From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga04.intel.com (mga04.intel.com [192.55.52.120]) by dpdk.org (Postfix) with ESMTP id 64E444C7C for ; Fri, 30 Mar 2018 19:33:00 +0200 (CEST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga002.jf.intel.com ([10.7.209.21]) by fmsmga104.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 30 Mar 2018 10:32:59 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.48,382,1517904000"; d="scan'208";a="46664501" Received: from sivswdev02.ir.intel.com (HELO localhost.localdomain) ([10.237.217.46]) by orsmga002.jf.intel.com with ESMTP; 30 Mar 2018 10:32:58 -0700 From: Konstantin Ananyev To: dev@dpdk.org Cc: Konstantin Ananyev , olivier.matz@6wind.com, pascal.mazon@6wind.com Date: Fri, 30 Mar 2018 18:32:37 +0100 Message-Id: <1522431163-25621-2-git-send-email-konstantin.ananyev@intel.com> X-Mailer: git-send-email 1.7.0.7 In-Reply-To: <1520613725-9176-1-git-send-email-konstantin.ananyev@intel.com> References: <1520613725-9176-1-git-send-email-konstantin.ananyev@intel.com> Subject: [dpdk-dev] [PATCH v2 1/7] net: move BPF related definitions into librte_net X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 30 Mar 2018 17:33:02 -0000 Different linux distro may include partial definitions for eBPF while the linux kernel (or dpdk) may support given eBPF feature. To avoid issues define in one place all that is needed (and/or supported) by various DPDK components. Signed-off-by: Konstantin Ananyev --- drivers/net/tap/tap_bpf.h | 80 +--------- lib/librte_net/Makefile | 1 + lib/librte_net/meson.build | 3 +- lib/librte_net/rte_bpf_def.h | 370 +++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 374 insertions(+), 80 deletions(-) create mode 100644 lib/librte_net/rte_bpf_def.h diff --git a/drivers/net/tap/tap_bpf.h b/drivers/net/tap/tap_bpf.h index 1a70ffe21..d059648d8 100644 --- a/drivers/net/tap/tap_bpf.h +++ b/drivers/net/tap/tap_bpf.h @@ -6,85 +6,7 @@ #define __TAP_BPF_H__ #include - -/* Do not #include since eBPF must compile on different - * distros which may include partial definitions for eBPF (while the - * kernel itself may support eBPF). Instead define here all that is needed - */ - -/* BPF_MAP_UPDATE_ELEM command flags */ -#define BPF_ANY 0 /* create a new element or update an existing */ - -/* BPF architecture instruction struct */ -struct bpf_insn { - __u8 code; - __u8 dst_reg:4; - __u8 src_reg:4; - __s16 off; - __s32 imm; /* immediate value */ -}; - -/* BPF program types */ -enum bpf_prog_type { - BPF_PROG_TYPE_UNSPEC, - BPF_PROG_TYPE_SOCKET_FILTER, - BPF_PROG_TYPE_KPROBE, - BPF_PROG_TYPE_SCHED_CLS, - BPF_PROG_TYPE_SCHED_ACT, -}; - -/* BPF commands types */ -enum bpf_cmd { - BPF_MAP_CREATE, - BPF_MAP_LOOKUP_ELEM, - BPF_MAP_UPDATE_ELEM, - BPF_MAP_DELETE_ELEM, - BPF_MAP_GET_NEXT_KEY, - BPF_PROG_LOAD, -}; - -/* BPF maps types */ -enum bpf_map_type { - BPF_MAP_TYPE_UNSPEC, - BPF_MAP_TYPE_HASH, -}; - -/* union of anonymous structs used with TAP BPF commands */ -union bpf_attr { - /* BPF_MAP_CREATE command */ - struct { - __u32 map_type; - __u32 key_size; - __u32 value_size; - __u32 max_entries; - __u32 map_flags; - __u32 inner_map_fd; - }; - - /* BPF_MAP_UPDATE_ELEM, BPF_MAP_DELETE_ELEM commands */ - struct { - __u32 map_fd; - __aligned_u64 key; - union { - __aligned_u64 value; - __aligned_u64 next_key; - }; - __u64 flags; - }; - - /* BPF_PROG_LOAD command */ - struct { - __u32 prog_type; - __u32 insn_cnt; - __aligned_u64 insns; - __aligned_u64 license; - __u32 log_level; - __u32 log_size; - __aligned_u64 log_buf; - __u32 kern_version; - __u32 prog_flags; - }; -} __attribute__((aligned(8))); +#include #ifndef __NR_bpf # if defined(__i386__) diff --git a/lib/librte_net/Makefile b/lib/librte_net/Makefile index 95ff54900..8876b3dcc 100644 --- a/lib/librte_net/Makefile +++ b/lib/librte_net/Makefile @@ -20,5 +20,6 @@ SYMLINK-$(CONFIG_RTE_LIBRTE_NET)-include := rte_ip.h rte_tcp.h rte_udp.h rte_esp SYMLINK-$(CONFIG_RTE_LIBRTE_NET)-include += rte_sctp.h rte_icmp.h rte_arp.h SYMLINK-$(CONFIG_RTE_LIBRTE_NET)-include += rte_ether.h rte_gre.h rte_net.h SYMLINK-$(CONFIG_RTE_LIBRTE_NET)-include += rte_net_crc.h +SYMLINK-$(CONFIG_RTE_LIBRTE_NET)-include += rte_bpf_def.h include $(RTE_SDK)/mk/rte.lib.mk diff --git a/lib/librte_net/meson.build b/lib/librte_net/meson.build index 78c0f03e5..ab0b82962 100644 --- a/lib/librte_net/meson.build +++ b/lib/librte_net/meson.build @@ -12,7 +12,8 @@ headers = files('rte_ip.h', 'rte_ether.h', 'rte_gre.h', 'rte_net.h', - 'rte_net_crc.h') + 'rte_net_crc.h', + 'rte_bpf_def.h') sources = files('rte_arp.c', 'rte_net.c', 'rte_net_crc.c') deps += ['mbuf'] diff --git a/lib/librte_net/rte_bpf_def.h b/lib/librte_net/rte_bpf_def.h new file mode 100644 index 000000000..3f4a5a3e7 --- /dev/null +++ b/lib/librte_net/rte_bpf_def.h @@ -0,0 +1,370 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 + * Copyright 2017 Mellanox Technologies, Ltd. + */ + +#ifndef _RTE_BPF_DEF_H_ +#define _RTE_BPF_DEF_H_ + +#ifdef __linux__ +#include +#else + +typedef uint8_t __u8; +typedef uint16_t __u16; +typedef uint32_t __u32; +typedef uint64_t __u64; + +typedef int8_t __s8; +typedef int16_t __s16; +typedef int32_t __s32; + +#define __aligned_u64 __u64 __attribute__((aligned(8))) + +#endif + +#ifdef __cplusplus +extern "C" { +#endif + +/* Do not #include since eBPF must compile on different + * distros which may include partial definitions for eBPF (while the + * kernel itself may support eBPF). Instead define here all that is needed + * by various DPDK components. + */ + +/* Instruction classes */ +#define BPF_CLASS(code) ((code) & 0x07) +#define BPF_LD 0x00 +#define BPF_LDX 0x01 +#define BPF_ST 0x02 +#define BPF_STX 0x03 +#define BPF_ALU 0x04 +#define BPF_JMP 0x05 +#define BPF_RET 0x06 +#define BPF_MISC 0x07 + +/* ld/ldx fields */ +#define BPF_SIZE(code) ((code) & 0x18) +#define BPF_W 0x00 +#define BPF_H 0x08 +#define BPF_B 0x10 +#define BPF_MODE(code) ((code) & 0xe0) +#define BPF_IMM 0x00 +#define BPF_ABS 0x20 +#define BPF_IND 0x40 +#define BPF_MEM 0x60 +#define BPF_LEN 0x80 +#define BPF_MSH 0xa0 + +/* alu/jmp fields */ +#define BPF_OP(code) ((code) & 0xf0) +#define BPF_ADD 0x00 +#define BPF_SUB 0x10 +#define BPF_MUL 0x20 +#define BPF_DIV 0x30 +#define BPF_OR 0x40 +#define BPF_AND 0x50 +#define BPF_LSH 0x60 +#define BPF_RSH 0x70 +#define BPF_NEG 0x80 +#define BPF_MOD 0x90 +#define BPF_XOR 0xa0 + +#define BPF_JA 0x00 +#define BPF_JEQ 0x10 +#define BPF_JGT 0x20 +#define BPF_JGE 0x30 +#define BPF_JSET 0x40 +#define BPF_SRC(code) ((code) & 0x08) +#define BPF_K 0x00 +#define BPF_X 0x08 + +#ifndef BPF_MAXINSNS +#define BPF_MAXINSNS 4096 +#endif + +/* Extended instruction set based on top of classic BPF */ + +/* instruction classes */ +#define BPF_ALU64 0x07 /* alu mode in double word width */ + +/* ld/ldx fields */ +#define BPF_DW 0x18 /* double word */ +#define BPF_XADD 0xc0 /* exclusive add */ + +/* alu/jmp fields */ +#define BPF_MOV 0xb0 /* mov reg to reg */ +#define BPF_ARSH 0xc0 /* sign extending arithmetic shift right */ + +/* change endianness of a register */ +#define BPF_END 0xd0 /* flags for endianness conversion: */ +#define BPF_TO_LE 0x00 /* convert to little-endian */ +#define BPF_TO_BE 0x08 /* convert to big-endian */ +#define BPF_FROM_LE BPF_TO_LE +#define BPF_FROM_BE BPF_TO_BE + +/* jmp encodings */ +#define BPF_JNE 0x50 /* jump != */ +#define BPF_JLT 0xa0 /* LT is unsigned, '<' */ +#define BPF_JLE 0xb0 /* LE is unsigned, '<=' */ +#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */ +#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ +#define BPF_JSLT 0xc0 /* SLT is signed, '<' */ +#define BPF_JSLE 0xd0 /* SLE is signed, '<=' */ +#define BPF_CALL 0x80 /* function call */ +#define BPF_EXIT 0x90 /* function return */ + +/* Register numbers */ +enum { + BPF_REG_0 = 0, + BPF_REG_1, + BPF_REG_2, + BPF_REG_3, + BPF_REG_4, + BPF_REG_5, + BPF_REG_6, + BPF_REG_7, + BPF_REG_8, + BPF_REG_9, + BPF_REG_10, + __MAX_BPF_REG, +}; + +/* BPF has 10 general purpose 64-bit registers and stack frame. */ +#define MAX_BPF_REG __MAX_BPF_REG + +struct bpf_insn { + __u8 code; /* opcode */ + __u8 dst_reg:4; /* dest register */ + __u8 src_reg:4; /* source register */ + __s16 off; /* signed offset */ + __s32 imm; /* signed immediate constant */ +}; + +/* BPF syscall commands, see bpf(2) man-page for details. */ +enum bpf_cmd { + BPF_MAP_CREATE, + BPF_MAP_LOOKUP_ELEM, + BPF_MAP_UPDATE_ELEM, + BPF_MAP_DELETE_ELEM, + BPF_MAP_GET_NEXT_KEY, + BPF_PROG_LOAD, + BPF_OBJ_PIN, + BPF_OBJ_GET, + BPF_PROG_ATTACH, + BPF_PROG_DETACH, + BPF_PROG_TEST_RUN, + BPF_PROG_GET_NEXT_ID, + BPF_MAP_GET_NEXT_ID, + BPF_PROG_GET_FD_BY_ID, + BPF_MAP_GET_FD_BY_ID, + BPF_OBJ_GET_INFO_BY_FD, +}; + +enum bpf_map_type { + BPF_MAP_TYPE_UNSPEC, + BPF_MAP_TYPE_HASH, + BPF_MAP_TYPE_ARRAY, + BPF_MAP_TYPE_PROG_ARRAY, + BPF_MAP_TYPE_PERF_EVENT_ARRAY, + BPF_MAP_TYPE_PERCPU_HASH, + BPF_MAP_TYPE_PERCPU_ARRAY, + BPF_MAP_TYPE_STACK_TRACE, + BPF_MAP_TYPE_CGROUP_ARRAY, + BPF_MAP_TYPE_LRU_HASH, + BPF_MAP_TYPE_LRU_PERCPU_HASH, + BPF_MAP_TYPE_LPM_TRIE, + BPF_MAP_TYPE_ARRAY_OF_MAPS, + BPF_MAP_TYPE_HASH_OF_MAPS, + BPF_MAP_TYPE_DEVMAP, + BPF_MAP_TYPE_SOCKMAP, +}; + +enum bpf_prog_type { + BPF_PROG_TYPE_UNSPEC, + BPF_PROG_TYPE_SOCKET_FILTER, + BPF_PROG_TYPE_KPROBE, + BPF_PROG_TYPE_SCHED_CLS, + BPF_PROG_TYPE_SCHED_ACT, + BPF_PROG_TYPE_TRACEPOINT, + BPF_PROG_TYPE_XDP, + BPF_PROG_TYPE_PERF_EVENT, + BPF_PROG_TYPE_CGROUP_SKB, + BPF_PROG_TYPE_CGROUP_SOCK, + BPF_PROG_TYPE_LWT_IN, + BPF_PROG_TYPE_LWT_OUT, + BPF_PROG_TYPE_LWT_XMIT, + BPF_PROG_TYPE_SOCK_OPS, + BPF_PROG_TYPE_SK_SKB, +}; + +enum bpf_attach_type { + BPF_CGROUP_INET_INGRESS, + BPF_CGROUP_INET_EGRESS, + BPF_CGROUP_INET_SOCK_CREATE, + BPF_CGROUP_SOCK_OPS, + BPF_SK_SKB_STREAM_PARSER, + BPF_SK_SKB_STREAM_VERDICT, + __MAX_BPF_ATTACH_TYPE +}; + +#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE + +/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command + * to the given target_fd cgroup the descendent cgroup will be able to + * override effective bpf program that was inherited from this cgroup + */ +#define BPF_F_ALLOW_OVERRIDE (1U << 0) + +/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the + * verifier will perform strict alignment checking as if the kernel + * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set, + * and NET_IP_ALIGN defined to 2. + */ +#define BPF_F_STRICT_ALIGNMENT (1U << 0) + +#define BPF_PSEUDO_MAP_FD 1 + +/* flags for BPF_MAP_UPDATE_ELEM command */ +#define BPF_ANY 0 /* create new element or update existing */ +#define BPF_NOEXIST 1 /* create new element if it didn't exist */ +#define BPF_EXIST 2 /* update existing element */ + +/* flags for BPF_MAP_CREATE command */ +#define BPF_F_NO_PREALLOC (1U << 0) +/* Instead of having one common LRU list in the + * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list + * which can scale and perform better. + * Note, the LRU nodes (including free nodes) cannot be moved + * across different LRU lists. + */ +#define BPF_F_NO_COMMON_LRU (1U << 1) +/* Specify numa node during map creation */ +#define BPF_F_NUMA_NODE (1U << 2) + +union bpf_attr { + struct { /* anonymous struct used by BPF_MAP_CREATE command */ + __u32 map_type; /* one of enum bpf_map_type */ + __u32 key_size; /* size of key in bytes */ + __u32 value_size; /* size of value in bytes */ + __u32 max_entries; /* max number of entries in a map */ + __u32 map_flags; /* BPF_MAP_CREATE related + * flags defined above. + */ + __u32 inner_map_fd; /* fd pointing to the inner map */ + __u32 numa_node; /* numa node (effective only if + * BPF_F_NUMA_NODE is set). + */ + }; + + struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ + __u32 map_fd; + __aligned_u64 key; + union { + __aligned_u64 value; + __aligned_u64 next_key; + }; + __u64 flags; + }; + + struct { /* anonymous struct used by BPF_PROG_LOAD command */ + __u32 prog_type; /* one of enum bpf_prog_type */ + __u32 insn_cnt; + __aligned_u64 insns; + __aligned_u64 license; + __u32 log_level; + /* verbosity level of verifier */ + __u32 log_size; /* size of user buffer */ + __aligned_u64 log_buf; /* user supplied buffer */ + __u32 kern_version; + /* checked when prog_type=kprobe */ + __u32 prog_flags; + }; + + struct { /* anonymous struct used by BPF_OBJ_* commands */ + __aligned_u64 pathname; + __u32 bpf_fd; + }; + + struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ + __u32 target_fd; + /* container object to attach to */ + __u32 attach_bpf_fd; /* eBPF program to attach */ + __u32 attach_type; + __u32 attach_flags; + }; + + struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ + __u32 prog_fd; + __u32 retval; + __u32 data_size_in; + __u32 data_size_out; + __aligned_u64 data_in; + __aligned_u64 data_out; + __u32 repeat; + __u32 duration; + } test; + + struct { /* anonymous struct used by BPF_*_GET_*_ID */ + union { + __u32 start_id; + __u32 prog_id; + __u32 map_id; + }; + __u32 next_id; + }; + + struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ + __u32 bpf_fd; + __u32 info_len; + __aligned_u64 info; + } info; +} __attribute__((aligned(8))); + +/* Generic BPF return codes which all BPF program types may support. + * The values are binary compatible with their TC_ACT_* counter-part to + * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT + * programs. + * + * XDP is handled seprately, see XDP_*. + */ +enum bpf_ret_code { + BPF_OK = 0, + /* 1 reserved */ + BPF_DROP = 2, + /* 3-6 reserved */ + BPF_REDIRECT = 7, + /* >127 are reserved for prog type specific return codes */ +}; + +enum sk_action { + SK_DROP = 0, + SK_PASS, +}; + +#define BPF_TAG_SIZE 8 + +struct bpf_prog_info { + __u32 type; + __u32 id; + __u8 tag[BPF_TAG_SIZE]; + __u32 jited_prog_len; + __u32 xlated_prog_len; + __aligned_u64 jited_prog_insns; + __aligned_u64 xlated_prog_insns; +} __attribute__((aligned(8))); + +struct bpf_map_info { + __u32 type; + __u32 id; + __u32 key_size; + __u32 value_size; + __u32 max_entries; + __u32 map_flags; +} __attribute__((aligned(8))); + +#ifdef __cplusplus +} +#endif + +#endif /* _RTE_BPF_DEF_H_ */ -- 2.13.6