diff options
-rw-r--r-- | include/linux/bpf.h | 55 | ||||
-rw-r--r-- | include/linux/bpf_verifier.h | 1 | ||||
-rw-r--r-- | include/linux/btf.h | 13 | ||||
-rw-r--r-- | include/uapi/linux/bpf.h | 10 | ||||
-rw-r--r-- | kernel/bpf/bpf_struct_ops.c | 431 | ||||
-rw-r--r-- | kernel/bpf/bpf_struct_ops_types.h | 12 | ||||
-rw-r--r-- | kernel/bpf/btf.c | 143 | ||||
-rw-r--r-- | kernel/bpf/syscall.c | 4 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 26 | ||||
-rw-r--r-- | net/bpf/bpf_dummy_struct_ops.c | 22 | ||||
-rw-r--r-- | net/ipv4/bpf_tcp_ca.c | 20 | ||||
-rw-r--r-- | tools/include/uapi/linux/bpf.h | 10 | ||||
-rw-r--r-- | tools/lib/bpf/bpf.c | 4 | ||||
-rw-r--r-- | tools/lib/bpf/bpf.h | 4 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf.c | 41 | ||||
-rw-r--r-- | tools/lib/bpf/libbpf_probes.c | 1 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c | 66 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h | 5 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c | 75 | ||||
-rw-r--r-- | tools/testing/selftests/bpf/progs/struct_ops_module.c | 30 |
20 files changed, 715 insertions, 258 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 377857b232c6..75b7f9b19c6a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1673,19 +1673,48 @@ struct bpf_struct_ops { void (*unreg)(void *kdata); int (*update)(void *kdata, void *old_kdata); int (*validate)(void *kdata); - const struct btf_type *type; - const struct btf_type *value_type; + void *cfi_stubs; + struct module *owner; const char *name; struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; +}; + +struct bpf_struct_ops_desc { + struct bpf_struct_ops *st_ops; + + const struct btf_type *type; + const struct btf_type *value_type; u32 type_id; u32 value_id; - void *cfi_stubs; +}; + +enum bpf_struct_ops_state { + BPF_STRUCT_OPS_STATE_INIT, + BPF_STRUCT_OPS_STATE_INUSE, + BPF_STRUCT_OPS_STATE_TOBEFREE, + BPF_STRUCT_OPS_STATE_READY, +}; + +struct bpf_struct_ops_common_value { + refcount_t refcnt; + enum bpf_struct_ops_state state; }; #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) +/* This macro helps developer to register a struct_ops type and generate + * type information correctly. Developers should use this macro to register + * a struct_ops type instead of calling __register_bpf_struct_ops() directly. + */ +#define register_bpf_struct_ops(st_ops, type) \ + ({ \ + struct bpf_struct_ops_##type { \ + struct bpf_struct_ops_common_value common; \ + struct type data ____cacheline_aligned_in_smp; \ + }; \ + BTF_TYPE_EMIT(struct bpf_struct_ops_##type); \ + __register_bpf_struct_ops(st_ops); \ + }) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) -const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id); -void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log); bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, @@ -1727,15 +1756,12 @@ struct bpf_dummy_ops { int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); #endif +int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, + struct btf *btf, + struct bpf_verifier_log *log); +void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map); #else -static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) -{ - return NULL; -} -static inline void bpf_struct_ops_init(struct btf *btf, - struct bpf_verifier_log *log) -{ -} +#define register_bpf_struct_ops(st_ops, type) ({ (void *)(st_ops); 0; }) static inline bool bpf_try_module_get(const void *data, struct module *owner) { return try_module_get(owner); @@ -1754,6 +1780,9 @@ static inline int bpf_struct_ops_link_create(union bpf_attr *attr) { return -EOPNOTSUPP; } +static inline void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map) +{ +} #endif diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e11baecbde68..7f5816482a10 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -662,6 +662,7 @@ struct bpf_verifier_env { u32 prev_insn_idx; struct bpf_prog *prog; /* eBPF program being verified */ const struct bpf_verifier_ops *ops; + struct module *attach_btf_mod; /* The owner module of prog->aux->attach_btf */ struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ int stack_size; /* number of states to be processed */ bool strict_alignment; /* perform strict pointer alignment checks */ diff --git a/include/linux/btf.h b/include/linux/btf.h index cf5c6ff48981..1ee8977b8c95 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -137,6 +137,7 @@ struct btf_struct_metas { extern const struct file_operations btf_fops; +const char *btf_get_name(const struct btf *btf); void btf_get(struct btf *btf); void btf_put(struct btf *btf); int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_sz); @@ -496,6 +497,18 @@ static inline void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) struct bpf_verifier_log; +#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) +struct bpf_struct_ops; +int __register_bpf_struct_ops(struct bpf_struct_ops *st_ops); +const struct bpf_struct_ops_desc *bpf_struct_ops_find_value(struct btf *btf, u32 value_id); +const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id); +#else +static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id) +{ + return NULL; +} +#endif + #ifdef CONFIG_BPF_SYSCALL 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); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 287d05732668..1fef6d5a1330 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1330,6 +1330,9 @@ enum { /* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ BPF_F_PATH_FD = (1U << 14), + +/* Flag for value_type_btf_obj_fd, the fd is available */ + BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15), }; /* Flags for BPF_PROG_QUERY. */ @@ -1403,6 +1406,11 @@ union bpf_attr { * to using 5 hash functions). */ __u64 map_extra; + + __s32 value_type_btf_obj_fd; /* fd pointing to a BTF + * type data for + * btf_vmlinux_value_type_id. + */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -6487,7 +6495,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; - __u32 :32; /* alignment pad */ + __u32 btf_vmlinux_id; __u64 map_extra; } __attribute__((aligned(8))); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 02068bd0e4d9..defc052e4622 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -13,26 +13,15 @@ #include <linux/btf_ids.h> #include <linux/rcupdate_wait.h> -enum bpf_struct_ops_state { - BPF_STRUCT_OPS_STATE_INIT, - BPF_STRUCT_OPS_STATE_INUSE, - BPF_STRUCT_OPS_STATE_TOBEFREE, - BPF_STRUCT_OPS_STATE_READY, -}; - -#define BPF_STRUCT_OPS_COMMON_VALUE \ - refcount_t refcnt; \ - enum bpf_struct_ops_state state - struct bpf_struct_ops_value { - BPF_STRUCT_OPS_COMMON_VALUE; + struct bpf_struct_ops_common_value common; char data[] ____cacheline_aligned_in_smp; }; struct bpf_struct_ops_map { struct bpf_map map; struct rcu_head rcu; - const struct bpf_struct_ops *st_ops; + const struct bpf_struct_ops_desc *st_ops_desc; /* protect map_update */ struct mutex lock; /* link has all the bpf_links that is populated @@ -40,12 +29,15 @@ struct bpf_struct_ops_map { * (in kvalue.data). */ struct bpf_link **links; + u32 links_cnt; /* image is a page that has all the trampolines * that stores the func args before calling the bpf_prog. * A PAGE_SIZE "image" is enough to store all trampoline for * "links[]". */ void *image; + /* The owner moduler's btf. */ + struct btf *btf; /* uvalue->data stores the kernel struct * (e.g. tcp_congestion_ops) that is more useful * to userspace than the kvalue. For example, @@ -70,35 +62,6 @@ static DEFINE_MUTEX(update_mutex); #define VALUE_PREFIX "bpf_struct_ops_" #define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1) -/* bpf_struct_ops_##_name (e.g. bpf_struct_ops_tcp_congestion_ops) is - * the map's value exposed to the userspace and its btf-type-id is - * stored at the map->btf_vmlinux_value_type_id. - * - */ -#define BPF_STRUCT_OPS_TYPE(_name) \ -extern struct bpf_struct_ops bpf_##_name; \ - \ -struct bpf_struct_ops_##_name { \ - BPF_STRUCT_OPS_COMMON_VALUE; \ - struct _name data ____cacheline_aligned_in_smp; \ -}; -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE - -enum { -#define BPF_STRUCT_OPS_TYPE(_name) BPF_STRUCT_OPS_TYPE_##_name, -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE - __NR_BPF_STRUCT_OPS_TYPE, -}; - -static struct bpf_struct_ops * const bpf_struct_ops[] = { -#define BPF_STRUCT_OPS_TYPE(_name) \ - [BPF_STRUCT_OPS_TYPE_##_name] = &bpf_##_name, -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE -}; - const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = { }; @@ -108,138 +71,139 @@ const struct bpf_prog_ops bpf_struct_ops_prog_ops = { #endif }; -static const struct btf_type *module_type; +BTF_ID_LIST(st_ops_ids) +BTF_ID(struct, module) +BTF_ID(struct, bpf_struct_ops_common_value) + +enum { + IDX_MODULE_ID, + IDX_ST_OPS_COMMON_VALUE_ID, +}; + +extern struct btf *btf_vmlinux; + +static bool is_valid_value_type(struct btf *btf, s32 value_id, + const struct btf_type *type, + const char *value_name) +{ + const struct btf_type *common_value_type; + const struct btf_member *member; + const struct btf_type *vt, *mt; + + vt = btf_type_by_id(btf, value_id); + if (btf_vlen(vt) != 2) { + pr_warn("The number of %s's members should be 2, but we get %d\n", + value_name, btf_vlen(vt)); + return false; + } + member = btf_type_member(vt); + mt = btf_type_by_id(btf, member->type); + common_value_type = btf_type_by_id(btf_vmlinux, + st_ops_ids[IDX_ST_OPS_COMMON_VALUE_ID]); + if (mt != common_value_type) { + pr_warn("The first member of %s should be bpf_struct_ops_common_value\n", + value_name); + return false; + } + member++; + mt = btf_type_by_id(btf, member->type); + if (mt != type) { + pr_warn("The second member of %s should be %s\n", + value_name, btf_name_by_offset(btf, type->name_off)); + return false; + } + + return true; +} -void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) +int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, + struct btf *btf, + struct bpf_verifier_log *log) { - s32 type_id, value_id, module_id; + struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; const struct btf_member *member; - struct bpf_struct_ops *st_ops; const struct btf_type *t; + s32 type_id, value_id; char value_name[128]; const char *mname; - u32 i, j; - - /* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */ -#define BPF_STRUCT_OPS_TYPE(_name) BTF_TYPE_EMIT(struct bpf_struct_ops_##_name); -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE + int i; - module_id = btf_find_by_name_kind(btf, "module", BTF_KIND_STRUCT); - if (module_id < 0) { - pr_warn("Cannot find struct module in btf_vmlinux\n"); - return; + if (strlen(st_ops->name) + VALUE_PREFIX_LEN >= + sizeof(value_name)) { + pr_warn("struct_ops name %s is too long\n", + st_ops->name); + return -EINVAL; } - module_type = btf_type_by_id(btf, module_id); + sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - st_ops = bpf_struct_ops[i]; + type_id = btf_find_by_name_kind(btf, st_ops->name, + BTF_KIND_STRUCT); + if (type_id < 0) { + pr_warn("Cannot find struct %s in %s\n", + st_ops->name, btf_get_name(btf)); + return -EINVAL; + } + t = btf_type_by_id(btf, type_id); + if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { + pr_warn("Cannot support #%u members in struct %s\n", + btf_type_vlen(t), st_ops->name); + return -EINVAL; + } - if (strlen(st_ops->name) + VALUE_PREFIX_LEN >= - sizeof(value_name)) { - pr_warn("struct_ops name %s is too long\n", - st_ops->name); - continue; - } - sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); + value_id = btf_find_by_name_kind(btf, value_name, + BTF_KIND_STRUCT); + if (value_id < 0) { + pr_warn("Cannot find struct %s in %s\n", + value_name, btf_get_name(btf)); + return -EINVAL; + } + if (!is_valid_value_type(btf, value_id, t, value_name)) + return -EINVAL; - value_id = btf_find_by_name_kind(btf, value_name, - BTF_KIND_STRUCT); - if (value_id < 0) { - pr_warn("Cannot find struct %s in btf_vmlinux\n", - value_name); - continue; - } + for_each_member(i, t, member) { + const struct btf_type *func_proto; - type_id = btf_find_by_name_kind(btf, st_ops->name, - BTF_KIND_STRUCT); - if (type_id < 0) { - pr_warn("Cannot find struct %s in btf_vmlinux\n", + mname = btf_name_by_offset(btf, member->name_off); + if (!*mname) { + pr_warn("anon member in struct %s is not supported\n", st_ops->name); - continue; - } - t = btf_type_by_id(btf, type_id); - if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { - pr_warn("Cannot support #%u members in struct %s\n", - btf_type_vlen(t), st_ops->name); - continue; + return -EOPNOTSUPP; } - for_each_member(j, t, member) { - const struct btf_type *func_proto; - - mname = btf_name_by_offset(btf, member->name_off); - if (!*mname) { - pr_warn("anon member in struct %s is not supported\n", - st_ops->name); - break; - } - - if (__btf_member_bitfield_size(t, member)) { - pr_warn("bit field member %s in struct %s is not supported\n", - mname, st_ops->name); - break; - } - - func_proto = btf_type_resolve_func_ptr(btf, - member->type, - NULL); - if (func_proto && - btf_distill_func_proto(log, btf, - func_proto, mname, - &st_ops->func_models[j])) { - pr_warn("Error in parsing func ptr %s in struct %s\n", - mname, st_ops->name); - break; - } + if (__btf_member_bitfield_size(t, member)) { + pr_warn("bit field member %s in struct %s is not supported\n", + mname, st_ops->name); + return -EOPNOTSUPP; } - if (j == btf_type_vlen(t)) { - if (st_ops->init(btf)) { - pr_warn("Error in init bpf_struct_ops %s\n", - st_ops->name); - } else { - st_ops->type_id = type_id; - st_ops->type = t; - st_ops->value_id = value_id; - st_ops->value_type = btf_type_by_id(btf, - value_id); - } + func_proto = btf_type_resolve_func_ptr(btf, + member->type, + NULL); + if (func_proto && + btf_distill_func_proto(log, btf, + func_proto, mname, + &st_ops->func_models[i])) { + pr_warn("Error in parsing func ptr %s in struct %s\n", + mname, st_ops->name); + return -EINVAL; } } -} - -extern struct btf *btf_vmlinux; - -static const struct bpf_struct_ops * -bpf_struct_ops_find_value(u32 value_id) -{ - unsigned int i; - - if (!value_id || !btf_vmlinux) - return NULL; - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i]->value_id == value_id) - return bpf_struct_ops[i]; - } - - return NULL; -} - -const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) -{ - unsigned int i; - - if (!type_id || !btf_vmlinux) - return NULL; - - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i]->type_id == type_id) - return bpf_struct_ops[i]; + if (i == btf_type_vlen(t)) { + if (st_ops->init(btf)) { + pr_warn("Error in init bpf_struct_ops %s\n", + st_ops->name); + return -EINVAL; + } else { + st_ops_desc->type_id = type_id; + st_ops_desc->type = t; + st_ops_desc->value_id = value_id; + st_ops_desc->value_type = btf_type_by_id(btf, + value_id); + } } - return NULL; + return 0; } static int bpf_struct_ops_map_get_next_key(struct bpf_map *map, void *key, @@ -265,7 +229,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, kvalue = &st_map->kvalue; /* Pair with smp_store_release() during map_update */ - state = smp_load_acquire(&kvalue->state); + state = smp_load_acquire(&kvalue->common.state); if (state == BPF_STRUCT_OPS_STATE_INIT) { memset(value, 0, map->value_size); return 0; @@ -276,7 +240,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, */ uvalue = value; memcpy(uvalue, st_map->uvalue, map->value_size); - uvalue->state = state; + uvalue->common.state = state; /* This value offers the user space a general estimate of how * many sockets are still utilizing this struct_ops for TCP @@ -284,7 +248,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, * should sufficiently meet our present goals. */ refcnt = atomic64_read(&map->refcnt) - atomic64_read(&map->usercnt); - refcount_set(&uvalue->refcnt, max_t(s64, refcnt, 0)); + refcount_set(&uvalue->common.refcnt, max_t(s64, refcnt, 0)); return 0; } @@ -296,10 +260,9 @@ static void *bpf_struct_ops_map_lookup_elem(struct bpf_map *map, void *key) static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) { - const struct btf_type *t = st_map->st_ops->type; u32 i; - for (i = 0; i < btf_type_vlen(t); i++) { + for (i = 0; i < st_map->links_cnt; i++) { if (st_map->links[i]) { bpf_link_put(st_map->links[i]); st_map->links[i] = NULL; @@ -307,7 +270,7 @@ static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) } } -static int check_zero_holes(const struct btf_type *t, void *data) +static int check_zero_holes(const struct btf *btf, const struct btf_type *t, void *data) { const struct btf_member *member; u32 i, moff, msize, prev_mend = 0; @@ -319,8 +282,8 @@ static int check_zero_holes(const struct btf_type *t, void *data) memchr_inv(data + prev_mend, 0, moff - prev_mend)) return -EINVAL; - mtype = btf_type_by_id(btf_vmlinux, member->type); - mtype = btf_resolve_size(btf_vmlinux, mtype, &msize); + mtype = btf_type_by_id(btf, member->type); + mtype = btf_resolve_size(btf, mtype, &msize); if (IS_ERR(mtype)) return PTR_ERR(mtype); prev_mend = moff + msize; @@ -376,10 +339,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; - const struct bpf_struct_ops *st_ops = st_map->st_ops; + const struct bpf_struct_ops_desc *st_ops_desc = st_map->st_ops_desc; + const struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; struct bpf_struct_ops_value *uvalue, *kvalue; + const struct btf_type *module_type; const struct btf_member *member; - const struct btf_type *t = st_ops->type; + const struct btf_type *t = st_ops_desc->type; struct bpf_tramp_links *tlinks; void *udata, *kdata; int prog_fd, err; @@ -392,16 +357,16 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (*(u32 *)key != 0) return -E2BIG; - err = check_zero_holes(st_ops->value_type, value); + err = check_zero_holes(st_map->btf, st_ops_desc->value_type, value); if (err) return err; uvalue = value; - err = check_zero_holes(t, uvalue->data); + err = check_zero_holes(st_map->btf, t, uvalue->data); if (err) return err; - if (uvalue->state || refcount_read(&uvalue->refcnt)) + if (uvalue->common.state || refcount_read(&uvalue->common.refcnt)) return -EINVAL; tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL); @@ -413,7 +378,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, mutex_lock(&st_map->lock); - if (kvalue->state != BPF_STRUCT_OPS_STATE_INIT) { + if (kvalue->common.state != BPF_STRUCT_OPS_STATE_INIT) { err = -EBUSY; goto unlock; } @@ -425,6 +390,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, image = st_map->image; image_end = st_map->image + PAGE_SIZE; + module_type = btf_type_by_id(btf_vmlinux, st_ops_ids[IDX_MODULE_ID]); for_each_member(i, t, member) { const struct btf_type *mtype, *ptype; struct bpf_prog *prog; @@ -432,7 +398,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, u32 moff; moff = __btf_member_bit_offset(t, member) / 8; - ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); + ptype = btf_type_resolve_ptr(st_map->btf, member->type, NULL); if (ptype == module_type) { if (*(void **)(udata + moff)) goto reset_unlock; @@ -457,8 +423,8 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (!ptype || !btf_type_is_func_proto(ptype)) { u32 msize; - mtype = btf_type_by_id(btf_vmlinux, member->type); - mtype = btf_resolve_size(btf_vmlinux, mtype, &msize); + mtype = btf_type_by_id(st_map->btf, member->type); + mtype = btf_resolve_size(st_map->btf, mtype, &msize); if (IS_ERR(mtype)) { err = PTR_ERR(mtype); goto reset_unlock; @@ -484,7 +450,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, } if (prog->type != BPF_PROG_TYPE_STRUCT_OPS || - prog->aux->attach_btf_id != st_ops->type_id || + prog->aux->attach_btf_id != st_ops_desc->type_id || prog->expected_attach_type != i) { bpf_prog_put(prog); err = -EINVAL; @@ -527,7 +493,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, * * Pair with smp_load_acquire() during lookup_elem(). */ - smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_READY); + smp_store_release(&kvalue->common.state, BPF_STRUCT_OPS_STATE_READY); goto unlock; } @@ -545,7 +511,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, * It ensures the above udata updates (e.g. prog->aux->id) * can be seen once BPF_STRUCT_OPS_STATE_INUSE is set. */ - smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_INUSE); + smp_store_release(&kvalue->common.state, BPF_STRUCT_OPS_STATE_INUSE); goto unlock; } @@ -575,12 +541,12 @@ static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) if (st_map->map.map_flags & BPF_F_LINK) return -EOPNOTSUPP; - prev_state = cmpxchg(&st_map->kvalue.state, + prev_state = cmpxchg(&st_map->kvalue.common.state, BPF_STRUCT_OPS_STATE_INUSE, BPF_STRUCT_OPS_STATE_TOBEFREE); switch (prev_state) { case BPF_STRUCT_OPS_STATE_INUSE: - st_map->st_ops->unreg(&st_map->kvalue.data); + st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data); bpf_map_put(map); return 0; case BPF_STRUCT_OPS_STATE_TOBEFREE: @@ -597,6 +563,7 @@ static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key, struct seq_file *m) { + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; void *value; int err; @@ -606,7 +573,8 @@ static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key, err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); if (!err) { - btf_type_seq_show(btf_vmlinux, map->btf_vmlinux_value_type_id, + btf_type_seq_show(st_map->btf, + map->btf_vmlinux_value_type_id, value, m); seq_puts(m, "\n"); } @@ -631,6 +599,15 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map) static void bpf_struct_ops_map_free(struct bpf_map *map) { + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + + /* st_ops->owner was acquired during map_alloc to implicitly holds + * the btf's refcnt. The acquire was only done when btf_is_module() + * st_map->btf cannot be NULL here. + */ + if (btf_is_module(st_map->btf)) + module_put(st_map->st_ops_desc->st_ops->owner); + /* The struct_ops's function may switch to another struct_ops. * * For example, bpf_tcp_cc_x->init() may switch to @@ -654,29 +631,59 @@ static void bpf_struct_ops_map_free(struct bpf_map *map) static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr) { if (attr->key_size != sizeof(unsigned int) || attr->max_entries != 1 || - (attr->map_flags & ~BPF_F_LINK) || !attr->btf_vmlinux_value_type_id) + (attr->map_flags & ~(BPF_F_LINK | BPF_F_VTYPE_BTF_OBJ_FD)) || + !attr->btf_vmlinux_value_type_id) return -EINVAL; return 0; } static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) { - const struct bpf_struct_ops *st_ops; + const struct bpf_struct_ops_desc *st_ops_desc; size_t st_map_size; struct bpf_struct_ops_map *st_map; const struct btf_type *t, *vt; + struct module *mod = NULL; struct bpf_map *map; + struct btf *btf; int ret; - st_ops = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id); - if (!st_ops) - return ERR_PTR(-ENOTSUPP); + if (attr->map_flags & BPF_F_VTYPE_BTF_OBJ_FD) { + /* The map holds btf for its whole life time. */ + btf = btf_get_by_fd(attr->value_type_btf_obj_fd); + if (IS_ERR(btf)) + return ERR_CAST(btf); + if (!btf_is_module(btf)) { + btf_put(btf); + return ERR_PTR(-EINVAL); + } + + mod = btf_try_get_module(btf); + /* mod holds a refcnt to btf. We don't need an extra refcnt + * here. + */ + btf_put(btf); + if (!mod) + return ERR_PTR(-EINVAL); + } else { + btf = bpf_get_btf_vmlinux(); + if (IS_ERR(btf)) + return ERR_CAST(btf); + } - vt = st_ops->value_type; - if (attr->value_size != vt->size) - return ERR_PTR(-EINVAL); + st_ops_desc = bpf_struct_ops_find_value(btf, attr->btf_vmlinux_value_type_id); + if (!st_ops_desc) { + ret = -ENOTSUPP; + goto errout; + } - t = st_ops->type; + vt = st_ops_desc->value_type; + if (attr->value_size != vt->size) { + ret = -EINVAL; + goto errout; + } + + t = st_ops_desc->type; st_map_size = sizeof(*st_map) + /* kvalue stores the @@ -685,17 +692,17 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) (vt->size - sizeof(struct bpf_struct_ops_value)); st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE); - if (!st_map) - return ERR_PTR(-ENOMEM); + if (!st_map) { + ret = -ENOMEM; + goto errout; + } - st_map->st_ops = st_ops; + st_map->st_ops_desc = st_ops_desc; map = &st_map->map; ret = bpf_jit_charge_modmem(PAGE_SIZE); - if (ret) { - __bpf_struct_ops_map_free(map); - return ERR_PTR(ret); - } + if (ret) + goto errout_free; st_map->image = arch_alloc_bpf_trampoline(PAGE_SIZE); if (!st_map->image) { @@ -704,29 +711,38 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) * here. */ bpf_jit_uncharge_modmem(PAGE_SIZE); - __bpf_struct_ops_map_free(map); - return ERR_PTR(-ENOMEM); + ret = -ENOMEM; + goto errout_free; } st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE); + st_map->links_cnt = btf_type_vlen(t); st_map->links = - bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *), + bpf_map_area_alloc(st_map->links_cnt * sizeof(struct bpf_links *), NUMA_NO_NODE); if (!st_map->uvalue || !st_map->links) { - __bpf_struct_ops_map_free(map); - return ERR_PTR(-ENOMEM); + ret = -ENOMEM; + goto errout_free; } + st_map->btf = btf; mutex_init(&st_map->lock); bpf_map_init_from_attr(map, attr); return map; + +errout_free: + __bpf_struct_ops_map_free(map); +errout: + module_put(mod); + + return ERR_PTR(ret); } static u64 bpf_struct_ops_map_mem_usage(const struct bpf_map *map) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; - const struct bpf_struct_ops *st_ops = st_map->st_ops; - const struct btf_type *vt = st_ops->value_type; + const struct bpf_struct_ops_desc *st_ops_desc = st_map->st_ops_desc; + const struct btf_type *vt = st_ops_desc->value_type; u64 usage; usage = sizeof(*st_map) + @@ -785,7 +801,7 @@ static bool bpf_struct_ops_valid_to_reg(struct bpf_map *map) return map->map_type == BPF_MAP_TYPE_STRUCT_OPS && map->map_flags & BPF_F_LINK && /* Pair with smp_store_release() during map_update */ - smp_load_acquire(&st_map->kvalue.state) == BPF_STRUCT_OPS_STATE_READY; + smp_load_acquire(&st_map->kvalue.common.state) == BPF_STRUCT_OPS_STATE_READY; } static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link) @@ -800,7 +816,7 @@ static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link) /* st_link->map can be NULL if * bpf_struct_ops_link_create() fails to register. */ - st_map->st_ops->unreg(&st_map->kvalue.data); + st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data); bpf_map_put(&st_map->map); } kfree(st_link); @@ -847,7 +863,7 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map if (!bpf_struct_ops_valid_to_reg(new_map)) return -EINVAL; - if (!st_map->st_ops->update) + if (!st_map->st_ops_desc->st_ops->update) return -EOPNOTSUPP; mutex_lock(&update_mutex); @@ -860,12 +876,12 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map old_st_map = container_of(old_map, struct bpf_struct_ops_map, map); /* The new and old struct_ops must be the same type. */ - if (st_map->st_ops != old_st_map->st_ops) { + if (st_map->st_ops_desc != old_st_map->st_ops_desc) { err = -EINVAL; goto err_out; } - err = st_map->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data); + err = st_map->st_ops_desc->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data); if (err) goto err_out; @@ -916,7 +932,7 @@ int bpf_struct_ops_link_create(union bpf_attr *attr) if (err) goto err_out; - err = st_map->st_ops->reg(st_map->kvalue.data); + err = st_map->st_ops_desc->st_ops->reg(st_map->kvalue.data); if (err) { bpf_link_cleanup(&link_primer); link = NULL; @@ -931,3 +947,10 @@ err_out: kfree(link); return err; } + +void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + + info->btf_vmlinux_id = btf_obj_id(st_map->btf); +} diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h deleted file mode 100644 index 5678a9ddf817..000000000000 --- a/kernel/bpf/bpf_struct_ops_types.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* internal file - do not include directly */ - -#ifdef CONFIG_BPF_JIT -#ifdef CONFIG_NET -BPF_STRUCT_OPS_TYPE(bpf_dummy_ops) -#endif -#ifdef CONFIG_INET -#include <net/tcp.h> -BPF_STRUCT_OPS_TYPE(tcp_congestion_ops) -#endif -#endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 4f532b303a27..edef96ceffa3 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -19,6 +19,7 @@ #include <linux/bpf_verifier.h> #include <linux/btf.h> #include <linux/btf_ids.h> +#include <linux/bpf.h> #include <linux/bpf_lsm.h> #include <linux/skmsg.h> #include <linux/perf_event.h> @@ -241,6 +242,12 @@ struct btf_id_dtor_kfunc_tab { struct btf_id_dtor_kfunc dtors[]; }; +struct btf_struct_ops_tab { + u32 cnt; + u32 capacity; + struct bpf_struct_ops_desc ops[]; +}; + struct btf { void *data; struct btf_type **types; @@ -258,6 +265,7 @@ struct btf { struct btf_kfunc_set_tab *kfunc_set_tab; struct btf_id_dtor_kfunc_tab *dtor_kfunc_tab; struct btf_struct_metas *struct_meta_tab; + struct btf_struct_ops_tab *struct_ops_tab; /* split BTF support */ struct btf *base_btf; @@ -1688,11 +1696,20 @@ static void btf_free_struct_meta_tab(struct btf *btf) btf->struct_meta_tab = NULL; } +static void btf_free_struct_ops_tab(struct btf *btf) +{ + struct btf_struct_ops_tab *tab = btf->struct_ops_tab; + + kfree(tab); + btf->struct_ops_tab = NULL; +} + static void btf_free(struct btf *btf) { btf_free_struct_meta_tab(btf); btf_free_dtor_kfunc_tab(btf); btf_free_kfunc_set_tab(btf); + btf_free_struct_ops_tab(btf); kvfree(btf->types); kvfree(btf->resolved_sizes); kvfree(btf->resolved_ids); @@ -1707,6 +1724,11 @@ static void btf_free_rcu(struct rcu_head *rcu) btf_free(btf); } +const char *btf_get_name(const struct btf *btf) +{ + return btf->name; +} + void btf_get(struct btf *btf) { refcount_inc(&btf->refcnt); @@ -5951,8 +5973,6 @@ struct btf *btf_parse_vmlinux(void) /* btf_parse_vmlinux() runs under bpf_verifier_lock */ bpf_ctx_convert.t = btf_type_by_id(btf, bpf_ctx_convert_btf_id[0]); - bpf_struct_ops_init(btf, log); - refcount_set(&btf->refcnt, 1); err = btf_alloc_id(btf); @@ -6302,6 +6322,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, __btf_name_by_offset(btf, t->name_off)); return true; } +EXPORT_SYMBOL_GPL(btf_ctx_access); enum bpf_struct_walk_result { /* < 0 error */ @@ -8684,3 +8705,121 @@ bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, return !strncmp(reg_name, arg_name, cmp_len); } + +#ifdef CONFIG_BPF_JIT +static int +btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops, + struct bpf_verifier_log *log) +{ + struct btf_struct_ops_tab *tab, *new_tab; + int i, err; + + tab = btf->struct_ops_tab; + if (!tab) { + tab = kzalloc(offsetof(struct btf_struct_ops_tab, ops[4]), + GFP_KERNEL); + if (!tab) + return -ENOMEM; + tab->capacity = 4; + btf->struct_ops_tab = tab; + } + + for (i = 0; i < tab->cnt; i++) + if (tab->ops[i].st_ops == st_ops) + return -EEXIST; + + if (tab->cnt == tab->capacity) { + new_tab = krealloc(tab, + offsetof(struct btf_struct_ops_tab, + ops[tab->capacity * 2]), + GFP_KERNEL); + if (!new_tab) + return -ENOMEM; + tab = new_tab; + tab->capacity *= 2; + btf->struct_ops_tab = tab; + } + + tab->ops[btf->struct_ops_tab->cnt].st_ops = st_ops; + + err = bpf_struct_ops_desc_init(&tab->ops[btf->struct_ops_tab->cnt], btf, log); + if (err) + return err; + + btf->struct_ops_tab->cnt++; + + return 0; +} + +const struct bpf_struct_ops_desc * +bpf_struct_ops_find_value(struct btf *btf, u32 value_id) +{ + const struct bpf_struct_ops_desc *st_ops_list; + unsigned int i; + u32 cnt; + + if (!value_id) + return NULL; + if (!btf->struct_ops_tab) + return NULL; + + cnt = btf->struct_ops_tab->cnt; + st_ops_list = btf->struct_ops_tab->ops; + for (i = 0; i < cnt; i++) { + if (st_ops_list[i].value_id == value_id) + return &st_ops_list[i]; + } + + return NULL; +} + +const struct bpf_struct_ops_desc * +bpf_struct_ops_find(struct btf *btf, u32 type_id) +{ + const struct bpf_struct_ops_desc *st_ops_list; + unsigned int i; + u32 cnt; + + if (!type_id) + return NULL; + if (!btf->struct_ops_tab) + return NULL; + + cnt = btf->struct_ops_tab->cnt; + st_ops_list = btf->struct_ops_tab->ops; + for (i = 0; i < cnt; i++) { + if (st_ops_list[i].type_id == type_id) + return &st_ops_list[i]; + } + + return NULL; +} + +int __register_bpf_struct_ops(struct bpf_struct_ops *st_ops) +{ + struct bpf_verifier_log *log; + struct btf *btf; + int err = 0; + + btf = btf_get_module_btf(st_ops->owner); + if (!btf) + return -EINVAL; + + log = kzalloc(sizeof(*log), GFP_KERNEL | __GFP_NOWARN); + if (!log) { + err = -ENOMEM; + goto errout; + } + + log->level = BPF_LOG_KERNEL; + + err = btf_add_struct_ops(btf, st_ops, log); + +errout: + kfree(log); + btf_put(btf); + + return err; +} +EXPORT_SYMBOL_GPL(__register_bpf_struct_ops); +#endif diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 13193aaafb64..f8124b3229e2 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1123,7 +1123,7 @@ free_map_tab: return ret; } -#define BPF_MAP_CREATE_LAST_FIELD map_extra +#define BPF_MAP_CREATE_LAST_FIELD value_type_btf_obj_fd /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -4691,6 +4691,8 @@ static int bpf_map_get_info_by_fd(struct file *file, info.btf_value_type_id = map->btf_value_type_id; } info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) + bpf_map_struct_ops_info_fill(&info, map); if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_info_fill(&info, map); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9e9cc132dd02..f31868ba0c2d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -20285,10 +20285,12 @@ static void print_verification_stats(struct bpf_verifier_env *env) static int check_struct_ops_btf_id(struct bpf_verifier_env *env) { const struct btf_type *t, *func_proto; + const struct bpf_struct_ops_desc *st_ops_desc; const struct bpf_struct_ops *st_ops; const struct btf_member *member; struct bpf_prog *prog = env->prog; u32 btf_id, member_idx; + struct btf *btf; const char *mname; if (!prog->gpl_compatible) { @@ -20296,15 +20298,27 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) return -EINVAL; } + btf = prog->aux->attach_btf ?: bpf_get_btf_vmlinux(); + if (btf_is_module(btf)) { + /* Make sure st_ops is valid through the lifetime of env */ + env->attach_btf_mod = btf_try_get_module(btf); + if (!env->attach_btf_mod) { + verbose(env, "struct_ops module %s is not found\n", + btf_get_name(btf)); + return -ENOTSUPP; + } + } + btf_id = prog->aux->attach_btf_id; - st_ops = bpf_struct_ops_find(btf_id); - if (!st_ops) { + st_ops_desc = bpf_struct_ops_find(btf, btf_id); + if (!st_ops_desc) { verbose(env, "attach_btf_id %u is not a supported struct\n", btf_id); return -ENOTSUPP; } + st_ops = st_ops_desc->st_ops; - t = st_ops->type; + t = st_ops_desc->type; member_idx = prog->expected_attach_type; if (member_idx >= btf_type_vlen(t)) { verbose(env, "attach to invalid member idx %u of struct %s\n", @@ -20313,8 +20327,8 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } member = &btf_type_member(t)[member_idx]; - mname = btf_name_by_offset(btf_vmlinux, member->name_off); - func_proto = btf_type_resolve_func_ptr(btf_vmlinux, member->type, + mname = btf_name_by_offset(btf, member->name_off); + func_proto = btf_type_resolve_func_ptr(btf, member->type, NULL); if (!func_proto) { verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n", @@ -21019,6 +21033,8 @@ err_release_maps: env->prog->expected_attach_type = 0; *prog = env->prog; + + module_put(env->attach_btf_mod); err_unlock: if (!is_priv) mutex_unlock(&bpf_verifier_lock); diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index 8906f7bdf4a9..02de71719aed 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -7,7 +7,7 @@ #include <linux/bpf.h> #include <linux/btf.h> -extern struct bpf_struct_ops bpf_bpf_dummy_ops; +static struct bpf_struct_ops bpf_bpf_dummy_ops; /* A common type for test_N with return value in bpf_dummy_ops */ typedef int (*dummy_ops_test_ret_fn)(struct bpf_dummy_ops_state *state, ...); @@ -22,6 +22,8 @@ struct bpf_dummy_ops_test_args { struct bpf_dummy_ops_state state; }; +static struct btf *bpf_dummy_ops_btf; + static struct bpf_dummy_ops_test_args * dummy_ops_init_args(const union bpf_attr *kattr, unsigned int nr) { @@ -90,9 +92,15 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, void *image = NULL; unsigned int op_idx; int prog_ret; + s32 type_id; int err; - if (prog->aux->attach_btf_id != st_ops->type_id) + type_id = btf_find_by_name_kind(bpf_dummy_ops_btf, + bpf_bpf_dummy_ops.name, + BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + if (prog->aux->attach_btf_id != type_id) return -EOPNOTSUPP; func_proto = prog->aux->attach_func_proto; @@ -148,6 +156,7 @@ out: static int bpf_dummy_init(struct btf *btf) { + bpf_dummy_ops_btf = btf; return 0; } @@ -247,7 +256,7 @@ static struct bpf_dummy_ops __bpf_bpf_dummy_ops = { .test_sleepable = bpf_dummy_test_sleepable, }; -struct bpf_struct_ops bpf_bpf_dummy_ops = { +static struct bpf_struct_ops bpf_bpf_dummy_ops = { .verifier_ops = &bpf_dummy_verifier_ops, .init = bpf_dummy_init, .check_member = bpf_dummy_ops_check_member, @@ -256,4 +265,11 @@ struct bpf_struct_ops bpf_bpf_dummy_ops = { .unreg = bpf_dummy_unreg, .name = "bpf_dummy_ops", .cfi_stubs = &__bpf_bpf_dummy_ops, + .owner = THIS_MODULE, }; + +static int __init bpf_dummy_struct_ops_init(void) +{ + return register_bpf_struct_ops(&bpf_bpf_dummy_ops, bpf_dummy_ops); +} +late_initcall(bpf_dummy_struct_ops_init); diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index ae8b15e6896f..8e7716256d3c 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -12,7 +12,7 @@ #include <net/bpf_sk_storage.h> /* "extern" is to avoid sparse warning. It is only used in bpf_struct_ops.c. */ -extern struct bpf_struct_ops bpf_tcp_congestion_ops; +static struct bpf_struct_ops bpf_tcp_congestion_ops; static u32 unsupported_ops[] = { offsetof(struct tcp_congestion_ops, get_info), @@ -20,6 +20,7 @@ static u32 unsupported_ops[] = { static const struct btf_type *tcp_sock_type; static u32 tcp_sock_id, sock_id; +static const struct btf_type *tcp_congestion_ops_type; static int bpf_tcp_ca_init(struct btf *btf) { @@ -36,6 +37,11 @@ static int bpf_tcp_ca_init(struct btf *btf) tcp_sock_id = type_id; tcp_sock_type = btf_type_by_id(btf, tcp_sock_id); + type_id = btf_find_by_name_kind(btf, "tcp_congestion_ops", BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + tcp_congestion_ops_type = btf_type_by_id(btf, type_id); + return 0; } @@ -149,7 +155,7 @@ static u32 prog_ops_moff(const struct bpf_prog *prog) u32 midx; midx = prog->expected_attach_type; - t = bpf_tcp_congestion_ops.type; + t = tcp_congestion_ops_type; m = &btf_type_member(t)[midx]; return __btf_member_bit_offset(t, m) / 8; @@ -339,7 +345,7 @@ static struct tcp_congestion_ops __bpf_ops_tcp_congestion_ops = { .release = __bpf_tcp_ca_release, }; -struct bpf_struct_ops bpf_tcp_congestion_ops = { +static struct bpf_struct_ops bpf_tcp_congestion_ops = { .verifier_ops = &bpf_tcp_ca_verifier_ops, .reg = bpf_tcp_ca_reg, .unreg = bpf_tcp_ca_unreg, @@ -350,10 +356,16 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = { .validate = bpf_tcp_ca_validate, .name = "tcp_congestion_ops", .cfi_stubs = &__bpf_ops_tcp_congestion_ops, + .owner = THIS_MODULE, }; static int __init bpf_tcp_ca_kfunc_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + int ret; + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + ret = ret ?: register_bpf_struct_ops(&bpf_tcp_congestion_ops, tcp_congestion_ops); + + return ret; } late_initcall(bpf_tcp_ca_kfunc_init); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 287d05732668..1fef6d5a1330 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1330,6 +1330,9 @@ enum { /* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ BPF_F_PATH_FD = (1U << 14), + +/* Flag for value_type_btf_obj_fd, the fd is available */ + BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15), }; /* Flags for BPF_PROG_QUERY. */ @@ -1403,6 +1406,11 @@ union bpf_attr { * to using 5 hash functions). */ __u64 map_extra; + + __s32 value_type_btf_obj_fd; /* fd pointing to a BTF + * type data for + * btf_vmlinux_value_type_id. + */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -6487,7 +6495,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; - __u32 :32; /* alignment pad */ + __u32 btf_vmlinux_id; __u64 map_extra; } __attribute__((aligned(8))); diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 9dc9625651dc..3a35472a17c5 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -169,7 +169,8 @@ int bpf_map_create(enum bpf_map_type map_type, __u32 max_entries, const struct bpf_map_create_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, map_extra); + const size_t attr_sz = offsetofend(union bpf_attr, + value_type_btf_obj_fd); union bpf_attr attr; int fd; @@ -191,6 +192,7 @@ int bpf_map_create(enum bpf_map_type map_type, attr.btf_key_type_id = OPTS_GET(opts, btf_key_type_id, 0); attr.btf_value_type_id = OPTS_GET(opts, btf_value_type_id, 0); attr.btf_vmlinux_value_type_id = OPTS_GET(opts, btf_vmlinux_value_type_id, 0); + attr.value_type_btf_obj_fd = OPTS_GET(opts, value_type_btf_obj_fd, -1); attr.inner_map_fd = OPTS_GET(opts, inner_map_fd, 0); attr.map_flags = OPTS_GET(opts, map_flags, 0); diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index d0f53772bdc0..53b0bee053ad 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -51,8 +51,10 @@ struct bpf_map_create_opts { __u32 numa_node; __u32 map_ifindex; + __s32 value_type_btf_obj_fd; + size_t:0; }; -#define bpf_map_create_opts__last_field map_ifindex +#define bpf_map_create_opts__last_field value_type_btf_obj_fd LIBBPF_API int bpf_map_create(enum bpf_map_type map_type, const char *map_name, diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index b8b00da62907..0569b4973a4f 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -528,6 +528,7 @@ struct bpf_map { struct bpf_map_def def; __u32 numa_node; __u32 btf_var_idx; + int mod_btf_fd; __u32 btf_key_type_id; __u32 btf_value_type_id; __u32 btf_vmlinux_value_type_id; @@ -931,22 +932,29 @@ find_member_by_name(const struct btf *btf, const struct btf_type *t, return NULL; } +static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name, + __u16 kind, struct btf **res_btf, + struct module_btf **res_mod_btf); + #define STRUCT_OPS_VALUE_PREFIX "bpf_struct_ops_" static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, const char *name, __u32 kind); static int -find_struct_ops_kern_types(const struct btf *btf, const char *tname, +find_struct_ops_kern_types(struct bpf_object *obj, const char *tname, + struct module_btf **mod_btf, const struct btf_type **type, __u32 *type_id, const struct btf_type **vtype, __u32 *vtype_id, const struct btf_member **data_member) { const struct btf_type *kern_type, *kern_vtype; const struct btf_member *kern_data_member; + struct btf *btf; __s32 kern_vtype_id, kern_type_id; __u32 i; - kern_type_id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT); + kern_type_id = find_ksym_btf_id(obj, tname, BTF_KIND_STRUCT, + &btf, mod_btf); if (kern_type_id < 0) { pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n", tname); @@ -1000,14 +1008,16 @@ static bool bpf_map__is_struct_ops(const struct bpf_map *map) } /* Init the map's fields that depend on kern_btf */ -static int bpf_map__init_kern_struct_ops(struct bpf_map *map, - const struct btf *btf, - const struct btf *kern_btf) +static int bpf_map__init_kern_struct_ops(struct bpf_map *map) { const struct btf_member *member, *kern_member, *kern_data_member; const struct btf_type *type, *kern_type, *kern_vtype; __u32 i, kern_type_id, kern_vtype_id, kern_data_off; + struct bpf_object *obj = map->obj; + const struct btf *btf = obj->btf; struct bpf_struct_ops *st_ops; + const struct btf *kern_btf; + struct module_btf *mod_btf; void *data, *kern_data; const char *tname; int err; @@ -1015,16 +1025,19 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map, st_ops = map->st_ops; type = st_ops->type; tname = st_ops->tname; - err = find_struct_ops_kern_types(kern_btf, tname, + err = find_struct_ops_kern_types(obj, tname, &mod_btf, &kern_type, &kern_type_id, &kern_vtype, &kern_vtype_id, &kern_data_member); if (err) return err; + kern_btf = mod_btf ? mod_btf->btf : obj->btf_vmlinux; + pr_debug("struct_ops init_kern %s: type_id:%u kern_type_id:%u kern_vtype_id:%u\n", map->name, st_ops->type_id, kern_type_id, kern_vtype_id); + map->mod_btf_fd = mod_btf ? mod_btf->fd : -1; map->def.value_size = kern_vtype->size; map->btf_vmlinux_value_type_id = kern_vtype_id; @@ -1100,6 +1113,8 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map, return -ENOTSUP; } + if (mod_btf) + prog->attach_btf_obj_fd = mod_btf->fd; prog->attach_btf_id = kern_type_id; prog->expected_attach_type = kern_member_idx; @@ -1142,8 +1157,7 @@ static int bpf_object__init_kern_struct_ops_maps(struct bpf_object *obj) if (!bpf_map__is_struct_ops(map)) continue; - err = bpf_map__init_kern_struct_ops(map, obj->btf, - obj->btf_vmlinux); + err = bpf_map__init_kern_struct_ops(map); if (err) return err; } @@ -5162,8 +5176,13 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.numa_node = map->numa_node; create_attr.map_extra = map->map_extra; - if (bpf_map__is_struct_ops(map)) + if (bpf_map__is_struct_ops(map)) { create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; + if (map->mod_btf_fd >= 0) { + create_attr.value_type_btf_obj_fd = map->mod_btf_fd; + create_attr.map_flags |= BPF_F_VTYPE_BTF_OBJ_FD; + } + } if (obj->btf && btf__fd(obj->btf) >= 0) { create_attr.btf_fd = btf__fd(obj->btf); @@ -9970,7 +9989,9 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attac *btf_obj_fd = 0; *btf_type_id = 1; } else { - err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id); + err = find_kernel_btf_id(prog->obj, attach_name, + attach_type, btf_obj_fd, + btf_type_id); } if (err) { pr_warn("prog '%s': failed to find kernel BTF type ID of '%s': %d\n", diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 9c4db90b92b6..98373d126d9d 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -326,6 +326,7 @@ static int probe_map_create(enum bpf_map_type map_type) case BPF_MAP_TYPE_STRUCT_OPS: /* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */ opts.btf_vmlinux_value_type_id = 1; + opts.value_type_btf_obj_fd = -1; exp_err = -524; /* -ENOTSUPP */ break; case BPF_MAP_TYPE_BLOOM_FILTER: diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index e7c9e1c7fde0..8befaf17d454 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ +#include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/delay.h> @@ -521,11 +522,75 @@ BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg) BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset) BTF_SET8_END(bpf_testmod_check_kfunc_ids) +static int bpf_testmod_ops_init(struct btf *btf) +{ + return 0; +} + +static bool bpf_testmod_ops_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + return bpf_tracing_btf_ctx_access(off, size, type, prog, info); +} + +static int bpf_testmod_ops_init_member(const struct btf_type *t, + const struct btf_member *member, + void *kdata, const void *udata) +{ + return 0; +} + static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_testmod_check_kfunc_ids, }; +static const struct bpf_verifier_ops bpf_testmod_verifier_ops = { + .is_valid_access = bpf_testmod_ops_is_valid_access, +}; + +static int bpf_dummy_reg(void *kdata) +{ + struct bpf_testmod_ops *ops = kdata; + int r; + + r = ops->test_2(4, 3); + + return 0; +} + +static void bpf_dummy_unreg(void *kdata) +{ +} + +static int bpf_testmod_test_1(void) +{ + return 0; +} + +static int bpf_testmod_test_2(int a, int b) +{ + return 0; +} + +static struct bpf_testmod_ops __bpf_testmod_ops = { + .test_1 = bpf_testmod_test_1, + .test_2 = bpf_testmod_test_2, +}; + +struct bpf_struct_ops bpf_bpf_testmod_ops = { + .verifier_ops = &bpf_testmod_verifier_ops, + .init = bpf_testmod_ops_init, + .init_member = bpf_testmod_ops_init_member, + .reg = bpf_dummy_reg, + .unreg = bpf_dummy_unreg, + .cfi_stubs = &__bpf_testmod_ops, + .name = "bpf_testmod_ops", + .owner = THIS_MODULE, +}; + extern int bpf_fentry_test1(int a); static int bpf_testmod_init(void) @@ -536,6 +601,7 @@ static int bpf_testmod_init(void) ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_testmod_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_testmod_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &bpf_testmod_kfunc_set); + ret = ret ?: register_bpf_struct_ops(&bpf_bpf_testmod_ops, bpf_testmod_ops); if (ret < 0) return ret; if (bpf_fentry_test1(0) < 0) diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h index f32793efe095..ca5435751c79 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h @@ -28,4 +28,9 @@ struct bpf_iter_testmod_seq { int cnt; }; +struct bpf_testmod_ops { + int (*test_1)(void); + int (*test_2)(int a, int b); +}; + #endif /* _BPF_TESTMOD_H */ diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c new file mode 100644 index 000000000000..8d833f0c7580 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include <test_progs.h> +#include <time.h> + +#include "struct_ops_module.skel.h" + +static void check_map_info(struct bpf_map_info *info) +{ + struct bpf_btf_info btf_info; + char btf_name[256]; + u32 btf_info_len = sizeof(btf_info); + int err, fd; + + fd = bpf_btf_get_fd_by_id(info->btf_vmlinux_id); + if (!ASSERT_GE(fd, 0, "get_value_type_btf_obj_fd")) + return; + + memset(&btf_info, 0, sizeof(btf_info)); + btf_info.name = ptr_to_u64(btf_name); + btf_info.name_len = sizeof(btf_name); + err = bpf_btf_get_info_by_fd(fd, &btf_info, &btf_info_len); + if (!ASSERT_OK(err, "get_value_type_btf_obj_info")) + goto cleanup; + + if (!ASSERT_EQ(strcmp(btf_name, "bpf_testmod"), 0, "get_value_type_btf_obj_name")) + goto cleanup; + +cleanup: + close(fd); +} + +static void test_struct_ops_load(void) +{ + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + struct struct_ops_module *skel; + struct bpf_map_info info = {}; + struct bpf_link *link; + int err; + u32 len; + + skel = struct_ops_module__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "struct_ops_module_open")) + return; + + err = struct_ops_module__load(skel); + if (!ASSERT_OK(err, "struct_ops_module_load")) + goto cleanup; + + len = sizeof(info); + err = bpf_map_get_info_by_fd(bpf_map__fd(skel->maps.testmod_1), &info, + &len); + if (!ASSERT_OK(err, "bpf_map_get_info_by_fd")) + goto cleanup; + + link = bpf_map__attach_struct_ops(skel->maps.testmod_1); + ASSERT_OK_PTR(link, "attach_test_mod_1"); + + /* test_2() will be called from bpf_dummy_reg() in bpf_testmod.c */ + ASSERT_EQ(skel->bss->test_2_result, 7, "test_2_result"); + + bpf_link__destroy(link); + + check_map_info(&info); + +cleanup: + struct_ops_module__destroy(skel); +} + +void serial_test_struct_ops_module(void) +{ + if (test__start_subtest("test_struct_ops_load")) + test_struct_ops_load(); +} + diff --git a/tools/testing/selftests/bpf/progs/struct_ops_module.c b/tools/testing/selftests/bpf/progs/struct_ops_module.c new file mode 100644 index 000000000000..e44ac55195ca --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_module.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "../bpf_testmod/bpf_testmod.h" + +char _license[] SEC("license") = "GPL"; + +int test_2_result = 0; + +SEC("struct_ops/test_1") +int BPF_PROG(test_1) +{ + return 0xdeadbeef; +} + +SEC("struct_ops/test_2") +int BPF_PROG(test_2, int a, int b) +{ + test_2_result = a + b; + return a + b; +} + +SEC(".struct_ops.link") +struct bpf_testmod_ops testmod_1 = { + .test_1 = (void *)test_1, + .test_2 = (void *)test_2, +}; + |