From 8bad74f9840f87661f20ced3dc80c84ab4fd55a1 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 28 Sep 2018 14:45:36 +0000 Subject: bpf: extend cgroup bpf core to allow multiple cgroup storage types In order to introduce per-cpu cgroup storage, let's generalize bpf cgroup core to support multiple cgroup storage types. Potentially, per-node cgroup storage can be added later. This commit is mostly a formal change that replaces cgroup_storage pointer with a array of cgroup_storage pointers. It doesn't actually introduce a new storage type, it will be done later. Each bpf program is now able to have one cgroup storage of each type. Signed-off-by: Roman Gushchin Acked-by: Song Liu Cc: Daniel Borkmann Cc: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/helpers.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'kernel/bpf/helpers.c') diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 1991466b8327..9070b2ace6aa 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -194,16 +194,18 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { .ret_type = RET_INTEGER, }; -DECLARE_PER_CPU(void*, bpf_cgroup_storage); +#ifdef CONFIG_CGROUP_BPF +DECLARE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) { - /* map and flags arguments are not used now, - * but provide an ability to extend the API - * for other types of local storages. - * verifier checks that their values are correct. + /* flags argument is not used now, + * but provides an ability to extend the API. + * verifier checks that its value is correct. */ - return (unsigned long) this_cpu_read(bpf_cgroup_storage); + enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); + + return (unsigned long) this_cpu_read(bpf_cgroup_storage[stype]); } const struct bpf_func_proto bpf_get_local_storage_proto = { @@ -214,3 +216,4 @@ const struct bpf_func_proto bpf_get_local_storage_proto = { .arg2_type = ARG_ANYTHING, }; #endif +#endif -- cgit v1.2.3 From f294b37ec7b24a574884cd157497a3748081c0f0 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 28 Sep 2018 14:45:40 +0000 Subject: bpf: rework cgroup storage pointer passing To simplify the following introduction of per-cpu cgroup storage, let's rework a bit a mechanism of passing a pointer to a cgroup storage into the bpf_get_local_storage(). Let's save a pointer to the corresponding bpf_cgroup_storage structure, instead of a pointer to the actual buffer. It will help us to handle per-cpu storage later, which has a different way of accessing to the actual data. Signed-off-by: Roman Gushchin Acked-by: Song Liu Cc: Daniel Borkmann Cc: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 13 ++++--------- kernel/bpf/helpers.c | 8 ++++++-- kernel/bpf/local_storage.c | 3 ++- 3 files changed, 12 insertions(+), 12 deletions(-) (limited to 'kernel/bpf/helpers.c') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index e9871b012dac..7e0c9a1d48b7 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -23,7 +23,8 @@ struct bpf_cgroup_storage; extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) -DECLARE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); +DECLARE_PER_CPU(struct bpf_cgroup_storage*, + bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); #define for_each_cgroup_storage_type(stype) \ for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) @@ -115,15 +116,9 @@ static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) { enum bpf_cgroup_storage_type stype; - struct bpf_storage_buffer *buf; - - for_each_cgroup_storage_type(stype) { - if (!storage[stype]) - continue; - buf = READ_ONCE(storage[stype]->buf); - this_cpu_write(bpf_cgroup_storage[stype], &buf->data[0]); - } + for_each_cgroup_storage_type(stype) + this_cpu_write(bpf_cgroup_storage[stype], storage[stype]); } struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 9070b2ace6aa..e42f8789b7ea 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -195,7 +195,8 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { }; #ifdef CONFIG_CGROUP_BPF -DECLARE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); +DECLARE_PER_CPU(struct bpf_cgroup_storage*, + bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) { @@ -204,8 +205,11 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) * verifier checks that its value is correct. */ enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); + struct bpf_cgroup_storage *storage; - return (unsigned long) this_cpu_read(bpf_cgroup_storage[stype]); + storage = this_cpu_read(bpf_cgroup_storage[stype]); + + return (unsigned long)&READ_ONCE(storage->buf)->data[0]; } 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 0bd9f19fc557..6742292fb39e 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -7,7 +7,8 @@ #include #include -DEFINE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); +DEFINE_PER_CPU(struct bpf_cgroup_storage*, + bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); #ifdef CONFIG_CGROUP_BPF -- 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 'kernel/bpf/helpers.c') 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 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 'kernel/bpf/helpers.c') 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