[dpdk-dev] [PATCH v4 1/3] lib/librte_table: add hash func header files

[Kevin Laatz <kevin.laatz@intel.com>]

This commit adds rte_table_hash_func.h and rte_table_hash_func_arm64.h to
librte_table. This reduces code duplication by removing duplicate header
files within two folders and consolidating them into a single one. This
also adds a scalar implementation of the x86_64 intrinsic for crc32 as a
generic fallback.

Signed-off-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Signed-off-by: Kevin Laatz <kevin.laatz@intel.com>
Acked-by: Gavin Hu <gavin.hu@arm.com>
---
v2:
   - Fixed typo in commit message
   - Fixed typo in arm header that caused some compilations to fail for the
     entire patchset
v3:
   - Improved commit message

v4:
   - Fixed checkpatch.sh and check-git-log.sh errors
---
 lib/librte_table/Makefile                    |   2 +
 lib/librte_table/meson.build                 |   2 +
 lib/librte_table/rte_table_hash_func.h       | 245 +++++++++++++++++++++++++++
 lib/librte_table/rte_table_hash_func_arm64.h |  21 +++
 4 files changed, 270 insertions(+)
 create mode 100644 lib/librte_table/rte_table_hash_func.h
 create mode 100644 lib/librte_table/rte_table_hash_func_arm64.h

diff --git a/lib/librte_table/Makefile b/lib/librte_table/Makefile
index 276d476..f935678 100644
--- a/lib/librte_table/Makefile
+++ b/lib/librte_table/Makefile
@@ -46,6 +46,8 @@ SYMLINK-$(CONFIG_RTE_LIBRTE_TABLE)-include += rte_table_acl.h
 endif
 SYMLINK-$(CONFIG_RTE_LIBRTE_TABLE)-include += rte_table_hash.h
 SYMLINK-$(CONFIG_RTE_LIBRTE_TABLE)-include += rte_table_hash_cuckoo.h
+SYMLINK-$(CONFIG_RTE_LIBRTE_TABLE)-include += rte_table_hash_func.h
+SYMLINK-$(CONFIG_RTE_LIBRTE_TABLE)-include += rte_table_hash_func_arm64.h
 SYMLINK-$(CONFIG_RTE_LIBRTE_TABLE)-include += rte_lru.h
 ifeq ($(CONFIG_RTE_ARCH_X86),y)
 SYMLINK-$(CONFIG_RTE_LIBRTE_TABLE)-include += rte_lru_x86.h
diff --git a/lib/librte_table/meson.build b/lib/librte_table/meson.build
index 8b2f841..6ae3cd6 100644
--- a/lib/librte_table/meson.build
+++ b/lib/librte_table/meson.build
@@ -19,6 +19,8 @@ headers = files('rte_table.h',
 		'rte_table_lpm_ipv6.h',
 		'rte_table_hash.h',
 		'rte_table_hash_cuckoo.h',
+		'rte_table_hash_func.h',
+		'rte_table_hash_func_arm64.h',
 		'rte_lru.h',
 		'rte_table_array.h',
 		'rte_table_stub.h')
diff --git a/lib/librte_table/rte_table_hash_func.h b/lib/librte_table/rte_table_hash_func.h
new file mode 100644
index 0000000..02296ea
--- /dev/null
+++ b/lib/librte_table/rte_table_hash_func.h
@@ -0,0 +1,245 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2018 Intel Corporation
+ */
+
+#ifndef __INCLUDE_RTE_TABLE_HASH_FUNC_H__
+#define __INCLUDE_RTE_TABLE_HASH_FUNC_H__
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <stdint.h>
+
+#include <rte_compat.h>
+#include <rte_common.h>
+
+static inline uint64_t __rte_experimental
+rte_crc32_u64_generic(uint64_t crc, uint64_t value)
+{
+	int i;
+
+	crc = (crc & 0xFFFFFFFFLLU) ^ value;
+	for (i = 63; i >= 0; i--) {
+		uint64_t mask;
+
+		mask = -(crc & 1LLU);
+		crc = (crc >> 1LLU) ^ (0x82F63B78LLU & mask);
+	}
+
+	return crc;
+}
+
+#if defined(RTE_ARCH_X86_64)
+
+#include <x86intrin.h>
+
+static inline uint64_t
+rte_crc32_u64(uint64_t crc, uint64_t v)
+{
+	return _mm_crc32_u64(crc, v);
+}
+
+#elif defined(RTE_ARCH_ARM64)
+#include "rte_table_hash_func_arm64.h"
+#else
+
+static inline uint64_t
+rte_crc32_u64(uint64_t crc, uint64_t v)
+{
+	return rte_crc32_u64_generic(crc, v);
+}
+
+#endif
+
+static inline uint64_t __rte_experimental
+rte_table_hash_crc_key8(void *key, void *mask, __rte_unused uint32_t key_size,
+	uint64_t seed)
+{
+	uint64_t *k = key;
+	uint64_t *m = mask;
+	uint64_t crc0;
+
+	crc0 = rte_crc32_u64(seed, k[0] & m[0]);
+
+	return crc0;
+}
+
+static inline uint64_t __rte_experimental
+rte_table_hash_crc_key16(void *key, void *mask, __rte_unused uint32_t key_size,
+	uint64_t seed)
+{
+	uint64_t *k = key;
+	uint64_t *m = mask;
+	uint64_t k0, crc0, crc1;
+
+	k0 = k[0] & m[0];
+
+	crc0 = rte_crc32_u64(k0, seed);
+	crc1 = rte_crc32_u64(k0 >> 32, k[1] & m[1]);
+
+	crc0 ^= crc1;
+
+	return crc0;
+}
+
+static inline uint64_t __rte_experimental
+rte_table_hash_crc_key24(void *key, void *mask, __rte_unused uint32_t key_size,
+	uint64_t seed)
+{
+	uint64_t *k = key;
+	uint64_t *m = mask;
+	uint64_t k0, k2, crc0, crc1;
+
+	k0 = k[0] & m[0];
+	k2 = k[2] & m[2];
+
+	crc0 = rte_crc32_u64(k0, seed);
+	crc1 = rte_crc32_u64(k0 >> 32, k[1] & m[1]);
+
+	crc0 = rte_crc32_u64(crc0, k2);
+
+	crc0 ^= crc1;
+
+	return crc0;
+}
+
+static inline uint64_t __rte_experimental
+rte_table_hash_crc_key32(void *key, void *mask, __rte_unused uint32_t key_size,
+	uint64_t seed)
+{
+	uint64_t *k = key;
+	uint64_t *m = mask;
+	uint64_t k0, k2, crc0, crc1, crc2, crc3;
+
+	k0 = k[0] & m[0];
+	k2 = k[2] & m[2];
+
+	crc0 = rte_crc32_u64(k0, seed);
+	crc1 = rte_crc32_u64(k0 >> 32, k[1] & m[1]);
+
+	crc2 = rte_crc32_u64(k2, k[3] & m[3]);
+	crc3 = k2 >> 32;
+
+	crc0 = rte_crc32_u64(crc0, crc1);
+	crc1 = rte_crc32_u64(crc2, crc3);
+
+	crc0 ^= crc1;
+
+	return crc0;
+}
+
+static inline uint64_t __rte_experimental
+rte_table_hash_crc_key40(void *key, void *mask, __rte_unused uint32_t key_size,
+	uint64_t seed)
+{
+	uint64_t *k = key;
+	uint64_t *m = mask;
+	uint64_t k0, k2, crc0, crc1, crc2, crc3;
+
+	k0 = k[0] & m[0];
+	k2 = k[2] & m[2];
+
+	crc0 = rte_crc32_u64(k0, seed);
+	crc1 = rte_crc32_u64(k0 >> 32, k[1] & m[1]);
+
+	crc2 = rte_crc32_u64(k2, k[3] & m[3]);
+	crc3 = rte_crc32_u64(k2 >> 32, k[4] & m[4]);
+
+	crc0 = rte_crc32_u64(crc0, crc1);
+	crc1 = rte_crc32_u64(crc2, crc3);
+
+	crc0 ^= crc1;
+
+	return crc0;
+}
+
+static inline uint64_t __rte_experimental
+rte_table_hash_crc_key48(void *key, void *mask, __rte_unused uint32_t key_size,
+	uint64_t seed)
+{
+	uint64_t *k = key;
+	uint64_t *m = mask;
+	uint64_t k0, k2, k5, crc0, crc1, crc2, crc3;
+
+	k0 = k[0] & m[0];
+	k2 = k[2] & m[2];
+	k5 = k[5] & m[5];
+
+	crc0 = rte_crc32_u64(k0, seed);
+	crc1 = rte_crc32_u64(k0 >> 32, k[1] & m[1]);
+
+	crc2 = rte_crc32_u64(k2, k[3] & m[3]);
+	crc3 = rte_crc32_u64(k2 >> 32, k[4] & m[4]);
+
+	crc0 = rte_crc32_u64(crc0, (crc1 << 32) ^ crc2);
+	crc1 = rte_crc32_u64(crc3, k5);
+
+	crc0 ^= crc1;
+
+	return crc0;
+}
+
+static inline uint64_t __rte_experimental
+rte_table_hash_crc_key56(void *key, void *mask, __rte_unused uint32_t key_size,
+	uint64_t seed)
+{
+	uint64_t *k = key;
+	uint64_t *m = mask;
+	uint64_t k0, k2, k5, crc0, crc1, crc2, crc3, crc4, crc5;
+
+	k0 = k[0] & m[0];
+	k2 = k[2] & m[2];
+	k5 = k[5] & m[5];
+
+	crc0 = rte_crc32_u64(k0, seed);
+	crc1 = rte_crc32_u64(k0 >> 32, k[1] & m[1]);
+
+	crc2 = rte_crc32_u64(k2, k[3] & m[3]);
+	crc3 = rte_crc32_u64(k2 >> 32, k[4] & m[4]);
+
+	crc4 = rte_crc32_u64(k5, k[6] & m[6]);
+	crc5 = k5 >> 32;
+
+	crc0 = rte_crc32_u64(crc0, (crc1 << 32) ^ crc2);
+	crc1 = rte_crc32_u64(crc3, (crc4 << 32) ^ crc5);
+
+	crc0 ^= crc1;
+
+	return crc0;
+}
+
+static inline uint64_t __rte_experimental
+rte_table_hash_crc_key64(void *key, void *mask, __rte_unused uint32_t key_size,
+	uint64_t seed)
+{
+	uint64_t *k = key;
+	uint64_t *m = mask;
+	uint64_t k0, k2, k5, crc0, crc1, crc2, crc3, crc4, crc5;
+
+	k0 = k[0] & m[0];
+	k2 = k[2] & m[2];
+	k5 = k[5] & m[5];
+
+	crc0 = rte_crc32_u64(k0, seed);
+	crc1 = rte_crc32_u64(k0 >> 32, k[1] & m[1]);
+
+	crc2 = rte_crc32_u64(k2, k[3] & m[3]);
+	crc3 = rte_crc32_u64(k2 >> 32, k[4] & m[4]);
+
+	crc4 = rte_crc32_u64(k5, k[6] & m[6]);
+	crc5 = rte_crc32_u64(k5 >> 32, k[7] & m[7]);
+
+	crc0 = rte_crc32_u64(crc0, (crc1 << 32) ^ crc2);
+	crc1 = rte_crc32_u64(crc3, (crc4 << 32) ^ crc5);
+
+	crc0 ^= crc1;
+
+	return crc0;
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/lib/librte_table/rte_table_hash_func_arm64.h b/lib/librte_table/rte_table_hash_func_arm64.h
new file mode 100644
index 0000000..eb04c1f
--- /dev/null
+++ b/lib/librte_table/rte_table_hash_func_arm64.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2017-2018 Linaro Limited
+ */
+
+#ifndef __INCLUDE_RTE_TABLE_HASH_FUNC_ARM64_H__
+#define __INCLUDE_RTE_TABLE_HASH_FUNC_ARM64_H__
+
+#define _CRC32CX(crc, val)	\
+	__asm__("crc32cx %w[c], %w[c], %x[v]":[c] "+r" (crc):[v] "r" (val))
+
+static inline uint64_t
+rte_crc32_u64(uint64_t crc, uint64_t v)
+{
+	uint32_t crc32 = crc;
+
+	_CRC32CX(crc32, v);
+
+	return crc32;
+}
+
+#endif
-- 
2.9.5