Re: [PATCH v1 1/5] bpf: add BPF loading and execution framework

[Jerin Jacob <jerin.jacob@caviumnetworks.com>]

-----Original Message-----
> Date: Fri, 9 Mar 2018 16:42:01 +0000
> From: Konstantin Ananyev <konstantin.ananyev@intel.com>
> To: dev@dpdk.org
> CC: Konstantin Ananyev <konstantin.ananyev@intel.com>
> Subject: [dpdk-dev] [PATCH v1 1/5] bpf: add BPF loading and execution
>  framework
> X-Mailer: git-send-email 1.7.0.7
> 
> librte_bpf provides a framework to load and execute eBPF bytecode
> inside user-space dpdk based applications.
> It supports basic set of features from eBPF spec
> (https://www.kernel.org/doc/Documentation/networking/filter.txt).
> 
> Not currently supported features:
>  - JIT
>  - cBPF
>  - tail-pointer call
>  - eBPF MAP
>  - skb
> 
> It also adds dependency on libelf.
> 
> Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
> ---
>  config/common_base                 |   5 +
>  config/common_linuxapp             |   1 +
>  lib/Makefile                       |   2 +
>  lib/librte_bpf/Makefile            |  30 +++
>  lib/librte_bpf/bpf.c               |  48 ++++
>  lib/librte_bpf/bpf_exec.c          | 452 +++++++++++++++++++++++++++++++++++++
>  lib/librte_bpf/bpf_impl.h          |  37 +++
>  lib/librte_bpf/bpf_load.c          | 380 +++++++++++++++++++++++++++++++
>  lib/librte_bpf/bpf_validate.c      |  55 +++++
>  lib/librte_bpf/rte_bpf.h           | 158 +++++++++++++
>  lib/librte_bpf/rte_bpf_version.map |  12 +
>  mk/rte.app.mk                      |   2 +
>  12 files changed, 1182 insertions(+)
>  create mode 100644 lib/librte_bpf/Makefile
>  create mode 100644 lib/librte_bpf/bpf.c
>  create mode 100644 lib/librte_bpf/bpf_exec.c
>  create mode 100644 lib/librte_bpf/bpf_impl.h
>  create mode 100644 lib/librte_bpf/bpf_load.c
>  create mode 100644 lib/librte_bpf/bpf_validate.c
>  create mode 100644 lib/librte_bpf/rte_bpf.h
>  create mode 100644 lib/librte_bpf/rte_bpf_version.map
> 
> diff --git a/config/common_base b/config/common_base
> index ad03cf433..2205b684f 100644
> --- a/config/common_base
> +++ b/config/common_base
> @@ -823,3 +823,8 @@ CONFIG_RTE_APP_CRYPTO_PERF=y
>  # Compile the eventdev application
>  #
>  CONFIG_RTE_APP_EVENTDEV=y
> +
> +#
> +# Compile librte_bpf
> +#
> +CONFIG_RTE_LIBRTE_BPF=n
> diff --git a/config/common_linuxapp b/config/common_linuxapp
> index ff98f2355..7b4a0ce7d 100644
> --- a/config/common_linuxapp
> +++ b/config/common_linuxapp
> @@ -10,6 +10,7 @@ CONFIG_RTE_EAL_NUMA_AWARE_HUGEPAGES=y
>  CONFIG_RTE_EAL_IGB_UIO=y
>  CONFIG_RTE_EAL_VFIO=y
>  CONFIG_RTE_KNI_KMOD=y
> +CONFIG_RTE_LIBRTE_BPF=y
>  CONFIG_RTE_LIBRTE_KNI=y
>  CONFIG_RTE_LIBRTE_PMD_KNI=y
>  CONFIG_RTE_LIBRTE_VHOST=y
> diff --git a/lib/Makefile b/lib/Makefile
> index ec965a606..a4a2329f9 100644
> --- a/lib/Makefile
> +++ b/lib/Makefile
> @@ -97,6 +97,8 @@ DEPDIRS-librte_pdump := librte_eal librte_mempool librte_mbuf librte_ether
>  DIRS-$(CONFIG_RTE_LIBRTE_GSO) += librte_gso
>  DEPDIRS-librte_gso := librte_eal librte_mbuf librte_ether librte_net
>  DEPDIRS-librte_gso += librte_mempool
> +DIRS-$(CONFIG_RTE_LIBRTE_BPF) += librte_bpf
> +DEPDIRS-librte_bpf := librte_eal librte_mempool librte_mbuf librte_ether
>  
>  ifeq ($(CONFIG_RTE_EXEC_ENV_LINUXAPP),y)
>  DIRS-$(CONFIG_RTE_LIBRTE_KNI) += librte_kni
> diff --git a/lib/librte_bpf/Makefile b/lib/librte_bpf/Makefile
> new file mode 100644
> index 000000000..e0f434e77
> --- /dev/null
> +++ b/lib/librte_bpf/Makefile
> @@ -0,0 +1,30 @@
> +# SPDX-License-Identifier: BSD-3-Clause
> +# Copyright(c) 2018 Intel Corporation
> +
> +include $(RTE_SDK)/mk/rte.vars.mk
> +
> +# library name
> +LIB = librte_bpf.a
> +
> +CFLAGS += -O3
> +CFLAGS += $(WERROR_FLAGS) -I$(SRCDIR)
> +CFLAGS += -DALLOW_EXPERIMENTAL_API
> +LDLIBS += -lrte_net -lrte_eal
> +LDLIBS += -lrte_mempool -lrte_ring
> +LDLIBS += -lrte_mbuf -lrte_ethdev
> +LDLIBS += -lelf
> +
> +EXPORT_MAP := rte_bpf_version.map
> +
> +LIBABIVER := 1
> +
> +# all source are stored in SRCS-y
> +SRCS-$(CONFIG_RTE_LIBRTE_BPF) += bpf.c
> +SRCS-$(CONFIG_RTE_LIBRTE_BPF) += bpf_exec.c
> +SRCS-$(CONFIG_RTE_LIBRTE_BPF) += bpf_load.c
> +SRCS-$(CONFIG_RTE_LIBRTE_BPF) += bpf_validate.c
> +
> +# install header files
> +SYMLINK-$(CONFIG_RTE_LIBRTE_BPF)-include += rte_bpf.h
> +
> +include $(RTE_SDK)/mk/rte.lib.mk
> diff --git a/lib/librte_bpf/bpf.c b/lib/librte_bpf/bpf.c
> new file mode 100644
> index 000000000..4727d2251
> --- /dev/null
> +++ b/lib/librte_bpf/bpf.c
> @@ -0,0 +1,48 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2018 Intel Corporation
> + */
> +
> +#include <stdarg.h>
> +#include <stdio.h>
> +#include <string.h>
> +#include <errno.h>
> +#include <stdint.h>
> +#include <inttypes.h>
> +
> +#include <rte_common.h>
> +#include <rte_eal.h>
> +
> +#include "bpf_impl.h"
> +
> +__rte_experimental void
> +rte_bpf_destroy(struct rte_bpf *bpf)
> +{
> +	if (bpf != NULL) {
> +		if (bpf->jit.func != NULL)
> +			munmap(bpf->jit.func, bpf->jit.sz);
> +		munmap(bpf, bpf->sz);


Any specific reason to not use this memory from huge page using rte_zmalloc
to avoid normal TLB misses?


> +	}
> +}
> +
> +__rte_experimental int
> +rte_bpf_get_jit(const struct rte_bpf *bpf, struct rte_bpf_jit *jit)
> +{
> +	if (bpf == NULL || jit == NULL)
> +		return -EINVAL;
> +
> +	jit[0] = bpf->jit;
> +	return 0;
> +}
> +
> +int
> +bpf_jit(struct rte_bpf *bpf)
> +{
> +	int32_t rc;
> +
> +	rc = -ENOTSUP;
> +
> +	if (rc != 0)
> +		RTE_LOG(WARNING, USER1, "%s(%p) failed, error code: %d;\n",
> +			__func__, bpf, rc);

How about using new dynamic logging option for this library?

> +	return rc;