From 5dc4c4b7d4e8115e7cde96a030f98cb3ab2e458c Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 8 Aug 2018 01:01:24 -0700 Subject: bpf: Introduce BPF_MAP_TYPE_REUSEPORT_SOCKARRAY 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 Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/Makefile | 3 + kernel/bpf/arraymap.c | 2 +- kernel/bpf/reuseport_array.c | 363 +++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 6 + 4 files changed, 373 insertions(+), 1 deletion(-) create mode 100644 kernel/bpf/reuseport_array.c (limited to 'kernel') diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index e8906cbad81f..0488b8258321 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -23,3 +23,6 @@ ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_BPF_SYSCALL) += stackmap.o endif obj-$(CONFIG_CGROUP_BPF) += cgroup.o +ifeq ($(CONFIG_INET),y) +obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o +endif diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 2aa55d030c77..f6ca3e712831 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -54,7 +54,7 @@ static int bpf_array_alloc_percpu(struct bpf_array *array) } /* Called from syscall */ -static int array_map_alloc_check(union bpf_attr *attr) +int array_map_alloc_check(union bpf_attr *attr) { bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; int numa_node = bpf_map_attr_numa_node(attr); diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c new file mode 100644 index 000000000000..18e225de80ff --- /dev/null +++ b/kernel/bpf/reuseport_array.c @@ -0,0 +1,363 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018 Facebook + */ +#include +#include +#include +#include + +struct reuseport_array { + struct bpf_map map; + struct sock __rcu *ptrs[]; +}; + +static struct reuseport_array *reuseport_array(struct bpf_map *map) +{ + return (struct reuseport_array *)map; +} + +/* The caller must hold the reuseport_lock */ +void bpf_sk_reuseport_detach(struct sock *sk) +{ + struct sock __rcu **socks; + + write_lock_bh(&sk->sk_callback_lock); + socks = sk->sk_user_data; + if (socks) { + WRITE_ONCE(sk->sk_user_data, NULL); + /* + * Do not move this NULL assignment outside of + * sk->sk_callback_lock because there is + * a race with reuseport_array_free() + * which does not hold the reuseport_lock. + */ + RCU_INIT_POINTER(*socks, NULL); + } + write_unlock_bh(&sk->sk_callback_lock); +} + +static int reuseport_array_alloc_check(union bpf_attr *attr) +{ + if (attr->value_size != sizeof(u32) && + attr->value_size != sizeof(u64)) + return -EINVAL; + + return array_map_alloc_check(attr); +} + +static void *reuseport_array_lookup_elem(struct bpf_map *map, void *key) +{ + struct reuseport_array *array = reuseport_array(map); + u32 index = *(u32 *)key; + + if (unlikely(index >= array->map.max_entries)) + return NULL; + + return rcu_dereference(array->ptrs[index]); +} + +/* Called from syscall only */ +static int reuseport_array_delete_elem(struct bpf_map *map, void *key) +{ + struct reuseport_array *array = reuseport_array(map); + u32 index = *(u32 *)key; + struct sock *sk; + int err; + + if (index >= map->max_entries) + return -E2BIG; + + if (!rcu_access_pointer(array->ptrs[index])) + return -ENOENT; + + spin_lock_bh(&reuseport_lock); + + sk = rcu_dereference_protected(array->ptrs[index], + lockdep_is_held(&reuseport_lock)); + if (sk) { + write_lock_bh(&sk->sk_callback_lock); + WRITE_ONCE(sk->sk_user_data, NULL); + RCU_INIT_POINTER(array->ptrs[index], NULL); + write_unlock_bh(&sk->sk_callback_lock); + err = 0; + } else { + err = -ENOENT; + } + + spin_unlock_bh(&reuseport_lock); + + return err; +} + +static void reuseport_array_free(struct bpf_map *map) +{ + struct reuseport_array *array = reuseport_array(map); + struct sock *sk; + u32 i; + + synchronize_rcu(); + + /* + * ops->map_*_elem() will not be able to access this + * array now. Hence, this function only races with + * bpf_sk_reuseport_detach() which was triggerred by + * close() or disconnect(). + * + * This function and bpf_sk_reuseport_detach() are + * both removing sk from "array". Who removes it + * first does not matter. + * + * The only concern here is bpf_sk_reuseport_detach() + * may access "array" which is being freed here. + * bpf_sk_reuseport_detach() access this "array" + * through sk->sk_user_data _and_ with sk->sk_callback_lock + * held which is enough because this "array" is not freed + * until all sk->sk_user_data has stopped referencing this "array". + * + * Hence, due to the above, taking "reuseport_lock" is not + * needed here. + */ + + /* + * Since reuseport_lock is not taken, sk is accessed under + * rcu_read_lock() + */ + rcu_read_lock(); + for (i = 0; i < map->max_entries; i++) { + sk = rcu_dereference(array->ptrs[i]); + if (sk) { + write_lock_bh(&sk->sk_callback_lock); + /* + * No need for WRITE_ONCE(). At this point, + * no one is reading it without taking the + * sk->sk_callback_lock. + */ + sk->sk_user_data = NULL; + write_unlock_bh(&sk->sk_callback_lock); + RCU_INIT_POINTER(array->ptrs[i], NULL); + } + } + rcu_read_unlock(); + + /* + * Once reaching here, all sk->sk_user_data is not + * referenceing this "array". "array" can be freed now. + */ + bpf_map_area_free(array); +} + +static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr) +{ + int err, numa_node = bpf_map_attr_numa_node(attr); + struct reuseport_array *array; + u64 cost, array_size; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + array_size = sizeof(*array); + array_size += (u64)attr->max_entries * sizeof(struct sock *); + + /* make sure there is no u32 overflow later in round_up() */ + cost = array_size; + if (cost >= U32_MAX - PAGE_SIZE) + return ERR_PTR(-ENOMEM); + cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + err = bpf_map_precharge_memlock(cost); + if (err) + return ERR_PTR(err); + + /* allocate all map elements and zero-initialize them */ + array = bpf_map_area_alloc(array_size, numa_node); + if (!array) + return ERR_PTR(-ENOMEM); + + /* copy mandatory map attributes */ + bpf_map_init_from_attr(&array->map, attr); + array->map.pages = cost; + + return &array->map; +} + +int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, + void *value) +{ + struct sock *sk; + int err; + + if (map->value_size != sizeof(u64)) + return -ENOSPC; + + rcu_read_lock(); + sk = reuseport_array_lookup_elem(map, key); + if (sk) { + *(u64 *)value = sock_gen_cookie(sk); + err = 0; + } else { + err = -ENOENT; + } + rcu_read_unlock(); + + return err; +} + +static int +reuseport_array_update_check(const struct reuseport_array *array, + const struct sock *nsk, + const struct sock *osk, + const struct sock_reuseport *nsk_reuse, + u32 map_flags) +{ + if (osk && map_flags == BPF_NOEXIST) + return -EEXIST; + + if (!osk && map_flags == BPF_EXIST) + return -ENOENT; + + if (nsk->sk_protocol != IPPROTO_UDP && nsk->sk_protocol != IPPROTO_TCP) + return -ENOTSUPP; + + if (nsk->sk_family != AF_INET && nsk->sk_family != AF_INET6) + return -ENOTSUPP; + + if (nsk->sk_type != SOCK_STREAM && nsk->sk_type != SOCK_DGRAM) + return -ENOTSUPP; + + /* + * sk must be hashed (i.e. listening in the TCP case or binded + * in the UDP case) and + * it must also be a SO_REUSEPORT sk (i.e. reuse cannot be NULL). + * + * Also, sk will be used in bpf helper that is protected by + * rcu_read_lock(). + */ + if (!sock_flag(nsk, SOCK_RCU_FREE) || !sk_hashed(nsk) || !nsk_reuse) + return -EINVAL; + + /* READ_ONCE because the sk->sk_callback_lock may not be held here */ + if (READ_ONCE(nsk->sk_user_data)) + return -EBUSY; + + return 0; +} + +/* + * Called from syscall only. + * The "nsk" in the fd refcnt. + * The "osk" and "reuse" are protected by reuseport_lock. + */ +int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) +{ + struct reuseport_array *array = reuseport_array(map); + struct sock *free_osk = NULL, *osk, *nsk; + struct sock_reuseport *reuse; + u32 index = *(u32 *)key; + struct socket *socket; + int err, fd; + + if (map_flags > BPF_EXIST) + return -EINVAL; + + if (index >= map->max_entries) + return -E2BIG; + + if (map->value_size == sizeof(u64)) { + u64 fd64 = *(u64 *)value; + + if (fd64 > S32_MAX) + return -EINVAL; + fd = fd64; + } else { + fd = *(int *)value; + } + + socket = sockfd_lookup(fd, &err); + if (!socket) + return err; + + nsk = socket->sk; + if (!nsk) { + err = -EINVAL; + goto put_file; + } + + /* Quick checks before taking reuseport_lock */ + err = reuseport_array_update_check(array, nsk, + rcu_access_pointer(array->ptrs[index]), + rcu_access_pointer(nsk->sk_reuseport_cb), + map_flags); + if (err) + goto put_file; + + spin_lock_bh(&reuseport_lock); + /* + * Some of the checks only need reuseport_lock + * but it is done under sk_callback_lock also + * for simplicity reason. + */ + write_lock_bh(&nsk->sk_callback_lock); + + osk = rcu_dereference_protected(array->ptrs[index], + lockdep_is_held(&reuseport_lock)); + reuse = rcu_dereference_protected(nsk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + err = reuseport_array_update_check(array, nsk, osk, reuse, map_flags); + if (err) + goto put_file_unlock; + + /* Ensure reuse->reuseport_id is set */ + err = reuseport_get_id(reuse); + if (err < 0) + goto put_file_unlock; + + WRITE_ONCE(nsk->sk_user_data, &array->ptrs[index]); + rcu_assign_pointer(array->ptrs[index], nsk); + free_osk = osk; + err = 0; + +put_file_unlock: + write_unlock_bh(&nsk->sk_callback_lock); + + if (free_osk) { + write_lock_bh(&free_osk->sk_callback_lock); + WRITE_ONCE(free_osk->sk_user_data, NULL); + write_unlock_bh(&free_osk->sk_callback_lock); + } + + spin_unlock_bh(&reuseport_lock); +put_file: + fput(socket->file); + return err; +} + +/* Called from syscall */ +static int reuseport_array_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + struct reuseport_array *array = reuseport_array(map); + u32 index = key ? *(u32 *)key : U32_MAX; + u32 *next = (u32 *)next_key; + + if (index >= array->map.max_entries) { + *next = 0; + return 0; + } + + if (index == array->map.max_entries - 1) + return -ENOENT; + + *next = index + 1; + return 0; +} + +const struct bpf_map_ops reuseport_array_ops = { + .map_alloc_check = reuseport_array_alloc_check, + .map_alloc = reuseport_array_alloc, + .map_free = reuseport_array_free, + .map_lookup_elem = reuseport_array_lookup_elem, + .map_get_next_key = reuseport_array_get_next_key, + .map_delete_elem = reuseport_array_delete_elem, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5af4e9e2722d..57f4d076141b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -684,6 +684,8 @@ static int map_lookup_elem(union bpf_attr *attr) err = bpf_fd_array_map_lookup_elem(map, key, value); } else if (IS_FD_HASH(map)) { err = bpf_fd_htab_map_lookup_elem(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { + err = bpf_fd_reuseport_array_lookup_elem(map, key, value); } else { rcu_read_lock(); ptr = map->ops->map_lookup_elem(map, key); @@ -790,6 +792,10 @@ static int map_update_elem(union bpf_attr *attr) err = bpf_fd_htab_map_update_elem(map, f.file, key, value, attr->flags); rcu_read_unlock(); + } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { + /* rcu_read_lock() is not needed */ + err = bpf_fd_reuseport_array_update_elem(map, key, value, + attr->flags); } else { rcu_read_lock(); err = map->ops->map_update_elem(map, key, value, attr->flags); -- cgit v1.2.3 From 2dbb9b9e6df67d444fbe425c7f6014858d337adf Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 8 Aug 2018 01:01:25 -0700 Subject: bpf: Introduce BPF_PROG_TYPE_SK_REUSEPORT This patch adds a BPF_PROG_TYPE_SK_REUSEPORT which can select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY. Like other non SK_FILTER/CGROUP_SKB program, it requires CAP_SYS_ADMIN. BPF_PROG_TYPE_SK_REUSEPORT introduces "struct sk_reuseport_kern" to store the bpf context instead of using the skb->cb[48]. At the SO_REUSEPORT sk lookup time, it is in the middle of transiting from a lower layer (ipv4/ipv6) to a upper layer (udp/tcp). At this point, it is not always clear where the bpf context can be appended in the skb->cb[48] to avoid saving-and-restoring cb[]. Even putting aside the difference between ipv4-vs-ipv6 and udp-vs-tcp. It is not clear if the lower layer is only ipv4 and ipv6 in the future and will it not touch the cb[] again before transiting to the upper layer. For example, in udp_gro_receive(), it uses the 48 byte NAPI_GRO_CB instead of IP[6]CB and it may still modify the cb[] after calling the udp[46]_lib_lookup_skb(). Because of the above reason, if sk->cb is used for the bpf ctx, saving-and-restoring is needed and likely the whole 48 bytes cb[] has to be saved and restored. Instead of saving, setting and restoring the cb[], this patch opts to create a new "struct sk_reuseport_kern" and setting the needed values in there. The new BPF_PROG_TYPE_SK_REUSEPORT and "struct sk_reuseport_(kern|md)" will serve all ipv4/ipv6 + udp/tcp combinations. There is no protocol specific usage at this point and it is also inline with the current sock_reuseport.c implementation (i.e. no protocol specific requirement). In "struct sk_reuseport_md", this patch exposes data/data_end/len with semantic similar to other existing usages. Together with "bpf_skb_load_bytes()" and "bpf_skb_load_bytes_relative()", the bpf prog can peek anywhere in the skb. The "bind_inany" tells the bpf prog that the reuseport group is bind-ed to a local INANY address which cannot be learned from skb. The new "bind_inany" is added to "struct sock_reuseport" which will be used when running the new "BPF_PROG_TYPE_SK_REUSEPORT" bpf prog in order to avoid repeating the "bind INANY" test on "sk_v6_rcv_saddr/sk->sk_rcv_saddr" every time a bpf prog is run. It can only be properly initialized when a "sk->sk_reuseport" enabled sk is adding to a hashtable (i.e. during "reuseport_alloc()" and "reuseport_add_sock()"). The new "sk_select_reuseport()" is the main helper that the bpf prog will use to select a SO_REUSEPORT sk. It is the only function that can use the new BPF_MAP_TYPE_REUSEPORT_ARRAY. As mentioned in the earlier patch, the validity of a selected sk is checked in run time in "sk_select_reuseport()". Doing the check in verification time is difficult and inflexible (consider the map-in-map use case). The runtime check is to compare the selected sk's reuseport_id with the reuseport_id that we want. This helper will return -EXXX if the selected sk cannot serve the incoming request (e.g. reuseport_id not match). The bpf prog can decide if it wants to do SK_DROP as its discretion. When the bpf prog returns SK_PASS, the kernel will check if a valid sk has been selected (i.e. "reuse_kern->selected_sk != NULL"). If it does , it will use the selected sk. If not, the kernel will select one from "reuse->socks[]" (as before this patch). The SK_DROP and SK_PASS handling logic will be in the next patch. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/verifier.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 587468a9c37d..ca90679a7fe5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1310,6 +1310,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_SEG6LOCAL: + case BPF_PROG_TYPE_SK_REUSEPORT: /* dst_input() and dst_output() can't write for now */ if (t == BPF_WRITE) return false; @@ -2166,6 +2167,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_msg_redirect_hash) goto error; break; + case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: + if (func_id != BPF_FUNC_sk_select_reuseport) + goto error; + break; default: break; } @@ -2217,6 +2222,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE) goto error; break; + case BPF_FUNC_sk_select_reuseport: + if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) + goto error; + break; default: break; } -- cgit v1.2.3