diff options
Diffstat (limited to 'kernel/bpf')
| -rw-r--r-- | kernel/bpf/arraymap.c | 1 | ||||
| -rw-r--r-- | kernel/bpf/btf.c | 860 | ||||
| -rw-r--r-- | kernel/bpf/core.c | 257 | ||||
| -rw-r--r-- | kernel/bpf/cpumap.c | 2 | ||||
| -rw-r--r-- | kernel/bpf/hashtab.c | 13 | ||||
| -rw-r--r-- | kernel/bpf/local_storage.c | 90 | ||||
| -rw-r--r-- | kernel/bpf/lpm_trie.c | 60 | ||||
| -rw-r--r-- | kernel/bpf/offload.c | 76 | ||||
| -rw-r--r-- | kernel/bpf/queue_stack_maps.c | 16 | ||||
| -rw-r--r-- | kernel/bpf/syscall.c | 195 | ||||
| -rw-r--r-- | kernel/bpf/verifier.c | 704 |
11 files changed, 1982 insertions, 292 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 24583da9ffd1..25632a75d630 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -382,6 +382,7 @@ static void percpu_array_map_seq_show_elem(struct bpf_map *map, void *key, } static int array_map_check_btf(const struct bpf_map *map, + const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index ee4c82667d65..715f9fcf4712 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5,6 +5,7 @@ #include <uapi/linux/types.h> #include <linux/seq_file.h> #include <linux/compiler.h> +#include <linux/ctype.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/anon_inodes.h> @@ -163,7 +164,7 @@ #define BITS_ROUNDUP_BYTES(bits) \ (BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits)) -#define BTF_INFO_MASK 0x0f00ffff +#define BTF_INFO_MASK 0x8f00ffff #define BTF_INT_MASK 0x0fffffff #define BTF_TYPE_ID_VALID(type_id) ((type_id) <= BTF_MAX_TYPE) #define BTF_STR_OFFSET_VALID(name_off) ((name_off) <= BTF_MAX_NAME_OFFSET) @@ -259,6 +260,8 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_VOLATILE] = "VOLATILE", [BTF_KIND_CONST] = "CONST", [BTF_KIND_RESTRICT] = "RESTRICT", + [BTF_KIND_FUNC] = "FUNC", + [BTF_KIND_FUNC_PROTO] = "FUNC_PROTO", }; struct btf_kind_operations { @@ -271,6 +274,10 @@ struct btf_kind_operations { const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type); + int (*check_kflag_member)(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type); void (*log_details)(struct btf_verifier_env *env, const struct btf_type *t); void (*seq_show)(const struct btf *btf, const struct btf_type *t, @@ -281,6 +288,9 @@ struct btf_kind_operations { static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS]; static struct btf_type btf_void; +static int btf_resolve(struct btf_verifier_env *env, + const struct btf_type *t, u32 type_id); + static bool btf_type_is_modifier(const struct btf_type *t) { /* Some of them is not strictly a C modifier @@ -306,15 +316,33 @@ static bool btf_type_is_modifier(const struct btf_type *t) static bool btf_type_is_void(const struct btf_type *t) { - /* void => no type and size info. - * Hence, FWD is also treated as void. - */ - return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD; + return t == &btf_void; +} + +static bool btf_type_is_fwd(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_FWD; +} + +static bool btf_type_is_func(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC; +} + +static bool btf_type_is_func_proto(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO; +} + +static bool btf_type_nosize(const struct btf_type *t) +{ + return btf_type_is_void(t) || btf_type_is_fwd(t) || + btf_type_is_func(t) || btf_type_is_func_proto(t); } -static bool btf_type_is_void_or_null(const struct btf_type *t) +static bool btf_type_nosize_or_null(const struct btf_type *t) { - return !t || btf_type_is_void(t); + return !t || btf_type_nosize(t); } /* union is only a special case of struct: @@ -395,6 +423,25 @@ static u16 btf_type_vlen(const struct btf_type *t) return BTF_INFO_VLEN(t->info); } +static bool btf_type_kflag(const struct btf_type *t) +{ + return BTF_INFO_KFLAG(t->info); +} + +static u32 btf_member_bit_offset(const struct btf_type *struct_type, + const struct btf_member *member) +{ + return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset) + : member->offset; +} + +static u32 btf_member_bitfield_size(const struct btf_type *struct_type, + const struct btf_member *member) +{ + return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset) + : 0; +} + static u32 btf_type_int(const struct btf_type *t) { return *(u32 *)(t + 1); @@ -420,13 +467,37 @@ static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) return kind_ops[BTF_INFO_KIND(t->info)]; } -static bool btf_name_offset_valid(const struct btf *btf, u32 offset) +bool btf_name_offset_valid(const struct btf *btf, u32 offset) { return BTF_STR_OFFSET_VALID(offset) && offset < btf->hdr.str_len; } -static const char *btf_name_by_offset(const struct btf *btf, u32 offset) +/* Only C-style identifier is permitted. This can be relaxed if + * necessary. + */ +static bool btf_name_valid_identifier(const struct btf *btf, u32 offset) +{ + /* offset must be valid */ + const char *src = &btf->strings[offset]; + const char *src_limit; + + if (!isalpha(*src) && *src != '_') + return false; + + /* set a limit on identifier length */ + src_limit = src + KSYM_NAME_LEN; + src++; + while (*src && src < src_limit) { + if (!isalnum(*src) && *src != '_') + return false; + src++; + } + + return !*src; +} + +static const char *__btf_name_by_offset(const struct btf *btf, u32 offset) { if (!offset) return "(anon)"; @@ -436,7 +507,15 @@ static const char *btf_name_by_offset(const struct btf *btf, u32 offset) return "(invalid-name-offset)"; } -static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) +const char *btf_name_by_offset(const struct btf *btf, u32 offset) +{ + if (offset < btf->hdr.str_len) + return &btf->strings[offset]; + + return NULL; +} + +const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) { if (type_id > btf->nr_types) return NULL; @@ -466,6 +545,47 @@ static bool btf_type_int_is_regular(const struct btf_type *t) return true; } +/* + * Check that given struct member is a regular int with expected + * offset and size. + */ +bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, + const struct btf_member *m, + u32 expected_offset, u32 expected_size) +{ + const struct btf_type *t; + u32 id, int_data; + u8 nr_bits; + + id = m->type; + t = btf_type_id_size(btf, &id, NULL); + if (!t || !btf_type_is_int(t)) + return false; + + int_data = btf_type_int(t); + nr_bits = BTF_INT_BITS(int_data); + if (btf_type_kflag(s)) { + u32 bitfield_size = BTF_MEMBER_BITFIELD_SIZE(m->offset); + u32 bit_offset = BTF_MEMBER_BIT_OFFSET(m->offset); + + /* if kflag set, int should be a regular int and + * bit offset should be at byte boundary. + */ + return !bitfield_size && + BITS_ROUNDUP_BYTES(bit_offset) == expected_offset && + BITS_ROUNDUP_BYTES(nr_bits) == expected_size; + } + + if (BTF_INT_OFFSET(int_data) || + BITS_PER_BYTE_MASKED(m->offset) || + BITS_ROUNDUP_BYTES(m->offset) != expected_offset || + BITS_PER_BYTE_MASKED(nr_bits) || + BITS_ROUNDUP_BYTES(nr_bits) != expected_size) + return false; + + return true; +} + __printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log, const char *fmt, ...) { @@ -506,7 +626,7 @@ __printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env, __btf_verifier_log(log, "[%u] %s %s%s", env->log_type_id, btf_kind_str[kind], - btf_name_by_offset(btf, t->name_off), + __btf_name_by_offset(btf, t->name_off), log_details ? " " : ""); if (log_details) @@ -549,9 +669,17 @@ static void btf_verifier_log_member(struct btf_verifier_env *env, if (env->phase != CHECK_META) btf_verifier_log_type(env, struct_type, NULL); - __btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u", - btf_name_by_offset(btf, member->name_off), - member->type, member->offset); + if (btf_type_kflag(struct_type)) + __btf_verifier_log(log, + "\t%s type_id=%u bitfield_size=%u bits_offset=%u", + __btf_name_by_offset(btf, member->name_off), + member->type, + BTF_MEMBER_BITFIELD_SIZE(member->offset), + BTF_MEMBER_BIT_OFFSET(member->offset)); + else + __btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u", + __btf_name_by_offset(btf, member->name_off), + member->type, member->offset); if (fmt && *fmt) { __btf_verifier_log(log, " "); @@ -740,11 +868,15 @@ static bool env_type_is_resolve_sink(const struct btf_verifier_env *env, /* int, enum or void is a sink */ return !btf_type_needs_resolve(next_type); case RESOLVE_PTR: - /* int, enum, void, struct or array is a sink for ptr */ + /* int, enum, void, struct, array, func or func_proto is a sink + * for ptr + */ return !btf_type_is_modifier(next_type) && !btf_type_is_ptr(next_type); case RESOLVE_STRUCT_OR_ARRAY: - /* int, enum, void or ptr is a sink for struct and array */ + /* int, enum, void, ptr, func or func_proto is a sink + * for struct and array + */ return !btf_type_is_modifier(next_type) && !btf_type_is_array(next_type) && !btf_type_is_struct(next_type); @@ -826,7 +958,7 @@ const struct btf_type *btf_type_id_size(const struct btf *btf, u32 size = 0; size_type = btf_type_by_id(btf, size_type_id); - if (btf_type_is_void_or_null(size_type)) + if (btf_type_nosize_or_null(size_type)) return NULL; if (btf_type_has_size(size_type)) { @@ -842,7 +974,7 @@ const struct btf_type *btf_type_id_size(const struct btf *btf, size = btf->resolved_sizes[size_type_id]; size_type_id = btf->resolved_ids[size_type_id]; size_type = btf_type_by_id(btf, size_type_id); - if (btf_type_is_void(size_type)) + if (btf_type_nosize_or_null(size_type)) return NULL; } @@ -863,6 +995,38 @@ static int btf_df_check_member(struct btf_verifier_env *env, return -EINVAL; } +static int btf_df_check_kflag_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + btf_verifier_log_basic(env, struct_type, + "Unsupported check_kflag_member"); + return -EINVAL; +} + +/* Used for ptr, array and struct/union type members. + * int, enum and modifier types have their specific callback functions. + */ +static int btf_generic_check_kflag_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + if (BTF_MEMBER_BITFIELD_SIZE(member->offset)) { + btf_verifier_log_member(env, struct_type, member, + "Invalid member bitfield_size"); + return -EINVAL; + } + + /* bitfield size is 0, so member->offset represents bit offset only. + * It is safe to call non kflag check_member variants. + */ + return btf_type_ops(member_type)->check_member(env, struct_type, + member, + member_type); +} + static int btf_df_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { @@ -915,6 +1079,62 @@ static int btf_int_check_member(struct btf_verifier_env *env, return 0; } +static int btf_int_check_kflag_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 struct_bits_off, nr_bits, nr_int_data_bits, bytes_offset; + u32 int_data = btf_type_int(member_type); + u32 struct_size = struct_type->size; + u32 nr_copy_bits; + + /* a regular int type is required for the kflag int member */ + if (!btf_type_int_is_regular(member_type)) { + btf_verifier_log_member(env, struct_type, member, + "Invalid member base type"); + return -EINVAL; + } + + /* check sanity of bitfield size */ + nr_bits = BTF_MEMBER_BITFIELD_SIZE(member->offset); + struct_bits_off = BTF_MEMBER_BIT_OFFSET(member->offset); + nr_int_data_bits = BTF_INT_BITS(int_data); + if (!nr_bits) { + /* Not a bitfield member, member offset must be at byte + * boundary. + */ + if (BITS_PER_BYTE_MASKED(struct_bits_off)) { + btf_verifier_log_member(env, struct_type, member, + "Invalid member offset"); + return -EINVAL; + } + + nr_bits = nr_int_data_bits; + } else if (nr_bits > nr_int_data_bits) { + btf_verifier_log_member(env, struct_type, member, + "Invalid member bitfield_size"); + return -EINVAL; + } + + bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); + nr_copy_bits = nr_bits + BITS_PER_BYTE_MASKED(struct_bits_off); + if (nr_copy_bits > BITS_PER_U64) { + btf_verifier_log_member(env, struct_type, member, + "nr_copy_bits exceeds 64"); + return -EINVAL; + } + + if (struct_size < bytes_offset || + struct_size - bytes_offset < BITS_ROUNDUP_BYTES(nr_copy_bits)) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + static s32 btf_int_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) @@ -934,6 +1154,11 @@ static s32 btf_int_check_meta(struct btf_verifier_env *env, return -EINVAL; } + if (btf_type_kflag(t)) { + btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); + return -EINVAL; + } + int_data = btf_type_int(t); if (int_data & ~BTF_INT_MASK) { btf_verifier_log_basic(env, t, "Invalid int_data:%x", @@ -986,26 +1211,16 @@ static void btf_int_log(struct btf_verifier_env *env, btf_int_encoding_str(BTF_INT_ENCODING(int_data))); } -static void btf_int_bits_seq_show(const struct btf *btf, - const struct btf_type *t, - void *data, u8 bits_offset, - struct seq_file *m) +static void btf_bitfield_seq_show(void *data, u8 bits_offset, + u8 nr_bits, struct seq_file *m) { u16 left_shift_bits, right_shift_bits; - u32 int_data = btf_type_int(t); - u8 nr_bits = BTF_INT_BITS(int_data); - u8 total_bits_offset; u8 nr_copy_bytes; u8 nr_copy_bits; u64 print_num; - /* - * bits_offset is at most 7. - * BTF_INT_OFFSET() cannot exceed 64 bits. - */ - total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data); - data += BITS_ROUNDDOWN_BYTES(total_bits_offset); - bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset); + data += BITS_ROUNDDOWN_BYTES(bits_offset); + bits_offset = BITS_PER_BYTE_MASKED(bits_offset); nr_copy_bits = nr_bits + bits_offset; nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits); @@ -1025,6 +1240,24 @@ static void btf_int_bits_seq_show(const struct btf *btf, seq_printf(m, "0x%llx", print_num); } + +static void btf_int_bits_seq_show(const struct btf *btf, + const struct btf_type *t, + void *data, u8 bits_offset, + struct seq_file *m) +{ + u32 int_data = btf_type_int(t); + u8 nr_bits = BTF_INT_BITS(int_data); + u8 total_bits_offset; + + /* + * bits_offset is at most 7. + * BTF_INT_OFFSET() cannot exceed 64 bits. + */ + total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data); + btf_bitfield_seq_show(data, total_bits_offset, nr_bits, m); +} + static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct seq_file *m) @@ -1074,6 +1307,7 @@ static const struct btf_kind_operations int_ops = { .check_meta = btf_int_check_meta, .resolve = btf_df_resolve, .check_member = btf_int_check_member, + .check_kflag_member = btf_int_check_kflag_member, .log_details = btf_int_log, .seq_show = btf_int_seq_show, }; @@ -1103,6 +1337,31 @@ static int btf_modifier_check_member(struct btf_verifier_env *env, resolved_type); } +static int btf_modifier_check_kflag_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + const struct btf_type *resolved_type; + u32 resolved_type_id = member->type; + struct btf_member resolved_member; + struct btf *btf = env->btf; + + resolved_type = btf_type_id_size(btf, &resolved_type_id, NULL); + if (!resolved_type) { + btf_verifier_log_member(env, struct_type, member, + "Invalid member"); + return -EINVAL; + } + + resolved_member = *member; + resolved_member.type = resolved_type_id; + + return btf_type_ops(resolved_type)->check_kflag_member(env, struct_type, + &resolved_member, + resolved_type); +} + static int btf_ptr_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, @@ -1138,11 +1397,32 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env, return -EINVAL; } + if (btf_type_kflag(t)) { + btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); + return -EINVAL; + } + if (!BTF_TYPE_ID_VALID(t->type)) { btf_verifier_log_type(env, t, "Invalid type_id"); return -EINVAL; } + /* typedef type must have a valid name, and other ref types, + * volatile, const, restrict, should have a null name. + */ + if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF) { + if (!t->name_off || + !btf_name_valid_identifier(env->btf, t->name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + } else { + if (t->name_off) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + } + btf_verifier_log_type(env, t, NULL); return 0; @@ -1163,10 +1443,6 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, return -EINVAL; } - /* "typedef void new_void", "const void"...etc */ - if (btf_type_is_void(next_type)) - goto resolved; - if (!env_type_is_resolve_sink(env, next_type) && !env_type_is_resolved(env, next_type_id)) return env_stack_push(env, next_type, next_type_id); @@ -1177,13 +1453,18 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, * save us a few type-following when we use it later (e.g. in * pretty print). */ - if (!btf_type_id_size(btf, &next_type_id, &next_type_size) && - !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) { - btf_verifier_log_type(env, v->t, "Invalid type_id"); - return -EINVAL; + if (!btf_type_id_size(btf, &next_type_id, &next_type_size)) { + if (env_type_is_resolved(env, next_type_id)) + next_type = btf_type_id_resolve(btf, &next_type_id); + + /* "typedef void new_void", "const void"...etc */ + if (!btf_type_is_void(next_type) && + !btf_type_is_fwd(next_type)) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } } -resolved: env_stack_pop_resolved(env, next_type_id, next_type_size); return 0; @@ -1196,7 +1477,6 @@ static int btf_ptr_resolve(struct btf_verifier_env *env, const struct btf_type *t = v->t; u32 next_type_id = t->type; struct btf *btf = env->btf; - u32 next_type_size = 0; next_type = btf_type_by_id(btf, next_type_id); if (!next_type) { @@ -1204,10 +1484,6 @@ static int btf_ptr_resolve(struct btf_verifier_env *env, return -EINVAL; } - /* "void *" */ - if (btf_type_is_void(next_type)) - goto resolved; - if (!env_type_is_resolve_sink(env, next_type) && !env_type_is_resolved(env, next_type_id)) return env_stack_push(env, next_type, next_type_id); @@ -1234,13 +1510,18 @@ static int btf_ptr_resolve(struct btf_verifier_env *env, resolved_type_id); } - if (!btf_type_id_size(btf, &next_type_id, &next_type_size) && - !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) { - btf_verifier_log_type(env, v->t, "Invalid type_id"); - return -EINVAL; + if (!btf_type_id_size(btf, &next_type_id, NULL)) { + if (env_type_is_resolved(env, next_type_id)) + next_type = btf_type_id_resolve(btf, &next_type_id); + + if (!btf_type_is_void(next_type) && + !btf_type_is_fwd(next_type) && + !btf_type_is_func_proto(next_type)) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } } -resolved: env_stack_pop_resolved(env, next_type_id, 0); return 0; @@ -1274,6 +1555,7 @@ static struct btf_kind_operations modifier_ops = { .check_meta = btf_ref_type_check_meta, .resolve = btf_modifier_resolve, .check_member = btf_modifier_check_member, + .check_kflag_member = btf_modifier_check_kflag_member, .log_details = btf_ref_type_log, .seq_show = btf_modifier_seq_show, }; @@ -1282,6 +1564,7 @@ static struct btf_kind_operations ptr_ops = { .check_meta = btf_ref_type_check_meta, .resolve = btf_ptr_resolve, .check_member = btf_ptr_check_member, + .check_kflag_member = btf_generic_check_kflag_member, .log_details = btf_ref_type_log, .seq_show = btf_ptr_seq_show, }; @@ -1300,16 +1583,30 @@ static s32 btf_fwd_check_meta(struct btf_verifier_env *env, return -EINVAL; } + /* fwd type must have a valid name */ + if (!t->name_off || + !btf_name_valid_identifier(env->btf, t->name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + btf_verifier_log_type(env, t, NULL); return 0; } +static void btf_fwd_type_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + btf_verifier_log(env, "%s", btf_type_kflag(t) ? "union" : "struct"); +} + static struct btf_kind_operations fwd_ops = { .check_meta = btf_fwd_check_meta, .resolve = btf_df_resolve, .check_member = btf_df_check_member, - .log_details = btf_ref_type_log, + .check_kflag_member = btf_df_check_kflag_member, + .log_details = btf_fwd_type_log, .seq_show = btf_df_seq_show, }; @@ -1356,11 +1653,22 @@ static s32 btf_array_check_meta(struct btf_verifier_env *env, return -EINVAL; } + /* array type should not have a name */ + if (t->name_off) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; } + if (btf_type_kflag(t)) { + btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); + return -EINVAL; + } + if (t->size) { btf_verifier_log_type(env, t, "size != 0"); return -EINVAL; @@ -1396,7 +1704,7 @@ static int btf_array_resolve(struct btf_verifier_env *env, /* Check array->index_type */ index_type_id = array->index_type; index_type = btf_type_by_id(btf, index_type_id); - if (btf_type_is_void_or_null(index_type)) { + if (btf_type_nosize_or_null(index_type)) { btf_verifier_log_type(env, v->t, "Invalid index"); return -EINVAL; } @@ -1415,7 +1723,7 @@ static int btf_array_resolve(struct btf_verifier_env *env, /* Check array->type */ elem_type_id = array->type; elem_type = btf_type_by_id(btf, elem_type_id); - if (btf_type_is_void_or_null(elem_type)) { + if (btf_type_nosize_or_null(elem_type)) { btf_verifier_log_type(env, v->t, "Invalid elem"); return -EINVAL; @@ -1484,6 +1792,7 @@ static struct btf_kind_operations array_ops = { .check_meta = btf_array_check_meta, .resolve = btf_array_resolve, .check_member = btf_array_check_member, + .check_kflag_member = btf_generic_check_kflag_member, .log_details = btf_array_log, .seq_show = btf_array_seq_show, }; @@ -1522,6 +1831,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, u32 meta_needed, last_offset; struct btf *btf = env->btf; u32 struct_size = t->size; + u32 offset; u16 i; meta_needed = btf_type_vlen(t) * sizeof(*member); @@ -1532,6 +1842,13 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, return -EINVAL; } + /* struct type either no name or a valid one */ + if (t->name_off && + !btf_name_valid_identifier(env->btf, t->name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + btf_verifier_log_type(env, t, NULL); last_offset = 0; @@ -1543,6 +1860,12 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, return -EINVAL; } + /* struct member either no name or a valid one */ + if (member->name_off && + !btf_name_valid_identifier(btf, member->name_off)) { + btf_verifier_log_member(env, t, member, "Invalid name"); + return -EINVAL; + } /* A member cannot be in type void */ if (!member->type || !BTF_TYPE_ID_VALID(member->type)) { btf_verifier_log_member(env, t, member, @@ -1550,7 +1873,8 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, return -EINVAL; } - if (is_union && member->offset) { + offset = btf_member_bit_offset(t, member); + if (is_union && offset) { btf_verifier_log_member(env, t, member, "Invalid member bits_offset"); return -EINVAL; @@ -1560,20 +1884,20 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, * ">" instead of ">=" because the last member could be * "char a[0];" */ - if (last_offset > member->offset) { + if (last_offset > offset) { btf_verifier_log_member(env, t, member, "Invalid member bits_offset"); return -EINVAL; } - if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) { + if (BITS_ROUNDUP_BYTES(offset) > struct_size) { btf_verifier_log_member(env, t, member, - "Memmber bits_offset exceeds its struct size"); + "Member bits_offset exceeds its struct size"); return -EINVAL; } btf_verifier_log_member(env, t, member, NULL); - last_offset = member->offset; + last_offset = offset; } return meta_needed; @@ -1603,9 +1927,14 @@ static int btf_struct_resolve(struct btf_verifier_env *env, last_member_type = btf_type_by_id(env->btf, last_member_type_id); - err = btf_type_ops(last_member_type)->check_member(env, v->t, - last_member, - last_member_type); + if (btf_type_kflag(v->t)) + err = btf_type_ops(last_member_type)->check_kflag_member(env, v->t, + last_member, + last_member_type); + else + err = btf_type_ops(last_member_type)->check_member(env, v->t, + last_member, + last_member_type); if (err) return err; } @@ -1615,7 +1944,7 @@ static int btf_struct_resolve(struct btf_verifier_env *env, const struct btf_type *member_type = btf_type_by_id(env->btf, member_type_id); - if (btf_type_is_void_or_null(member_type)) { + if (btf_type_nosize_or_null(member_type)) { btf_verifier_log_member(env, v->t, member, "Invalid member"); return -EINVAL; @@ -1627,9 +1956,14 @@ static int btf_struct_resolve(struct btf_verifier_env *env, return env_stack_push(env, member_type, member_type_id); } - err = btf_type_ops(member_type)->check_member(env, v->t, - member, - member_type); + if (btf_type_kflag(v->t)) + err = btf_type_ops(member_type)->check_kflag_member(env, v->t, + member, + member_type); + else + err = btf_type_ops(member_type)->check_member(env, v->t, + member, + member_type); if (err) return err; } @@ -1657,17 +1991,26 @@ static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t, for_each_member(i, t, member) { const struct btf_type *member_type = btf_type_by_id(btf, member->type); - u32 member_offset = member->offset; - u32 bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset); - u8 bits8_offset = BITS_PER_BYTE_MASKED(member_offset); const struct btf_kind_operations *ops; + u32 member_offset, bitfield_size; + u32 bytes_offset; + u8 bits8_offset; if (i) seq_puts(m, seq); - ops = btf_type_ops(member_type); - ops->seq_show(btf, member_type, member->type, - data + bytes_offset, bits8_offset, m); + member_offset = btf_member_bit_offset(t, member); + bitfield_size = btf_member_bitfield_size(t, member); + if (bitfield_size) { + btf_bitfield_seq_show(data, member_offset, + bitfield_size, m); + } else { + bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset); + bits8_offset = BITS_PER_BYTE_MASKED(member_offset); + ops = btf_type_ops(member_type); + ops->seq_show(btf, member_type, member->type, + data + bytes_offset, bits8_offset, m); + } } seq_puts(m, "}"); } @@ -1676,6 +2019,7 @@ static struct btf_kind_operations struct_ops = { .check_meta = btf_struct_check_meta, .resolve = btf_struct_resolve, .check_member = btf_struct_check_member, + .check_kflag_member = btf_generic_check_kflag_member, .log_details = btf_struct_log, .seq_show = btf_struct_seq_show, }; @@ -1705,6 +2049,41 @@ static int btf_enum_check_member(struct btf_verifier_env *env, return 0; } +static int btf_enum_check_kflag_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 struct_bits_off, nr_bits, bytes_end, struct_size; + u32 int_bitsize = sizeof(int) * BITS_PER_BYTE; + + struct_bits_off = BTF_MEMBER_BIT_OFFSET(member->offset); + nr_bits = BTF_MEMBER_BITFIELD_SIZE(member->offset); + if (!nr_bits) { + if (BITS_PER_BYTE_MASKED(struct_bits_off)) { + btf_verifier_log_member(env, struct_type, member, + "Member is not byte aligned"); + return -EINVAL; + } + + nr_bits = int_bitsize; + } else if (nr_bits > int_bitsize) { + btf_verifier_log_member(env, struct_type, member, + "Invalid member bitfield_size"); + return -EINVAL; + } + + struct_size = struct_type->size; + bytes_end = BITS_ROUNDUP_BYTES(struct_bits_off + nr_bits); + if (struct_size < bytes_end) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + static s32 btf_enum_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) @@ -1724,12 +2103,24 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env, return -EINVAL; } + if (btf_type_kflag(t)) { + btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); + return -EINVAL; + } + if (t->size != sizeof(int)) { btf_verifier_log_type(env, t, "Expected size:%zu", sizeof(int)); return -EINVAL; } + /* enum type either no name or a valid one */ + if (t->name_off && + !btf_name_valid_identifier(env->btf, t->name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + btf_verifier_log_type(env, t, NULL); for (i = 0; i < nr_enums; i++) { @@ -1739,8 +2130,16 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env, return -EINVAL; } + /* enum member must have a valid name */ + if (!enums[i].name_off || + !btf_name_valid_identifier(btf, enums[i].name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + + btf_verifier_log(env, "\t%s val=%d\n", - btf_name_by_offset(btf, enums[i].name_off), + __btf_name_by_offset(btf, enums[i].name_off), enums[i].val); } @@ -1764,7 +2163,8 @@ static void btf_enum_seq_show(const struct btf *btf, const struct btf_type *t, for (i = 0; i < nr_enums; i++) { if (v == enums[i].val) { seq_printf(m, "%s", - btf_name_by_offset(btf, enums[i].name_off)); + __btf_name_by_offset(btf, + enums[i].name_off)); return; } } @@ -1776,10 +2176,249 @@ static struct btf_kind_operations enum_ops = { .check_meta = btf_enum_check_meta, .resolve = btf_df_resolve, .check_member = btf_enum_check_member, + .check_kflag_member = btf_enum_check_kflag_member, .log_details = btf_enum_log, .seq_show = btf_enum_seq_show, }; +static s32 btf_func_proto_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + u32 meta_needed = btf_type_vlen(t) * sizeof(struct btf_param); + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + if (t->name_off) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + + if (btf_type_kflag(t)) { + btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return meta_needed; +} + +static void btf_func_proto_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + const struct btf_param *args = (const struct btf_param *)(t + 1); + u16 nr_args = btf_type_vlen(t), i; + + btf_verifier_log(env, "return=%u args=(", t->type); + if (!nr_args) { + btf_verifier_log(env, "void"); + goto done; + } + + if (nr_args == 1 && !args[0].type) { + /* Only one vararg */ + btf_verifier_log(env, "vararg"); + goto done; + } + + btf_verifier_log(env, "%u %s", args[0].type, + __btf_name_by_offset(env->btf, + args[0].name_off)); + for (i = 1; i < nr_args - 1; i++) + btf_verifier_log(env, ", %u %s", args[i].type, + __btf_name_by_offset(env->btf, + args[i].name_off)); + + if (nr_args > 1) { + const struct btf_param *last_arg = &args[nr_args - 1]; + + if (last_arg->type) + btf_verifier_log(env, ", %u %s", last_arg->type, + __btf_name_by_offset(env->btf, + last_arg->name_off)); + else + btf_verifier_log(env, ", vararg"); + } + +done: + btf_verifier_log(env, ")"); +} + +static struct btf_kind_operations func_proto_ops = { + .check_meta = btf_func_proto_check_meta, + .resolve = btf_df_resolve, + /* + * BTF_KIND_FUNC_PROTO cannot be directly referred by + * a struct's member. + * + * It should be a funciton pointer instead. + * (i.e. struct's member -> BTF_KIND_PTR -> BTF_KIND_FUNC_PROTO) + * + * Hence, there is no btf_func_check_member(). + */ + .check_member = btf_df_check_member, + .check_kflag_member = btf_df_check_kflag_member, + .log_details = btf_func_proto_log, + .seq_show = btf_df_seq_show, +}; + +static s32 btf_func_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + if (!t->name_off || + !btf_name_valid_identifier(env->btf, t->name_off)) { + btf_verifier_log_type(env, t, "Invalid name"); + return -EINVAL; + } + + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + if (btf_type_kflag(t)) { + btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return 0; +} + +static struct btf_kind_operations func_ops = { + .check_meta = btf_func_check_meta, + .resolve = btf_df_resolve, + .check_member = btf_df_check_member, + .check_kflag_member = btf_df_check_kflag_member, + .log_details = btf_ref_type_log, + .seq_show = btf_df_seq_show, +}; + +static int btf_func_proto_check(struct btf_verifier_env *env, + const struct btf_type *t) +{ + const struct btf_type *ret_type; + const struct btf_param *args; + const struct btf *btf; + u16 nr_args, i; + int err; + + btf = env->btf; + args = (const struct btf_param *)(t + 1); + nr_args = btf_type_vlen(t); + + /* Check func return type which could be "void" (t->type == 0) */ + if (t->type) { + u32 ret_type_id = t->type; + + ret_type = btf_type_by_id(btf, ret_type_id); + if (!ret_type) { + btf_verifier_log_type(env, t, "Invalid return type"); + return -EINVAL; + } + + if (btf_type_needs_resolve(ret_type) && + !env_type_is_resolved(env, ret_type_id)) { + err = btf_resolve(env, ret_type, ret_type_id); + if (err) + return err; + } + + /* Ensure the return type is a type that has a size */ + if (!btf_type_id_size(btf, &ret_type_id, NULL)) { + btf_verifier_log_type(env, t, "Invalid return type"); + return -EINVAL; + } + } + + if (!nr_args) + return 0; + + /* Last func arg type_id could be 0 if it is a vararg */ + if (!args[nr_args - 1].type) { + if (args[nr_args - 1].name_off) { + btf_verifier_log_type(env, t, "Invalid arg#%u", + nr_args); + return -EINVAL; + } + nr_args--; + } + + err = 0; + for (i = 0; i < nr_args; i++) { + const struct btf_type *arg_type; + u32 arg_type_id; + + arg_type_id = args[i].type; + arg_type = btf_type_by_id(btf, arg_type_id); + if (!arg_type) { + btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); + err = -EINVAL; + break; + } + + if (args[i].name_off && + (!btf_name_offset_valid(btf, args[i].name_off) || + !btf_name_valid_identifier(btf, args[i].name_off))) { + btf_verifier_log_type(env, t, + "Invalid arg#%u", i + 1); + err = -EINVAL; + break; + } + + if (btf_type_needs_resolve(arg_type) && + !env_type_is_resolved(env, arg_type_id)) { + err = btf_resolve(env, arg_type, arg_type_id); + if (err) + break; + } + + if (!btf_type_id_size(btf, &arg_type_id, NULL)) { + btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); + err = -EINVAL; + break; + } + } + + return err; +} + +static int btf_func_check(struct btf_verifier_env *env, + const struct btf_type *t) +{ + const struct btf_type *proto_type; + const struct btf_param *args; + const struct btf *btf; + u16 nr_args, i; + + btf = env->btf; + proto_type = btf_type_by_id(btf, t->type); + + if (!proto_type || !btf_type_is_func_proto(proto_type)) { + btf_verifier_log_type(env, t, "Invalid type_id"); + return -EINVAL; + } + + args = (const struct btf_param *)(proto_type + 1); + nr_args = btf_type_vlen(proto_type); + for (i = 0; i < nr_args; i++) { + if (!args[i].name_off && args[i].type) { + btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); + return -EINVAL; + } + } + + return 0; +} + static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_INT] = &int_ops, [BTF_KIND_PTR] = &ptr_ops, @@ -1792,6 +2431,8 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_VOLATILE] = &modifier_ops, [BTF_KIND_CONST] = &modifier_ops, [BTF_KIND_RESTRICT] = &modifier_ops, + [BTF_KIND_FUNC] = &func_ops, + [BTF_KIND_FUNC_PROTO] = &func_proto_ops, }; static s32 btf_check_meta(struct btf_verifier_env *env, @@ -1863,30 +2504,6 @@ static int btf_check_all_metas(struct btf_verifier_env *env) return 0; } -static int btf_resolve(struct btf_verifier_env *env, - const struct btf_type *t, u32 type_id) -{ - const struct resolve_vertex *v; - int err = 0; - - env->resolve_mode = RESOLVE_TBD; - env_stack_push(env, t, type_id); - while (!err && (v = env_stack_peak(env))) { - env->log_type_id = v->type_id; - err = btf_type_ops(v->t)->resolve(env, v); - } - - env->log_type_id = type_id; - if (err == -E2BIG) - btf_verifier_log_type(env, t, - "Exceeded max resolving depth:%u", - MAX_RESOLVE_DEPTH); - else if (err == -EEXIST) - btf_verifier_log_type(env, t, "Loop detected"); - - return err; -} - static bool btf_resolve_valid(struct btf_verifier_env *env, const struct btf_type *t, u32 type_id) @@ -1920,6 +2537,39 @@ static bool btf_resolve_valid(struct btf_verifier_env *env, return false; } +static int btf_resolve(struct btf_verifier_env *env, + const struct btf_type *t, u32 type_id) +{ + u32 save_log_type_id = env->log_type_id; + const struct resolve_vertex *v; + int err = 0; + + env->resolve_mode = RESOLVE_TBD; + env_stack_push(env, t, type_id); + while (!err && (v = env_stack_peak(env))) { + env->log_type_id = v->type_id; + err = btf_type_ops(v->t)->resolve(env, v); + } + + env->log_type_id = type_id; + if (err == -E2BIG) { + btf_verifier_log_type(env, t, + "Exceeded max resolving depth:%u", + MAX_RESOLVE_DEPTH); + } else if (err == -EEXIST) { + btf_verifier_log_type(env, t, "Loop detected"); + } + + /* Final sanity check */ + if (!err && !btf_resolve_valid(env, t, type_id)) { + btf_verifier_log_type(env, t, "Invalid resolve state"); + err = -EINVAL; + } + + env->log_type_id = save_log_type_id; + return err; +} + static int btf_check_all_types(struct btf_verifier_env *env) { struct btf *btf = env->btf; @@ -1942,10 +2592,16 @@ static int btf_check_all_types(struct btf_verifier_env *env) return err; } - if (btf_type_needs_resolve(t) && - !btf_resolve_valid(env, t, type_id)) { - btf_verifier_log_type(env, t, "Invalid resolve state"); - return -EINVAL; + if (btf_type_is_func_proto(t)) { + err = btf_func_proto_check(env, t); + if (err) + return err; + } + + if (btf_type_is_func(t)) { + err = btf_func_check(env, t); + if (err) + return err; } } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6377225b2082..38de580abcc2 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -21,12 +21,14 @@ * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ +#include <uapi/linux/btf.h> #include <linux/filter.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/random.h> #include <linux/moduleloader.h> #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/frame.h> #include <linux/rbtree_latch.h> #include <linux/kallsyms.h> @@ -103,6 +105,91 @@ struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) } EXPORT_SYMBOL_GPL(bpf_prog_alloc); +int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog) +{ + if (!prog->aux->nr_linfo || !prog->jit_requested) + return 0; + + prog->aux->jited_linfo = kcalloc(prog->aux->nr_linfo, + sizeof(*prog->aux->jited_linfo), + GFP_KERNEL | __GFP_NOWARN); + if (!prog->aux->jited_linfo) + return -ENOMEM; + + return 0; +} + +void bpf_prog_free_jited_linfo(struct bpf_prog *prog) +{ + kfree(prog->aux->jited_linfo); + prog->aux->jited_linfo = NULL; +} + +void bpf_prog_free_unused_jited_linfo(struct bpf_prog *prog) +{ + if (prog->aux->jited_linfo && !prog->aux->jited_linfo[0]) + bpf_prog_free_jited_linfo(prog); +} + +/* The jit engine is responsible to provide an array + * for insn_off to the jited_off mapping (insn_to_jit_off). + * + * The idx to this array is the insn_off. Hence, the insn_off + * here is relative to the prog itself instead of the main prog. + * This array has one entry for each xlated bpf insn. + * + * jited_off is the byte off to the last byte of the jited insn. + * + * Hence, with + * insn_start: + * The first bpf insn off of the prog. The insn off + * here is relative to the main prog. + * e.g. if prog is a subprog, insn_start > 0 + * linfo_idx: + * The prog's idx to prog->aux->linfo and jited_linfo + * + * jited_linfo[linfo_idx] = prog->bpf_func + * + * For i > linfo_idx, + * + * jited_linfo[i] = prog->bpf_func + + * insn_to_jit_off[linfo[i].insn_off - insn_start - 1] + */ +void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, + const u32 *insn_to_jit_off) +{ + u32 linfo_idx, insn_start, insn_end, nr_linfo, i; + const struct bpf_line_info *linfo; + void **jited_linfo; + + if (!prog->aux->jited_linfo) + /* Userspace did not provide linfo */ + return; + + linfo_idx = prog->aux->linfo_idx; + linfo = &prog->aux->linfo[linfo_idx]; + insn_start = linfo[0].insn_off; + insn_end = insn_start + prog->len; + + jited_linfo = &prog->aux->jited_linfo[linfo_idx]; + jited_linfo[0] = prog->bpf_func; + + nr_linfo = prog->aux->nr_linfo - linfo_idx; + + for (i = 1; i < nr_linfo && linfo[i].insn_off < insn_end; i++) + /* The verifier ensures that linfo[i].insn_off is + * strictly increasing + */ + jited_linfo[i] = prog->bpf_func + + insn_to_jit_off[linfo[i].insn_off - insn_start - 1]; +} + +void bpf_prog_free_linfo(struct bpf_prog *prog) +{ + bpf_prog_free_jited_linfo(prog); + kvfree(prog->aux->linfo); +} + struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags) { @@ -292,6 +379,26 @@ static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta, return ret; } +static void bpf_adj_linfo(struct bpf_prog *prog, u32 off, u32 delta) +{ + struct bpf_line_info *linfo; + u32 i, nr_linfo; + + nr_linfo = prog->aux->nr_linfo; + if (!nr_linfo || !delta) + return; + + linfo = prog->aux->linfo; + + for (i = 0; i < nr_linfo; i++) + if (off < linfo[i].insn_off) + break; + + /* Push all off < linfo[i].insn_off by delta */ + for (; i < nr_linfo; i++) + linfo[i].insn_off += delta; +} + struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len) { @@ -347,6 +454,8 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, */ BUG_ON(bpf_adj_branches(prog_adj, off, insn_delta, false)); + bpf_adj_linfo(prog_adj, off, insn_delta); + return prog_adj; } @@ -365,13 +474,11 @@ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp) } #ifdef CONFIG_BPF_JIT -# define BPF_JIT_LIMIT_DEFAULT (PAGE_SIZE * 40000) - /* All BPF JIT sysctl knobs here. */ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON); int bpf_jit_harden __read_mostly; int bpf_jit_kallsyms __read_mostly; -int bpf_jit_limit __read_mostly = BPF_JIT_LIMIT_DEFAULT; +long bpf_jit_limit __read_mostly; static __always_inline void bpf_get_prog_addr_region(const struct bpf_prog *prog, @@ -390,6 +497,8 @@ bpf_get_prog_addr_region(const struct bpf_prog *prog, static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) { const char *end = sym + KSYM_NAME_LEN; + const struct btf_type *type; + const char *func_name; BUILD_BUG_ON(sizeof("bpf_prog_") + sizeof(prog->tag) * 2 + @@ -404,6 +513,16 @@ static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_"); sym = bin2hex(sym, prog->tag, sizeof(prog->tag)); + + /* prog->aux->name will be ignored if full btf name is available */ + if (prog->aux->func_info_cnt) { + type = btf_type_by_id(prog->aux->btf, + prog->aux->func_info[prog->aux->func_idx].type_id); + func_name = btf_name_by_offset(prog->aux->btf, type->name_off); + snprintf(sym, (size_t)(end - sym), "_%s", func_name); + return; + } + if (prog->aux->name[0]) snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name); else @@ -553,7 +672,6 @@ bool is_bpf_text_address(unsigned long addr) int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { - unsigned long symbol_start, symbol_end; struct bpf_prog_aux *aux; unsigned int it = 0; int ret = -ERANGE; @@ -566,10 +684,9 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, if (it++ != symnum) continue; - bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end); bpf_get_prog_name(aux->prog, sym); - *value = symbol_start; + *value = (unsigned long)aux->prog->bpf_func; *type = BPF_SYM_ELF_TYPE; ret = 0; @@ -582,16 +699,27 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, static atomic_long_t bpf_jit_current; +/* Can be overridden by an arch's JIT compiler if it has a custom, + * dedicated BPF backend memory area, or if neither of the two + * below apply. + */ +u64 __weak bpf_jit_alloc_exec_limit(void) +{ #if defined(MODULES_VADDR) + return MODULES_END - MODULES_VADDR; +#else + return VMALLOC_END - VMALLOC_START; +#endif +} + static int __init bpf_jit_charge_init(void) { /* Only used as heuristic here to derive limit. */ - bpf_jit_limit = min_t(u64, round_up((MODULES_END - MODULES_VADDR) >> 2, - PAGE_SIZE), INT_MAX); + bpf_jit_limit = min_t(u64, round_up(bpf_jit_alloc_exec_limit() >> 2, + PAGE_SIZE), LONG_MAX); return 0; } pure_initcall(bpf_jit_charge_init); -#endif static int bpf_jit_charge_modmem(u32 pages) { @@ -611,6 +739,16 @@ static void bpf_jit_uncharge_modmem(u32 pages) atomic_long_sub(pages, &bpf_jit_current); } +void *__weak bpf_jit_alloc_exec(unsigned long size) +{ + return module_alloc(size); +} + +void __weak bpf_jit_free_exec(void *addr) +{ + module_memfree(addr); +} + struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, @@ -628,7 +766,7 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, if (bpf_jit_charge_modmem(pages)) return NULL; - hdr = module_alloc(size); + hdr = bpf_jit_alloc_exec(size); if (!hdr) { bpf_jit_uncharge_modmem(pages); return NULL; @@ -652,7 +790,7 @@ void bpf_jit_binary_free(struct bpf_binary_header *hdr) { u32 pages = hdr->pages; - module_memfree(hdr); + bpf_jit_free_exec(hdr); bpf_jit_uncharge_modmem(pages); } @@ -674,6 +812,40 @@ void __weak bpf_jit_free(struct bpf_prog *fp) bpf_prog_unlock_free(fp); } +int bpf_jit_get_func_addr(const struct bpf_prog *prog, + const struct bpf_insn *insn, bool extra_pass, + u64 *func_addr, bool *func_addr_fixed) +{ + s16 off = insn->off; + s32 imm = insn->imm; + u8 *addr; + + *func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL; + if (!*func_addr_fixed) { + /* Place-holder address till the last pass has collected + * all addresses for JITed subprograms in which case we + * can pick them up from prog->aux. + */ + if (!extra_pass) + addr = NULL; + else if (prog->aux->func && + off >= 0 && off < prog->aux->func_cnt) + addr = (u8 *)prog->aux->func[off]->bpf_func; + else + return -EINVAL; + } else { + /* Address of a BPF helper call. Since part of the core + * kernel, it's always at a fixed location. __bpf_call_base + * and the helper with imm relative to it are both in core + * kernel. + */ + addr = (u8 *)__bpf_call_base + imm; + } + + *func_addr = (unsigned long)addr; + return 0; +} + static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, struct bpf_insn *to_buff) @@ -877,32 +1049,34 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); #define BPF_INSN_MAP(INSN_2, INSN_3) \ /* 32 bit ALU operations. */ \ /* Register based. */ \ - INSN_3(ALU, ADD, X), \ - INSN_3(ALU, SUB, X), \ - INSN_3(ALU, AND, X), \ - INSN_3(ALU, OR, X), \ - INSN_3(ALU, LSH, X), \ - INSN_3(ALU, RSH, X), \ - INSN_3(ALU, XOR, X), \ - INSN_3(ALU, MUL, X), \ - INSN_3(ALU, MOV, X), \ - INSN_3(ALU, DIV, X), \ - INSN_3(ALU, MOD, X), \ + INSN_3(ALU, ADD, X), \ + INSN_3(ALU, SUB, X), \ + INSN_3(ALU, AND, X), \ + INSN_3(ALU, OR, X), \ + INSN_3(ALU, LSH, X), \ + INSN_3(ALU, RSH, X), \ + INSN_3(ALU, XOR, X), \ + INSN_3(ALU, MUL, X), \ + INSN_3(ALU, MOV, X), \ + INSN_3(ALU, ARSH, X), \ + INSN_3(ALU, DIV, X), \ + INSN_3(ALU, MOD, X), \ INSN_2(ALU, NEG), \ INSN_3(ALU, END, TO_BE), \ INSN_3(ALU, END, TO_LE), \ /* Immediate based. */ \ - INSN_3(ALU, ADD, K), \ - INSN_3(ALU, SUB, K), \ - INSN_3(ALU, AND, K), \ - INSN_3(ALU, OR, K), \ - INSN_3(ALU, LSH, K), \ - INSN_3(ALU, RSH, K), \ - INSN_3(ALU, XOR, K), \ - INSN_3(ALU, MUL, K), \ - INSN_3(ALU, MOV, K), \ - INSN_3(ALU, DIV, K), \ - INSN_3(ALU, MOD, K), \ + INSN_3(ALU, ADD, K), \ + INSN_3(ALU, SUB, K), \ + INSN_3(ALU, AND, K), \ + INSN_3(ALU, OR, K), \ + INSN_3(ALU, LSH, K), \ + INSN_3(ALU, RSH, K), \ + INSN_3(ALU, XOR, K), \ + INSN_3(ALU, MUL, K), \ + INSN_3(ALU, MOV, K), \ + INSN_3(ALU, ARSH, K), \ + INSN_3(ALU, DIV, K), \ + INSN_3(ALU, MOD, K), \ /* 64 bit ALU operations. */ \ /* Register based. */ \ INSN_3(ALU64, ADD, X), \ @@ -1081,6 +1255,12 @@ select_insn: DST = (u64) (u32) insn[0].imm | ((u64) (u32) insn[1].imm) << 32; insn++; CONT; + ALU_ARSH_X: + DST = (u64) (u32) ((*(s32 *) &DST) >> SRC); + CONT; + ALU_ARSH_K: + DST = (u64) (u32) ((*(s32 *) &DST) >> IMM); + CONT; ALU64_ARSH_X: (*(s64 *) &DST) >>= SRC; CONT; @@ -1527,13 +1707,20 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) * be JITed, but falls back to the interpreter. */ if (!bpf_prog_is_dev_bound(fp->aux)) { + *err = bpf_prog_alloc_jited_linfo(fp); + if (*err) + return fp; + fp = bpf_int_jit_compile(fp); -#ifdef CONFIG_BPF_JIT_ALWAYS_ON if (!fp->jited) { + bpf_prog_free_jited_linfo(fp); +#ifdef CONFIG_BPF_JIT_ALWAYS_ON *err = -ENOTSUPP; return fp; - } #endif + } else { + bpf_prog_free_unused_jited_linfo(fp); + } } else { *err = bpf_prog_offload_compile(fp); if (*err) diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 24aac0d0f412..8974b3755670 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -183,7 +183,7 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, * is not at a fixed memory location, with mixed length * packets, which is bad for cache-line hotness. */ - frame_size = SKB_DATA_ALIGN(xdpf->len) + xdpf->headroom + + frame_size = SKB_DATA_ALIGN(xdpf->len + xdpf->headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); pkt_data_start = xdpf->data - xdpf->headroom; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 2c1790288138..4b7c76765d9d 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -23,7 +23,7 @@ #define HTAB_CREATE_FLAG_MASK \ (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \ - BPF_F_RDONLY | BPF_F_WRONLY) + BPF_F_RDONLY | BPF_F_WRONLY | BPF_F_ZERO_SEED) struct bucket { struct hlist_nulls_head head; @@ -244,6 +244,7 @@ static int htab_map_alloc_check(union bpf_attr *attr) */ bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU); bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); + bool zero_seed = (attr->map_flags & BPF_F_ZERO_SEED); int numa_node = bpf_map_attr_numa_node(attr); BUILD_BUG_ON(offsetof(struct htab_elem, htab) != @@ -257,6 +258,10 @@ static int htab_map_alloc_check(union bpf_attr *attr) */ return -EPERM; + if (zero_seed && !capable(CAP_SYS_ADMIN)) + /* Guard against local DoS, and discourage production use. */ + return -EPERM; + if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK) /* reserved bits should not be used */ return -EINVAL; @@ -373,7 +378,11 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (!htab->buckets) goto free_htab; - htab->hashrnd = get_random_int(); + if (htab->map.map_flags & BPF_F_ZERO_SEED) + htab->hashrnd = 0; + else + htab->hashrnd = get_random_int(); + for (i = 0; i < htab->n_buckets; i++) { INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); raw_spin_lock_init(&htab->buckets[i].lock); diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index c97a8f968638..07a34ef562a0 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -1,14 +1,15 @@ //SPDX-License-Identifier: GPL-2.0 #include <linux/bpf-cgroup.h> #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/bug.h> #include <linux/filter.h> #include <linux/mm.h> #include <linux/rbtree.h> #include <linux/slab.h> +#include <uapi/linux/btf.h> -DEFINE_PER_CPU(struct bpf_cgroup_storage*, - 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 @@ -139,7 +140,8 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, return -ENOENT; new = kmalloc_node(sizeof(struct bpf_storage_buffer) + - map->value_size, __GFP_ZERO | GFP_USER, + map->value_size, + __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN, map->numa_node); if (!new) return -ENOMEM; @@ -308,6 +310,85 @@ static int cgroup_storage_delete_elem(struct bpf_map *map, void *key) return -EINVAL; } +static int cgroup_storage_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type) +{ + struct btf_member *m; + u32 offset, size; + + /* Key is expected to be of struct bpf_cgroup_storage_key type, + * which is: + * struct bpf_cgroup_storage_key { + * __u64 cgroup_inode_id; + * __u32 attach_type; + * }; + */ + + /* + * Key_type must be a structure with two fields. + */ + if (BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT || + BTF_INFO_VLEN(key_type->info) != 2) + return -EINVAL; + + /* + * The first field must be a 64 bit integer at 0 offset. + */ + m = (struct btf_member *)(key_type + 1); + size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, cgroup_inode_id); + if (!btf_member_is_reg_int(btf, key_type, m, 0, size)) + return -EINVAL; + + /* + * The second field must be a 32 bit integer at 64 bit offset. + */ + m++; + offset = offsetof(struct bpf_cgroup_storage_key, attach_type); + size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, attach_type); + if (!btf_member_is_reg_int(btf, key_type, m, offset, size)) + return -EINVAL; + + return 0; +} + +static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *_key, + struct seq_file *m) +{ + enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); + struct bpf_cgroup_storage_key *key = _key; + struct bpf_cgroup_storage *storage; + int cpu; + + rcu_read_lock(); + storage = cgroup_storage_lookup(map_to_storage(map), key, false); + if (!storage) { + rcu_read_unlock(); + return; + } + + btf_type_seq_show(map->btf, map->btf_key_type_id, key, m); + stype = cgroup_storage_type(map); + if (stype == BPF_CGROUP_STORAGE_SHARED) { + seq_puts(m, ": "); + btf_type_seq_show(map->btf, map->btf_value_type_id, + &READ_ONCE(storage->buf)->data[0], m); + seq_puts(m, "\n"); + } else { + seq_puts(m, ": {\n"); + for_each_possible_cpu(cpu) { + seq_printf(m, "\tcpu%d: ", cpu); + btf_type_seq_show(map->btf, map->btf_value_type_id, + per_cpu_ptr(storage->percpu_buf, cpu), + m); + seq_puts(m, "\n"); + } + seq_puts(m, "}\n"); + } + rcu_read_unlock(); +} + const struct bpf_map_ops cgroup_storage_map_ops = { .map_alloc = cgroup_storage_map_alloc, .map_free = cgroup_storage_map_free, @@ -315,7 +396,8 @@ const struct bpf_map_ops cgroup_storage_map_ops = { .map_lookup_elem = cgroup_storage_lookup_elem, .map_update_elem = cgroup_storage_update_elem, .map_delete_elem = cgroup_storage_delete_elem, - .map_check_btf = map_check_no_btf, + .map_check_btf = cgroup_storage_check_btf, + .map_seq_show_elem = cgroup_storage_seq_show_elem, }; int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 9058317ba9de..abf1002080df 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -168,20 +168,59 @@ static size_t longest_prefix_match(const struct lpm_trie *trie, const struct lpm_trie_node *node, const struct bpf_lpm_trie_key *key) { - size_t prefixlen = 0; - size_t i; + u32 limit = min(node->prefixlen, key->prefixlen); + u32 prefixlen = 0, i = 0; - for (i = 0; i < trie->data_size; i++) { - size_t b; + BUILD_BUG_ON(offsetof(struct lpm_trie_node, data) % sizeof(u32)); + BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key, data) % sizeof(u32)); - b = 8 - fls(node->data[i] ^ key->data[i]); - prefixlen += b; +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(CONFIG_64BIT) - if (prefixlen >= node->prefixlen || prefixlen >= key->prefixlen) - return min(node->prefixlen, key->prefixlen); + /* data_size >= 16 has very small probability. + * We do not use a loop for optimal code generation. + */ + if (trie->data_size >= 8) { + u64 diff = be64_to_cpu(*(__be64 *)node->data ^ + *(__be64 *)key->data); + + prefixlen = 64 - fls64(diff); + if (prefixlen >= limit) + return limit; + if (diff) + return prefixlen; + i = 8; + } +#endif + + while (trie->data_size >= i + 4) { + u32 diff = be32_to_cpu(*(__be32 *)&node->data[i] ^ + *(__be32 *)&key->data[i]); + + prefixlen += 32 - fls(diff); + if (prefixlen >= limit) + return limit; + if (diff) + return prefixlen; + i += 4; + } - if (b < 8) - break; + if (trie->data_size >= i + 2) { + u16 diff = be16_to_cpu(*(__be16 *)&node->data[i] ^ + *(__be16 *)&key->data[i]); + + prefixlen += 16 - fls(diff); + if (prefixlen >= limit) + return limit; + if (diff) + return prefixlen; + i += 2; + } + + if (trie->data_size >= i + 1) { + prefixlen += 8 - fls(node->data[i] ^ key->data[i]); + + if (prefixlen >= limit) + return limit; } return prefixlen; @@ -689,6 +728,7 @@ free_stack: } static int trie_check_btf(const struct bpf_map *map, + const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 8e93c47f0779..54cf2b9c44a4 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -33,6 +33,7 @@ static DECLARE_RWSEM(bpf_devs_lock); struct bpf_offload_dev { + const struct bpf_prog_offload_ops *ops; struct list_head netdevs; }; @@ -106,6 +107,7 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) err = -EINVAL; goto err_unlock; } + offload->offdev = ondev->offdev; prog->aux->offload = offload; list_add_tail(&offload->offloads, &ondev->progs); dev_put(offload->netdev); @@ -121,40 +123,20 @@ err_maybe_put: return err; } -static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd, - struct netdev_bpf *data) +int bpf_prog_offload_verifier_prep(struct bpf_prog *prog) { - struct bpf_prog_offload *offload = prog->aux->offload; - struct net_device *netdev; - - ASSERT_RTNL(); - - if (!offload) - return -ENODEV; - netdev = offload->netdev; - - data->command = cmd; - - return netdev->netdev_ops->ndo_bpf(netdev, data); -} - -int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env) -{ - struct netdev_bpf data = {}; - int err; - - data.verifier.prog = env->prog; + struct bpf_prog_offload *offload; + int ret = -ENODEV; - rtnl_lock(); - err = __bpf_offload_ndo(env->prog, BPF_OFFLOAD_VERIFIER_PREP, &data); - if (err) - goto exit_unlock; + down_read(&bpf_devs_lock); + offload = prog->aux->offload; + if (offload) { + ret = offload->offdev->ops->prepare(prog); + offload->dev_state = !ret; + } + up_read(&bpf_devs_lock); - env->prog->aux->offload->dev_ops = data.verifier.ops; - env->prog->aux->offload->dev_state = true; -exit_unlock: - rtnl_unlock(); - return err; + return ret; } int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, @@ -166,7 +148,8 @@ int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, down_read(&bpf_devs_lock); offload = env->prog->aux->offload; if (offload) - ret = offload->dev_ops->insn_hook(env, insn_idx, prev_insn_idx); + ret = offload->offdev->ops->insn_hook(env, insn_idx, + prev_insn_idx); up_read(&bpf_devs_lock); return ret; @@ -180,8 +163,8 @@ int bpf_prog_offload_finalize(struct bpf_verifier_env *env) down_read(&bpf_devs_lock); offload = env->prog->aux->offload; if (offload) { - if (offload->dev_ops->finalize) - ret = offload->dev_ops->finalize(env); + if (offload->offdev->ops->finalize) + ret = offload->offdev->ops->finalize(env); else ret = 0; } @@ -193,12 +176,9 @@ int bpf_prog_offload_finalize(struct bpf_verifier_env *env) static void __bpf_prog_offload_destroy(struct bpf_prog *prog) { struct bpf_prog_offload *offload = prog->aux->offload; - struct netdev_bpf data = {}; - - data.offload.prog = prog; if (offload->dev_state) - WARN_ON(__bpf_offload_ndo(prog, BPF_OFFLOAD_DESTROY, &data)); + offload->offdev->ops->destroy(prog); /* Make sure BPF_PROG_GET_NEXT_ID can't find this dead program */ bpf_prog_free_id(prog, true); @@ -210,24 +190,22 @@ static void __bpf_prog_offload_destroy(struct bpf_prog *prog) void bpf_prog_offload_destroy(struct bpf_prog *prog) { - rtnl_lock(); down_write(&bpf_devs_lock); if (prog->aux->offload) __bpf_prog_offload_destroy(prog); up_write(&bpf_devs_lock); - rtnl_unlock(); } static int bpf_prog_offload_translate(struct bpf_prog *prog) { - struct netdev_bpf data = {}; - int ret; - - data.offload.prog = prog; + struct bpf_prog_offload *offload; + int ret = -ENODEV; - rtnl_lock(); - ret = __bpf_offload_ndo(prog, BPF_OFFLOAD_TRANSLATE, &data); - rtnl_unlock(); + down_read(&bpf_devs_lock); + offload = prog->aux->offload; + if (offload) + ret = offload->offdev->ops->translate(prog); + up_read(&bpf_devs_lock); return ret; } @@ -655,7 +633,8 @@ unlock: } EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister); -struct bpf_offload_dev *bpf_offload_dev_create(void) +struct bpf_offload_dev * +bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops) { struct bpf_offload_dev *offdev; int err; @@ -673,6 +652,7 @@ struct bpf_offload_dev *bpf_offload_dev_create(void) if (!offdev) return ERR_PTR(-ENOMEM); + offdev->ops = ops; INIT_LIST_HEAD(&offdev->netdevs); return offdev; diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 8bbd72d3a121..b384ea9f3254 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -7,6 +7,7 @@ #include <linux/bpf.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/capability.h> #include "percpu_freelist.h" #define QUEUE_STACK_CREATE_FLAG_MASK \ @@ -45,8 +46,12 @@ static bool queue_stack_map_is_full(struct bpf_queue_stack *qs) /* Called from syscall */ static int queue_stack_map_alloc_check(union bpf_attr *attr) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 0 || + attr->value_size == 0 || attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK) return -EINVAL; @@ -63,15 +68,10 @@ 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; + u64 size, queue_size, cost; - cost = queue_size; + size = (u64) attr->max_entries + 1; + cost = queue_size = sizeof(*qs) + size * attr->value_size; if (cost >= U32_MAX - PAGE_SIZE) return ERR_PTR(-E2BIG); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ccb93277aae2..0607db304def 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -456,6 +456,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src) } int map_check_no_btf(const struct bpf_map *map, + const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { @@ -478,7 +479,7 @@ static int map_check_btf(const struct bpf_map *map, const struct btf *btf, return -EINVAL; if (map->ops->map_check_btf) - ret = map->ops->map_check_btf(map, key_type, value_type); + ret = map->ops->map_check_btf(map, btf, key_type, value_type); return ret; } @@ -1213,6 +1214,9 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); bpf_prog_kallsyms_del_all(prog); + btf_put(prog->aux->btf); + kvfree(prog->aux->func_info); + bpf_prog_free_linfo(prog); call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); } @@ -1437,9 +1441,9 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type, } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD expected_attach_type +#define BPF_PROG_LOAD_LAST_FIELD line_info_cnt -static int bpf_prog_load(union bpf_attr *attr) +static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog; @@ -1450,9 +1454,14 @@ static int bpf_prog_load(union bpf_attr *attr) if (CHECK_ATTR(BPF_PROG_LOAD)) return -EINVAL; - if (attr->prog_flags & ~BPF_F_STRICT_ALIGNMENT) + if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT)) return -EINVAL; + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && + (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && + !capable(CAP_SYS_ADMIN)) + return -EPERM; + /* copy eBPF program license from user space */ if (strncpy_from_user(license, u64_to_user_ptr(attr->license), sizeof(license) - 1) < 0) @@ -1464,11 +1473,6 @@ static int bpf_prog_load(union bpf_attr *attr) if (attr->insn_cnt == 0 || attr->insn_cnt > BPF_MAXINSNS) return -E2BIG; - - if (type == BPF_PROG_TYPE_KPROBE && - attr->kern_version != LINUX_VERSION_CODE) - return -EINVAL; - if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && !capable(CAP_SYS_ADMIN)) @@ -1525,7 +1529,7 @@ static int bpf_prog_load(union bpf_attr *attr) goto free_prog; /* run eBPF verifier */ - err = bpf_check(&prog, attr); + err = bpf_check(&prog, attr, uattr); if (err < 0) goto free_used_maps; @@ -1553,6 +1557,9 @@ static int bpf_prog_load(union bpf_attr *attr) return err; free_used_maps: + bpf_prog_free_linfo(prog); + kvfree(prog->aux->func_info); + btf_put(prog->aux->btf); bpf_prog_kallsyms_del_subprogs(prog); free_used_maps(prog->aux); free_prog: @@ -1597,6 +1604,7 @@ static int bpf_raw_tracepoint_release(struct inode *inode, struct file *filp) bpf_probe_unregister(raw_tp->btp, raw_tp->prog); bpf_prog_put(raw_tp->prog); } + bpf_put_raw_tracepoint(raw_tp->btp); kfree(raw_tp); return 0; } @@ -1622,13 +1630,15 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) return -EFAULT; tp_name[sizeof(tp_name) - 1] = 0; - btp = bpf_find_raw_tracepoint(tp_name); + btp = bpf_get_raw_tracepoint(tp_name); if (!btp) return -ENOENT; raw_tp = kzalloc(sizeof(*raw_tp), GFP_USER); - if (!raw_tp) - return -ENOMEM; + if (!raw_tp) { + err = -ENOMEM; + goto out_put_btp; + } raw_tp->btp = btp; prog = bpf_prog_get_type(attr->raw_tracepoint.prog_fd, @@ -1656,6 +1666,8 @@ out_put_prog: bpf_prog_put(prog); out_free_tp: kfree(raw_tp); +out_put_btp: + bpf_put_raw_tracepoint(btp); return err; } @@ -2020,18 +2032,42 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog) insns[i + 1].imm = 0; continue; } - - if (!bpf_dump_raw_ok() && - imm == (unsigned long)prog->aux) { - insns[i].imm = 0; - insns[i + 1].imm = 0; - continue; - } } return insns; } +static int set_info_rec_size(struct bpf_prog_info *info) +{ + /* + * Ensure info.*_rec_size is the same as kernel expected size + * + * or + * + * Only allow zero *_rec_size if both _rec_size and _cnt are + * zero. In this case, the kernel will set the expected + * _rec_size back to the info. + */ + + if ((info->nr_func_info || info->func_info_rec_size) && + info->func_info_rec_size != sizeof(struct bpf_func_info)) + return -EINVAL; + + if ((info->nr_line_info || info->line_info_rec_size) && + info->line_info_rec_size != sizeof(struct bpf_line_info)) + return -EINVAL; + + if ((info->nr_jited_line_info || info->jited_line_info_rec_size) && + info->jited_line_info_rec_size != sizeof(__u64)) + return -EINVAL; + + info->func_info_rec_size = sizeof(struct bpf_func_info); + info->line_info_rec_size = sizeof(struct bpf_line_info); + info->jited_line_info_rec_size = sizeof(__u64); + + return 0; +} + static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, const union bpf_attr *attr, union bpf_attr __user *uattr) @@ -2074,10 +2110,18 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, return -EFAULT; } + err = set_info_rec_size(&info); + if (err) + return err; + if (!capable(CAP_SYS_ADMIN)) { info.jited_prog_len = 0; info.xlated_prog_len = 0; info.nr_jited_ksyms = 0; + info.nr_jited_func_lens = 0; + info.nr_func_info = 0; + info.nr_line_info = 0; + info.nr_jited_line_info = 0; goto done; } @@ -2158,11 +2202,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } ulen = info.nr_jited_ksyms; - info.nr_jited_ksyms = prog->aux->func_cnt; - if (info.nr_jited_ksyms && ulen) { + info.nr_jited_ksyms = prog->aux->func_cnt ? : 1; + if (ulen) { if (bpf_dump_raw_ok()) { + unsigned long ksym_addr; u64 __user *user_ksyms; - ulong ksym_addr; u32 i; /* copy the address of the kernel symbol @@ -2170,10 +2214,17 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, */ ulen = min_t(u32, info.nr_jited_ksyms, ulen); user_ksyms = u64_to_user_ptr(info.jited_ksyms); - for (i = 0; i < ulen; i++) { - ksym_addr = (ulong) prog->aux->func[i]->bpf_func; - ksym_addr &= PAGE_MASK; - if (put_user((u64) ksym_addr, &user_ksyms[i])) + if (prog->aux->func_cnt) { + for (i = 0; i < ulen; i++) { + ksym_addr = (unsigned long) + prog->aux->func[i]->bpf_func; + if (put_user((u64) ksym_addr, + &user_ksyms[i])) + return -EFAULT; + } + } else { + ksym_addr = (unsigned long) prog->bpf_func; + if (put_user((u64) ksym_addr, &user_ksyms[0])) return -EFAULT; } } else { @@ -2182,8 +2233,8 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } ulen = info.nr_jited_func_lens; - info.nr_jited_func_lens = prog->aux->func_cnt; - if (info.nr_jited_func_lens && ulen) { + info.nr_jited_func_lens = prog->aux->func_cnt ? : 1; + if (ulen) { if (bpf_dump_raw_ok()) { u32 __user *user_lens; u32 func_len, i; @@ -2191,9 +2242,16 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, /* copy the JITed image lengths for each function */ ulen = min_t(u32, info.nr_jited_func_lens, ulen); user_lens = u64_to_user_ptr(info.jited_func_lens); - for (i = 0; i < ulen; i++) { - func_len = prog->aux->func[i]->jited_len; - if (put_user(func_len, &user_lens[i])) + if (prog->aux->func_cnt) { + for (i = 0; i < ulen; i++) { + func_len = + prog->aux->func[i]->jited_len; + if (put_user(func_len, &user_lens[i])) + return -EFAULT; + } + } else { + func_len = prog->jited_len; + if (put_user(func_len, &user_lens[0])) return -EFAULT; } } else { @@ -2201,6 +2259,77 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } } + if (prog->aux->btf) + info.btf_id = btf_id(prog->aux->btf); + + ulen = info.nr_func_info; + info.nr_func_info = prog->aux->func_info_cnt; + if (info.nr_func_info && ulen) { + char __user *user_finfo; + + user_finfo = u64_to_user_ptr(info.func_info); + ulen = min_t(u32, info.nr_func_info, ulen); + if (copy_to_user(user_finfo, prog->aux->func_info, + info.func_info_rec_size * ulen)) + return -EFAULT; + } + + ulen = info.nr_line_info; + info.nr_line_info = prog->aux->nr_linfo; + if (info.nr_line_info && ulen) { + __u8 __user *user_linfo; + + user_linfo = u64_to_user_ptr(info.line_info); + ulen = min_t(u32, info.nr_line_info, ulen); + if (copy_to_user(user_linfo, prog->aux->linfo, + info.line_info_rec_size * ulen)) + return -EFAULT; + } + + ulen = info.nr_jited_line_info; + if (prog->aux->jited_linfo) + info.nr_jited_line_info = prog->aux->nr_linfo; + else + info.nr_jited_line_info = 0; + if (info.nr_jited_line_info && ulen) { + if (bpf_dump_raw_ok()) { + __u64 __user *user_linfo; + u32 i; + + user_linfo = u64_to_user_ptr(info.jited_line_info); + ulen = min_t(u32, info.nr_jited_line_info, ulen); + for (i = 0; i < ulen; i++) { + if (put_user((__u64)(long)prog->aux->jited_linfo[i], + &user_linfo[i])) + return -EFAULT; + } + } else { + info.jited_line_info = 0; + } + } + + ulen = info.nr_prog_tags; + info.nr_prog_tags = prog->aux->func_cnt ? : 1; + if (ulen) { + __u8 __user (*user_prog_tags)[BPF_TAG_SIZE]; + u32 i; + + user_prog_tags = u64_to_user_ptr(info.prog_tags); + ulen = min_t(u32, info.nr_prog_tags, ulen); + if (prog->aux->func_cnt) { + for (i = 0; i < ulen; i++) { + if (copy_to_user(user_prog_tags[i], + prog->aux->func[i]->tag, + BPF_TAG_SIZE)) + return -EFAULT; + } + } else { + if (copy_to_user(user_prog_tags[0], + prog->tag, BPF_TAG_SIZE)) + return -EFAULT; + } + } + done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) @@ -2486,7 +2615,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = map_get_next_key(&attr); break; case BPF_PROG_LOAD: - err = bpf_prog_load(&attr); + err = bpf_prog_load(&attr, uattr); break; case BPF_OBJ_PIN: err = bpf_obj_pin(&attr); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1971ca325fb4..71d86e3024ae 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -11,10 +11,12 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. */ +#include <uapi/linux/btf.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/bpf_verifier.h> #include <linux/filter.h> #include <net/netlink.h> @@ -24,6 +26,7 @@ #include <linux/bsearch.h> #include <linux/sort.h> #include <linux/perf_event.h> +#include <linux/ctype.h> #include "disasm.h" @@ -175,6 +178,7 @@ struct bpf_verifier_stack_elem { #define BPF_COMPLEXITY_LIMIT_INSNS 131072 #define BPF_COMPLEXITY_LIMIT_STACK 1024 +#define BPF_COMPLEXITY_LIMIT_STATES 64 #define BPF_MAP_PTR_UNPRIV 1UL #define BPF_MAP_PTR_POISON ((void *)((0xeB9FUL << 1) + \ @@ -213,6 +217,27 @@ struct bpf_call_arg_meta { static DEFINE_MUTEX(bpf_verifier_lock); +static const struct bpf_line_info * +find_linfo(const struct bpf_verifier_env *env, u32 insn_off) +{ + const struct bpf_line_info *linfo; + const struct bpf_prog *prog; + u32 i, nr_linfo; + + prog = env->prog; + nr_linfo = prog->aux->nr_linfo; + + if (!nr_linfo || insn_off >= prog->len) + return NULL; + + linfo = prog->aux->linfo; + for (i = 1; i < nr_linfo; i++) + if (insn_off < linfo[i].insn_off) + break; + + return &linfo[i - 1]; +} + void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, va_list args) { @@ -263,6 +288,42 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) va_end(args); } +static const char *ltrim(const char *s) +{ + while (isspace(*s)) + s++; + + return s; +} + +__printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env, + u32 insn_off, + const char *prefix_fmt, ...) +{ + const struct bpf_line_info *linfo; + + if (!bpf_verifier_log_needed(&env->log)) + return; + + linfo = find_linfo(env, insn_off); + if (!linfo || linfo == env->prev_linfo) + return; + + if (prefix_fmt) { + va_list args; + + va_start(args, prefix_fmt); + bpf_verifier_vlog(&env->log, prefix_fmt, args); + va_end(args); + } + + verbose(env, "%s\n", + ltrim(btf_name_by_offset(env->prog->aux->btf, + linfo->line_off))); + + env->prev_linfo = linfo; +} + static bool type_is_pkt_pointer(enum bpf_reg_type type) { return type == PTR_TO_PACKET || @@ -336,12 +397,14 @@ static char slot_type_char[] = { static void print_liveness(struct bpf_verifier_env *env, enum bpf_reg_liveness live) { - if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN)) + if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE)) verbose(env, "_"); if (live & REG_LIVE_READ) verbose(env, "r"); if (live & REG_LIVE_WRITTEN) verbose(env, "w"); + if (live & REG_LIVE_DONE) + verbose(env, "D"); } static struct bpf_func_state *func(struct bpf_verifier_env *env, @@ -1071,6 +1134,12 @@ static int mark_reg_read(struct bpf_verifier_env *env, /* if read wasn't screened by an earlier write ... */ if (writes && state->live & REG_LIVE_WRITTEN) break; + if (parent->live & REG_LIVE_DONE) { + verbose(env, "verifier BUG type %s var_off %lld off %d\n", + reg_type_str[parent->type], + parent->var_off.value, parent->off); + return -EFAULT; + } /* ... then we depend on parent's value */ parent->live |= REG_LIVE_READ; state = parent; @@ -1217,6 +1286,10 @@ static int check_stack_write(struct bpf_verifier_env *env, /* regular write of data into stack destroys any spilled ptr */ state->stack[spi].spilled_ptr.type = NOT_INIT; + /* Mark slots as STACK_MISC if they belonged to spilled ptr. */ + if (state->stack[spi].slot_type[0] == STACK_SPILL) + for (i = 0; i < BPF_REG_SIZE; i++) + state->stack[spi].slot_type[i] = STACK_MISC; /* only mark the slot as written if all 8 bytes were written * otherwise read propagation may incorrectly stop too soon @@ -1234,6 +1307,7 @@ static int check_stack_write(struct bpf_verifier_env *env, register_is_null(&cur->regs[value_regno])) type = STACK_ZERO; + /* Mark slots affected by this stack write. */ for (i = 0; i < size; i++) state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = type; @@ -1455,6 +1529,17 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, verbose(env, "R%d offset is outside of the packet\n", regno); return err; } + + /* __check_packet_access has made sure "off + size - 1" is within u16. + * reg->umax_value can't be bigger than MAX_PACKET_OFF which is 0xffff, + * otherwise find_good_pkt_pointers would have refused to set range info + * that __check_packet_access would have rejected this pkt access. + * Therefore, "off + reg->umax_value + size - 1" won't overflow u32. + */ + env->prog->aux->max_pkt_offset = + max_t(u32, env->prog->aux->max_pkt_offset, + off + reg->umax_value + size - 1); + return err; } @@ -3570,12 +3655,15 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; if (BPF_SRC(insn->code) == BPF_X) { + struct bpf_reg_state *src_reg = regs + insn->src_reg; + struct bpf_reg_state *dst_reg = regs + insn->dst_reg; + if (BPF_CLASS(insn->code) == BPF_ALU64) { /* case: R1 = R2 * copy register state to dest reg */ - regs[insn->dst_reg] = regs[insn->src_reg]; - regs[insn->dst_reg].live |= REG_LIVE_WRITTEN; + *dst_reg = *src_reg; + dst_reg->live |= REG_LIVE_WRITTEN; } else { /* R1 = (u32) R2 */ if (is_pointer_value(env, insn->src_reg)) { @@ -3583,9 +3671,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) "R%d partial copy of pointer\n", insn->src_reg); return -EACCES; + } else if (src_reg->type == SCALAR_VALUE) { + *dst_reg = *src_reg; + dst_reg->live |= REG_LIVE_WRITTEN; + } else { + mark_reg_unknown(env, regs, + insn->dst_reg); } - mark_reg_unknown(env, regs, insn->dst_reg); - coerce_reg_to_size(®s[insn->dst_reg], 4); + coerce_reg_to_size(dst_reg, 4); } } else { /* case: R = imm @@ -3636,11 +3729,6 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } - if (opcode == BPF_ARSH && BPF_CLASS(insn->code) != BPF_ALU64) { - verbose(env, "BPF_ARSH not supported for 32 bit ALU\n"); - return -EINVAL; - } - if ((opcode == BPF_LSH || opcode == BPF_RSH || opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) { int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32; @@ -3751,6 +3839,85 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, } } +/* compute branch direction of the expression "if (reg opcode val) goto target;" + * and return: + * 1 - branch will be taken and "goto target" will be executed + * 0 - branch will not be taken and fall-through to next insn + * -1 - unknown. Example: "if (reg < 5)" is unknown when register value range [0,10] + */ +static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode) +{ + if (__is_pointer_value(false, reg)) + return -1; + + switch (opcode) { + case BPF_JEQ: + if (tnum_is_const(reg->var_off)) + return !!tnum_equals_const(reg->var_off, val); + break; + case BPF_JNE: + if (tnum_is_const(reg->var_off)) + return !tnum_equals_const(reg->var_off, val); + break; + case BPF_JSET: + if ((~reg->var_off.mask & reg->var_off.value) & val) + return 1; + if (!((reg->var_off.mask | reg->var_off.value) & val)) + return 0; + break; + case BPF_JGT: + if (reg->umin_value > val) + return 1; + else if (reg->umax_value <= val) + return 0; + break; + case BPF_JSGT: + if (reg->smin_value > (s64)val) + return 1; + else if (reg->smax_value < (s64)val) + return 0; + break; + case BPF_JLT: + if (reg->umax_value < val) + return 1; + else if (reg->umin_value >= val) + return 0; + break; + case BPF_JSLT: + if (reg->smax_value < (s64)val) + return 1; + else if (reg->smin_value >= (s64)val) + return 0; + break; + case BPF_JGE: + if (reg->umin_value >= val) + return 1; + else if (reg->umax_value < val) + return 0; + break; + case BPF_JSGE: + if (reg->smin_value >= (s64)val) + return 1; + else if (reg->smax_value < (s64)val) + return 0; + break; + case BPF_JLE: + if (reg->umax_value <= val) + return 1; + else if (reg->umin_value > val) + return 0; + break; + case BPF_JSLE: + if (reg->smax_value <= (s64)val) + return 1; + else if (reg->smin_value > (s64)val) + return 0; + break; + } + + return -1; +} + /* Adjusts the register min/max values in the case that the dst_reg is the * variable register that we are working on, and src_reg is a constant or we're * simply doing a BPF_K check. @@ -3782,6 +3949,13 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg, */ __mark_reg_known(false_reg, val); break; + case BPF_JSET: + false_reg->var_off = tnum_and(false_reg->var_off, + tnum_const(~val)); + if (is_power_of_2(val)) + true_reg->var_off = tnum_or(true_reg->var_off, + tnum_const(val)); + break; case BPF_JGT: false_reg->umax_value = min(false_reg->umax_value, val); true_reg->umin_value = max(true_reg->umin_value, val + 1); @@ -3854,6 +4028,13 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, */ __mark_reg_known(false_reg, val); break; + case BPF_JSET: + false_reg->var_off = tnum_and(false_reg->var_off, + tnum_const(~val)); + if (is_power_of_2(val)) + true_reg->var_off = tnum_or(true_reg->var_off, + tnum_const(val)); + break; case BPF_JGT: true_reg->umax_value = min(true_reg->umax_value, val - 1); false_reg->umin_value = max(false_reg->umin_value, val); @@ -4152,21 +4333,15 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, dst_reg = ®s[insn->dst_reg]; - /* detect if R == 0 where R was initialized to zero earlier */ - if (BPF_SRC(insn->code) == BPF_K && - (opcode == BPF_JEQ || opcode == BPF_JNE) && - dst_reg->type == SCALAR_VALUE && - tnum_is_const(dst_reg->var_off)) { - if ((opcode == BPF_JEQ && dst_reg->var_off.value == insn->imm) || - (opcode == BPF_JNE && dst_reg->var_off.value != insn->imm)) { - /* if (imm == imm) goto pc+off; - * only follow the goto, ignore fall-through - */ + if (BPF_SRC(insn->code) == BPF_K) { + int pred = is_branch_taken(dst_reg, insn->imm, opcode); + + if (pred == 1) { + /* only follow the goto, ignore fall-through */ *insn_idx += insn->off; return 0; - } else { - /* if (imm != imm) goto pc+off; - * only follow fall-through branch, since + } else if (pred == 0) { + /* only follow fall-through branch, since * that's where the program will go */ return 0; @@ -4477,6 +4652,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) return 0; if (w < 0 || w >= env->prog->len) { + verbose_linfo(env, t, "%d: ", t); verbose(env, "jump out of range from insn %d to %d\n", t, w); return -EINVAL; } @@ -4494,6 +4670,8 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) insn_stack[cur_stack++] = w; return 1; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { + verbose_linfo(env, t, "%d: ", t); + verbose_linfo(env, w, "%d: ", w); verbose(env, "back-edge from insn %d to %d\n", t, w); return -EINVAL; } else if (insn_state[w] == EXPLORED) { @@ -4516,10 +4694,6 @@ static int check_cfg(struct bpf_verifier_env *env) int ret = 0; int i, t; - ret = check_subprogs(env); - if (ret < 0) - return ret; - insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_state) return -ENOMEM; @@ -4628,6 +4802,277 @@ err_free: return ret; } +/* The minimum supported BTF func info size */ +#define MIN_BPF_FUNCINFO_SIZE 8 +#define MAX_FUNCINFO_REC_SIZE 252 + +static int check_btf_func(struct bpf_verifier_env *env, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + u32 i, nfuncs, urec_size, min_size, prev_offset; + u32 krec_size = sizeof(struct bpf_func_info); + struct bpf_func_info *krecord; + const struct btf_type *type; + struct bpf_prog *prog; + const struct btf *btf; + void __user *urecord; + int ret = 0; + + nfuncs = attr->func_info_cnt; + if (!nfuncs) + return 0; + + if (nfuncs != env->subprog_cnt) { + verbose(env, "number of funcs in func_info doesn't match number of subprogs\n"); + return -EINVAL; + } + + urec_size = attr->func_info_rec_size; + if (urec_size < MIN_BPF_FUNCINFO_SIZE || + urec_size > MAX_FUNCINFO_REC_SIZE || + urec_size % sizeof(u32)) { + verbose(env, "invalid func info rec size %u\n", urec_size); + return -EINVAL; + } + + prog = env->prog; + btf = prog->aux->btf; + + urecord = u64_to_user_ptr(attr->func_info); + min_size = min_t(u32, krec_size, urec_size); + + krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN); + if (!krecord) + return -ENOMEM; + + for (i = 0; i < nfuncs; i++) { + ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size); + if (ret) { + if (ret == -E2BIG) { + verbose(env, "nonzero tailing record in func info"); + /* set the size kernel expects so loader can zero + * out the rest of the record. + */ + if (put_user(min_size, &uattr->func_info_rec_size)) + ret = -EFAULT; + } + goto err_free; + } + + if (copy_from_user(&krecord[i], urecord, min_size)) { + ret = -EFAULT; + goto err_free; + } + + /* check insn_off */ + if (i == 0) { + if (krecord[i].insn_off) { + verbose(env, + "nonzero insn_off %u for the first func info record", + krecord[i].insn_off); + ret = -EINVAL; + goto err_free; + } + } else if (krecord[i].insn_off <= prev_offset) { + verbose(env, + "same or smaller insn offset (%u) than previous func info record (%u)", + krecord[i].insn_off, prev_offset); + ret = -EINVAL; + goto err_free; + } + + if (env->subprog_info[i].start != krecord[i].insn_off) { + verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n"); + ret = -EINVAL; + goto err_free; + } + + /* check type_id */ + type = btf_type_by_id(btf, krecord[i].type_id); + if (!type || BTF_INFO_KIND(type->info) != BTF_KIND_FUNC) { + verbose(env, "invalid type id %d in func info", + krecord[i].type_id); + ret = -EINVAL; + goto err_free; + } + + prev_offset = krecord[i].insn_off; + urecord += urec_size; + } + + prog->aux->func_info = krecord; + prog->aux->func_info_cnt = nfuncs; + return 0; + +err_free: + kvfree(krecord); + return ret; +} + +static void adjust_btf_func(struct bpf_verifier_env *env) +{ + int i; + + if (!env->prog->aux->func_info) + return; + + for (i = 0; i < env->subprog_cnt; i++) + env->prog->aux->func_info[i].insn_off = env->subprog_info[i].start; +} + +#define MIN_BPF_LINEINFO_SIZE (offsetof(struct bpf_line_info, line_col) + \ + sizeof(((struct bpf_line_info *)(0))->line_col)) +#define MAX_LINEINFO_REC_SIZE MAX_FUNCINFO_REC_SIZE + +static int check_btf_line(struct bpf_verifier_env *env, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + u32 i, s, nr_linfo, ncopy, expected_size, rec_size, prev_offset = 0; + struct bpf_subprog_info *sub; + struct bpf_line_info *linfo; + struct bpf_prog *prog; + const struct btf *btf; + void __user *ulinfo; + int err; + + nr_linfo = attr->line_info_cnt; + if (!nr_linfo) + return 0; + + rec_size = attr->line_info_rec_size; + if (rec_size < MIN_BPF_LINEINFO_SIZE || + rec_size > MAX_LINEINFO_REC_SIZE || + rec_size & (sizeof(u32) - 1)) + return -EINVAL; + + /* Need to zero it in case the userspace may + * pass in a smaller bpf_line_info object. + */ + linfo = kvcalloc(nr_linfo, sizeof(struct bpf_line_info), + GFP_KERNEL | __GFP_NOWARN); + if (!linfo) + return -ENOMEM; + + prog = env->prog; + btf = prog->aux->btf; + + s = 0; + sub = env->subprog_info; + ulinfo = u64_to_user_ptr(attr->line_info); + expected_size = sizeof(struct bpf_line_info); + ncopy = min_t(u32, expected_size, rec_size); + for (i = 0; i < nr_linfo; i++) { + err = bpf_check_uarg_tail_zero(ulinfo, expected_size, rec_size); + if (err) { + if (err == -E2BIG) { + verbose(env, "nonzero tailing record in line_info"); + if (put_user(expected_size, + &uattr->line_info_rec_size)) + err = -EFAULT; + } + goto err_free; + } + + if (copy_from_user(&linfo[i], ulinfo, ncopy)) { + err = -EFAULT; + goto err_free; + } + + /* + * Check insn_off to ensure + * 1) strictly increasing AND + * 2) bounded by prog->len + * + * The linfo[0].insn_off == 0 check logically falls into + * the later "missing bpf_line_info for func..." case + * because the first linfo[0].insn_off must be the + * first sub also and the first sub must have + * subprog_info[0].start == 0. + */ + if ((i && linfo[i].insn_off <= prev_offset) || + linfo[i].insn_off >= prog->len) { + verbose(env, "Invalid line_info[%u].insn_off:%u (prev_offset:%u prog->len:%u)\n", + i, linfo[i].insn_off, prev_offset, + prog->len); + err = -EINVAL; + goto err_free; + } + + if (!prog->insnsi[linfo[i].insn_off].code) { + verbose(env, + "Invalid insn code at line_info[%u].insn_off\n", + i); + err = -EINVAL; + goto err_free; + } + + if (!btf_name_by_offset(btf, linfo[i].line_off) || + !btf_name_by_offset(btf, linfo[i].file_name_off)) { + verbose(env, "Invalid line_info[%u].line_off or .file_name_off\n", i); + err = -EINVAL; + goto err_free; + } + + if (s != env->subprog_cnt) { + if (linfo[i].insn_off == sub[s].start) { + sub[s].linfo_idx = i; + s++; + } else if (sub[s].start < linfo[i].insn_off) { + verbose(env, "missing bpf_line_info for func#%u\n", s); + err = -EINVAL; + goto err_free; + } + } + + prev_offset = linfo[i].insn_off; + ulinfo += rec_size; + } + + if (s != env->subprog_cnt) { + verbose(env, "missing bpf_line_info for %u funcs starting from func#%u\n", + env->subprog_cnt - s, s); + err = -EINVAL; + goto err_free; + } + + prog->aux->linfo = linfo; + prog->aux->nr_linfo = nr_linfo; + + return 0; + +err_free: + kvfree(linfo); + return err; +} + +static int check_btf_info(struct bpf_verifier_env *env, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct btf *btf; + int err; + + if (!attr->func_info_cnt && !attr->line_info_cnt) + return 0; + + btf = btf_get_by_fd(attr->prog_btf_fd); + if (IS_ERR(btf)) + return PTR_ERR(btf); + env->prog->aux->btf = btf; + + err = check_btf_func(env, attr, uattr); + if (err) + return err; + + err = check_btf_line(env, attr, uattr); + if (err) + return err; + + return 0; +} + /* check %cur's range satisfies %old's */ static bool range_within(struct bpf_reg_state *old, struct bpf_reg_state *cur) @@ -4674,6 +5119,102 @@ static bool check_ids(u32 old_id, u32 cur_id, struct idpair *idmap) return false; } +static void clean_func_state(struct bpf_verifier_env *env, + struct bpf_func_state *st) +{ + enum bpf_reg_liveness live; + int i, j; + + for (i = 0; i < BPF_REG_FP; i++) { + live = st->regs[i].live; + /* liveness must not touch this register anymore */ + st->regs[i].live |= REG_LIVE_DONE; + if (!(live & REG_LIVE_READ)) + /* since the register is unused, clear its state + * to make further comparison simpler + */ + __mark_reg_not_init(&st->regs[i]); + } + + for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) { + live = st->stack[i].spilled_ptr.live; + /* liveness must not touch this stack slot anymore */ + st->stack[i].spilled_ptr.live |= REG_LIVE_DONE; + if (!(live & REG_LIVE_READ)) { + __mark_reg_not_init(&st->stack[i].spilled_ptr); + for (j = 0; j < BPF_REG_SIZE; j++) + st->stack[i].slot_type[j] = STACK_INVALID; + } + } +} + +static void clean_verifier_state(struct bpf_verifier_env *env, + struct bpf_verifier_state *st) +{ + int i; + + if (st->frame[0]->regs[0].live & REG_LIVE_DONE) + /* all regs in this state in all frames were already marked */ + return; + + for (i = 0; i <= st->curframe; i++) + clean_func_state(env, st->frame[i]); +} + +/* the parentage chains form a tree. + * the verifier states are added to state lists at given insn and + * pushed into state stack for future exploration. + * when the verifier reaches bpf_exit insn some of the verifer states + * stored in the state lists have their final liveness state already, + * but a lot of states will get revised from liveness point of view when + * the verifier explores other branches. + * Example: + * 1: r0 = 1 + * 2: if r1 == 100 goto pc+1 + * 3: r0 = 2 + * 4: exit + * when the verifier reaches exit insn the register r0 in the state list of + * insn 2 will be seen as !REG_LIVE_READ. Then the verifier pops the other_branch + * of insn 2 and goes exploring further. At the insn 4 it will walk the + * parentage chain from insn 4 into insn 2 and will mark r0 as REG_LIVE_READ. + * + * Since the verifier pushes the branch states as it sees them while exploring + * the program the condition of walking the branch instruction for the second + * time means that all states below this branch were already explored and + * their final liveness markes are already propagated. + * Hence when the verifier completes the search of state list in is_state_visited() + * we can call this clean_live_states() function to mark all liveness states + * as REG_LIVE_DONE to indicate that 'parent' pointers of 'struct bpf_reg_state' + * will not be used. + * This function also clears the registers and stack for states that !READ + * to simplify state merging. + * + * Important note here that walking the same branch instruction in the callee + * doesn't meant that the states are DONE. The verifier has to compare + * the callsites + */ +static void clean_live_states(struct bpf_verifier_env *env, int insn, + struct bpf_verifier_state *cur) +{ + struct bpf_verifier_state_list *sl; + int i; + + sl = env->explored_states[insn]; + if (!sl) + return; + + while (sl != STATE_LIST_MARK) { + if (sl->state.curframe != cur->curframe) + goto next; + for (i = 0; i <= cur->curframe; i++) + if (sl->state.frame[i]->callsite != cur->frame[i]->callsite) + goto next; + clean_verifier_state(env, &sl->state); +next: + sl = sl->next; + } +} + /* Returns true if (rold safe implies rcur safe) */ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, struct idpair *idmap) @@ -4787,12 +5328,6 @@ static bool stacksafe(struct bpf_func_state *old, { int i, spi; - /* if explored stack has more populated slots than current stack - * such stacks are not equivalent - */ - if (old->allocated_stack > cur->allocated_stack) - return false; - /* walk slots of the explored stack and ignore any additional * slots in the current stack, since explored(safe) state * didn't use them @@ -4800,12 +5335,21 @@ static bool stacksafe(struct bpf_func_state *old, for (i = 0; i < old->allocated_stack; i++) { spi = i / BPF_REG_SIZE; - if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) + if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) { + i += BPF_REG_SIZE - 1; /* explored state didn't use this */ continue; + } if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID) continue; + + /* explored stack has more populated slots than current stack + * and these slots were used + */ + if (i >= cur->allocated_stack) + return false; + /* if old state was safe with misc data in the stack * it will be safe with zero-initialized stack. * The opposite is not true @@ -4980,7 +5524,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) struct bpf_verifier_state_list *new_sl; struct bpf_verifier_state_list *sl; struct bpf_verifier_state *cur = env->cur_state, *new; - int i, j, err; + int i, j, err, states_cnt = 0; sl = env->explored_states[insn_idx]; if (!sl) @@ -4989,6 +5533,8 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) */ return 0; + clean_live_states(env, insn_idx, cur); + while (sl != STATE_LIST_MARK) { if (states_equal(env, &sl->state, cur)) { /* reached equivalent register/stack state, @@ -5007,8 +5553,12 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return 1; } sl = sl->next; + states_cnt++; } + if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES) + return 0; + /* there were no equivalent states, remember current one. * technically the current state is not proven to be safe yet, * but it will either reach outer most bpf_exit (which means it's safe) @@ -5030,9 +5580,16 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) } new_sl->next = env->explored_states[insn_idx]; env->explored_states[insn_idx] = new_sl; - /* connect new state to parentage chain */ - for (i = 0; i < BPF_REG_FP; i++) - cur_regs(env)[i].parent = &new->frame[new->curframe]->regs[i]; + /* connect new state to parentage chain. Current frame needs all + * registers connected. Only r6 - r9 of the callers are alive (pushed + * to the stack implicitly by JITs) so in callers' frames connect just + * r6 - r9 as an optimization. Callers will have r1 - r5 connected to + * the state of the call instruction (with WRITTEN set), and r0 comes + * from callee with its full parentage chain, anyway. + */ + for (j = 0; j <= cur->curframe; j++) + for (i = j < cur->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) + cur->frame[j]->regs[i].parent = &new->frame[j]->regs[i]; /* clear write marks in current state: the writes we did are not writes * our child did, so they don't screen off its reads from us. * (There are no read marks in current state, because reads always mark @@ -5097,6 +5654,8 @@ static int do_check(struct bpf_verifier_env *env) int insn_processed = 0; bool do_print_state = false; + env->prev_linfo = NULL; + state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL); if (!state) return -ENOMEM; @@ -5148,6 +5707,9 @@ static int do_check(struct bpf_verifier_env *env) goto process_bpf_exit; } + if (signal_pending(current)) + return -EAGAIN; + if (need_resched()) cond_resched(); @@ -5167,6 +5729,7 @@ static int do_check(struct bpf_verifier_env *env) .private_data = env, }; + verbose_linfo(env, insn_idx, "; "); verbose(env, "%d: ", insn_idx); print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); } @@ -5650,7 +6213,7 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len return; /* NOTE: fake 'exit' subprog should be updated as well. */ for (i = 0; i <= env->subprog_cnt; i++) { - if (env->subprog_info[i].start < off) + if (env->subprog_info[i].start <= off) continue; env->subprog_info[i].start += len - 1; } @@ -5707,10 +6270,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) int i, cnt, size, ctx_field_size, delta = 0; const int insn_cnt = env->prog->len; struct bpf_insn insn_buf[16], *insn; + u32 target_size, size_default, off; struct bpf_prog *new_prog; enum bpf_access_type type; bool is_narrower_load; - u32 target_size; if (ops->gen_prologue || env->seen_direct_write) { if (!ops->gen_prologue) { @@ -5803,9 +6366,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) * we will apply proper mask to the result. */ is_narrower_load = size < ctx_field_size; + size_default = bpf_ctx_off_adjust_machine(ctx_field_size); + off = insn->off; if (is_narrower_load) { - u32 size_default = bpf_ctx_off_adjust_machine(ctx_field_size); - u32 off = insn->off; u8 size_code; if (type == BPF_WRITE) { @@ -5833,12 +6396,23 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } if (is_narrower_load && size < target_size) { - if (ctx_field_size <= 4) + u8 shift = (off & (size_default - 1)) * 8; + + if (ctx_field_size <= 4) { + if (shift) + insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH, + insn->dst_reg, + shift); insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg, (1 << size * 8) - 1); - else + } else { + if (shift) + insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH, + insn->dst_reg, + shift); insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg, (1 << size * 8) - 1); + } } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); @@ -5861,7 +6435,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) int i, j, subprog_start, subprog_end = 0, len, subprog; struct bpf_insn *insn; void *old_bpf_func; - int err = -ENOMEM; + int err; if (env->subprog_cnt <= 1) return 0; @@ -5892,6 +6466,11 @@ static int jit_subprogs(struct bpf_verifier_env *env) insn->imm = 1; } + err = bpf_prog_alloc_jited_linfo(prog); + if (err) + goto out_undo_insn; + + err = -ENOMEM; func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL); if (!func) goto out_undo_insn; @@ -5911,12 +6490,21 @@ static int jit_subprogs(struct bpf_verifier_env *env) if (bpf_prog_calc_tag(func[i])) goto out_free; func[i]->is_func = 1; + func[i]->aux->func_idx = i; + /* the btf and func_info will be freed only at prog->aux */ + func[i]->aux->btf = prog->aux->btf; + func[i]->aux->func_info = prog->aux->func_info; + /* Use bpf_prog_F_tag to indicate functions in stack traces. * Long term would need debug info to populate names */ func[i]->aux->name[0] = 'F'; func[i]->aux->stack_depth = env->subprog_info[i].stack_depth; func[i]->jit_requested = 1; + func[i]->aux->linfo = prog->aux->linfo; + func[i]->aux->nr_linfo = prog->aux->nr_linfo; + func[i]->aux->jited_linfo = prog->aux->jited_linfo; + func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx; func[i] = bpf_int_jit_compile(func[i]); if (!func[i]->jited) { err = -ENOTSUPP; @@ -5990,6 +6578,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) prog->bpf_func = func[0]->bpf_func; prog->aux->func = func; prog->aux->func_cnt = env->subprog_cnt; + bpf_prog_free_unused_jited_linfo(prog); return 0; out_free: for (i = 0; i < env->subprog_cnt; i++) @@ -6006,6 +6595,7 @@ out_undo_insn: insn->off = 0; insn->imm = env->insn_aux_data[i].call_imm; } + bpf_prog_free_jited_linfo(prog); return err; } @@ -6138,6 +6728,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) */ prog->cb_access = 1; env->prog->aux->stack_depth = MAX_BPF_STACK; + env->prog->aux->max_pkt_offset = MAX_PACKET_OFF; /* mark bpf_tail_call as different opcode to avoid * conditional branch in the interpeter for every normal @@ -6302,7 +6893,8 @@ static void free_states(struct bpf_verifier_env *env) kfree(env->explored_states); } -int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) +int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, + union bpf_attr __user *uattr) { struct bpf_verifier_env *env; struct bpf_verifier_log *log; @@ -6350,13 +6942,15 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT); if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; + if (attr->prog_flags & BPF_F_ANY_ALIGNMENT) + env->strict_alignment = false; ret = replace_map_fd_with_map_ptr(env); if (ret < 0) goto skip_full_check; if (bpf_prog_is_dev_bound(env->prog->aux)) { - ret = bpf_prog_offload_verifier_prep(env); + ret = bpf_prog_offload_verifier_prep(env->prog); if (ret) goto skip_full_check; } @@ -6370,6 +6964,14 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) env->allow_ptr_leaks = capable(CAP_SYS_ADMIN); + ret = check_subprogs(env); + if (ret < 0) + goto skip_full_check; + + ret = check_btf_info(env, attr, uattr); + if (ret < 0) + goto skip_full_check; + ret = check_cfg(env); if (ret < 0) goto skip_full_check; @@ -6388,10 +6990,11 @@ skip_full_check: free_states(env); if (ret == 0) - sanitize_dead_code(env); + ret = check_max_stack_depth(env); + /* instruction rewrites happen after this point */ if (ret == 0) - ret = check_max_stack_depth(env); + sanitize_dead_code(env); if (ret == 0) /* program is valid, convert *(u32*)(ctx + off) accesses */ @@ -6431,6 +7034,9 @@ skip_full_check: convert_pseudo_ld_imm64(env); } + if (ret == 0) + adjust_btf_func(env); + err_release_maps: if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release |