;
+	unsigned int sig_cmp_fn;
 	/**< Indicates which signature compare function to use. */
 	uint32_t bucket_bitmask;
 	/**< Bitmask for getting bucket index from hash signature. */
-- 
2.25.1