diff options
Diffstat (limited to 'kernel/bpf')
| -rw-r--r-- | kernel/bpf/cgroup.c | 76 | ||||
| -rw-r--r-- | kernel/bpf/helpers.c | 25 | ||||
| -rw-r--r-- | kernel/bpf/local_storage.c | 169 | ||||
| -rw-r--r-- | kernel/bpf/map_in_map.c | 3 | ||||
| -rw-r--r-- | kernel/bpf/offload.c | 18 | ||||
| -rw-r--r-- | kernel/bpf/syscall.c | 20 | ||||
| -rw-r--r-- | kernel/bpf/verifier.c | 640 |
7 files changed, 767 insertions, 184 deletions
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 6a7d931bbc55..00f6ed2e4f9a 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -25,6 +25,7 @@ EXPORT_SYMBOL(cgroup_bpf_enabled_key); */ void cgroup_bpf_put(struct cgroup *cgrp) { + enum bpf_cgroup_storage_type stype; unsigned int type; for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) { @@ -34,8 +35,10 @@ void cgroup_bpf_put(struct cgroup *cgrp) list_for_each_entry_safe(pl, tmp, progs, node) { list_del(&pl->node); bpf_prog_put(pl->prog); - bpf_cgroup_storage_unlink(pl->storage); - bpf_cgroup_storage_free(pl->storage); + for_each_cgroup_storage_type(stype) { + bpf_cgroup_storage_unlink(pl->storage[stype]); + bpf_cgroup_storage_free(pl->storage[stype]); + } kfree(pl); static_branch_dec(&cgroup_bpf_enabled_key); } @@ -97,6 +100,7 @@ static int compute_effective_progs(struct cgroup *cgrp, enum bpf_attach_type type, struct bpf_prog_array __rcu **array) { + enum bpf_cgroup_storage_type stype; struct bpf_prog_array *progs; struct bpf_prog_list *pl; struct cgroup *p = cgrp; @@ -125,7 +129,9 @@ static int compute_effective_progs(struct cgroup *cgrp, continue; progs->items[cnt].prog = pl->prog; - progs->items[cnt].cgroup_storage = pl->storage; + for_each_cgroup_storage_type(stype) + progs->items[cnt].cgroup_storage[stype] = + pl->storage[stype]; cnt++; } } while ((p = cgroup_parent(p))); @@ -232,7 +238,9 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, { struct list_head *progs = &cgrp->bpf.progs[type]; struct bpf_prog *old_prog = NULL; - struct bpf_cgroup_storage *storage, *old_storage = NULL; + struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE], + *old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {NULL}; + enum bpf_cgroup_storage_type stype; struct bpf_prog_list *pl; bool pl_was_allocated; int err; @@ -254,34 +262,44 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) return -E2BIG; - storage = bpf_cgroup_storage_alloc(prog); - if (IS_ERR(storage)) - return -ENOMEM; + for_each_cgroup_storage_type(stype) { + storage[stype] = bpf_cgroup_storage_alloc(prog, stype); + if (IS_ERR(storage[stype])) { + storage[stype] = NULL; + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_free(storage[stype]); + return -ENOMEM; + } + } if (flags & BPF_F_ALLOW_MULTI) { list_for_each_entry(pl, progs, node) { if (pl->prog == prog) { /* disallow attaching the same prog twice */ - bpf_cgroup_storage_free(storage); + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_free(storage[stype]); return -EINVAL; } } pl = kmalloc(sizeof(*pl), GFP_KERNEL); if (!pl) { - bpf_cgroup_storage_free(storage); + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_free(storage[stype]); return -ENOMEM; } pl_was_allocated = true; pl->prog = prog; - pl->storage = storage; + for_each_cgroup_storage_type(stype) + pl->storage[stype] = storage[stype]; list_add_tail(&pl->node, progs); } else { if (list_empty(progs)) { pl = kmalloc(sizeof(*pl), GFP_KERNEL); if (!pl) { - bpf_cgroup_storage_free(storage); + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_free(storage[stype]); return -ENOMEM; } pl_was_allocated = true; @@ -289,12 +307,15 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, } else { pl = list_first_entry(progs, typeof(*pl), node); old_prog = pl->prog; - old_storage = pl->storage; - bpf_cgroup_storage_unlink(old_storage); + for_each_cgroup_storage_type(stype) { + old_storage[stype] = pl->storage[stype]; + bpf_cgroup_storage_unlink(old_storage[stype]); + } pl_was_allocated = false; } pl->prog = prog; - pl->storage = storage; + for_each_cgroup_storage_type(stype) + pl->storage[stype] = storage[stype]; } cgrp->bpf.flags[type] = flags; @@ -304,21 +325,27 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, goto cleanup; static_branch_inc(&cgroup_bpf_enabled_key); - if (old_storage) - bpf_cgroup_storage_free(old_storage); + for_each_cgroup_storage_type(stype) { + if (!old_storage[stype]) + continue; + bpf_cgroup_storage_free(old_storage[stype]); + } if (old_prog) { bpf_prog_put(old_prog); static_branch_dec(&cgroup_bpf_enabled_key); } - bpf_cgroup_storage_link(storage, cgrp, type); + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_link(storage[stype], cgrp, type); return 0; cleanup: /* and cleanup the prog list */ pl->prog = old_prog; - bpf_cgroup_storage_free(pl->storage); - pl->storage = old_storage; - bpf_cgroup_storage_link(old_storage, cgrp, type); + for_each_cgroup_storage_type(stype) { + bpf_cgroup_storage_free(pl->storage[stype]); + pl->storage[stype] = old_storage[stype]; + bpf_cgroup_storage_link(old_storage[stype], cgrp, type); + } if (pl_was_allocated) { list_del(&pl->node); kfree(pl); @@ -339,6 +366,7 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 unused_flags) { struct list_head *progs = &cgrp->bpf.progs[type]; + enum bpf_cgroup_storage_type stype; u32 flags = cgrp->bpf.flags[type]; struct bpf_prog *old_prog = NULL; struct bpf_prog_list *pl; @@ -385,8 +413,10 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, /* now can actually delete it from this cgroup list */ list_del(&pl->node); - bpf_cgroup_storage_unlink(pl->storage); - bpf_cgroup_storage_free(pl->storage); + for_each_cgroup_storage_type(stype) { + bpf_cgroup_storage_unlink(pl->storage[stype]); + bpf_cgroup_storage_free(pl->storage[stype]); + } kfree(pl); if (list_empty(progs)) /* last program was detached, reset flags to zero */ @@ -677,6 +707,8 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; + case BPF_FUNC_get_current_cgroup_id: + return &bpf_get_current_cgroup_id_proto; case BPF_FUNC_trace_printk: if (capable(CAP_SYS_ADMIN)) return bpf_get_trace_printk_proto(); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 1991466b8327..6502115e8f55 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -194,16 +194,28 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { .ret_type = RET_INTEGER, }; -DECLARE_PER_CPU(void*, bpf_cgroup_storage); +#ifdef CONFIG_CGROUP_BPF +DECLARE_PER_CPU(struct bpf_cgroup_storage*, + bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) { - /* map and flags arguments are not used now, - * but provide an ability to extend the API - * for other types of local storages. - * verifier checks that their values are correct. + /* flags argument is not used now, + * but provides an ability to extend the API. + * verifier checks that its value is correct. */ - return (unsigned long) this_cpu_read(bpf_cgroup_storage); + enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); + struct bpf_cgroup_storage *storage; + void *ptr; + + storage = this_cpu_read(bpf_cgroup_storage[stype]); + + if (stype == BPF_CGROUP_STORAGE_SHARED) + ptr = &READ_ONCE(storage->buf)->data[0]; + else + ptr = this_cpu_ptr(storage->percpu_buf); + + return (unsigned long)ptr; } const struct bpf_func_proto bpf_get_local_storage_proto = { @@ -214,3 +226,4 @@ const struct bpf_func_proto bpf_get_local_storage_proto = { .arg2_type = ARG_ANYTHING, }; #endif +#endif diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 830d7f095748..c97a8f968638 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -7,7 +7,8 @@ #include <linux/rbtree.h> #include <linux/slab.h> -DEFINE_PER_CPU(void*, bpf_cgroup_storage); +DEFINE_PER_CPU(struct bpf_cgroup_storage*, + bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); #ifdef CONFIG_CGROUP_BPF @@ -151,6 +152,71 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, return 0; } +int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *_key, + void *value) +{ + struct bpf_cgroup_storage_map *map = map_to_storage(_map); + struct bpf_cgroup_storage_key *key = _key; + struct bpf_cgroup_storage *storage; + int cpu, off = 0; + u32 size; + + rcu_read_lock(); + storage = cgroup_storage_lookup(map, key, false); + if (!storage) { + rcu_read_unlock(); + return -ENOENT; + } + + /* per_cpu areas are zero-filled and bpf programs can only + * access 'value_size' of them, so copying rounded areas + * will not leak any kernel data + */ + size = round_up(_map->value_size, 8); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(value + off, + per_cpu_ptr(storage->percpu_buf, cpu), size); + off += size; + } + rcu_read_unlock(); + return 0; +} + +int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *_key, + void *value, u64 map_flags) +{ + struct bpf_cgroup_storage_map *map = map_to_storage(_map); + struct bpf_cgroup_storage_key *key = _key; + struct bpf_cgroup_storage *storage; + int cpu, off = 0; + u32 size; + + if (map_flags != BPF_ANY && map_flags != BPF_EXIST) + return -EINVAL; + + rcu_read_lock(); + storage = cgroup_storage_lookup(map, key, false); + if (!storage) { + rcu_read_unlock(); + return -ENOENT; + } + + /* the user space will provide round_up(value_size, 8) bytes that + * will be copied into per-cpu area. bpf programs can only access + * value_size of it. During lookup the same extra bytes will be + * returned or zeros which were zero-filled by percpu_alloc, + * so no kernel data leaks possible + */ + size = round_up(_map->value_size, 8); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(per_cpu_ptr(storage->percpu_buf, cpu), + value + off, size); + off += size; + } + rcu_read_unlock(); + return 0; +} + static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key, void *_next_key) { @@ -254,6 +320,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = { int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) { + enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); struct bpf_cgroup_storage_map *map = map_to_storage(_map); int ret = -EBUSY; @@ -261,11 +328,12 @@ int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) if (map->prog && map->prog != prog) goto unlock; - if (prog->aux->cgroup_storage && prog->aux->cgroup_storage != _map) + if (prog->aux->cgroup_storage[stype] && + prog->aux->cgroup_storage[stype] != _map) goto unlock; map->prog = prog; - prog->aux->cgroup_storage = _map; + prog->aux->cgroup_storage[stype] = _map; ret = 0; unlock: spin_unlock_bh(&map->lock); @@ -275,70 +343,117 @@ unlock: void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map) { + enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); struct bpf_cgroup_storage_map *map = map_to_storage(_map); spin_lock_bh(&map->lock); if (map->prog == prog) { - WARN_ON(prog->aux->cgroup_storage != _map); + WARN_ON(prog->aux->cgroup_storage[stype] != _map); map->prog = NULL; - prog->aux->cgroup_storage = NULL; + prog->aux->cgroup_storage[stype] = NULL; } spin_unlock_bh(&map->lock); } -struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog) +static size_t bpf_cgroup_storage_calculate_size(struct bpf_map *map, u32 *pages) +{ + size_t size; + + if (cgroup_storage_type(map) == BPF_CGROUP_STORAGE_SHARED) { + size = sizeof(struct bpf_storage_buffer) + map->value_size; + *pages = round_up(sizeof(struct bpf_cgroup_storage) + size, + PAGE_SIZE) >> PAGE_SHIFT; + } else { + size = map->value_size; + *pages = round_up(round_up(size, 8) * num_possible_cpus(), + PAGE_SIZE) >> PAGE_SHIFT; + } + + return size; +} + +struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, + enum bpf_cgroup_storage_type stype) { struct bpf_cgroup_storage *storage; struct bpf_map *map; + gfp_t flags; + size_t size; u32 pages; - map = prog->aux->cgroup_storage; + map = prog->aux->cgroup_storage[stype]; if (!map) return NULL; - pages = round_up(sizeof(struct bpf_cgroup_storage) + - sizeof(struct bpf_storage_buffer) + - map->value_size, PAGE_SIZE) >> PAGE_SHIFT; + size = bpf_cgroup_storage_calculate_size(map, &pages); + if (bpf_map_charge_memlock(map, pages)) return ERR_PTR(-EPERM); storage = kmalloc_node(sizeof(struct bpf_cgroup_storage), __GFP_ZERO | GFP_USER, map->numa_node); - if (!storage) { - bpf_map_uncharge_memlock(map, pages); - return ERR_PTR(-ENOMEM); - } + if (!storage) + goto enomem; - storage->buf = kmalloc_node(sizeof(struct bpf_storage_buffer) + - map->value_size, __GFP_ZERO | GFP_USER, - map->numa_node); - if (!storage->buf) { - bpf_map_uncharge_memlock(map, pages); - kfree(storage); - return ERR_PTR(-ENOMEM); + flags = __GFP_ZERO | GFP_USER; + + if (stype == BPF_CGROUP_STORAGE_SHARED) { + storage->buf = kmalloc_node(size, flags, map->numa_node); + if (!storage->buf) + goto enomem; + } else { + storage->percpu_buf = __alloc_percpu_gfp(size, 8, flags); + if (!storage->percpu_buf) + goto enomem; } storage->map = (struct bpf_cgroup_storage_map *)map; return storage; + +enomem: + bpf_map_uncharge_memlock(map, pages); + kfree(storage); + return ERR_PTR(-ENOMEM); +} + +static void free_shared_cgroup_storage_rcu(struct rcu_head *rcu) +{ + struct bpf_cgroup_storage *storage = + container_of(rcu, struct bpf_cgroup_storage, rcu); + + kfree(storage->buf); + kfree(storage); +} + +static void free_percpu_cgroup_storage_rcu(struct rcu_head *rcu) +{ + struct bpf_cgroup_storage *storage = + container_of(rcu, struct bpf_cgroup_storage, rcu); + + free_percpu(storage->percpu_buf); + kfree(storage); } void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage) { - u32 pages; + enum bpf_cgroup_storage_type stype; struct bpf_map *map; + u32 pages; if (!storage) return; map = &storage->map->map; - pages = round_up(sizeof(struct bpf_cgroup_storage) + - sizeof(struct bpf_storage_buffer) + - map->value_size, PAGE_SIZE) >> PAGE_SHIFT; + + bpf_cgroup_storage_calculate_size(map, &pages); bpf_map_uncharge_memlock(map, pages); - kfree_rcu(storage->buf, rcu); - kfree_rcu(storage, rcu); + stype = cgroup_storage_type(map); + if (stype == BPF_CGROUP_STORAGE_SHARED) + call_rcu(&storage->rcu, free_shared_cgroup_storage_rcu); + else + call_rcu(&storage->rcu, free_percpu_cgroup_storage_rcu); } void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 3bfbf4464416..99d243e1ad6e 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -24,7 +24,8 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) * in the verifier is not enough. */ if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY || - inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE) { + inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || + inner_map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { fdput(f); return ERR_PTR(-ENOTSUPP); } diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 177a52436394..8e93c47f0779 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -172,6 +172,24 @@ int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, return ret; } +int bpf_prog_offload_finalize(struct bpf_verifier_env *env) +{ + struct bpf_prog_offload *offload; + int ret = -ENODEV; + + down_read(&bpf_devs_lock); + offload = env->prog->aux->offload; + if (offload) { + if (offload->dev_ops->finalize) + ret = offload->dev_ops->finalize(env); + else + ret = 0; + } + up_read(&bpf_devs_lock); + + return ret; +} + static void __bpf_prog_offload_destroy(struct bpf_prog *prog) { struct bpf_prog_offload *offload = prog->aux->offload; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b3c2d09bcf7a..5742df21598c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -686,7 +686,8 @@ static int map_lookup_elem(union bpf_attr *attr) if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) value_size = round_up(map->value_size, 8) * num_possible_cpus(); else if (IS_FD_MAP(map)) value_size = sizeof(u32); @@ -705,6 +706,8 @@ static int map_lookup_elem(union bpf_attr *attr) err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { + err = bpf_percpu_cgroup_storage_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { err = bpf_stackmap_copy(map, key, value); } else if (IS_FD_ARRAY(map)) { @@ -774,7 +777,8 @@ static int map_update_elem(union bpf_attr *attr) if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) value_size = round_up(map->value_size, 8) * num_possible_cpus(); else value_size = map->value_size; @@ -809,6 +813,9 @@ static int map_update_elem(union bpf_attr *attr) err = bpf_percpu_hash_update(map, key, value, attr->flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_update(map, key, value, attr->flags); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { + err = bpf_percpu_cgroup_storage_update(map, key, value, + attr->flags); } else if (IS_FD_ARRAY(map)) { rcu_read_lock(); err = bpf_fd_array_map_update_elem(map, f.file, key, value, @@ -988,10 +995,15 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) /* drop refcnt on maps used by eBPF program and free auxilary data */ static void free_used_maps(struct bpf_prog_aux *aux) { + enum bpf_cgroup_storage_type stype; int i; - if (aux->cgroup_storage) - bpf_cgroup_storage_release(aux->prog, aux->cgroup_storage); + for_each_cgroup_storage_type(stype) { + if (!aux->cgroup_storage[stype]) + continue; + bpf_cgroup_storage_release(aux->prog, + aux->cgroup_storage[stype]); + } for (i = 0; i < aux->used_map_cnt; i++) bpf_map_put(aux->used_maps[i]); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 3584ab27d25c..3f93a548a642 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1,5 +1,6 @@ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook + * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -80,8 +81,8 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { * (like pointer plus pointer becomes SCALAR_VALUE type) * * When verifier sees load or store instructions the type of base register - * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK. These are three pointer - * types recognized by check_mem_access() function. + * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK, PTR_TO_SOCKET. These are + * four pointer types recognized by check_mem_access() function. * * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value' * and the range of [ptr, ptr + map's value_size) is accessible. @@ -140,6 +141,24 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { * * After the call R0 is set to return type of the function and registers R1-R5 * are set to NOT_INIT to indicate that they are no longer readable. + * + * The following reference types represent a potential reference to a kernel + * resource which, after first being allocated, must be checked and freed by + * the BPF program: + * - PTR_TO_SOCKET_OR_NULL, PTR_TO_SOCKET + * + * When the verifier sees a helper call return a reference type, it allocates a + * pointer id for the reference and stores it in the current function state. + * Similar to the way that PTR_TO_MAP_VALUE_OR_NULL is converted into + * PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL becomes PTR_TO_SOCKET when the type + * passes through a NULL-check conditional. For the branch wherein the state is + * changed to CONST_IMM, the verifier releases the reference. + * + * For each helper function that allocates a reference, such as + * bpf_sk_lookup_tcp(), there is a corresponding release function, such as + * bpf_sk_release(). When a reference type passes into the release function, + * the verifier also releases the reference. If any unchecked or unreleased + * reference remains at the end of the program, the verifier rejects it. */ /* verifier_state + insn_idx are pushed to stack when branch is encountered */ @@ -189,6 +208,7 @@ struct bpf_call_arg_meta { int access_size; s64 msize_smax_value; u64 msize_umax_value; + int ptr_id; }; static DEFINE_MUTEX(bpf_verifier_lock); @@ -249,6 +269,46 @@ static bool type_is_pkt_pointer(enum bpf_reg_type type) type == PTR_TO_PACKET_META; } +static bool reg_type_may_be_null(enum bpf_reg_type type) +{ + return type == PTR_TO_MAP_VALUE_OR_NULL || + type == PTR_TO_SOCKET_OR_NULL; +} + +static bool type_is_refcounted(enum bpf_reg_type type) +{ + return type == PTR_TO_SOCKET; +} + +static bool type_is_refcounted_or_null(enum bpf_reg_type type) +{ + return type == PTR_TO_SOCKET || type == PTR_TO_SOCKET_OR_NULL; +} + +static bool reg_is_refcounted(const struct bpf_reg_state *reg) +{ + return type_is_refcounted(reg->type); +} + +static bool reg_is_refcounted_or_null(const struct bpf_reg_state *reg) +{ + return type_is_refcounted_or_null(reg->type); +} + +static bool arg_type_is_refcounted(enum bpf_arg_type type) +{ + return type == ARG_PTR_TO_SOCKET; +} + +/* Determine whether the function releases some resources allocated by another + * function call. The first reference type argument will be assumed to be + * released by release_reference(). + */ +static bool is_release_function(enum bpf_func_id func_id) +{ + return func_id == BPF_FUNC_sk_release; +} + /* string representation of 'enum bpf_reg_type' */ static const char * const reg_type_str[] = { [NOT_INIT] = "?", @@ -262,6 +322,8 @@ static const char * const reg_type_str[] = { [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", [PTR_TO_FLOW_KEYS] = "flow_keys", + [PTR_TO_SOCKET] = "sock", + [PTR_TO_SOCKET_OR_NULL] = "sock_or_null", }; static char slot_type_char[] = { @@ -378,62 +440,158 @@ static void print_verifier_state(struct bpf_verifier_env *env, else verbose(env, "=%s", types_buf); } + if (state->acquired_refs && state->refs[0].id) { + verbose(env, " refs=%d", state->refs[0].id); + for (i = 1; i < state->acquired_refs; i++) + if (state->refs[i].id) + verbose(env, ",%d", state->refs[i].id); + } verbose(env, "\n"); } -static int copy_stack_state(struct bpf_func_state *dst, - const struct bpf_func_state *src) -{ - if (!src->stack) - return 0; - if (WARN_ON_ONCE(dst->allocated_stack < src->allocated_stack)) { - /* internal bug, make state invalid to reject the program */ - memset(dst, 0, sizeof(*dst)); - return -EFAULT; - } - memcpy(dst->stack, src->stack, - sizeof(*src->stack) * (src->allocated_stack / BPF_REG_SIZE)); - return 0; -} +#define COPY_STATE_FN(NAME, COUNT, FIELD, SIZE) \ +static int copy_##NAME##_state(struct bpf_func_state *dst, \ + const struct bpf_func_state *src) \ +{ \ + if (!src->FIELD) \ + return 0; \ + if (WARN_ON_ONCE(dst->COUNT < src->COUNT)) { \ + /* internal bug, make state invalid to reject the program */ \ + memset(dst, 0, sizeof(*dst)); \ + return -EFAULT; \ + } \ + memcpy(dst->FIELD, src->FIELD, \ + sizeof(*src->FIELD) * (src->COUNT / SIZE)); \ + return 0; \ +} +/* copy_reference_state() */ +COPY_STATE_FN(reference, acquired_refs, refs, 1) +/* copy_stack_state() */ +COPY_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE) +#undef COPY_STATE_FN + +#define REALLOC_STATE_FN(NAME, COUNT, FIELD, SIZE) \ +static int realloc_##NAME##_state(struct bpf_func_state *state, int size, \ + bool copy_old) \ +{ \ + u32 old_size = state->COUNT; \ + struct bpf_##NAME##_state *new_##FIELD; \ + int slot = size / SIZE; \ + \ + if (size <= old_size || !size) { \ + if (copy_old) \ + return 0; \ + state->COUNT = slot * SIZE; \ + if (!size && old_size) { \ + kfree(state->FIELD); \ + state->FIELD = NULL; \ + } \ + return 0; \ + } \ + new_##FIELD = kmalloc_array(slot, sizeof(struct bpf_##NAME##_state), \ + GFP_KERNEL); \ + if (!new_##FIELD) \ + return -ENOMEM; \ + if (copy_old) { \ + if (state->FIELD) \ + memcpy(new_##FIELD, state->FIELD, \ + sizeof(*new_##FIELD) * (old_size / SIZE)); \ + memset(new_##FIELD + old_size / SIZE, 0, \ + sizeof(*new_##FIELD) * (size - old_size) / SIZE); \ + } \ + state->COUNT = slot * SIZE; \ + kfree(state->FIELD); \ + state->FIELD = new_##FIELD; \ + return 0; \ +} +/* realloc_reference_state() */ +REALLOC_STATE_FN(reference, acquired_refs, refs, 1) +/* realloc_stack_state() */ +REALLOC_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE) +#undef REALLOC_STATE_FN /* do_check() starts with zero-sized stack in struct bpf_verifier_state to * make it consume minimal amount of memory. check_stack_write() access from * the program calls into realloc_func_state() to grow the stack size. - * Note there is a non-zero parent pointer inside each reg of bpf_verifier_state - * which this function copies over. It points to corresponding reg in previous - * bpf_verifier_state which is never reallocated + * Note there is a non-zero 'parent' pointer inside bpf_verifier_state + * which realloc_stack_state() copies over. It points to previous + * bpf_verifier_state which is never reallocated. + */ +static int realloc_func_state(struct bpf_func_state *state, int stack_size, + int refs_size, bool copy_old) +{ + int err = realloc_reference_state(state, refs_size, copy_old); + if (err) + return err; + return realloc_stack_state(state, stack_size, copy_old); +} + +/* Acquire a pointer id from the env and update the state->refs to include + * this new pointer reference. + * On success, returns a valid pointer id to associate with the register + * On failure, returns a negative errno. */ -static int realloc_func_state(struct bpf_func_state *state, int size, - bool copy_old) +static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx) { - u32 old_size = state->allocated_stack; - struct bpf_stack_state *new_stack; - int slot = size / BPF_REG_SIZE; + struct bpf_func_state *state = cur_func(env); + int new_ofs = state->acquired_refs; + int id, err; + + err = realloc_reference_state(state, state->acquired_refs + 1, true); + if (err) + return err; + id = ++env->id_gen; + state->refs[new_ofs].id = id; + state->refs[new_ofs].insn_idx = insn_idx; - if (size <= old_size || !size) { - if (copy_old) + return id; +} + +/* release function corresponding to acquire_reference_state(). Idempotent. */ +static int __release_reference_state(struct bpf_func_state *state, int ptr_id) +{ + int i, last_idx; + + if (!ptr_id) + return -EFAULT; + + last_idx = state->acquired_refs - 1; + for (i = 0; i < state->acquired_refs; i++) { + if (state->refs[i].id == ptr_id) { + if (last_idx && i != last_idx) + memcpy(&state->refs[i], &state->refs[last_idx], + sizeof(*state->refs)); + memset(&state->refs[last_idx], 0, sizeof(*state->refs)); + state->acquired_refs--; return 0; - state->allocated_stack = slot * BPF_REG_SIZE; - if (!size && old_size) { - kfree(state->stack); - state->stack = NULL; } - return 0; } - new_stack = kmalloc_array(slot, sizeof(struct bpf_stack_state), - GFP_KERNEL); - if (!new_stack) - return -ENOMEM; - if (copy_old) { - if (state->stack) - memcpy(new_stack, state->stack, - sizeof(*new_stack) * (old_size / BPF_REG_SIZE)); - memset(new_stack + old_size / BPF_REG_SIZE, 0, - sizeof(*new_stack) * (size - old_size) / BPF_REG_SIZE); - } - state->allocated_stack = slot * BPF_REG_SIZE; - kfree(state->stack); - state->stack = new_stack; + return -EFAULT; +} + +/* variation on the above for cases where we expect that there must be an + * outstanding reference for the specified ptr_id. + */ +static int release_reference_state(struct bpf_verifier_env *env, int ptr_id) +{ + struct bpf_func_state *state = cur_func(env); + int err; + + err = __release_reference_state(state, ptr_id); + if (WARN_ON_ONCE(err != 0)) + verbose(env, "verifier internal error: can't release reference\n"); + return err; +} + +static int transfer_reference_state(struct bpf_func_state *dst, + struct bpf_func_state *src) +{ + int err = realloc_reference_state(dst, src->acquired_refs, false); + if (err) + return err; + err = copy_reference_state(dst, src); + if (err) + return err; return 0; } @@ -441,6 +599,7 @@ static void free_func_state(struct bpf_func_state *state) { if (!state) return; + kfree(state->refs); kfree(state->stack); kfree(state); } @@ -466,10 +625,14 @@ static int copy_func_state(struct bpf_func_state *dst, { int err; - err = realloc_func_state(dst, src->allocated_stack, false); + err = realloc_func_state(dst, src->allocated_stack, src->acquired_refs, + false); + if (err) + return err; + memcpy(dst, src, offsetof(struct bpf_func_state, acquired_refs)); + err = copy_reference_state(dst, src); if (err) return err; - memcpy(dst, src, offsetof(struct bpf_func_state, allocated_stack)); return copy_stack_state(dst, src); } @@ -846,10 +1009,6 @@ static int check_subprogs(struct bpf_verifier_env *env) verbose(env, "function calls to other bpf functions are allowed for root only\n"); return -EPERM; } - if (bpf_prog_is_dev_bound(env->prog->aux)) { - verbose(env, "function calls in offloaded programs are not supported yet\n"); - return -EINVAL; - } ret = add_subprog(env, i + insn[i].imm + 1); if (ret < 0) return ret; @@ -968,6 +1127,8 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_PACKET_END: case PTR_TO_FLOW_KEYS: case CONST_PTR_TO_MAP: + case PTR_TO_SOCKET: + case PTR_TO_SOCKET_OR_NULL: return true; default: return false; @@ -992,7 +1153,7 @@ static int check_stack_write(struct bpf_verifier_env *env, enum bpf_reg_type type; err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE), - true); + state->acquired_refs, true); if (err) return err; /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, @@ -1336,6 +1497,28 @@ static int check_flow_keys_access(struct bpf_verifier_env *env, int off, return 0; } +static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off, + int size, enum bpf_access_type t) +{ + struct bpf_reg_state *regs = cur_regs(env); + struct bpf_reg_state *reg = ®s[regno]; + struct bpf_insn_access_aux info; + + if (reg->smin_value < 0) { + verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", + regno); + return -EACCES; + } + + if (!bpf_sock_is_valid_access(off, size, t, &info)) { + verbose(env, "invalid bpf_sock access off=%d size=%d\n", + off, size); + return -EACCES; + } + + return 0; +} + static bool __is_pointer_value(bool allow_ptr_leaks, const struct bpf_reg_state *reg) { @@ -1354,7 +1537,8 @@ static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = cur_regs(env) + regno; - return reg->type == PTR_TO_CTX; + return reg->type == PTR_TO_CTX || + reg->type == PTR_TO_SOCKET; } static bool is_pkt_reg(struct bpf_verifier_env *env, int regno) @@ -1454,6 +1638,9 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, */ strict = true; break; + case PTR_TO_SOCKET: + pointer_desc = "sock "; + break; default: break; } @@ -1721,6 +1908,14 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_flow_keys_access(env, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); + } else if (reg->type == PTR_TO_SOCKET) { + if (t == BPF_WRITE) { + verbose(env, "cannot write into socket\n"); + return -EACCES; + } + err = check_sock_access(env, regno, off, size, t); + if (!err && value_regno >= 0) + mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str[reg->type]); @@ -1763,8 +1958,7 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins if (is_ctx_reg(env, insn->dst_reg) || is_pkt_reg(env, insn->dst_reg)) { verbose(env, "BPF_XADD stores into R%d %s is not allowed\n", - insn->dst_reg, is_ctx_reg(env, insn->dst_reg) ? - "context" : "packet"); + insn->dst_reg, reg_type_str[insn->dst_reg]); return -EACCES; } @@ -1944,6 +2138,16 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, err = check_ctx_reg(env, reg, regno); if (err < 0) return err; + } else if (arg_type == ARG_PTR_TO_SOCKET) { + expected_type = PTR_TO_SOCKET; + if (type != expected_type) + goto err_type; + if (meta->ptr_id || !reg->id) { + verbose(env, "verifier internal error: mismatched references meta=%d, reg=%d\n", + meta->ptr_id, reg->id); + return -EFAULT; + } + meta->ptr_id = reg->id; } else if (arg_type_is_mem_ptr(arg_type)) { expected_type = PTR_TO_STACK; /* One exception here. In case function allows for NULL to be @@ -2074,6 +2278,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_MAP_TYPE_CGROUP_STORAGE: + case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: if (func_id != BPF_FUNC_get_local_storage) goto error; break; @@ -2164,7 +2369,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_FUNC_get_local_storage: - if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE) + if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && + map->map_type != BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) goto error; break; case BPF_FUNC_sk_select_reuseport: @@ -2231,10 +2437,32 @@ static bool check_arg_pair_ok(const struct bpf_func_proto *fn) return true; } +static bool check_refcount_ok(const struct bpf_func_proto *fn) +{ + int count = 0; + + if (arg_type_is_refcounted(fn->arg1_type)) + count++; + if (arg_type_is_refcounted(fn->arg2_type)) + count++; + if (arg_type_is_refcounted(fn->arg3_type)) + count++; + if (arg_type_is_refcounted(fn->arg4_type)) + count++; + if (arg_type_is_refcounted(fn->arg5_type)) + count++; + + /* We only support one arg being unreferenced at the moment, + * which is sufficient for the helper functions we have right now. + */ + return count <= 1; +} + static int check_func_proto(const struct bpf_func_proto *fn) { return check_raw_mode_ok(fn) && - check_arg_pair_ok(fn) ? 0 : -EINVAL; + check_arg_pair_ok(fn) && + check_refcount_ok(fn) ? 0 : -EINVAL; } /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] @@ -2250,10 +2478,9 @@ static void __clear_all_pkt_pointers(struct bpf_verifier_env *env, if (reg_is_pkt_pointer_any(®s[i])) mark_reg_unknown(env, regs, i); - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) continue; - reg = &state->stack[i].spilled_ptr; if (reg_is_pkt_pointer_any(reg)) __mark_reg_unknown(reg); } @@ -2268,12 +2495,45 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) __clear_all_pkt_pointers(env, vstate->frame[i]); } +static void release_reg_references(struct bpf_verifier_env *env, + struct bpf_func_state *state, int id) +{ + struct bpf_reg_state *regs = state->regs, *reg; + int i; + + for (i = 0; i < MAX_BPF_REG; i++) + if (regs[i].id == id) + mark_reg_unknown(env, regs, i); + + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) + continue; + if (reg_is_refcounted(reg) && reg->id == id) + __mark_reg_unknown(reg); + } +} + +/* The pointer with the specified id has released its reference to kernel + * resources. Identify all copies of the same pointer and clear the reference. + */ +static int release_reference(struct bpf_verifier_env *env, + struct bpf_call_arg_meta *meta) +{ + struct bpf_verifier_state *vstate = env->cur_state; + int i; + + for (i = 0; i <= vstate->curframe; i++) + release_reg_references(env, vstate->frame[i], meta->ptr_id); + + return release_reference_state(env, meta->ptr_id); +} + static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state; struct bpf_func_state *caller, *callee; - int i, subprog, target_insn; + int i, err, subprog, target_insn; if (state->curframe + 1 >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep\n", @@ -2311,6 +2571,11 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, state->curframe + 1 /* frameno within this callchain */, subprog /* subprog number within this prog */); + /* Transfer references to the callee */ + err = transfer_reference_state(callee, caller); + if (err) + return err; + /* copy r1 - r5 args that callee can access. The copy includes parent * pointers, which connects us up to the liveness chain */ @@ -2343,6 +2608,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) struct bpf_verifier_state *state = env->cur_state; struct bpf_func_state *caller, *callee; struct bpf_reg_state *r0; + int err; callee = state->frame[state->curframe]; r0 = &callee->regs[BPF_REG_0]; @@ -2362,6 +2628,11 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) /* return to the caller whatever r0 had in the callee */ caller->regs[BPF_REG_0] = *r0; + /* Transfer references to the caller */ + err = transfer_reference_state(caller, callee); + if (err) + return err; + *insn_idx = callee->callsite + 1; if (env->log.level) { verbose(env, "returning from callee:\n"); @@ -2418,6 +2689,18 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, return 0; } +static int check_reference_leak(struct bpf_verifier_env *env) +{ + struct bpf_func_state *state = cur_func(env); + int i; + + for (i = 0; i < state->acquired_refs; i++) { + verbose(env, "Unreleased reference id=%d alloc_insn=%d\n", + state->refs[i].id, state->refs[i].insn_idx); + } + return state->acquired_refs ? -EINVAL : 0; +} + static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx) { const struct bpf_func_proto *fn = NULL; @@ -2496,6 +2779,18 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return err; } + if (func_id == BPF_FUNC_tail_call) { + err = check_reference_leak(env); + if (err) { + verbose(env, "tail_call would lead to reference leak\n"); + return err; + } + } else if (is_release_function(func_id)) { + err = release_reference(env, &meta); + if (err) + return err; + } + regs = cur_regs(env); /* check that flags argument in get_local_storage(map, flags) is 0, @@ -2538,6 +2833,13 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn } regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].id = ++env->id_gen; + } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) { + int id = acquire_reference_state(env, insn_idx); + if (id < 0) + return id; + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL; + regs[BPF_REG_0].id = id; } else { verbose(env, "unknown return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); @@ -2668,20 +2970,20 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return -EACCES; } - if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) { - verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n", - dst); - return -EACCES; - } - if (ptr_reg->type == CONST_PTR_TO_MAP) { - verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n", - dst); + switch (ptr_reg->type) { + case PTR_TO_MAP_VALUE_OR_NULL: + verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n", + dst, reg_type_str[ptr_reg->type]); return -EACCES; - } - if (ptr_reg->type == PTR_TO_PACKET_END) { - verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n", - dst); + case CONST_PTR_TO_MAP: + case PTR_TO_PACKET_END: + case PTR_TO_SOCKET: + case PTR_TO_SOCKET_OR_NULL: + verbose(env, "R%d pointer arithmetic on %s prohibited\n", + dst, reg_type_str[ptr_reg->type]); return -EACCES; + default: + break; } /* In case of 'scalar += pointer', dst_reg inherits pointer type and id. @@ -3401,10 +3703,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, for (j = 0; j <= vstate->curframe; j++) { state = vstate->frame[j]; - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) continue; - reg = &state->stack[i].spilled_ptr; if (reg->type == type && reg->id == dst_reg->id) reg->range = max(reg->range, new_range); } @@ -3610,12 +3911,11 @@ static void reg_combine_min_max(struct bpf_reg_state *true_src, } } -static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id, - bool is_null) +static void mark_ptr_or_null_reg(struct bpf_func_state *state, + struct bpf_reg_state *reg, u32 id, + bool is_null) { - struct bpf_reg_state *reg = ®s[regno]; - - if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) { + if (reg_type_may_be_null(reg->type) && reg->id == id) { /* Old offset (both fixed and variable parts) should * have been known-zero, because we don't allow pointer * arithmetic on pointers that might be NULL. @@ -3628,40 +3928,49 @@ static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id, } if (is_null) { reg->type = SCALAR_VALUE; - } else if (reg->map_ptr->inner_map_meta) { - reg->type = CONST_PTR_TO_MAP; - reg->map_ptr = reg->map_ptr->inner_map_meta; - } else { - reg->type = PTR_TO_MAP_VALUE; + } else if (reg->type == PTR_TO_MAP_VALUE_OR_NULL) { + if (reg->map_ptr->inner_map_meta) { + reg->type = CONST_PTR_TO_MAP; + reg->map_ptr = reg->map_ptr->inner_map_meta; + } else { + reg->type = PTR_TO_MAP_VALUE; + } + } else if (reg->type == PTR_TO_SOCKET_OR_NULL) { + reg->type = PTR_TO_SOCKET; + } + if (is_null || !reg_is_refcounted(reg)) { + /* We don't need id from this point onwards anymore, + * thus we should better reset it, so that state + * pruning has chances to take effect. + */ + reg->id = 0; } - /* We don't need id from this point onwards anymore, thus we - * should better reset it, so that state pruning has chances - * to take effect. - */ - reg->id = 0; } } /* The logic is similar to find_good_pkt_pointers(), both could eventually * be folded together at some point. */ -static void mark_map_regs(struct bpf_verifier_state *vstate, u32 regno, - bool is_null) +static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, + bool is_null) { struct bpf_func_state *state = vstate->frame[vstate->curframe]; - struct bpf_reg_state *regs = state->regs; + struct bpf_reg_state *reg, *regs = state->regs; u32 id = regs[regno].id; int i, j; + if (reg_is_refcounted_or_null(®s[regno]) && is_null) + __release_reference_state(state, id); + for (i = 0; i < MAX_BPF_REG; i++) - mark_map_reg(regs, i, id, is_null); + mark_ptr_or_null_reg(state, ®s[i], id, is_null); for (j = 0; j <= vstate->curframe; j++) { state = vstate->frame[j]; - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) continue; - mark_map_reg(&state->stack[i].spilled_ptr, 0, id, is_null); + mark_ptr_or_null_reg(state, reg, id, is_null); } } } @@ -3863,12 +4172,14 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, /* detect if R == 0 where R is returned from bpf_map_lookup_elem() */ if (BPF_SRC(insn->code) == BPF_K && insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) && - dst_reg->type == PTR_TO_MAP_VALUE_OR_NULL) { - /* Mark all identical map registers in each branch as either + reg_type_may_be_null(dst_reg->type)) { + /* Mark all identical registers in each branch as either * safe or unknown depending R == 0 or R != 0 conditional. */ - mark_map_regs(this_branch, insn->dst_reg, opcode == BPF_JNE); - mark_map_regs(other_branch, insn->dst_reg, opcode == BPF_JEQ); + mark_ptr_or_null_regs(this_branch, insn->dst_reg, + opcode == BPF_JNE); + mark_ptr_or_null_regs(other_branch, insn->dst_reg, + opcode == BPF_JEQ); } else if (!try_match_pkt_pointers(insn, dst_reg, ®s[insn->src_reg], this_branch, other_branch) && is_pointer_value(env, insn->dst_reg)) { @@ -3991,6 +4302,16 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) if (err) return err; + /* Disallow usage of BPF_LD_[ABS|IND] with reference tracking, as + * gen_ld_abs() may terminate the program at runtime, leading to + * reference leak. + */ + err = check_reference_leak(env); + if (err) { + verbose(env, "BPF_LD_[ABS|IND] cannot be mixed with socket references\n"); + return err; + } + if (regs[BPF_REG_6].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); @@ -4406,6 +4727,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, case CONST_PTR_TO_MAP: case PTR_TO_PACKET_END: case PTR_TO_FLOW_KEYS: + case PTR_TO_SOCKET: + case PTR_TO_SOCKET_OR_NULL: /* Only valid matches are exact, which memcmp() above * would have accepted */ @@ -4481,6 +4804,14 @@ static bool stacksafe(struct bpf_func_state *old, return true; } +static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur) +{ + if (old->acquired_refs != cur->acquired_refs) + return false; + return !memcmp(old->refs, cur->refs, + sizeof(*old->refs) * old->acquired_refs); +} + /* compare two verifier states * * all states stored in state_list are known to be valid, since @@ -4526,6 +4857,9 @@ static bool func_states_equal(struct bpf_func_state *old, if (!stacksafe(old, cur, idmap)) goto out_free; + + if (!refsafe(old, cur)) + goto out_free; ret = true; out_free: kfree(idmap); @@ -4683,6 +5017,37 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return 0; } +/* Return true if it's OK to have the same insn return a different type. */ +static bool reg_type_mismatch_ok(enum bpf_reg_type type) +{ + switch (type) { + case PTR_TO_CTX: + case PTR_TO_SOCKET: + case PTR_TO_SOCKET_OR_NULL: + return false; + default: + return true; + } +} + +/* If an instruction was previously used with particular pointer types, then we + * need to be careful to avoid cases such as the below, where it may be ok + * for one branch accessing the pointer, but not ok for the other branch: + * + * R1 = sock_ptr + * goto X; + * ... + * R1 = some_other_valid_ptr; + * goto X; + * ... + * R2 = *(u32 *)(R1 + 0); + */ +static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev) +{ + return src != prev && (!reg_type_mismatch_ok(src) || + !reg_type_mismatch_ok(prev)); +} + static int do_check(struct bpf_verifier_env *env) { struct bpf_verifier_state *state; @@ -4776,6 +5141,7 @@ static int do_check(struct bpf_verifier_env *env) regs = cur_regs(env); env->insn_aux_data[insn_idx].seen = true; + if (class == BPF_ALU || class == BPF_ALU64) { err = check_alu_op(env, insn); if (err) @@ -4815,9 +5181,7 @@ static int do_check(struct bpf_verifier_env *env) */ *prev_src_type = src_reg_type; - } else if (src_reg_type != *prev_src_type && - (src_reg_type == PTR_TO_CTX || - *prev_src_type == PTR_TO_CTX)) { + } else if (reg_type_mismatch(src_reg_type, *prev_src_type)) { /* ABuser program is trying to use the same insn * dst_reg = *(u32*) (src_reg + off) * with different pointer types: @@ -4862,9 +5226,7 @@ static int do_check(struct bpf_verifier_env *env) if (*prev_dst_type == NOT_INIT) { *prev_dst_type = dst_reg_type; - } else if (dst_reg_type != *prev_dst_type && - (dst_reg_type == PTR_TO_CTX || - *prev_dst_type == PTR_TO_CTX)) { + } else if (reg_type_mismatch(dst_reg_type, *prev_dst_type)) { verbose(env, "same insn cannot be used with different pointers\n"); return -EINVAL; } @@ -4881,8 +5243,8 @@ static int do_check(struct bpf_verifier_env *env) return err; if (is_ctx_reg(env, insn->dst_reg)) { - verbose(env, "BPF_ST stores into R%d context is not allowed\n", - insn->dst_reg); + verbose(env, "BPF_ST stores into R%d %s is not allowed\n", + insn->dst_reg, reg_type_str[insn->dst_reg]); return -EACCES; } @@ -4944,6 +5306,10 @@ static int do_check(struct bpf_verifier_env *env) continue; } + err = check_reference_leak(env); + if (err) + return err; + /* eBPF calling convetion is such that R0 is used * to return the value from eBPF program. * Make sure that it's readable at this time @@ -5057,6 +5423,12 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, return 0; } +static bool bpf_map_is_cgroup_storage(struct bpf_map *map) +{ + return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); +} + /* look for pseudo eBPF instructions that access map FDs and * replace them with actual map pointers */ @@ -5147,10 +5519,9 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) } env->used_maps[env->used_map_cnt++] = map; - if (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE && + if (bpf_map_is_cgroup_storage(map) && bpf_cgroup_storage_assign(env->prog, map)) { - verbose(env, - "only one cgroup storage is allowed\n"); + verbose(env, "only one cgroup storage of each type is allowed\n"); fdput(f); return -EBUSY; } @@ -5179,11 +5550,15 @@ next_insn: /* drop refcnt of maps used by the rejected program */ static void release_maps(struct bpf_verifier_env *env) { + enum bpf_cgroup_storage_type stype; int i; - if (env->prog->aux->cgroup_storage) + for_each_cgroup_storage_type(stype) { + if (!env->prog->aux->cgroup_storage[stype]) + continue; bpf_cgroup_storage_release(env->prog, - env->prog->aux->cgroup_storage); + env->prog->aux->cgroup_storage[stype]); + } for (i = 0; i < env->used_map_cnt; i++) bpf_map_put(env->used_maps[i]); @@ -5281,8 +5656,10 @@ static void sanitize_dead_code(struct bpf_verifier_env *env) } } -/* convert load instructions that access fields of 'struct __sk_buff' - * into sequence of instructions that access fields of 'struct sk_buff' +/* convert load instructions that access fields of a context type into a + * sequence of instructions that access fields of the underlying structure: + * struct __sk_buff -> struct sk_buff + * struct bpf_sock_ops -> struct sock */ static int convert_ctx_accesses(struct bpf_verifier_env *env) { @@ -5311,12 +5688,14 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } } - if (!ops->convert_ctx_access || bpf_prog_is_dev_bound(env->prog->aux)) + if (bpf_prog_is_dev_bound(env->prog->aux)) return 0; insn = env->prog->insnsi + delta; for (i = 0; i < insn_cnt; i++, insn++) { + bpf_convert_ctx_access_t convert_ctx_access; + if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) || insn->code == (BPF_LDX | BPF_MEM | BPF_H) || insn->code == (BPF_LDX | BPF_MEM | BPF_W) || @@ -5358,8 +5737,18 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) continue; } - if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX) + switch (env->insn_aux_data[i + delta].ptr_type) { + case PTR_TO_CTX: + if (!ops->convert_ctx_access) + continue; + convert_ctx_access = ops->convert_ctx_access; + break; + case PTR_TO_SOCKET: + convert_ctx_access = bpf_sock_convert_ctx_access; + break; + default: continue; + } ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size; size = BPF_LDST_BYTES(insn); @@ -5391,8 +5780,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } target_size = 0; - cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog, - &target_size); + cnt = convert_ctx_access(type, insn, insn_buf, env->prog, + &target_size); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) || (ctx_field_size && !target_size)) { verbose(env, "bpf verifier is misconfigured\n"); @@ -5583,10 +5972,10 @@ static int fixup_call_args(struct bpf_verifier_env *env) struct bpf_insn *insn = prog->insnsi; int i, depth; #endif - int err; + int err = 0; - err = 0; - if (env->prog->jit_requested) { + if (env->prog->jit_requested && + !bpf_prog_is_dev_bound(env->prog->aux)) { err = jit_subprogs(env); if (err == 0) return 0; @@ -5924,6 +6313,9 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) env->cur_state = NULL; } + if (ret == 0 && bpf_prog_is_dev_bound(env->prog->aux)) + ret = bpf_prog_offload_finalize(env); + skip_full_check: while (!pop_stack(env, NULL, NULL)); free_states(env); |