__u32 attach_type; /* program attach type (enum bpf_attach_type) */
};
+enum bpf_cgroup_iter_order {
+ BPF_CGROUP_ITER_ORDER_UNSPEC = 0,
+ BPF_CGROUP_ITER_SELF_ONLY, /* process only a single object. */
+ BPF_CGROUP_ITER_DESCENDANTS_PRE, /* walk descendants in pre-order. */
+ BPF_CGROUP_ITER_DESCENDANTS_POST, /* walk descendants in post-order. */
+ BPF_CGROUP_ITER_ANCESTORS_UP, /* walk ancestors upward. */
+};
+
union bpf_iter_link_info {
struct {
__u32 map_fd;
} map;
+ struct {
+ enum bpf_cgroup_iter_order order;
+
+ /* At most one of cgroup_fd and cgroup_id can be non-zero. If
+ * both are zero, the walk starts from the default cgroup v2
+ * root. For walking v1 hierarchy, one should always explicitly
+ * specify cgroup_fd.
+ */
+ __u32 cgroup_fd;
+ __u64 cgroup_id;
+ } cgroup;
+ /* Parameters of task iterators. */
+ struct {
+ __u32 tid;
+ __u32 pid;
+ __u32 pid_fd;
+ } task;
};
/* BPF syscall commands, see bpf(2) man-page for more details. */
BPF_MAP_TYPE_CPUMAP,
BPF_MAP_TYPE_XSKMAP,
BPF_MAP_TYPE_SOCKHASH,
- BPF_MAP_TYPE_CGROUP_STORAGE,
+ BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED,
+ /* BPF_MAP_TYPE_CGROUP_STORAGE is available to bpf programs attaching
+ * to a cgroup. The newer BPF_MAP_TYPE_CGRP_STORAGE is available to
+ * both cgroup-attached and other progs and supports all functionality
+ * provided by BPF_MAP_TYPE_CGROUP_STORAGE. So mark
+ * BPF_MAP_TYPE_CGROUP_STORAGE deprecated.
+ */
+ 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_QUEUE,
BPF_MAP_TYPE_INODE_STORAGE,
BPF_MAP_TYPE_TASK_STORAGE,
BPF_MAP_TYPE_BLOOM_FILTER,
+ BPF_MAP_TYPE_USER_RINGBUF,
+ BPF_MAP_TYPE_CGRP_STORAGE,
};
/* Note that tracing related programs such as
*/
#define BPF_F_XDP_HAS_FRAGS (1U << 5)
+/* If BPF_F_XDP_DEV_BOUND_ONLY is used in BPF_PROG_LOAD command, the loaded
+ * program becomes device-bound but can access XDP metadata.
+ */
+#define BPF_F_XDP_DEV_BOUND_ONLY (1U << 6)
+
/* link_create.kprobe_multi.flags used in LINK_CREATE command for
* BPF_TRACE_KPROBE_MULTI attach type to create return probe.
*/
/* Query effective (directly attached + inherited from ancestor cgroups)
* programs that will be executed for events within a cgroup.
- * attach_flags with this flag are returned only for directly attached programs.
+ * attach_flags with this flag are always returned 0.
*/
#define BPF_F_QUERY_EFFECTIVE (1U << 0)
__u32 attach_flags;
__aligned_u64 prog_ids;
__u32 prog_cnt;
- __aligned_u64 prog_attach_flags; /* output: per-program attach_flags */
+ /* output: per-program attach_flags.
+ * not allowed to be set during effective query.
+ */
+ __aligned_u64 prog_attach_flags;
} query;
struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
* sending the packet. This flag was added for GRE
* encapsulation, but might be used with other protocols
* as well in the future.
+ * **BPF_F_NO_TUNNEL_KEY**
+ * Add a flag to tunnel metadata indicating that no tunnel
+ * key should be set in the resulting tunnel header.
*
* Here is a typical usage on the transmit path:
*
* * **SOL_SOCKET**, which supports the following *optname*\ s:
* **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**,
* **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**,
- * **SO_BINDTODEVICE**, **SO_KEEPALIVE**.
+ * **SO_BINDTODEVICE**, **SO_KEEPALIVE**, **SO_REUSEADDR**,
+ * **SO_REUSEPORT**, **SO_BINDTOIFINDEX**, **SO_TXREHASH**.
* * **IPPROTO_TCP**, which supports the following *optname*\ s:
* **TCP_CONGESTION**, **TCP_BPF_IW**,
* **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**,
* **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**,
- * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**.
+ * **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**.
* * **IPPROTO_IP**, which supports *optname* **IP_TOS**.
- * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
+ * * **IPPROTO_IPV6**, which supports the following *optname*\ s:
+ * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**.
* Return
* 0 on success, or a negative error in case of failure.
*
* There are two supported modes at this time:
*
* * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
- * (room space is added or removed below the layer 2 header).
+ * (room space is added or removed between the layer 2 and
+ * layer 3 headers).
*
* * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
- * (room space is added or removed below the layer 3 header).
+ * (room space is added or removed between the layer 3 and
+ * layer 4 headers).
*
* The following flags are supported at this time:
*
* Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the
* L2 type as Ethernet.
*
+ * * **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**,
+ * **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**:
+ * Indicate the new IP header version after decapsulating the outer
+ * IP header. Used when the inner and outer IP versions are different.
+ *
* A call to this helper is susceptible to change the underlying
* packet buffer. Therefore, at load time, all checks on pointers
* previously done by the verifier are invalidated and must be
* Return
* 0 on success, or a negative error in case of failure.
*
- * long bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags)
+ * long bpf_redirect_map(struct bpf_map *map, u64 key, u64 flags)
* Description
* Redirect the packet to the endpoint referenced by *map* at
* index *key*. Depending on its type, this *map* can contain
*
* long bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size)
* Description
- * For en eBPF program attached to a perf event, retrieve the
+ * For an eBPF program attached to a perf event, retrieve the
* value of the event counter associated to *ctx* and store it in
* the structure pointed by *buf* and of size *buf_size*. Enabled
* and running times are also stored in the structure (see
* and **BPF_CGROUP_INET6_CONNECT**.
*
* This helper actually implements a subset of **getsockopt()**.
- * It supports the following *level*\ s:
- *
- * * **IPPROTO_TCP**, which supports *optname*
- * **TCP_CONGESTION**.
- * * **IPPROTO_IP**, which supports *optname* **IP_TOS**.
- * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
+ * It supports the same set of *optname*\ s that is supported by
+ * the **bpf_setsockopt**\ () helper. The exceptions are
+ * **TCP_BPF_*** is **bpf_setsockopt**\ () only and
+ * **TCP_SAVED_SYN** is **bpf_getsockopt**\ () only.
* Return
* 0 on success, or a negative error in case of failure.
*
* **BPF_F_USER_STACK**
* Collect a user space stack instead of a kernel stack.
* **BPF_F_USER_BUILD_ID**
- * Collect buildid+offset instead of ips for user stack,
- * only valid if **BPF_F_USER_STACK** is also specified.
+ * Collect (build_id, file_offset) instead of ips for user
+ * stack, only valid if **BPF_F_USER_STACK** is also
+ * specified.
+ *
+ * *file_offset* is an offset relative to the beginning
+ * of the executable or shared object file backing the vma
+ * which the *ip* falls in. It is *not* an offset relative
+ * to that object's base address. Accordingly, it must be
+ * adjusted by adding (sh_addr - sh_offset), where
+ * sh_{addr,offset} correspond to the executable section
+ * containing *file_offset* in the object, for comparisons
+ * to symbols' st_value to be valid.
*
* **bpf_get_stack**\ () can collect up to
* **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
* **BPF_FIB_LOOKUP_OUTPUT**
* Perform lookup from an egress perspective (default is
* ingress).
+ * **BPF_FIB_LOOKUP_SKIP_NEIGH**
+ * Skip the neighbour table lookup. *params*->dmac
+ * and *params*->smac will not be set as output. A common
+ * use case is to call **bpf_redirect_neigh**\ () after
+ * doing **bpf_fib_lookup**\ ().
*
* *ctx* is either **struct xdp_md** for XDP programs or
* **struct sk_buff** tc cls_act programs.
*
* **-EEXIST** if the option already exists.
*
- * **-EFAULT** on failrue to parse the existing header options.
+ * **-EFAULT** on failure to parse the existing header options.
*
* **-EPERM** if the helper cannot be used under the current
* *skops*\ **->op**.
* a *map* with *task* as the **key**. From this
* perspective, the usage is not much different from
* **bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
- * helper enforces the key must be an task_struct and the map must also
+ * helper enforces the key must be a task_struct and the map must also
* be a **BPF_MAP_TYPE_TASK_STORAGE**.
*
* Underneath, the value is stored locally at *task* instead of
*
* long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size)
* Description
- * Returns the stored IMA hash of the *inode* (if it's avaialable).
+ * Returns the stored IMA hash of the *inode* (if it's available).
* If the hash is larger than *size*, then only *size*
* bytes will be copied to *dst*
* Return
*
* The argument *len_diff* can be used for querying with a planned
* size change. This allows to check MTU prior to changing packet
- * ctx. Providing an *len_diff* adjustment that is larger than the
+ * ctx. Providing a *len_diff* adjustment that is larger than the
* actual packet size (resulting in negative packet size) will in
- * principle not exceed the MTU, why it is not considered a
- * failure. Other BPF-helpers are needed for performing the
- * planned size change, why the responsability for catch a negative
- * packet size belong in those helpers.
+ * principle not exceed the MTU, which is why it is not considered
+ * a failure. Other BPF helpers are needed for performing the
+ * planned size change; therefore the responsibility for catching
+ * a negative packet size belongs in those helpers.
*
* Specifying *ifindex* zero means the MTU check is performed
* against the current net device. This is practical if this isn't
* Get address of the traced function (for tracing and kprobe programs).
* Return
* Address of the traced function.
+ * 0 for kprobes placed within the function (not at the entry).
*
* u64 bpf_get_attach_cookie(void *ctx)
* Description
*
* long bpf_get_func_arg(void *ctx, u32 n, u64 *value)
* Description
- * Get **n**-th argument (zero based) of the traced function (for tracing programs)
+ * Get **n**-th argument register (zero based) of the traced function (for tracing programs)
* returned in **value**.
*
* Return
* 0 on success.
- * **-EINVAL** if n >= arguments count of traced function.
+ * **-EINVAL** if n >= argument register count of traced function.
*
* long bpf_get_func_ret(void *ctx, u64 *value)
* Description
*
* long bpf_get_func_arg_cnt(void *ctx)
* Description
- * Get number of arguments of the traced function (for tracing programs).
+ * Get number of registers of the traced function (for tracing programs) where
+ * function arguments are stored in these registers.
*
* Return
- * The number of arguments of the traced function.
+ * The number of argument registers of the traced function.
*
* int bpf_get_retval(void)
* Description
- * Get the syscall's return value that will be returned to userspace.
+ * Get the BPF program's return value that will be returned to the upper layers.
*
- * This helper is currently supported by cgroup programs only.
+ * This helper is currently supported by cgroup programs and only by the hooks
+ * where BPF program's return value is returned to the userspace via errno.
* Return
- * The syscall's return value.
+ * The BPF program's return value.
*
* int bpf_set_retval(int retval)
* Description
- * Set the syscall's return value that will be returned to userspace.
+ * Set the BPF program's return value that will be returned to the upper layers.
+ *
+ * This helper is currently supported by cgroup programs and only by the hooks
+ * where BPF program's return value is returned to the userspace via errno.
+ *
+ * Note that there is the following corner case where the program exports an error
+ * via bpf_set_retval but signals success via 'return 1':
+ *
+ * bpf_set_retval(-EPERM);
+ * return 1;
+ *
+ * In this case, the BPF program's return value will use helper's -EPERM. This
+ * still holds true for cgroup/bind{4,6} which supports extra 'return 3' success case.
*
- * This helper is currently supported by cgroup programs only.
* Return
* 0 on success, or a negative error in case of failure.
*
* Return
* Nothing. Always succeeds.
*
- * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset, u64 flags)
+ * long bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr *src, u32 offset, u64 flags)
* Description
* Read *len* bytes from *src* into *dst*, starting from *offset*
* into *src*.
* of *src*'s data, -EINVAL if *src* is an invalid dynptr or if
* *flags* is not 0.
*
- * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags)
+ * long bpf_dynptr_write(const struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags)
* Description
* Write *len* bytes from *src* into *dst*, starting from *offset*
* into *dst*.
* of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
* is a read-only dynptr or if *flags* is not 0.
*
- * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len)
+ * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u32 offset, u32 len)
* Description
* Get a pointer to the underlying dynptr data.
*
* **-EACCES** if the SYN cookie is not valid.
*
* **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ *
+ * u64 bpf_ktime_get_tai_ns(void)
+ * Description
+ * A nonsettable system-wide clock derived from wall-clock time but
+ * ignoring leap seconds. This clock does not experience
+ * discontinuities and backwards jumps caused by NTP inserting leap
+ * seconds as CLOCK_REALTIME does.
+ *
+ * See: **clock_gettime**\ (**CLOCK_TAI**)
+ * Return
+ * Current *ktime*.
+ *
+ * long bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void *ctx, u64 flags)
+ * Description
+ * Drain samples from the specified user ring buffer, and invoke
+ * the provided callback for each such sample:
+ *
+ * long (\*callback_fn)(const struct bpf_dynptr \*dynptr, void \*ctx);
+ *
+ * If **callback_fn** returns 0, the helper will continue to try
+ * and drain the next sample, up to a maximum of
+ * BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1,
+ * the helper will skip the rest of the samples and return. Other
+ * return values are not used now, and will be rejected by the
+ * verifier.
+ * Return
+ * The number of drained samples if no error was encountered while
+ * draining samples, or 0 if no samples were present in the ring
+ * buffer. If a user-space producer was epoll-waiting on this map,
+ * and at least one sample was drained, they will receive an event
+ * notification notifying them of available space in the ring
+ * buffer. If the BPF_RB_NO_WAKEUP flag is passed to this
+ * function, no wakeup notification will be sent. If the
+ * BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will
+ * be sent even if no sample was drained.
+ *
+ * On failure, the returned value is one of the following:
+ *
+ * **-EBUSY** if the ring buffer is contended, and another calling
+ * context was concurrently draining the ring buffer.
+ *
+ * **-EINVAL** if user-space is not properly tracking the ring
+ * buffer due to the producer position not being aligned to 8
+ * bytes, a sample not being aligned to 8 bytes, or the producer
+ * position not matching the advertised length of a sample.
+ *
+ * **-E2BIG** if user-space has tried to publish a sample which is
+ * larger than the size of the ring buffer, or which cannot fit
+ * within a struct bpf_dynptr.
+ *
+ * void *bpf_cgrp_storage_get(struct bpf_map *map, struct cgroup *cgroup, void *value, u64 flags)
+ * Description
+ * Get a bpf_local_storage from the *cgroup*.
+ *
+ * Logically, it could be thought of as getting the value from
+ * a *map* with *cgroup* as the **key**. From this
+ * perspective, the usage is not much different from
+ * **bpf_map_lookup_elem**\ (*map*, **&**\ *cgroup*) except this
+ * helper enforces the key must be a cgroup struct and the map must also
+ * be a **BPF_MAP_TYPE_CGRP_STORAGE**.
+ *
+ * In reality, the local-storage value is embedded directly inside of the
+ * *cgroup* object itself, rather than being located in the
+ * **BPF_MAP_TYPE_CGRP_STORAGE** map. When the local-storage value is
+ * queried for some *map* on a *cgroup* object, the kernel will perform an
+ * O(n) iteration over all of the live local-storage values for that
+ * *cgroup* object until the local-storage value for the *map* is found.
+ *
+ * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ * used such that a new bpf_local_storage will be
+ * created if one does not exist. *value* can be used
+ * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ * the initial value of a bpf_local_storage. If *value* is
+ * **NULL**, the new bpf_local_storage will be zero initialized.
+ * Return
+ * A bpf_local_storage pointer is returned on success.
+ *
+ * **NULL** if not found or there was an error in adding
+ * a new bpf_local_storage.
+ *
+ * long bpf_cgrp_storage_delete(struct bpf_map *map, struct cgroup *cgroup)
+ * Description
+ * Delete a bpf_local_storage from a *cgroup*.
+ * Return
+ * 0 on success.
+ *
+ * **-ENOENT** if the bpf_local_storage cannot be found.
*/
-#define __BPF_FUNC_MAPPER(FN) \
- FN(unspec), \
- FN(map_lookup_elem), \
- FN(map_update_elem), \
- FN(map_delete_elem), \
- FN(probe_read), \
- FN(ktime_get_ns), \
- FN(trace_printk), \
- FN(get_prandom_u32), \
- FN(get_smp_processor_id), \
- FN(skb_store_bytes), \
- FN(l3_csum_replace), \
- FN(l4_csum_replace), \
- FN(tail_call), \
- FN(clone_redirect), \
- FN(get_current_pid_tgid), \
- FN(get_current_uid_gid), \
- FN(get_current_comm), \
- FN(get_cgroup_classid), \
- FN(skb_vlan_push), \
- FN(skb_vlan_pop), \
- FN(skb_get_tunnel_key), \
- FN(skb_set_tunnel_key), \
- FN(perf_event_read), \
- FN(redirect), \
- FN(get_route_realm), \
- FN(perf_event_output), \
- FN(skb_load_bytes), \
- FN(get_stackid), \
- FN(csum_diff), \
- FN(skb_get_tunnel_opt), \
- FN(skb_set_tunnel_opt), \
- FN(skb_change_proto), \
- FN(skb_change_type), \
- FN(skb_under_cgroup), \
- FN(get_hash_recalc), \
- FN(get_current_task), \
- FN(probe_write_user), \
- FN(current_task_under_cgroup), \
- FN(skb_change_tail), \
- FN(skb_pull_data), \
- FN(csum_update), \
- FN(set_hash_invalid), \
- FN(get_numa_node_id), \
- FN(skb_change_head), \
- FN(xdp_adjust_head), \
- FN(probe_read_str), \
- FN(get_socket_cookie), \
- FN(get_socket_uid), \
- FN(set_hash), \
- FN(setsockopt), \
- FN(skb_adjust_room), \
- FN(redirect_map), \
- FN(sk_redirect_map), \
- FN(sock_map_update), \
- FN(xdp_adjust_meta), \
- FN(perf_event_read_value), \
- FN(perf_prog_read_value), \
- FN(getsockopt), \
- FN(override_return), \
- FN(sock_ops_cb_flags_set), \
- FN(msg_redirect_map), \
- FN(msg_apply_bytes), \
- FN(msg_cork_bytes), \
- FN(msg_pull_data), \
- FN(bind), \
- FN(xdp_adjust_tail), \
- FN(skb_get_xfrm_state), \
- FN(get_stack), \
- FN(skb_load_bytes_relative), \
- FN(fib_lookup), \
- FN(sock_hash_update), \
- FN(msg_redirect_hash), \
- FN(sk_redirect_hash), \
- FN(lwt_push_encap), \
- FN(lwt_seg6_store_bytes), \
- FN(lwt_seg6_adjust_srh), \
- FN(lwt_seg6_action), \
- FN(rc_repeat), \
- FN(rc_keydown), \
- FN(skb_cgroup_id), \
- FN(get_current_cgroup_id), \
- FN(get_local_storage), \
- FN(sk_select_reuseport), \
- FN(skb_ancestor_cgroup_id), \
- FN(sk_lookup_tcp), \
- FN(sk_lookup_udp), \
- FN(sk_release), \
- FN(map_push_elem), \
- FN(map_pop_elem), \
- FN(map_peek_elem), \
- FN(msg_push_data), \
- FN(msg_pop_data), \
- FN(rc_pointer_rel), \
- FN(spin_lock), \
- FN(spin_unlock), \
- FN(sk_fullsock), \
- FN(tcp_sock), \
- FN(skb_ecn_set_ce), \
- FN(get_listener_sock), \
- FN(skc_lookup_tcp), \
- FN(tcp_check_syncookie), \
- FN(sysctl_get_name), \
- FN(sysctl_get_current_value), \
- FN(sysctl_get_new_value), \
- FN(sysctl_set_new_value), \
- FN(strtol), \
- FN(strtoul), \
- FN(sk_storage_get), \
- FN(sk_storage_delete), \
- FN(send_signal), \
- FN(tcp_gen_syncookie), \
- FN(skb_output), \
- FN(probe_read_user), \
- FN(probe_read_kernel), \
- FN(probe_read_user_str), \
- FN(probe_read_kernel_str), \
- FN(tcp_send_ack), \
- FN(send_signal_thread), \
- FN(jiffies64), \
- FN(read_branch_records), \
- FN(get_ns_current_pid_tgid), \
- FN(xdp_output), \
- FN(get_netns_cookie), \
- FN(get_current_ancestor_cgroup_id), \
- FN(sk_assign), \
- FN(ktime_get_boot_ns), \
- FN(seq_printf), \
- FN(seq_write), \
- FN(sk_cgroup_id), \
- FN(sk_ancestor_cgroup_id), \
- FN(ringbuf_output), \
- FN(ringbuf_reserve), \
- FN(ringbuf_submit), \
- FN(ringbuf_discard), \
- FN(ringbuf_query), \
- FN(csum_level), \
- FN(skc_to_tcp6_sock), \
- FN(skc_to_tcp_sock), \
- FN(skc_to_tcp_timewait_sock), \
- FN(skc_to_tcp_request_sock), \
- FN(skc_to_udp6_sock), \
- FN(get_task_stack), \
- FN(load_hdr_opt), \
- FN(store_hdr_opt), \
- FN(reserve_hdr_opt), \
- FN(inode_storage_get), \
- FN(inode_storage_delete), \
- FN(d_path), \
- FN(copy_from_user), \
- FN(snprintf_btf), \
- FN(seq_printf_btf), \
- FN(skb_cgroup_classid), \
- FN(redirect_neigh), \
- FN(per_cpu_ptr), \
- FN(this_cpu_ptr), \
- FN(redirect_peer), \
- FN(task_storage_get), \
- FN(task_storage_delete), \
- FN(get_current_task_btf), \
- FN(bprm_opts_set), \
- FN(ktime_get_coarse_ns), \
- FN(ima_inode_hash), \
- FN(sock_from_file), \
- FN(check_mtu), \
- FN(for_each_map_elem), \
- FN(snprintf), \
- FN(sys_bpf), \
- FN(btf_find_by_name_kind), \
- FN(sys_close), \
- FN(timer_init), \
- FN(timer_set_callback), \
- FN(timer_start), \
- FN(timer_cancel), \
- FN(get_func_ip), \
- FN(get_attach_cookie), \
- FN(task_pt_regs), \
- FN(get_branch_snapshot), \
- FN(trace_vprintk), \
- FN(skc_to_unix_sock), \
- FN(kallsyms_lookup_name), \
- FN(find_vma), \
- FN(loop), \
- FN(strncmp), \
- FN(get_func_arg), \
- FN(get_func_ret), \
- FN(get_func_arg_cnt), \
- FN(get_retval), \
- FN(set_retval), \
- FN(xdp_get_buff_len), \
- FN(xdp_load_bytes), \
- FN(xdp_store_bytes), \
- FN(copy_from_user_task), \
- FN(skb_set_tstamp), \
- FN(ima_file_hash), \
- FN(kptr_xchg), \
- FN(map_lookup_percpu_elem), \
- FN(skc_to_mptcp_sock), \
- FN(dynptr_from_mem), \
- FN(ringbuf_reserve_dynptr), \
- FN(ringbuf_submit_dynptr), \
- FN(ringbuf_discard_dynptr), \
- FN(dynptr_read), \
- FN(dynptr_write), \
- FN(dynptr_data), \
- FN(tcp_raw_gen_syncookie_ipv4), \
- FN(tcp_raw_gen_syncookie_ipv6), \
- FN(tcp_raw_check_syncookie_ipv4), \
- FN(tcp_raw_check_syncookie_ipv6), \
+#define ___BPF_FUNC_MAPPER(FN, ctx...) \
+ FN(unspec, 0, ##ctx) \
+ FN(map_lookup_elem, 1, ##ctx) \
+ FN(map_update_elem, 2, ##ctx) \
+ FN(map_delete_elem, 3, ##ctx) \
+ FN(probe_read, 4, ##ctx) \
+ FN(ktime_get_ns, 5, ##ctx) \
+ FN(trace_printk, 6, ##ctx) \
+ FN(get_prandom_u32, 7, ##ctx) \
+ FN(get_smp_processor_id, 8, ##ctx) \
+ FN(skb_store_bytes, 9, ##ctx) \
+ FN(l3_csum_replace, 10, ##ctx) \
+ FN(l4_csum_replace, 11, ##ctx) \
+ FN(tail_call, 12, ##ctx) \
+ FN(clone_redirect, 13, ##ctx) \
+ FN(get_current_pid_tgid, 14, ##ctx) \
+ FN(get_current_uid_gid, 15, ##ctx) \
+ FN(get_current_comm, 16, ##ctx) \
+ FN(get_cgroup_classid, 17, ##ctx) \
+ FN(skb_vlan_push, 18, ##ctx) \
+ FN(skb_vlan_pop, 19, ##ctx) \
+ FN(skb_get_tunnel_key, 20, ##ctx) \
+ FN(skb_set_tunnel_key, 21, ##ctx) \
+ FN(perf_event_read, 22, ##ctx) \
+ FN(redirect, 23, ##ctx) \
+ FN(get_route_realm, 24, ##ctx) \
+ FN(perf_event_output, 25, ##ctx) \
+ FN(skb_load_bytes, 26, ##ctx) \
+ FN(get_stackid, 27, ##ctx) \
+ FN(csum_diff, 28, ##ctx) \
+ FN(skb_get_tunnel_opt, 29, ##ctx) \
+ FN(skb_set_tunnel_opt, 30, ##ctx) \
+ FN(skb_change_proto, 31, ##ctx) \
+ FN(skb_change_type, 32, ##ctx) \
+ FN(skb_under_cgroup, 33, ##ctx) \
+ FN(get_hash_recalc, 34, ##ctx) \
+ FN(get_current_task, 35, ##ctx) \
+ FN(probe_write_user, 36, ##ctx) \
+ FN(current_task_under_cgroup, 37, ##ctx) \
+ FN(skb_change_tail, 38, ##ctx) \
+ FN(skb_pull_data, 39, ##ctx) \
+ FN(csum_update, 40, ##ctx) \
+ FN(set_hash_invalid, 41, ##ctx) \
+ FN(get_numa_node_id, 42, ##ctx) \
+ FN(skb_change_head, 43, ##ctx) \
+ FN(xdp_adjust_head, 44, ##ctx) \
+ FN(probe_read_str, 45, ##ctx) \
+ FN(get_socket_cookie, 46, ##ctx) \
+ FN(get_socket_uid, 47, ##ctx) \
+ FN(set_hash, 48, ##ctx) \
+ FN(setsockopt, 49, ##ctx) \
+ FN(skb_adjust_room, 50, ##ctx) \
+ FN(redirect_map, 51, ##ctx) \
+ FN(sk_redirect_map, 52, ##ctx) \
+ FN(sock_map_update, 53, ##ctx) \
+ FN(xdp_adjust_meta, 54, ##ctx) \
+ FN(perf_event_read_value, 55, ##ctx) \
+ FN(perf_prog_read_value, 56, ##ctx) \
+ FN(getsockopt, 57, ##ctx) \
+ FN(override_return, 58, ##ctx) \
+ FN(sock_ops_cb_flags_set, 59, ##ctx) \
+ FN(msg_redirect_map, 60, ##ctx) \
+ FN(msg_apply_bytes, 61, ##ctx) \
+ FN(msg_cork_bytes, 62, ##ctx) \
+ FN(msg_pull_data, 63, ##ctx) \
+ FN(bind, 64, ##ctx) \
+ FN(xdp_adjust_tail, 65, ##ctx) \
+ FN(skb_get_xfrm_state, 66, ##ctx) \
+ FN(get_stack, 67, ##ctx) \
+ FN(skb_load_bytes_relative, 68, ##ctx) \
+ FN(fib_lookup, 69, ##ctx) \
+ FN(sock_hash_update, 70, ##ctx) \
+ FN(msg_redirect_hash, 71, ##ctx) \
+ FN(sk_redirect_hash, 72, ##ctx) \
+ FN(lwt_push_encap, 73, ##ctx) \
+ FN(lwt_seg6_store_bytes, 74, ##ctx) \
+ FN(lwt_seg6_adjust_srh, 75, ##ctx) \
+ FN(lwt_seg6_action, 76, ##ctx) \
+ FN(rc_repeat, 77, ##ctx) \
+ FN(rc_keydown, 78, ##ctx) \
+ FN(skb_cgroup_id, 79, ##ctx) \
+ FN(get_current_cgroup_id, 80, ##ctx) \
+ FN(get_local_storage, 81, ##ctx) \
+ FN(sk_select_reuseport, 82, ##ctx) \
+ FN(skb_ancestor_cgroup_id, 83, ##ctx) \
+ FN(sk_lookup_tcp, 84, ##ctx) \
+ FN(sk_lookup_udp, 85, ##ctx) \
+ FN(sk_release, 86, ##ctx) \
+ FN(map_push_elem, 87, ##ctx) \
+ FN(map_pop_elem, 88, ##ctx) \
+ FN(map_peek_elem, 89, ##ctx) \
+ FN(msg_push_data, 90, ##ctx) \
+ FN(msg_pop_data, 91, ##ctx) \
+ FN(rc_pointer_rel, 92, ##ctx) \
+ FN(spin_lock, 93, ##ctx) \
+ FN(spin_unlock, 94, ##ctx) \
+ FN(sk_fullsock, 95, ##ctx) \
+ FN(tcp_sock, 96, ##ctx) \
+ FN(skb_ecn_set_ce, 97, ##ctx) \
+ FN(get_listener_sock, 98, ##ctx) \
+ FN(skc_lookup_tcp, 99, ##ctx) \
+ FN(tcp_check_syncookie, 100, ##ctx) \
+ FN(sysctl_get_name, 101, ##ctx) \
+ FN(sysctl_get_current_value, 102, ##ctx) \
+ FN(sysctl_get_new_value, 103, ##ctx) \
+ FN(sysctl_set_new_value, 104, ##ctx) \
+ FN(strtol, 105, ##ctx) \
+ FN(strtoul, 106, ##ctx) \
+ FN(sk_storage_get, 107, ##ctx) \
+ FN(sk_storage_delete, 108, ##ctx) \
+ FN(send_signal, 109, ##ctx) \
+ FN(tcp_gen_syncookie, 110, ##ctx) \
+ FN(skb_output, 111, ##ctx) \
+ FN(probe_read_user, 112, ##ctx) \
+ FN(probe_read_kernel, 113, ##ctx) \
+ FN(probe_read_user_str, 114, ##ctx) \
+ FN(probe_read_kernel_str, 115, ##ctx) \
+ FN(tcp_send_ack, 116, ##ctx) \
+ FN(send_signal_thread, 117, ##ctx) \
+ FN(jiffies64, 118, ##ctx) \
+ FN(read_branch_records, 119, ##ctx) \
+ FN(get_ns_current_pid_tgid, 120, ##ctx) \
+ FN(xdp_output, 121, ##ctx) \
+ FN(get_netns_cookie, 122, ##ctx) \
+ FN(get_current_ancestor_cgroup_id, 123, ##ctx) \
+ FN(sk_assign, 124, ##ctx) \
+ FN(ktime_get_boot_ns, 125, ##ctx) \
+ FN(seq_printf, 126, ##ctx) \
+ FN(seq_write, 127, ##ctx) \
+ FN(sk_cgroup_id, 128, ##ctx) \
+ FN(sk_ancestor_cgroup_id, 129, ##ctx) \
+ FN(ringbuf_output, 130, ##ctx) \
+ FN(ringbuf_reserve, 131, ##ctx) \
+ FN(ringbuf_submit, 132, ##ctx) \
+ FN(ringbuf_discard, 133, ##ctx) \
+ FN(ringbuf_query, 134, ##ctx) \
+ FN(csum_level, 135, ##ctx) \
+ FN(skc_to_tcp6_sock, 136, ##ctx) \
+ FN(skc_to_tcp_sock, 137, ##ctx) \
+ FN(skc_to_tcp_timewait_sock, 138, ##ctx) \
+ FN(skc_to_tcp_request_sock, 139, ##ctx) \
+ FN(skc_to_udp6_sock, 140, ##ctx) \
+ FN(get_task_stack, 141, ##ctx) \
+ FN(load_hdr_opt, 142, ##ctx) \
+ FN(store_hdr_opt, 143, ##ctx) \
+ FN(reserve_hdr_opt, 144, ##ctx) \
+ FN(inode_storage_get, 145, ##ctx) \
+ FN(inode_storage_delete, 146, ##ctx) \
+ FN(d_path, 147, ##ctx) \
+ FN(copy_from_user, 148, ##ctx) \
+ FN(snprintf_btf, 149, ##ctx) \
+ FN(seq_printf_btf, 150, ##ctx) \
+ FN(skb_cgroup_classid, 151, ##ctx) \
+ FN(redirect_neigh, 152, ##ctx) \
+ FN(per_cpu_ptr, 153, ##ctx) \
+ FN(this_cpu_ptr, 154, ##ctx) \
+ FN(redirect_peer, 155, ##ctx) \
+ FN(task_storage_get, 156, ##ctx) \
+ FN(task_storage_delete, 157, ##ctx) \
+ FN(get_current_task_btf, 158, ##ctx) \
+ FN(bprm_opts_set, 159, ##ctx) \
+ FN(ktime_get_coarse_ns, 160, ##ctx) \
+ FN(ima_inode_hash, 161, ##ctx) \
+ FN(sock_from_file, 162, ##ctx) \
+ FN(check_mtu, 163, ##ctx) \
+ FN(for_each_map_elem, 164, ##ctx) \
+ FN(snprintf, 165, ##ctx) \
+ FN(sys_bpf, 166, ##ctx) \
+ FN(btf_find_by_name_kind, 167, ##ctx) \
+ FN(sys_close, 168, ##ctx) \
+ FN(timer_init, 169, ##ctx) \
+ FN(timer_set_callback, 170, ##ctx) \
+ FN(timer_start, 171, ##ctx) \
+ FN(timer_cancel, 172, ##ctx) \
+ FN(get_func_ip, 173, ##ctx) \
+ FN(get_attach_cookie, 174, ##ctx) \
+ FN(task_pt_regs, 175, ##ctx) \
+ FN(get_branch_snapshot, 176, ##ctx) \
+ FN(trace_vprintk, 177, ##ctx) \
+ FN(skc_to_unix_sock, 178, ##ctx) \
+ FN(kallsyms_lookup_name, 179, ##ctx) \
+ FN(find_vma, 180, ##ctx) \
+ FN(loop, 181, ##ctx) \
+ FN(strncmp, 182, ##ctx) \
+ FN(get_func_arg, 183, ##ctx) \
+ FN(get_func_ret, 184, ##ctx) \
+ FN(get_func_arg_cnt, 185, ##ctx) \
+ FN(get_retval, 186, ##ctx) \
+ FN(set_retval, 187, ##ctx) \
+ FN(xdp_get_buff_len, 188, ##ctx) \
+ FN(xdp_load_bytes, 189, ##ctx) \
+ FN(xdp_store_bytes, 190, ##ctx) \
+ FN(copy_from_user_task, 191, ##ctx) \
+ FN(skb_set_tstamp, 192, ##ctx) \
+ FN(ima_file_hash, 193, ##ctx) \
+ FN(kptr_xchg, 194, ##ctx) \
+ FN(map_lookup_percpu_elem, 195, ##ctx) \
+ FN(skc_to_mptcp_sock, 196, ##ctx) \
+ FN(dynptr_from_mem, 197, ##ctx) \
+ FN(ringbuf_reserve_dynptr, 198, ##ctx) \
+ FN(ringbuf_submit_dynptr, 199, ##ctx) \
+ FN(ringbuf_discard_dynptr, 200, ##ctx) \
+ FN(dynptr_read, 201, ##ctx) \
+ FN(dynptr_write, 202, ##ctx) \
+ FN(dynptr_data, 203, ##ctx) \
+ FN(tcp_raw_gen_syncookie_ipv4, 204, ##ctx) \
+ FN(tcp_raw_gen_syncookie_ipv6, 205, ##ctx) \
+ FN(tcp_raw_check_syncookie_ipv4, 206, ##ctx) \
+ FN(tcp_raw_check_syncookie_ipv6, 207, ##ctx) \
+ FN(ktime_get_tai_ns, 208, ##ctx) \
+ FN(user_ringbuf_drain, 209, ##ctx) \
+ FN(cgrp_storage_get, 210, ##ctx) \
+ FN(cgrp_storage_delete, 211, ##ctx) \
/* */
+/* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't
+ * know or care about integer value that is now passed as second argument
+ */
+#define __BPF_FUNC_MAPPER_APPLY(name, value, FN) FN(name),
+#define __BPF_FUNC_MAPPER(FN) ___BPF_FUNC_MAPPER(__BPF_FUNC_MAPPER_APPLY, FN)
+
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
*/
-#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x
+#define __BPF_ENUM_FN(x, y) BPF_FUNC_ ## x = y,
enum bpf_func_id {
- __BPF_FUNC_MAPPER(__BPF_ENUM_FN)
+ ___BPF_FUNC_MAPPER(__BPF_ENUM_FN)
__BPF_FUNC_MAX_ID,
};
#undef __BPF_ENUM_FN
BPF_F_ZERO_CSUM_TX = (1ULL << 1),
BPF_F_DONT_FRAGMENT = (1ULL << 2),
BPF_F_SEQ_NUMBER = (1ULL << 3),
+ BPF_F_NO_TUNNEL_KEY = (1ULL << 4),
+};
+
+/* BPF_FUNC_skb_get_tunnel_key flags. */
+enum {
+ BPF_F_TUNINFO_FLAGS = (1ULL << 4),
};
/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4),
BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5),
BPF_F_ADJ_ROOM_ENCAP_L2_ETH = (1ULL << 6),
+ BPF_F_ADJ_ROOM_DECAP_L3_IPV4 = (1ULL << 7),
+ BPF_F_ADJ_ROOM_DECAP_L3_IPV6 = (1ULL << 8),
};
enum {
};
__u8 tunnel_tos;
__u8 tunnel_ttl;
- __u16 tunnel_ext; /* Padding, future use. */
+ union {
+ __u16 tunnel_ext; /* compat */
+ __be16 tunnel_flags;
+ };
__u32 tunnel_label;
union {
__u32 local_ipv4;
* represented by BPF_REDIRECT above).
*/
BPF_LWT_REROUTE = 128,
+ /* BPF_FLOW_DISSECTOR_CONTINUE: used by BPF_PROG_TYPE_FLOW_DISSECTOR
+ * to indicate that no custom dissection was performed, and
+ * fallback to standard dissector is requested.
+ */
+ BPF_FLOW_DISSECTOR_CONTINUE = 129,
};
struct bpf_sock {
struct {
__aligned_u64 target_name; /* in/out: target_name buffer ptr */
__u32 target_name_len; /* in/out: target_name buffer len */
+
+ /* If the iter specific field is 32 bits, it can be put
+ * in the first or second union. Otherwise it should be
+ * put in the second union.
+ */
union {
struct {
__u32 map_id;
} map;
};
+ union {
+ struct {
+ __u64 cgroup_id;
+ __u32 order;
+ } cgroup;
+ struct {
+ __u32 tid;
+ __u32 pid;
+ } task;
+ };
} iter;
struct {
__u32 netns_ino;
* the outgoing header has not
* been written yet.
*/
+ __u64 skb_hwtstamp;
};
/* Definitions for bpf_sock_ops_cb_flags */
enum {
BPF_FIB_LOOKUP_DIRECT = (1U << 0),
BPF_FIB_LOOKUP_OUTPUT = (1U << 1),
+ BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2),
};
enum {
__u64 :64;
} __attribute__((aligned(8)));
+struct bpf_list_head {
+ __u64 :64;
+ __u64 :64;
+} __attribute__((aligned(8)));
+
+struct bpf_list_node {
+ __u64 :64;
+ __u64 :64;
+} __attribute__((aligned(8)));
+
+struct bpf_rb_root {
+ __u64 :64;
+ __u64 :64;
+} __attribute__((aligned(8)));
+
+struct bpf_rb_node {
+ __u64 :64;
+ __u64 :64;
+ __u64 :64;
+} __attribute__((aligned(8)));
+
struct bpf_sysctl {
__u32 write; /* Sysctl is being read (= 0) or written (= 1).
* Allows 1,2,4-byte read, but no write.
projects / 0xmirror / xdp-tools.git / commitdiff