-/*-
- * 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
- * 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) 2010-2014 Intel Corporation
*/
+#include <rte_eal_memconfig.h>
+#include <rte_string_fns.h>
#include <rte_acl.h>
+#include <rte_tailq.h>
+#include <rte_vect.h>
+
#include "acl.h"
TAILQ_HEAD(rte_acl_list, rte_tailq_entry);
};
EAL_REGISTER_TAILQ(rte_acl_tailq)
+#ifndef CC_AVX512_SUPPORT
+/*
+ * If the compiler doesn't support AVX512 instructions,
+ * then the dummy one would be used instead for AVX512 classify method.
+ */
+int
+rte_acl_classify_avx512x16(__rte_unused const struct rte_acl_ctx *ctx,
+ __rte_unused const uint8_t **data,
+ __rte_unused uint32_t *results,
+ __rte_unused uint32_t num,
+ __rte_unused uint32_t categories)
+{
+ return -ENOTSUP;
+}
+
+int
+rte_acl_classify_avx512x32(__rte_unused const struct rte_acl_ctx *ctx,
+ __rte_unused const uint8_t **data,
+ __rte_unused uint32_t *results,
+ __rte_unused uint32_t num,
+ __rte_unused uint32_t categories)
+{
+ return -ENOTSUP;
+}
+#endif
+
+#ifndef CC_AVX2_SUPPORT
/*
* If the compiler doesn't support AVX2 instructions,
* then the dummy one would be used instead for AVX2 classify method.
*/
-int __attribute__ ((weak))
+int
rte_acl_classify_avx2(__rte_unused const struct rte_acl_ctx *ctx,
__rte_unused const uint8_t **data,
__rte_unused uint32_t *results,
{
return -ENOTSUP;
}
+#endif
-int __attribute__ ((weak))
+#ifndef RTE_ARCH_X86
+int
rte_acl_classify_sse(__rte_unused const struct rte_acl_ctx *ctx,
__rte_unused const uint8_t **data,
__rte_unused uint32_t *results,
{
return -ENOTSUP;
}
+#endif
-int __attribute__ ((weak))
+#ifndef RTE_ARCH_ARM
+int
rte_acl_classify_neon(__rte_unused const struct rte_acl_ctx *ctx,
__rte_unused const uint8_t **data,
__rte_unused uint32_t *results,
{
return -ENOTSUP;
}
+#endif
-int __attribute__ ((weak))
+#ifndef RTE_ARCH_PPC_64
+int
rte_acl_classify_altivec(__rte_unused const struct rte_acl_ctx *ctx,
__rte_unused const uint8_t **data,
__rte_unused uint32_t *results,
{
return -ENOTSUP;
}
+#endif
static const rte_acl_classify_t classify_fns[] = {
[RTE_ACL_CLASSIFY_DEFAULT] = rte_acl_classify_scalar,
[RTE_ACL_CLASSIFY_AVX2] = rte_acl_classify_avx2,
[RTE_ACL_CLASSIFY_NEON] = rte_acl_classify_neon,
[RTE_ACL_CLASSIFY_ALTIVEC] = rte_acl_classify_altivec,
+ [RTE_ACL_CLASSIFY_AVX512X16] = rte_acl_classify_avx512x16,
+ [RTE_ACL_CLASSIFY_AVX512X32] = rte_acl_classify_avx512x32,
};
-/* by default, use always available scalar code path. */
-static enum rte_acl_classify_alg rte_acl_default_classify =
- RTE_ACL_CLASSIFY_SCALAR;
-
-static void
-rte_acl_set_default_classify(enum rte_acl_classify_alg alg)
+/*
+ * Helper function for acl_check_alg.
+ * Check support for ARM specific classify methods.
+ */
+static int
+acl_check_alg_arm(enum rte_acl_classify_alg alg)
{
- rte_acl_default_classify = alg;
+ if (alg == RTE_ACL_CLASSIFY_NEON) {
+#if defined(RTE_ARCH_ARM64)
+ if (rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_128)
+ return 0;
+#elif defined(RTE_ARCH_ARM)
+ if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON) &&
+ rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_128)
+ return 0;
+#endif
+ return -ENOTSUP;
+ }
+
+ return -EINVAL;
}
-extern int
-rte_acl_set_ctx_classify(struct rte_acl_ctx *ctx, enum rte_acl_classify_alg alg)
+/*
+ * Helper function for acl_check_alg.
+ * Check support for PPC specific classify methods.
+ */
+static int
+acl_check_alg_ppc(enum rte_acl_classify_alg alg)
{
- if (ctx == NULL || (uint32_t)alg >= RTE_DIM(classify_fns))
- return -EINVAL;
+ if (alg == RTE_ACL_CLASSIFY_ALTIVEC) {
+#if defined(RTE_ARCH_PPC_64)
+ if (rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_128)
+ return 0;
+#endif
+ return -ENOTSUP;
+ }
- ctx->alg = alg;
- return 0;
+ return -EINVAL;
}
+#ifdef CC_AVX512_SUPPORT
+static int
+acl_check_avx512_cpu_flags(void)
+{
+ return (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F) &&
+ rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512VL) &&
+ rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512CD) &&
+ rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512BW));
+}
+#endif
+
/*
- * Select highest available classify method as default one.
- * Note that CLASSIFY_AVX2 should be set as a default only
- * if both conditions are met:
- * at build time compiler supports AVX2 and target cpu supports AVX2.
+ * Helper function for acl_check_alg.
+ * Check support for x86 specific classify methods.
*/
-static void __attribute__((constructor))
-rte_acl_init(void)
+static int
+acl_check_alg_x86(enum rte_acl_classify_alg alg)
{
- enum rte_acl_classify_alg alg = RTE_ACL_CLASSIFY_DEFAULT;
+ if (alg == RTE_ACL_CLASSIFY_AVX512X32) {
+#ifdef CC_AVX512_SUPPORT
+ if (acl_check_avx512_cpu_flags() != 0 &&
+ rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_512)
+ return 0;
+#endif
+ return -ENOTSUP;
+ }
-#if defined(RTE_ARCH_ARM64)
- alg = RTE_ACL_CLASSIFY_NEON;
-#elif defined(RTE_ARCH_ARM)
- if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON))
- alg = RTE_ACL_CLASSIFY_NEON;
-#elif defined(RTE_ARCH_PPC_64)
- alg = RTE_ACL_CLASSIFY_ALTIVEC;
-#else
+ if (alg == RTE_ACL_CLASSIFY_AVX512X16) {
+#ifdef CC_AVX512_SUPPORT
+ if (acl_check_avx512_cpu_flags() != 0 &&
+ rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_256)
+ return 0;
+#endif
+ return -ENOTSUP;
+ }
+
+ if (alg == RTE_ACL_CLASSIFY_AVX2) {
#ifdef CC_AVX2_SUPPORT
- if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2))
- alg = RTE_ACL_CLASSIFY_AVX2;
- else if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_SSE4_1))
-#else
- if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_SSE4_1))
+ if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2) &&
+ rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_256)
+ return 0;
+#endif
+ return -ENOTSUP;
+ }
+
+ if (alg == RTE_ACL_CLASSIFY_SSE) {
+#ifdef RTE_ARCH_X86
+ if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_SSE4_1) &&
+ rte_vect_get_max_simd_bitwidth() >= RTE_VECT_SIMD_128)
+ return 0;
#endif
- alg = RTE_ACL_CLASSIFY_SSE;
+ return -ENOTSUP;
+ }
+
+ return -EINVAL;
+}
+
+/*
+ * Check if input alg is supported by given platform/binary.
+ * Note that both conditions should be met:
+ * - at build time compiler supports ISA used by given methods
+ * - at run time target cpu supports necessary ISA.
+ */
+static int
+acl_check_alg(enum rte_acl_classify_alg alg)
+{
+ switch (alg) {
+ case RTE_ACL_CLASSIFY_NEON:
+ return acl_check_alg_arm(alg);
+ case RTE_ACL_CLASSIFY_ALTIVEC:
+ return acl_check_alg_ppc(alg);
+ case RTE_ACL_CLASSIFY_AVX512X32:
+ case RTE_ACL_CLASSIFY_AVX512X16:
+ case RTE_ACL_CLASSIFY_AVX2:
+ case RTE_ACL_CLASSIFY_SSE:
+ return acl_check_alg_x86(alg);
+ /* scalar method is supported on all platforms */
+ case RTE_ACL_CLASSIFY_SCALAR:
+ return 0;
+ default:
+ return -EINVAL;
+ }
+}
+/*
+ * Get preferred alg for given platform.
+ */
+static enum rte_acl_classify_alg
+acl_get_best_alg(void)
+{
+ /*
+ * array of supported methods for each platform.
+ * Note that order is important - from most to less preferable.
+ */
+ static const enum rte_acl_classify_alg alg[] = {
+#if defined(RTE_ARCH_ARM)
+ RTE_ACL_CLASSIFY_NEON,
+#elif defined(RTE_ARCH_PPC_64)
+ RTE_ACL_CLASSIFY_ALTIVEC,
+#elif defined(RTE_ARCH_X86)
+ RTE_ACL_CLASSIFY_AVX512X32,
+ RTE_ACL_CLASSIFY_AVX512X16,
+ RTE_ACL_CLASSIFY_AVX2,
+ RTE_ACL_CLASSIFY_SSE,
#endif
- rte_acl_set_default_classify(alg);
+ RTE_ACL_CLASSIFY_SCALAR,
+ };
+
+ uint32_t i;
+
+ /* find best possible alg */
+ for (i = 0; i != RTE_DIM(alg) && acl_check_alg(alg[i]) != 0; i++)
+ ;
+
+ /* we always have to find something suitable */
+ RTE_VERIFY(i != RTE_DIM(alg));
+ return alg[i];
+}
+
+extern int
+rte_acl_set_ctx_classify(struct rte_acl_ctx *ctx, enum rte_acl_classify_alg alg)
+{
+ int32_t rc;
+
+ /* formal parameters check */
+ if (ctx == NULL || (uint32_t)alg >= RTE_DIM(classify_fns))
+ return -EINVAL;
+
+ /* user asked us to select the *best* one */
+ if (alg == RTE_ACL_CLASSIFY_DEFAULT)
+ alg = acl_get_best_alg();
+
+ /* check that given alg is supported */
+ rc = acl_check_alg(alg);
+ if (rc != 0)
+ return rc;
+
+ ctx->alg = alg;
+ return 0;
}
int
acl_list = RTE_TAILQ_CAST(rte_acl_tailq.head, rte_acl_list);
- rte_rwlock_read_lock(RTE_EAL_TAILQ_RWLOCK);
+ rte_mcfg_tailq_read_lock();
TAILQ_FOREACH(te, acl_list, next) {
ctx = (struct rte_acl_ctx *) te->data;
if (strncmp(name, ctx->name, sizeof(ctx->name)) == 0)
break;
}
- rte_rwlock_read_unlock(RTE_EAL_TAILQ_RWLOCK);
+ rte_mcfg_tailq_read_unlock();
if (te == NULL) {
rte_errno = ENOENT;
acl_list = RTE_TAILQ_CAST(rte_acl_tailq.head, rte_acl_list);
- rte_rwlock_write_lock(RTE_EAL_TAILQ_RWLOCK);
+ rte_mcfg_tailq_write_lock();
/* find our tailq entry */
TAILQ_FOREACH(te, acl_list, next) {
break;
}
if (te == NULL) {
- rte_rwlock_write_unlock(RTE_EAL_TAILQ_RWLOCK);
+ rte_mcfg_tailq_write_unlock();
return;
}
TAILQ_REMOVE(acl_list, te, next);
- rte_rwlock_write_unlock(RTE_EAL_TAILQ_RWLOCK);
+ rte_mcfg_tailq_write_unlock();
rte_free(ctx->mem);
rte_free(ctx);
sz = sizeof(*ctx) + param->max_rule_num * param->rule_size;
/* get EAL TAILQ lock. */
- rte_rwlock_write_lock(RTE_EAL_TAILQ_RWLOCK);
+ rte_mcfg_tailq_write_lock();
/* if we already have one with that name */
TAILQ_FOREACH(te, acl_list, next) {
ctx->max_rules = param->max_rule_num;
ctx->rule_sz = param->rule_size;
ctx->socket_id = param->socket_id;
- ctx->alg = rte_acl_default_classify;
- snprintf(ctx->name, sizeof(ctx->name), "%s", param->name);
+ ctx->alg = acl_get_best_alg();
+ strlcpy(ctx->name, param->name, sizeof(ctx->name));
te->data = (void *) ctx;
}
exit:
- rte_rwlock_write_unlock(RTE_EAL_TAILQ_RWLOCK);
+ rte_mcfg_tailq_write_unlock();
return ctx;
}
printf("acl context <%s>@%p\n", ctx->name, ctx);
printf(" socket_id=%"PRId32"\n", ctx->socket_id);
printf(" alg=%"PRId32"\n", ctx->alg);
+ printf(" first_load_sz=%"PRIu32"\n", ctx->first_load_sz);
printf(" max_rules=%"PRIu32"\n", ctx->max_rules);
printf(" rule_size=%"PRIu32"\n", ctx->rule_sz);
printf(" num_rules=%"PRIu32"\n", ctx->num_rules);
acl_list = RTE_TAILQ_CAST(rte_acl_tailq.head, rte_acl_list);
- rte_rwlock_read_lock(RTE_EAL_TAILQ_RWLOCK);
+ rte_mcfg_tailq_read_lock();
TAILQ_FOREACH(te, acl_list, next) {
ctx = (struct rte_acl_ctx *) te->data;
rte_acl_dump(ctx);
}
- rte_rwlock_read_unlock(RTE_EAL_TAILQ_RWLOCK);
+ rte_mcfg_tailq_read_unlock();
}