From d58e468b1112dcd1d5193c0a89ff9f98b5a3e8b9 Mon Sep 17 00:00:00 2001 From: Petar Penkov Date: Fri, 14 Sep 2018 07:46:18 -0700 Subject: flow_dissector: implements flow dissector BPF hook Adds a hook for programs of type BPF_PROG_TYPE_FLOW_DISSECTOR and attach type BPF_FLOW_DISSECTOR that is executed in the flow dissector path. The BPF program is per-network namespace. Signed-off-by: Petar Penkov Signed-off-by: Willem de Bruijn Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 66917a4eba27..aa5ccd2385ed 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -152,6 +152,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_LWT_SEG6LOCAL, BPF_PROG_TYPE_LIRC_MODE2, BPF_PROG_TYPE_SK_REUSEPORT, + BPF_PROG_TYPE_FLOW_DISSECTOR, }; enum bpf_attach_type { @@ -172,6 +173,7 @@ enum bpf_attach_type { BPF_CGROUP_UDP4_SENDMSG, BPF_CGROUP_UDP6_SENDMSG, BPF_LIRC_MODE2, + BPF_FLOW_DISSECTOR, __MAX_BPF_ATTACH_TYPE }; @@ -2333,6 +2335,7 @@ struct __sk_buff { /* ... here. */ __u32 data_meta; + struct bpf_flow_keys *flow_keys; }; struct bpf_tunnel_key { @@ -2778,4 +2781,27 @@ enum bpf_task_fd_type { BPF_FD_TYPE_URETPROBE, /* filename + offset */ }; +struct bpf_flow_keys { + __u16 nhoff; + __u16 thoff; + __u16 addr_proto; /* ETH_P_* of valid addrs */ + __u8 is_frag; + __u8 is_first_frag; + __u8 is_encap; + __u8 ip_proto; + __be16 n_proto; + __be16 sport; + __be16 dport; + union { + struct { + __be32 ipv4_src; + __be32 ipv4_dst; + }; + struct { + __u32 ipv6_src[4]; /* in6_addr; network order */ + __u32 ipv6_dst[4]; /* in6_addr; network order */ + }; + }; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.2.3 From b741f1630346defcbc8cc60f1a2bdae8b3b0036f Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 28 Sep 2018 14:45:43 +0000 Subject: bpf: introduce per-cpu cgroup local storage This commit introduced per-cpu cgroup local storage. Per-cpu cgroup local storage is very similar to simple cgroup storage (let's call it shared), except all the data is per-cpu. The main goal of per-cpu variant is to implement super fast counters (e.g. packet counters), which don't require neither lookups, neither atomic operations. >From userspace's point of view, accessing a per-cpu cgroup storage is similar to other per-cpu map types (e.g. per-cpu hashmaps and arrays). Writing to a per-cpu cgroup storage is not atomic, but is performed by copying longs, so some minimal atomicity is here, exactly as with other per-cpu maps. Signed-off-by: Roman Gushchin Cc: Daniel Borkmann Cc: Alexei Starovoitov Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 20 +++++- include/linux/bpf.h | 1 + include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/helpers.c | 8 ++- kernel/bpf/local_storage.c | 150 +++++++++++++++++++++++++++++++++++++++------ kernel/bpf/syscall.c | 11 +++- kernel/bpf/verifier.c | 15 +++-- 8 files changed, 179 insertions(+), 28 deletions(-) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 7e0c9a1d48b7..588dd5f0bd85 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -37,7 +37,10 @@ struct bpf_storage_buffer { }; struct bpf_cgroup_storage { - struct bpf_storage_buffer *buf; + union { + struct bpf_storage_buffer *buf; + void __percpu *percpu_buf; + }; struct bpf_cgroup_storage_map *map; struct bpf_cgroup_storage_key key; struct list_head list; @@ -109,6 +112,9 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { + if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) + return BPF_CGROUP_STORAGE_PERCPU; + return BPF_CGROUP_STORAGE_SHARED; } @@ -131,6 +137,10 @@ void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage); int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map); void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map); +int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value); +int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, + void *value, u64 flags); + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ @@ -285,6 +295,14 @@ static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return 0; } static inline void bpf_cgroup_storage_free( struct bpf_cgroup_storage *storage) {} +static inline int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, + void *value) { + return 0; +} +static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, + void *key, void *value, u64 flags) { + return 0; +} #define cgroup_bpf_enabled (0) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b457fbe7b70b..018299a595c8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -274,6 +274,7 @@ struct bpf_prog_offload { enum bpf_cgroup_storage_type { BPF_CGROUP_STORAGE_SHARED, + BPF_CGROUP_STORAGE_PERCPU, __BPF_CGROUP_STORAGE_MAX }; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index c9bd6fb765b0..5432f4c9f50e 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -43,6 +43,7 @@ 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) +BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_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) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index aa5ccd2385ed..e2070d819e04 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -127,6 +127,7 @@ enum bpf_map_type { BPF_MAP_TYPE_SOCKHASH, BPF_MAP_TYPE_CGROUP_STORAGE, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, }; enum bpf_prog_type { diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index e42f8789b7ea..6502115e8f55 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -206,10 +206,16 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) */ enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); struct bpf_cgroup_storage *storage; + void *ptr; storage = this_cpu_read(bpf_cgroup_storage[stype]); - return (unsigned long)&READ_ONCE(storage->buf)->data[0]; + if (stype == BPF_CGROUP_STORAGE_SHARED) + ptr = &READ_ONCE(storage->buf)->data[0]; + else + ptr = this_cpu_ptr(storage->percpu_buf); + + return (unsigned long)ptr; } const struct bpf_func_proto bpf_get_local_storage_proto = { diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 6742292fb39e..944eb297465f 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -152,6 +152,71 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, return 0; } +int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *_key, + void *value) +{ + struct bpf_cgroup_storage_map *map = map_to_storage(_map); + struct bpf_cgroup_storage_key *key = _key; + struct bpf_cgroup_storage *storage; + int cpu, off = 0; + u32 size; + + rcu_read_lock(); + storage = cgroup_storage_lookup(map, key, false); + if (!storage) { + rcu_read_unlock(); + return -ENOENT; + } + + /* per_cpu areas are zero-filled and bpf programs can only + * access 'value_size' of them, so copying rounded areas + * will not leak any kernel data + */ + size = round_up(_map->value_size, 8); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(value + off, + per_cpu_ptr(storage->percpu_buf, cpu), size); + off += size; + } + rcu_read_unlock(); + return 0; +} + +int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *_key, + void *value, u64 map_flags) +{ + struct bpf_cgroup_storage_map *map = map_to_storage(_map); + struct bpf_cgroup_storage_key *key = _key; + struct bpf_cgroup_storage *storage; + int cpu, off = 0; + u32 size; + + if (map_flags != BPF_ANY && map_flags != BPF_EXIST) + return -EINVAL; + + rcu_read_lock(); + storage = cgroup_storage_lookup(map, key, false); + if (!storage) { + rcu_read_unlock(); + return -ENOENT; + } + + /* the user space will provide round_up(value_size, 8) bytes that + * will be copied into per-cpu area. bpf programs can only access + * value_size of it. During lookup the same extra bytes will be + * returned or zeros which were zero-filled by percpu_alloc, + * so no kernel data leaks possible + */ + size = round_up(_map->value_size, 8); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(per_cpu_ptr(storage->percpu_buf, cpu), + value + off, size); + off += size; + } + rcu_read_unlock(); + return 0; +} + static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key, void *_next_key) { @@ -287,60 +352,105 @@ void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map) spin_unlock_bh(&map->lock); } +static size_t bpf_cgroup_storage_calculate_size(struct bpf_map *map, u32 *pages) +{ + size_t size; + + if (cgroup_storage_type(map) == BPF_CGROUP_STORAGE_SHARED) { + size = sizeof(struct bpf_storage_buffer) + map->value_size; + *pages = round_up(sizeof(struct bpf_cgroup_storage) + size, + PAGE_SIZE) >> PAGE_SHIFT; + } else { + size = map->value_size; + *pages = round_up(round_up(size, 8) * num_possible_cpus(), + PAGE_SIZE) >> PAGE_SHIFT; + } + + return size; +} + struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { struct bpf_cgroup_storage *storage; struct bpf_map *map; + gfp_t flags; + size_t size; u32 pages; map = prog->aux->cgroup_storage[stype]; if (!map) return NULL; - pages = round_up(sizeof(struct bpf_cgroup_storage) + - sizeof(struct bpf_storage_buffer) + - map->value_size, PAGE_SIZE) >> PAGE_SHIFT; + size = bpf_cgroup_storage_calculate_size(map, &pages); + if (bpf_map_charge_memlock(map, pages)) return ERR_PTR(-EPERM); storage = kmalloc_node(sizeof(struct bpf_cgroup_storage), __GFP_ZERO | GFP_USER, map->numa_node); - if (!storage) { - bpf_map_uncharge_memlock(map, pages); - return ERR_PTR(-ENOMEM); - } + if (!storage) + goto enomem; - storage->buf = kmalloc_node(sizeof(struct bpf_storage_buffer) + - map->value_size, __GFP_ZERO | GFP_USER, - map->numa_node); - if (!storage->buf) { - bpf_map_uncharge_memlock(map, pages); - kfree(storage); - return ERR_PTR(-ENOMEM); + flags = __GFP_ZERO | GFP_USER; + + if (stype == BPF_CGROUP_STORAGE_SHARED) { + storage->buf = kmalloc_node(size, flags, map->numa_node); + if (!storage->buf) + goto enomem; + } else { + storage->percpu_buf = __alloc_percpu_gfp(size, 8, flags); + if (!storage->percpu_buf) + goto enomem; } storage->map = (struct bpf_cgroup_storage_map *)map; return storage; + +enomem: + bpf_map_uncharge_memlock(map, pages); + kfree(storage); + return ERR_PTR(-ENOMEM); +} + +static void free_shared_cgroup_storage_rcu(struct rcu_head *rcu) +{ + struct bpf_cgroup_storage *storage = + container_of(rcu, struct bpf_cgroup_storage, rcu); + + kfree(storage->buf); + kfree(storage); +} + +static void free_percpu_cgroup_storage_rcu(struct rcu_head *rcu) +{ + struct bpf_cgroup_storage *storage = + container_of(rcu, struct bpf_cgroup_storage, rcu); + + free_percpu(storage->percpu_buf); + kfree(storage); } void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage) { - u32 pages; + enum bpf_cgroup_storage_type stype; struct bpf_map *map; + u32 pages; if (!storage) return; map = &storage->map->map; - pages = round_up(sizeof(struct bpf_cgroup_storage) + - sizeof(struct bpf_storage_buffer) + - map->value_size, PAGE_SIZE) >> PAGE_SHIFT; + + bpf_cgroup_storage_calculate_size(map, &pages); bpf_map_uncharge_memlock(map, pages); - kfree_rcu(storage->buf, rcu); - kfree_rcu(storage, rcu); + stype = cgroup_storage_type(map); + if (stype == BPF_CGROUP_STORAGE_SHARED) + call_rcu(&storage->rcu, free_shared_cgroup_storage_rcu); + else + call_rcu(&storage->rcu, free_percpu_cgroup_storage_rcu); } void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8c91d2b41b1e..5742df21598c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -686,7 +686,8 @@ static int map_lookup_elem(union bpf_attr *attr) if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) value_size = round_up(map->value_size, 8) * num_possible_cpus(); else if (IS_FD_MAP(map)) value_size = sizeof(u32); @@ -705,6 +706,8 @@ static int map_lookup_elem(union bpf_attr *attr) err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { + err = bpf_percpu_cgroup_storage_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { err = bpf_stackmap_copy(map, key, value); } else if (IS_FD_ARRAY(map)) { @@ -774,7 +777,8 @@ static int map_update_elem(union bpf_attr *attr) if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) value_size = round_up(map->value_size, 8) * num_possible_cpus(); else value_size = map->value_size; @@ -809,6 +813,9 @@ static int map_update_elem(union bpf_attr *attr) err = bpf_percpu_hash_update(map, key, value, attr->flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_update(map, key, value, attr->flags); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { + err = bpf_percpu_cgroup_storage_update(map, key, value, + attr->flags); } else if (IS_FD_ARRAY(map)) { rcu_read_lock(); err = bpf_fd_array_map_update_elem(map, f.file, key, value, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e90899df585d..a8cc83a970d1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2074,6 +2074,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_MAP_TYPE_CGROUP_STORAGE: + case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: if (func_id != BPF_FUNC_get_local_storage) goto error; break; @@ -2164,7 +2165,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_FUNC_get_local_storage: - if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE) + if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && + map->map_type != BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) goto error; break; case BPF_FUNC_sk_select_reuseport: @@ -5049,6 +5051,12 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, return 0; } +static bool bpf_map_is_cgroup_storage(struct bpf_map *map) +{ + return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); +} + /* look for pseudo eBPF instructions that access map FDs and * replace them with actual map pointers */ @@ -5139,10 +5147,9 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) } env->used_maps[env->used_map_cnt++] = map; - if (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE && + if (bpf_map_is_cgroup_storage(map) && bpf_cgroup_storage_assign(env->prog, map)) { - verbose(env, - "only one cgroup storage is allowed\n"); + verbose(env, "only one cgroup storage of each type is allowed\n"); fdput(f); return -EBUSY; } -- cgit v1.2.3 From 6acc9b432e6714d72d7d77ec7c27f6f8358d0c71 Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Tue, 2 Oct 2018 13:35:36 -0700 Subject: bpf: Add helper to retrieve socket in BPF This patch adds new BPF helper functions, bpf_sk_lookup_tcp() and bpf_sk_lookup_udp() which allows BPF programs to find out if there is a socket listening on this host, and returns a socket pointer which the BPF program can then access to determine, for instance, whether to forward or drop traffic. bpf_sk_lookup_xxx() may take a reference on the socket, so when a BPF program makes use of this function, it must subsequently pass the returned pointer into the newly added sk_release() to return the reference. By way of example, the following pseudocode would filter inbound connections at XDP if there is no corresponding service listening for the traffic: struct bpf_sock_tuple tuple; struct bpf_sock_ops *sk; populate_tuple(ctx, &tuple); // Extract the 5tuple from the packet sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof tuple, netns, 0); if (!sk) { // Couldn't find a socket listening for this traffic. Drop. return TC_ACT_SHOT; } bpf_sk_release(sk, 0); return TC_ACT_OK; Signed-off-by: Joe Stringer Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 93 +++++++++++++++++- kernel/bpf/verifier.c | 8 +- net/core/filter.c | 151 ++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 93 +++++++++++++++++- tools/testing/selftests/bpf/bpf_helpers.h | 12 +++ 5 files changed, 354 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e2070d819e04..f9187b41dff6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2144,6 +2144,77 @@ union bpf_attr { * request in the skb. * 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) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-NULL, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **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*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * 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) + * Description + * Look for UDP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-NULL, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **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*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to *struct bpf_sock*, or NULL in case of failure. + * + * int bpf_sk_release(struct bpf_sock *sk) + * Description + * Release the reference held by *sock*. *sock* must be a non-NULL + * pointer that was returned from bpf_sk_lookup_xxx\ (). + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2229,7 +2300,10 @@ union bpf_attr { FN(get_current_cgroup_id), \ FN(get_local_storage), \ FN(sk_select_reuseport), \ - FN(skb_ancestor_cgroup_id), + FN(skb_ancestor_cgroup_id), \ + FN(sk_lookup_tcp), \ + FN(sk_lookup_udp), \ + FN(sk_release), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2399,6 +2473,23 @@ struct bpf_sock { */ }; +struct bpf_sock_tuple { + union { + struct { + __be32 saddr; + __be32 daddr; + __be16 sport; + __be16 dport; + } ipv4; + struct { + __be32 saddr[4]; + __be32 daddr[4]; + __be16 sport; + __be16 dport; + } ipv6; + }; +}; + #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index cd0d8bc00bd1..73c81bef6ae8 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -153,6 +153,12 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { * PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL becomes PTR_TO_SOCKET when the type * passes through a NULL-check conditional. For the branch wherein the state is * changed to CONST_IMM, the verifier releases the reference. + * + * For each helper function that allocates a reference, such as + * bpf_sk_lookup_tcp(), there is a corresponding release function, such as + * bpf_sk_release(). When a reference type passes into the release function, + * the verifier also releases the reference. If any unchecked or unreleased + * reference remains at the end of the program, the verifier rejects it. */ /* verifier_state + insn_idx are pushed to stack when branch is encountered */ @@ -300,7 +306,7 @@ static bool arg_type_is_refcounted(enum bpf_arg_type type) */ static bool is_release_function(enum bpf_func_id func_id) { - return false; + return func_id == BPF_FUNC_sk_release; } /* string representation of 'enum bpf_reg_type' */ diff --git a/net/core/filter.c b/net/core/filter.c index b2cb186252e4..591c698bc517 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -58,13 +58,17 @@ #include #include #include +#include #include #include #include +#include +#include #include #include #include #include +#include #include #include #include @@ -4813,6 +4817,141 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { }; #endif /* CONFIG_IPV6_SEG6_BPF */ +struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, + struct sk_buff *skb, u8 family, u8 proto) +{ + int dif = skb->dev->ifindex; + bool refcounted = false; + struct sock *sk = NULL; + + if (family == AF_INET) { + __be32 src4 = tuple->ipv4.saddr; + __be32 dst4 = tuple->ipv4.daddr; + int sdif = inet_sdif(skb); + + if (proto == IPPROTO_TCP) + sk = __inet_lookup(net, &tcp_hashinfo, skb, 0, + src4, tuple->ipv4.sport, + dst4, tuple->ipv4.dport, + dif, sdif, &refcounted); + else + sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport, + dst4, tuple->ipv4.dport, + dif, sdif, &udp_table, skb); +#if IS_ENABLED(CONFIG_IPV6) + } else { + struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr; + struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr; + int sdif = inet6_sdif(skb); + + if (proto == IPPROTO_TCP) + sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0, + src6, tuple->ipv6.sport, + dst6, tuple->ipv6.dport, + dif, sdif, &refcounted); + else + sk = __udp6_lib_lookup(net, src6, tuple->ipv6.sport, + dst6, tuple->ipv6.dport, + dif, sdif, &udp_table, skb); +#endif + } + + if (unlikely(sk && !refcounted && !sock_flag(sk, SOCK_RCU_FREE))) { + WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); + sk = NULL; + } + return sk; +} + +/* bpf_sk_lookup performs the core lookup for different types of sockets, + * taking a reference on the socket if it doesn't have the flag SOCK_RCU_FREE. + * Returns the socket as an 'unsigned long' to simplify the casting in the + * callers to satisfy BPF_CALL declarations. + */ +static unsigned long +bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, + u8 proto, u64 netns_id, u64 flags) +{ + struct net *caller_net; + struct sock *sk = NULL; + u8 family = AF_UNSPEC; + struct net *net; + + family = len == sizeof(tuple->ipv4) ? AF_INET : AF_INET6; + if (unlikely(family == AF_UNSPEC || netns_id > U32_MAX || flags)) + goto out; + + if (skb->dev) + caller_net = dev_net(skb->dev); + else + caller_net = sock_net(skb->sk); + if (netns_id) { + 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) + sk = sk_to_full_sk(sk); +out: + return (unsigned long) sk; +} + +BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb, + struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) +{ + return bpf_sk_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags); +} + +static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = { + .func = bpf_sk_lookup_tcp, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_PTR_TO_SOCKET_OR_NULL, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + +BPF_CALL_5(bpf_sk_lookup_udp, struct sk_buff *, skb, + struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) +{ + return bpf_sk_lookup(skb, tuple, len, IPPROTO_UDP, netns_id, flags); +} + +static const struct bpf_func_proto bpf_sk_lookup_udp_proto = { + .func = bpf_sk_lookup_udp, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_PTR_TO_SOCKET_OR_NULL, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, + .arg5_type = ARG_ANYTHING, +}; + +BPF_CALL_1(bpf_sk_release, struct sock *, sk) +{ + if (!sock_flag(sk, SOCK_RCU_FREE)) + sock_gen_put(sk); + return 0; +} + +static const struct bpf_func_proto bpf_sk_release_proto = { + .func = bpf_sk_release, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_SOCKET, +}; + bool bpf_helper_changes_pkt_data(void *func) { if (func == bpf_skb_vlan_push || @@ -5019,6 +5158,12 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_ancestor_cgroup_id: return &bpf_skb_ancestor_cgroup_id_proto; #endif + case BPF_FUNC_sk_lookup_tcp: + return &bpf_sk_lookup_tcp_proto; + case BPF_FUNC_sk_lookup_udp: + return &bpf_sk_lookup_udp_proto; + case BPF_FUNC_sk_release: + return &bpf_sk_release_proto; default: return bpf_base_func_proto(func_id); } @@ -5119,6 +5264,12 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_redirect_hash_proto; case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; + case BPF_FUNC_sk_lookup_tcp: + return &bpf_sk_lookup_tcp_proto; + case BPF_FUNC_sk_lookup_udp: + return &bpf_sk_lookup_udp_proto; + case BPF_FUNC_sk_release: + return &bpf_sk_release_proto; default: return bpf_base_func_proto(func_id); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e2070d819e04..f9187b41dff6 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2144,6 +2144,77 @@ union bpf_attr { * request in the skb. * 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) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-NULL, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **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*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * 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) + * Description + * Look for UDP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-NULL, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **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*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to *struct bpf_sock*, or NULL in case of failure. + * + * int bpf_sk_release(struct bpf_sock *sk) + * Description + * Release the reference held by *sock*. *sock* must be a non-NULL + * pointer that was returned from bpf_sk_lookup_xxx\ (). + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2229,7 +2300,10 @@ union bpf_attr { FN(get_current_cgroup_id), \ FN(get_local_storage), \ FN(sk_select_reuseport), \ - FN(skb_ancestor_cgroup_id), + FN(skb_ancestor_cgroup_id), \ + FN(sk_lookup_tcp), \ + FN(sk_lookup_udp), \ + FN(sk_release), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2399,6 +2473,23 @@ struct bpf_sock { */ }; +struct bpf_sock_tuple { + union { + struct { + __be32 saddr; + __be32 daddr; + __be16 sport; + __be16 dport; + } ipv4; + struct { + __be32 saddr[4]; + __be32 daddr[4]; + __be16 sport; + __be16 dport; + } ipv6; + }; +}; + #define XDP_PACKET_HEADROOM 256 /* User return codes for XDP prog type. diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index e4be7730222d..1d407b3494f9 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -143,6 +143,18 @@ static unsigned long long (*bpf_skb_cgroup_id)(void *ctx) = (void *) BPF_FUNC_skb_cgroup_id; 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, + 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, + unsigned long long flags) = + (void *) BPF_FUNC_sk_lookup_udp; +static int (*bpf_sk_release)(struct bpf_sock *sk) = + (void *) BPF_FUNC_sk_release; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions -- cgit v1.2.3 From b55cbc8d9b44aaee94f19e995a5f241d453763ee Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Wed, 17 Oct 2018 16:24:48 +0200 Subject: bpf: fix doc of bpf_skb_adjust_room() in uapi len_diff is signed. Fixes: fa15601ab31e ("bpf: add documentation for eBPF helpers (33-41)") CC: Quentin Monnet Signed-off-by: Nicolas Dichtel Reviewed-by: Quentin Monnet Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 2 +- tools/include/uapi/linux/bpf.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f9187b41dff6..5e46f6732781 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1433,7 +1433,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags) + * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags) * Description * Grow or shrink the room for data in the packet associated to * *skb* by *len_diff*, and according to the selected *mode*. diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f9187b41dff6..5e46f6732781 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1433,7 +1433,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags) + * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags) * Description * Grow or shrink the room for data in the packet associated to * *skb* by *len_diff*, and according to the selected *mode*. -- cgit v1.2.3 From f1a2e44a3aeccb3ff18d3ccc0b0203e70b95bd92 Mon Sep 17 00:00:00 2001 From: Mauricio Vasquez B Date: Thu, 18 Oct 2018 15:16:25 +0200 Subject: bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 + include/linux/bpf_types.h | 2 + include/uapi/linux/bpf.h | 29 ++++- kernel/bpf/Makefile | 2 +- kernel/bpf/core.c | 3 + kernel/bpf/helpers.c | 43 +++++++ kernel/bpf/queue_stack_maps.c | 288 ++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 6 + kernel/bpf/verifier.c | 19 ++- net/core/filter.c | 6 + 10 files changed, 401 insertions(+), 3 deletions(-) create mode 100644 kernel/bpf/queue_stack_maps.c (limited to 'include/uapi/linux/bpf.h') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0f8b863e0229..33014ae73103 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -39,6 +39,9 @@ struct bpf_map_ops { void *(*map_lookup_elem)(struct bpf_map *map, void *key); int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); int (*map_delete_elem)(struct bpf_map *map, void *key); + int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); + int (*map_pop_elem)(struct bpf_map *map, void *value); + int (*map_peek_elem)(struct bpf_map *map, void *value); /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, @@ -811,6 +814,9 @@ static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; extern const struct bpf_func_proto bpf_map_delete_elem_proto; +extern const struct bpf_func_proto bpf_map_push_elem_proto; +extern const struct bpf_func_proto bpf_map_pop_elem_proto; +extern const struct bpf_func_proto bpf_map_peek_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 7bad4e1947ed..44d9ab4809bd 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -69,3 +69,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops) #endif #endif +BPF_MAP_TYPE(BPF_MAP_TYPE_QUEUE, queue_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 5e46f6732781..70082cb626b4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -128,6 +128,8 @@ enum bpf_map_type { BPF_MAP_TYPE_CGROUP_STORAGE, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + BPF_MAP_TYPE_QUEUE, + BPF_MAP_TYPE_STACK, }; enum bpf_prog_type { @@ -462,6 +464,28 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * + * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * Description + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is removed to + * make room for this. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_pop_elem(struct bpf_map *map, void *value) + * Description + * Pop an element from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_peek_elem(struct bpf_map *map, void *value) + * Description + * Get an element from *map* without removing it. + * Return + * 0 on success, or a negative error in case of failure. + * * int bpf_probe_read(void *dst, u32 size, const void *src) * Description * For tracing programs, safely attempt to read *size* bytes from @@ -2303,7 +2327,10 @@ union bpf_attr { FN(skb_ancestor_cgroup_id), \ FN(sk_lookup_tcp), \ FN(sk_lookup_udp), \ - FN(sk_release), + FN(sk_release), \ + FN(map_push_elem), \ + FN(map_pop_elem), \ + FN(map_peek_elem), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index ff8262626b8f..4c2fa3ac56f6 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -3,7 +3,7 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o -obj-$(CONFIG_BPF_SYSCALL) += local_storage.o +obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o obj-$(CONFIG_BPF_SYSCALL) += btf.o ifeq ($(CONFIG_NET),y) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index defcf4df6d91..7c7eeea8cffc 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1783,6 +1783,9 @@ BPF_CALL_0(bpf_user_rnd_u32) const struct bpf_func_proto bpf_map_lookup_elem_proto __weak; const struct bpf_func_proto bpf_map_update_elem_proto __weak; const struct bpf_func_proto bpf_map_delete_elem_proto __weak; +const struct bpf_func_proto bpf_map_push_elem_proto __weak; +const struct bpf_func_proto bpf_map_pop_elem_proto __weak; +const struct bpf_func_proto bpf_map_peek_elem_proto __weak; const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 6502115e8f55..ab0d5e3f9892 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -76,6 +76,49 @@ const struct bpf_func_proto bpf_map_delete_elem_proto = { .arg2_type = ARG_PTR_TO_MAP_KEY, }; +BPF_CALL_3(bpf_map_push_elem, struct bpf_map *, map, void *, value, u64, flags) +{ + return map->ops->map_push_elem(map, value, flags); +} + +const struct bpf_func_proto bpf_map_push_elem_proto = { + .func = bpf_map_push_elem, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_VALUE, + .arg3_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_map_pop_elem, struct bpf_map *, map, void *, value) +{ + return map->ops->map_pop_elem(map, value); +} + +const struct bpf_func_proto bpf_map_pop_elem_proto = { + .func = bpf_map_pop_elem, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, +}; + +BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value) +{ + return map->ops->map_peek_elem(map, value); +} + +const struct bpf_func_proto bpf_map_peek_elem_proto = { + .func = bpf_map_pop_elem, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, +}; + const struct bpf_func_proto bpf_get_prandom_u32_proto = { .func = bpf_user_rnd_u32, .gpl_only = false, diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c new file mode 100644 index 000000000000..12a93fb37449 --- /dev/null +++ b/kernel/bpf/queue_stack_maps.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * queue_stack_maps.c: BPF queue and stack maps + * + * Copyright (c) 2018 Politecnico di Torino + */ +#include +#include +#include +#include "percpu_freelist.h" + +#define QUEUE_STACK_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + + +struct bpf_queue_stack { + struct bpf_map map; + raw_spinlock_t lock; + u32 head, tail; + u32 size; /* max_entries + 1 */ + + char elements[0] __aligned(8); +}; + +static struct bpf_queue_stack *bpf_queue_stack(struct bpf_map *map) +{ + return container_of(map, struct bpf_queue_stack, map); +} + +static bool queue_stack_map_is_empty(struct bpf_queue_stack *qs) +{ + return qs->head == qs->tail; +} + +static bool queue_stack_map_is_full(struct bpf_queue_stack *qs) +{ + u32 head = qs->head + 1; + + if (unlikely(head >= qs->size)) + head = 0; + + return head == qs->tail; +} + +/* Called from syscall */ +static int queue_stack_map_alloc_check(union bpf_attr *attr) +{ + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 0 || + attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK) + return -EINVAL; + + if (attr->value_size > KMALLOC_MAX_SIZE) + /* if value_size is bigger, the user space won't be able to + * access the elements. + */ + return -E2BIG; + + return 0; +} + +static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr) +{ + int ret, numa_node = bpf_map_attr_numa_node(attr); + struct bpf_queue_stack *qs; + u32 size, value_size; + u64 queue_size, cost; + + size = attr->max_entries + 1; + value_size = attr->value_size; + + queue_size = sizeof(*qs) + (u64) value_size * size; + + cost = queue_size; + if (cost >= U32_MAX - PAGE_SIZE) + return ERR_PTR(-E2BIG); + + cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + ret = bpf_map_precharge_memlock(cost); + if (ret < 0) + return ERR_PTR(ret); + + qs = bpf_map_area_alloc(queue_size, numa_node); + if (!qs) + return ERR_PTR(-ENOMEM); + + memset(qs, 0, sizeof(*qs)); + + bpf_map_init_from_attr(&qs->map, attr); + + qs->map.pages = cost; + qs->size = size; + + raw_spin_lock_init(&qs->lock); + + return &qs->map; +} + +/* Called when map->refcnt goes to zero, either from workqueue or from syscall */ +static void queue_stack_map_free(struct bpf_map *map) +{ + struct bpf_queue_stack *qs = bpf_queue_stack(map); + + /* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, + * so the programs (can be more than one that used this map) were + * disconnected from events. Wait for outstanding critical sections in + * these programs to complete + */ + synchronize_rcu(); + + bpf_map_area_free(qs); +} + +static int __queue_map_get(struct bpf_map *map, void *value, bool delete) +{ + struct bpf_queue_stack *qs = bpf_queue_stack(map); + unsigned long flags; + int err = 0; + void *ptr; + + raw_spin_lock_irqsave(&qs->lock, flags); + + if (queue_stack_map_is_empty(qs)) { + err = -ENOENT; + goto out; + } + + ptr = &qs->elements[qs->tail * qs->map.value_size]; + memcpy(value, ptr, qs->map.value_size); + + if (delete) { + if (unlikely(++qs->tail >= qs->size)) + qs->tail = 0; + } + +out: + raw_spin_unlock_irqrestore(&qs->lock, flags); + return err; +} + + +static int __stack_map_get(struct bpf_map *map, void *value, bool delete) +{ + struct bpf_queue_stack *qs = bpf_queue_stack(map); + unsigned long flags; + int err = 0; + void *ptr; + u32 index; + + raw_spin_lock_irqsave(&qs->lock, flags); + + if (queue_stack_map_is_empty(qs)) { + err = -ENOENT; + goto out; + } + + index = qs->head - 1; + if (unlikely(index >= qs->size)) + index = qs->size - 1; + + ptr = &qs->elements[index * qs->map.value_size]; + memcpy(value, ptr, qs->map.value_size); + + if (delete) + qs->head = index; + +out: + raw_spin_unlock_irqrestore(&qs->lock, flags); + return err; +} + +/* Called from syscall or from eBPF program */ +static int queue_map_peek_elem(struct bpf_map *map, void *value) +{ + return __queue_map_get(map, value, false); +} + +/* Called from syscall or from eBPF program */ +static int stack_map_peek_elem(struct bpf_map *map, void *value) +{ + return __stack_map_get(map, value, false); +} + +/* Called from syscall or from eBPF program */ +static int queue_map_pop_elem(struct bpf_map *map, void *value) +{ + return __queue_map_get(map, value, true); +} + +/* Called from syscall or from eBPF program */ +static int stack_map_pop_elem(struct bpf_map *map, void *value) +{ + return __stack_map_get(map, value, true); +} + +/* Called from syscall or from eBPF program */ +static int queue_stack_map_push_elem(struct bpf_map *map, void *value, + u64 flags) +{ + struct bpf_queue_stack *qs = bpf_queue_stack(map); + unsigned long irq_flags; + int err = 0; + void *dst; + + /* BPF_EXIST is used to force making room for a new element in case the + * map is full + */ + bool replace = (flags & BPF_EXIST); + + /* Check supported flags for queue and stack maps */ + if (flags & BPF_NOEXIST || flags > BPF_EXIST) + return -EINVAL; + + raw_spin_lock_irqsave(&qs->lock, irq_flags); + + if (queue_stack_map_is_full(qs)) { + if (!replace) { + err = -E2BIG; + goto out; + } + /* advance tail pointer to overwrite oldest element */ + if (unlikely(++qs->tail >= qs->size)) + qs->tail = 0; + } + + dst = &qs->elements[qs->head * qs->map.value_size]; + memcpy(dst, value, qs->map.value_size); + + if (unlikely(++qs->head >= qs->size)) + qs->head = 0; + +out: + raw_spin_unlock_irqrestore(&qs->lock, irq_flags); + return err; +} + +/* Called from syscall or from eBPF program */ +static void *queue_stack_map_lookup_elem(struct bpf_map *map, void *key) +{ + return NULL; +} + +/* Called from syscall or from eBPF program */ +static int queue_stack_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + return -EINVAL; +} + +/* Called from syscall or from eBPF program */ +static int queue_stack_map_delete_elem(struct bpf_map *map, void *key) +{ + return -EINVAL; +} + +/* Called from syscall */ +static int queue_stack_map_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + return -EINVAL; +} + +const struct bpf_map_ops queue_map_ops = { + .map_alloc_check = queue_stack_map_alloc_check, + .map_alloc = queue_stack_map_alloc, + .map_free = queue_stack_map_free, + .map_lookup_elem = queue_stack_map_lookup_elem, + .map_update_elem = queue_stack_map_update_elem, + .map_delete_elem = queue_stack_map_delete_elem, + .map_push_elem = queue_stack_map_push_elem, + .map_pop_elem = queue_map_pop_elem, + .map_peek_elem = queue_map_peek_elem, + .map_get_next_key = queue_stack_map_get_next_key, +}; + +const struct bpf_map_ops stack_map_ops = { + .map_alloc_check = queue_stack_map_alloc_check, + .map_alloc = queue_stack_map_alloc, + .map_free = queue_stack_map_free, + .map_lookup_elem = queue_stack_map_lookup_elem, + .map_update_elem = queue_stack_map_update_elem, + .map_delete_elem = queue_stack_map_delete_elem, + .map_push_elem = queue_stack_map_push_elem, + .map_pop_elem = stack_map_pop_elem, + .map_peek_elem = stack_map_peek_elem, + .map_get_next_key = queue_stack_map_get_next_key, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 78d9dd95e25f..1617407f9ee5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -727,6 +727,9 @@ static int map_lookup_elem(union bpf_attr *attr) 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 if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_peek_elem(map, value); } else { rcu_read_lock(); ptr = map->ops->map_lookup_elem(map, key); @@ -857,6 +860,9 @@ static int map_update_elem(union bpf_attr *attr) /* rcu_read_lock() is not needed */ err = bpf_fd_reuseport_array_update_elem(map, key, value, attr->flags); + } else if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_push_elem(map, value, attr->flags); } else { rcu_read_lock(); err = map->ops->map_update_elem(map, key, value, attr->flags); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d84c91ac3b70..7d6d9cf9ebd5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2324,6 +2324,13 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (func_id != BPF_FUNC_sk_select_reuseport) goto error; break; + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: + if (func_id != BPF_FUNC_map_peek_elem && + func_id != BPF_FUNC_map_pop_elem && + func_id != BPF_FUNC_map_push_elem) + goto error; + break; default: break; } @@ -2380,6 +2387,13 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) goto error; break; + case BPF_FUNC_map_peek_elem: + case BPF_FUNC_map_pop_elem: + case BPF_FUNC_map_push_elem: + if (map->map_type != BPF_MAP_TYPE_QUEUE && + map->map_type != BPF_MAP_TYPE_STACK) + goto error; + break; default: break; } @@ -2675,7 +2689,10 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, if (func_id != BPF_FUNC_tail_call && func_id != BPF_FUNC_map_lookup_elem && func_id != BPF_FUNC_map_update_elem && - func_id != BPF_FUNC_map_delete_elem) + func_id != BPF_FUNC_map_delete_elem && + func_id != BPF_FUNC_map_push_elem && + func_id != BPF_FUNC_map_pop_elem && + func_id != BPF_FUNC_map_peek_elem) return 0; if (meta->map_ptr == NULL) { diff --git a/net/core/filter.c b/net/core/filter.c index 1a3ac6c46873..ea48ec789b5c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4876,6 +4876,12 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_map_update_elem_proto; case BPF_FUNC_map_delete_elem: return &bpf_map_delete_elem_proto; + case BPF_FUNC_map_push_elem: + return &bpf_map_push_elem_proto; + case BPF_FUNC_map_pop_elem: + return &bpf_map_pop_elem_proto; + case BPF_FUNC_map_peek_elem: + return &bpf_map_peek_elem_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_get_smp_processor_id: -- cgit v1.2.3 From bd513cd08f10cbe28856f99ae951e86e86803861 Mon Sep 17 00:00:00 2001 From: Mauricio Vasquez B Date: Thu, 18 Oct 2018 15:16:30 +0200 Subject: bpf: add MAP_LOOKUP_AND_DELETE_ELEM syscall The previous patch implemented a bpf queue/stack maps that provided the peek/pop/push functions. There is not a direct relationship between those functions and the current maps syscalls, hence a new MAP_LOOKUP_AND_DELETE_ELEM syscall is added, this is mapped to the pop operation in the queue/stack maps and it is still to implement in other kind of maps. Signed-off-by: Mauricio Vasquez B Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 67 insertions(+) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 70082cb626b4..a2fb333290dc 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -103,6 +103,7 @@ enum bpf_cmd { BPF_BTF_LOAD, BPF_BTF_GET_FD_BY_ID, BPF_TASK_FD_QUERY, + BPF_MAP_LOOKUP_AND_DELETE_ELEM, }; enum bpf_map_type { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 1617407f9ee5..49ae64a26562 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -999,6 +999,69 @@ err_put: return err; } +#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value + +static int map_lookup_and_delete_elem(union bpf_attr *attr) +{ + void __user *ukey = u64_to_user_ptr(attr->key); + void __user *uvalue = u64_to_user_ptr(attr->value); + int ufd = attr->map_fd; + struct bpf_map *map; + void *key, *value, *ptr; + u32 value_size; + struct fd f; + int err; + + if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM)) + return -EINVAL; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + + key = __bpf_copy_key(ukey, map->key_size); + if (IS_ERR(key)) { + err = PTR_ERR(key); + goto err_put; + } + + value_size = map->value_size; + + err = -ENOMEM; + value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); + if (!value) + goto free_key; + + if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_pop_elem(map, value); + } else { + err = -ENOTSUPP; + } + + if (err) + goto free_value; + + if (copy_to_user(uvalue, value, value_size) != 0) + goto free_value; + + err = 0; + +free_value: + kfree(value); +free_key: + kfree(key); +err_put: + fdput(f); + return err; +} + static const struct bpf_prog_ops * const bpf_prog_types[] = { #define BPF_PROG_TYPE(_id, _name) \ [_id] = & _name ## _prog_ops, @@ -2472,6 +2535,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_TASK_FD_QUERY: err = bpf_task_fd_query(&attr, uattr); break; + case BPF_MAP_LOOKUP_AND_DELETE_ELEM: + err = map_lookup_and_delete_elem(&attr); + break; default: err = -EINVAL; break; -- cgit v1.2.3 From 6fff607e2f14bd7c63c06c464a6f93b8efbabe28 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 19 Oct 2018 19:56:49 -0700 Subject: bpf: sk_msg program helper bpf_msg_push_data This allows user to push data into a msg using sk_msg program types. The format is as follows, bpf_msg_push_data(msg, offset, len, flags) this will insert 'len' bytes at offset 'offset'. For example to prepend 10 bytes at the front of the message the user can, bpf_msg_push_data(msg, 0, 10, 0); This will invalidate data bounds so BPF user will have to then recheck data bounds after calling this. After this the msg size will have been updated and the user is free to write into the added bytes. We allow any offset/len as long as it is within the (data, data_end) range. However, a copy will be required if the ring is full and its possible for the helper to fail with ENOMEM or EINVAL errors which need to be handled by the BPF program. This can be used similar to XDP metadata to pass data between sk_msg layer and lower layers. Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann --- include/linux/skmsg.h | 5 ++ include/uapi/linux/bpf.h | 20 ++++++- net/core/filter.c | 134 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 158 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux/bpf.h') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 84e18863f6a4..2a11e9d91dfa 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -207,6 +207,11 @@ static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which) return &msg->sg.data[which]; } +static inline struct scatterlist sk_msg_elem_cpy(struct sk_msg *msg, int which) +{ + return msg->sg.data[which]; +} + static inline struct page *sk_msg_page(struct sk_msg *msg, int which) { return sg_page(sk_msg_elem(msg, which)); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a2fb333290dc..852dc17ab47a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2240,6 +2240,23 @@ union bpf_attr { * pointer that was returned from bpf_sk_lookup_xxx\ (). * Return * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags) + * Description + * For socket policies, insert *len* bytes into msg at offset + * *start*. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it may want to insert metadata or options into the msg. + * This can later be read and used by any of the lower layer BPF + * hooks. + * + * This helper may fail if under memory pressure (a malloc + * fails) in these cases BPF programs will get an appropriate + * error and BPF programs will need to handle them. + * + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2331,7 +2348,8 @@ union bpf_attr { FN(sk_release), \ FN(map_push_elem), \ FN(map_pop_elem), \ - FN(map_peek_elem), + FN(map_peek_elem), \ + FN(msg_push_data), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/net/core/filter.c b/net/core/filter.c index 5fd5139e8638..35c6933c2622 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2297,6 +2297,137 @@ static const struct bpf_func_proto bpf_msg_pull_data_proto = { .arg4_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, + u32, len, u64, flags) +{ + struct scatterlist sge, nsge, nnsge, rsge = {0}, *psge; + u32 new, i = 0, l, space, copy = 0, offset = 0; + u8 *raw, *to, *from; + struct page *page; + + if (unlikely(flags)) + return -EINVAL; + + /* First find the starting scatterlist element */ + i = msg->sg.start; + do { + l = sk_msg_elem(msg, i)->length; + + if (start < offset + l) + break; + offset += l; + sk_msg_iter_var_next(i); + } while (i != msg->sg.end); + + if (start >= offset + l) + return -EINVAL; + + space = MAX_MSG_FRAGS - sk_msg_elem_used(msg); + + /* If no space available will fallback to copy, we need at + * least one scatterlist elem available to push data into + * when start aligns to the beginning of an element or two + * when it falls inside an element. We handle the start equals + * offset case because its the common case for inserting a + * header. + */ + if (!space || (space == 1 && start != offset)) + copy = msg->sg.data[i].length; + + page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, + get_order(copy + len)); + if (unlikely(!page)) + return -ENOMEM; + + if (copy) { + int front, back; + + raw = page_address(page); + + psge = sk_msg_elem(msg, i); + front = start - offset; + back = psge->length - front; + from = sg_virt(psge); + + if (front) + memcpy(raw, from, front); + + if (back) { + from += front; + to = raw + front + len; + + memcpy(to, from, back); + } + + put_page(sg_page(psge)); + } else if (start - offset) { + psge = sk_msg_elem(msg, i); + rsge = sk_msg_elem_cpy(msg, i); + + psge->length = start - offset; + rsge.length -= psge->length; + rsge.offset += start; + + sk_msg_iter_var_next(i); + sg_unmark_end(psge); + sk_msg_iter_next(msg, end); + } + + /* Slot(s) to place newly allocated data */ + new = i; + + /* Shift one or two slots as needed */ + if (!copy) { + sge = sk_msg_elem_cpy(msg, i); + + sk_msg_iter_var_next(i); + sg_unmark_end(&sge); + sk_msg_iter_next(msg, end); + + nsge = sk_msg_elem_cpy(msg, i); + if (rsge.length) { + sk_msg_iter_var_next(i); + nnsge = sk_msg_elem_cpy(msg, i); + } + + while (i != msg->sg.end) { + msg->sg.data[i] = sge; + sge = nsge; + sk_msg_iter_var_next(i); + if (rsge.length) { + nsge = nnsge; + nnsge = sk_msg_elem_cpy(msg, i); + } else { + nsge = sk_msg_elem_cpy(msg, i); + } + } + } + + /* Place newly allocated data buffer */ + sk_mem_charge(msg->sk, len); + msg->sg.size += len; + msg->sg.copy[new] = false; + sg_set_page(&msg->sg.data[new], page, len + copy, 0); + if (rsge.length) { + get_page(sg_page(&rsge)); + sk_msg_iter_var_next(new); + msg->sg.data[new] = rsge; + } + + sk_msg_compute_data_pointers(msg); + return 0; +} + +static const struct bpf_func_proto bpf_msg_push_data_proto = { + .func = bpf_msg_push_data, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, +}; + BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) { return task_get_classid(skb); @@ -4854,6 +4985,7 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_xdp_adjust_head || func == bpf_xdp_adjust_meta || func == bpf_msg_pull_data || + func == bpf_msg_push_data || func == bpf_xdp_adjust_tail || #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) func == bpf_lwt_seg6_store_bytes || @@ -5130,6 +5262,8 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_msg_cork_bytes_proto; case BPF_FUNC_msg_pull_data: return &bpf_msg_pull_data_proto; + case BPF_FUNC_msg_push_data: + return &bpf_msg_push_data_proto; case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; default: -- cgit v1.2.3