[PATCH v5 1/2] ip_frag: optimize key compare and hash generation

[pbhagavatula at marvell.com]

From: Pavan Nikhilesh <pbhagavatula at marvell.com>

Use optimized rte_hash_k32_cmp_eq routine for key comparison for
x86 and ARM64.
Use CRC instructions for hash generation on ARM64.

Signed-off-by: Pavan Nikhilesh <pbhagavatula at marvell.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang at arm.com>
---
On Neoverse-N2, performance improved by 10% when measured with
examples/ip_reassembly.

 v5 Changes:
 - Fix spellcheck.
 v4 Changes:
 - Fix compilation failures (sys/queue)
 - Update test case to use proper macros.
 v3 Changes:
 - Drop NEON patch.
 v2 Changes:
 - Fix compilation failure with non ARM64/x86 targets

 lib/hash/rte_cmp_arm64.h       | 16 ++++++++--------
 lib/hash/rte_cmp_x86.h         | 16 ++++++++--------
 lib/ip_frag/ip_frag_common.h   | 14 ++++++++++++++
 lib/ip_frag/ip_frag_internal.c |  4 ++--
 4 files changed, 32 insertions(+), 18 deletions(-)

diff --git a/lib/hash/rte_cmp_arm64.h b/lib/hash/rte_cmp_arm64.h
index e9e26f9abd..a3e85635eb 100644
--- a/lib/hash/rte_cmp_arm64.h
+++ b/lib/hash/rte_cmp_arm64.h
@@ -3,7 +3,7 @@
  */

 /* Functions to compare multiple of 16 byte keys (up to 128 bytes) */
-static int
+static inline int
 rte_hash_k16_cmp_eq(const void *key1, const void *key2,
 		    size_t key_len __rte_unused)
 {
@@ -24,7 +24,7 @@ rte_hash_k16_cmp_eq(const void *key1, const void *key2,
 	return !(x0 == 0 && x1 == 0);
 }

-static int
+static inline int
 rte_hash_k32_cmp_eq(const void *key1, const void *key2, size_t key_len)
 {
 	return rte_hash_k16_cmp_eq(key1, key2, key_len) ||
@@ -32,7 +32,7 @@ rte_hash_k32_cmp_eq(const void *key1, const void *key2, size_t key_len)
 				(const char *) key2 + 16, key_len);
 }

-static int
+static inline int
 rte_hash_k48_cmp_eq(const void *key1, const void *key2, size_t key_len)
 {
 	return rte_hash_k16_cmp_eq(key1, key2, key_len) ||
@@ -42,7 +42,7 @@ rte_hash_k48_cmp_eq(const void *key1, const void *key2, size_t key_len)
 				(const char *) key2 + 32, key_len);
 }

-static int
+static inline int
 rte_hash_k64_cmp_eq(const void *key1, const void *key2, size_t key_len)
 {
 	return rte_hash_k32_cmp_eq(key1, key2, key_len) ||
@@ -50,7 +50,7 @@ rte_hash_k64_cmp_eq(const void *key1, const void *key2, size_t key_len)
 				(const char *) key2 + 32, key_len);
 }

-static int
+static inline int
 rte_hash_k80_cmp_eq(const void *key1, const void *key2, size_t key_len)
 {
 	return rte_hash_k64_cmp_eq(key1, key2, key_len) ||
@@ -58,7 +58,7 @@ rte_hash_k80_cmp_eq(const void *key1, const void *key2, size_t key_len)
 				(const char *) key2 + 64, key_len);
 }

-static int
+static inline int
 rte_hash_k96_cmp_eq(const void *key1, const void *key2, size_t key_len)
 {
 	return rte_hash_k64_cmp_eq(key1, key2, key_len) ||
@@ -66,7 +66,7 @@ rte_hash_k96_cmp_eq(const void *key1, const void *key2, size_t key_len)
 				(const char *) key2 + 64, key_len);
 }

-static int
+static inline int
 rte_hash_k112_cmp_eq(const void *key1, const void *key2, size_t key_len)
 {
 	return rte_hash_k64_cmp_eq(key1, key2, key_len) ||
@@ -76,7 +76,7 @@ rte_hash_k112_cmp_eq(const void *key1, const void *key2, size_t key_len)
 				(const char *) key2 + 96, key_len);
 }

-static int
+static inline int
 rte_hash_k128_cmp_eq(const void *key1, const void *key2, size_t key_len)
 {
 	return rte_hash_k64_cmp_eq(key1, key2, key_len) ||
diff --git a/lib/hash/rte_cmp_x86.h b/lib/hash/rte_cmp_x86.h
index 13a5836351..ddfbef462f 100644
--- a/lib/hash/rte_cmp_x86.h
+++ b/lib/hash/rte_cmp_x86.h
@@ -5,7 +5,7 @@
 #include <rte_vect.h>

 /* Functions to compare multiple of 16 byte keys (up to 128 bytes) */
-static int
+static inline int
 rte_hash_k16_cmp_eq(const void *key1, const void *key2, size_t key_len __rte_unused)
 {
 	const __m128i k1 = _mm_loadu_si128((const __m128i *) key1);
@@ -15,7 +15,7 @@ rte_hash_k16_cmp_eq(const void *key1, const void *key2, size_t key_len __rte_unu
 	return !_mm_test_all_zeros(x, x);
 }

-static int
+static inline int
 rte_hash_k32_cmp_eq(const void *key1, const void *key2, size_t key_len)
 {
 	return rte_hash_k16_cmp_eq(key1, key2, key_len) ||
@@ -23,7 +23,7 @@ rte_hash_k32_cmp_eq(const void *key1, const void *key2, size_t key_len)
 				(const char *) key2 + 16, key_len);
 }

-static int
+static inline int
 rte_hash_k48_cmp_eq(const void *key1, const void *key2, size_t key_len)
 {
 	return rte_hash_k16_cmp_eq(key1, key2, key_len) ||
@@ -33,7 +33,7 @@ rte_hash_k48_cmp_eq(const void *key1, const void *key2, size_t key_len)
 				(const char *) key2 + 32, key_len);
 }

-static int
+static inline int
 rte_hash_k64_cmp_eq(const void *key1, const void *key2, size_t key_len)
 {
 	return rte_hash_k32_cmp_eq(key1, key2, key_len) ||
@@ -41,7 +41,7 @@ rte_hash_k64_cmp_eq(const void *key1, const void *key2, size_t key_len)
 				(const char *) key2 + 32, key_len);
 }

-static int
+static inline int
 rte_hash_k80_cmp_eq(const void *key1, const void *key2, size_t key_len)
 {
 	return rte_hash_k64_cmp_eq(key1, key2, key_len) ||
@@ -49,7 +49,7 @@ rte_hash_k80_cmp_eq(const void *key1, const void *key2, size_t key_len)
 				(const char *) key2 + 64, key_len);
 }

-static int
+static inline int
 rte_hash_k96_cmp_eq(const void *key1, const void *key2, size_t key_len)
 {
 	return rte_hash_k64_cmp_eq(key1, key2, key_len) ||
@@ -57,7 +57,7 @@ rte_hash_k96_cmp_eq(const void *key1, const void *key2, size_t key_len)
 				(const char *) key2 + 64, key_len);
 }

-static int
+static inline int
 rte_hash_k112_cmp_eq(const void *key1, const void *key2, size_t key_len)
 {
 	return rte_hash_k64_cmp_eq(key1, key2, key_len) ||
@@ -67,7 +67,7 @@ rte_hash_k112_cmp_eq(const void *key1, const void *key2, size_t key_len)
 				(const char *) key2 + 96, key_len);
 }

-static int
+static inline int
 rte_hash_k128_cmp_eq(const void *key1, const void *key2, size_t key_len)
 {
 	return rte_hash_k64_cmp_eq(key1, key2, key_len) ||
diff --git a/lib/ip_frag/ip_frag_common.h b/lib/ip_frag/ip_frag_common.h
index 0d8ce6a1e1..7d6c1aa98d 100644
--- a/lib/ip_frag/ip_frag_common.h
+++ b/lib/ip_frag/ip_frag_common.h
@@ -7,6 +7,14 @@

 #include <sys/queue.h>

+#include <rte_common.h>
+
+#if defined(RTE_ARCH_ARM64)
+#include <rte_cmp_arm64.h>
+#elif defined(RTE_ARCH_X86)
+#include <rte_cmp_x86.h>
+#endif
+
 #include "rte_ip_frag.h"
 #include "ip_reassembly.h"

@@ -75,12 +83,18 @@ ip_frag_key_invalidate(struct ip_frag_key * key)
 static inline uint64_t
 ip_frag_key_cmp(const struct ip_frag_key * k1, const struct ip_frag_key * k2)
 {
+#if defined(RTE_ARCH_X86) || defined(RTE_ARCH_ARM64)
+	return (k1->id_key_len != k2->id_key_len) ||
+	       (k1->key_len == IPV4_KEYLEN ? k1->src_dst[0] != k2->src_dst[0] :
+					     rte_hash_k32_cmp_eq(k1, k2, 32));
+#else
 	uint32_t i;
 	uint64_t val;
 	val = k1->id_key_len ^ k2->id_key_len;
 	for (i = 0; i < k1->key_len; i++)
 		val |= k1->src_dst[i] ^ k2->src_dst[i];
 	return val;
+#endif
 }

 /*
diff --git a/lib/ip_frag/ip_frag_internal.c b/lib/ip_frag/ip_frag_internal.c
index b436a4c931..7cbef647df 100644
--- a/lib/ip_frag/ip_frag_internal.c
+++ b/lib/ip_frag/ip_frag_internal.c
@@ -45,7 +45,7 @@ ipv4_frag_hash(const struct ip_frag_key *key, uint32_t *v1, uint32_t *v2)

 	p = (const uint32_t *)&key->src_dst;

-#ifdef RTE_ARCH_X86
+#if defined(RTE_ARCH_X86) || defined(RTE_ARCH_ARM64)
 	v = rte_hash_crc_4byte(p[0], PRIME_VALUE);
 	v = rte_hash_crc_4byte(p[1], v);
 	v = rte_hash_crc_4byte(key->id, v);
@@ -66,7 +66,7 @@ ipv6_frag_hash(const struct ip_frag_key *key, uint32_t *v1, uint32_t *v2)

 	p = (const uint32_t *) &key->src_dst;

-#ifdef RTE_ARCH_X86
+#if defined(RTE_ARCH_X86) || defined(RTE_ARCH_ARM64)
 	v = rte_hash_crc_4byte(p[0], PRIME_VALUE);
 	v = rte_hash_crc_4byte(p[1], v);
 	v = rte_hash_crc_4byte(p[2], v);
--
2.25.1