mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 13:55:32 +00:00
![Martin KaFai Lau](/assets/img/avatar_default.png)
This patch introduces a new map type BPF_MAP_TYPE_REUSEPORT_SOCKARRAY. To unleash the full potential of a bpf prog, it is essential for the userspace to be capable of directly setting up a bpf map which can then be consumed by the bpf prog to make decision. In this case, decide which SO_REUSEPORT sk to serve the incoming request. By adding BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, the userspace has total control and visibility on where a SO_REUSEPORT sk should be located in a bpf map. The later patch will introduce BPF_PROG_TYPE_SK_REUSEPORT such that the bpf prog can directly select a sk from the bpf map. That will raise the programmability of the bpf prog attached to a reuseport group (a group of sk serving the same IP:PORT). For example, in UDP, the bpf prog can peek into the payload (e.g. through the "data" pointer introduced in the later patch) to learn the application level's connection information and then decide which sk to pick from a bpf map. The userspace can tightly couple the sk's location in a bpf map with the application logic in generating the UDP payload's connection information. This connection info contact/API stays within the userspace. Also, when used with map-in-map, the userspace can switch the old-server-process's inner map to a new-server-process's inner map in one call "bpf_map_update_elem(outer_map, &index, &new_reuseport_array)". The bpf prog will then direct incoming requests to the new process instead of the old process. The old process can finish draining the pending requests (e.g. by "accept()") before closing the old-fds. [Note that deleting a fd from a bpf map does not necessary mean the fd is closed] During map_update_elem(), Only SO_REUSEPORT sk (i.e. which has already been added to a reuse->socks[]) can be used. That means a SO_REUSEPORT sk that is "bind()" for UDP or "bind()+listen()" for TCP. These conditions are ensured in "reuseport_array_update_check()". A SO_REUSEPORT sk can only be added once to a map (i.e. the same sk cannot be added twice even to the same map). SO_REUSEPORT already allows another sk to be created for the same IP:PORT. There is no need to re-create a similar usage in the BPF side. When a SO_REUSEPORT is deleted from the "reuse->socks[]" (e.g. "close()"), it will notify the bpf map to remove it from the map also. It is done through "bpf_sk_reuseport_detach()" and it will only be called if >=1 of the "reuse->sock[]" has ever been added to a bpf map. The map_update()/map_delete() has to be in-sync with the "reuse->socks[]". Hence, the same "reuseport_lock" used by "reuse->socks[]" has to be used here also. Care has been taken to ensure the lock is only acquired when the adding sk passes some strict tests. and freeing the map does not require the reuseport_lock. The reuseport_array will also support lookup from the syscall side. It will return a sock_gen_cookie(). The sock_gen_cookie() is on-demand (i.e. a sk's cookie is not generated until the very first map_lookup_elem()). The lookup cookie is 64bits but it goes against the logical userspace expectation on 32bits sizeof(fd) (and as other fd based bpf maps do also). It may catch user in surprise if we enforce value_size=8 while userspace still pass a 32bits fd during update. Supporting different value_size between lookup and update seems unintuitive also. We also need to consider what if other existing fd based maps want to return 64bits value from syscall's lookup in the future. Hence, reuseport_array supports both value_size 4 and 8, and assuming user will usually use value_size=4. The syscall's lookup will return ENOSPC on value_size=4. It will will only return 64bits value from sock_gen_cookie() when user consciously choose value_size=8 (as a signal that lookup is desired) which then requires a 64bits value in both lookup and update. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
66 lines
2.5 KiB
C
66 lines
2.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/* internal file - do not include directly */
|
|
|
|
#ifdef CONFIG_NET
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter)
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act)
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act)
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp)
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb)
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock)
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr)
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in)
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out)
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit)
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local)
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops)
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb)
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg)
|
|
#endif
|
|
#ifdef CONFIG_BPF_EVENTS
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe)
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint)
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event)
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint)
|
|
#endif
|
|
#ifdef CONFIG_CGROUP_BPF
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
|
|
#endif
|
|
#ifdef CONFIG_BPF_LIRC_MODE2
|
|
BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2)
|
|
#endif
|
|
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops)
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops)
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_PROG_ARRAY, prog_array_map_ops)
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_PERF_EVENT_ARRAY, perf_event_array_map_ops)
|
|
#ifdef CONFIG_CGROUPS
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, cgroup_array_map_ops)
|
|
#endif
|
|
#ifdef CONFIG_CGROUP_BPF
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, cgroup_storage_map_ops)
|
|
#endif
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_HASH, htab_map_ops)
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_HASH, htab_percpu_map_ops)
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_HASH, htab_lru_map_ops)
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_PERCPU_HASH, htab_lru_percpu_map_ops)
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_LPM_TRIE, trie_map_ops)
|
|
#ifdef CONFIG_PERF_EVENTS
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_map_ops)
|
|
#endif
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops)
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops)
|
|
#ifdef CONFIG_NET
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
|
|
#if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_INET)
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops)
|
|
#endif
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
|
|
#if defined(CONFIG_XDP_SOCKETS)
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
|
|
#endif
|
|
#ifdef CONFIG_INET
|
|
BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops)
|
|
#endif
|
|
#endif
|