diff options
25 files changed, 1429 insertions, 51 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 31421c74ba08..50105e0b8fcc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -169,6 +169,7 @@ struct bpf_map { u32 value_size; u32 max_entries; u32 map_flags; + u64 map_extra; /* any per-map-type extra fields */ int spin_lock_off; /* >=0 valid offset, <0 error */ int timer_off; /* >=0 valid offset, <0 error */ u32 id; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 9c81724e4b98..c4424ac2fa02 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -125,6 +125,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_RINGBUF, ringbuf_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_BLOOM_FILTER, bloom_filter_map_ops) BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint) BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c10820037883..8bead4aa3ad0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -906,6 +906,7 @@ enum bpf_map_type { BPF_MAP_TYPE_RINGBUF, BPF_MAP_TYPE_INODE_STORAGE, BPF_MAP_TYPE_TASK_STORAGE, + BPF_MAP_TYPE_BLOOM_FILTER, }; /* Note that tracing related programs such as @@ -1274,6 +1275,13 @@ union bpf_attr { * struct stored as the * map value */ + /* Any per-map-type extra fields + * + * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the + * number of hash functions (if 0, the bloom filter will default + * to using 5 hash functions). + */ + __u64 map_extra; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -5638,6 +5646,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u64 map_extra; } __attribute__((aligned(8))); struct bpf_btf_info { diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 7f33098ca63f..cf6ca339f3cd 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -7,7 +7,7 @@ endif CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.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) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c new file mode 100644 index 000000000000..7c50232b7571 --- /dev/null +++ b/kernel/bpf/bloom_filter.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <linux/bitmap.h> +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/err.h> +#include <linux/jhash.h> +#include <linux/random.h> + +#define BLOOM_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_ZERO_SEED | BPF_F_ACCESS_MASK) + +struct bpf_bloom_filter { + struct bpf_map map; + u32 bitset_mask; + u32 hash_seed; + /* If the size of the values in the bloom filter is u32 aligned, + * then it is more performant to use jhash2 as the underlying hash + * function, else we use jhash. This tracks the number of u32s + * in an u32-aligned value size. If the value size is not u32 aligned, + * this will be 0. + */ + u32 aligned_u32_count; + u32 nr_hash_funcs; + unsigned long bitset[]; +}; + +static u32 hash(struct bpf_bloom_filter *bloom, void *value, + u32 value_size, u32 index) +{ + u32 h; + + if (bloom->aligned_u32_count) + h = jhash2(value, bloom->aligned_u32_count, + bloom->hash_seed + index); + else + h = jhash(value, value_size, bloom->hash_seed + index); + + return h & bloom->bitset_mask; +} + +static int peek_elem(struct bpf_map *map, void *value) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + u32 i, h; + + for (i = 0; i < bloom->nr_hash_funcs; i++) { + h = hash(bloom, value, map->value_size, i); + if (!test_bit(h, bloom->bitset)) + return -ENOENT; + } + + return 0; +} + +static int push_elem(struct bpf_map *map, void *value, u64 flags) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + u32 i, h; + + if (flags != BPF_ANY) + return -EINVAL; + + for (i = 0; i < bloom->nr_hash_funcs; i++) { + h = hash(bloom, value, map->value_size, i); + set_bit(h, bloom->bitset); + } + + return 0; +} + +static int pop_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static struct bpf_map *map_alloc(union bpf_attr *attr) +{ + u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; + int numa_node = bpf_map_attr_numa_node(attr); + struct bpf_bloom_filter *bloom; + + if (!bpf_capable()) + return ERR_PTR(-EPERM); + + if (attr->key_size != 0 || attr->value_size == 0 || + attr->max_entries == 0 || + attr->map_flags & ~BLOOM_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags) || + (attr->map_extra & ~0xF)) + return ERR_PTR(-EINVAL); + + /* The lower 4 bits of map_extra specify the number of hash functions */ + nr_hash_funcs = attr->map_extra & 0xF; + if (nr_hash_funcs == 0) + /* Default to using 5 hash functions if unspecified */ + nr_hash_funcs = 5; + + /* For the bloom filter, the optimal bit array size that minimizes the + * false positive probability is n * k / ln(2) where n is the number of + * expected entries in the bloom filter and k is the number of hash + * functions. We use 7 / 5 to approximate 1 / ln(2). + * + * We round this up to the nearest power of two to enable more efficient + * hashing using bitmasks. The bitmask will be the bit array size - 1. + * + * If this overflows a u32, the bit array size will have 2^32 (4 + * GB) bits. + */ + if (check_mul_overflow(attr->max_entries, nr_hash_funcs, &nr_bits) || + check_mul_overflow(nr_bits / 5, (u32)7, &nr_bits) || + nr_bits > (1UL << 31)) { + /* The bit array size is 2^32 bits but to avoid overflowing the + * u32, we use U32_MAX, which will round up to the equivalent + * number of bytes + */ + bitset_bytes = BITS_TO_BYTES(U32_MAX); + bitset_mask = U32_MAX; + } else { + if (nr_bits <= BITS_PER_LONG) + nr_bits = BITS_PER_LONG; + else + nr_bits = roundup_pow_of_two(nr_bits); + bitset_bytes = BITS_TO_BYTES(nr_bits); + bitset_mask = nr_bits - 1; + } + + bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long)); + bloom = bpf_map_area_alloc(sizeof(*bloom) + bitset_bytes, numa_node); + + if (!bloom) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&bloom->map, attr); + + bloom->nr_hash_funcs = nr_hash_funcs; + bloom->bitset_mask = bitset_mask; + + /* Check whether the value size is u32-aligned */ + if ((attr->value_size & (sizeof(u32) - 1)) == 0) + bloom->aligned_u32_count = + attr->value_size / sizeof(u32); + + if (!(attr->map_flags & BPF_F_ZERO_SEED)) + bloom->hash_seed = get_random_int(); + + return &bloom->map; +} + +static void map_free(struct bpf_map *map) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + + bpf_map_area_free(bloom); +} + +static void *lookup_elem(struct bpf_map *map, void *key) +{ + /* The eBPF program should use map_peek_elem instead */ + return ERR_PTR(-EINVAL); +} + +static int update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + /* The eBPF program should use map_push_elem instead */ + return -EINVAL; +} + +static int check_btf(const struct bpf_map *map, const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type) +{ + /* Bloom filter maps are keyless */ + return btf_type_is_void(key_type) ? 0 : -EINVAL; +} + +static int bpf_bloom_btf_id; +const struct bpf_map_ops bloom_filter_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc = map_alloc, + .map_free = map_free, + .map_push_elem = push_elem, + .map_peek_elem = peek_elem, + .map_pop_elem = pop_elem, + .map_lookup_elem = lookup_elem, + .map_update_elem = update_elem, + .map_check_btf = check_btf, + .map_btf_name = "bpf_bloom_filter", + .map_btf_id = &bpf_bloom_btf_id, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 3e1c024ce3ed..f7c2c6354add 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -199,7 +199,8 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, err = bpf_fd_reuseport_array_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { + map->map_type == BPF_MAP_TYPE_STACK || + map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_push_elem(map, value, flags); } else { rcu_read_lock(); @@ -238,7 +239,8 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *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) { + map->map_type == BPF_MAP_TYPE_STACK || + map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_peek_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* struct_ops map requires directly updating "value" */ @@ -348,6 +350,7 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) map->max_entries = attr->max_entries; map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); map->numa_node = bpf_map_attr_numa_node(attr); + map->map_extra = attr->map_extra; } static int bpf_map_alloc_id(struct bpf_map *map) @@ -553,6 +556,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" + "map_extra:\t%#llx\n" "memlock:\t%lu\n" "map_id:\t%u\n" "frozen:\t%u\n", @@ -561,6 +565,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) map->value_size, map->max_entries, map->map_flags, + (unsigned long long)map->map_extra, bpf_map_memory_footprint(map), map->id, READ_ONCE(map->frozen)); @@ -810,7 +815,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return ret; } -#define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id +#define BPF_MAP_CREATE_LAST_FIELD map_extra /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -831,6 +836,10 @@ static int map_create(union bpf_attr *attr) return -EINVAL; } + if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && + attr->map_extra != 0) + return -EINVAL; + f_flags = bpf_get_file_flag(attr->map_flags); if (f_flags < 0) return f_flags; @@ -1080,6 +1089,14 @@ static int map_lookup_elem(union bpf_attr *attr) if (!value) goto free_key; + if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { + if (copy_from_user(value, uvalue, value_size)) + err = -EFAULT; + else + err = bpf_map_copy_value(map, key, value, attr->flags); + goto free_value; + } + err = bpf_map_copy_value(map, key, value, attr->flags); if (err) goto free_value; @@ -3881,6 +3898,7 @@ static int bpf_map_get_info_by_fd(struct file *file, info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; + info.map_extra = map->map_extra; memcpy(info.name, map->name, sizeof(map->name)); if (map->btf) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c6616e325803..3c8aa7df1773 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5002,7 +5002,10 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env, return -EINVAL; } break; - + case BPF_MAP_TYPE_BLOOM_FILTER: + if (meta->func_id == BPF_FUNC_map_peek_elem) + *arg_type = ARG_PTR_TO_MAP_VALUE; + break; default: break; } @@ -5577,6 +5580,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_task_storage_delete) goto error; break; + case BPF_MAP_TYPE_BLOOM_FILTER: + if (func_id != BPF_FUNC_map_peek_elem && + func_id != BPF_FUNC_map_push_elem) + goto error; + break; default: break; } @@ -5644,13 +5652,18 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, map->map_type != BPF_MAP_TYPE_SOCKHASH) 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; + case BPF_FUNC_map_peek_elem: + case BPF_FUNC_map_push_elem: + if (map->map_type != BPF_MAP_TYPE_QUEUE && + map->map_type != BPF_MAP_TYPE_STACK && + map->map_type != BPF_MAP_TYPE_BLOOM_FILTER) + goto error; + break; case BPF_FUNC_sk_storage_get: case BPF_FUNC_sk_storage_delete: if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c10820037883..8bead4aa3ad0 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -906,6 +906,7 @@ enum bpf_map_type { BPF_MAP_TYPE_RINGBUF, BPF_MAP_TYPE_INODE_STORAGE, BPF_MAP_TYPE_TASK_STORAGE, + BPF_MAP_TYPE_BLOOM_FILTER, }; /* Note that tracing related programs such as @@ -1274,6 +1275,13 @@ union bpf_attr { * struct stored as the * map value */ + /* Any per-map-type extra fields + * + * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the + * number of hash functions (if 0, the bloom filter will default + * to using 5 hash functions). + */ + __u64 map_extra; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -5638,6 +5646,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u64 map_extra; } __attribute__((aligned(8))); struct bpf_btf_info { diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 7d1741ceaa32..fe4b6ebc9b8f 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -77,7 +77,7 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size) return fd; } -int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) +int libbpf__bpf_create_map_xattr(const struct bpf_create_map_params *create_attr) { union bpf_attr attr; int fd; @@ -102,11 +102,36 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) create_attr->btf_vmlinux_value_type_id; else attr.inner_map_fd = create_attr->inner_map_fd; + attr.map_extra = create_attr->map_extra; fd = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); return libbpf_err_errno(fd); } +int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) +{ + struct bpf_create_map_params p = {}; + + p.map_type = create_attr->map_type; + p.key_size = create_attr->key_size; + p.value_size = create_attr->value_size; + p.max_entries = create_attr->max_entries; + p.map_flags = create_attr->map_flags; + p.name = create_attr->name; + p.numa_node = create_attr->numa_node; + p.btf_fd = create_attr->btf_fd; + p.btf_key_type_id = create_attr->btf_key_type_id; + p.btf_value_type_id = create_attr->btf_value_type_id; + p.map_ifindex = create_attr->map_ifindex; + if (p.map_type == BPF_MAP_TYPE_STRUCT_OPS) + p.btf_vmlinux_value_type_id = + create_attr->btf_vmlinux_value_type_id; + else + p.inner_map_fd = create_attr->inner_map_fd; + + return libbpf__bpf_create_map_xattr(&p); +} + int bpf_create_map_node(enum bpf_map_type map_type, const char *name, int key_size, int value_size, int max_entries, __u32 map_flags, int node) diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h index 70eccbffefb1..b8d41d6fbc40 100644 --- a/tools/lib/bpf/bpf_gen_internal.h +++ b/tools/lib/bpf/bpf_gen_internal.h @@ -43,7 +43,7 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level); int bpf_gen__finish(struct bpf_gen *gen); void bpf_gen__free(struct bpf_gen *gen); void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size); -void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_attr *map_attr, int map_idx); +void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_params *map_attr, int map_idx); struct bpf_prog_load_params; void bpf_gen__prog_load(struct bpf_gen *gen, struct bpf_prog_load_params *load_attr, int prog_idx); void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u32 value_size); diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index 937bfc7db41e..e552484ae4a4 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -431,7 +431,7 @@ void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data, } void bpf_gen__map_create(struct bpf_gen *gen, - struct bpf_create_map_attr *map_attr, int map_idx) + struct bpf_create_map_params *map_attr, int map_idx) { int attr_size = offsetofend(union bpf_attr, btf_vmlinux_value_type_id); bool close_inner_map_fd = false; @@ -443,6 +443,7 @@ void bpf_gen__map_create(struct bpf_gen *gen, attr.key_size = map_attr->key_size; attr.value_size = map_attr->value_size; attr.map_flags = map_attr->map_flags; + attr.map_extra = map_attr->map_extra; memcpy(attr.map_name, map_attr->name, min((unsigned)strlen(map_attr->name), BPF_OBJ_NAME_LEN - 1)); attr.numa_node = map_attr->numa_node; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 59d39ce9f375..232e4efe82e9 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -400,6 +400,7 @@ struct bpf_map { char *pin_path; bool pinned; bool reused; + __u64 map_extra; }; enum extern_type { @@ -2324,6 +2325,13 @@ int parse_btf_map_def(const char *map_name, struct btf *btf, } map_def->pinning = val; map_def->parts |= MAP_DEF_PINNING; + } else if (strcmp(name, "map_extra") == 0) { + __u32 map_extra; + + if (!get_map_field_int(map_name, btf, m, &map_extra)) + return -EINVAL; + map_def->map_extra = map_extra; + map_def->parts |= MAP_DEF_MAP_EXTRA; } else { if (strict) { pr_warn("map '%s': unknown field '%s'.\n", map_name, name); @@ -2348,6 +2356,7 @@ static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def map->def.value_size = def->value_size; map->def.max_entries = def->max_entries; map->def.map_flags = def->map_flags; + map->map_extra = def->map_extra; map->numa_node = def->numa_node; map->btf_key_type_id = def->key_type_id; @@ -2371,7 +2380,10 @@ static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def if (def->parts & MAP_DEF_MAX_ENTRIES) pr_debug("map '%s': found max_entries = %u.\n", map->name, def->max_entries); if (def->parts & MAP_DEF_MAP_FLAGS) - pr_debug("map '%s': found map_flags = %u.\n", map->name, def->map_flags); + pr_debug("map '%s': found map_flags = 0x%x.\n", map->name, def->map_flags); + if (def->parts & MAP_DEF_MAP_EXTRA) + pr_debug("map '%s': found map_extra = 0x%llx.\n", map->name, + (unsigned long long)def->map_extra); if (def->parts & MAP_DEF_PINNING) pr_debug("map '%s': found pinning = %u.\n", map->name, def->pinning); if (def->parts & MAP_DEF_NUMA_NODE) @@ -4210,6 +4222,7 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) map->btf_key_type_id = info.btf_key_type_id; map->btf_value_type_id = info.btf_value_type_id; map->reused = true; + map->map_extra = info.map_extra; return 0; @@ -4724,7 +4737,8 @@ static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) map_info.key_size == map->def.key_size && map_info.value_size == map->def.value_size && map_info.max_entries == map->def.max_entries && - map_info.map_flags == map->def.map_flags); + map_info.map_flags == map->def.map_flags && + map_info.map_extra == map->map_extra); } static int @@ -4807,7 +4821,7 @@ static void bpf_map__destroy(struct bpf_map *map); static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner) { - struct bpf_create_map_attr create_attr; + struct bpf_create_map_params create_attr; struct bpf_map_def *def = &map->def; int err = 0; @@ -4821,6 +4835,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.key_size = def->key_size; create_attr.value_size = def->value_size; create_attr.numa_node = map->numa_node; + create_attr.map_extra = map->map_extra; if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && !def->max_entries) { int nr_cpus; @@ -4895,7 +4910,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b */ map->fd = 0; } else { - map->fd = bpf_create_map_xattr(&create_attr); + map->fd = libbpf__bpf_create_map_xattr(&create_attr); } if (map->fd < 0 && (create_attr.btf_key_type_id || create_attr.btf_value_type_id)) { @@ -4910,7 +4925,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.btf_value_type_id = 0; map->btf_key_type_id = 0; map->btf_value_type_id = 0; - map->fd = bpf_create_map_xattr(&create_attr); + map->fd = libbpf__bpf_create_map_xattr(&create_attr); } err = map->fd < 0 ? -errno : 0; @@ -8880,6 +8895,19 @@ int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags) return 0; } +__u64 bpf_map__map_extra(const struct bpf_map *map) +{ + return map->map_extra; +} + +int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra) +{ + if (map->fd >= 0) + return libbpf_err(-EBUSY); + map->map_extra = map_extra; + return 0; +} + __u32 bpf_map__numa_node(const struct bpf_map *map) { return map->numa_node; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index defabdbe7760..9de0f299706b 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -600,6 +600,9 @@ LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map); /* get/set map if_index */ LIBBPF_API __u32 bpf_map__ifindex(const struct bpf_map *map); LIBBPF_API int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); +/* get/set map map_extra flags */ +LIBBPF_API __u64 bpf_map__map_extra(const struct bpf_map *map); +LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 15239c05659c..43580eb47740 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -389,6 +389,8 @@ LIBBPF_0.5.0 { LIBBPF_0.6.0 { global: + bpf_map__map_extra; + bpf_map__set_map_extra; bpf_object__next_map; bpf_object__next_program; bpf_object__prev_map; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 13bc7950e304..a6dd7e25747f 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -193,8 +193,9 @@ enum map_def_parts { MAP_DEF_NUMA_NODE = 0x080, MAP_DEF_PINNING = 0x100, MAP_DEF_INNER_MAP = 0x200, + MAP_DEF_MAP_EXTRA = 0x400, - MAP_DEF_ALL = 0x3ff, /* combination of all above */ + MAP_DEF_ALL = 0x7ff, /* combination of all above */ }; struct btf_map_def { @@ -208,6 +209,7 @@ struct btf_map_def { __u32 map_flags; __u32 numa_node; __u32 pinning; + __u64 map_extra; }; int parse_btf_map_def(const char *map_name, struct btf *btf, @@ -303,6 +305,27 @@ struct bpf_prog_load_params { int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr); +struct bpf_create_map_params { + const char *name; + enum bpf_map_type map_type; + __u32 map_flags; + __u32 key_size; + __u32 value_size; + __u32 max_entries; + __u32 numa_node; + __u32 btf_fd; + __u32 btf_key_type_id; + __u32 btf_value_type_id; + __u32 map_ifindex; + union { + __u32 inner_map_fd; + __u32 btf_vmlinux_value_type_id; + }; + __u64 map_extra; +}; + +int libbpf__bpf_create_map_xattr(const struct bpf_create_map_params *create_attr); + struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf); void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, const char **prefix, int *kind); diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index ac47cf9760fc..2c464cb78d6b 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -524,18 +524,20 @@ $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) # Benchmark runner $(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(BPFOBJ) $(call msg,CC,,$@) - $(Q)$(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@ + $(Q)$(CC) $(CFLAGS) -O2 -c $(filter %.c,$^) $(LDLIBS) -o $@ $(OUTPUT)/bench_rename.o: $(OUTPUT)/test_overhead.skel.h $(OUTPUT)/bench_trigger.o: $(OUTPUT)/trigger_bench.skel.h $(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \ $(OUTPUT)/perfbuf_bench.skel.h +$(OUTPUT)/bench_bloom_filter_map.o: $(OUTPUT)/bloom_filter_bench.skel.h $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ) $(OUTPUT)/bench: LDLIBS += -lm $(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \ $(OUTPUT)/bench_count.o \ $(OUTPUT)/bench_rename.o \ $(OUTPUT)/bench_trigger.o \ - $(OUTPUT)/bench_ringbufs.o + $(OUTPUT)/bench_ringbufs.o \ + $(OUTPUT)/bench_bloom_filter_map.o $(call msg,BINARY,,$@) $(Q)$(CC) $(LDFLAGS) -o $@ $(filter %.a %.o,$^) $(LDLIBS) diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index 6ea15b93a2f8..cc4722f693e9 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -51,6 +51,35 @@ void setup_libbpf() fprintf(stderr, "failed to increase RLIMIT_MEMLOCK: %d", err); } +void false_hits_report_progress(int iter, struct bench_res *res, long delta_ns) +{ + long total = res->false_hits + res->hits + res->drops; + + printf("Iter %3d (%7.3lfus): ", + iter, (delta_ns - 1000000000) / 1000.0); + + printf("%ld false hits of %ld total operations. Percentage = %2.2f %%\n", + res->false_hits, total, ((float)res->false_hits / total) * 100); +} + +void false_hits_report_final(struct bench_res res[], int res_cnt) +{ + long total_hits = 0, total_drops = 0, total_false_hits = 0, total_ops = 0; + int i; + + for (i = 0; i < res_cnt; i++) { + total_hits += res[i].hits; + total_false_hits += res[i].false_hits; + total_drops += res[i].drops; + } + total_ops = total_hits + total_false_hits + total_drops; + + printf("Summary: %ld false hits of %ld total operations. ", + total_false_hits, total_ops); + printf("Percentage = %2.2f %%\n", + ((float)total_false_hits / total_ops) * 100); +} + void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns) { double hits_per_sec, drops_per_sec; @@ -63,20 +92,22 @@ void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns) printf("Iter %3d (%7.3lfus): ", iter, (delta_ns - 1000000000) / 1000.0); - printf("hits %8.3lfM/s (%7.3lfM/prod), drops %8.3lfM/s\n", - hits_per_sec, hits_per_prod, drops_per_sec); + printf("hits %8.3lfM/s (%7.3lfM/prod), drops %8.3lfM/s, total operations %8.3lfM/s\n", + hits_per_sec, hits_per_prod, drops_per_sec, hits_per_sec + drops_per_sec); } void hits_drops_report_final(struct bench_res res[], int res_cnt) { int i; - double hits_mean = 0.0, drops_mean = 0.0; - double hits_stddev = 0.0, drops_stddev = 0.0; + double hits_mean = 0.0, drops_mean = 0.0, total_ops_mean = 0.0; + double hits_stddev = 0.0, drops_stddev = 0.0, total_ops_stddev = 0.0; + double total_ops; for (i = 0; i < res_cnt; i++) { hits_mean += res[i].hits / 1000000.0 / (0.0 + res_cnt); drops_mean += res[i].drops / 1000000.0 / (0.0 + res_cnt); } + total_ops_mean = hits_ |