-/*-
- * BSD LICENSE
- *
- * Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2016 Intel Corporation
*/
#include <stdio.h>
#include <errno.h>
#include <getopt.h>
#include <stdbool.h>
+#include <netinet/in.h>
#include <rte_debug.h>
#include <rte_ether.h>
#include <rte_ethdev.h>
-#include <rte_ring.h>
-#include <rte_mempool.h>
#include <rte_cycles.h>
#include <rte_mbuf.h>
#include <rte_ip.h>
#include <rte_hash.h>
#include "l3fwd.h"
+#include "l3fwd_event.h"
-#ifdef RTE_MACHINE_CPUFLAG_SSE4_2
+#if defined(RTE_ARCH_X86) || defined(__ARM_FEATURE_CRC32)
+#define EM_HASH_CRC 1
+#endif
+
+#ifdef EM_HASH_CRC
#include <rte_hash_crc.h>
#define DEFAULT_HASH_FUNC rte_hash_crc
#else
#include <rte_jhash.h>
#define DEFAULT_HASH_FUNC rte_jhash
-#endif /* RTE_MACHINE_CPUFLAG_SSE4_2 */
+#endif
#define IPV6_ADDR_LEN 16
uint16_t port_dst;
uint16_t port_src;
uint8_t proto;
-} __attribute__((__packed__));
+} __rte_packed;
union ipv4_5tuple_host {
struct {
uint16_t port_src;
uint16_t port_dst;
};
- __m128i xmm;
+ xmm_t xmm;
};
#define XMM_NUM_IN_IPV6_5TUPLE 3
uint16_t port_dst;
uint16_t port_src;
uint8_t proto;
-} __attribute__((__packed__));
+} __rte_packed;
union ipv6_5tuple_host {
struct {
uint16_t port_dst;
uint64_t reserve;
};
- __m128i xmm[XMM_NUM_IN_IPV6_5TUPLE];
+ xmm_t xmm[XMM_NUM_IN_IPV6_5TUPLE];
};
+
+
struct ipv4_l3fwd_em_route {
struct ipv4_5tuple key;
uint8_t if_out;
uint8_t if_out;
};
-static struct ipv4_l3fwd_em_route ipv4_l3fwd_em_route_array[] = {
- {{IPv4(101, 0, 0, 0), IPv4(100, 10, 0, 1), 101, 11, IPPROTO_TCP}, 0},
- {{IPv4(201, 0, 0, 0), IPv4(200, 20, 0, 1), 102, 12, IPPROTO_TCP}, 1},
- {{IPv4(111, 0, 0, 0), IPv4(100, 30, 0, 1), 101, 11, IPPROTO_TCP}, 2},
- {{IPv4(211, 0, 0, 0), IPv4(200, 40, 0, 1), 102, 12, IPPROTO_TCP}, 3},
+/* 198.18.0.0/16 are set aside for RFC2544 benchmarking (RFC5735).
+ * Use RFC863 Discard Protocol.
+ */
+static const struct ipv4_l3fwd_em_route ipv4_l3fwd_em_route_array[] = {
+ {{RTE_IPV4(198, 18, 0, 0), RTE_IPV4(198, 18, 0, 1), 9, 9, IPPROTO_UDP}, 0},
+ {{RTE_IPV4(198, 18, 1, 0), RTE_IPV4(198, 18, 1, 1), 9, 9, IPPROTO_UDP}, 1},
+ {{RTE_IPV4(198, 18, 2, 0), RTE_IPV4(198, 18, 2, 1), 9, 9, IPPROTO_UDP}, 2},
+ {{RTE_IPV4(198, 18, 3, 0), RTE_IPV4(198, 18, 3, 1), 9, 9, IPPROTO_UDP}, 3},
+ {{RTE_IPV4(198, 18, 4, 0), RTE_IPV4(198, 18, 4, 1), 9, 9, IPPROTO_UDP}, 4},
+ {{RTE_IPV4(198, 18, 5, 0), RTE_IPV4(198, 18, 5, 1), 9, 9, IPPROTO_UDP}, 5},
+ {{RTE_IPV4(198, 18, 6, 0), RTE_IPV4(198, 18, 6, 1), 9, 9, IPPROTO_UDP}, 6},
+ {{RTE_IPV4(198, 18, 7, 0), RTE_IPV4(198, 18, 7, 1), 9, 9, IPPROTO_UDP}, 7},
+ {{RTE_IPV4(198, 18, 8, 0), RTE_IPV4(198, 18, 8, 1), 9, 9, IPPROTO_UDP}, 8},
+ {{RTE_IPV4(198, 18, 9, 0), RTE_IPV4(198, 18, 9, 1), 9, 9, IPPROTO_UDP}, 9},
+ {{RTE_IPV4(198, 18, 10, 0), RTE_IPV4(198, 18, 10, 1), 9, 9, IPPROTO_UDP}, 10},
+ {{RTE_IPV4(198, 18, 11, 0), RTE_IPV4(198, 18, 11, 1), 9, 9, IPPROTO_UDP}, 11},
+ {{RTE_IPV4(198, 18, 12, 0), RTE_IPV4(198, 18, 12, 1), 9, 9, IPPROTO_UDP}, 12},
+ {{RTE_IPV4(198, 18, 13, 0), RTE_IPV4(198, 18, 13, 1), 9, 9, IPPROTO_UDP}, 13},
+ {{RTE_IPV4(198, 18, 14, 0), RTE_IPV4(198, 18, 14, 1), 9, 9, IPPROTO_UDP}, 14},
+ {{RTE_IPV4(198, 18, 15, 0), RTE_IPV4(198, 18, 15, 1), 9, 9, IPPROTO_UDP}, 15},
};
-static struct ipv6_l3fwd_em_route ipv6_l3fwd_em_route_array[] = {
- {{
- {0xfe, 0x80, 0, 0, 0, 0, 0, 0, 0x02, 0x1e, 0x67, 0xff, 0xfe, 0, 0, 0},
- {0xfe, 0x80, 0, 0, 0, 0, 0, 0, 0x02, 0x1b, 0x21, 0xff, 0xfe, 0x91, 0x38, 0x05},
- 101, 11, IPPROTO_TCP}, 0},
-
- {{
- {0xfe, 0x90, 0, 0, 0, 0, 0, 0, 0x02, 0x1e, 0x67, 0xff, 0xfe, 0, 0, 0},
- {0xfe, 0x90, 0, 0, 0, 0, 0, 0, 0x02, 0x1b, 0x21, 0xff, 0xfe, 0x91, 0x38, 0x05},
- 102, 12, IPPROTO_TCP}, 1},
-
- {{
- {0xfe, 0xa0, 0, 0, 0, 0, 0, 0, 0x02, 0x1e, 0x67, 0xff, 0xfe, 0, 0, 0},
- {0xfe, 0xa0, 0, 0, 0, 0, 0, 0, 0x02, 0x1b, 0x21, 0xff, 0xfe, 0x91, 0x38, 0x05},
- 101, 11, IPPROTO_TCP}, 2},
-
- {{
- {0xfe, 0xb0, 0, 0, 0, 0, 0, 0, 0x02, 0x1e, 0x67, 0xff, 0xfe, 0, 0, 0},
- {0xfe, 0xb0, 0, 0, 0, 0, 0, 0, 0x02, 0x1b, 0x21, 0xff, 0xfe, 0x91, 0x38, 0x05},
- 102, 12, IPPROTO_TCP}, 3},
+/* 2001:0200::/48 is IANA reserved range for IPv6 benchmarking (RFC5180).
+ * Use RFC863 Discard Protocol.
+ */
+static const struct ipv6_l3fwd_em_route ipv6_l3fwd_em_route_array[] = {
+ {{{32, 1, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+ {32, 1, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1}, 9, 9, IPPROTO_UDP}, 0},
+ {{{32, 1, 2, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0},
+ {32, 1, 2, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1}, 9, 9, IPPROTO_UDP}, 1},
+ {{{32, 1, 2, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0},
+ {32, 1, 2, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 1}, 9, 9, IPPROTO_UDP}, 2},
+ {{{32, 1, 2, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0},
+ {32, 1, 2, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 1}, 9, 9, IPPROTO_UDP}, 3},
+ {{{32, 1, 2, 0, 0, 0, 0, 4, 0, 0, 0, 0, 0, 0, 0, 0},
+ {32, 1, 2, 0, 0, 0, 0, 4, 0, 0, 0, 0, 0, 0, 0, 1}, 9, 9, IPPROTO_UDP}, 4},
+ {{{32, 1, 2, 0, 0, 0, 0, 5, 0, 0, 0, 0, 0, 0, 0, 0},
+ {32, 1, 2, 0, 0, 0, 0, 5, 0, 0, 0, 0, 0, 0, 0, 1}, 9, 9, IPPROTO_UDP}, 5},
+ {{{32, 1, 2, 0, 0, 0, 0, 6, 0, 0, 0, 0, 0, 0, 0, 0},
+ {32, 1, 2, 0, 0, 0, 0, 6, 0, 0, 0, 0, 0, 0, 0, 1}, 9, 9, IPPROTO_UDP}, 6},
+ {{{32, 1, 2, 0, 0, 0, 0, 7, 0, 0, 0, 0, 0, 0, 0, 0},
+ {32, 1, 2, 0, 0, 0, 0, 7, 0, 0, 0, 0, 0, 0, 0, 1}, 9, 9, IPPROTO_UDP}, 7},
+ {{{32, 1, 2, 0, 0, 0, 0, 8, 0, 0, 0, 0, 0, 0, 0, 0},
+ {32, 1, 2, 0, 0, 0, 0, 8, 0, 0, 0, 0, 0, 0, 0, 1}, 9, 9, IPPROTO_UDP}, 8},
+ {{{32, 1, 2, 0, 0, 0, 0, 9, 0, 0, 0, 0, 0, 0, 0, 0},
+ {32, 1, 2, 0, 0, 0, 0, 9, 0, 0, 0, 0, 0, 0, 0, 1}, 9, 9, IPPROTO_UDP}, 9},
+ {{{32, 1, 2, 0, 0, 0, 0, 10, 0, 0, 0, 0, 0, 0, 0, 0},
+ {32, 1, 2, 0, 0, 0, 0, 10, 0, 0, 0, 0, 0, 0, 0, 1}, 9, 9, IPPROTO_UDP}, 10},
+ {{{32, 1, 2, 0, 0, 0, 0, 11, 0, 0, 0, 0, 0, 0, 0, 0},
+ {32, 1, 2, 0, 0, 0, 0, 11, 0, 0, 0, 0, 0, 0, 0, 1}, 9, 9, IPPROTO_UDP}, 11},
+ {{{32, 1, 2, 0, 0, 0, 0, 12, 0, 0, 0, 0, 0, 0, 0, 0},
+ {32, 1, 2, 0, 0, 0, 0, 12, 0, 0, 0, 0, 0, 0, 0, 1}, 9, 9, IPPROTO_UDP}, 12},
+ {{{32, 1, 2, 0, 0, 0, 0, 13, 0, 0, 0, 0, 0, 0, 0, 0},
+ {32, 1, 2, 0, 0, 0, 0, 13, 0, 0, 0, 0, 0, 0, 0, 1}, 9, 9, IPPROTO_UDP}, 13},
+ {{{32, 1, 2, 0, 0, 0, 0, 14, 0, 0, 0, 0, 0, 0, 0, 0},
+ {32, 1, 2, 0, 0, 0, 0, 14, 0, 0, 0, 0, 0, 0, 0, 1}, 9, 9, IPPROTO_UDP}, 14},
+ {{{32, 1, 2, 0, 0, 0, 0, 15, 0, 0, 0, 0, 0, 0, 0, 0},
+ {32, 1, 2, 0, 0, 0, 0, 15, 0, 0, 0, 0, 0, 0, 0, 1}, 9, 9, IPPROTO_UDP}, 15},
};
struct rte_hash *ipv4_l3fwd_em_lookup_struct[NB_SOCKETS];
t = k->proto;
p = (const uint32_t *)&k->port_src;
-#ifdef RTE_MACHINE_CPUFLAG_SSE4_2
+#ifdef EM_HASH_CRC
init_val = rte_hash_crc_4byte(t, init_val);
init_val = rte_hash_crc_4byte(k->ip_src, init_val);
init_val = rte_hash_crc_4byte(k->ip_dst, init_val);
init_val = rte_hash_crc_4byte(*p, init_val);
-#else /* RTE_MACHINE_CPUFLAG_SSE4_2 */
+#else
init_val = rte_jhash_1word(t, init_val);
init_val = rte_jhash_1word(k->ip_src, init_val);
init_val = rte_jhash_1word(k->ip_dst, init_val);
init_val = rte_jhash_1word(*p, init_val);
-#endif /* RTE_MACHINE_CPUFLAG_SSE4_2 */
+#endif
return init_val;
}
const union ipv6_5tuple_host *k;
uint32_t t;
const uint32_t *p;
-#ifdef RTE_MACHINE_CPUFLAG_SSE4_2
+#ifdef EM_HASH_CRC
const uint32_t *ip_src0, *ip_src1, *ip_src2, *ip_src3;
const uint32_t *ip_dst0, *ip_dst1, *ip_dst2, *ip_dst3;
-#endif /* RTE_MACHINE_CPUFLAG_SSE4_2 */
+#endif
k = data;
t = k->proto;
p = (const uint32_t *)&k->port_src;
-#ifdef RTE_MACHINE_CPUFLAG_SSE4_2
+#ifdef EM_HASH_CRC
ip_src0 = (const uint32_t *) k->ip_src;
ip_src1 = (const uint32_t *)(k->ip_src+4);
ip_src2 = (const uint32_t *)(k->ip_src+8);
init_val = rte_hash_crc_4byte(*ip_dst2, init_val);
init_val = rte_hash_crc_4byte(*ip_dst3, init_val);
init_val = rte_hash_crc_4byte(*p, init_val);
-#else /* RTE_MACHINE_CPUFLAG_SSE4_2 */
+#else
init_val = rte_jhash_1word(t, init_val);
init_val = rte_jhash(k->ip_src,
sizeof(uint8_t) * IPV6_ADDR_LEN, init_val);
init_val = rte_jhash(k->ip_dst,
sizeof(uint8_t) * IPV6_ADDR_LEN, init_val);
init_val = rte_jhash_1word(*p, init_val);
-#endif /* RTE_MACHINE_CPUFLAG_SSE4_2 */
+#endif
return init_val;
}
-#define IPV4_L3FWD_EM_NUM_ROUTES \
- (sizeof(ipv4_l3fwd_em_route_array) / sizeof(ipv4_l3fwd_em_route_array[0]))
+#define IPV4_L3FWD_EM_NUM_ROUTES RTE_DIM(ipv4_l3fwd_em_route_array)
-#define IPV6_L3FWD_EM_NUM_ROUTES \
- (sizeof(ipv6_l3fwd_em_route_array) / sizeof(ipv6_l3fwd_em_route_array[0]))
+#define IPV6_L3FWD_EM_NUM_ROUTES RTE_DIM(ipv6_l3fwd_em_route_array)
static uint8_t ipv4_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned;
static uint8_t ipv6_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned;
-static __m128i mask0;
-static __m128i mask1;
-static __m128i mask2;
+static rte_xmm_t mask0;
+static rte_xmm_t mask1;
+static rte_xmm_t mask2;
-static inline uint8_t
-em_get_ipv4_dst_port(void *ipv4_hdr, uint8_t portid, void *lookup_struct)
+#if defined(__SSE2__)
+static inline xmm_t
+em_mask_key(void *key, xmm_t mask)
+{
+ __m128i data = _mm_loadu_si128((__m128i *)(key));
+
+ return _mm_and_si128(data, mask);
+}
+#elif defined(__ARM_NEON)
+static inline xmm_t
+em_mask_key(void *key, xmm_t mask)
+{
+ int32x4_t data = vld1q_s32((int32_t *)key);
+
+ return vandq_s32(data, mask);
+}
+#elif defined(__ALTIVEC__)
+static inline xmm_t
+em_mask_key(void *key, xmm_t mask)
+{
+ xmm_t data = vec_ld(0, (xmm_t *)(key));
+
+ return vec_and(data, mask);
+}
+#else
+#error No vector engine (SSE, NEON, ALTIVEC) available, check your toolchain
+#endif
+
+/* Performing hash-based lookups. 8< */
+static inline uint16_t
+em_get_ipv4_dst_port(void *ipv4_hdr, uint16_t portid, void *lookup_struct)
{
int ret = 0;
union ipv4_5tuple_host key;
struct rte_hash *ipv4_l3fwd_lookup_struct =
(struct rte_hash *)lookup_struct;
- ipv4_hdr = (uint8_t *)ipv4_hdr + offsetof(struct ipv4_hdr, time_to_live);
- __m128i data = _mm_loadu_si128((__m128i *)(ipv4_hdr));
+ ipv4_hdr = (uint8_t *)ipv4_hdr +
+ offsetof(struct rte_ipv4_hdr, time_to_live);
/*
* Get 5 tuple: dst port, src port, dst IP address,
* src IP address and protocol.
*/
- key.xmm = _mm_and_si128(data, mask0);
+ key.xmm = em_mask_key(ipv4_hdr, mask0.x);
/* Find destination port */
ret = rte_hash_lookup(ipv4_l3fwd_lookup_struct, (const void *)&key);
- return (uint8_t)((ret < 0) ? portid : ipv4_l3fwd_out_if[ret]);
+ return (ret < 0) ? portid : ipv4_l3fwd_out_if[ret];
}
+/* >8 End of performing hash-based lookups. */
-static inline uint8_t
-em_get_ipv6_dst_port(void *ipv6_hdr, uint8_t portid, void *lookup_struct)
+static inline uint16_t
+em_get_ipv6_dst_port(void *ipv6_hdr, uint16_t portid, void *lookup_struct)
{
int ret = 0;
union ipv6_5tuple_host key;
struct rte_hash *ipv6_l3fwd_lookup_struct =
(struct rte_hash *)lookup_struct;
- ipv6_hdr = (uint8_t *)ipv6_hdr + offsetof(struct ipv6_hdr, payload_len);
- __m128i data0 =
- _mm_loadu_si128((__m128i *)(ipv6_hdr));
- __m128i data1 =
- _mm_loadu_si128((__m128i *)(((uint8_t *)ipv6_hdr)+
- sizeof(__m128i)));
- __m128i data2 =
- _mm_loadu_si128((__m128i *)(((uint8_t *)ipv6_hdr)+
- sizeof(__m128i)+sizeof(__m128i)));
+ ipv6_hdr = (uint8_t *)ipv6_hdr +
+ offsetof(struct rte_ipv6_hdr, payload_len);
+ void *data0 = ipv6_hdr;
+ void *data1 = ((uint8_t *)ipv6_hdr) + sizeof(xmm_t);
+ void *data2 = ((uint8_t *)ipv6_hdr) + sizeof(xmm_t) + sizeof(xmm_t);
/* Get part of 5 tuple: src IP address lower 96 bits and protocol */
- key.xmm[0] = _mm_and_si128(data0, mask1);
+ key.xmm[0] = em_mask_key(data0, mask1.x);
/*
* Get part of 5 tuple: dst IP address lower 96 bits
* and src IP address higher 32 bits.
*/
- key.xmm[1] = data1;
+#if defined RTE_ARCH_X86
+ key.xmm[1] = _mm_loadu_si128(data1);
+#else
+ key.xmm[1] = *(xmm_t *)data1;
+#endif
/*
* Get part of 5 tuple: dst port and src port
* and dst IP address higher 32 bits.
*/
- key.xmm[2] = _mm_and_si128(data2, mask2);
+ key.xmm[2] = em_mask_key(data2, mask2.x);
/* Find destination port */
ret = rte_hash_lookup(ipv6_l3fwd_lookup_struct, (const void *)&key);
- return (uint8_t)((ret < 0) ? portid : ipv6_l3fwd_out_if[ret]);
+ return (ret < 0) ? portid : ipv6_l3fwd_out_if[ret];
}
-/*
- * Include header file if SSE4_1 is enabled for
- * buffer optimization i.e. ENABLE_MULTI_BUFFER_OPTIMIZE=1.
- */
-#if defined(__SSE4_1__)
-#ifndef HASH_MULTI_LOOKUP
-#include "l3fwd_em_sse.h"
+#if defined RTE_ARCH_X86 || defined __ARM_NEON
+#if defined(NO_HASH_MULTI_LOOKUP)
+#include "l3fwd_em_sequential.h"
#else
-#include "l3fwd_em_hlm_sse.h"
+#include "l3fwd_em_hlm.h"
#endif
#else
#include "l3fwd_em.h"
#define BYTE_VALUE_MAX 256
#define ALL_32_BITS 0xffffffff
#define BIT_8_TO_15 0x0000ff00
+
static inline void
populate_ipv4_few_flow_into_table(const struct rte_hash *h)
{
uint32_t i;
int32_t ret;
- mask0 = _mm_set_epi32(ALL_32_BITS, ALL_32_BITS,
- ALL_32_BITS, BIT_8_TO_15);
+ mask0 = (rte_xmm_t){.u32 = {BIT_8_TO_15, ALL_32_BITS,
+ ALL_32_BITS, ALL_32_BITS} };
for (i = 0; i < IPV4_L3FWD_EM_NUM_ROUTES; i++) {
struct ipv4_l3fwd_em_route entry;
uint32_t i;
int32_t ret;
- mask1 = _mm_set_epi32(ALL_32_BITS, ALL_32_BITS,
- ALL_32_BITS, BIT_16_TO_23);
+ mask1 = (rte_xmm_t){.u32 = {BIT_16_TO_23, ALL_32_BITS,
+ ALL_32_BITS, ALL_32_BITS} };
- mask2 = _mm_set_epi32(0, 0, ALL_32_BITS, ALL_32_BITS);
+ mask2 = (rte_xmm_t){.u32 = {ALL_32_BITS, ALL_32_BITS, 0, 0} };
for (i = 0; i < IPV6_L3FWD_EM_NUM_ROUTES; i++) {
struct ipv6_l3fwd_em_route entry;
(uint64_t)IPV6_L3FWD_EM_NUM_ROUTES);
}
-#define NUMBER_PORT_USED 4
+#define NUMBER_PORT_USED 16
static inline void
populate_ipv4_many_flow_into_table(const struct rte_hash *h,
unsigned int nr_flow)
{
unsigned i;
- mask0 = _mm_set_epi32(ALL_32_BITS, ALL_32_BITS,
- ALL_32_BITS, BIT_8_TO_15);
+ mask0 = (rte_xmm_t){.u32 = {BIT_8_TO_15, ALL_32_BITS,
+ ALL_32_BITS, ALL_32_BITS} };
for (i = 0; i < nr_flow; i++) {
+ uint8_t port = i % NUMBER_PORT_USED;
struct ipv4_l3fwd_em_route entry;
union ipv4_5tuple_host newkey;
- uint8_t a = (uint8_t)
- ((i/NUMBER_PORT_USED)%BYTE_VALUE_MAX);
- uint8_t b = (uint8_t)
- (((i/NUMBER_PORT_USED)/BYTE_VALUE_MAX)%BYTE_VALUE_MAX);
- uint8_t c = (uint8_t)
- ((i/NUMBER_PORT_USED)/(BYTE_VALUE_MAX*BYTE_VALUE_MAX));
+ uint8_t a = (uint8_t)((port + 1) % BYTE_VALUE_MAX);
/* Create the ipv4 exact match flow */
memset(&entry, 0, sizeof(entry));
- switch (i & (NUMBER_PORT_USED - 1)) {
- case 0:
- entry = ipv4_l3fwd_em_route_array[0];
- entry.key.ip_dst = IPv4(101, c, b, a);
- break;
- case 1:
- entry = ipv4_l3fwd_em_route_array[1];
- entry.key.ip_dst = IPv4(201, c, b, a);
- break;
- case 2:
- entry = ipv4_l3fwd_em_route_array[2];
- entry.key.ip_dst = IPv4(111, c, b, a);
- break;
- case 3:
- entry = ipv4_l3fwd_em_route_array[3];
- entry.key.ip_dst = IPv4(211, c, b, a);
- break;
- };
+ entry = ipv4_l3fwd_em_route_array[port];
+ entry.key.ip_dst = RTE_IPV4(198, 18, port, a);
convert_ipv4_5tuple(&entry.key, &newkey);
int32_t ret = rte_hash_add_key(h, (void *) &newkey);
{
unsigned i;
- mask1 = _mm_set_epi32(ALL_32_BITS, ALL_32_BITS,
- ALL_32_BITS, BIT_16_TO_23);
- mask2 = _mm_set_epi32(0, 0, ALL_32_BITS, ALL_32_BITS);
+ mask1 = (rte_xmm_t){.u32 = {BIT_16_TO_23, ALL_32_BITS,
+ ALL_32_BITS, ALL_32_BITS} };
+ mask2 = (rte_xmm_t){.u32 = {ALL_32_BITS, ALL_32_BITS, 0, 0} };
for (i = 0; i < nr_flow; i++) {
+ uint8_t port = i % NUMBER_PORT_USED;
struct ipv6_l3fwd_em_route entry;
union ipv6_5tuple_host newkey;
- uint8_t a = (uint8_t)
- ((i/NUMBER_PORT_USED)%BYTE_VALUE_MAX);
- uint8_t b = (uint8_t)
- (((i/NUMBER_PORT_USED)/BYTE_VALUE_MAX)%BYTE_VALUE_MAX);
- uint8_t c = (uint8_t)
- ((i/NUMBER_PORT_USED)/(BYTE_VALUE_MAX*BYTE_VALUE_MAX));
-
/* Create the ipv6 exact match flow */
memset(&entry, 0, sizeof(entry));
- switch (i & (NUMBER_PORT_USED - 1)) {
- case 0:
- entry = ipv6_l3fwd_em_route_array[0];
- break;
- case 1:
- entry = ipv6_l3fwd_em_route_array[1];
- break;
- case 2:
- entry = ipv6_l3fwd_em_route_array[2];
- break;
- case 3:
- entry = ipv6_l3fwd_em_route_array[3];
- break;
- };
- entry.key.ip_dst[13] = c;
- entry.key.ip_dst[14] = b;
- entry.key.ip_dst[15] = a;
+ entry = ipv6_l3fwd_em_route_array[port];
+ entry.key.ip_dst[15] = (port + 1) % BYTE_VALUE_MAX;
convert_ipv6_5tuple(&entry.key, &newkey);
int32_t ret = rte_hash_add_key(h, (void *) &newkey);
printf("Hash: Adding 0x%x keys\n", nr_flow);
}
+/* Requirements:
+ * 1. IP packets without extension;
+ * 2. L4 payload should be either TCP or UDP.
+ */
+int
+em_check_ptype(int portid)
+{
+ int i, ret;
+ int ptype_l3_ipv4_ext = 0;
+ int ptype_l3_ipv6_ext = 0;
+ int ptype_l4_tcp = 0;
+ int ptype_l4_udp = 0;
+ uint32_t ptype_mask = RTE_PTYPE_L3_MASK | RTE_PTYPE_L4_MASK;
+
+ ret = rte_eth_dev_get_supported_ptypes(portid, ptype_mask, NULL, 0);
+ if (ret <= 0)
+ return 0;
+
+ uint32_t ptypes[ret];
+
+ ret = rte_eth_dev_get_supported_ptypes(portid, ptype_mask, ptypes, ret);
+ for (i = 0; i < ret; ++i) {
+ switch (ptypes[i]) {
+ case RTE_PTYPE_L3_IPV4_EXT:
+ ptype_l3_ipv4_ext = 1;
+ break;
+ case RTE_PTYPE_L3_IPV6_EXT:
+ ptype_l3_ipv6_ext = 1;
+ break;
+ case RTE_PTYPE_L4_TCP:
+ ptype_l4_tcp = 1;
+ break;
+ case RTE_PTYPE_L4_UDP:
+ ptype_l4_udp = 1;
+ break;
+ }
+ }
+
+ if (ptype_l3_ipv4_ext == 0)
+ printf("port %d cannot parse RTE_PTYPE_L3_IPV4_EXT\n", portid);
+ if (ptype_l3_ipv6_ext == 0)
+ printf("port %d cannot parse RTE_PTYPE_L3_IPV6_EXT\n", portid);
+ if (!ptype_l3_ipv4_ext || !ptype_l3_ipv6_ext)
+ return 0;
+
+ if (ptype_l4_tcp == 0)
+ printf("port %d cannot parse RTE_PTYPE_L4_TCP\n", portid);
+ if (ptype_l4_udp == 0)
+ printf("port %d cannot parse RTE_PTYPE_L4_UDP\n", portid);
+ if (ptype_l4_tcp && ptype_l4_udp)
+ return 1;
+
+ return 0;
+}
+
+static inline void
+em_parse_ptype(struct rte_mbuf *m)
+{
+ struct rte_ether_hdr *eth_hdr;
+ uint32_t packet_type = RTE_PTYPE_UNKNOWN;
+ uint16_t ether_type;
+ void *l3;
+ int hdr_len;
+ struct rte_ipv4_hdr *ipv4_hdr;
+ struct rte_ipv6_hdr *ipv6_hdr;
+
+ eth_hdr = rte_pktmbuf_mtod(m, struct rte_ether_hdr *);
+ ether_type = eth_hdr->ether_type;
+ l3 = (uint8_t *)eth_hdr + sizeof(struct rte_ether_hdr);
+ if (ether_type == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV4)) {
+ ipv4_hdr = (struct rte_ipv4_hdr *)l3;
+ hdr_len = rte_ipv4_hdr_len(ipv4_hdr);
+ if (hdr_len == sizeof(struct rte_ipv4_hdr)) {
+ packet_type |= RTE_PTYPE_L3_IPV4;
+ if (ipv4_hdr->next_proto_id == IPPROTO_TCP)
+ packet_type |= RTE_PTYPE_L4_TCP;
+ else if (ipv4_hdr->next_proto_id == IPPROTO_UDP)
+ packet_type |= RTE_PTYPE_L4_UDP;
+ } else
+ packet_type |= RTE_PTYPE_L3_IPV4_EXT;
+ } else if (ether_type == rte_cpu_to_be_16(RTE_ETHER_TYPE_IPV6)) {
+ ipv6_hdr = (struct rte_ipv6_hdr *)l3;
+ if (ipv6_hdr->proto == IPPROTO_TCP)
+ packet_type |= RTE_PTYPE_L3_IPV6 | RTE_PTYPE_L4_TCP;
+ else if (ipv6_hdr->proto == IPPROTO_UDP)
+ packet_type |= RTE_PTYPE_L3_IPV6 | RTE_PTYPE_L4_UDP;
+ else
+ packet_type |= RTE_PTYPE_L3_IPV6_EXT_UNKNOWN;
+ }
+
+ m->packet_type = packet_type;
+}
+
+uint16_t
+em_cb_parse_ptype(uint16_t port __rte_unused, uint16_t queue __rte_unused,
+ struct rte_mbuf *pkts[], uint16_t nb_pkts,
+ uint16_t max_pkts __rte_unused,
+ void *user_param __rte_unused)
+{
+ unsigned i;
+
+ for (i = 0; i < nb_pkts; ++i)
+ em_parse_ptype(pkts[i]);
+
+ return nb_pkts;
+}
+
/* main processing loop */
int
-em_main_loop(__attribute__((unused)) void *dummy)
+em_main_loop(__rte_unused void *dummy)
{
struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
unsigned lcore_id;
uint64_t prev_tsc, diff_tsc, cur_tsc;
int i, nb_rx;
- uint8_t portid, queueid;
+ uint8_t queueid;
+ uint16_t portid;
struct lcore_conf *qconf;
const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) /
US_PER_S * BURST_TX_DRAIN_US;
- prev_tsc = 0;
-
lcore_id = rte_lcore_id();
qconf = &lcore_conf[lcore_id];
- if (qconf->n_rx_queue == 0) {
+ const uint16_t n_rx_q = qconf->n_rx_queue;
+ const uint16_t n_tx_p = qconf->n_tx_port;
+ if (n_rx_q == 0) {
RTE_LOG(INFO, L3FWD, "lcore %u has nothing to do\n", lcore_id);
return 0;
}
RTE_LOG(INFO, L3FWD, "entering main loop on lcore %u\n", lcore_id);
- for (i = 0; i < qconf->n_rx_queue; i++) {
+ for (i = 0; i < n_rx_q; i++) {
portid = qconf->rx_queue_list[i].port_id;
queueid = qconf->rx_queue_list[i].queue_id;
RTE_LOG(INFO, L3FWD,
- " -- lcoreid=%u portid=%hhu rxqueueid=%hhu\n",
+ " -- lcoreid=%u portid=%u rxqueueid=%hhu\n",
lcore_id, portid, queueid);
}
- while (!force_quit) {
+ cur_tsc = rte_rdtsc();
+ prev_tsc = cur_tsc;
- cur_tsc = rte_rdtsc();
+ while (!force_quit) {
/*
* TX burst queue drain
diff_tsc = cur_tsc - prev_tsc;
if (unlikely(diff_tsc > drain_tsc)) {
- for (i = 0; i < qconf->n_rx_queue; i++) {
- portid = qconf->rx_queue_list[i].port_id;
+ for (i = 0; i < n_tx_p; ++i) {
+ portid = qconf->tx_port_id[i];
if (qconf->tx_mbufs[portid].len == 0)
continue;
send_burst(qconf,
/*
* Read packet from RX queues
*/
- for (i = 0; i < qconf->n_rx_queue; ++i) {
+ for (i = 0; i < n_rx_q; ++i) {
portid = qconf->rx_queue_list[i].port_id;
queueid = qconf->rx_queue_list[i].queue_id;
nb_rx = rte_eth_rx_burst(portid, queueid, pkts_burst,
if (nb_rx == 0)
continue;
- /*
- * For SSE4_1 use ENABLE_MULTI_BUFFER_OPTIMIZE=1
- * code.
- */
-#if defined(__SSE4_1__)
+#if defined RTE_ARCH_X86 || defined __ARM_NEON
l3fwd_em_send_packets(nb_rx, pkts_burst,
portid, qconf);
#else
l3fwd_em_no_opt_send_packets(nb_rx, pkts_burst,
portid, qconf);
-#endif /* __SSE_4_1__ */
+#endif
}
+
+ cur_tsc = rte_rdtsc();
}
return 0;
}
-/*
- * Initialize exact match (hash) parameters.
- */
+static __rte_always_inline void
+em_event_loop_single(struct l3fwd_event_resources *evt_rsrc,
+ const uint8_t flags)
+{
+ const int event_p_id = l3fwd_get_free_event_port(evt_rsrc);
+ const uint8_t tx_q_id = evt_rsrc->evq.event_q_id[
+ evt_rsrc->evq.nb_queues - 1];
+ const uint8_t event_d_id = evt_rsrc->event_d_id;
+ struct lcore_conf *lconf;
+ unsigned int lcore_id;
+ struct rte_event ev;
+
+ if (event_p_id < 0)
+ return;
+
+ lcore_id = rte_lcore_id();
+ lconf = &lcore_conf[lcore_id];
+
+ RTE_LOG(INFO, L3FWD, "entering %s on lcore %u\n", __func__, lcore_id);
+ while (!force_quit) {
+ if (!rte_event_dequeue_burst(event_d_id, event_p_id, &ev, 1, 0))
+ continue;
+
+ struct rte_mbuf *mbuf = ev.mbuf;
+
+#if defined RTE_ARCH_X86 || defined __ARM_NEON
+ mbuf->port = em_get_dst_port(lconf, mbuf, mbuf->port);
+ process_packet(mbuf, &mbuf->port);
+#else
+ l3fwd_em_simple_process(mbuf, lconf);
+#endif
+ if (mbuf->port == BAD_PORT) {
+ rte_pktmbuf_free(mbuf);
+ continue;
+ }
+
+ if (flags & L3FWD_EVENT_TX_ENQ) {
+ ev.queue_id = tx_q_id;
+ ev.op = RTE_EVENT_OP_FORWARD;
+ while (rte_event_enqueue_burst(event_d_id, event_p_id,
+ &ev, 1) && !force_quit)
+ ;
+ }
+
+ if (flags & L3FWD_EVENT_TX_DIRECT) {
+ rte_event_eth_tx_adapter_txq_set(mbuf, 0);
+ while (!rte_event_eth_tx_adapter_enqueue(event_d_id,
+ event_p_id, &ev, 1, 0) &&
+ !force_quit)
+ ;
+ }
+ }
+}
+
+static __rte_always_inline void
+em_event_loop_burst(struct l3fwd_event_resources *evt_rsrc,
+ const uint8_t flags)
+{
+ const int event_p_id = l3fwd_get_free_event_port(evt_rsrc);
+ const uint8_t tx_q_id = evt_rsrc->evq.event_q_id[
+ evt_rsrc->evq.nb_queues - 1];
+ const uint8_t event_d_id = evt_rsrc->event_d_id;
+ const uint16_t deq_len = evt_rsrc->deq_depth;
+ struct rte_event events[MAX_PKT_BURST];
+ struct lcore_conf *lconf;
+ unsigned int lcore_id;
+ int i, nb_enq, nb_deq;
+
+ if (event_p_id < 0)
+ return;
+
+ lcore_id = rte_lcore_id();
+
+ lconf = &lcore_conf[lcore_id];
+
+ RTE_LOG(INFO, L3FWD, "entering %s on lcore %u\n", __func__, lcore_id);
+
+ while (!force_quit) {
+ /* Read events from RX queues */
+ nb_deq = rte_event_dequeue_burst(event_d_id, event_p_id,
+ events, deq_len, 0);
+ if (nb_deq == 0) {
+ rte_pause();
+ continue;
+ }
+
+#if defined RTE_ARCH_X86 || defined __ARM_NEON
+ l3fwd_em_process_events(nb_deq, (struct rte_event **)&events,
+ lconf);
+#else
+ l3fwd_em_no_opt_process_events(nb_deq,
+ (struct rte_event **)&events,
+ lconf);
+#endif
+ for (i = 0; i < nb_deq; i++) {
+ if (flags & L3FWD_EVENT_TX_ENQ) {
+ events[i].queue_id = tx_q_id;
+ events[i].op = RTE_EVENT_OP_FORWARD;
+ }
+
+ if (flags & L3FWD_EVENT_TX_DIRECT)
+ rte_event_eth_tx_adapter_txq_set(events[i].mbuf,
+ 0);
+ }
+
+ if (flags & L3FWD_EVENT_TX_ENQ) {
+ nb_enq = rte_event_enqueue_burst(event_d_id, event_p_id,
+ events, nb_deq);
+ while (nb_enq < nb_deq && !force_quit)
+ nb_enq += rte_event_enqueue_burst(event_d_id,
+ event_p_id, events + nb_enq,
+ nb_deq - nb_enq);
+ }
+
+ if (flags & L3FWD_EVENT_TX_DIRECT) {
+ nb_enq = rte_event_eth_tx_adapter_enqueue(event_d_id,
+ event_p_id, events, nb_deq, 0);
+ while (nb_enq < nb_deq && !force_quit)
+ nb_enq += rte_event_eth_tx_adapter_enqueue(
+ event_d_id, event_p_id,
+ events + nb_enq,
+ nb_deq - nb_enq, 0);
+ }
+ }
+}
+
+static __rte_always_inline void
+em_event_loop(struct l3fwd_event_resources *evt_rsrc,
+ const uint8_t flags)
+{
+ if (flags & L3FWD_EVENT_SINGLE)
+ em_event_loop_single(evt_rsrc, flags);
+ if (flags & L3FWD_EVENT_BURST)
+ em_event_loop_burst(evt_rsrc, flags);
+}
+
+int __rte_noinline
+em_event_main_loop_tx_d(__rte_unused void *dummy)
+{
+ struct l3fwd_event_resources *evt_rsrc =
+ l3fwd_get_eventdev_rsrc();
+
+ em_event_loop(evt_rsrc, L3FWD_EVENT_TX_DIRECT | L3FWD_EVENT_SINGLE);
+ return 0;
+}
+
+int __rte_noinline
+em_event_main_loop_tx_d_burst(__rte_unused void *dummy)
+{
+ struct l3fwd_event_resources *evt_rsrc =
+ l3fwd_get_eventdev_rsrc();
+
+ em_event_loop(evt_rsrc, L3FWD_EVENT_TX_DIRECT | L3FWD_EVENT_BURST);
+ return 0;
+}
+
+int __rte_noinline
+em_event_main_loop_tx_q(__rte_unused void *dummy)
+{
+ struct l3fwd_event_resources *evt_rsrc =
+ l3fwd_get_eventdev_rsrc();
+
+ em_event_loop(evt_rsrc, L3FWD_EVENT_TX_ENQ | L3FWD_EVENT_SINGLE);
+ return 0;
+}
+
+int __rte_noinline
+em_event_main_loop_tx_q_burst(__rte_unused void *dummy)
+{
+ struct l3fwd_event_resources *evt_rsrc =
+ l3fwd_get_eventdev_rsrc();
+
+ em_event_loop(evt_rsrc, L3FWD_EVENT_TX_ENQ | L3FWD_EVENT_BURST);
+ return 0;
+}
+
+/* Same eventdev loop for single and burst of vector */
+static __rte_always_inline void
+em_event_loop_vector(struct l3fwd_event_resources *evt_rsrc,
+ const uint8_t flags)
+{
+ const int event_p_id = l3fwd_get_free_event_port(evt_rsrc);
+ const uint8_t tx_q_id =
+ evt_rsrc->evq.event_q_id[evt_rsrc->evq.nb_queues - 1];
+ const uint8_t event_d_id = evt_rsrc->event_d_id;
+ const uint16_t deq_len = evt_rsrc->deq_depth;
+ struct rte_event events[MAX_PKT_BURST];
+ struct lcore_conf *lconf;
+ unsigned int lcore_id;
+ int i, nb_enq, nb_deq;
+
+ if (event_p_id < 0)
+ return;
+
+ lcore_id = rte_lcore_id();
+ lconf = &lcore_conf[lcore_id];
+
+ RTE_LOG(INFO, L3FWD, "entering %s on lcore %u\n", __func__, lcore_id);
+
+ while (!force_quit) {
+ /* Read events from RX queues */
+ nb_deq = rte_event_dequeue_burst(event_d_id, event_p_id, events,
+ deq_len, 0);
+ if (nb_deq == 0) {
+ rte_pause();
+ continue;
+ }
+
+ for (i = 0; i < nb_deq; i++) {
+ if (flags & L3FWD_EVENT_TX_ENQ) {
+ events[i].queue_id = tx_q_id;
+ events[i].op = RTE_EVENT_OP_FORWARD;
+ }
+
+#if defined RTE_ARCH_X86 || defined __ARM_NEON
+ l3fwd_em_process_event_vector(events[i].vec, lconf);
+#else
+ l3fwd_em_no_opt_process_event_vector(events[i].vec,
+ lconf);
+#endif
+ if (flags & L3FWD_EVENT_TX_DIRECT)
+ event_vector_txq_set(events[i].vec, 0);
+ }
+
+ if (flags & L3FWD_EVENT_TX_ENQ) {
+ nb_enq = rte_event_enqueue_burst(event_d_id, event_p_id,
+ events, nb_deq);
+ while (nb_enq < nb_deq && !force_quit)
+ nb_enq += rte_event_enqueue_burst(
+ event_d_id, event_p_id, events + nb_enq,
+ nb_deq - nb_enq);
+ }
+
+ if (flags & L3FWD_EVENT_TX_DIRECT) {
+ nb_enq = rte_event_eth_tx_adapter_enqueue(
+ event_d_id, event_p_id, events, nb_deq, 0);
+ while (nb_enq < nb_deq && !force_quit)
+ nb_enq += rte_event_eth_tx_adapter_enqueue(
+ event_d_id, event_p_id, events + nb_enq,
+ nb_deq - nb_enq, 0);
+ }
+ }
+}
+
+int __rte_noinline
+em_event_main_loop_tx_d_vector(__rte_unused void *dummy)
+{
+ struct l3fwd_event_resources *evt_rsrc = l3fwd_get_eventdev_rsrc();
+
+ em_event_loop_vector(evt_rsrc, L3FWD_EVENT_TX_DIRECT);
+ return 0;
+}
+
+int __rte_noinline
+em_event_main_loop_tx_d_burst_vector(__rte_unused void *dummy)
+{
+ struct l3fwd_event_resources *evt_rsrc = l3fwd_get_eventdev_rsrc();
+
+ em_event_loop_vector(evt_rsrc, L3FWD_EVENT_TX_DIRECT);
+ return 0;
+}
+
+int __rte_noinline
+em_event_main_loop_tx_q_vector(__rte_unused void *dummy)
+{
+ struct l3fwd_event_resources *evt_rsrc = l3fwd_get_eventdev_rsrc();
+
+ em_event_loop_vector(evt_rsrc, L3FWD_EVENT_TX_ENQ);
+ return 0;
+}
+
+int __rte_noinline
+em_event_main_loop_tx_q_burst_vector(__rte_unused void *dummy)
+{
+ struct l3fwd_event_resources *evt_rsrc = l3fwd_get_eventdev_rsrc();
+
+ em_event_loop_vector(evt_rsrc, L3FWD_EVENT_TX_ENQ);
+ return 0;
+}
+
+/* Initialize exact match (hash) parameters. 8< */
void
setup_hash(const int socketid)
{
}
}
}
+/* >8 End of initialization of hash parameters. */
/* Return ipv4/ipv6 em fwd lookup struct. */
void *
git.droids-corp.org / dpdk.git / blobdiff