From 282de143ead96a5d53331e946f31c977b4610a74 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:25:55 +0530 Subject: bpf: Introduce allocated objects support Introduce support for representing pointers to objects allocated by the BPF program, i.e. PTR_TO_BTF_ID that point to a type in program BTF. This is indicated by the presence of MEM_ALLOC type flag in reg->type to avoid having to check btf_is_kernel when trying to match argument types in helpers. Whenever walking such types, any pointers being walked will always yield a SCALAR instead of pointer. In the future we might permit kptr inside such allocated objects (either kernel or program allocated), and it will then form a PTR_TO_BTF_ID of the respective type. For now, such allocated objects will always be referenced in verifier context, hence ref_obj_id == 0 for them is a bug. It is allowed to write to such objects, as long fields that are special are not touched (support for which will be added in subsequent patches). Note that once such a pointer is marked PTR_UNTRUSTED, it is no longer allowed to write to it. No PROBE_MEM handling is therefore done for loads into this type unless PTR_UNTRUSTED is part of the register type, since they can never be in an undefined state, and their lifetime will always be valid. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-6-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e60a5c052473..7440c20c4192 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -525,6 +525,11 @@ enum bpf_type_flag { /* Size is known at compile time. */ MEM_FIXED_SIZE = BIT(10 + BPF_BASE_TYPE_BITS), + /* MEM is of an allocated object of type in program BTF. This is used to + * tag PTR_TO_BTF_ID allocated using bpf_obj_new. + */ + MEM_ALLOC = BIT(11 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; @@ -2792,4 +2797,10 @@ struct bpf_key { bool has_ref; }; #endif /* CONFIG_KEYS */ + +static inline bool type_is_alloc(u32 type) +{ + return type & MEM_ALLOC; +} + #endif /* _LINUX_BPF_H */ -- cgit v1.2.3 From 8ffa5cc142137a59d6a10eb5273fa2ba5dcd4947 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:25:56 +0530 Subject: bpf: Recognize lock and list fields in allocated objects Allow specifying bpf_spin_lock, bpf_list_head, bpf_list_node fields in a allocated object. Also update btf_struct_access to reject direct access to these special fields. A bpf_list_head allows implementing map-in-map style use cases, where an allocated object with bpf_list_head is linked into a list in a map value. This would require embedding a bpf_list_node, support for which is also included. The bpf_spin_lock is used to protect the bpf_list_head and other data. While we strictly don't require to hold a bpf_spin_lock while touching the bpf_list_head in such objects, as when have access to it, we have complete ownership of the object, the locking constraint is still kept and may be conditionally lifted in the future. Note that the specification of such types can be done just like map values, e.g.: struct bar { struct bpf_list_node node; }; struct foo { struct bpf_spin_lock lock; struct bpf_list_head head __contains(bar, node); struct bpf_list_node node; }; struct map_value { struct bpf_spin_lock lock; struct bpf_list_head head __contains(foo, node); }; To recognize such types in user BTF, we build a btf_struct_metas array of metadata items corresponding to each BTF ID. This is done once during the btf_parse stage to avoid having to do it each time during the verification process's requirement to inspect the metadata. Moreover, the computed metadata needs to be passed to some helpers in future patches which requires allocating them and storing them in the BTF that is pinned by the program itself, so that valid access can be assumed to such data during program runtime. A key thing to note is that once a btf_struct_meta is available for a type, both the btf_record and btf_field_offs should be available. It is critical that btf_field_offs is available in case special fields are present, as we extensively rely on special fields being zeroed out in map values and allocated objects in later patches. The code ensures that by bailing out in case of errors and ensuring both are available together. If the record is not available, the special fields won't be recognized, so not having both is also fine (in terms of being a verification error and not a runtime bug). Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-7-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 7 ++ include/linux/btf.h | 35 +++++++++ kernel/bpf/btf.c | 197 ++++++++++++++++++++++++++++++++++++++++++++++----- kernel/bpf/syscall.c | 4 ++ 4 files changed, 225 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7440c20c4192..eb6ea53fa5a2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -177,6 +177,7 @@ enum btf_field_type { BPF_KPTR_REF = (1 << 3), BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF, BPF_LIST_HEAD = (1 << 4), + BPF_LIST_NODE = (1 << 5), }; struct btf_field_kptr { @@ -277,6 +278,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) return "kptr"; case BPF_LIST_HEAD: return "bpf_list_head"; + case BPF_LIST_NODE: + return "bpf_list_node"; default: WARN_ON_ONCE(1); return "unknown"; @@ -295,6 +298,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type) return sizeof(u64); case BPF_LIST_HEAD: return sizeof(struct bpf_list_head); + case BPF_LIST_NODE: + return sizeof(struct bpf_list_node); default: WARN_ON_ONCE(1); return 0; @@ -313,6 +318,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type) return __alignof__(u64); case BPF_LIST_HEAD: return __alignof__(struct bpf_list_head); + case BPF_LIST_NODE: + return __alignof__(struct bpf_list_node); default: WARN_ON_ONCE(1); return 0; diff --git a/include/linux/btf.h b/include/linux/btf.h index d80345fa566b..a01a8da20021 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -6,6 +6,8 @@ #include #include +#include +#include #include #include @@ -78,6 +80,17 @@ struct btf_id_dtor_kfunc { u32 kfunc_btf_id; }; +struct btf_struct_meta { + u32 btf_id; + struct btf_record *record; + struct btf_field_offs *field_offs; +}; + +struct btf_struct_metas { + u32 cnt; + struct btf_struct_meta types[]; +}; + typedef void (*btf_dtor_kfunc_t)(void *); extern const struct file_operations btf_fops; @@ -408,6 +421,23 @@ static inline struct btf_param *btf_params(const struct btf_type *t) return (struct btf_param *)(t + 1); } +static inline int btf_id_cmp_func(const void *a, const void *b) +{ + const int *pa = a, *pb = b; + + return *pa - *pb; +} + +static inline bool btf_id_set_contains(const struct btf_id_set *set, u32 id) +{ + return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL; +} + +static inline void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) +{ + return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func); +} + #ifdef CONFIG_BPF_SYSCALL struct bpf_prog; @@ -423,6 +453,7 @@ int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id); int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, struct module *owner); +struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -454,6 +485,10 @@ static inline int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dt { return 0; } +static inline struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id) +{ + return NULL; +} #endif static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 9a596f430558..a04e10477567 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -237,6 +237,7 @@ struct btf { struct rcu_head rcu; struct btf_kfunc_set_tab *kfunc_set_tab; struct btf_id_dtor_kfunc_tab *dtor_kfunc_tab; + struct btf_struct_metas *struct_meta_tab; /* split BTF support */ struct btf *base_btf; @@ -1642,8 +1643,30 @@ static void btf_free_dtor_kfunc_tab(struct btf *btf) btf->dtor_kfunc_tab = NULL; } +static void btf_struct_metas_free(struct btf_struct_metas *tab) +{ + int i; + + if (!tab) + return; + for (i = 0; i < tab->cnt; i++) { + btf_record_free(tab->types[i].record); + kfree(tab->types[i].field_offs); + } + kfree(tab); +} + +static void btf_free_struct_meta_tab(struct btf *btf) +{ + struct btf_struct_metas *tab = btf->struct_meta_tab; + + btf_struct_metas_free(tab); + btf->struct_meta_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); kvfree(btf->types); @@ -3353,6 +3376,12 @@ static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask, goto end; } } + if (field_mask & BPF_LIST_NODE) { + if (!strcmp(name, "bpf_list_node")) { + type = BPF_LIST_NODE; + goto end; + } + } /* Only return BPF_KPTR when all other types with matchable names fail */ if (field_mask & BPF_KPTR) { type = BPF_KPTR_REF; @@ -3396,6 +3425,7 @@ static int btf_find_struct_field(const struct btf *btf, switch (field_type) { case BPF_SPIN_LOCK: case BPF_TIMER: + case BPF_LIST_NODE: ret = btf_find_struct(btf, member_type, off, sz, field_type, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) @@ -3456,6 +3486,7 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, switch (field_type) { case BPF_SPIN_LOCK: case BPF_TIMER: + case BPF_LIST_NODE: ret = btf_find_struct(btf, var_type, off, sz, field_type, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) @@ -3671,6 +3702,8 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type if (ret < 0) goto end; break; + case BPF_LIST_NODE: + break; default: ret = -EFAULT; goto end; @@ -5141,6 +5174,119 @@ static int btf_parse_hdr(struct btf_verifier_env *env) return btf_check_sec_info(env, btf_data_size); } +static const char *alloc_obj_fields[] = { + "bpf_spin_lock", + "bpf_list_head", + "bpf_list_node", +}; + +static struct btf_struct_metas * +btf_parse_struct_metas(struct bpf_verifier_log *log, struct btf *btf) +{ + union { + struct btf_id_set set; + struct { + u32 _cnt; + u32 _ids[ARRAY_SIZE(alloc_obj_fields)]; + } _arr; + } aof; + struct btf_struct_metas *tab = NULL; + int i, n, id, ret; + + BUILD_BUG_ON(offsetof(struct btf_id_set, cnt) != 0); + BUILD_BUG_ON(sizeof(struct btf_id_set) != sizeof(u32)); + + memset(&aof, 0, sizeof(aof)); + for (i = 0; i < ARRAY_SIZE(alloc_obj_fields); i++) { + /* Try to find whether this special type exists in user BTF, and + * if so remember its ID so we can easily find it among members + * of structs that we iterate in the next loop. + */ + id = btf_find_by_name_kind(btf, alloc_obj_fields[i], BTF_KIND_STRUCT); + if (id < 0) + continue; + aof.set.ids[aof.set.cnt++] = id; + } + + if (!aof.set.cnt) + return NULL; + sort(&aof.set.ids, aof.set.cnt, sizeof(aof.set.ids[0]), btf_id_cmp_func, NULL); + + n = btf_nr_types(btf); + for (i = 1; i < n; i++) { + struct btf_struct_metas *new_tab; + const struct btf_member *member; + struct btf_field_offs *foffs; + struct btf_struct_meta *type; + struct btf_record *record; + const struct btf_type *t; + int j, tab_cnt; + + t = btf_type_by_id(btf, i); + if (!t) { + ret = -EINVAL; + goto free; + } + if (!__btf_type_is_struct(t)) + continue; + + cond_resched(); + + for_each_member(j, t, member) { + if (btf_id_set_contains(&aof.set, member->type)) + goto parse; + } + continue; + parse: + tab_cnt = tab ? tab->cnt : 0; + new_tab = krealloc(tab, offsetof(struct btf_struct_metas, types[tab_cnt + 1]), + GFP_KERNEL | __GFP_NOWARN); + if (!new_tab) { + ret = -ENOMEM; + goto free; + } + if (!tab) + new_tab->cnt = 0; + tab = new_tab; + + type = &tab->types[tab->cnt]; + type->btf_id = i; + record = btf_parse_fields(btf, t, BPF_SPIN_LOCK | BPF_LIST_HEAD | BPF_LIST_NODE, t->size); + /* The record cannot be unset, treat it as an error if so */ + if (IS_ERR_OR_NULL(record)) { + ret = PTR_ERR_OR_ZERO(record) ?: -EFAULT; + goto free; + } + foffs = btf_parse_field_offs(record); + /* We need the field_offs to be valid for a valid record, + * either both should be set or both should be unset. + */ + if (IS_ERR_OR_NULL(foffs)) { + btf_record_free(record); + ret = -EFAULT; + goto free; + } + type->record = record; + type->field_offs = foffs; + tab->cnt++; + } + return tab; +free: + btf_struct_metas_free(tab); + return ERR_PTR(ret); +} + +struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id) +{ + struct btf_struct_metas *tab; + + BUILD_BUG_ON(offsetof(struct btf_struct_meta, btf_id) != 0); + tab = btf->struct_meta_tab; + if (!tab) + return NULL; + return bsearch(&btf_id, tab->types, tab->cnt, sizeof(tab->types[0]), btf_id_cmp_func); +} + static int btf_check_type_tags(struct btf_verifier_env *env, struct btf *btf, int start_id) { @@ -5191,6 +5337,7 @@ static int btf_check_type_tags(struct btf_verifier_env *env, static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, u32 log_level, char __user *log_ubuf, u32 log_size) { + struct btf_struct_metas *struct_meta_tab; struct btf_verifier_env *env = NULL; struct bpf_verifier_log *log; struct btf *btf = NULL; @@ -5259,15 +5406,24 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, if (err) goto errout; + struct_meta_tab = btf_parse_struct_metas(log, btf); + if (IS_ERR(struct_meta_tab)) { + err = PTR_ERR(struct_meta_tab); + goto errout; + } + btf->struct_meta_tab = struct_meta_tab; + if (log->level && bpf_verifier_log_full(log)) { err = -ENOSPC; - goto errout; + goto errout_meta; } btf_verifier_env_free(env); refcount_set(&btf->refcnt, 1); return btf; +errout_meta: + btf_free_struct_meta_tab(btf); errout: btf_verifier_env_free(env); if (btf) @@ -6028,6 +6184,28 @@ int btf_struct_access(struct bpf_verifier_log *log, u32 id = reg->btf_id; int err; + while (type_is_alloc(reg->type)) { + struct btf_struct_meta *meta; + struct btf_record *rec; + int i; + + meta = btf_find_struct_meta(btf, id); + if (!meta) + break; + rec = meta->record; + for (i = 0; i < rec->cnt; i++) { + struct btf_field *field = &rec->fields[i]; + u32 offset = field->offset; + if (off < offset + btf_field_type_size(field->type) && offset < off + size) { + bpf_log(log, + "direct access to %s is disallowed\n", + btf_field_type_name(field->type)); + return -EACCES; + } + } + break; + } + t = btf_type_by_id(btf, id); do { err = btf_struct_walk(log, btf, t, off, size, &id, &tmp_flag); @@ -7269,23 +7447,6 @@ bool btf_is_module(const struct btf *btf) return btf->kernel_btf && strcmp(btf->name, "vmlinux") != 0; } -static int btf_id_cmp_func(const void *a, const void *b) -{ - const int *pa = a, *pb = b; - - return *pa - *pb; -} - -bool btf_id_set_contains(const struct btf_id_set *set, u32 id) -{ - return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL; -} - -static void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) -{ - return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func); -} - enum { BTF_MODULE_F_LIVE = (1 << 0), }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4c20dcbc6526..56ae97d490f4 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -537,6 +537,7 @@ void btf_record_free(struct btf_record *rec) btf_put(rec->fields[i].kptr.btf); break; case BPF_LIST_HEAD: + case BPF_LIST_NODE: /* Nothing to release for bpf_list_head */ break; default: @@ -582,6 +583,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) } break; case BPF_LIST_HEAD: + case BPF_LIST_NODE: /* Nothing to acquire for bpf_list_head */ break; default: @@ -648,6 +650,8 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) continue; bpf_list_head_free(field, field_ptr, obj + rec->spin_lock_off); break; + case BPF_LIST_NODE: + break; default: WARN_ON_ONCE(1); continue; -- cgit v1.2.3 From 865ce09a49d79d2b2c1d980f4c05ffc0b3517bdc Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:25:57 +0530 Subject: bpf: Verify ownership relationships for user BTF types Ensure that there can be no ownership cycles among different types by way of having owning objects that can hold some other type as their element. For instance, a map value can only hold allocated objects, but these are allowed to have another bpf_list_head. To prevent unbounded recursion while freeing resources, elements of bpf_list_head in local kptrs can never have a bpf_list_head which are part of list in a map value. Later patches will verify this by having dedicated BTF selftests. Also, to make runtime destruction easier, once btf_struct_metas is fully populated, we can stash the metadata of the value type directly in the metadata of the list_head fields, as that allows easier access to the value type's layout to destruct it at runtime from the btf_field entry of the list head itself. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-8-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/linux/btf.h | 1 + kernel/bpf/btf.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 4 +++ 4 files changed, 77 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index eb6ea53fa5a2..323985a39ece 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -191,6 +191,7 @@ struct btf_field_list_head { struct btf *btf; u32 value_btf_id; u32 node_offset; + struct btf_record *value_rec; }; struct btf_field { diff --git a/include/linux/btf.h b/include/linux/btf.h index a01a8da20021..42d8f3730a8d 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -178,6 +178,7 @@ int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); int btf_find_timer(const struct btf *btf, const struct btf_type *t); struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, u32 field_mask, u32 value_size); +int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec); struct btf_field_offs *btf_parse_field_offs(struct btf_record *rec); bool btf_type_is_void(const struct btf_type *t); s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index a04e10477567..91aa9c96621f 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3723,6 +3723,67 @@ end: return ERR_PTR(ret); } +int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec) +{ + int i; + + /* There are two owning types, kptr_ref and bpf_list_head. The former + * only supports storing kernel types, which can never store references + * to program allocated local types, atleast not yet. Hence we only need + * to ensure that bpf_list_head ownership does not form cycles. + */ + if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & BPF_LIST_HEAD)) + return 0; + for (i = 0; i < rec->cnt; i++) { + struct btf_struct_meta *meta; + u32 btf_id; + + if (!(rec->fields[i].type & BPF_LIST_HEAD)) + continue; + btf_id = rec->fields[i].list_head.value_btf_id; + meta = btf_find_struct_meta(btf, btf_id); + if (!meta) + return -EFAULT; + rec->fields[i].list_head.value_rec = meta->record; + + if (!(rec->field_mask & BPF_LIST_NODE)) + continue; + + /* We need to ensure ownership acyclicity among all types. The + * proper way to do it would be to topologically sort all BTF + * IDs based on the ownership edges, since there can be multiple + * bpf_list_head in a type. Instead, we use the following + * reasoning: + * + * - A type can only be owned by another type in user BTF if it + * has a bpf_list_node. + * - A type can only _own_ another type in user BTF if it has a + * bpf_list_head. + * + * We ensure that if a type has both bpf_list_head and + * bpf_list_node, its element types cannot be owning types. + * + * To ensure acyclicity: + * + * When A only has bpf_list_head, ownership chain can be: + * A -> B -> C + * Where: + * - B has both bpf_list_head and bpf_list_node. + * - C only has bpf_list_node. + * + * When A has both bpf_list_head and bpf_list_node, some other + * type already owns it in the BTF domain, hence it can not own + * another owning type through any of the bpf_list_head edges. + * A -> B + * Where: + * - B only has bpf_list_node. + */ + if (meta->record->field_mask & BPF_LIST_HEAD) + return -ELOOP; + } + return 0; +} + static int btf_field_offs_cmp(const void *_a, const void *_b, const void *priv) { const u32 a = *(const u32 *)_a; @@ -5413,6 +5474,16 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, } btf->struct_meta_tab = struct_meta_tab; + if (struct_meta_tab) { + int i; + + for (i = 0; i < struct_meta_tab->cnt; i++) { + err = btf_check_and_fixup_fields(btf, struct_meta_tab->types[i].record); + if (err < 0) + goto errout_meta; + } + } + if (log->level && bpf_verifier_log_full(log)) { err = -ENOSPC; goto errout_meta; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 56ae97d490f4..6140cbc3ed8a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1054,6 +1054,10 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, } } + ret = btf_check_and_fixup_fields(btf, map->record); + if (ret < 0) + goto free_map_tab; + if (map->ops->map_check_btf) { ret = map->ops->map_check_btf(map, btf, key_type, value_type); if (ret < 0) -- cgit v1.2.3 From d0d78c1df9b1dbfb5e172de473561ce09d5e9d39 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:25:59 +0530 Subject: bpf: Allow locking bpf_spin_lock global variables Global variables reside in maps accessible using direct_value_addr callbacks, so giving each load instruction's rewrite a unique reg->id disallows us from holding locks which are global. The reason for preserving reg->id as a unique value for registers that may point to spin lock is that two separate lookups are treated as two separate memory regions, and any possible aliasing is ignored for the purposes of spin lock correctness. This is not great especially for the global variable case, which are served from maps that have max_entries == 1, i.e. they always lead to map values pointing into the same map value. So refactor the active_spin_lock into a 'active_lock' structure which represents the lock identity, and instead of the reg->id, remember two fields, a pointer and the reg->id. The pointer will store reg->map_ptr or reg->btf. It's only necessary to distinguish for the id == 0 case of global variables, but always setting the pointer to a non-NULL value and using the pointer to check whether the lock is held simplifies code in the verifier. This is generic enough to allow it for global variables, map lookups, and allocated objects at the same time. Note that while whether a lock is held can be answered by just comparing active_lock.ptr to NULL, to determine whether the register is pointing to the same held lock requires comparing _both_ ptr and id. Finally, as a result of this refactoring, pseudo load instructions are not given a unique reg->id, as they are doing lookup for the same map value (max_entries is never greater than 1). Essentially, we consider that the tuple of (ptr, id) will always be unique for any kind of argument to bpf_spin_{lock,unlock}. Note that this can be extended in the future to also remember offset used for locking, so that we can introduce multiple bpf_spin_lock fields in the same allocation. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-10-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 16 +++++++++++++++- kernel/bpf/verifier.c | 41 ++++++++++++++++++++++++++++------------- 2 files changed, 43 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 1a32baa78ce2..1db2b4dc7009 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -323,7 +323,21 @@ struct bpf_verifier_state { u32 branches; u32 insn_idx; u32 curframe; - u32 active_spin_lock; + /* For every reg representing a map value or allocated object pointer, + * we consider the tuple of (ptr, id) for them to be unique in verifier + * context and conside them to not alias each other for the purposes of + * tracking lock state. + */ + struct { + /* This can either be reg->map_ptr or reg->btf. If ptr is NULL, + * there's no active lock held, and other fields have no + * meaning. If non-NULL, it indicates that a lock is held and + * id member has the reg->id of the register which can be >= 0. + */ + void *ptr; + /* This will be reg->id */ + u32 id; + } active_lock; bool speculative; /* first and last insn idx of this verifier state */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 19467dda5dd9..c8f3abe9b08e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1221,7 +1221,8 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, } dst_state->speculative = src->speculative; dst_state->curframe = src->curframe; - dst_state->active_spin_lock = src->active_spin_lock; + dst_state->active_lock.ptr = src->active_lock.ptr; + dst_state->active_lock.id = src->active_lock.id; dst_state->branches = src->branches; dst_state->parent = src->parent; dst_state->first_insn_idx = src->first_insn_idx; @@ -5596,7 +5597,7 @@ int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state * Since only one bpf_spin_lock is allowed the checks are simpler than * reg_is_refcounted() logic. The verifier needs to remember only * one spin_lock instead of array of acquired_refs. - * cur_state->active_spin_lock remembers which map value element or allocated + * cur_state->active_lock remembers which map value element or allocated * object got locked and clears it after bpf_spin_unlock. */ static int process_spin_lock(struct bpf_verifier_env *env, int regno, @@ -5640,22 +5641,35 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, return -EINVAL; } if (is_lock) { - if (cur->active_spin_lock) { + if (cur->active_lock.ptr) { verbose(env, "Locking two bpf_spin_locks are not allowed\n"); return -EINVAL; } - cur->active_spin_lock = reg->id; + if (map) + cur->active_lock.ptr = map; + else + cur->active_lock.ptr = btf; + cur->active_lock.id = reg->id; } else { - if (!cur->active_spin_lock) { + void *ptr; + + if (map) + ptr = map; + else + ptr = btf; + + if (!cur->active_lock.ptr) { verbose(env, "bpf_spin_unlock without taking a lock\n"); return -EINVAL; } - if (cur->active_spin_lock != reg->id) { + if (cur->active_lock.ptr != ptr || + cur->active_lock.id != reg->id) { verbose(env, "bpf_spin_unlock of different lock\n"); return -EINVAL; } - cur->active_spin_lock = 0; + cur->active_lock.ptr = NULL; + cur->active_lock.id = 0; } return 0; } @@ -10617,8 +10631,8 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) { dst_reg->type = PTR_TO_MAP_VALUE; dst_reg->off = aux->map_off; - if (btf_record_has_field(map->record, BPF_SPIN_LOCK)) - dst_reg->id = ++env->id_gen; + WARN_ON_ONCE(map->max_entries != 1); + /* We want reg->id to be same (0) as map_value is not distinct */ } else if (insn->src_reg == BPF_PSEUDO_MAP_FD || insn->src_reg == BPF_PSEUDO_MAP_IDX) { dst_reg->type = CONST_PTR_TO_MAP; @@ -10696,7 +10710,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } - if (env->cur_state->active_spin_lock) { + if (env->cur_state->active_lock.ptr) { verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_spin_lock-ed region\n"); return -EINVAL; } @@ -11962,7 +11976,8 @@ static bool states_equal(struct bpf_verifier_env *env, if (old->speculative && !cur->speculative) return false; - if (old->active_spin_lock != cur->active_spin_lock) + if (old->active_lock.ptr != cur->active_lock.ptr || + old->active_lock.id != cur->active_lock.id) return false; /* for states to be equal callsites have to be the same @@ -12607,7 +12622,7 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } - if (env->cur_state->active_spin_lock && + if (env->cur_state->active_lock.ptr && (insn->src_reg == BPF_PSEUDO_CALL || insn->imm != BPF_FUNC_spin_unlock)) { verbose(env, "function calls are not allowed while holding a lock\n"); @@ -12644,7 +12659,7 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } - if (env->cur_state->active_spin_lock) { + if (env->cur_state->active_lock.ptr) { verbose(env, "bpf_spin_unlock is missing\n"); return -EINVAL; } -- cgit v1.2.3 From 00b85860feb809852af9a88cb4ca8766d7dff6a3 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:26:01 +0530 Subject: bpf: Rewrite kfunc argument handling As we continue to add more features, argument types, kfunc flags, and different extensions to kfuncs, the code to verify the correctness of the kfunc prototype wrt the passed in registers has become ad-hoc and ugly to read. To make life easier, and make a very clear split between different stages of argument processing, move all the code into verifier.c and refactor into easier to read helpers and functions. This also makes sharing code within the verifier easier with kfunc argument processing. This will be more and more useful in later patches as we are now moving to implement very core BPF helpers as kfuncs, to keep them experimental before baking into UAPI. Remove all kfunc related bits now from btf_check_func_arg_match, as users have been converted away to refactored kfunc argument handling. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-12-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 11 - include/linux/bpf_verifier.h | 2 - include/linux/btf.h | 31 +- kernel/bpf/btf.c | 380 +------------- kernel/bpf/verifier.c | 545 ++++++++++++++++++++- .../selftests/bpf/prog_tests/kfunc_dynptr_param.c | 2 +- tools/testing/selftests/bpf/verifier/calls.c | 2 +- .../testing/selftests/bpf/verifier/ref_tracking.c | 4 +- 8 files changed, 573 insertions(+), 404 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 323985a39ece..0a74df731eb8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2109,22 +2109,11 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, const char *func_name, struct btf_func_model *m); -struct bpf_kfunc_arg_meta { - u64 r0_size; - bool r0_rdonly; - int ref_obj_id; - u32 flags; -}; - struct bpf_reg_state; int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); -int btf_check_kfunc_arg_match(struct bpf_verifier_env *env, - const struct btf *btf, u32 func_id, - struct bpf_reg_state *regs, - struct bpf_kfunc_arg_meta *meta); int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *reg); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 1db2b4dc7009..fb146b0ce006 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -603,8 +603,6 @@ int check_ptr_off_reg(struct bpf_verifier_env *env, int check_func_arg_reg_off(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, enum bpf_arg_type arg_type); -int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - u32 regno); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size); bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, diff --git a/include/linux/btf.h b/include/linux/btf.h index 42d8f3730a8d..d5b26380a60f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -338,6 +338,16 @@ static inline bool btf_type_is_struct(const struct btf_type *t) return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; } +static inline bool __btf_type_is_struct(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT; +} + +static inline bool btf_type_is_array(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; +} + static inline u16 btf_type_vlen(const struct btf_type *t) { return BTF_INFO_VLEN(t->info); @@ -439,9 +449,10 @@ static inline void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func); } -#ifdef CONFIG_BPF_SYSCALL struct bpf_prog; +struct bpf_verifier_log; +#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); struct btf *btf_parse_vmlinux(void); @@ -455,6 +466,12 @@ s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id); int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, struct module *owner); struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id); +const struct btf_member * +btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, enum bpf_prog_type prog_type, + int arg); +bool btf_types_are_same(const struct btf *btf1, u32 id1, + const struct btf *btf2, u32 id2); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -490,6 +507,18 @@ static inline struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf { return NULL; } +static inline const struct btf_member * +btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, enum bpf_prog_type prog_type, + int arg) +{ + return NULL; +} +static inline bool btf_types_are_same(const struct btf *btf1, u32 id1, + const struct btf *btf2, u32 id2) +{ + return false; +} #endif static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 91aa9c96621f..4dcda4ae48c1 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -478,16 +478,6 @@ static bool btf_type_nosize_or_null(const struct btf_type *t) return !t || btf_type_nosize(t); } -static bool __btf_type_is_struct(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT; -} - -static bool btf_type_is_array(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; -} - static bool btf_type_is_datasec(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; @@ -5536,7 +5526,7 @@ static u8 bpf_ctx_convert_map[] = { #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE -static const struct btf_member * +const struct btf_member * btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, enum bpf_prog_type prog_type, int arg) @@ -6322,8 +6312,8 @@ int btf_struct_access(struct bpf_verifier_log *log, * end up with two different module BTFs, but IDs point to the common type in * vmlinux BTF. */ -static bool btf_types_are_same(const struct btf *btf1, u32 id1, - const struct btf *btf2, u32 id2) +bool btf_types_are_same(const struct btf *btf1, u32 id1, + const struct btf *btf2, u32 id2) { if (id1 != id2) return false; @@ -6605,122 +6595,19 @@ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *pr return btf_check_func_type_match(log, btf1, t1, btf2, t2); } -static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { -#ifdef CONFIG_NET - [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], - [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], - [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP], -#endif -}; - -/* Returns true if struct is composed of scalars, 4 levels of nesting allowed */ -static bool __btf_type_is_scalar_struct(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int rec) -{ - const struct btf_type *member_type; - const struct btf_member *member; - u32 i; - - if (!btf_type_is_struct(t)) - return false; - - for_each_member(i, t, member) { - const struct btf_array *array; - - member_type = btf_type_skip_modifiers(btf, member->type, NULL); - if (btf_type_is_struct(member_type)) { - if (rec >= 3) { - bpf_log(log, "max struct nesting depth exceeded\n"); - return false; - } - if (!__btf_type_is_scalar_struct(log, btf, member_type, rec + 1)) - return false; - continue; - } - if (btf_type_is_array(member_type)) { - array = btf_type_array(member_type); - if (!array->nelems) - return false; - member_type = btf_type_skip_modifiers(btf, array->type, NULL); - if (!btf_type_is_scalar(member_type)) - return false; - continue; - } - if (!btf_type_is_scalar(member_type)) - return false; - } - return true; -} - -static bool is_kfunc_arg_mem_size(const struct btf *btf, - const struct btf_param *arg, - const struct bpf_reg_state *reg) -{ - int len, sfx_len = sizeof("__sz") - 1; - const struct btf_type *t; - const char *param_name; - - t = btf_type_skip_modifiers(btf, arg->type, NULL); - if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) - return false; - - /* In the future, this can be ported to use BTF tagging */ - param_name = btf_name_by_offset(btf, arg->name_off); - if (str_is_empty(param_name)) - return false; - len = strlen(param_name); - if (len < sfx_len) - return false; - param_name += len - sfx_len; - if (strncmp(param_name, "__sz", sfx_len)) - return false; - - return true; -} - -static bool btf_is_kfunc_arg_mem_size(const struct btf *btf, - const struct btf_param *arg, - const struct bpf_reg_state *reg, - const char *name) -{ - int len, target_len = strlen(name); - const struct btf_type *t; - const char *param_name; - - t = btf_type_skip_modifiers(btf, arg->type, NULL); - if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) - return false; - - param_name = btf_name_by_offset(btf, arg->name_off); - if (str_is_empty(param_name)) - return false; - len = strlen(param_name); - if (len != target_len) - return false; - if (strcmp(param_name, name)) - return false; - - return true; -} - static int btf_check_func_arg_match(struct bpf_verifier_env *env, const struct btf *btf, u32 func_id, struct bpf_reg_state *regs, bool ptr_to_mem_ok, - struct bpf_kfunc_arg_meta *kfunc_meta, bool processing_call) { enum bpf_prog_type prog_type = resolve_prog_type(env->prog); - bool rel = false, kptr_get = false, trusted_args = false; - bool sleepable = false; struct bpf_verifier_log *log = &env->log; - u32 i, nargs, ref_id, ref_obj_id = 0; - bool is_kfunc = btf_is_kernel(btf); const char *func_name, *ref_tname; const struct btf_type *t, *ref_t; const struct btf_param *args; - int ref_regno = 0, ret; + u32 i, nargs, ref_id; + int ret; t = btf_type_by_id(btf, func_id); if (!t || !btf_type_is_func(t)) { @@ -6746,14 +6633,6 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, return -EINVAL; } - if (is_kfunc && kfunc_meta) { - /* Only kfunc can be release func */ - rel = kfunc_meta->flags & KF_RELEASE; - kptr_get = kfunc_meta->flags & KF_KPTR_GET; - trusted_args = kfunc_meta->flags & KF_TRUSTED_ARGS; - sleepable = kfunc_meta->flags & KF_SLEEPABLE; - } - /* check that BTF function arguments match actual types that the * verifier sees. */ @@ -6761,42 +6640,9 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, enum bpf_arg_type arg_type = ARG_DONTCARE; u32 regno = i + 1; struct bpf_reg_state *reg = ®s[regno]; - bool obj_ptr = false; t = btf_type_skip_modifiers(btf, args[i].type, NULL); if (btf_type_is_scalar(t)) { - if (is_kfunc && kfunc_meta) { - bool is_buf_size = false; - - /* check for any const scalar parameter of name "rdonly_buf_size" - * or "rdwr_buf_size" - */ - if (btf_is_kfunc_arg_mem_size(btf, &args[i], reg, - "rdonly_buf_size")) { - kfunc_meta->r0_rdonly = true; - is_buf_size = true; - } else if (btf_is_kfunc_arg_mem_size(btf, &args[i], reg, - "rdwr_buf_size")) - is_buf_size = true; - - if (is_buf_size) { - if (kfunc_meta->r0_size) { - bpf_log(log, "2 or more rdonly/rdwr_buf_size parameters for kfunc"); - return -EINVAL; - } - - if (!tnum_is_const(reg->var_off)) { - bpf_log(log, "R%d is not a const\n", regno); - return -EINVAL; - } - - kfunc_meta->r0_size = reg->var_off.value; - ret = mark_chain_precision(env, regno); - if (ret) - return ret; - } - } - if (reg->type == SCALAR_VALUE) continue; bpf_log(log, "R%d is not a scalar\n", regno); @@ -6809,88 +6655,14 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, return -EINVAL; } - /* These register types have special constraints wrt ref_obj_id - * and offset checks. The rest of trusted args don't. - */ - obj_ptr = reg->type == PTR_TO_CTX || reg->type == PTR_TO_BTF_ID || - reg2btf_ids[base_type(reg->type)]; - - /* Check if argument must be a referenced pointer, args + i has - * been verified to be a pointer (after skipping modifiers). - * PTR_TO_CTX is ok without having non-zero ref_obj_id. - */ - if (is_kfunc && trusted_args && (obj_ptr && reg->type != PTR_TO_CTX) && !reg->ref_obj_id) { - bpf_log(log, "R%d must be referenced\n", regno); - return -EINVAL; - } - ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id); ref_tname = btf_name_by_offset(btf, ref_t->name_off); - /* Trusted args have the same offset checks as release arguments */ - if ((trusted_args && obj_ptr) || (rel && reg->ref_obj_id)) - arg_type |= OBJ_RELEASE; ret = check_func_arg_reg_off(env, reg, regno, arg_type); if (ret < 0) return ret; - if (is_kfunc && reg->ref_obj_id) { - /* Ensure only one argument is referenced PTR_TO_BTF_ID */ - if (ref_obj_id) { - bpf_log(log, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", - regno, reg->ref_obj_id, ref_obj_id); - return -EFAULT; - } - ref_regno = regno; - ref_obj_id = reg->ref_obj_id; - } - - /* kptr_get is only true for kfunc */ - if (i == 0 && kptr_get) { - struct btf_field *kptr_field; - - if (reg->type != PTR_TO_MAP_VALUE) { - bpf_log(log, "arg#0 expected pointer to map value\n"); - return -EINVAL; - } - - /* check_func_arg_reg_off allows var_off for - * PTR_TO_MAP_VALUE, but we need fixed offset to find - * off_desc. - */ - if (!tnum_is_const(reg->var_off)) { - bpf_log(log, "arg#0 must have constant offset\n"); - return -EINVAL; - } - - kptr_field = btf_record_find(reg->map_ptr->record, reg->off + reg->var_off.value, BPF_KPTR); - if (!kptr_field || kptr_field->type != BPF_KPTR_REF) { - bpf_log(log, "arg#0 no referenced kptr at map value offset=%llu\n", - reg->off + reg->var_off.value); - return -EINVAL; - } - - if (!btf_type_is_ptr(ref_t)) { - bpf_log(log, "arg#0 BTF type must be a double pointer\n"); - return -EINVAL; - } - - ref_t = btf_type_skip_modifiers(btf, ref_t->type, &ref_id); - ref_tname = btf_name_by_offset(btf, ref_t->name_off); - - if (!btf_type_is_struct(ref_t)) { - bpf_log(log, "kernel function %s args#%d pointer type %s %s is not supported\n", - func_name, i, btf_type_str(ref_t), ref_tname); - return -EINVAL; - } - if (!btf_struct_ids_match(log, btf, ref_id, 0, kptr_field->kptr.btf, - kptr_field->kptr.btf_id, true)) { - bpf_log(log, "kernel function %s args#%d expected pointer to %s %s\n", - func_name, i, btf_type_str(ref_t), ref_tname); - return -EINVAL; - } - /* rest of the arguments can be anything, like normal kfunc */ - } else if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { + if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { /* If function expects ctx type in BTF check that caller * is passing PTR_TO_CTX. */ @@ -6900,109 +6672,10 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, i, btf_type_str(t)); return -EINVAL; } - } else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || - (reg2btf_ids[base_type(reg->type)] && !type_flag(reg->type)))) { - const struct btf_type *reg_ref_t; - const struct btf *reg_btf; - const char *reg_ref_tname; - u32 reg_ref_id; - - if (!btf_type_is_struct(ref_t)) { - bpf_log(log, "kernel function %s args#%d pointer type %s %s is not supported\n", - func_name, i, btf_type_str(ref_t), - ref_tname); - return -EINVAL; - } - - if (reg->type == PTR_TO_BTF_ID) { - reg_btf = reg->btf; - reg_ref_id = reg->btf_id; - } else { - reg_btf = btf_vmlinux; - reg_ref_id = *reg2btf_ids[base_type(reg->type)]; - } - - reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id, - ®_ref_id); - reg_ref_tname = btf_name_by_offset(reg_btf, - reg_ref_t->name_off); - if (!btf_struct_ids_match(log, reg_btf, reg_ref_id, - reg->off, btf, ref_id, - trusted_args || (rel && reg->ref_obj_id))) { - bpf_log(log, "kernel function %s args#%d expected pointer to %s %s but R%d has a pointer to %s %s\n", - func_name, i, - btf_type_str(ref_t), ref_tname, - regno, btf_type_str(reg_ref_t), - reg_ref_tname); - return -EINVAL; - } } else if (ptr_to_mem_ok && processing_call) { const struct btf_type *resolve_ret; u32 type_size; - if (is_kfunc) { - bool arg_mem_size = i + 1 < nargs && is_kfunc_arg_mem_size(btf, &args[i + 1], ®s[regno + 1]); - bool arg_dynptr = btf_type_is_struct(ref_t) && - !strcmp(ref_tname, - stringify_struct(bpf_dynptr_kern)); - - /* Permit pointer to mem, but only when argument - * type is pointer to scalar, or struct composed - * (recursively) of scalars. - * When arg_mem_size is true, the pointer can be - * void *. - * Also permit initialized local dynamic pointers. - */ - if (!btf_type_is_scalar(ref_t) && - !__btf_type_is_scalar_struct(log, btf, ref_t, 0) && - !arg_dynptr && - (arg_mem_size ? !btf_type_is_void(ref_t) : 1)) { - bpf_log(log, - "arg#%d pointer type %s %s must point to %sscalar, or struct with scalar\n", - i, btf_type_str(ref_t), ref_tname, arg_mem_size ? "void, " : ""); - return -EINVAL; - } - - if (arg_dynptr) { - if (reg->type != PTR_TO_STACK) { - bpf_log(log, "arg#%d pointer type %s %s not to stack\n", - i, btf_type_str(ref_t), - ref_tname); - return -EINVAL; - } - - if (!is_dynptr_reg_valid_init(env, reg)) { - bpf_log(log, - "arg#%d pointer type %s %s must be valid and initialized\n", - i, btf_type_str(ref_t), - ref_tname); - return -EINVAL; - } - - if (!is_dynptr_type_expected(env, reg, - ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL)) { - bpf_log(log, - "arg#%d pointer type %s %s points to unsupported dynamic pointer type\n", - i, btf_type_str(ref_t), - ref_tname); - return -EINVAL; - } - - continue; - } - - /* Check for mem, len pair */ - if (arg_mem_size) { - if (check_kfunc_mem_size_reg(env, ®s[regno + 1], regno + 1)) { - bpf_log(log, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", - i, i + 1); - return -EINVAL; - } - i++; - continue; - } - } - resolve_ret = btf_resolve_size(btf, ref_t, &type_size); if (IS_ERR(resolve_ret)) { bpf_log(log, @@ -7015,36 +6688,13 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, if (check_mem_reg(env, reg, regno, type_size)) return -EINVAL; } else { - bpf_log(log, "reg type unsupported for arg#%d %sfunction %s#%d\n", i, - is_kfunc ? "kernel " : "", func_name, func_id); + bpf_log(log, "reg type unsupported for arg#%d function %s#%d\n", i, + func_name, func_id); return -EINVAL; } } - /* Either both are set, or neither */ - WARN_ON_ONCE((ref_obj_id && !ref_regno) || (!ref_obj_id && ref_regno)); - /* We already made sure ref_obj_id is set only for one argument. We do - * allow (!rel && ref_obj_id), so that passing such referenced - * PTR_TO_BTF_ID to other kfuncs works. Note that rel is only true when - * is_kfunc is true. - */ - if (rel && !ref_obj_id) { - bpf_log(log, "release kernel function %s expects refcounted PTR_TO_BTF_ID\n", - func_name); - return -EINVAL; - } - - if (sleepable && !env->prog->aux->sleepable) { - bpf_log(log, "kernel function %s is sleepable but the program is not\n", - func_name); - return -EINVAL; - } - - if (kfunc_meta && ref_obj_id) - kfunc_meta->ref_obj_id = ref_obj_id; - - /* returns argument register number > 0 in case of reference release kfunc */ - return rel ? ref_regno : 0; + return 0; } /* Compare BTF of a function declaration with given bpf_reg_state. @@ -7074,7 +6724,7 @@ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, return -EINVAL; is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; - err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, NULL, false); + err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, false); /* Compiler optimizations can remove arguments from static functions * or mismatched type can be passed into a global function. @@ -7117,7 +6767,7 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, return -EINVAL; is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; - err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, NULL, true); + err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, true); /* Compiler optimizations can remove arguments from static functions * or mismatched type can be passed into a global function. @@ -7128,14 +6778,6 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, return err; } -int btf_check_kfunc_arg_match(struct bpf_verifier_env *env, - const struct btf *btf, u32 func_id, - struct bpf_reg_state *regs, - struct bpf_kfunc_arg_meta *meta) -{ - return btf_check_func_arg_match(env, btf, func_id, regs, true, meta, true); -} - /* Convert BTF of a function into bpf_reg_state if possible * Returns: * EFAULT - there is a verifier bug. Abort verification. diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c8f3abe9b08e..7d7a91c54709 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5550,8 +5550,8 @@ int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, return err; } -int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - u32 regno) +static int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno) { struct bpf_reg_state *mem_reg = &cur_regs(env)[regno - 1]; bool may_be_null = type_may_be_null(mem_reg->type); @@ -7863,19 +7863,517 @@ static void mark_btf_func_reg_size(struct bpf_verifier_env *env, u32 regno, } } +struct bpf_kfunc_call_arg_meta { + /* In parameters */ + struct btf *btf; + u32 func_id; + u32 kfunc_flags; + const struct btf_type *func_proto; + const char *func_name; + /* Out parameters */ + u32 ref_obj_id; + u8 release_regno; + bool r0_rdonly; + u64 r0_size; +}; + +static bool is_kfunc_acquire(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_ACQUIRE; +} + +static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_RET_NULL; +} + +static bool is_kfunc_release(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_RELEASE; +} + +static bool is_kfunc_trusted_args(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_TRUSTED_ARGS; +} + +static bool is_kfunc_sleepable(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_SLEEPABLE; +} + +static bool is_kfunc_destructive(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_DESTRUCTIVE; +} + +static bool is_kfunc_arg_kptr_get(struct bpf_kfunc_call_arg_meta *meta, int arg) +{ + return arg == 0 && (meta->kfunc_flags & KF_KPTR_GET); +} + +static bool is_kfunc_arg_mem_size(const struct btf *btf, + const struct btf_param *arg, + const struct bpf_reg_state *reg) +{ + int len, sfx_len = sizeof("__sz") - 1; + const struct btf_type *t; + const char *param_name; + + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) + return false; + + /* In the future, this can be ported to use BTF tagging */ + param_name = btf_name_by_offset(btf, arg->name_off); + if (str_is_empty(param_name)) + return false; + len = strlen(param_name); + if (len < sfx_len) + return false; + param_name += len - sfx_len; + if (strncmp(param_name, "__sz", sfx_len)) + return false; + + return true; +} + +static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, + const struct btf_param *arg, + const char *name) +{ + int len, target_len = strlen(name); + const char *param_name; + + param_name = btf_name_by_offset(btf, arg->name_off); + if (str_is_empty(param_name)) + return false; + len = strlen(param_name); + if (len != target_len) + return false; + if (strcmp(param_name, name)) + return false; + + return true; +} + +enum { + KF_ARG_DYNPTR_ID, +}; + +BTF_ID_LIST(kf_arg_btf_ids) +BTF_ID(struct, bpf_dynptr_kern) + +static bool is_kfunc_arg_dynptr(const struct btf *btf, + const struct btf_param *arg) +{ + const struct btf_type *t; + u32 res_id; + + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!t) + return false; + if (!btf_type_is_ptr(t)) + return false; + t = btf_type_skip_modifiers(btf, t->type, &res_id); + if (!t) + return false; + return btf_types_are_same(btf, res_id, btf_vmlinux, kf_arg_btf_ids[KF_ARG_DYNPTR_ID]); +} + +/* Returns true if struct is composed of scalars, 4 levels of nesting allowed */ +static bool __btf_type_is_scalar_struct(struct bpf_verifier_env *env, + const struct btf *btf, + const struct btf_type *t, int rec) +{ + const struct btf_type *member_type; + const struct btf_member *member; + u32 i; + + if (!btf_type_is_struct(t)) + return false; + + for_each_member(i, t, member) { + const struct btf_array *array; + + member_type = btf_type_skip_modifiers(btf, member->type, NULL); + if (btf_type_is_struct(member_type)) { + if (rec >= 3) { + verbose(env, "max struct nesting depth exceeded\n"); + return false; + } + if (!__btf_type_is_scalar_struct(env, btf, member_type, rec + 1)) + return false; + continue; + } + if (btf_type_is_array(member_type)) { + array = btf_array(member_type); + if (!array->nelems) + return false; + member_type = btf_type_skip_modifiers(btf, array->type, NULL); + if (!btf_type_is_scalar(member_type)) + return false; + continue; + } + if (!btf_type_is_scalar(member_type)) + return false; + } + return true; +} + + +static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { +#ifdef CONFIG_NET + [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], + [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], + [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP], +#endif +}; + +enum kfunc_ptr_arg_type { + KF_ARG_PTR_TO_CTX, + KF_ARG_PTR_TO_KPTR, /* PTR_TO_KPTR but type specific */ + KF_ARG_PTR_TO_DYNPTR, + KF_ARG_PTR_TO_BTF_ID, /* Also covers reg2btf_ids conversions */ + KF_ARG_PTR_TO_MEM, + KF_ARG_PTR_TO_MEM_SIZE, /* Size derived from next argument, skip it */ +}; + +static enum kfunc_ptr_arg_type +get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, + struct bpf_kfunc_call_arg_meta *meta, + const struct btf_type *t, const struct btf_type *ref_t, + const char *ref_tname, const struct btf_param *args, + int argno, int nargs) +{ + u32 regno = argno + 1; + struct bpf_reg_state *regs = cur_regs(env); + struct bpf_reg_state *reg = ®s[regno]; + bool arg_mem_size = false; + + /* In this function, we verify the kfunc's BTF as per the argument type, + * leaving the rest of the verification with respect to the register + * type to our caller. When a set of conditions hold in the BTF type of + * arguments, we resolve it to a known kfunc_ptr_arg_type. + */ + if (btf_get_prog_ctx_type(&env->log, meta->btf, t, resolve_prog_type(env->prog), argno)) + return KF_ARG_PTR_TO_CTX; + + if (is_kfunc_arg_kptr_get(meta, argno)) { + if (!btf_type_is_ptr(ref_t)) { + verbose(env, "arg#0 BTF type must be a double pointer for kptr_get kfunc\n"); + return -EINVAL; + } + ref_t = btf_type_by_id(meta->btf, ref_t->type); + ref_tname = btf_name_by_offset(meta->btf, ref_t->name_off); + if (!btf_type_is_struct(ref_t)) { + verbose(env, "kernel function %s args#0 pointer type %s %s is not supported\n", + meta->func_name, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + return KF_ARG_PTR_TO_KPTR; + } + + if (is_kfunc_arg_dynptr(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_DYNPTR; + + if ((base_type(reg->type) == PTR_TO_BTF_ID || reg2btf_ids[base_type(reg->type)])) { + if (!btf_type_is_struct(ref_t)) { + verbose(env, "kernel function %s args#%d pointer type %s %s is not supported\n", + meta->func_name, argno, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + return KF_ARG_PTR_TO_BTF_ID; + } + + if (argno + 1 < nargs && is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1])) + arg_mem_size = true; + + /* This is the catch all argument type of register types supported by + * check_helper_mem_access. However, we only allow when argument type is + * pointer to scalar, or struct composed (recursively) of scalars. When + * arg_mem_size is true, the pointer can be void *. + */ + if (!btf_type_is_scalar(ref_t) && !__btf_type_is_scalar_struct(env, meta->btf, ref_t, 0) && + (arg_mem_size ? !btf_type_is_void(ref_t) : 1)) { + verbose(env, "arg#%d pointer type %s %s must point to %sscalar, or struct with scalar\n", + argno, btf_type_str(ref_t), ref_tname, arg_mem_size ? "void, " : ""); + return -EINVAL; + } + return arg_mem_size ? KF_ARG_PTR_TO_MEM_SIZE : KF_ARG_PTR_TO_MEM; +} + +static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + const struct btf_type *ref_t, + const char *ref_tname, u32 ref_id, + struct bpf_kfunc_call_arg_meta *meta, + int argno) +{ + const struct btf_type *reg_ref_t; + bool strict_type_match = false; + const struct btf *reg_btf; + const char *reg_ref_tname; + u32 reg_ref_id; + + if (reg->type == PTR_TO_BTF_ID) { + reg_btf = reg->btf; + reg_ref_id = reg->btf_id; + } else { + reg_btf = btf_vmlinux; + reg_ref_id = *reg2btf_ids[base_type(reg->type)]; + } + + if (is_kfunc_trusted_args(meta) || (is_kfunc_release(meta) && reg->ref_obj_id)) + strict_type_match = true; + + reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id, ®_ref_id); + reg_ref_tname = btf_name_by_offset(reg_btf, reg_ref_t->name_off); + if (!btf_struct_ids_match(&env->log, reg_btf, reg_ref_id, reg->off, meta->btf, ref_id, strict_type_match)) { + verbose(env, "kernel function %s args#%d expected pointer to %s %s but R%d has a pointer to %s %s\n", + meta->func_name, argno, btf_type_str(ref_t), ref_tname, argno + 1, + btf_type_str(reg_ref_t), reg_ref_tname); + return -EINVAL; + } + return 0; +} + +static int process_kf_arg_ptr_to_kptr(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + const struct btf_type *ref_t, + const char *ref_tname, + struct bpf_kfunc_call_arg_meta *meta, + int argno) +{ + struct btf_field *kptr_field; + + /* check_func_arg_reg_off allows var_off for + * PTR_TO_MAP_VALUE, but we need fixed offset to find + * off_desc. + */ + if (!tnum_is_const(reg->var_off)) { + verbose(env, "arg#0 must have constant offset\n"); + return -EINVAL; + } + + kptr_field = btf_record_find(reg->map_ptr->record, reg->off + reg->var_off.value, BPF_KPTR); + if (!kptr_field || kptr_field->type != BPF_KPTR_REF) { + verbose(env, "arg#0 no referenced kptr at map value offset=%llu\n", + reg->off + reg->var_off.value); + return -EINVAL; + } + + if (!btf_struct_ids_match(&env->log, meta->btf, ref_t->type, 0, kptr_field->kptr.btf, + kptr_field->kptr.btf_id, true)) { + verbose(env, "kernel function %s args#%d expected pointer to %s %s\n", + meta->func_name, argno, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + return 0; +} + +static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta) +{ + const char *func_name = meta->func_name, *ref_tname; + const struct btf *btf = meta->btf; + const struct btf_param *args; + u32 i, nargs; + int ret; + + args = (const struct btf_param *)(meta->func_proto + 1); + nargs = btf_type_vlen(meta->func_proto); + if (nargs > MAX_BPF_FUNC_REG_ARGS) { + verbose(env, "Function %s has %d > %d args\n", func_name, nargs, + MAX_BPF_FUNC_REG_ARGS); + return -EINVAL; + } + + /* Check that BTF function arguments match actual types that the + * verifier sees. + */ + for (i = 0; i < nargs; i++) { + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[i + 1]; + const struct btf_type *t, *ref_t, *resolve_ret; + enum bpf_arg_type arg_type = ARG_DONTCARE; + u32 regno = i + 1, ref_id, type_size; + bool is_ret_buf_sz = false; + int kf_arg_type; + + t = btf_type_skip_modifiers(btf, args[i].type, NULL); + if (btf_type_is_scalar(t)) { + if (reg->type != SCALAR_VALUE) { + verbose(env, "R%d is not a scalar\n", regno); + return -EINVAL; + } + if (is_kfunc_arg_scalar_with_name(btf, &args[i], "rdonly_buf_size")) { + meta->r0_rdonly = true; + is_ret_buf_sz = true; + } else if (is_kfunc_arg_scalar_with_name(btf, &args[i], "rdwr_buf_size")) { + is_ret_buf_sz = true; + } + + if (is_ret_buf_sz) { + if (meta->r0_size) { + verbose(env, "2 or more rdonly/rdwr_buf_size parameters for kfunc"); + return -EINVAL; + } + + if (!tnum_is_const(reg->var_off)) { + verbose(env, "R%d is not a const\n", regno); + return -EINVAL; + } + + meta->r0_size = reg->var_off.value; + ret = mark_chain_precision(env, regno); + if (ret) + return ret; + } + continue; + } + + if (!btf_type_is_ptr(t)) { + verbose(env, "Unrecognized arg#%d type %s\n", i, btf_type_str(t)); + return -EINVAL; + } + + if (reg->ref_obj_id) { + if (is_kfunc_release(meta) && meta->ref_obj_id) { + verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", + regno, reg->ref_obj_id, + meta->ref_obj_id); + return -EFAULT; + } + meta->ref_obj_id = reg->ref_obj_id; + if (is_kfunc_release(meta)) + meta->release_regno = regno; + } + + ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id); + ref_tname = btf_name_by_offset(btf, ref_t->name_off); + + kf_arg_type = get_kfunc_ptr_arg_type(env, meta, t, ref_t, ref_tname, args, i, nargs); + if (kf_arg_type < 0) + return kf_arg_type; + + switch (kf_arg_type) { + case KF_ARG_PTR_TO_BTF_ID: + if (!is_kfunc_trusted_args(meta)) + break; + if (!reg->ref_obj_id) { + verbose(env, "R%d must be referenced\n", regno); + return -EINVAL; + } + fallthrough; + case KF_ARG_PTR_TO_CTX: + /* Trusted arguments have the same offset checks as release arguments */ + arg_type |= OBJ_RELEASE; + break; + case KF_ARG_PTR_TO_KPTR: + case KF_ARG_PTR_TO_DYNPTR: + case KF_ARG_PTR_TO_MEM: + case KF_ARG_PTR_TO_MEM_SIZE: + /* Trusted by default */ + break; + default: + WARN_ON_ONCE(1); + return -EFAULT; + } + + if (is_kfunc_release(meta) && reg->ref_obj_id) + arg_type |= OBJ_RELEASE; + ret = check_func_arg_reg_off(env, reg, regno, arg_type); + if (ret < 0) + return ret; + + switch (kf_arg_type) { + case KF_ARG_PTR_TO_CTX: + if (reg->type != PTR_TO_CTX) { + verbose(env, "arg#%d expected pointer to ctx, but got %s\n", i, btf_type_str(t)); + return -EINVAL; + } + break; + case KF_ARG_PTR_TO_KPTR: + if (reg->type != PTR_TO_MAP_VALUE) { + verbose(env, "arg#0 expected pointer to map value\n"); + return -EINVAL; + } + ret = process_kf_arg_ptr_to_kptr(env, reg, ref_t, ref_tname, meta, i); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_DYNPTR: + if (reg->type != PTR_TO_STACK) { + verbose(env, "arg#%d expected pointer to stack\n", i); + return -EINVAL; + } + + if (!is_dynptr_reg_valid_init(env, reg)) { + verbose(env, "arg#%d pointer type %s %s must be valid and initialized\n", + i, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + + if (!is_dynptr_type_expected(env, reg, ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL)) { + verbose(env, "arg#%d pointer type %s %s points to unsupported dynamic pointer type\n", + i, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + break; + case KF_ARG_PTR_TO_BTF_ID: + /* Only base_type is checked, further checks are done here */ + if (reg->type != PTR_TO_BTF_ID && + (!reg2btf_ids[base_type(reg->type)] || type_flag(reg->type))) { + verbose(env, "arg#%d expected pointer to btf or socket\n", i); + return -EINVAL; + } + ret = process_kf_arg_ptr_to_btf_id(env, reg, ref_t, ref_tname, ref_id, meta, i); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_MEM: + resolve_ret = btf_resolve_size(btf, ref_t, &type_size); + if (IS_ERR(resolve_ret)) { + verbose(env, "arg#%d reference type('%s %s') size cannot be determined: %ld\n", + i, btf_type_str(ref_t), ref_tname, PTR_ERR(resolve_ret)); + return -EINVAL; + } + ret = check_mem_reg(env, reg, regno, type_size); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_MEM_SIZE: + ret = check_kfunc_mem_size_reg(env, ®s[regno + 1], regno + 1); + if (ret < 0) { + verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1); + return ret; + } + /* Skip next '__sz' argument */ + i++; + break; + } + } + + if (is_kfunc_release(meta) && !meta->release_regno) { + verbose(env, "release kernel function %s expects refcounted PTR_TO_BTF_ID\n", + func_name); + return -EINVAL; + } + + return 0; +} + static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) { const struct btf_type *t, *func, *func_proto, *ptr_type; struct bpf_reg_state *regs = cur_regs(env); - struct bpf_kfunc_arg_meta meta = { 0 }; const char *func_name, *ptr_type_name; + struct bpf_kfunc_call_arg_meta meta; u32 i, nargs, func_id, ptr_type_id; int err, insn_idx = *insn_idx_p; const struct btf_param *args; struct btf *desc_btf; u32 *kfunc_flags; - bool acq; /* skip for now, but return error when we find this in fixup_kfunc_call */ if (!insn->imm) @@ -7896,24 +8394,34 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, func_name); return -EACCES; } - if (*kfunc_flags & KF_DESTRUCTIVE && !capable(CAP_SYS_BOOT)) { - verbose(env, "destructive kfunc calls require CAP_SYS_BOOT capabilities\n"); + + /* Prepare kfunc call metadata */ + memset(&meta, 0, sizeof(meta)); + meta.btf = desc_btf; + meta.func_id = func_id; + meta.kfunc_flags = *kfunc_flags; + meta.func_proto = func_proto; + meta.func_name = func_name; + + if (is_kfunc_destructive(&meta) && !capable(CAP_SYS_BOOT)) { + verbose(env, "destructive kfunc calls require CAP_SYS_BOOT capability\n"); return -EACCES; } - acq = *kfunc_flags & KF_ACQUIRE; - - meta.flags = *kfunc_flags; + if (is_kfunc_sleepable(&meta) && !env->prog->aux->sleepable) { + verbose(env, "program must be sleepable to call sleepable kfunc %s\n", func_name); + return -EACCES; + } /* Check the arguments */ - err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs, &meta); + err = check_kfunc_args(env, &meta); if (err < 0) return err; /* In case of release function, we get register number of refcounted - * PTR_TO_BTF_ID back from btf_check_kfunc_arg_match, do the release now + * PTR_TO_BTF_ID in bpf_kfunc_arg_meta, do the release now. */ - if (err) { - err = release_reference(env, regs[err].ref_obj_id); + if (meta.release_regno) { + err = release_reference(env, regs[meta.release_regno].ref_obj_id); if (err) { verbose(env, "kfunc %s#%d reference has not been acquired before\n", func_name, func_id); @@ -7927,7 +8435,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, /* Check return type */ t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL); - if (acq && !btf_type_is_struct_ptr(desc_btf, t)) { + if (is_kfunc_acquire(&meta) && !btf_type_is_struct_ptr(meta.btf, t)) { verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n"); return -EINVAL; } @@ -7966,20 +8474,23 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, regs[BPF_REG_0].type = PTR_TO_BTF_ID; regs[BPF_REG_0].btf_id = ptr_type_id; } - if (*kfunc_flags & KF_RET_NULL) { + if (is_kfunc_ret_null(&meta)) { regs[BPF_REG_0].type |= PTR_MAYBE_NULL; /* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */ regs[BPF_REG_0].id = ++env->id_gen; } mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *)); - if (acq) { + if (is_kfunc_acquire(&meta)) { int id = acquire_reference_state(env, insn_idx); if (id < 0) return id; - regs[BPF_REG_0].id = id; + if (is_kfunc_ret_null(&meta)) + regs[BPF_REG_0].id = id; regs[BPF_REG_0].ref_obj_id = id; } + if (reg_may_point_to_spin_lock(®s[BPF_REG_0]) && !regs[BPF_REG_0].id) + regs[BPF_REG_0].id = ++env->id_gen; } /* else { add_kfunc_call() ensures it is btf_type_is_void(t) } */ nargs = btf_type_vlen(func_proto); diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c index c210657d4d0a..55d641c1f126 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c @@ -22,7 +22,7 @@ static struct { "arg#0 pointer type STRUCT bpf_dynptr_kern points to unsupported dynamic pointer type", 0}, {"not_valid_dynptr", "arg#0 pointer type STRUCT bpf_dynptr_kern must be valid and initialized", 0}, - {"not_ptr_to_stack", "arg#0 pointer type STRUCT bpf_dynptr_kern not to stack", 0}, + {"not_ptr_to_stack", "arg#0 expected pointer to stack", 0}, {"dynptr_data_null", NULL, -EBADMSG}, }; diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index e1a937277b54..86d6fef2e3b4 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -109,7 +109,7 @@ }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "arg#0 pointer type STRUCT prog_test_ref_kfunc must point", + .errstr = "arg#0 expected pointer to btf or socket", .fixup_kfunc_btf_id = { { "bpf_kfunc_call_test_acquire", 3 }, { "bpf_kfunc_call_test_release", 5 }, diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c index fd683a32a276..55cba01c99d5 100644 --- a/tools/testing/selftests/bpf/verifier/ref_tracking.c +++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c @@ -142,7 +142,7 @@ .kfunc = "bpf", .expected_attach_type = BPF_LSM_MAC, .flags = BPF_F_SLEEPABLE, - .errstr = "arg#0 pointer type STRUCT bpf_key must point to scalar, or struct with scalar", + .errstr = "arg#0 expected pointer to btf or socket", .fixup_kfunc_btf_id = { { "bpf_lookup_user_key", 2 }, { "bpf_key_put", 4 }, @@ -163,7 +163,7 @@ .kfunc = "bpf", .expected_attach_type = BPF_LSM_MAC, .flags = BPF_F_SLEEPABLE, - .errstr = "arg#0 pointer type STRUCT bpf_key must point to scalar, or struct with scalar", + .errstr = "arg#0 expected pointer to btf or socket", .fixup_kfunc_btf_id = { { "bpf_lookup_system_key", 1 }, { "bpf_key_put", 3 }, -- cgit v1.2.3 From 958cf2e273f0929c66169e0788031310e8118722 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:26:03 +0530 Subject: bpf: Introduce bpf_obj_new Introduce type safe memory allocator bpf_obj_new for BPF programs. The kernel side kfunc is named bpf_obj_new_impl, as passing hidden arguments to kfuncs still requires having them in prototype, unlike BPF helpers which always take 5 arguments and have them checked using bpf_func_proto in verifier, ignoring unset argument types. Introduce __ign suffix to ignore a specific kfunc argument during type checks, then use this to introduce support for passing type metadata to the bpf_obj_new_impl kfunc. The user passes BTF ID of the type it wants to allocates in program BTF, the verifier then rewrites the first argument as the size of this type, after performing some sanity checks (to ensure it exists and it is a struct type). The second argument is also fixed up and passed by the verifier. This is the btf_struct_meta for the type being allocated. It would be needed mostly for the offset array which is required for zero initializing special fields while leaving the rest of storage in unitialized state. It would also be needed in the next patch to perform proper destruction of the object's special fields. Under the hood, bpf_obj_new will call bpf_mem_alloc and bpf_mem_free, using the any context BPF memory allocator introduced recently. To this end, a global instance of the BPF memory allocator is initialized on boot to be used for this purpose. This 'bpf_global_ma' serves all allocations for bpf_obj_new. In the future, bpf_obj_new variants will allow specifying a custom allocator. Note that now that bpf_obj_new can be used to allocate objects that can be linked to BPF linked list (when future linked list helpers are available), we need to also free the elements using bpf_mem_free. However, since the draining of elements is done outside the bpf_spin_lock, we need to do migrate_disable around the call since bpf_list_head_free can be called from map free path where migration is enabled. Otherwise, when called from BPF programs migration is already disabled. A convenience macro is included in the bpf_experimental.h header to hide over the ugly details of the implementation, leading to user code looking similar to a language level extension which allocates and constructs fields of a user type. struct bar { struct bpf_list_node node; }; struct foo { struct bpf_spin_lock lock; struct bpf_list_head head __contains(bar, node); }; void prog(void) { struct foo *f; f = bpf_obj_new(typeof(*f)); if (!f) return; ... } A key piece of this story is still missing, i.e. the free function, which will come in the next patch. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-14-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 21 +++-- include/linux/bpf_verifier.h | 2 + kernel/bpf/core.c | 16 ++++ kernel/bpf/helpers.c | 47 ++++++++++-- kernel/bpf/verifier.c | 102 +++++++++++++++++++++++-- tools/testing/selftests/bpf/bpf_experimental.h | 25 ++++++ 6 files changed, 190 insertions(+), 23 deletions(-) create mode 100644 tools/testing/selftests/bpf/bpf_experimental.h (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0a74df731eb8..8b32376ce746 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -54,6 +54,8 @@ struct cgroup; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; extern struct kobject *btf_kobj; +extern struct bpf_mem_alloc bpf_global_ma; +extern bool bpf_global_ma_set; typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, @@ -334,16 +336,19 @@ static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_f return rec->field_mask & type; } -static inline void check_and_init_map_value(struct bpf_map *map, void *dst) +static inline void bpf_obj_init(const struct btf_field_offs *foffs, void *obj) { - if (!IS_ERR_OR_NULL(map->record)) { - struct btf_field *fields = map->record->fields; - u32 cnt = map->record->cnt; - int i; + int i; - for (i = 0; i < cnt; i++) - memset(dst + fields[i].offset, 0, btf_field_type_size(fields[i].type)); - } + if (!foffs) + return; + for (i = 0; i < foffs->cnt; i++) + memset(obj + foffs->field_off[i], 0, foffs->field_sz[i]); +} + +static inline void check_and_init_map_value(struct bpf_map *map, void *dst) +{ + bpf_obj_init(map->field_offs, dst); } /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index fb146b0ce006..3dc72d396dfc 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -433,6 +433,8 @@ struct bpf_insn_aux_data { */ struct bpf_loop_inline_state loop_inline_state; }; + u64 obj_new_size; /* remember the size of type passed to bpf_obj_new to rewrite R1 */ + struct btf_struct_meta *kptr_struct_meta; u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ u32 seen; /* this insn was processed by the verifier at env->pass_cnt */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9c16338bcbe8..2e57fc839a5c 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include @@ -60,6 +61,9 @@ #define CTX regs[BPF_REG_CTX] #define IMM insn->imm +struct bpf_mem_alloc bpf_global_ma; +bool bpf_global_ma_set; + /* No hurry in this branch * * Exported for the bpf jit load helper. @@ -2746,6 +2750,18 @@ int __weak bpf_arch_text_invalidate(void *dst, size_t len) return -ENOTSUPP; } +#ifdef CONFIG_BPF_SYSCALL +static int __init bpf_global_ma_init(void) +{ + int ret; + + ret = bpf_mem_alloc_init(&bpf_global_ma, 0, false); + bpf_global_ma_set = !ret; + return ret; +} +late_initcall(bpf_global_ma_init); +#endif + DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key); EXPORT_SYMBOL(bpf_stats_enabled_key); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 5bc0b9f0f306..c4f1c22cc44c 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -19,6 +19,7 @@ #include #include #include +#include #include "../../lib/kstrtox.h" @@ -1735,25 +1736,57 @@ unlock: obj -= field->list_head.node_offset; head = head->next; - /* TODO: Rework later */ - kfree(obj); + /* The contained type can also have resources, including a + * bpf_list_head which needs to be freed. + */ + bpf_obj_free_fields(field->list_head.value_rec, obj); + /* bpf_mem_free requires migrate_disable(), since we can be + * called from map free path as well apart from BPF program (as + * part of map ops doing bpf_obj_free_fields). + */ + migrate_disable(); + bpf_mem_free(&bpf_global_ma, obj); + migrate_enable(); } } -BTF_SET8_START(tracing_btf_ids) +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "Global functions as their definitions will be in vmlinux BTF"); + +void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign) +{ + struct btf_struct_meta *meta = meta__ign; + u64 size = local_type_id__k; + void *p; + + if (unlikely(!bpf_global_ma_set)) + return NULL; + p = bpf_mem_alloc(&bpf_global_ma, size); + if (!p) + return NULL; + if (meta) + bpf_obj_init(meta->field_offs, p); + return p; +} + +__diag_pop(); + +BTF_SET8_START(generic_btf_ids) #ifdef CONFIG_KEXEC_CORE BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE) #endif -BTF_SET8_END(tracing_btf_ids) +BTF_ID_FLAGS(func, bpf_obj_new_impl, KF_ACQUIRE | KF_RET_NULL) +BTF_SET8_END(generic_btf_ids) -static const struct btf_kfunc_id_set tracing_kfunc_set = { +static const struct btf_kfunc_id_set generic_kfunc_set = { .owner = THIS_MODULE, - .set = &tracing_btf_ids, + .set = &generic_btf_ids, }; static int __init kfunc_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &tracing_kfunc_set); + return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &generic_kfunc_set); } late_initcall(kfunc_init); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c8fcc2808d99..804f3bca6c08 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7952,6 +7952,11 @@ static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param return __kfunc_param_match_suffix(btf, arg, "__k"); } +static bool is_kfunc_arg_ignore(const struct btf *btf, const struct btf_param *arg) +{ + return __kfunc_param_match_suffix(btf, arg, "__ign"); +} + static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, const struct btf_param *arg, const char *name) @@ -8214,6 +8219,10 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ int kf_arg_type; t = btf_type_skip_modifiers(btf, args[i].type, NULL); + + if (is_kfunc_arg_ignore(btf, &args[i])) + continue; + if (btf_type_is_scalar(t)) { if (reg->type != SCALAR_VALUE) { verbose(env, "R%d is not a scalar\n", regno); @@ -8391,6 +8400,17 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return 0; } +enum special_kfunc_type { + KF_bpf_obj_new_impl, +}; + +BTF_SET_START(special_kfunc_set) +BTF_ID(func, bpf_obj_new_impl) +BTF_SET_END(special_kfunc_set) + +BTF_ID_LIST(special_kfunc_list) +BTF_ID(func, bpf_obj_new_impl) + static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) { @@ -8465,17 +8485,59 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL); if (is_kfunc_acquire(&meta) && !btf_type_is_struct_ptr(meta.btf, t)) { - verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n"); - return -EINVAL; + /* Only exception is bpf_obj_new_impl */ + if (meta.btf != btf_vmlinux || meta.func_id != special_kfunc_list[KF_bpf_obj_new_impl]) { + verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n"); + return -EINVAL; + } } if (btf_type_is_scalar(t)) { mark_reg_unknown(env, regs, BPF_REG_0); mark_btf_func_reg_size(env, BPF_REG_0, t->size); } else if (btf_type_is_ptr(t)) { - ptr_type = btf_type_skip_modifiers(desc_btf, t->type, - &ptr_type_id); - if (!btf_type_is_struct(ptr_type)) { + ptr_type = btf_type_skip_modifiers(desc_btf, t->type, &ptr_type_id); + + if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) { + if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl]) { + const struct btf_type *ret_t; + struct btf *ret_btf; + u32 ret_btf_id; + + if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) { + verbose(env, "local type ID argument must be in range [0, U32_MAX]\n"); + return -EINVAL; + } + + ret_btf = env->prog->aux->btf; + ret_btf_id = meta.arg_constant.value; + + /* This may be NULL due to user not supplying a BTF */ + if (!ret_btf) { + verbose(env, "bpf_obj_new requires prog BTF\n"); + return -EINVAL; + } + + ret_t = btf_type_by_id(ret_btf, ret_btf_id); + if (!ret_t || !__btf_type_is_struct(ret_t)) { + verbose(env, "bpf_obj_new type ID argument must be of a struct\n"); + return -EINVAL; + } + + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC; + regs[BPF_REG_0].btf = ret_btf; + regs[BPF_REG_0].btf_id = ret_btf_id; + + env->insn_aux_data[insn_idx].obj_new_size = ret_t->size; + env->insn_aux_data[insn_idx].kptr_struct_meta = + btf_find_struct_meta(ret_btf, ret_btf_id); + } else { + verbose(env, "kernel function %s unhandled dynamic return type\n", + meta.func_name); + return -EFAULT; + } + } else if (!__btf_type_is_struct(ptr_type)) { if (!meta.r0_size) { ptr_type_name = btf_name_by_offset(desc_btf, ptr_type->name_off); @@ -8503,6 +8565,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, regs[BPF_REG_0].type = PTR_TO_BTF_ID; regs[BPF_REG_0].btf_id = ptr_type_id; } + if (is_kfunc_ret_null(&meta)) { regs[BPF_REG_0].type |= PTR_MAYBE_NULL; /* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */ @@ -14671,8 +14734,8 @@ static int fixup_call_args(struct bpf_verifier_env *env) return err; } -static int fixup_kfunc_call(struct bpf_verifier_env *env, - struct bpf_insn *insn) +static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, + struct bpf_insn *insn_buf, int insn_idx, int *cnt) { const struct bpf_kfunc_desc *desc; @@ -14691,8 +14754,21 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, return -EFAULT; } + *cnt = 0; insn->imm = desc->imm; + if (insn->off) + return 0; + if (desc->func_id == special_kfunc_list[KF_bpf_obj_new_impl]) { + struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta; + struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) }; + u64 obj_new_size = env->insn_aux_data[insn_idx].obj_new_size; + insn_buf[0] = BPF_MOV64_IMM(BPF_REG_1, obj_new_size); + insn_buf[1] = addr[0]; + insn_buf[2] = addr[1]; + insn_buf[3] = *insn; + *cnt = 4; + } return 0; } @@ -14834,9 +14910,19 @@ static int do_misc_fixups(struct bpf_verifier_env *env) if (insn->src_reg == BPF_PSEUDO_CALL) continue; if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { - ret = fixup_kfunc_call(env, insn); + ret = fixup_kfunc_call(env, insn, insn_buf, i + delta, &cnt); if (ret) return ret; + if (cnt == 0) + continue; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; continue; } diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h new file mode 100644 index 000000000000..aeb6a7fcb7c4 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -0,0 +1,25 @@ +#ifndef __BPF_EXPERIMENTAL__ +#define __BPF_EXPERIMENTAL__ + +#include +#include +#include +#include + +/* Description + * Allocates an object of the type represented by 'local_type_id' in + * program BTF. User may use the bpf_core_type_id_local macro to pass the + * type ID of a struct in program BTF. + * + * The 'local_type_id' parameter must be a known constant. + * The 'meta' parameter is a hidden argument that is ignored. + * Returns + * A pointer to an object of the type corresponding to the passed in + * 'local_type_id', or NULL on failure. + */ +extern void *bpf_obj_new_impl(__u64 local_type_id, void *meta) __ksym; + +/* Convenience macro to wrap over bpf_obj_new_impl */ +#define bpf_obj_new(type) ((type *)bpf_obj_new_impl(bpf_core_type_id_local(type), NULL)) + +#endif -- cgit v1.2.3 From 534e86bc6c66e1e0c798a1c0a6a680bb231c08db Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:26:07 +0530 Subject: bpf: Add 'release on unlock' logic for bpf_list_push_{front,back} This commit implements the delayed release logic for bpf_list_push_front and bpf_list_push_back. Once a node has been added to the list, it's pointer changes to PTR_UNTRUSTED. However, it is only released once the lock protecting the list is unlocked. For such PTR_TO_BTF_ID | MEM_ALLOC with PTR_UNTRUSTED set but an active ref_obj_id, it is still permitted to read them as long as the lock is held. Writing to them is not allowed. This allows having read access to push items we no longer own until we release the lock guarding the list, allowing a little more flexibility when working with these APIs. Note that enabling write support has fairly tricky interactions with what happens inside the critical section. Just as an example, currently, bpf_obj_drop is not permitted, but if it were, being able to write to the PTR_UNTRUSTED pointer while the object gets released back to the memory allocator would violate safety properties we wish to guarantee (i.e. not crashing the kernel). The memory could be reused for a different type in the BPF program or even in the kernel as it gets eventually kfree'd. Not enabling bpf_obj_drop inside the critical section would appear to prevent all of the above, but that is more of an artifical limitation right now. Since the write support is tangled with how we handle potential aliasing of nodes inside the critical section that may or may not be part of the list anymore, it has been deferred to a future patch. Acked-by: Dave Marchevsky Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-18-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 5 ++++ kernel/bpf/verifier.c | 58 +++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 62 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 3dc72d396dfc..23f30c685f28 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -223,6 +223,11 @@ struct bpf_reference_state { * exiting a callback function. */ int callback_ref; + /* Mark the reference state to release the registers sharing the same id + * on bpf_spin_unlock (for nodes that we will lose ownership to but are + * safe to access inside the critical section). + */ + bool release_on_unlock; }; /* state of the program: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1364df74129e..195d24316750 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5652,7 +5652,9 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, cur->active_lock.ptr = btf; cur->active_lock.id = reg->id; } else { + struct bpf_func_state *fstate = cur_func(env); void *ptr; + int i; if (map) ptr = map; @@ -5670,6 +5672,23 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, } cur->active_lock.ptr = NULL; cur->active_lock.id = 0; + + for (i = 0; i < fstate->acquired_refs; i++) { + int err; + + /* Complain on error because this reference state cannot + * be freed before this point, as bpf_spin_lock critical + * section does not allow functions that release the + * allocated object immediately. + */ + if (!fstate->refs[i].release_on_unlock) + continue; + err = release_reference(env, fstate->refs[i].id); + if (err) { + verbose(env, "failed to release release_on_unlock reference"); + return err; + } + } } return 0; } @@ -8260,6 +8279,42 @@ static int process_kf_arg_ptr_to_kptr(struct bpf_verifier_env *env, return 0; } +static int ref_set_release_on_unlock(struct bpf_verifier_env *env, u32 ref_obj_id) +{ + struct bpf_func_state *state = cur_func(env); + struct bpf_reg_state *reg; + int i; + + /* bpf_spin_lock only allows calling list_push and list_pop, no BPF + * subprogs, no global functions. This means that the references would + * not be released inside the critical section but they may be added to + * the reference state, and the acquired_refs are never copied out for a + * different frame as BPF to BPF calls don't work in bpf_spin_lock + * critical sections. + */ + if (!ref_obj_id) { + verbose(env, "verifier internal error: ref_obj_id is zero for release_on_unlock\n"); + return -EFAULT; + } + for (i = 0; i < state->acquired_refs; i++) { + if (state->refs[i].id == ref_obj_id) { + if (state->refs[i].release_on_unlock) { + verbose(env, "verifier internal error: expected false release_on_unlock"); + return -EFAULT; + } + state->refs[i].release_on_unlock = true; + /* Now mark everyone sharing same ref_obj_id as untrusted */ + bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ + if (reg->ref_obj_id == ref_obj_id) + reg->type |= PTR_UNTRUSTED; + })); + return 0; + } + } + verbose(env, "verifier internal error: ref state missing for ref_obj_id\n"); + return -EFAULT; +} + /* Implementation details: * * Each register points to some region of memory, which we define as an @@ -8433,7 +8488,8 @@ static int process_kf_arg_ptr_to_list_node(struct bpf_verifier_env *env, btf_name_by_offset(field->list_head.btf, et->name_off)); return -EINVAL; } - return 0; + /* Set arg#1 for expiration after unlock */ + return ref_set_release_on_unlock(env, reg->ref_obj_id); } static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta) -- cgit v1.2.3