diff options
Diffstat (limited to 'include/uapi/linux/bpf.h')
| -rw-r--r-- | include/uapi/linux/bpf.h | 265 |
1 files changed, 222 insertions, 43 deletions
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 431bc700bcfb..5a5cdb453935 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -42,6 +42,7 @@ #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_JCOND 0xe0 /* conditional pseudo jumps: may_goto, goto_or_nop */ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ @@ -50,6 +51,10 @@ #define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ #define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ +enum bpf_cond_pseudo_jmp { + BPF_MAY_GOTO = 0, +}; + /* Register numbers */ enum { BPF_REG_0 = 0, @@ -634,7 +639,11 @@ union bpf_iter_link_info { * to NULL to begin the batched operation. After each subsequent * **BPF_MAP_LOOKUP_BATCH**, the caller should pass the resultant * *out_batch* as the *in_batch* for the next operation to - * continue iteration from the current point. + * continue iteration from the current point. Both *in_batch* and + * *out_batch* must point to memory large enough to hold a key, + * except for maps of type **BPF_MAP_TYPE_{HASH, PERCPU_HASH, + * LRU_HASH, LRU_PERCPU_HASH}**, for which batch parameters + * must be at least 4 bytes wide regardless of key size. * * The *keys* and *values* are output parameters which must point * to memory large enough to hold *count* items based on the key @@ -864,6 +873,36 @@ union bpf_iter_link_info { * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. * + * BPF_TOKEN_CREATE + * Description + * Create BPF token with embedded information about what + * BPF-related functionality it allows: + * - a set of allowed bpf() syscall commands; + * - a set of allowed BPF map types to be created with + * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; + * - a set of allowed BPF program types and BPF program attach + * types to be loaded with BPF_PROG_LOAD command, if + * BPF_PROG_LOAD itself is allowed. + * + * BPF token is created (derived) from an instance of BPF FS, + * assuming it has necessary delegation mount options specified. + * This BPF token can be passed as an extra parameter to various + * bpf() syscall commands to grant BPF subsystem functionality to + * unprivileged processes. + * + * When created, BPF token is "associated" with the owning + * user namespace of BPF FS instance (super block) that it was + * derived from, and subsequent BPF operations performed with + * BPF token would be performing capabilities checks (i.e., + * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within + * that user namespace. Without BPF token, such capabilities + * have to be granted in init user namespace, making bpf() + * syscall incompatible with user namespace, for the most part. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -918,6 +957,8 @@ enum bpf_cmd { BPF_ITER_CREATE, BPF_LINK_DETACH, BPF_PROG_BIND_MAP, + BPF_TOKEN_CREATE, + __MAX_BPF_CMD, }; enum bpf_map_type { @@ -949,7 +990,14 @@ enum bpf_map_type { */ BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, - BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED, + /* BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE is available to bpf programs + * attaching to a cgroup. The new mechanism (BPF_MAP_TYPE_CGRP_STORAGE + + * local percpu kptr) supports all BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE + * functionality and more. So mark * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE + * deprecated. + */ + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED, BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, BPF_MAP_TYPE_SK_STORAGE, @@ -961,6 +1009,8 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + BPF_MAP_TYPE_ARENA, + __MAX_BPF_MAP_TYPE }; /* Note that tracing related programs such as @@ -1005,6 +1055,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1057,11 +1108,22 @@ enum bpf_attach_type { BPF_TCX_INGRESS, BPF_TCX_EGRESS, BPF_TRACE_UPROBE_MULTI, + BPF_CGROUP_UNIX_CONNECT, + BPF_CGROUP_UNIX_SENDMSG, + BPF_CGROUP_UNIX_RECVMSG, + BPF_CGROUP_UNIX_GETPEERNAME, + BPF_CGROUP_UNIX_GETSOCKNAME, + BPF_NETKIT_PRIMARY, + BPF_NETKIT_PEER, + BPF_TRACE_KPROBE_SESSION, __MAX_BPF_ATTACH_TYPE }; #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE +/* Add BPF_LINK_TYPE(type, name) in bpf_types.h to keep bpf_link_type_strs[] + * in sync with the definitions below. + */ enum bpf_link_type { BPF_LINK_TYPE_UNSPEC = 0, BPF_LINK_TYPE_RAW_TRACEPOINT = 1, @@ -1076,9 +1138,13 @@ enum bpf_link_type { BPF_LINK_TYPE_NETFILTER = 10, BPF_LINK_TYPE_TCX = 11, BPF_LINK_TYPE_UPROBE_MULTI = 12, - MAX_BPF_LINK_TYPE, + BPF_LINK_TYPE_NETKIT = 13, + BPF_LINK_TYPE_SOCKMAP = 14, + __MAX_BPF_LINK_TYPE, }; +#define MAX_BPF_LINK_TYPE __MAX_BPF_LINK_TYPE + enum bpf_perf_event_type { BPF_PERF_EVENT_UNSPEC = 0, BPF_PERF_EVENT_UPROBE = 1, @@ -1140,6 +1206,7 @@ enum bpf_perf_event_type { #define BPF_F_BEFORE (1U << 3) #define BPF_F_AFTER (1U << 4) #define BPF_F_ID (1U << 5) +#define BPF_F_PREORDER (1U << 6) #define BPF_F_LINK BPF_F_LINK /* 1 << 13 */ /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the @@ -1202,6 +1269,9 @@ enum bpf_perf_event_type { */ #define BPF_F_XDP_DEV_BOUND_ONLY (1U << 6) +/* The verifier internal test flag. Behavior is undefined */ +#define BPF_F_TEST_REG_INVARIANTS (1U << 7) + /* link_create.kprobe_multi.flags used in LINK_CREATE command for * BPF_TRACE_KPROBE_MULTI attach type to create return probe. */ @@ -1275,6 +1345,10 @@ enum { */ #define BPF_PSEUDO_KFUNC_CALL 2 +enum bpf_addr_space_cast { + BPF_ADDR_SPACE_CAST = 1, +}; + /* flags for BPF_MAP_UPDATE_ELEM command */ enum { BPF_ANY = 0, /* create new element or update existing */ @@ -1327,6 +1401,18 @@ enum { /* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ BPF_F_PATH_FD = (1U << 14), + +/* Flag for value_type_btf_obj_fd, the fd is available */ + BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15), + +/* BPF token FD is passed in a corresponding command's token_fd field */ + BPF_F_TOKEN_FD = (1U << 16), + +/* When user space page faults in bpf_arena send SIGSEGV instead of inserting new page */ + BPF_F_SEGV_ON_FAULT = (1U << 17), + +/* Do not translate kernel bpf_arena pointers to user pointers */ + BPF_F_NO_USER_CONV = (1U << 18), }; /* Flags for BPF_PROG_QUERY. */ @@ -1343,6 +1429,8 @@ enum { #define BPF_F_TEST_RUN_ON_CPU (1U << 0) /* If set, XDP frames will be transmitted after processing */ #define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1) +/* If set, apply CHECKSUM_COMPLETE to skb and validate the checksum */ +#define BPF_F_TEST_SKB_CHECKSUM_COMPLETE (1U << 2) /* type for BPF_ENABLE_STATS */ enum bpf_stats_type { @@ -1398,8 +1486,20 @@ union bpf_attr { * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the * number of hash functions (if 0, the bloom filter will default * to using 5 hash functions). + * + * BPF_MAP_TYPE_ARENA - contains the address where user space + * is going to mmap() the arena. It has to be page aligned. */ __u64 map_extra; + + __s32 value_type_btf_obj_fd; /* fd pointing to a BTF + * type data for + * btf_vmlinux_value_type_id. + */ + /* BPF token FD to use with BPF_MAP_CREATE operation. + * If provided, map_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 map_token_fd; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -1469,6 +1569,10 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; + /* BPF token FD to use with BPF_PROG_LOAD operation. + * If provided, prog_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -1566,8 +1670,10 @@ union bpf_attr { } query; struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ - __u64 name; - __u32 prog_fd; + __u64 name; + __u32 prog_fd; + __u32 :32; + __aligned_u64 cookie; } raw_tracepoint; struct { /* anonymous struct for BPF_BTF_LOAD */ @@ -1581,6 +1687,11 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 btf_log_true_size; + __u32 btf_flags; + /* BPF token FD to use with BPF_BTF_LOAD operation. + * If provided, btf_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 btf_token_fd; }; struct { @@ -1661,6 +1772,13 @@ union bpf_attr { __u32 flags; __u32 pid; } uprobe_multi; + struct { + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; + } netkit; }; } link_create; @@ -1704,6 +1822,11 @@ union bpf_attr { __u32 flags; /* extra flags */ } prog_bind_map; + struct { /* struct used by BPF_TOKEN_CREATE command */ + __u32 flags; + __u32 bpffs_fd; + } token_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF @@ -1912,6 +2035,7 @@ union bpf_attr { * for updates resulting in a null checksum the value is set to * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates * the checksum is to be computed against a pseudo-header. + * Flag **BPF_F_IPV6** should be set for IPv6 packets. * * This helper works in combination with **bpf_csum_diff**\ (), * which does not update the checksum in-place, but offers more @@ -2714,8 +2838,8 @@ union bpf_attr { * *bpf_socket* should be one of the following: * * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. - * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** - * and **BPF_CGROUP_INET6_CONNECT**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**, + * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**. * * This helper actually implements a subset of **setsockopt()**. * It supports the following *level*\ s: @@ -2732,7 +2856,7 @@ union bpf_attr { * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**, * **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**, * **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**, - * **TCP_BPF_RTO_MIN**. + * **TCP_BPF_RTO_MIN**, **TCP_BPF_SOCK_OPS_CB_FLAGS**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. * * **IPPROTO_IPV6**, which supports the following *optname*\ s: * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**. @@ -2953,8 +3077,8 @@ union bpf_attr { * *bpf_socket* should be one of the following: * * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. - * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** - * and **BPF_CGROUP_INET6_CONNECT**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**, + * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**. * * This helper actually implements a subset of **getsockopt()**. * It supports the same set of *optname*\ s that is supported by @@ -3279,6 +3403,10 @@ union bpf_attr { * for the nexthop. If the src addr cannot be derived, * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this * case, *params*->dmac and *params*->smac are not set either. + * **BPF_FIB_LOOKUP_MARK** + * Use the mark present in *params*->mark for the fib lookup. + * This option should not be used with BPF_FIB_LOOKUP_DIRECT, + * as it only has meaning for full lookups. * * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. @@ -4829,9 +4957,9 @@ union bpf_attr { * going through the CPU's backlog queue. * * The *flags* argument is reserved and must be 0. The helper is - * currently only supported for tc BPF program types at the ingress - * hook and for veth device types. The peer device must reside in a - * different network namespace. + * currently only supported for tc BPF program types at the + * ingress hook and for veth and netkit target device types. The + * peer device must reside in a different network namespace. * Return * The helper returns **TC_ACT_REDIRECT** on success or * **TC_ACT_SHOT** on error. @@ -4907,7 +5035,7 @@ union bpf_attr { * bytes will be copied to *dst* * Return * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * **-EOPNOTSUPP** if IMA is disabled or **-EINVAL** if * invalid arguments are passed. * * struct socket *bpf_sock_from_file(struct file *file) @@ -5114,6 +5242,8 @@ union bpf_attr { * **BPF_F_TIMER_ABS** * Start the timer in absolute expire value instead of the * default relative one. + * **BPF_F_TIMER_CPU_PIN** + * Timer will be pinned to the CPU of the caller. * * Return * 0 on success. @@ -5391,14 +5521,15 @@ union bpf_attr { * bytes will be copied to *dst* * Return * The **hash_algo** is returned on success, - * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if + * **-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if * invalid arguments are passed. * - * void *bpf_kptr_xchg(void *map_value, void *ptr) + * void *bpf_kptr_xchg(void *dst, void *ptr) * Description - * Exchange kptr at pointer *map_value* with *ptr*, and return the - * old value. *ptr* can be NULL, otherwise it must be a referenced - * pointer which will be released when this helper is called. + * Exchange kptr at pointer *dst* with *ptr*, and return the old value. + * *dst* can be map value or local kptr. *ptr* can be NULL, otherwise + * it must be a referenced pointer which will be released when this helper + * is called. * Return * The old value of kptr (which can be NULL). The returned pointer * if not NULL, is a reference which must be released using its @@ -5919,6 +6050,7 @@ enum { BPF_F_PSEUDO_HDR = (1ULL << 4), BPF_F_MARK_MANGLED_0 = (1ULL << 5), BPF_F_MARK_ENFORCE = (1ULL << 6), + BPF_F_IPV6 = (1ULL << 7), }; /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ @@ -6081,12 +6213,17 @@ union { \ __u64 :64; \ } __attribute__((aligned(8))) +/* The enum used in skb->tstamp_type. It specifies the clock type + * of the time stored in the skb->tstamp. + */ enum { - BPF_SKB_TSTAMP_UNSPEC, - BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */ - /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle, - * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC - * and try to deduce it by ingress, egress or skb->sk->sk_clockid. + BPF_SKB_TSTAMP_UNSPEC = 0, /* DEPRECATED */ + BPF_SKB_TSTAMP_DELIVERY_MONO = 1, /* DEPRECATED */ + BPF_SKB_CLOCK_REALTIME = 0, + BPF_SKB_CLOCK_MONOTONIC = 1, + BPF_SKB_CLOCK_TAI = 2, + /* For any future BPF_SKB_CLOCK_* that the bpf prog cannot handle, + * the bpf prog can try to deduce it by ingress/egress/skb->sk->sk_clockid. */ }; @@ -6472,7 +6609,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; - __u32 :32; /* alignment pad */ + __u32 btf_vmlinux_id; __u64 map_extra; } __attribute__((aligned(8))); @@ -6547,8 +6684,20 @@ struct bpf_link_info { __aligned_u64 addrs; __u32 count; /* in/out: kprobe_multi function count */ __u32 flags; + __u64 missed; + __aligned_u64 cookies; } kprobe_multi; struct { + __aligned_u64 path; + __aligned_u64 offsets; + __aligned_u64 ref_ctr_offsets; + __aligned_u64 cookies; + __u32 path_size; /* in/out: real path size on success, including zero byte */ + __u32 count; /* in/out: uprobe_multi offsets/ref_ctr_offsets/cookies count */ + __u32 flags; + __u32 pid; + } uprobe_multi; + struct { __u32 type; /* enum bpf_perf_event_type */ __u32 :32; union { @@ -6584,6 +6733,14 @@ struct bpf_link_info { __u32 ifindex; __u32 attach_type; } tcx; + struct { + __u32 ifindex; + __u32 attach_type; + } netkit; + struct { + __u32 map_id; + __u32 attach_type; + } sockmap; }; } __attribute__((aligned(8))); @@ -6802,6 +6959,8 @@ enum { * socket transition to LISTEN state. */ BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. + * Arg1: measured RTT input (mrtt) + * Arg2: updated srtt */ BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option. * It will be called to handle @@ -6880,6 +7039,7 @@ enum { BPF_TCP_LISTEN, BPF_TCP_CLOSING, /* Now a valid state */ BPF_TCP_NEW_SYN_RECV, + BPF_TCP_BOUND_INACTIVE, BPF_TCP_MAX_STATES /* Leave at the end! */ }; @@ -6924,6 +7084,7 @@ enum { TCP_BPF_SYN = 1005, /* Copy the TCP header */ TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */ TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */ + TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */ }; enum { @@ -6983,6 +7144,7 @@ enum { BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), BPF_FIB_LOOKUP_TBID = (1U << 3), BPF_FIB_LOOKUP_SRC = (1U << 4), + BPF_FIB_LOOKUP_MARK = (1U << 5), }; enum { @@ -7060,8 +7222,19 @@ struct bpf_fib_lookup { __u32 tbid; }; - __u8 smac[6]; /* ETH_ALEN */ - __u8 dmac[6]; /* ETH_ALEN */ + union { + /* input */ + struct { + __u32 mark; /* policy routing */ + /* 2 4-byte holes for input */ + }; + + /* output: source and dest mac */ + struct { + __u8 smac[6]; /* ETH_ALEN */ + __u8 dmac[6]; /* ETH_ALEN */ + }; + }; }; struct bpf_redir_neigh { @@ -7145,40 +7318,35 @@ struct bpf_spin_lock { }; struct bpf_timer { - __u64 :64; - __u64 :64; + __u64 __opaque[2]; +} __attribute__((aligned(8))); + +struct bpf_wq { + __u64 __opaque[2]; } __attribute__((aligned(8))); struct bpf_dynptr { - __u64 :64; - __u64 :64; + __u64 __opaque[2]; } __attribute__((aligned(8))); struct bpf_list_head { - __u64 :64; - __u64 :64; + __u64 __opaque[2]; } __attribute__((aligned(8))); struct bpf_list_node { - __u64 :64; - __u64 :64; - __u64 :64; + __u64 __opaque[3]; } __attribute__((aligned(8))); struct bpf_rb_root { - __u64 :64; - __u64 :64; + __u64 __opaque[2]; } __attribute__((aligned(8))); struct bpf_rb_node { - __u64 :64; - __u64 :64; - __u64 :64; - __u64 :64; + __u64 __opaque[4]; } __attribute__((aligned(8))); struct bpf_refcount { - __u32 :32; + __u32 __opaque[1]; } __attribute__((aligned(4))); struct bpf_sysctl { @@ -7334,9 +7502,11 @@ struct bpf_core_relo { * Flags to control bpf_timer_start() behaviour. * - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is * relative to current time. + * - BPF_F_TIMER_CPU_PIN: Timer will be pinned to the CPU of the caller. */ enum { BPF_F_TIMER_ABS = (1ULL << 0), + BPF_F_TIMER_CPU_PIN = (1ULL << 1), }; /* BPF numbers iterator state */ @@ -7347,4 +7517,13 @@ struct bpf_iter_num { __u64 __opaque[1]; } __attribute__((aligned(8))); +/* + * Flags to control BPF kfunc behaviour. + * - BPF_F_PAD_ZEROS: Pad destination buffer with zeros. (See the respective + * helper documentation for details.) + */ +enum bpf_kfunc_flags { + BPF_F_PAD_ZEROS = (1ULL << 0), +}; + #endif /* _UAPI__LINUX_BPF_H__ */ |