From 49a249c387268882e8393dd1fafc51e3b21cb7a2 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 7 Nov 2018 19:55:36 -0800 Subject: tools/bpftool: copy a few net uapi headers to tools directory Commit f6f3bac08ff9 ("tools/bpf: bpftool: add net support") added certain networking support to bpftool. The implementation relies on a relatively recent uapi header file linux/tc_act/tc_bpf.h on the host which contains the marco definition of TCA_ACT_BPF_ID. Unfortunately, this is not the case for all distributions. See the email message below where rhel-7.2 does not have an up-to-date linux/tc_act/tc_bpf.h. https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1799211.html Further investigation found that linux/pkt_cls.h is also needed for macro TCA_BPF_TAG. This patch fixed the issue by copying linux/tc_act/tc_bpf.h and linux/pkt_cls.h from kernel include/uapi directory to tools/include/uapi directory so building the bpftool does not depend on host system for these files. Fixes: f6f3bac08ff9 ("tools/bpf: bpftool: add net support") Reported-by: kernel test robot Cc: Li Zhijian Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann --- tools/include/uapi/linux/pkt_cls.h | 612 +++++++++++++++++++++++++++++++ tools/include/uapi/linux/tc_act/tc_bpf.h | 37 ++ 2 files changed, 649 insertions(+) create mode 100644 tools/include/uapi/linux/pkt_cls.h create mode 100644 tools/include/uapi/linux/tc_act/tc_bpf.h (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h new file mode 100644 index 000000000000..401d0c1e612d --- /dev/null +++ b/tools/include/uapi/linux/pkt_cls.h @@ -0,0 +1,612 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __LINUX_PKT_CLS_H +#define __LINUX_PKT_CLS_H + +#include +#include + +#define TC_COOKIE_MAX_SIZE 16 + +/* Action attributes */ +enum { + TCA_ACT_UNSPEC, + TCA_ACT_KIND, + TCA_ACT_OPTIONS, + TCA_ACT_INDEX, + TCA_ACT_STATS, + TCA_ACT_PAD, + TCA_ACT_COOKIE, + __TCA_ACT_MAX +}; + +#define TCA_ACT_MAX __TCA_ACT_MAX +#define TCA_OLD_COMPAT (TCA_ACT_MAX+1) +#define TCA_ACT_MAX_PRIO 32 +#define TCA_ACT_BIND 1 +#define TCA_ACT_NOBIND 0 +#define TCA_ACT_UNBIND 1 +#define TCA_ACT_NOUNBIND 0 +#define TCA_ACT_REPLACE 1 +#define TCA_ACT_NOREPLACE 0 + +#define TC_ACT_UNSPEC (-1) +#define TC_ACT_OK 0 +#define TC_ACT_RECLASSIFY 1 +#define TC_ACT_SHOT 2 +#define TC_ACT_PIPE 3 +#define TC_ACT_STOLEN 4 +#define TC_ACT_QUEUED 5 +#define TC_ACT_REPEAT 6 +#define TC_ACT_REDIRECT 7 +#define TC_ACT_TRAP 8 /* For hw path, this means "trap to cpu" + * and don't further process the frame + * in hardware. For sw path, this is + * equivalent of TC_ACT_STOLEN - drop + * the skb and act like everything + * is alright. + */ +#define TC_ACT_VALUE_MAX TC_ACT_TRAP + +/* There is a special kind of actions called "extended actions", + * which need a value parameter. These have a local opcode located in + * the highest nibble, starting from 1. The rest of the bits + * are used to carry the value. These two parts together make + * a combined opcode. + */ +#define __TC_ACT_EXT_SHIFT 28 +#define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT) +#define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1) +#define TC_ACT_EXT_OPCODE(combined) ((combined) & (~TC_ACT_EXT_VAL_MASK)) +#define TC_ACT_EXT_CMP(combined, opcode) (TC_ACT_EXT_OPCODE(combined) == opcode) + +#define TC_ACT_JUMP __TC_ACT_EXT(1) +#define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2) +#define TC_ACT_EXT_OPCODE_MAX TC_ACT_GOTO_CHAIN + +/* Action type identifiers*/ +enum { + TCA_ID_UNSPEC=0, + TCA_ID_POLICE=1, + /* other actions go here */ + __TCA_ID_MAX=255 +}; + +#define TCA_ID_MAX __TCA_ID_MAX + +struct tc_police { + __u32 index; + int action; +#define TC_POLICE_UNSPEC TC_ACT_UNSPEC +#define TC_POLICE_OK TC_ACT_OK +#define TC_POLICE_RECLASSIFY TC_ACT_RECLASSIFY +#define TC_POLICE_SHOT TC_ACT_SHOT +#define TC_POLICE_PIPE TC_ACT_PIPE + + __u32 limit; + __u32 burst; + __u32 mtu; + struct tc_ratespec rate; + struct tc_ratespec peakrate; + int refcnt; + int bindcnt; + __u32 capab; +}; + +struct tcf_t { + __u64 install; + __u64 lastuse; + __u64 expires; + __u64 firstuse; +}; + +struct tc_cnt { + int refcnt; + int bindcnt; +}; + +#define tc_gen \ + __u32 index; \ + __u32 capab; \ + int action; \ + int refcnt; \ + int bindcnt + +enum { + TCA_POLICE_UNSPEC, + TCA_POLICE_TBF, + TCA_POLICE_RATE, + TCA_POLICE_PEAKRATE, + TCA_POLICE_AVRATE, + TCA_POLICE_RESULT, + TCA_POLICE_TM, + TCA_POLICE_PAD, + __TCA_POLICE_MAX +#define TCA_POLICE_RESULT TCA_POLICE_RESULT +}; + +#define TCA_POLICE_MAX (__TCA_POLICE_MAX - 1) + +/* tca flags definitions */ +#define TCA_CLS_FLAGS_SKIP_HW (1 << 0) /* don't offload filter to HW */ +#define TCA_CLS_FLAGS_SKIP_SW (1 << 1) /* don't use filter in SW */ +#define TCA_CLS_FLAGS_IN_HW (1 << 2) /* filter is offloaded to HW */ +#define TCA_CLS_FLAGS_NOT_IN_HW (1 << 3) /* filter isn't offloaded to HW */ +#define TCA_CLS_FLAGS_VERBOSE (1 << 4) /* verbose logging */ + +/* U32 filters */ + +#define TC_U32_HTID(h) ((h)&0xFFF00000) +#define TC_U32_USERHTID(h) (TC_U32_HTID(h)>>20) +#define TC_U32_HASH(h) (((h)>>12)&0xFF) +#define TC_U32_NODE(h) ((h)&0xFFF) +#define TC_U32_KEY(h) ((h)&0xFFFFF) +#define TC_U32_UNSPEC 0 +#define TC_U32_ROOT (0xFFF00000) + +enum { + TCA_U32_UNSPEC, + TCA_U32_CLASSID, + TCA_U32_HASH, + TCA_U32_LINK, + TCA_U32_DIVISOR, + TCA_U32_SEL, + TCA_U32_POLICE, + TCA_U32_ACT, + TCA_U32_INDEV, + TCA_U32_PCNT, + TCA_U32_MARK, + TCA_U32_FLAGS, + TCA_U32_PAD, + __TCA_U32_MAX +}; + +#define TCA_U32_MAX (__TCA_U32_MAX - 1) + +struct tc_u32_key { + __be32 mask; + __be32 val; + int off; + int offmask; +}; + +struct tc_u32_sel { + unsigned char flags; + unsigned char offshift; + unsigned char nkeys; + + __be16 offmask; + __u16 off; + short offoff; + + short hoff; + __be32 hmask; + struct tc_u32_key keys[0]; +}; + +struct tc_u32_mark { + __u32 val; + __u32 mask; + __u32 success; +}; + +struct tc_u32_pcnt { + __u64 rcnt; + __u64 rhit; + __u64 kcnts[0]; +}; + +/* Flags */ + +#define TC_U32_TERMINAL 1 +#define TC_U32_OFFSET 2 +#define TC_U32_VAROFFSET 4 +#define TC_U32_EAT 8 + +#define TC_U32_MAXDEPTH 8 + + +/* RSVP filter */ + +enum { + TCA_RSVP_UNSPEC, + TCA_RSVP_CLASSID, + TCA_RSVP_DST, + TCA_RSVP_SRC, + TCA_RSVP_PINFO, + TCA_RSVP_POLICE, + TCA_RSVP_ACT, + __TCA_RSVP_MAX +}; + +#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 ) + +struct tc_rsvp_gpi { + __u32 key; + __u32 mask; + int offset; +}; + +struct tc_rsvp_pinfo { + struct tc_rsvp_gpi dpi; + struct tc_rsvp_gpi spi; + __u8 protocol; + __u8 tunnelid; + __u8 tunnelhdr; + __u8 pad; +}; + +/* ROUTE filter */ + +enum { + TCA_ROUTE4_UNSPEC, + TCA_ROUTE4_CLASSID, + TCA_ROUTE4_TO, + TCA_ROUTE4_FROM, + TCA_ROUTE4_IIF, + TCA_ROUTE4_POLICE, + TCA_ROUTE4_ACT, + __TCA_ROUTE4_MAX +}; + +#define TCA_ROUTE4_MAX (__TCA_ROUTE4_MAX - 1) + + +/* FW filter */ + +enum { + TCA_FW_UNSPEC, + TCA_FW_CLASSID, + TCA_FW_POLICE, + TCA_FW_INDEV, /* used by CONFIG_NET_CLS_IND */ + TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */ + TCA_FW_MASK, + __TCA_FW_MAX +}; + +#define TCA_FW_MAX (__TCA_FW_MAX - 1) + +/* TC index filter */ + +enum { + TCA_TCINDEX_UNSPEC, + TCA_TCINDEX_HASH, + TCA_TCINDEX_MASK, + TCA_TCINDEX_SHIFT, + TCA_TCINDEX_FALL_THROUGH, + TCA_TCINDEX_CLASSID, + TCA_TCINDEX_POLICE, + TCA_TCINDEX_ACT, + __TCA_TCINDEX_MAX +}; + +#define TCA_TCINDEX_MAX (__TCA_TCINDEX_MAX - 1) + +/* Flow filter */ + +enum { + FLOW_KEY_SRC, + FLOW_KEY_DST, + FLOW_KEY_PROTO, + FLOW_KEY_PROTO_SRC, + FLOW_KEY_PROTO_DST, + FLOW_KEY_IIF, + FLOW_KEY_PRIORITY, + FLOW_KEY_MARK, + FLOW_KEY_NFCT, + FLOW_KEY_NFCT_SRC, + FLOW_KEY_NFCT_DST, + FLOW_KEY_NFCT_PROTO_SRC, + FLOW_KEY_NFCT_PROTO_DST, + FLOW_KEY_RTCLASSID, + FLOW_KEY_SKUID, + FLOW_KEY_SKGID, + FLOW_KEY_VLAN_TAG, + FLOW_KEY_RXHASH, + __FLOW_KEY_MAX, +}; + +#define FLOW_KEY_MAX (__FLOW_KEY_MAX - 1) + +enum { + FLOW_MODE_MAP, + FLOW_MODE_HASH, +}; + +enum { + TCA_FLOW_UNSPEC, + TCA_FLOW_KEYS, + TCA_FLOW_MODE, + TCA_FLOW_BASECLASS, + TCA_FLOW_RSHIFT, + TCA_FLOW_ADDEND, + TCA_FLOW_MASK, + TCA_FLOW_XOR, + TCA_FLOW_DIVISOR, + TCA_FLOW_ACT, + TCA_FLOW_POLICE, + TCA_FLOW_EMATCHES, + TCA_FLOW_PERTURB, + __TCA_FLOW_MAX +}; + +#define TCA_FLOW_MAX (__TCA_FLOW_MAX - 1) + +/* Basic filter */ + +enum { + TCA_BASIC_UNSPEC, + TCA_BASIC_CLASSID, + TCA_BASIC_EMATCHES, + TCA_BASIC_ACT, + TCA_BASIC_POLICE, + __TCA_BASIC_MAX +}; + +#define TCA_BASIC_MAX (__TCA_BASIC_MAX - 1) + + +/* Cgroup classifier */ + +enum { + TCA_CGROUP_UNSPEC, + TCA_CGROUP_ACT, + TCA_CGROUP_POLICE, + TCA_CGROUP_EMATCHES, + __TCA_CGROUP_MAX, +}; + +#define TCA_CGROUP_MAX (__TCA_CGROUP_MAX - 1) + +/* BPF classifier */ + +#define TCA_BPF_FLAG_ACT_DIRECT (1 << 0) + +enum { + TCA_BPF_UNSPEC, + TCA_BPF_ACT, + TCA_BPF_POLICE, + TCA_BPF_CLASSID, + TCA_BPF_OPS_LEN, + TCA_BPF_OPS, + TCA_BPF_FD, + TCA_BPF_NAME, + TCA_BPF_FLAGS, + TCA_BPF_FLAGS_GEN, + TCA_BPF_TAG, + TCA_BPF_ID, + __TCA_BPF_MAX, +}; + +#define TCA_BPF_MAX (__TCA_BPF_MAX - 1) + +/* Flower classifier */ + +enum { + TCA_FLOWER_UNSPEC, + TCA_FLOWER_CLASSID, + TCA_FLOWER_INDEV, + TCA_FLOWER_ACT, + TCA_FLOWER_KEY_ETH_DST, /* ETH_ALEN */ + TCA_FLOWER_KEY_ETH_DST_MASK, /* ETH_ALEN */ + TCA_FLOWER_KEY_ETH_SRC, /* ETH_ALEN */ + TCA_FLOWER_KEY_ETH_SRC_MASK, /* ETH_ALEN */ + TCA_FLOWER_KEY_ETH_TYPE, /* be16 */ + TCA_FLOWER_KEY_IP_PROTO, /* u8 */ + TCA_FLOWER_KEY_IPV4_SRC, /* be32 */ + TCA_FLOWER_KEY_IPV4_SRC_MASK, /* be32 */ + TCA_FLOWER_KEY_IPV4_DST, /* be32 */ + TCA_FLOWER_KEY_IPV4_DST_MASK, /* be32 */ + TCA_FLOWER_KEY_IPV6_SRC, /* struct in6_addr */ + TCA_FLOWER_KEY_IPV6_SRC_MASK, /* struct in6_addr */ + TCA_FLOWER_KEY_IPV6_DST, /* struct in6_addr */ + TCA_FLOWER_KEY_IPV6_DST_MASK, /* struct in6_addr */ + TCA_FLOWER_KEY_TCP_SRC, /* be16 */ + TCA_FLOWER_KEY_TCP_DST, /* be16 */ + TCA_FLOWER_KEY_UDP_SRC, /* be16 */ + TCA_FLOWER_KEY_UDP_DST, /* be16 */ + + TCA_FLOWER_FLAGS, + TCA_FLOWER_KEY_VLAN_ID, /* be16 */ + TCA_FLOWER_KEY_VLAN_PRIO, /* u8 */ + TCA_FLOWER_KEY_VLAN_ETH_TYPE, /* be16 */ + + TCA_FLOWER_KEY_ENC_KEY_ID, /* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_SRC, /* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,/* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_DST, /* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,/* be32 */ + TCA_FLOWER_KEY_ENC_IPV6_SRC, /* struct in6_addr */ + TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,/* struct in6_addr */ + TCA_FLOWER_KEY_ENC_IPV6_DST, /* struct in6_addr */ + TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,/* struct in6_addr */ + + TCA_FLOWER_KEY_TCP_SRC_MASK, /* be16 */ + TCA_FLOWER_KEY_TCP_DST_MASK, /* be16 */ + TCA_FLOWER_KEY_UDP_SRC_MASK, /* be16 */ + TCA_FLOWER_KEY_UDP_DST_MASK, /* be16 */ + TCA_FLOWER_KEY_SCTP_SRC_MASK, /* be16 */ + TCA_FLOWER_KEY_SCTP_DST_MASK, /* be16 */ + + TCA_FLOWER_KEY_SCTP_SRC, /* be16 */ + TCA_FLOWER_KEY_SCTP_DST, /* be16 */ + + TCA_FLOWER_KEY_ENC_UDP_SRC_PORT, /* be16 */ + TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK, /* be16 */ + TCA_FLOWER_KEY_ENC_UDP_DST_PORT, /* be16 */ + TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, /* be16 */ + + TCA_FLOWER_KEY_FLAGS, /* be32 */ + TCA_FLOWER_KEY_FLAGS_MASK, /* be32 */ + + TCA_FLOWER_KEY_ICMPV4_CODE, /* u8 */ + TCA_FLOWER_KEY_ICMPV4_CODE_MASK,/* u8 */ + TCA_FLOWER_KEY_ICMPV4_TYPE, /* u8 */ + TCA_FLOWER_KEY_ICMPV4_TYPE_MASK,/* u8 */ + TCA_FLOWER_KEY_ICMPV6_CODE, /* u8 */ + TCA_FLOWER_KEY_ICMPV6_CODE_MASK,/* u8 */ + TCA_FLOWER_KEY_ICMPV6_TYPE, /* u8 */ + TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,/* u8 */ + + TCA_FLOWER_KEY_ARP_SIP, /* be32 */ + TCA_FLOWER_KEY_ARP_SIP_MASK, /* be32 */ + TCA_FLOWER_KEY_ARP_TIP, /* be32 */ + TCA_FLOWER_KEY_ARP_TIP_MASK, /* be32 */ + TCA_FLOWER_KEY_ARP_OP, /* u8 */ + TCA_FLOWER_KEY_ARP_OP_MASK, /* u8 */ + TCA_FLOWER_KEY_ARP_SHA, /* ETH_ALEN */ + TCA_FLOWER_KEY_ARP_SHA_MASK, /* ETH_ALEN */ + TCA_FLOWER_KEY_ARP_THA, /* ETH_ALEN */ + TCA_FLOWER_KEY_ARP_THA_MASK, /* ETH_ALEN */ + + TCA_FLOWER_KEY_MPLS_TTL, /* u8 - 8 bits */ + TCA_FLOWER_KEY_MPLS_BOS, /* u8 - 1 bit */ + TCA_FLOWER_KEY_MPLS_TC, /* u8 - 3 bits */ + TCA_FLOWER_KEY_MPLS_LABEL, /* be32 - 20 bits */ + + TCA_FLOWER_KEY_TCP_FLAGS, /* be16 */ + TCA_FLOWER_KEY_TCP_FLAGS_MASK, /* be16 */ + + TCA_FLOWER_KEY_IP_TOS, /* u8 */ + TCA_FLOWER_KEY_IP_TOS_MASK, /* u8 */ + TCA_FLOWER_KEY_IP_TTL, /* u8 */ + TCA_FLOWER_KEY_IP_TTL_MASK, /* u8 */ + + TCA_FLOWER_KEY_CVLAN_ID, /* be16 */ + TCA_FLOWER_KEY_CVLAN_PRIO, /* u8 */ + TCA_FLOWER_KEY_CVLAN_ETH_TYPE, /* be16 */ + + TCA_FLOWER_KEY_ENC_IP_TOS, /* u8 */ + TCA_FLOWER_KEY_ENC_IP_TOS_MASK, /* u8 */ + TCA_FLOWER_KEY_ENC_IP_TTL, /* u8 */ + TCA_FLOWER_KEY_ENC_IP_TTL_MASK, /* u8 */ + + TCA_FLOWER_KEY_ENC_OPTS, + TCA_FLOWER_KEY_ENC_OPTS_MASK, + + TCA_FLOWER_IN_HW_COUNT, + + __TCA_FLOWER_MAX, +}; + +#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1) + +enum { + TCA_FLOWER_KEY_ENC_OPTS_UNSPEC, + TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested + * TCA_FLOWER_KEY_ENC_OPT_GENEVE_ + * attributes + */ + __TCA_FLOWER_KEY_ENC_OPTS_MAX, +}; + +#define TCA_FLOWER_KEY_ENC_OPTS_MAX (__TCA_FLOWER_KEY_ENC_OPTS_MAX - 1) + +enum { + TCA_FLOWER_KEY_ENC_OPT_GENEVE_UNSPEC, + TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS, /* u16 */ + TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE, /* u8 */ + TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA, /* 4 to 128 bytes */ + + __TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX, +}; + +#define TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX \ + (__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1) + +enum { + TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0), + TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1), +}; + +/* Match-all classifier */ + +enum { + TCA_MATCHALL_UNSPEC, + TCA_MATCHALL_CLASSID, + TCA_MATCHALL_ACT, + TCA_MATCHALL_FLAGS, + __TCA_MATCHALL_MAX, +}; + +#define TCA_MATCHALL_MAX (__TCA_MATCHALL_MAX - 1) + +/* Extended Matches */ + +struct tcf_ematch_tree_hdr { + __u16 nmatches; + __u16 progid; +}; + +enum { + TCA_EMATCH_TREE_UNSPEC, + TCA_EMATCH_TREE_HDR, + TCA_EMATCH_TREE_LIST, + __TCA_EMATCH_TREE_MAX +}; +#define TCA_EMATCH_TREE_MAX (__TCA_EMATCH_TREE_MAX - 1) + +struct tcf_ematch_hdr { + __u16 matchid; + __u16 kind; + __u16 flags; + __u16 pad; /* currently unused */ +}; + +/* 0 1 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 + * +-----------------------+-+-+---+ + * | Unused |S|I| R | + * +-----------------------+-+-+---+ + * + * R(2) ::= relation to next ematch + * where: 0 0 END (last ematch) + * 0 1 AND + * 1 0 OR + * 1 1 Unused (invalid) + * I(1) ::= invert result + * S(1) ::= simple payload + */ +#define TCF_EM_REL_END 0 +#define TCF_EM_REL_AND (1<<0) +#define TCF_EM_REL_OR (1<<1) +#define TCF_EM_INVERT (1<<2) +#define TCF_EM_SIMPLE (1<<3) + +#define TCF_EM_REL_MASK 3 +#define TCF_EM_REL_VALID(v) (((v) & TCF_EM_REL_MASK) != TCF_EM_REL_MASK) + +enum { + TCF_LAYER_LINK, + TCF_LAYER_NETWORK, + TCF_LAYER_TRANSPORT, + __TCF_LAYER_MAX +}; +#define TCF_LAYER_MAX (__TCF_LAYER_MAX - 1) + +/* Ematch type assignments + * 1..32767 Reserved for ematches inside kernel tree + * 32768..65535 Free to use, not reliable + */ +#define TCF_EM_CONTAINER 0 +#define TCF_EM_CMP 1 +#define TCF_EM_NBYTE 2 +#define TCF_EM_U32 3 +#define TCF_EM_META 4 +#define TCF_EM_TEXT 5 +#define TCF_EM_VLAN 6 +#define TCF_EM_CANID 7 +#define TCF_EM_IPSET 8 +#define TCF_EM_IPT 9 +#define TCF_EM_MAX 9 + +enum { + TCF_EM_PROG_TC +}; + +enum { + TCF_EM_OPND_EQ, + TCF_EM_OPND_GT, + TCF_EM_OPND_LT +}; + +#endif diff --git a/tools/include/uapi/linux/tc_act/tc_bpf.h b/tools/include/uapi/linux/tc_act/tc_bpf.h new file mode 100644 index 000000000000..6e89a5df49a4 --- /dev/null +++ b/tools/include/uapi/linux/tc_act/tc_bpf.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * Copyright (c) 2015 Jiri Pirko + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __LINUX_TC_BPF_H +#define __LINUX_TC_BPF_H + +#include + +#define TCA_ACT_BPF 13 + +struct tc_act_bpf { + tc_gen; +}; + +enum { + TCA_ACT_BPF_UNSPEC, + TCA_ACT_BPF_TM, + TCA_ACT_BPF_PARMS, + TCA_ACT_BPF_OPS_LEN, + TCA_ACT_BPF_OPS, + TCA_ACT_BPF_FD, + TCA_ACT_BPF_NAME, + TCA_ACT_BPF_PAD, + TCA_ACT_BPF_TAG, + TCA_ACT_BPF_ID, + __TCA_ACT_BPF_MAX, +}; +#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1) + +#endif -- cgit v1.2.3 From 9137bb27e60e554dab694eafa4cca241fa3a694f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:53 +0100 Subject: x86/speculation: Add prctl() control for indirect branch speculation Add the PR_SPEC_INDIRECT_BRANCH option for the PR_GET_SPECULATION_CTRL and PR_SET_SPECULATION_CTRL prctls to allow fine grained per task control of indirect branch speculation via STIBP and IBPB. Invocations: Check indirect branch speculation status with - prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, 0, 0, 0); Enable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_ENABLE, 0, 0); Disable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_DISABLE, 0, 0); Force disable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_FORCE_DISABLE, 0, 0); See Documentation/userspace-api/spec_ctrl.rst. Signed-off-by: Tim Chen Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185005.866780996@linutronix.de --- Documentation/userspace-api/spec_ctrl.rst | 9 +++++ arch/x86/include/asm/nospec-branch.h | 1 + arch/x86/kernel/cpu/bugs.c | 67 +++++++++++++++++++++++++++++++ arch/x86/kernel/process.c | 5 +++ include/linux/sched.h | 9 +++++ include/uapi/linux/prctl.h | 1 + tools/include/uapi/linux/prctl.h | 1 + 7 files changed, 93 insertions(+) (limited to 'tools/include/uapi/linux') diff --git a/Documentation/userspace-api/spec_ctrl.rst b/Documentation/userspace-api/spec_ctrl.rst index 32f3d55c54b7..c4dbe6f7cdae 100644 --- a/Documentation/userspace-api/spec_ctrl.rst +++ b/Documentation/userspace-api/spec_ctrl.rst @@ -92,3 +92,12 @@ Speculation misfeature controls * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0); * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0); * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_FORCE_DISABLE, 0, 0); + +- PR_SPEC_INDIR_BRANCH: Indirect Branch Speculation in User Processes + (Mitigate Spectre V2 style attacks against user processes) + + Invocations: + * prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, 0, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_ENABLE, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_DISABLE, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_FORCE_DISABLE, 0, 0); diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index d4d35baf0430..2adbe7b047fa 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -232,6 +232,7 @@ enum spectre_v2_mitigation { enum spectre_v2_user_mitigation { SPECTRE_V2_USER_NONE, SPECTRE_V2_USER_STRICT, + SPECTRE_V2_USER_PRCTL, }; /* The Speculative Store Bypass disable variants */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 9cab538e10f1..74359fff87fd 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -566,6 +566,8 @@ void arch_smt_update(void) case SPECTRE_V2_USER_STRICT: update_stibp_strict(); break; + case SPECTRE_V2_USER_PRCTL: + break; } mutex_unlock(&spec_ctrl_mutex); @@ -752,12 +754,50 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) return 0; } +static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) +{ + switch (ctrl) { + case PR_SPEC_ENABLE: + if (spectre_v2_user == SPECTRE_V2_USER_NONE) + return 0; + /* + * Indirect branch speculation is always disabled in strict + * mode. + */ + if (spectre_v2_user == SPECTRE_V2_USER_STRICT) + return -EPERM; + task_clear_spec_ib_disable(task); + task_update_spec_tif(task); + break; + case PR_SPEC_DISABLE: + case PR_SPEC_FORCE_DISABLE: + /* + * Indirect branch speculation is always allowed when + * mitigation is force disabled. + */ + if (spectre_v2_user == SPECTRE_V2_USER_NONE) + return -EPERM; + if (spectre_v2_user == SPECTRE_V2_USER_STRICT) + return 0; + task_set_spec_ib_disable(task); + if (ctrl == PR_SPEC_FORCE_DISABLE) + task_set_spec_ib_force_disable(task); + task_update_spec_tif(task); + break; + default: + return -ERANGE; + } + return 0; +} + int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, unsigned long ctrl) { switch (which) { case PR_SPEC_STORE_BYPASS: return ssb_prctl_set(task, ctrl); + case PR_SPEC_INDIRECT_BRANCH: + return ib_prctl_set(task, ctrl); default: return -ENODEV; } @@ -790,11 +830,34 @@ static int ssb_prctl_get(struct task_struct *task) } } +static int ib_prctl_get(struct task_struct *task) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + return PR_SPEC_NOT_AFFECTED; + + switch (spectre_v2_user) { + case SPECTRE_V2_USER_NONE: + return PR_SPEC_ENABLE; + case SPECTRE_V2_USER_PRCTL: + if (task_spec_ib_force_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; + if (task_spec_ib_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_DISABLE; + return PR_SPEC_PRCTL | PR_SPEC_ENABLE; + case SPECTRE_V2_USER_STRICT: + return PR_SPEC_DISABLE; + default: + return PR_SPEC_NOT_AFFECTED; + } +} + int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) { switch (which) { case PR_SPEC_STORE_BYPASS: return ssb_prctl_get(task); + case PR_SPEC_INDIRECT_BRANCH: + return ib_prctl_get(task); default: return -ENODEV; } @@ -974,6 +1037,8 @@ static char *stibp_state(void) return ", STIBP: disabled"; case SPECTRE_V2_USER_STRICT: return ", STIBP: forced"; + case SPECTRE_V2_USER_PRCTL: + return ""; } return ""; } @@ -986,6 +1051,8 @@ static char *ibpb_state(void) return ", IBPB: disabled"; case SPECTRE_V2_USER_STRICT: return ", IBPB: always-on"; + case SPECTRE_V2_USER_PRCTL: + return ""; } } return ""; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index afbe2eb4a1c6..7d31192296a8 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -450,6 +450,11 @@ static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) set_tsk_thread_flag(tsk, TIF_SSBD); else clear_tsk_thread_flag(tsk, TIF_SSBD); + + if (task_spec_ib_disable(tsk)) + set_tsk_thread_flag(tsk, TIF_SPEC_IB); + else + clear_tsk_thread_flag(tsk, TIF_SPEC_IB); } /* Return the updated threadinfo flags*/ return task_thread_info(tsk)->flags; diff --git a/include/linux/sched.h b/include/linux/sched.h index a51c13c2b1a0..d607db5fcc6a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1453,6 +1453,8 @@ static inline bool is_percpu_thread(void) #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ +#define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ +#define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ @@ -1484,6 +1486,13 @@ TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) +TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable) +TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable) +TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable) + +TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) +TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) + static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index c0d7ea0bf5b6..b17201edfa09 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -212,6 +212,7 @@ struct prctl_mm_map { #define PR_SET_SPECULATION_CTRL 53 /* Speculation control variants */ # define PR_SPEC_STORE_BYPASS 0 +# define PR_SPEC_INDIRECT_BRANCH 1 /* Return and control values for PR_SET/GET_SPECULATION_CTRL */ # define PR_SPEC_NOT_AFFECTED 0 # define PR_SPEC_PRCTL (1UL << 0) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index c0d7ea0bf5b6..b17201edfa09 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -212,6 +212,7 @@ struct prctl_mm_map { #define PR_SET_SPECULATION_CTRL 53 /* Speculation control variants */ # define PR_SPEC_STORE_BYPASS 0 +# define PR_SPEC_INDIRECT_BRANCH 1 /* Return and control values for PR_SET/GET_SPECULATION_CTRL */ # define PR_SPEC_NOT_AFFECTED 0 # define PR_SPEC_PRCTL (1UL << 0) -- cgit v1.2.3 From b7df9ada9a7700dbcca1ba53d217c01e3d48179c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 1 Dec 2018 01:18:53 +0100 Subject: bpf: fix pointer offsets in context for 32 bit Currently, pointer offsets in three BPF context structures are broken in two scenarios: i) 32 bit compiled applications running on 64 bit kernels, and ii) LLVM compiled BPF programs running on 32 bit kernels. The latter is due to BPF target machine being strictly 64 bit. So in each of the cases the offsets will mismatch in verifier when checking / rewriting context access. Fix this by providing a helper macro __bpf_md_ptr() that will enforce padding up to 64 bit and proper alignment, and for context access a macro bpf_ctx_range_ptr() which will cover full 64 bit member range on 32 bit archs. For flow_keys, we additionally need to force the size check to sizeof(__u64) as with other pointer types. Fixes: d58e468b1112 ("flow_dissector: implements flow dissector BPF hook") Fixes: 4f738adba30a ("bpf: create tcp_bpf_ulp allowing BPF to monitor socket TX/RX data") Fixes: 2dbb9b9e6df6 ("bpf: Introduce BPF_PROG_TYPE_SK_REUSEPORT") Reported-by: David S. Miller Signed-off-by: Daniel Borkmann Acked-by: David S. Miller Tested-by: David S. Miller Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 7 +++++++ include/uapi/linux/bpf.h | 17 ++++++++++++----- net/core/filter.c | 16 ++++++++-------- tools/include/uapi/linux/bpf.h | 17 ++++++++++++----- 4 files changed, 39 insertions(+), 18 deletions(-) (limited to 'tools/include/uapi/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 448dcc448f1f..795ff0b869bb 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -449,6 +449,13 @@ struct sock_reuseport; offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2) \ offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1 +#if BITS_PER_LONG == 64 +# define bpf_ctx_range_ptr(TYPE, MEMBER) \ + offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 +#else +# define bpf_ctx_range_ptr(TYPE, MEMBER) \ + offsetof(TYPE, MEMBER) ... offsetof(TYPE, MEMBER) + 8 - 1 +#endif /* BITS_PER_LONG == 64 */ #define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ ({ \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 852dc17ab47a..426b5c8a245b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2422,6 +2422,12 @@ enum bpf_lwt_encap_mode { BPF_LWT_ENCAP_SEG6_INLINE }; +#define __bpf_md_ptr(type, name) \ +union { \ + type name; \ + __u64 :64; \ +} __attribute__((aligned(8))) + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -2456,7 +2462,7 @@ struct __sk_buff { /* ... here. */ __u32 data_meta; - struct bpf_flow_keys *flow_keys; + __bpf_md_ptr(struct bpf_flow_keys *, flow_keys); }; struct bpf_tunnel_key { @@ -2572,8 +2578,8 @@ enum sk_action { * be added to the end of this structure */ struct sk_msg_md { - void *data; - void *data_end; + __bpf_md_ptr(void *, data); + __bpf_md_ptr(void *, data_end); __u32 family; __u32 remote_ip4; /* Stored in network byte order */ @@ -2589,8 +2595,9 @@ struct sk_reuseport_md { * Start of directly accessible data. It begins from * the tcp/udp header. */ - void *data; - void *data_end; /* End of directly accessible data */ + __bpf_md_ptr(void *, data); + /* End of directly accessible data */ + __bpf_md_ptr(void *, data_end); /* * Total length of packet (starting from the tcp/udp header). * Note that the directly accessible bytes (data_end - data) diff --git a/net/core/filter.c b/net/core/filter.c index 9a1327eb25fa..6ee605da990f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5435,8 +5435,8 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type if (size != size_default) return false; break; - case bpf_ctx_range(struct __sk_buff, flow_keys): - if (size != sizeof(struct bpf_flow_keys *)) + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): + if (size != sizeof(__u64)) return false; break; default: @@ -5464,7 +5464,7 @@ static bool sk_filter_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): - case bpf_ctx_range(struct __sk_buff, flow_keys): + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; } @@ -5489,7 +5489,7 @@ static bool cg_skb_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range(struct __sk_buff, flow_keys): + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): @@ -5530,7 +5530,7 @@ static bool lwt_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range(struct __sk_buff, flow_keys): + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; } @@ -5756,7 +5756,7 @@ static bool tc_cls_act_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; - case bpf_ctx_range(struct __sk_buff, flow_keys): + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; } @@ -5958,7 +5958,7 @@ static bool sk_skb_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range(struct __sk_buff, flow_keys): + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; } @@ -6039,7 +6039,7 @@ static bool flow_dissector_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; - case bpf_ctx_range(struct __sk_buff, flow_keys): + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): info->reg_type = PTR_TO_FLOW_KEYS; break; case bpf_ctx_range(struct __sk_buff, tc_classid): diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 852dc17ab47a..426b5c8a245b 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2422,6 +2422,12 @@ enum bpf_lwt_encap_mode { BPF_LWT_ENCAP_SEG6_INLINE }; +#define __bpf_md_ptr(type, name) \ +union { \ + type name; \ + __u64 :64; \ +} __attribute__((aligned(8))) + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -2456,7 +2462,7 @@ struct __sk_buff { /* ... here. */ __u32 data_meta; - struct bpf_flow_keys *flow_keys; + __bpf_md_ptr(struct bpf_flow_keys *, flow_keys); }; struct bpf_tunnel_key { @@ -2572,8 +2578,8 @@ enum sk_action { * be added to the end of this structure */ struct sk_msg_md { - void *data; - void *data_end; + __bpf_md_ptr(void *, data); + __bpf_md_ptr(void *, data_end); __u32 family; __u32 remote_ip4; /* Stored in network byte order */ @@ -2589,8 +2595,9 @@ struct sk_reuseport_md { * Start of directly accessible data. It begins from * the tcp/udp header. */ - void *data; - void *data_end; /* End of directly accessible data */ + __bpf_md_ptr(void *, data); + /* End of directly accessible data */ + __bpf_md_ptr(void *, data_end); /* * Total length of packet (starting from the tcp/udp header). * Note that the directly accessible bytes (data_end - data) -- cgit v1.2.3 From f71c6143c2038df1cb43a4b9c90740d14f77467c Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Fri, 30 Nov 2018 15:32:20 -0800 Subject: bpf: Support sk lookup in netns with id 0 David Ahern and Nicolas Dichtel report that the handling of the netns id 0 is incorrect for the BPF socket lookup helpers: rather than finding the netns with id 0, it is resolving to the current netns. This renders the netns_id 0 inaccessible. To fix this, adjust the API for the netns to treat all negative s32 values as a lookup in the current netns (including u64 values which when truncated to s32 become negative), while any values with a positive value in the signed 32-bit integer space would result in a lookup for a socket in the netns corresponding to that id. As before, if the netns with that ID does not exist, no socket will be found. Any netns outside of these ranges will fail to find a corresponding socket, as those values are reserved for future usage. Signed-off-by: Joe Stringer Acked-by: Nicolas Dichtel Acked-by: Joey Pabalinas Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 35 ++++++++++++-------- net/core/filter.c | 11 ++++--- tools/include/uapi/linux/bpf.h | 39 +++++++++++++++-------- tools/testing/selftests/bpf/bpf_helpers.h | 4 +-- tools/testing/selftests/bpf/test_sk_lookup_kern.c | 18 +++++------ 5 files changed, 63 insertions(+), 44 deletions(-) (limited to 'tools/include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 426b5c8a245b..cba518c57229 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2170,7 +2170,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags) + * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) * Description * Look for TCP socket matching *tuple*, optionally in a child * network namespace *netns*. The return value must be checked, @@ -2187,12 +2187,14 @@ union bpf_attr { * **sizeof**\ (*tuple*\ **->ipv6**) * Look for an IPv6 socket. * - * If the *netns* is zero, then the socket lookup table in the - * netns associated with the *ctx* will be used. For the TC hooks, - * this in the netns of the device in the skb. For socket hooks, - * this in the netns of the socket. If *netns* is non-zero, then - * it specifies the ID of the netns relative to the netns - * associated with the *ctx*. + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. * * All values for *flags* are reserved for future usage, and must * be left at zero. @@ -2202,7 +2204,7 @@ union bpf_attr { * Return * Pointer to *struct bpf_sock*, or NULL in case of failure. * - * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags) + * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) * Description * Look for UDP socket matching *tuple*, optionally in a child * network namespace *netns*. The return value must be checked, @@ -2219,12 +2221,14 @@ union bpf_attr { * **sizeof**\ (*tuple*\ **->ipv6**) * Look for an IPv6 socket. * - * If the *netns* is zero, then the socket lookup table in the - * netns associated with the *ctx* will be used. For the TC hooks, - * this in the netns of the device in the skb. For socket hooks, - * this in the netns of the socket. If *netns* is non-zero, then - * it specifies the ID of the netns relative to the netns - * associated with the *ctx*. + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. * * All values for *flags* are reserved for future usage, and must * be left at zero. @@ -2405,6 +2409,9 @@ enum bpf_func_id { /* BPF_FUNC_perf_event_output for sk_buff input context. */ #define BPF_F_CTXLEN_MASK (0xfffffULL << 32) +/* Current network namespace */ +#define BPF_F_CURRENT_NETNS (-1L) + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, diff --git a/net/core/filter.c b/net/core/filter.c index 6ee605da990f..8d2c629501e2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4890,22 +4890,23 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, struct net *net; family = len == sizeof(tuple->ipv4) ? AF_INET : AF_INET6; - if (unlikely(family == AF_UNSPEC || netns_id > U32_MAX || flags)) + if (unlikely(family == AF_UNSPEC || flags || + !((s32)netns_id < 0 || netns_id <= S32_MAX))) goto out; if (skb->dev) caller_net = dev_net(skb->dev); else caller_net = sock_net(skb->sk); - if (netns_id) { + if ((s32)netns_id < 0) { + net = caller_net; + sk = sk_lookup(net, tuple, skb, family, proto); + } else { net = get_net_ns_by_id(caller_net, netns_id); if (unlikely(!net)) goto out; sk = sk_lookup(net, tuple, skb, family, proto); put_net(net); - } else { - net = caller_net; - sk = sk_lookup(net, tuple, skb, family, proto); } if (sk) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 426b5c8a245b..76b265c7d93e 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2170,7 +2170,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags) + * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) * Description * Look for TCP socket matching *tuple*, optionally in a child * network namespace *netns*. The return value must be checked, @@ -2187,12 +2187,14 @@ union bpf_attr { * **sizeof**\ (*tuple*\ **->ipv6**) * Look for an IPv6 socket. * - * If the *netns* is zero, then the socket lookup table in the - * netns associated with the *ctx* will be used. For the TC hooks, - * this in the netns of the device in the skb. For socket hooks, - * this in the netns of the socket. If *netns* is non-zero, then - * it specifies the ID of the netns relative to the netns - * associated with the *ctx*. + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. * * All values for *flags* are reserved for future usage, and must * be left at zero. @@ -2201,8 +2203,10 @@ union bpf_attr { * **CONFIG_NET** configuration option. * Return * Pointer to *struct bpf_sock*, or NULL in case of failure. + * For sockets with reuseport option, *struct bpf_sock* + * return is from reuse->socks[] using hash of the packet. * - * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags) + * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) * Description * Look for UDP socket matching *tuple*, optionally in a child * network namespace *netns*. The return value must be checked, @@ -2219,12 +2223,14 @@ union bpf_attr { * **sizeof**\ (*tuple*\ **->ipv6**) * Look for an IPv6 socket. * - * If the *netns* is zero, then the socket lookup table in the - * netns associated with the *ctx* will be used. For the TC hooks, - * this in the netns of the device in the skb. For socket hooks, - * this in the netns of the socket. If *netns* is non-zero, then - * it specifies the ID of the netns relative to the netns - * associated with the *ctx*. + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. * * All values for *flags* are reserved for future usage, and must * be left at zero. @@ -2233,6 +2239,8 @@ union bpf_attr { * **CONFIG_NET** configuration option. * Return * Pointer to *struct bpf_sock*, or NULL in case of failure. + * For sockets with reuseport option, *struct bpf_sock* + * return is from reuse->socks[] using hash of the packet. * * int bpf_sk_release(struct bpf_sock *sk) * Description @@ -2405,6 +2413,9 @@ enum bpf_func_id { /* BPF_FUNC_perf_event_output for sk_buff input context. */ #define BPF_F_CTXLEN_MASK (0xfffffULL << 32) +/* Current network namespace */ +#define BPF_F_CURRENT_NETNS (-1L) + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 686e57ce40f4..efb6c13ab0de 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -154,12 +154,12 @@ static unsigned long long (*bpf_skb_ancestor_cgroup_id)(void *ctx, int level) = (void *) BPF_FUNC_skb_ancestor_cgroup_id; static struct bpf_sock *(*bpf_sk_lookup_tcp)(void *ctx, struct bpf_sock_tuple *tuple, - int size, unsigned int netns_id, + int size, unsigned long long netns_id, unsigned long long flags) = (void *) BPF_FUNC_sk_lookup_tcp; static struct bpf_sock *(*bpf_sk_lookup_udp)(void *ctx, struct bpf_sock_tuple *tuple, - int size, unsigned int netns_id, + int size, unsigned long long netns_id, unsigned long long flags) = (void *) BPF_FUNC_sk_lookup_udp; static int (*bpf_sk_release)(struct bpf_sock *sk) = diff --git a/tools/testing/selftests/bpf/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/test_sk_lookup_kern.c index b745bdc08c2b..e21cd736c196 100644 --- a/tools/testing/selftests/bpf/test_sk_lookup_kern.c +++ b/tools/testing/selftests/bpf/test_sk_lookup_kern.c @@ -72,7 +72,7 @@ int bpf_sk_lookup_test0(struct __sk_buff *skb) return TC_ACT_SHOT; tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6); - sk = bpf_sk_lookup_tcp(skb, tuple, tuple_len, 0, 0); + sk = bpf_sk_lookup_tcp(skb, tuple, tuple_len, BPF_F_CURRENT_NETNS, 0); if (sk) bpf_sk_release(sk); return sk ? TC_ACT_OK : TC_ACT_UNSPEC; @@ -84,7 +84,7 @@ int bpf_sk_lookup_test1(struct __sk_buff *skb) struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; - sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0); + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); if (sk) bpf_sk_release(sk); return 0; @@ -97,7 +97,7 @@ int bpf_sk_lookup_uaf(struct __sk_buff *skb) struct bpf_sock *sk; __u32 family = 0; - sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0); + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); if (sk) { bpf_sk_release(sk); family = sk->family; @@ -112,7 +112,7 @@ int bpf_sk_lookup_modptr(struct __sk_buff *skb) struct bpf_sock *sk; __u32 family; - sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0); + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); if (sk) { sk += 1; bpf_sk_release(sk); @@ -127,7 +127,7 @@ int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb) struct bpf_sock *sk; __u32 family; - sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0); + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); sk += 1; if (sk) bpf_sk_release(sk); @@ -139,7 +139,7 @@ int bpf_sk_lookup_test2(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; - bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0); + bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); return 0; } @@ -149,7 +149,7 @@ int bpf_sk_lookup_test3(struct __sk_buff *skb) struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; - sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0); + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); bpf_sk_release(sk); bpf_sk_release(sk); return 0; @@ -161,7 +161,7 @@ int bpf_sk_lookup_test4(struct __sk_buff *skb) struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; - sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0); + sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); bpf_sk_release(sk); return 0; } @@ -169,7 +169,7 @@ int bpf_sk_lookup_test4(struct __sk_buff *skb) void lookup_no_release(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; - bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), 0, 0); + bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); } SEC("fail_no_release_subcall") -- cgit v1.2.3 From d74286d2c25ad29dbf9e342955dd8dc31f21653b Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Fri, 30 Nov 2018 15:32:21 -0800 Subject: bpf: Improve socket lookup reuseport documentation Improve the wording around socket lookup for reuseport sockets, and ensure that both bpf.h headers are in sync. Signed-off-by: Joe Stringer Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 4 ++++ tools/include/uapi/linux/bpf.h | 8 ++++---- 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'tools/include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index cba518c57229..72c453a8bf50 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2203,6 +2203,8 @@ union bpf_attr { * **CONFIG_NET** configuration option. * Return * Pointer to *struct bpf_sock*, or NULL in case of failure. + * For sockets with reuseport option, the *struct bpf_sock* + * result is from reuse->socks[] using the hash of the tuple. * * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) * Description @@ -2237,6 +2239,8 @@ union bpf_attr { * **CONFIG_NET** configuration option. * Return * Pointer to *struct bpf_sock*, or NULL in case of failure. + * For sockets with reuseport option, the *struct bpf_sock* + * result is from reuse->socks[] using the hash of the tuple. * * int bpf_sk_release(struct bpf_sock *sk) * Description diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 76b265c7d93e..72c453a8bf50 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2203,8 +2203,8 @@ union bpf_attr { * **CONFIG_NET** configuration option. * Return * Pointer to *struct bpf_sock*, or NULL in case of failure. - * For sockets with reuseport option, *struct bpf_sock* - * return is from reuse->socks[] using hash of the packet. + * For sockets with reuseport option, the *struct bpf_sock* + * result is from reuse->socks[] using the hash of the tuple. * * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) * Description @@ -2239,8 +2239,8 @@ union bpf_attr { * **CONFIG_NET** configuration option. * Return * Pointer to *struct bpf_sock*, or NULL in case of failure. - * For sockets with reuseport option, *struct bpf_sock* - * return is from reuse->socks[] using hash of the packet. + * For sockets with reuseport option, the *struct bpf_sock* + * result is from reuse->socks[] using the hash of the tuple. * * int bpf_sk_release(struct bpf_sock *sk) * Description -- cgit v1.2.3