/*-
* BSD LICENSE
- *
+ *
* Copyright(c) 2010-2014 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
* * 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
#include <stdlib.h>
#include <errno.h>
#include <sys/queue.h>
-#include <cmdline_parse.h>
#include <rte_common.h>
#include <rte_cycles.h>
#include "test.h"
-#ifdef RTE_LIBRTE_LPM
-
#include "rte_lpm.h"
#include "test_lpm_routes.h"
} \
} while(0)
-typedef int32_t (* rte_lpm_test)(void);
+typedef int32_t (*rte_lpm_test)(void);
static int32_t test0(void);
static int32_t test1(void);
{
struct rte_lpm *lpm = NULL;
- lpm = rte_lpm_create(__func__, SOCKET_ID_ANY, MAX_RULES, RTE_LPM_HEAP);
+ lpm = rte_lpm_create(__func__, SOCKET_ID_ANY, MAX_RULES, 0);
TEST_LPM_ASSERT(lpm != NULL);
rte_lpm_free(lpm);
test3(void)
{
struct rte_lpm *lpm = NULL;
- uint32_t ip = IPv4(0, 0, 0, 0);
- uint8_t depth = 24, next_hop = 100;
+ uint32_t ip = IPv4(0, 0, 0, 0), next_hop = 100;
+ uint8_t depth = 24;
int32_t status = 0;
/* rte_lpm_add: lpm == NULL */
{
#if defined(RTE_LIBRTE_LPM_DEBUG)
struct rte_lpm *lpm = NULL;
- uint32_t ip = IPv4(0, 0, 0, 0);
- uint8_t next_hop_return = 0;
+ uint32_t ip = IPv4(0, 0, 0, 0), next_hop_return = 0;
int32_t status = 0;
/* rte_lpm_lookup: lpm == NULL */
test6(void)
{
struct rte_lpm *lpm = NULL;
- uint32_t ip = IPv4(0, 0, 0, 0);
- uint8_t depth = 24, next_hop_add = 100, next_hop_return = 0;
+ uint32_t ip = IPv4(0, 0, 0, 0), next_hop_add = 100, next_hop_return = 0;
+ uint8_t depth = 24;
int32_t status = 0;
lpm = rte_lpm_create(__func__, SOCKET_ID_ANY, MAX_RULES, 0);
int32_t
test7(void)
{
+ __m128i ipx4;
+ uint32_t hop[4];
struct rte_lpm *lpm = NULL;
- uint32_t ip = IPv4(0, 0, 0, 0);
- uint8_t depth = 32, next_hop_add = 100, next_hop_return = 0;
+ uint32_t ip = IPv4(0, 0, 0, 0), next_hop_add = 100, next_hop_return = 0;
+ uint8_t depth = 32;
int32_t status = 0;
lpm = rte_lpm_create(__func__, SOCKET_ID_ANY, MAX_RULES, 0);
status = rte_lpm_lookup(lpm, ip, &next_hop_return);
TEST_LPM_ASSERT((status == 0) && (next_hop_return == next_hop_add));
+ ipx4 = _mm_set_epi32(ip, ip + 0x100, ip - 0x100, ip);
+ rte_lpm_lookupx4(lpm, ipx4, hop, UINT32_MAX);
+ TEST_LPM_ASSERT(hop[0] == next_hop_add);
+ TEST_LPM_ASSERT(hop[1] == UINT32_MAX);
+ TEST_LPM_ASSERT(hop[2] == UINT32_MAX);
+ TEST_LPM_ASSERT(hop[3] == next_hop_add);
+
status = rte_lpm_delete(lpm, ip, depth);
TEST_LPM_ASSERT(status == 0);
int32_t
test8(void)
{
+ __m128i ipx4;
+ uint32_t hop[4];
struct rte_lpm *lpm = NULL;
uint32_t ip1 = IPv4(127, 255, 255, 255), ip2 = IPv4(128, 0, 0, 0);
- uint8_t depth, next_hop_add, next_hop_return;
+ uint32_t next_hop_add, next_hop_return;
+ uint8_t depth;
int32_t status = 0;
lpm = rte_lpm_create(__func__, SOCKET_ID_ANY, MAX_RULES, 0);
status = rte_lpm_lookup(lpm, ip2, &next_hop_return);
TEST_LPM_ASSERT((status == 0) &&
(next_hop_return == next_hop_add));
+
+ ipx4 = _mm_set_epi32(ip2, ip1, ip2, ip1);
+ rte_lpm_lookupx4(lpm, ipx4, hop, UINT32_MAX);
+ TEST_LPM_ASSERT(hop[0] == UINT32_MAX);
+ TEST_LPM_ASSERT(hop[1] == next_hop_add);
+ TEST_LPM_ASSERT(hop[2] == UINT32_MAX);
+ TEST_LPM_ASSERT(hop[3] == next_hop_add);
}
/* Loop with rte_lpm_delete. */
if (depth != 1) {
TEST_LPM_ASSERT((status == 0) &&
(next_hop_return == next_hop_add));
- }
- else {
+ } else {
TEST_LPM_ASSERT(status == -ENOENT);
}
status = rte_lpm_lookup(lpm, ip1, &next_hop_return);
TEST_LPM_ASSERT(status == -ENOENT);
+
+ ipx4 = _mm_set_epi32(ip1, ip1, ip2, ip2);
+ rte_lpm_lookupx4(lpm, ipx4, hop, UINT32_MAX);
+ if (depth != 1) {
+ TEST_LPM_ASSERT(hop[0] == next_hop_add);
+ TEST_LPM_ASSERT(hop[1] == next_hop_add);
+ } else {
+ TEST_LPM_ASSERT(hop[0] == UINT32_MAX);
+ TEST_LPM_ASSERT(hop[1] == UINT32_MAX);
+ }
+ TEST_LPM_ASSERT(hop[2] == UINT32_MAX);
+ TEST_LPM_ASSERT(hop[3] == UINT32_MAX);
}
rte_lpm_free(lpm);
{
struct rte_lpm *lpm = NULL;
uint32_t ip, ip_1, ip_2;
- uint8_t depth, depth_1, depth_2, next_hop_add, next_hop_add_1,
- next_hop_add_2, next_hop_return;
+ uint8_t depth, depth_1, depth_2;
+ uint32_t next_hop_add, next_hop_add_1, next_hop_add_2, next_hop_return;
int32_t status = 0;
/* Add & lookup to hit invalid TBL24 entry */
{
struct rte_lpm *lpm = NULL;
- uint32_t ip;
- uint8_t depth, next_hop_add, next_hop_return;
+ uint32_t ip, next_hop_add, next_hop_return;
+ uint8_t depth;
int32_t status = 0;
/* Add rule that covers a TBL24 range previously invalid & lookup
* (& delete & lookup) */
- lpm = rte_lpm_create(__func__, SOCKET_ID_ANY, MAX_RULES, RTE_LPM_HEAP);
+ lpm = rte_lpm_create(__func__, SOCKET_ID_ANY, MAX_RULES, 0);
TEST_LPM_ASSERT(lpm != NULL);
ip = IPv4(128, 0, 0, 0);
{
struct rte_lpm *lpm = NULL;
- uint32_t ip;
- uint8_t depth, next_hop_add, next_hop_return;
+ uint32_t ip, next_hop_add, next_hop_return;
+ uint8_t depth;
int32_t status = 0;
lpm = rte_lpm_create(__func__, SOCKET_ID_ANY, MAX_RULES, 0);
int32_t
test12(void)
{
+ __m128i ipx4;
+ uint32_t hop[4];
struct rte_lpm *lpm = NULL;
- uint32_t ip, i;
- uint8_t depth, next_hop_add, next_hop_return;
+ uint32_t ip, i, next_hop_add, next_hop_return;
+ uint8_t depth;
int32_t status = 0;
lpm = rte_lpm_create(__func__, SOCKET_ID_ANY, MAX_RULES, 0);
TEST_LPM_ASSERT((status == 0) &&
(next_hop_return == next_hop_add));
+ ipx4 = _mm_set_epi32(ip, ip + 1, ip, ip - 1);
+ rte_lpm_lookupx4(lpm, ipx4, hop, UINT32_MAX);
+ TEST_LPM_ASSERT(hop[0] == UINT32_MAX);
+ TEST_LPM_ASSERT(hop[1] == next_hop_add);
+ TEST_LPM_ASSERT(hop[2] == UINT32_MAX);
+ TEST_LPM_ASSERT(hop[3] == next_hop_add);
+
status = rte_lpm_delete(lpm, ip, depth);
TEST_LPM_ASSERT(status == 0);
test13(void)
{
struct rte_lpm *lpm = NULL;
- uint32_t ip, i;
- uint8_t depth, next_hop_add_1, next_hop_add_2, next_hop_return;
+ uint32_t ip, i, next_hop_add_1, next_hop_add_2, next_hop_return;
+ uint8_t depth;
int32_t status = 0;
lpm = rte_lpm_create(__func__, SOCKET_ID_ANY, MAX_RULES, 0);
* that we have enough storage for all rules at that depth*/
struct rte_lpm *lpm = NULL;
- uint32_t ip;
- uint8_t depth, next_hop_add, next_hop_return;
+ uint32_t ip, next_hop_add, next_hop_return;
+ uint8_t depth;
int32_t status = 0;
/* Add enough space for 256 rules for every depth */
256 * 32, 0);
/* ip loops through all possibilities for top 24 bits of address */
- for (ip = 0; ip < 0xFFFFFF; ip++){
+ for (ip = 0; ip < 0xFFFFFF; ip++) {
/* add an entry within a different tbl8 each time, since
* depth >24 and the top 24 bits are different */
if (rte_lpm_add(lpm, (ip << 8) + 0xF0, 30, 0) < 0)
const uint8_t d_ip_10_32 = 32,
d_ip_10_24 = 24,
d_ip_20_25 = 25;
- const uint8_t next_hop_ip_10_32 = 100,
+ const uint32_t next_hop_ip_10_32 = 100,
next_hop_ip_10_24 = 105,
next_hop_ip_20_25 = 111;
- uint8_t next_hop_return = 0;
+ uint32_t next_hop_return = 0;
int32_t status = 0;
lpm = rte_lpm_create(__func__, SOCKET_ID_ANY, MAX_RULES, 0);
return -1;
status = rte_lpm_lookup(lpm, ip_10_32, &next_hop_return);
- uint8_t test_hop_10_32 = next_hop_return;
+ uint32_t test_hop_10_32 = next_hop_return;
TEST_LPM_ASSERT(status == 0);
TEST_LPM_ASSERT(next_hop_return == next_hop_ip_10_32);
return -1;
status = rte_lpm_lookup(lpm, ip_10_24, &next_hop_return);
- uint8_t test_hop_10_24 = next_hop_return;
+ uint32_t test_hop_10_24 = next_hop_return;
TEST_LPM_ASSERT(status == 0);
TEST_LPM_ASSERT(next_hop_return == next_hop_ip_10_24);
return -1;
status = rte_lpm_lookup(lpm, ip_20_25, &next_hop_return);
- uint8_t test_hop_20_25 = next_hop_return;
+ uint32_t test_hop_20_25 = next_hop_return;
TEST_LPM_ASSERT(status == 0);
TEST_LPM_ASSERT(next_hop_return == next_hop_ip_20_25);
return -1;
}
- if (test_hop_10_24 == test_hop_20_25){
+ if (test_hop_10_24 == test_hop_20_25) {
printf("Next hop return equal\n");
return -1;
}
printf("--------------------------- \n");
/* Count depths. */
- for(i = 1; i <= 32; i++) {
+ for (i = 1; i <= 32; i++) {
unsigned depth_counter = 0;
double percent_hits;
struct rte_lpm *lpm = NULL;
uint64_t begin, total_time, lpm_used_entries = 0;
unsigned i, j;
- uint8_t next_hop_add = 0xAA, next_hop_return = 0;
+ uint32_t next_hop_add = 0xAA, next_hop_return = 0;
int status = 0;
uint64_t cache_line_counter = 0;
int64_t count = 0;
if (lpm->tbl24[i].valid)
lpm_used_entries++;
- if (i % 32 == 0){
+ if (i % 32 == 0) {
if ((uint64_t)count < lpm_used_entries) {
cache_line_counter++;
count = lpm_used_entries;
printf("64 byte Cache entries used = %u (%u bytes)\n",
(unsigned) cache_line_counter, (unsigned) cache_line_counter * 64);
- printf("Average LPM Add: %g cycles\n", (double)total_time / NUM_ROUTE_ENTRIES);
+ printf("Average LPM Add: %g cycles\n",
+ (double)total_time / NUM_ROUTE_ENTRIES);
/* Measure single Lookup */
total_time = 0;
count = 0;
- for (i = 0; i < ITERATIONS; i ++) {
+ for (i = 0; i < ITERATIONS; i++) {
static uint32_t ip_batch[BATCH_SIZE];
- for (j = 0; j < BATCH_SIZE; j ++)
+ for (j = 0; j < BATCH_SIZE; j++)
ip_batch[j] = rte_rand();
/* Lookup per batch */
begin = rte_rdtsc();
- for (j = 0; j < BATCH_SIZE; j ++) {
+ for (j = 0; j < BATCH_SIZE; j++) {
if (rte_lpm_lookup(lpm, ip_batch[j], &next_hop_return) != 0)
count++;
}
/* Measure bulk Lookup */
total_time = 0;
count = 0;
- for (i = 0; i < ITERATIONS; i ++) {
+ for (i = 0; i < ITERATIONS; i++) {
static uint32_t ip_batch[BATCH_SIZE];
- uint16_t next_hops[BULK_SIZE];
+ uint32_t next_hops[BULK_SIZE];
/* Create array of random IP addresses */
- for (j = 0; j < BATCH_SIZE; j ++)
+ for (j = 0; j < BATCH_SIZE; j++)
ip_batch[j] = rte_rand();
/* Lookup per batch */
(double)total_time / ((double)ITERATIONS * BATCH_SIZE),
(count * 100.0) / (double)(ITERATIONS * BATCH_SIZE));
+ /* Measure LookupX4 */
+ total_time = 0;
+ count = 0;
+ for (i = 0; i < ITERATIONS; i++) {
+ static uint32_t ip_batch[BATCH_SIZE];
+ uint32_t next_hops[4];
+
+ /* Create array of random IP addresses */
+ for (j = 0; j < BATCH_SIZE; j++)
+ ip_batch[j] = rte_rand();
+
+ /* Lookup per batch */
+ begin = rte_rdtsc();
+ for (j = 0; j < BATCH_SIZE; j += RTE_DIM(next_hops)) {
+ unsigned k;
+ __m128i ipx4;
+
+ ipx4 = _mm_loadu_si128((__m128i *)(ip_batch + j));
+ ipx4 = *(__m128i *)(ip_batch + j);
+ rte_lpm_lookupx4(lpm, ipx4, next_hops, UINT32_MAX);
+ for (k = 0; k < RTE_DIM(next_hops); k++)
+ if (unlikely(next_hops[k] == UINT32_MAX))
+ count++;
+ }
+
+ total_time += rte_rdtsc() - begin;
+ }
+ printf("LPM LookupX4: %.1f cycles (fails = %.1f%%)\n",
+ (double)total_time / ((double)ITERATIONS * BATCH_SIZE),
+ (count * 100.0) / (double)(ITERATIONS * BATCH_SIZE));
+
/* Delete */
status = 0;
begin = rte_rdtsc();
* Do all unit and performance tests.
*/
-int
+static int
test_lpm(void)
{
unsigned i;
return global_status;
}
-#else /* RTE_LIBRTE_LPM */
-
-int
-test_lpm(void)
-{
- printf("The LPM library is not included in this build\n");
- return 0;
-}
-
-#endif /* RTE_LIBRTE_LPM */
+static struct test_command lpm_cmd = {
+ .command = "lpm_autotest",
+ .callback = test_lpm,
+};
+REGISTER_TEST_COMMAND(lpm_cmd);