| // SPDX-License-Identifier: GPL-2.0-only |
| /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com |
| */ |
| #include <linux/bpf.h> |
| #include <linux/bpf-cgroup.h> |
| #include <linux/bpf_trace.h> |
| #include <linux/bpf_lirc.h> |
| #include <linux/bpf_verifier.h> |
| #include <linux/bsearch.h> |
| #include <linux/btf.h> |
| #include <linux/syscalls.h> |
| #include <linux/slab.h> |
| #include <linux/sched/signal.h> |
| #include <linux/vmalloc.h> |
| #include <linux/mmzone.h> |
| #include <linux/anon_inodes.h> |
| #include <linux/fdtable.h> |
| #include <linux/file.h> |
| #include <linux/fs.h> |
| #include <linux/license.h> |
| #include <linux/filter.h> |
| #include <linux/kernel.h> |
| #include <linux/idr.h> |
| #include <linux/cred.h> |
| #include <linux/timekeeping.h> |
| #include <linux/ctype.h> |
| #include <linux/nospec.h> |
| #include <linux/audit.h> |
| #include <uapi/linux/btf.h> |
| #include <linux/pgtable.h> |
| #include <linux/bpf_lsm.h> |
| #include <linux/poll.h> |
| #include <linux/sort.h> |
| #include <linux/bpf-netns.h> |
| #include <linux/rcupdate_trace.h> |
| #include <linux/memcontrol.h> |
| #include <linux/trace_events.h> |
| |
| #include <trace/hooks/syscall_check.h> |
| |
| #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ |
| (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ |
| (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) |
| #define IS_FD_PROG_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY) |
| #define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) |
| #define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map) || \ |
| IS_FD_HASH(map)) |
| |
| #define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) |
| |
| DEFINE_PER_CPU(int, bpf_prog_active); |
| static DEFINE_IDR(prog_idr); |
| static DEFINE_SPINLOCK(prog_idr_lock); |
| static DEFINE_IDR(map_idr); |
| static DEFINE_SPINLOCK(map_idr_lock); |
| static DEFINE_IDR(link_idr); |
| static DEFINE_SPINLOCK(link_idr_lock); |
| |
| int sysctl_unprivileged_bpf_disabled __read_mostly = |
| IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0; |
| |
| static const struct bpf_map_ops * const bpf_map_types[] = { |
| #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) |
| #define BPF_MAP_TYPE(_id, _ops) \ |
| [_id] = &_ops, |
| #define BPF_LINK_TYPE(_id, _name) |
| #include <linux/bpf_types.h> |
| #undef BPF_PROG_TYPE |
| #undef BPF_MAP_TYPE |
| #undef BPF_LINK_TYPE |
| }; |
| |
| /* |
| * If we're handed a bigger struct than we know of, ensure all the unknown bits |
| * are 0 - i.e. new user-space does not rely on any kernel feature extensions |
| * we don't know about yet. |
| * |
| * There is a ToCToU between this function call and the following |
| * copy_from_user() call. However, this is not a concern since this function is |
| * meant to be a future-proofing of bits. |
| */ |
| int bpf_check_uarg_tail_zero(bpfptr_t uaddr, |
| size_t expected_size, |
| size_t actual_size) |
| { |
| int res; |
| |
| if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ |
| return -E2BIG; |
| |
| if (actual_size <= expected_size) |
| return 0; |
| |
| if (uaddr.is_kernel) |
| res = memchr_inv(uaddr.kernel + expected_size, 0, |
| actual_size - expected_size) == NULL; |
| else |
| res = check_zeroed_user(uaddr.user + expected_size, |
| actual_size - expected_size); |
| if (res < 0) |
| return res; |
| return res ? 0 : -E2BIG; |
| } |
| |
| const struct bpf_map_ops bpf_map_offload_ops = { |
| .map_meta_equal = bpf_map_meta_equal, |
| .map_alloc = bpf_map_offload_map_alloc, |
| .map_free = bpf_map_offload_map_free, |
| .map_check_btf = map_check_no_btf, |
| }; |
| |
| static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) |
| { |
| const struct bpf_map_ops *ops; |
| u32 type = attr->map_type; |
| struct bpf_map *map; |
| int err; |
| |
| if (type >= ARRAY_SIZE(bpf_map_types)) |
| return ERR_PTR(-EINVAL); |
| type = array_index_nospec(type, ARRAY_SIZE(bpf_map_types)); |
| ops = bpf_map_types[type]; |
| if (!ops) |
| return ERR_PTR(-EINVAL); |
| |
| if (ops->map_alloc_check) { |
| err = ops->map_alloc_check(attr); |
| if (err) |
| return ERR_PTR(err); |
| } |
| if (attr->map_ifindex) |
| ops = &bpf_map_offload_ops; |
| map = ops->map_alloc(attr); |
| if (IS_ERR(map)) |
| return map; |
| map->ops = ops; |
| map->map_type = type; |
| return map; |
| } |
| |
| static void bpf_map_write_active_inc(struct bpf_map *map) |
| { |
| atomic64_inc(&map->writecnt); |
| } |
| |
| static void bpf_map_write_active_dec(struct bpf_map *map) |
| { |
| atomic64_dec(&map->writecnt); |
| } |
| |
| bool bpf_map_write_active(const struct bpf_map *map) |
| { |
| return atomic64_read(&map->writecnt) != 0; |
| } |
| |
| static u32 bpf_map_value_size(const struct bpf_map *map) |
| { |
| 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_CGROUP_STORAGE) |
| return round_up(map->value_size, 8) * num_possible_cpus(); |
| else if (IS_FD_MAP(map)) |
| return sizeof(u32); |
| else |
| return map->value_size; |
| } |
| |
| static void maybe_wait_bpf_programs(struct bpf_map *map) |
| { |
| /* Wait for any running BPF programs to complete so that |
| * userspace, when we return to it, knows that all programs |
| * that could be running use the new map value. |
| */ |
| if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS || |
| map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) |
| synchronize_rcu(); |
| } |
| |
| static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, |
| void *value, __u64 flags) |
| { |
| int err; |
| |
| /* Need to create a kthread, thus must support schedule */ |
| if (bpf_map_is_dev_bound(map)) { |
| return bpf_map_offload_update_elem(map, key, value, flags); |
| } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || |
| map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { |
| return map->ops->map_update_elem(map, key, value, flags); |
| } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH || |
| map->map_type == BPF_MAP_TYPE_SOCKMAP) { |
| return sock_map_update_elem_sys(map, key, value, flags); |
| } else if (IS_FD_PROG_ARRAY(map)) { |
| return bpf_fd_array_map_update_elem(map, f.file, key, value, |
| flags); |
| } |
| |
| bpf_disable_instrumentation(); |
| if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || |
| map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { |
| err = bpf_percpu_hash_update(map, key, value, flags); |
| } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { |
| err = bpf_percpu_array_update(map, key, value, flags); |
| } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { |
| err = bpf_percpu_cgroup_storage_update(map, key, value, |
| flags); |
| } else if (IS_FD_ARRAY(map)) { |
| rcu_read_lock(); |
| err = bpf_fd_array_map_update_elem(map, f.file, key, value, |
| flags); |
| rcu_read_unlock(); |
| } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { |
| rcu_read_lock(); |
| err = bpf_fd_htab_map_update_elem(map, f.file, key, value, |
| flags); |
| rcu_read_unlock(); |
| } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { |
| /* rcu_read_lock() is not needed */ |
| err = bpf_fd_reuseport_array_update_elem(map, key, value, |
| flags); |
| } else if (map->map_type == BPF_MAP_TYPE_QUEUE || |
| map->map_type == BPF_MAP_TYPE_STACK || |
| map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { |
| err = map->ops->map_push_elem(map, value, flags); |
| } else { |
| rcu_read_lock(); |
| err = map->ops->map_update_elem(map, key, value, flags); |
| rcu_read_unlock(); |
| } |
| bpf_enable_instrumentation(); |
| maybe_wait_bpf_programs(map); |
| |
| return err; |
| } |
| |
| static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, |
| __u64 flags) |
| { |
| void *ptr; |
| int err; |
| |
| if (bpf_map_is_dev_bound(map)) |
| return bpf_map_offload_lookup_elem(map, key, value); |
| |
| bpf_disable_instrumentation(); |
| if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || |
| map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { |
| 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) || IS_FD_PROG_ARRAY(map)) { |
| err = bpf_fd_array_map_lookup_elem(map, key, value); |
| } else if (IS_FD_HASH(map)) { |
| err = bpf_fd_htab_map_lookup_elem(map, key, value); |
| } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { |
| err = bpf_fd_reuseport_array_lookup_elem(map, key, value); |
| } else if (map->map_type == BPF_MAP_TYPE_QUEUE || |
| map->map_type == BPF_MAP_TYPE_STACK || |
| map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { |
| err = map->ops->map_peek_elem(map, value); |
| } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { |
| /* struct_ops map requires directly updating "value" */ |
| err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); |
| } else { |
| rcu_read_lock(); |
| if (map->ops->map_lookup_elem_sys_only) |
| ptr = map->ops->map_lookup_elem_sys_only(map, key); |
| else |
| ptr = map->ops->map_lookup_elem(map, key); |
| if (IS_ERR(ptr)) { |
| err = PTR_ERR(ptr); |
| } else if (!ptr) { |
| err = -ENOENT; |
| } else { |
| err = 0; |
| if (flags & BPF_F_LOCK) |
| /* lock 'ptr' and copy everything but lock */ |
| copy_map_value_locked(map, value, ptr, true); |
| else |
| copy_map_value(map, value, ptr); |
| /* mask lock and timer, since value wasn't zero inited */ |
| check_and_init_map_value(map, value); |
| } |
| rcu_read_unlock(); |
| } |
| |
| bpf_enable_instrumentation(); |
| maybe_wait_bpf_programs(map); |
| |
| return err; |
| } |
| |
| /* Please, do not use this function outside from the map creation path |
| * (e.g. in map update path) without taking care of setting the active |
| * memory cgroup (see at bpf_map_kmalloc_node() for example). |
| */ |
| static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) |
| { |
| /* We really just want to fail instead of triggering OOM killer |
| * under memory pressure, therefore we set __GFP_NORETRY to kmalloc, |
| * which is used for lower order allocation requests. |
| * |
| * It has been observed that higher order allocation requests done by |
| * vmalloc with __GFP_NORETRY being set might fail due to not trying |
| * to reclaim memory from the page cache, thus we set |
| * __GFP_RETRY_MAYFAIL to avoid such situations. |
| */ |
| |
| const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO | __GFP_ACCOUNT; |
| unsigned int flags = 0; |
| unsigned long align = 1; |
| void *area; |
| |
| if (size >= SIZE_MAX) |
| return NULL; |
| |
| /* kmalloc()'ed memory can't be mmap()'ed */ |
| if (mmapable) { |
| BUG_ON(!PAGE_ALIGNED(size)); |
| align = SHMLBA; |
| flags = VM_USERMAP; |
| } else if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { |
| area = kmalloc_node(size, gfp | GFP_USER | __GFP_NORETRY, |
| numa_node); |
| if (area != NULL) |
| return area; |
| } |
| |
| return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, |
| gfp | GFP_KERNEL | __GFP_RETRY_MAYFAIL, PAGE_KERNEL, |
| flags, numa_node, __builtin_return_address(0)); |
| } |
| |
| void *bpf_map_area_alloc(u64 size, int numa_node) |
| { |
| return __bpf_map_area_alloc(size, numa_node, false); |
| } |
| |
| void *bpf_map_area_mmapable_alloc(u64 size, int numa_node) |
| { |
| return __bpf_map_area_alloc(size, numa_node, true); |
| } |
| |
| void bpf_map_area_free(void *area) |
| { |
| kvfree(area); |
| } |
| |
| static u32 bpf_map_flags_retain_permanent(u32 flags) |
| { |
| /* Some map creation flags are not tied to the map object but |
| * rather to the map fd instead, so they have no meaning upon |
| * map object inspection since multiple file descriptors with |
| * different (access) properties can exist here. Thus, given |
| * this has zero meaning for the map itself, lets clear these |
| * from here. |
| */ |
| return flags & ~(BPF_F_RDONLY | BPF_F_WRONLY); |
| } |
| |
| void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) |
| { |
| map->map_type = attr->map_type; |
| map->key_size = attr->key_size; |
| map->value_size = attr->value_size; |
| map->max_entries = attr->max_entries; |
| map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); |
| map->numa_node = bpf_map_attr_numa_node(attr); |
| map->map_extra = attr->map_extra; |
| } |
| |
| static int bpf_map_alloc_id(struct bpf_map *map) |
| { |
| int id; |
| |
| idr_preload(GFP_KERNEL); |
| spin_lock_bh(&map_idr_lock); |
| id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC); |
| if (id > 0) |
| map->id = id; |
| spin_unlock_bh(&map_idr_lock); |
| idr_preload_end(); |
| |
| if (WARN_ON_ONCE(!id)) |
| return -ENOSPC; |
| |
| return id > 0 ? 0 : id; |
| } |
| |
| void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) |
| { |
| unsigned long flags; |
| |
| /* Offloaded maps are removed from the IDR store when their device |
| * disappears - even if someone holds an fd to them they are unusable, |
| * the memory is gone, all ops will fail; they are simply waiting for |
| * refcnt to drop to be freed. |
| */ |
| if (!map->id) |
| return; |
| |
| if (do_idr_lock) |
| spin_lock_irqsave(&map_idr_lock, flags); |
| else |
| __acquire(&map_idr_lock); |
| |
| idr_remove(&map_idr, map->id); |
| map->id = 0; |
| |
| if (do_idr_lock) |
| spin_unlock_irqrestore(&map_idr_lock, flags); |
| else |
| __release(&map_idr_lock); |
| } |
| |
| #ifdef CONFIG_MEMCG_KMEM |
| static void bpf_map_save_memcg(struct bpf_map *map) |
| { |
| /* Currently if a map is created by a process belonging to the root |
| * memory cgroup, get_obj_cgroup_from_current() will return NULL. |
| * So we have to check map->objcg for being NULL each time it's |
| * being used. |
| */ |
| map->objcg = get_obj_cgroup_from_current(); |
| } |
| |
| static void bpf_map_release_memcg(struct bpf_map *map) |
| { |
| if (map->objcg) |
| obj_cgroup_put(map->objcg); |
| } |
| |
| static struct mem_cgroup *bpf_map_get_memcg(const struct bpf_map *map) |
| { |
| if (map->objcg) |
| return get_mem_cgroup_from_objcg(map->objcg); |
| |
| return root_mem_cgroup; |
| } |
| |
| void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, |
| int node) |
| { |
| struct mem_cgroup *memcg, *old_memcg; |
| void *ptr; |
| |
| memcg = bpf_map_get_memcg(map); |
| old_memcg = set_active_memcg(memcg); |
| ptr = kmalloc_node(size, flags | __GFP_ACCOUNT, node); |
| set_active_memcg(old_memcg); |
| mem_cgroup_put(memcg); |
| |
| return ptr; |
| } |
| |
| void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) |
| { |
| struct mem_cgroup *memcg, *old_memcg; |
| void *ptr; |
| |
| memcg = bpf_map_get_memcg(map); |
| old_memcg = set_active_memcg(memcg); |
| ptr = kzalloc(size, flags | __GFP_ACCOUNT); |
| set_active_memcg(old_memcg); |
| mem_cgroup_put(memcg); |
| |
| return ptr; |
| } |
| |
| void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, |
| size_t align, gfp_t flags) |
| { |
| struct mem_cgroup *memcg, *old_memcg; |
| void __percpu *ptr; |
| |
| memcg = bpf_map_get_memcg(map); |
| old_memcg = set_active_memcg(memcg); |
| ptr = __alloc_percpu_gfp(size, align, flags | __GFP_ACCOUNT); |
| set_active_memcg(old_memcg); |
| mem_cgroup_put(memcg); |
| |
| return ptr; |
| } |
| |
| #else |
| static void bpf_map_save_memcg(struct bpf_map *map) |
| { |
| } |
| |
| static void bpf_map_release_memcg(struct bpf_map *map) |
| { |
| } |
| #endif |
| |
| static int bpf_map_kptr_off_cmp(const void *a, const void *b) |
| { |
| const struct bpf_map_value_off_desc *off_desc1 = a, *off_desc2 = b; |
| |
| if (off_desc1->offset < off_desc2->offset) |
| return -1; |
| else if (off_desc1->offset > off_desc2->offset) |
| return 1; |
| return 0; |
| } |
| |
| struct bpf_map_value_off_desc *bpf_map_kptr_off_contains(struct bpf_map *map, u32 offset) |
| { |
| /* Since members are iterated in btf_find_field in increasing order, |
| * offsets appended to kptr_off_tab are in increasing order, so we can |
| * do bsearch to find exact match. |
| */ |
| struct bpf_map_value_off *tab; |
| |
| if (!map_value_has_kptrs(map)) |
| return NULL; |
| tab = map->kptr_off_tab; |
| return bsearch(&offset, tab->off, tab->nr_off, sizeof(tab->off[0]), bpf_map_kptr_off_cmp); |
| } |
| |
| void bpf_map_free_kptr_off_tab(struct bpf_map *map) |
| { |
| struct bpf_map_value_off *tab = map->kptr_off_tab; |
| int i; |
| |
| if (!map_value_has_kptrs(map)) |
| return; |
| for (i = 0; i < tab->nr_off; i++) { |
| if (tab->off[i].kptr.module) |
| module_put(tab->off[i].kptr.module); |
| btf_put(tab->off[i].kptr.btf); |
| } |
| kfree(tab); |
| map->kptr_off_tab = NULL; |
| } |
| |
| struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map) |
| { |
| struct bpf_map_value_off *tab = map->kptr_off_tab, *new_tab; |
| int size, i; |
| |
| if (!map_value_has_kptrs(map)) |
| return ERR_PTR(-ENOENT); |
| size = offsetof(struct bpf_map_value_off, off[tab->nr_off]); |
| new_tab = kmemdup(tab, size, GFP_KERNEL | __GFP_NOWARN); |
| if (!new_tab) |
| return ERR_PTR(-ENOMEM); |
| /* Do a deep copy of the kptr_off_tab */ |
| for (i = 0; i < tab->nr_off; i++) { |
| btf_get(tab->off[i].kptr.btf); |
| if (tab->off[i].kptr.module && !try_module_get(tab->off[i].kptr.module)) { |
| while (i--) { |
| if (tab->off[i].kptr.module) |
| module_put(tab->off[i].kptr.module); |
| btf_put(tab->off[i].kptr.btf); |
| } |
| kfree(new_tab); |
| return ERR_PTR(-ENXIO); |
| } |
| } |
| return new_tab; |
| } |
| |
| bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_map *map_b) |
| { |
| struct bpf_map_value_off *tab_a = map_a->kptr_off_tab, *tab_b = map_b->kptr_off_tab; |
| bool a_has_kptr = map_value_has_kptrs(map_a), b_has_kptr = map_value_has_kptrs(map_b); |
| int size; |
| |
| if (!a_has_kptr && !b_has_kptr) |
| return true; |
| if (a_has_kptr != b_has_kptr) |
| return false; |
| if (tab_a->nr_off != tab_b->nr_off) |
| return false; |
| size = offsetof(struct bpf_map_value_off, off[tab_a->nr_off]); |
| return !memcmp(tab_a, tab_b, size); |
| } |
| |
| /* Caller must ensure map_value_has_kptrs is true. Note that this function can |
| * be called on a map value while the map_value is visible to BPF programs, as |
| * it ensures the correct synchronization, and we already enforce the same using |
| * the bpf_kptr_xchg helper on the BPF program side for referenced kptrs. |
| */ |
| void bpf_map_free_kptrs(struct bpf_map *map, void *map_value) |
| { |
| struct bpf_map_value_off *tab = map->kptr_off_tab; |
| unsigned long *btf_id_ptr; |
| int i; |
| |
| for (i = 0; i < tab->nr_off; i++) { |
| struct bpf_map_value_off_desc *off_desc = &tab->off[i]; |
| unsigned long old_ptr; |
| |
| btf_id_ptr = map_value + off_desc->offset; |
| if (off_desc->type == BPF_KPTR_UNREF) { |
| u64 *p = (u64 *)btf_id_ptr; |
| |
| WRITE_ONCE(*p, 0); |
| continue; |
| } |
| old_ptr = xchg(btf_id_ptr, 0); |
| off_desc->kptr.dtor((void *)old_ptr); |
| } |
| } |
| |
| /* called from workqueue */ |
| static void bpf_map_free_deferred(struct work_struct *work) |
| { |
| struct bpf_map *map = container_of(work, struct bpf_map, work); |
| |
| security_bpf_map_free(map); |
| kfree(map->off_arr); |
| bpf_map_release_memcg(map); |
| /* implementation dependent freeing, map_free callback also does |
| * bpf_map_free_kptr_off_tab, if needed. |
| */ |
| map->ops->map_free(map); |
| } |
| |
| static void bpf_map_put_uref(struct bpf_map *map) |
| { |
| if (atomic64_dec_and_test(&map->usercnt)) { |
| if (map->ops->map_release_uref) |
| map->ops->map_release_uref(map); |
| } |
| } |
| |
| /* decrement map refcnt and schedule it for freeing via workqueue |
| * (unrelying map implementation ops->map_free() might sleep) |
| */ |
| static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) |
| { |
| if (atomic64_dec_and_test(&map->refcnt)) { |
| /* bpf_map_free_id() must be called first */ |
| bpf_map_free_id(map, do_idr_lock); |
| btf_put(map->btf); |
| INIT_WORK(&map->work, bpf_map_free_deferred); |
| /* Avoid spawning kworkers, since they all might contend |
| * for the same mutex like slab_mutex. |
| */ |
| queue_work(system_unbound_wq, &map->work); |
| } |
| } |
| |
| void bpf_map_put(struct bpf_map *map) |
| { |
| __bpf_map_put(map, true); |
| } |
| EXPORT_SYMBOL_GPL(bpf_map_put); |
| |
| void bpf_map_put_with_uref(struct bpf_map *map) |
| { |
| bpf_map_put_uref(map); |
| bpf_map_put(map); |
| } |
| |
| static int bpf_map_release(struct inode *inode, struct file *filp) |
| { |
| struct bpf_map *map = filp->private_data; |
| |
| if (map->ops->map_release) |
| map->ops->map_release(map, filp); |
| |
| bpf_map_put_with_uref(map); |
| return 0; |
| } |
| |
| static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f) |
| { |
| fmode_t mode = f.file->f_mode; |
| |
| /* Our file permissions may have been overridden by global |
| * map permissions facing syscall side. |
| */ |
| if (READ_ONCE(map->frozen)) |
| mode &= ~FMODE_CAN_WRITE; |
| return mode; |
| } |
| |
| #ifdef CONFIG_PROC_FS |
| /* Provides an approximation of the map's memory footprint. |
| * Used only to provide a backward compatibility and display |
| * a reasonable "memlock" info. |
| */ |
| static unsigned long bpf_map_memory_footprint(const struct bpf_map *map) |
| { |
| unsigned long size; |
| |
| size = round_up(map->key_size + bpf_map_value_size(map), 8); |
| |
| return round_up(map->max_entries * size, PAGE_SIZE); |
| } |
| |
| static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) |
| { |
| struct bpf_map *map = filp->private_data; |
| u32 type = 0, jited = 0; |
| |
| if (map_type_contains_progs(map)) { |
| spin_lock(&map->owner.lock); |
| type = map->owner.type; |
| jited = map->owner.jited; |
| spin_unlock(&map->owner.lock); |
| } |
| |
| seq_printf(m, |
| "map_type:\t%u\n" |
| "key_size:\t%u\n" |
| "value_size:\t%u\n" |
| "max_entries:\t%u\n" |
| "map_flags:\t%#x\n" |
| "map_extra:\t%#llx\n" |
| "memlock:\t%lu\n" |
| "map_id:\t%u\n" |
| "frozen:\t%u\n", |
| map->map_type, |
| map->key_size, |
| map->value_size, |
| map->max_entries, |
| map->map_flags, |
| (unsigned long long)map->map_extra, |
| bpf_map_memory_footprint(map), |
| map->id, |
| READ_ONCE(map->frozen)); |
| if (type) { |
| seq_printf(m, "owner_prog_type:\t%u\n", type); |
| seq_printf(m, "owner_jited:\t%u\n", jited); |
| } |
| } |
| #endif |
| |
| static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz, |
| loff_t *ppos) |
| { |
| /* We need this handler such that alloc_file() enables |
| * f_mode with FMODE_CAN_READ. |
| */ |
| return -EINVAL; |
| } |
| |
| static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf, |
| size_t siz, loff_t *ppos) |
| { |
| /* We need this handler such that alloc_file() enables |
| * f_mode with FMODE_CAN_WRITE. |
| */ |
| return -EINVAL; |
| } |
| |
| /* called for any extra memory-mapped regions (except initial) */ |
| static void bpf_map_mmap_open(struct vm_area_struct *vma) |
| { |
| struct bpf_map *map = vma->vm_file->private_data; |
| |
| if (vma->vm_flags & VM_MAYWRITE) |
| bpf_map_write_active_inc(map); |
| } |
| |
| /* called for all unmapped memory region (including initial) */ |
| static void bpf_map_mmap_close(struct vm_area_struct *vma) |
| { |
| struct bpf_map *map = vma->vm_file->private_data; |
| |
| if (vma->vm_flags & VM_MAYWRITE) |
| bpf_map_write_active_dec(map); |
| } |
| |
| static const struct vm_operations_struct bpf_map_default_vmops = { |
| .open = bpf_map_mmap_open, |
| .close = bpf_map_mmap_close, |
| }; |
| |
| static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) |
| { |
| struct bpf_map *map = filp->private_data; |
| int err; |
| |
| if (!map->ops->map_mmap || map_value_has_spin_lock(map) || |
| map_value_has_timer(map) || map_value_has_kptrs(map)) |
| return -ENOTSUPP; |
| |
| if (!(vma->vm_flags & VM_SHARED)) |
| return -EINVAL; |
| |
| mutex_lock(&map->freeze_mutex); |
| |
| if (vma->vm_flags & VM_WRITE) { |
| if (map->frozen) { |
| err = -EPERM; |
| goto out; |
| } |
| /* map is meant to be read-only, so do not allow mapping as |
| * writable, because it's possible to leak a writable page |
| * reference and allows user-space to still modify it after |
| * freezing, while verifier will assume contents do not change |
| */ |
| if (map->map_flags & BPF_F_RDONLY_PROG) { |
| err = -EACCES; |
| goto out; |
| } |
| } |
| |
| /* set default open/close callbacks */ |
| vma->vm_ops = &bpf_map_default_vmops; |
| vma->vm_private_data = map; |
| vm_flags_clear(vma, VM_MAYEXEC); |
| if (!(vma->vm_flags & VM_WRITE)) |
| /* disallow re-mapping with PROT_WRITE */ |
| vm_flags_clear(vma, VM_MAYWRITE); |
| |
| err = map->ops->map_mmap(map, vma); |
| if (err) |
| goto out; |
| |
| if (vma->vm_flags & VM_MAYWRITE) |
| bpf_map_write_active_inc(map); |
| out: |
| mutex_unlock(&map->freeze_mutex); |
| return err; |
| } |
| |
| static __poll_t bpf_map_poll(struct file *filp, struct poll_table_struct *pts) |
| { |
| struct bpf_map *map = filp->private_data; |
| |
| if (map->ops->map_poll) |
| return map->ops->map_poll(map, filp, pts); |
| |
| return EPOLLERR; |
| } |
| |
| const struct file_operations bpf_map_fops = { |
| #ifdef CONFIG_PROC_FS |
| .show_fdinfo = bpf_map_show_fdinfo, |
| #endif |
| .release = bpf_map_release, |
| .read = bpf_dummy_read, |
| .write = bpf_dummy_write, |
| .mmap = bpf_map_mmap, |
| .poll = bpf_map_poll, |
| }; |
| |
| int bpf_map_new_fd(struct bpf_map *map, int flags) |
| { |
| int ret; |
| |
| ret = security_bpf_map(map, OPEN_FMODE(flags)); |
| if (ret < 0) |
| return ret; |
| |
| return anon_inode_getfd("bpf-map", &bpf_map_fops, map, |
| flags | O_CLOEXEC); |
| } |
| |
| int bpf_get_file_flag(int flags) |
| { |
| if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY)) |
| return -EINVAL; |
| if (flags & BPF_F_RDONLY) |
| return O_RDONLY; |
| if (flags & BPF_F_WRONLY) |
| return O_WRONLY; |
| return O_RDWR; |
| } |
| |
| /* helper macro to check that unused fields 'union bpf_attr' are zero */ |
| #define CHECK_ATTR(CMD) \ |
| memchr_inv((void *) &attr->CMD##_LAST_FIELD + \ |
| sizeof(attr->CMD##_LAST_FIELD), 0, \ |
| sizeof(*attr) - \ |
| offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ |
| sizeof(attr->CMD##_LAST_FIELD)) != NULL |
| |
| /* dst and src must have at least "size" number of bytes. |
| * Return strlen on success and < 0 on error. |
| */ |
| int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size) |
| { |
| const char *end = src + size; |
| const char *orig_src = src; |
| |
| memset(dst, 0, size); |
| /* Copy all isalnum(), '_' and '.' chars. */ |
| while (src < end && *src) { |
| if (!isalnum(*src) && |
| *src != '_' && *src != '.') |
| return -EINVAL; |
| *dst++ = *src++; |
| } |
| |
| /* No '\0' found in "size" number of bytes */ |
| if (src == end) |
| return -EINVAL; |
| |
| return src - orig_src; |
| } |
| |
| int map_check_no_btf(const struct bpf_map *map, |
| const struct btf *btf, |
| const struct btf_type *key_type, |
| const struct btf_type *value_type) |
| { |
| return -ENOTSUPP; |
| } |
| |
| static int map_off_arr_cmp(const void *_a, const void *_b, const void *priv) |
| { |
| const u32 a = *(const u32 *)_a; |
| const u32 b = *(const u32 *)_b; |
| |
| if (a < b) |
| return -1; |
| else if (a > b) |
| return 1; |
| return 0; |
| } |
| |
| static void map_off_arr_swap(void *_a, void *_b, int size, const void *priv) |
| { |
| struct bpf_map *map = (struct bpf_map *)priv; |
| u32 *off_base = map->off_arr->field_off; |
| u32 *a = _a, *b = _b; |
| u8 *sz_a, *sz_b; |
| |
| sz_a = map->off_arr->field_sz + (a - off_base); |
| sz_b = map->off_arr->field_sz + (b - off_base); |
| |
| swap(*a, *b); |
| swap(*sz_a, *sz_b); |
| } |
| |
| static int bpf_map_alloc_off_arr(struct bpf_map *map) |
| { |
| bool has_spin_lock = map_value_has_spin_lock(map); |
| bool has_timer = map_value_has_timer(map); |
| bool has_kptrs = map_value_has_kptrs(map); |
| struct bpf_map_off_arr *off_arr; |
| u32 i; |
| |
| if (!has_spin_lock && !has_timer && !has_kptrs) { |
| map->off_arr = NULL; |
| return 0; |
| } |
| |
| off_arr = kmalloc(sizeof(*map->off_arr), GFP_KERNEL | __GFP_NOWARN); |
| if (!off_arr) |
| return -ENOMEM; |
| map->off_arr = off_arr; |
| |
| off_arr->cnt = 0; |
| if (has_spin_lock) { |
| i = off_arr->cnt; |
| |
| off_arr->field_off[i] = map->spin_lock_off; |
| off_arr->field_sz[i] = sizeof(struct bpf_spin_lock); |
| off_arr->cnt++; |
| } |
| if (has_timer) { |
| i = off_arr->cnt; |
| |
| off_arr->field_off[i] = map->timer_off; |
| off_arr->field_sz[i] = sizeof(struct bpf_timer); |
| off_arr->cnt++; |
| } |
| if (has_kptrs) { |
| struct bpf_map_value_off *tab = map->kptr_off_tab; |
| u32 *off = &off_arr->field_off[off_arr->cnt]; |
| u8 *sz = &off_arr->field_sz[off_arr->cnt]; |
| |
| for (i = 0; i < tab->nr_off; i++) { |
| *off++ = tab->off[i].offset; |
| *sz++ = sizeof(u64); |
| } |
| off_arr->cnt += tab->nr_off; |
| } |
| |
| if (off_arr->cnt == 1) |
| return 0; |
| sort_r(off_arr->field_off, off_arr->cnt, sizeof(off_arr->field_off[0]), |
| map_off_arr_cmp, map_off_arr_swap, map); |
| return 0; |
| } |
| |
| static int map_check_btf(struct bpf_map *map, const struct btf *btf, |
| u32 btf_key_id, u32 btf_value_id) |
| { |
| const struct btf_type *key_type, *value_type; |
| u32 key_size, value_size; |
| int ret = 0; |
| |
| /* Some maps allow key to be unspecified. */ |
| if (btf_key_id) { |
| key_type = btf_type_id_size(btf, &btf_key_id, &key_size); |
| if (!key_type || key_size != map->key_size) |
| return -EINVAL; |
| } else { |
| key_type = btf_type_by_id(btf, 0); |
| if (!map->ops->map_check_btf) |
| return -EINVAL; |
| } |
| |
| value_type = btf_type_id_size(btf, &btf_value_id, &value_size); |
| if (!value_type || value_size != map->value_size) |
| return -EINVAL; |
| |
| map->spin_lock_off = btf_find_spin_lock(btf, value_type); |
| |
| if (map_value_has_spin_lock(map)) { |
| if (map->map_flags & BPF_F_RDONLY_PROG) |
| return -EACCES; |
| if (map->map_type != BPF_MAP_TYPE_HASH && |
| map->map_type != BPF_MAP_TYPE_ARRAY && |
| map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && |
| map->map_type != BPF_MAP_TYPE_SK_STORAGE && |
| map->map_type != BPF_MAP_TYPE_INODE_STORAGE && |
| map->map_type != BPF_MAP_TYPE_TASK_STORAGE) |
| return -ENOTSUPP; |
| if (map->spin_lock_off + sizeof(struct bpf_spin_lock) > |
| map->value_size) { |
| WARN_ONCE(1, |
| "verifier bug spin_lock_off %d value_size %d\n", |
| map->spin_lock_off, map->value_size); |
| return -EFAULT; |
| } |
| } |
| |
| map->timer_off = btf_find_timer(btf, value_type); |
| if (map_value_has_timer(map)) { |
| if (map->map_flags & BPF_F_RDONLY_PROG) |
| return -EACCES; |
| if (map->map_type != BPF_MAP_TYPE_HASH && |
| map->map_type != BPF_MAP_TYPE_LRU_HASH && |
| map->map_type != BPF_MAP_TYPE_ARRAY) |
| return -EOPNOTSUPP; |
| } |
| |
| map->kptr_off_tab = btf_parse_kptrs(btf, value_type); |
| if (map_value_has_kptrs(map)) { |
| if (!bpf_capable()) { |
| ret = -EPERM; |
| goto free_map_tab; |
| } |
| if (map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) { |
| ret = -EACCES; |
| goto free_map_tab; |
| } |
| if (map->map_type != BPF_MAP_TYPE_HASH && |
| map->map_type != BPF_MAP_TYPE_LRU_HASH && |
| map->map_type != BPF_MAP_TYPE_ARRAY && |
| map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY) { |
| ret = -EOPNOTSUPP; |
| 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) |
| goto free_map_tab; |
| } |
| |
| return ret; |
| free_map_tab: |
| bpf_map_free_kptr_off_tab(map); |
| return ret; |
| } |
| |
| #define BPF_MAP_CREATE_LAST_FIELD map_extra |
| /* called via syscall */ |
| static int map_create(union bpf_attr *attr) |
| { |
| int numa_node = bpf_map_attr_numa_node(attr); |
| struct bpf_map *map; |
| int f_flags; |
| int err; |
| |
| err = CHECK_ATTR(BPF_MAP_CREATE); |
| if (err) |
| return -EINVAL; |
| |
| if (attr->btf_vmlinux_value_type_id) { |
| if (attr->map_type != BPF_MAP_TYPE_STRUCT_OPS || |
| attr->btf_key_type_id || attr->btf_value_type_id) |
| return -EINVAL; |
| } else if (attr->btf_key_type_id && !attr->btf_value_type_id) { |
| return -EINVAL; |
| } |
| |
| if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && |
| attr->map_extra != 0) |
| return -EINVAL; |
| |
| f_flags = bpf_get_file_flag(attr->map_flags); |
| if (f_flags < 0) |
| return f_flags; |
| |
| if (numa_node != NUMA_NO_NODE && |
| ((unsigned int)numa_node >= nr_node_ids || |
| !node_online(numa_node))) |
| return -EINVAL; |
| |
| /* find map type and init map: hashtable vs rbtree vs bloom vs ... */ |
| map = find_and_alloc_map(attr); |
| if (IS_ERR(map)) |
| return PTR_ERR(map); |
| |
| err = bpf_obj_name_cpy(map->name, attr->map_name, |
| sizeof(attr->map_name)); |
| if (err < 0) |
| goto free_map; |
| |
| atomic64_set(&map->refcnt, 1); |
| atomic64_set(&map->usercnt, 1); |
| mutex_init(&map->freeze_mutex); |
| spin_lock_init(&map->owner.lock); |
| |
| map->spin_lock_off = -EINVAL; |
| map->timer_off = -EINVAL; |
| if (attr->btf_key_type_id || attr->btf_value_type_id || |
| /* Even the map's value is a kernel's struct, |
| * the bpf_prog.o must have BTF to begin with |
| * to figure out the corresponding kernel's |
| * counter part. Thus, attr->btf_fd has |
| * to be valid also. |
| */ |
| attr->btf_vmlinux_value_type_id) { |
| struct btf *btf; |
| |
| btf = btf_get_by_fd(attr->btf_fd); |
| if (IS_ERR(btf)) { |
| err = PTR_ERR(btf); |
| goto free_map; |
| } |
| if (btf_is_kernel(btf)) { |
| btf_put(btf); |
| err = -EACCES; |
| goto free_map; |
| } |
| map->btf = btf; |
| |
| if (attr->btf_value_type_id) { |
| err = map_check_btf(map, btf, attr->btf_key_type_id, |
| attr->btf_value_type_id); |
| if (err) |
| goto free_map; |
| } |
| |
| map->btf_key_type_id = attr->btf_key_type_id; |
| map->btf_value_type_id = attr->btf_value_type_id; |
| map->btf_vmlinux_value_type_id = |
| attr->btf_vmlinux_value_type_id; |
| } |
| |
| err = bpf_map_alloc_off_arr(map); |
| if (err) |
| goto free_map; |
| |
| err = security_bpf_map_alloc(map); |
| if (err) |
| goto free_map_off_arr; |
| |
| err = bpf_map_alloc_id(map); |
| if (err) |
| goto free_map_sec; |
| |
| bpf_map_save_memcg(map); |
| |
| err = bpf_map_new_fd(map, f_flags); |
| if (err < 0) { |
| /* failed to allocate fd. |
| * bpf_map_put_with_uref() is needed because the above |
| * bpf_map_alloc_id() has published the map |
| * to the userspace and the userspace may |
| * have refcnt-ed it through BPF_MAP_GET_FD_BY_ID. |
| */ |
| bpf_map_put_with_uref(map); |
| return err; |
| } |
| |
| return err; |
| |
| free_map_sec: |
| security_bpf_map_free(map); |
| free_map_off_arr: |
| kfree(map->off_arr); |
| free_map: |
| btf_put(map->btf); |
| map->ops->map_free(map); |
| return err; |
| } |
| |
| /* if error is returned, fd is released. |
| * On success caller should complete fd access with matching fdput() |
| */ |
| struct bpf_map *__bpf_map_get(struct fd f) |
| { |
| if (!f.file) |
| return ERR_PTR(-EBADF); |
| if (f.file->f_op != &bpf_map_fops) { |
| fdput(f); |
| return ERR_PTR(-EINVAL); |
| } |
| |
| return f.file->private_data; |
| } |
| |
| void bpf_map_inc(struct bpf_map *map) |
| { |
| atomic64_inc(&map->refcnt); |
| } |
| EXPORT_SYMBOL_GPL(bpf_map_inc); |
| |
| void bpf_map_inc_with_uref(struct bpf_map *map) |
| { |
| atomic64_inc(&map->refcnt); |
| atomic64_inc(&map->usercnt); |
| } |
| EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref); |
| |
| struct bpf_map *bpf_map_get(u32 ufd) |
| { |
| struct fd f = fdget(ufd); |
| struct bpf_map *map; |
| |
| map = __bpf_map_get(f); |
| if (IS_ERR(map)) |
| return map; |
| |
| bpf_map_inc(map); |
| fdput(f); |
| |
| return map; |
| } |
| EXPORT_SYMBOL(bpf_map_get); |
| |
| struct bpf_map *bpf_map_get_with_uref(u32 ufd) |
| { |
| struct fd f = fdget(ufd); |
| struct bpf_map *map; |
| |
| map = __bpf_map_get(f); |
| if (IS_ERR(map)) |
| return map; |
| |
| bpf_map_inc_with_uref(map); |
| fdput(f); |
| |
| return map; |
| } |
| |
| /* map_idr_lock should have been held */ |
| static struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref) |
| { |
| int refold; |
| |
| refold = atomic64_fetch_add_unless(&map->refcnt, 1, 0); |
| if (!refold) |
| return ERR_PTR(-ENOENT); |
| if (uref) |
| atomic64_inc(&map->usercnt); |
| |
| return map; |
| } |
| |
| struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map) |
| { |
| spin_lock_bh(&map_idr_lock); |
| map = __bpf_map_inc_not_zero(map, false); |
| spin_unlock_bh(&map_idr_lock); |
| |
| return map; |
| } |
| EXPORT_SYMBOL_GPL(bpf_map_inc_not_zero); |
| |
| int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) |
| { |
| return -ENOTSUPP; |
| } |
| |
| static void *__bpf_copy_key(void __user *ukey, u64 key_size) |
| { |
| if (key_size) |
| return vmemdup_user(ukey, key_size); |
| |
| if (ukey) |
| return ERR_PTR(-EINVAL); |
| |
| return NULL; |
| } |
| |
| static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size) |
| { |
| if (key_size) |
| return kvmemdup_bpfptr(ukey, key_size); |
| |
| if (!bpfptr_is_null(ukey)) |
| return ERR_PTR(-EINVAL); |
| |
| return NULL; |
| } |
| |
| /* last field in 'union bpf_attr' used by this command */ |
| #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags |
| |
| static int map_lookup_elem(union bpf_attr *attr) |
| { |
| void __user *ukey = u64_to_user_ptr(attr->key); |
| void __user *uvalue = u64_to_user_ptr(attr->value); |
| int ufd = attr->map_fd; |
| struct bpf_map *map; |
| void *key, *value; |
| u32 value_size; |
| struct fd f; |
| int err; |
| |
| if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM)) |
| return -EINVAL; |
| |
| if (attr->flags & ~BPF_F_LOCK) |
| return -EINVAL; |
| |
| f = fdget(ufd); |
| map = __bpf_map_get(f); |
| if (IS_ERR(map)) |
| return PTR_ERR(map); |
| if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { |
| err = -EPERM; |
| goto err_put; |
| } |
| |
| if ((attr->flags & BPF_F_LOCK) && |
| !map_value_has_spin_lock(map)) { |
| err = -EINVAL; |
| goto err_put; |
| } |
| |
| key = __bpf_copy_key(ukey, map->key_size); |
| if (IS_ERR(key)) { |
| err = PTR_ERR(key); |
| goto err_put; |
| } |
| |
| value_size = bpf_map_value_size(map); |
| |
| err = -ENOMEM; |
| value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); |
| if (!value) |
| goto free_key; |
| |
| if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { |
| if (copy_from_user(value, uvalue, value_size)) |
| err = -EFAULT; |
| else |
| err = bpf_map_copy_value(map, key, value, attr->flags); |
| goto free_value; |
| } |
| |
| err = bpf_map_copy_value(map, key, value, attr->flags); |
| if (err) |
| goto free_value; |
| |
| err = -EFAULT; |
| if (copy_to_user(uvalue, value, value_size) != 0) |
| goto free_value; |
| |
| err = 0; |
| |
| free_value: |
| kvfree(value); |
| free_key: |
| kvfree(key); |
| err_put: |
| fdput(f); |
| return err; |
| } |
| |
| |
| #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags |
| |
| static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) |
| { |
| bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); |
| bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel); |
| int ufd = attr->map_fd; |
| struct bpf_map *map; |
| void *key, *value; |
| u32 value_size; |
| struct fd f; |
| int err; |
| |
| if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM)) |
| return -EINVAL; |
| |
| f = fdget(ufd); |
| map = __bpf_map_get(f); |
| if (IS_ERR(map)) |
| return PTR_ERR(map); |
| bpf_map_write_active_inc(map); |
| if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { |
| err = -EPERM; |
| goto err_put; |
| } |
| |
| if ((attr->flags & BPF_F_LOCK) && |
| !map_value_has_spin_lock(map)) { |
| err = -EINVAL; |
| goto err_put; |
| } |
| |
| key = ___bpf_copy_key(ukey, map->key_size); |
| if (IS_ERR(key)) { |
| err = PTR_ERR(key); |
| goto err_put; |
| } |
| |
| value_size = bpf_map_value_size(map); |
| value = kvmemdup_bpfptr(uvalue, value_size); |
| if (IS_ERR(value)) { |
| err = PTR_ERR(value); |
| goto free_key; |
| } |
| |
| err = bpf_map_update_value(map, f, key, value, attr->flags); |
| |
| kvfree(value); |
| free_key: |
| kvfree(key); |
| err_put: |
| bpf_map_write_active_dec(map); |
| fdput(f); |
| return err; |
| } |
| |
| #define BPF_MAP_DELETE_ELEM_LAST_FIELD key |
| |
| static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr) |
| { |
| bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); |
| int ufd = attr->map_fd; |
| struct bpf_map *map; |
| struct fd f; |
| void *key; |
| int err; |
| |
| if (CHECK_ATTR(BPF_MAP_DELETE_ELEM)) |
| return -EINVAL; |
| |
| f = fdget(ufd); |
| map = __bpf_map_get(f); |
| if (IS_ERR(map)) |
| return PTR_ERR(map); |
| bpf_map_write_active_inc(map); |
| if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { |
| err = -EPERM; |
| goto err_put; |
| } |
| |
| key = ___bpf_copy_key(ukey, map->key_size); |
| if (IS_ERR(key)) { |
| err = PTR_ERR(key); |
| goto err_put; |
| } |
| |
| if (bpf_map_is_dev_bound(map)) { |
| err = bpf_map_offload_delete_elem(map, key); |
| goto out; |
| } else if (IS_FD_PROG_ARRAY(map) || |
| map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { |
| /* These maps require sleepable context */ |
| err = map->ops->map_delete_elem(map, key); |
| goto out; |
| } |
| |
| bpf_disable_instrumentation(); |
| rcu_read_lock(); |
| err = map->ops->map_delete_elem(map, key); |
| rcu_read_unlock(); |
| bpf_enable_instrumentation(); |
| maybe_wait_bpf_programs(map); |
| out: |
| kvfree(key); |
| err_put: |
| bpf_map_write_active_dec(map); |
| fdput(f); |
| return err; |
| } |
| |
| /* last field in 'union bpf_attr' used by this command */ |
| #define BPF_MAP_GET_NEXT_KEY_LAST_FIELD next_key |
| |
| static int map_get_next_key(union bpf_attr *attr) |
| { |
| void __user *ukey = u64_to_user_ptr(attr->key); |
| void __user *unext_key = u64_to_user_ptr(attr->next_key); |
| int ufd = attr->map_fd; |
| struct bpf_map *map; |
| void *key, *next_key; |
| struct fd f; |
| int err; |
| |
| if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY)) |
| return -EINVAL; |
| |
| f = fdget(ufd); |
| map = __bpf_map_get(f); |
| if (IS_ERR(map)) |
| return PTR_ERR(map); |
| if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { |
| err = -EPERM; |
| goto err_put; |
| } |
| |
| if (ukey) { |
| key = __bpf_copy_key(ukey, map->key_size); |
| if (IS_ERR(key)) { |
| err = PTR_ERR(key); |
| goto err_put; |
| } |
| } else { |
| key = NULL; |
| } |
| |
| err = -ENOMEM; |
| next_key = kvmalloc(map->key_size, GFP_USER); |
| if (!next_key) |
| goto free_key; |
| |
| if (bpf_map_is_dev_bound(map)) { |
| err = bpf_map_offload_get_next_key(map, key, next_key); |
| goto out; |
| } |
| |
| rcu_read_lock(); |
| err = map->ops->map_get_next_key(map, key, next_key); |
| rcu_read_unlock(); |
| out: |
| if (err) |
| goto free_next_key; |
| |
| err = -EFAULT; |
| if (copy_to_user(unext_key, next_key, map->key_size) != 0) |
| goto free_next_key; |
| |
| err = 0; |
| |
| free_next_key: |
| kvfree(next_key); |
| free_key: |
| kvfree(key); |
| err_put: |
| fdput(f); |
| return err; |
| } |
| |
| int generic_map_delete_batch(struct bpf_map *map, |
| const union bpf_attr *attr, |
| union bpf_attr __user *uattr) |
| { |
| void __user *keys = u64_to_user_ptr(attr->batch.keys); |
| u32 cp, max_count; |
| int err = 0; |
| void *key; |
| |
| if (attr->batch.elem_flags & ~BPF_F_LOCK) |
| return -EINVAL; |
| |
| if ((attr->batch.elem_flags & BPF_F_LOCK) && |
| !map_value_has_spin_lock(map)) { |
| return -EINVAL; |
| } |
| |
| max_count = attr->batch.count; |
| if (!max_count) |
| return 0; |
| |
| if (put_user(0, &uattr->batch.count)) |
| return -EFAULT; |
| |
| key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); |
| if (!key) |
| return -ENOMEM; |
| |
| for (cp = 0; cp < max_count; cp++) { |
| err = -EFAULT; |
| if (copy_from_user(key, keys + cp * map->key_size, |
| map->key_size)) |
| break; |
| |
| if (bpf_map_is_dev_bound(map)) { |
| err = bpf_map_offload_delete_elem(map, key); |
| break; |
| } |
| |
| bpf_disable_instrumentation(); |
| rcu_read_lock(); |
| err = map->ops->map_delete_elem(map, key); |
| rcu_read_unlock(); |
| bpf_enable_instrumentation(); |
| if (err) |
| break; |
| cond_resched(); |
| } |
| if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) |
| err = -EFAULT; |
| |
| kvfree(key); |
| |
| maybe_wait_bpf_programs(map); |
| return err; |
| } |
| |
| int generic_map_update_batch(struct bpf_map *map, |
| const union bpf_attr *attr, |
| union bpf_attr __user *uattr) |
| { |
| void __user *values = u64_to_user_ptr(attr->batch.values); |
| void __user *keys = u64_to_user_ptr(attr->batch.keys); |
| u32 value_size, cp, max_count; |
| int ufd = attr->batch.map_fd; |
| void *key, *value; |
| struct fd f; |
| int err = 0; |
| |
| if (attr->batch.elem_flags & ~BPF_F_LOCK) |
| return -EINVAL; |
| |
| if ((attr->batch.elem_flags & BPF_F_LOCK) && |
| !map_value_has_spin_lock(map)) { |
| return -EINVAL; |
| } |
| |
| value_size = bpf_map_value_size(map); |
| |
| max_count = attr->batch.count; |
| if (!max_count) |
| return 0; |
| |
| if (put_user(0, &uattr->batch.count)) |
| return -EFAULT; |
| |
| key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); |
| if (!key) |
| return -ENOMEM; |
| |
| value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); |
| if (!value) { |
| kvfree(key); |
| return -ENOMEM; |
| } |
| |
| f = fdget(ufd); /* bpf_map_do_batch() guarantees ufd is valid */ |
| for (cp = 0; cp < max_count; cp++) { |
| err = -EFAULT; |
| if (copy_from_user(key, keys + cp * map->key_size, |
| map->key_size) || |
| copy_from_user(value, values + cp * value_size, value_size)) |
| break; |
| |
| err = bpf_map_update_value(map, f, key, value, |
| attr->batch.elem_flags); |
| |
| if (err) |
| break; |
| cond_resched(); |
| } |
| |
| if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) |
| err = -EFAULT; |
| |
| kvfree(value); |
| kvfree(key); |
| fdput(f); |
| return err; |
| } |
| |
| #define MAP_LOOKUP_RETRIES 3 |
| |
| int generic_map_lookup_batch(struct bpf_map *map, |
| const union bpf_attr *attr, |
| union bpf_attr __user *uattr) |
| { |
| void __user *uobatch = u64_to_user_ptr(attr->batch.out_batch); |
| void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch); |
| void __user *values = u64_to_user_ptr(attr->batch.values); |
| void __user *keys = u64_to_user_ptr(attr->batch.keys); |
| void *buf, *buf_prevkey, *prev_key, *key, *value; |
| int err, retry = MAP_LOOKUP_RETRIES; |
| u32 value_size, cp, max_count; |
| |
| if (attr->batch.elem_flags & ~BPF_F_LOCK) |
| return -EINVAL; |
| |
| if ((attr->batch.elem_flags & BPF_F_LOCK) && |
| !map_value_has_spin_lock(map)) |
| return -EINVAL; |
| |
| value_size = bpf_map_value_size(map); |
| |
| max_count = attr->batch.count; |
| if (!max_count) |
| return 0; |
| |
| if (put_user(0, &uattr->batch.count)) |
| return -EFAULT; |
| |
| buf_prevkey = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); |
| if (!buf_prevkey) |
| return -ENOMEM; |
| |
| buf = kvmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN); |
| if (!buf) { |
| kvfree(buf_prevkey); |
| return -ENOMEM; |
| } |
| |
| err = -EFAULT; |
| prev_key = NULL; |
| if (ubatch && copy_from_user(buf_prevkey, ubatch, map->key_size)) |
| goto free_buf; |
| key = buf; |
| value = key + map->key_size; |
| if (ubatch) |
| prev_key = buf_prevkey; |
| |
| for (cp = 0; cp < max_count;) { |
| rcu_read_lock(); |
| err = map->ops->map_get_next_key(map, prev_key, key); |
| rcu_read_unlock(); |
| if (err) |
| break; |
| err = bpf_map_copy_value(map, key, value, |
| attr->batch.elem_flags); |
| |
| if (err == -ENOENT) { |
| if (retry) { |
| retry--; |
| continue; |
| } |
| err = -EINTR; |
| break; |
| } |
| |
| if (err) |
| goto free_buf; |
| |
| if (copy_to_user(keys + cp * map->key_size, key, |
| map->key_size)) { |
| err = -EFAULT; |
| goto free_buf; |
| } |
| if (copy_to_user(values + cp * value_size, value, value_size)) { |
| err = -EFAULT; |
| goto free_buf; |
| } |
| |
| if (!prev_key) |
| prev_key = buf_prevkey; |
| |
| swap(prev_key, key); |
| retry = MAP_LOOKUP_RETRIES; |
| cp++; |
| cond_resched(); |
| } |
| |
| if (err == -EFAULT) |
| goto free_buf; |
| |
| if ((copy_to_user(&uattr->batch.count, &cp, sizeof(cp)) || |
| (cp && copy_to_user(uobatch, prev_key, map->key_size)))) |
| err = -EFAULT; |
| |
| free_buf: |
| kvfree(buf_prevkey); |
| kvfree(buf); |
| return err; |
| } |
| |
| #define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD flags |
| |
| static int map_lookup_and_delete_elem(union bpf_attr *attr) |
| { |
| void __user *ukey = u64_to_user_ptr(attr->key); |
| void __user *uvalue = u64_to_user_ptr(attr->value); |
| int ufd = attr->map_fd; |
| struct bpf_map *map; |
| void *key, *value; |
| u32 value_size; |
| struct fd f; |
| int err; |
| |
| if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM)) |
| return -EINVAL; |
| |
| if (attr->flags & ~BPF_F_LOCK) |
| return -EINVAL; |
| |
| f = fdget(ufd); |
| map = __bpf_map_get(f); |
| if (IS_ERR(map)) |
| return PTR_ERR(map); |
| bpf_map_write_active_inc(map); |
| if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) || |
| !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { |
| err = -EPERM; |
| goto err_put; |
| } |
| |
| if (attr->flags && |
| (map->map_type == BPF_MAP_TYPE_QUEUE || |
| map->map_type == BPF_MAP_TYPE_STACK)) { |
| err = -EINVAL; |
| goto err_put; |
| } |
| |
| if ((attr->flags & BPF_F_LOCK) && |
| !map_value_has_spin_lock(map)) { |
| err = -EINVAL; |
| goto err_put; |
| } |
| |
| key = __bpf_copy_key(ukey, map->key_size); |
| if (IS_ERR(key)) { |
| err = PTR_ERR(key); |
| goto err_put; |
| } |
| |
| value_size = bpf_map_value_size(map); |
| |
| err = -ENOMEM; |
| value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); |
| if (!value) |
| goto free_key; |
| |
| err = -ENOTSUPP; |
| if (map->map_type == BPF_MAP_TYPE_QUEUE || |
| map->map_type == BPF_MAP_TYPE_STACK) { |
| err = map->ops->map_pop_elem(map, value); |
| } else if (map->map_type == BPF_MAP_TYPE_HASH || |
| map->map_type == BPF_MAP_TYPE_PERCPU_HASH || |
| map->map_type == BPF_MAP_TYPE_LRU_HASH || |
| map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { |
| if (!bpf_map_is_dev_bound(map)) { |
| bpf_disable_instrumentation(); |
| rcu_read_lock(); |
| err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags); |
| rcu_read_unlock(); |
| bpf_enable_instrumentation(); |
| } |
| } |
| |
| if (err) |
| goto free_value; |
| |
| if (copy_to_user(uvalue, value, value_size) != 0) { |
| err = -EFAULT; |
| goto free_value; |
| } |
| |
| err = 0; |
| |
| free_value: |
| kvfree(value); |
| free_key: |
| kvfree(key); |
| err_put: |
| bpf_map_write_active_dec(map); |
| fdput(f); |
| return err; |
| } |
| |
| #define BPF_MAP_FREEZE_LAST_FIELD map_fd |
| |
| static int map_freeze(const union bpf_attr *attr) |
| { |
| int err = 0, ufd = attr->map_fd; |
| struct bpf_map *map; |
| struct fd f; |
| |
| if (CHECK_ATTR(BPF_MAP_FREEZE)) |
| return -EINVAL; |
| |
| f = fdget(ufd); |
| map = __bpf_map_get(f); |
| if (IS_ERR(map)) |
| return PTR_ERR(map); |
| |
| if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || |
| map_value_has_timer(map) || map_value_has_kptrs(map)) { |
| fdput(f); |
| return -ENOTSUPP; |
| } |
| |
| mutex_lock(&map->freeze_mutex); |
| if (bpf_map_write_active(map)) { |
| err = -EBUSY; |
| goto err_put; |
| } |
| if (READ_ONCE(map->frozen)) { |
| err = -EBUSY; |
| goto err_put; |
| } |
| if (!bpf_capable()) { |
| err = -EPERM; |
| goto err_put; |
| } |
| |
| WRITE_ONCE(map->frozen, true); |
| err_put: |
| mutex_unlock(&map->freeze_mutex); |
| fdput(f); |
| return err; |
| } |
| |
| static const struct bpf_prog_ops * const bpf_prog_types[] = { |
| #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ |
| [_id] = & _name ## _prog_ops, |
| #define BPF_MAP_TYPE(_id, _ops) |
| #define BPF_LINK_TYPE(_id, _name) |
| #include <linux/bpf_types.h> |
| #undef BPF_PROG_TYPE |
| #undef BPF_MAP_TYPE |
| #undef BPF_LINK_TYPE |
| }; |
| |
| static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) |
| { |
| const struct bpf_prog_ops *ops; |
| |
| if (type >= ARRAY_SIZE(bpf_prog_types)) |
| return -EINVAL; |
| type = array_index_nospec(type, ARRAY_SIZE(bpf_prog_types)); |
| ops = bpf_prog_types[type]; |
| if (!ops) |
| return -EINVAL; |
| |
| if (!bpf_prog_is_dev_bound(prog->aux)) |
| prog->aux->ops = ops; |
| else |
| prog->aux->ops = &bpf_offload_prog_ops; |
| prog->type = type; |
| return 0; |
| } |
| |
| enum bpf_audit { |
| BPF_AUDIT_LOAD, |
| BPF_AUDIT_UNLOAD, |
| BPF_AUDIT_MAX, |
| }; |
| |
| static const char * const bpf_audit_str[BPF_AUDIT_MAX] = { |
| [BPF_AUDIT_LOAD] = "LOAD", |
| [BPF_AUDIT_UNLOAD] = "UNLOAD", |
| }; |
| |
| static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op) |
| { |
| struct audit_context *ctx = NULL; |
| struct audit_buffer *ab; |
| |
| if (WARN_ON_ONCE(op >= BPF_AUDIT_MAX)) |
| return; |
| if (audit_enabled == AUDIT_OFF) |
| return; |
| if (!in_irq() && !irqs_disabled()) |
| ctx = audit_context(); |
| ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF); |
| if (unlikely(!ab)) |
| return; |
| audit_log_format(ab, "prog-id=%u op=%s", |
| prog->aux->id, bpf_audit_str[op]); |
| audit_log_end(ab); |
| } |
| |
| static int bpf_prog_alloc_id(struct bpf_prog *prog) |
| { |
| int id; |
| |
| idr_preload(GFP_KERNEL); |
| spin_lock_bh(&prog_idr_lock); |
| id = idr_alloc_cyclic(&prog_idr, prog, 1, INT_MAX, GFP_ATOMIC); |
| if (id > 0) |
| prog->aux->id = id; |
| spin_unlock_bh(&prog_idr_lock); |
| idr_preload_end(); |
| |
| /* id is in [1, INT_MAX) */ |
| if (WARN_ON_ONCE(!id)) |
| return -ENOSPC; |
| |
| return id > 0 ? 0 : id; |
| } |
| |
| void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) |
| { |
| unsigned long flags; |
| |
| /* cBPF to eBPF migrations are currently not in the idr store. |
| * Offloaded programs are removed from the store when their device |
| * disappears - even if someone grabs an fd to them they are unusable, |
| * simply waiting for refcnt to drop to be freed. |
| */ |
| if (!prog->aux->id) |
| return; |
| |
| if (do_idr_lock) |
| spin_lock_irqsave(&prog_idr_lock, flags); |
| else |
| __acquire(&prog_idr_lock); |
| |
| idr_remove(&prog_idr, prog->aux->id); |
| prog->aux->id = 0; |
| |
| if (do_idr_lock) |
| spin_unlock_irqrestore(&prog_idr_lock, flags); |
| else |
| __release(&prog_idr_lock); |
| } |
| |
| static void __bpf_prog_put_rcu(struct rcu_head *rcu) |
| { |
| struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); |
| |
| kvfree(aux->func_info); |
| kfree(aux->func_info_aux); |
| free_uid(aux->user); |
| security_bpf_prog_free(aux); |
| bpf_prog_free(aux->prog); |
| } |
| |
| static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) |
| { |
| bpf_prog_kallsyms_del_all(prog); |
| btf_put(prog->aux->btf); |
| kvfree(prog->aux->jited_linfo); |
| kvfree(prog->aux->linfo); |
| kfree(prog->aux->kfunc_tab); |
| if (prog->aux->attach_btf) |
| btf_put(prog->aux->attach_btf); |
| |
| if (deferred) { |
| if (prog->aux->sleepable) |
| call_rcu_tasks_trace(&prog->aux->rcu, __bpf_prog_put_rcu); |
| else |
| call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); |
| } else { |
| __bpf_prog_put_rcu(&prog->aux->rcu); |
| } |
| } |
| |
| static void bpf_prog_put_deferred(struct work_struct *work) |
| { |
| struct bpf_prog_aux *aux; |
| struct bpf_prog *prog; |
| |
| aux = container_of(work, struct bpf_prog_aux, work); |
| prog = aux->prog; |
| perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); |
| bpf_audit_prog(prog, BPF_AUDIT_UNLOAD); |
| bpf_prog_free_id(prog, true); |
| __bpf_prog_put_noref(prog, true); |
| } |
| |
| static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) |
| { |
| struct bpf_prog_aux *aux = prog->aux; |
| |
| if (atomic64_dec_and_test(&aux->refcnt)) { |
| if (in_irq() || irqs_disabled()) { |
| INIT_WORK(&aux->work, bpf_prog_put_deferred); |
| schedule_work(&aux->work); |
| } else { |
| bpf_prog_put_deferred(&aux->work); |
| } |
| } |
| } |
| |
| void bpf_prog_put(struct bpf_prog *prog) |
| { |
| __bpf_prog_put(prog, true); |
| } |
| EXPORT_SYMBOL_GPL(bpf_prog_put); |
| |
| static int bpf_prog_release(struct inode *inode, struct file *filp) |
| { |
| struct bpf_prog *prog = filp->private_data; |
| |
| bpf_prog_put(prog); |
| return 0; |
| } |
| |
| struct bpf_prog_kstats { |
| u64 nsecs; |
| u64 cnt; |
| u64 misses; |
| }; |
| |
| void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog) |
| { |
| struct bpf_prog_stats *stats; |
| unsigned int flags; |
| |
| stats = this_cpu_ptr(prog->stats); |
| flags = u64_stats_update_begin_irqsave(&stats->syncp); |
| u64_stats_inc(&stats->misses); |
| u64_stats_update_end_irqrestore(&stats->syncp, flags); |
| } |
| |
| static void bpf_prog_get_stats(const struct bpf_prog *prog, |
| struct bpf_prog_kstats *stats) |
| { |
| u64 nsecs = 0, cnt = 0, misses = 0; |
| int cpu; |
| |
| for_each_possible_cpu(cpu) { |
| const struct bpf_prog_stats *st; |
| unsigned int start; |
| u64 tnsecs, tcnt, tmisses; |
| |
| st = per_cpu_ptr(prog->stats, cpu); |
| do { |
| start = u64_stats_fetch_begin_irq(&st->syncp); |
| tnsecs = u64_stats_read(&st->nsecs); |
| tcnt = u64_stats_read(&st->cnt); |
| tmisses = u64_stats_read(&st->misses); |
| } while (u64_stats_fetch_retry_irq(&st->syncp, start)); |
| nsecs += tnsecs; |
| cnt += tcnt; |
| misses += tmisses; |
| } |
| stats->nsecs = nsecs; |
| stats->cnt = cnt; |
| stats->misses = misses; |
| } |
| |
| #ifdef CONFIG_PROC_FS |
| static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) |
| { |
| const struct bpf_prog *prog = filp->private_data; |
| char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; |
| struct bpf_prog_kstats stats; |
| |
| bpf_prog_get_stats(prog, &stats); |
| bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); |
| seq_printf(m, |
| "prog_type:\t%u\n" |
| "prog_jited:\t%u\n" |
| "prog_tag:\t%s\n" |
| "memlock:\t%llu\n" |
| "prog_id:\t%u\n" |
| "run_time_ns:\t%llu\n" |
| "run_cnt:\t%llu\n" |
| "recursion_misses:\t%llu\n" |
| "verified_insns:\t%u\n", |
| prog->type, |
| prog->jited, |
| prog_tag, |
| prog->pages * 1ULL << PAGE_SHIFT, |
| prog->aux->id, |
| stats.nsecs, |
| stats.cnt, |
| stats.misses, |
| prog->aux->verified_insns); |
| } |
| #endif |
| |
| const struct file_operations bpf_prog_fops = { |
| #ifdef CONFIG_PROC_FS |
| .show_fdinfo = bpf_prog_show_fdinfo, |
| #endif |
| .release = bpf_prog_release, |
| .read = bpf_dummy_read, |
| .write = bpf_dummy_write, |
| }; |
| |
| int bpf_prog_new_fd(struct bpf_prog *prog) |
| { |
| int ret; |
| |
| ret = security_bpf_prog(prog); |
| if (ret < 0) |
| return ret; |
| |
| return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, |
| O_RDWR | O_CLOEXEC); |
| } |
| |
| static struct bpf_prog *____bpf_prog_get(struct fd f) |
| { |
| if (!f.file) |
| return ERR_PTR(-EBADF); |
| if (f.file->f_op != &bpf_prog_fops) { |
| fdput(f); |
| return ERR_PTR(-EINVAL); |
| } |
| |
| return f.file->private_data; |
| } |
| |
| void bpf_prog_add(struct bpf_prog *prog, int i) |
| { |
| atomic64_add(i, &prog->aux->refcnt); |
| } |
| EXPORT_SYMBOL_GPL(bpf_prog_add); |
| |
| void bpf_prog_sub(struct bpf_prog *prog, int i) |
| { |
| /* Only to be used for undoing previous bpf_prog_add() in some |
| * error path. We still know that another entity in our call |
| * path holds a reference to the program, thus atomic_sub() can |
| * be safely used in such cases! |
| */ |
| WARN_ON(atomic64_sub_return(i, &prog->aux->refcnt) == 0); |
| } |
| EXPORT_SYMBOL_GPL(bpf_prog_sub); |
| |
| void bpf_prog_inc(struct bpf_prog *prog) |
| { |
| atomic64_inc(&prog->aux->refcnt); |
| } |
| EXPORT_SYMBOL_GPL(bpf_prog_inc); |
| |
| /* prog_idr_lock should have been held */ |
| struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) |
| { |
| int refold; |
| |
| refold = atomic64_fetch_add_unless(&prog->aux->refcnt, 1, 0); |
| |
| if (!refold) |
| return ERR_PTR(-ENOENT); |
| |
| return prog; |
| } |
| EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero); |
| |
| bool bpf_prog_get_ok(struct bpf_prog *prog, |
| enum bpf_prog_type *attach_type, bool attach_drv) |
| { |
| /* not an attachment, just a refcount inc, always allow */ |
| if (!attach_type) |
| return true; |
| |
| if (prog->type != *attach_type) |
| return false; |
| if (bpf_prog_is_dev_bound(prog->aux) && !attach_drv) |
| return false; |
| |
| return true; |
| } |
| |
| static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type, |
| bool attach_drv) |
| { |
| struct fd f = fdget(ufd); |
| struct bpf_prog *prog; |
| |
| prog = ____bpf_prog_get(f); |
| if (IS_ERR(prog)) |
| return prog; |
| if (!bpf_prog_get_ok(prog, attach_type, attach_drv)) { |
| prog = ERR_PTR(-EINVAL); |
| goto out; |
| } |
| |
| bpf_prog_inc(prog); |
| out: |
| fdput(f); |
| return prog; |
| } |
| |
| struct bpf_prog *bpf_prog_get(u32 ufd) |
| { |
| return __bpf_prog_get(ufd, NULL, false); |
| } |
| |
| struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, |
| bool attach_drv) |
| { |
| return __bpf_prog_get(ufd, &type, attach_drv); |
| } |
| EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev); |
| |
| /* Initially all BPF programs could be loaded w/o specifying |
| * expected_attach_type. Later for some of them specifying expected_attach_type |
| * at load time became required so that program could be validated properly. |
| * Programs of types that are allowed to be loaded both w/ and w/o (for |
| * backward compatibility) expected_attach_type, should have the default attach |
| * type assigned to expected_attach_type for the latter case, so that it can be |
| * validated later at attach time. |
| * |
| * bpf_prog_load_fixup_attach_type() sets expected_attach_type in @attr if |
| * prog type requires it but has some attach types that have to be backward |
| * compatible. |
| */ |
| static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr) |
| { |
| switch (attr->prog_type) { |
| case BPF_PROG_TYPE_CGROUP_SOCK: |
| /* Unfortunately BPF_ATTACH_TYPE_UNSPEC enumeration doesn't |
| * exist so checking for non-zero is the way to go here. |
| */ |
| if (!attr->expected_attach_type) |
| attr->expected_attach_type = |
| BPF_CGROUP_INET_SOCK_CREATE; |
| break; |
| case BPF_PROG_TYPE_SK_REUSEPORT: |
| if (!attr->expected_attach_type) |
| attr->expected_attach_type = |
| BPF_SK_REUSEPORT_SELECT; |
| break; |
| } |
| } |
| |
| static int |
| bpf_prog_load_check_attach(enum bpf_prog_type prog_type, |
| enum bpf_attach_type expected_attach_type, |
| struct btf *attach_btf, u32 btf_id, |
| struct bpf_prog *dst_prog) |
| { |
| if (btf_id) { |
| if (btf_id > BTF_MAX_TYPE) |
| return -EINVAL; |
| |
| if (!attach_btf && !dst_prog) |
| return -EINVAL; |
| |
| switch (prog_type) { |
| case BPF_PROG_TYPE_TRACING: |
| case BPF_PROG_TYPE_LSM: |
| case BPF_PROG_TYPE_STRUCT_OPS: |
| case BPF_PROG_TYPE_EXT: |
| break; |
| default: |
| return -EINVAL; |
| } |
| } |
| |
| if (attach_btf && (!btf_id || dst_prog)) |
| return -EINVAL; |
| |
| if (dst_prog && prog_type != BPF_PROG_TYPE_TRACING && |
| prog_type != BPF_PROG_TYPE_EXT) |
| return -EINVAL; |
| |
| switch (prog_type) { |
| case BPF_PROG_TYPE_CGROUP_SOCK: |
| switch (expected_attach_type) { |
| case BPF_CGROUP_INET_SOCK_CREATE: |
| case BPF_CGROUP_INET_SOCK_RELEASE: |
| case BPF_CGROUP_INET4_POST_BIND: |
| case BPF_CGROUP_INET6_POST_BIND: |
| return 0; |
| default: |
| return -EINVAL; |
| } |
| case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: |
| switch (expected_attach_type) { |
| case BPF_CGROUP_INET4_BIND: |
| case BPF_CGROUP_INET6_BIND: |
| case BPF_CGROUP_INET4_CONNECT: |
| case BPF_CGROUP_INET6_CONNECT: |
| case BPF_CGROUP_INET4_GETPEERNAME: |
| case BPF_CGROUP_INET6_GETPEERNAME: |
| case BPF_CGROUP_INET4_GETSOCKNAME: |
| case BPF_CGROUP_INET6_GETSOCKNAME: |
| case BPF_CGROUP_UDP4_SENDMSG: |
| case BPF_CGROUP_UDP6_SENDMSG: |
| case BPF_CGROUP_UDP4_RECVMSG: |
| case BPF_CGROUP_UDP6_RECVMSG: |
| return 0; |
| default: |
| return -EINVAL; |
| } |
| case BPF_PROG_TYPE_CGROUP_SKB: |
| switch (expected_attach_type) { |
| case BPF_CGROUP_INET_INGRESS: |
| case BPF_CGROUP_INET_EGRESS: |
| return 0; |
| default: |
| return -EINVAL; |
| } |
| case BPF_PROG_TYPE_CGROUP_SOCKOPT: |
| switch (expected_attach_type) { |
| case BPF_CGROUP_SETSOCKOPT: |
| case BPF_CGROUP_GETSOCKOPT: |
| return 0; |
| default: |
| return -EINVAL; |
| } |
| case BPF_PROG_TYPE_SK_LOOKUP: |
| if (expected_attach_type == BPF_SK_LOOKUP) |
| return 0; |
| return -EINVAL; |
| case BPF_PROG_TYPE_SK_REUSEPORT: |
| switch (expected_attach_type) { |
| case BPF_SK_REUSEPORT_SELECT: |
| case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE: |
| return 0; |
| default: |
| return -EINVAL; |
| } |
| case BPF_PROG_TYPE_SYSCALL: |
| case BPF_PROG_TYPE_EXT: |
| if (expected_attach_type) |
| return -EINVAL; |
| fallthrough; |
| default: |
| return 0; |
| } |
| } |
| |
| static bool is_net_admin_prog_type(enum bpf_prog_type prog_type) |
| { |
| switch (prog_type) { |
| case BPF_PROG_TYPE_SCHED_CLS: |
| case BPF_PROG_TYPE_SCHED_ACT: |
| case BPF_PROG_TYPE_XDP: |
| case BPF_PROG_TYPE_LWT_IN: |
| case BPF_PROG_TYPE_LWT_OUT: |
| case BPF_PROG_TYPE_LWT_XMIT: |
| case BPF_PROG_TYPE_LWT_SEG6LOCAL: |
| case BPF_PROG_TYPE_SK_SKB: |
| case BPF_PROG_TYPE_SK_MSG: |
| case BPF_PROG_TYPE_LIRC_MODE2: |
| case BPF_PROG_TYPE_FLOW_DISSECTOR: |
| case BPF_PROG_TYPE_CGROUP_DEVICE: |
| case BPF_PROG_TYPE_CGROUP_SOCK: |
| case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: |
| case BPF_PROG_TYPE_CGROUP_SOCKOPT: |
| case BPF_PROG_TYPE_CGROUP_SYSCTL: |
| case BPF_PROG_TYPE_SOCK_OPS: |
| case BPF_PROG_TYPE_EXT: /* extends any prog */ |
| return true; |
| case BPF_PROG_TYPE_CGROUP_SKB: |
| /* always unpriv */ |
| case BPF_PROG_TYPE_SK_REUSEPORT: |
| /* equivalent to SOCKET_FILTER. need CAP_BPF only */ |
| default: |
| return false; |
| } |
| } |
| |
| static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) |
| { |
| switch (prog_type) { |
| case BPF_PROG_TYPE_KPROBE: |
| case BPF_PROG_TYPE_TRACEPOINT: |
| case BPF_PROG_TYPE_PERF_EVENT: |
| case BPF_PROG_TYPE_RAW_TRACEPOINT: |
| case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: |
| case BPF_PROG_TYPE_TRACING: |
| case BPF_PROG_TYPE_LSM: |
| case BPF_PROG_TYPE_STRUCT_OPS: /* has access to struct sock */ |
| case BPF_PROG_TYPE_EXT: /* extends any prog */ |
| return true; |
| default: |
| return false; |
| } |
| } |
| |
| /* last field in 'union bpf_attr' used by this command */ |
| #define BPF_PROG_LOAD_LAST_FIELD core_relo_rec_size |
| |
| static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) |
| { |
| enum bpf_prog_type type = attr->prog_type; |
| struct bpf_prog *prog, *dst_prog = NULL; |
| struct btf *attach_btf = NULL; |
| int err; |
| char license[128]; |
| bool is_gpl; |
| |
| if (CHECK_ATTR(BPF_PROG_LOAD)) |
| return -EINVAL; |
| |
| if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | |
| BPF_F_ANY_ALIGNMENT | |
| BPF_F_TEST_STATE_FREQ | |
| BPF_F_SLEEPABLE | |
| BPF_F_TEST_RND_HI32 | |
| BPF_F_XDP_HAS_FRAGS)) |
| return -EINVAL; |
| |
| if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && |
| (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && |
| !bpf_capable()) |
| return -EPERM; |
| |
| /* copy eBPF program license from user space */ |
| if (strncpy_from_bpfptr(license, |
| make_bpfptr(attr->license, uattr.is_kernel), |
| sizeof(license) - 1) < 0) |
| return -EFAULT; |
| license[sizeof(license) - 1] = 0; |
| |
| /* eBPF programs must be GPL compatible to use GPL-ed functions */ |
| is_gpl = license_is_gpl_compatible(license); |
| |
| if (attr->insn_cnt == 0 || |
| attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) |
| return -E2BIG; |
| if (type != BPF_PROG_TYPE_SOCKET_FILTER && |
| type != BPF_PROG_TYPE_CGROUP_SKB && |
| !bpf_capable()) |
| return -EPERM; |
| |
| if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN) && !capable(CAP_SYS_ADMIN)) |
| return -EPERM; |
| if (is_perfmon_prog_type(type) && !perfmon_capable()) |
| return -EPERM; |
| |
| /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog |
| * or btf, we need to check which one it is |
| */ |
| if (attr->attach_prog_fd) { |
| dst_prog = bpf_prog_get(attr->attach_prog_fd); |
| if (IS_ERR(dst_prog)) { |
| dst_prog = NULL; |
| attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); |
| if (IS_ERR(attach_btf)) |
| return -EINVAL; |
| if (!btf_is_kernel(attach_btf)) { |
| /* attaching through specifying bpf_prog's BTF |
| * objects directly might be supported eventually |
| */ |
| btf_put(attach_btf); |
| return -ENOTSUPP; |
| } |
| } |
| } else if (attr->attach_btf_id) { |
| /* fall back to vmlinux BTF, if BTF type ID is specified */ |
| attach_btf = bpf_get_btf_vmlinux(); |
| if (IS_ERR(attach_btf)) |
| return PTR_ERR(attach_btf); |
| if (!attach_btf) |
| return -EINVAL; |
| btf_get(attach_btf); |
| } |
| |
| bpf_prog_load_fixup_attach_type(attr); |
| if (bpf_prog_load_check_attach(type, attr->expected_attach_type, |
| attach_btf, attr->attach_btf_id, |
| dst_prog)) { |
| if (dst_prog) |
| bpf_prog_put(dst_prog); |
| if (attach_btf) |
| btf_put(attach_btf); |
| return -EINVAL; |
| } |
| |
| /* plain bpf_prog allocation */ |
| prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); |
| if (!prog) { |
| if (dst_prog) |
| bpf_prog_put(dst_prog); |
| if (attach_btf) |
| btf_put(attach_btf); |
| return -ENOMEM; |
| } |
| |
| prog->expected_attach_type = attr->expected_attach_type; |
| prog->aux->attach_btf = attach_btf; |
| prog->aux->attach_btf_id = attr->attach_btf_id; |
| prog->aux->dst_prog = dst_prog; |
| prog->aux->offload_requested = !!attr->prog_ifindex; |
| prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; |
| prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; |
| |
| err = security_bpf_prog_alloc(prog->aux); |
| if (err) |
| goto free_prog; |
| |
| prog->aux->user = get_current_user(); |
| prog->len = attr->insn_cnt; |
| |
| err = -EFAULT; |
| if (copy_from_bpfptr(prog->insns, |
| make_bpfptr(attr->insns, uattr.is_kernel), |
| bpf_prog_insn_size(prog)) != 0) |
| goto free_prog_sec; |
| |
| prog->orig_prog = NULL; |
| prog->jited = 0; |
| |
| atomic64_set(&prog->aux->refcnt, 1); |
| prog->gpl_compatible = is_gpl ? 1 : 0; |
| |
| if (bpf_prog_is_dev_bound(prog->aux)) { |
| err = bpf_prog_offload_init(prog, attr); |
| if (err) |
| goto free_prog_sec; |
| } |
| |
| /* find program type: socket_filter vs tracing_filter */ |
| err = find_prog_type(type, prog); |
| if (err < 0) |
| goto free_prog_sec; |
| |
| prog->aux->load_time = ktime_get_boottime_ns(); |
| err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, |
| sizeof(attr->prog_name)); |
| if (err < 0) |
| goto free_prog_sec; |
| |
| /* run eBPF verifier */ |
| err = bpf_check(&prog, attr, uattr); |
| if (err < 0) |
| goto free_used_maps; |
| |
| prog = bpf_prog_select_runtime(prog, &err); |
| if (err < 0) |
| goto free_used_maps; |
| |
| err = bpf_prog_alloc_id(prog); |
| if (err) |
| goto free_used_maps; |
| |
| /* Upon success of bpf_prog_alloc_id(), the BPF prog is |
| * effectively publicly exposed. However, retrieving via |
| * bpf_prog_get_fd_by_id() will take another reference, |
| * therefore it cannot be gone underneath us. |
| * |
| * Only for the time /after/ successful bpf_prog_new_fd() |
| * and before returning to userspace, we might just hold |
| * one reference and any parallel close on that fd could |
| * rip everything out. Hence, below notifications must |
| * happen before bpf_prog_new_fd(). |
| * |
| * Also, any failure handling from this point onwards must |
| * be using bpf_prog_put() given the program is exposed. |
| */ |
| bpf_prog_kallsyms_add(prog); |
| perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0); |
| bpf_audit_prog(prog, BPF_AUDIT_LOAD); |
| |
| err = bpf_prog_new_fd(prog); |
| if (err < 0) |
| bpf_prog_put(prog); |
| return err; |
| |
| free_used_maps: |
| /* In case we have subprogs, we need to wait for a grace |
| * period before we can tear down JIT memory since symbols |
| * are already exposed under kallsyms. |
| */ |
| __bpf_prog_put_noref(prog, prog->aux->func_cnt); |
| return err; |
| free_prog_sec: |
| free_uid(prog->aux->user); |
| security_bpf_prog_free(prog->aux); |
| free_prog: |
| if (prog->aux->attach_btf) |
| btf_put(prog->aux->attach_btf); |
| bpf_prog_free(prog); |
| return err; |
| } |
| |
| #define BPF_OBJ_LAST_FIELD file_flags |
| |
| static int bpf_obj_pin(const union bpf_attr *attr) |
| { |
| if (CHECK_ATTR(BPF_OBJ) || attr->file_flags != 0) |
| return -EINVAL; |
| |
| return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname)); |
| } |
| |
| static int bpf_obj_get(const union bpf_attr *attr) |
| { |
| if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 || |
| attr->file_flags & ~BPF_OBJ_FLAG_MASK) |
| return -EINVAL; |
| |
| return bpf_obj_get_user(u64_to_user_ptr(attr->pathname), |
| attr->file_flags); |
| } |
| |
| void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, |
| const struct bpf_link_ops *ops, struct bpf_prog *prog) |
| { |
| atomic64_set(&link->refcnt, 1); |
| link->type = type; |
| link->id = 0; |
| link->ops = ops; |
| link->prog = prog; |
| } |
| |
| static void bpf_link_free_id(int id) |
| { |
| if (!id) |
| return; |
| |
| spin_lock_bh(&link_idr_lock); |
| idr_remove(&link_idr, id); |
| spin_unlock_bh(&link_idr_lock); |
| } |
| |
| /* Clean up bpf_link and corresponding anon_inode file and FD. After |
| * anon_inode is created, bpf_link can't be just kfree()'d due to deferred |
| * anon_inode's release() call. This helper marksbpf_link as |
| * defunct, releases anon_inode file and puts reserved FD. bpf_prog's refcnt |
| * is not decremented, it's the responsibility of a calling code that failed |
| * to complete bpf_link initialization. |
| */ |
| void bpf_link_cleanup(struct bpf_link_primer *primer) |
| { |
| primer->link->prog = NULL; |
| bpf_link_free_id(primer->id); |
| fput(primer->file); |
| put_unused_fd(primer->fd); |
| } |
| |
| void bpf_link_inc(struct bpf_link *link) |
| { |
| atomic64_inc(&link->refcnt); |
| } |
| |
| /* bpf_link_free is guaranteed to be called from process context */ |
| static void bpf_link_free(struct bpf_link *link) |
| { |
| bpf_link_free_id(link->id); |
| if (link->prog) { |
| /* detach BPF program, clean up used resources */ |
| link->ops->release(link); |
| bpf_prog_put(link->prog); |
| } |
| /* free bpf_link and its containing memory */ |
| link->ops->dealloc(link); |
| } |
| |
| static void bpf_link_put_deferred(struct work_struct *work) |
| { |
| struct bpf_link *link = container_of(work, struct bpf_link, work); |
| |
| bpf_link_free(link); |
| } |
| |
| /* bpf_link_put can be called from atomic context, but ensures that resources |
| * are freed from process context |
| */ |
| void bpf_link_put(struct bpf_link *link) |
| { |
| if (!atomic64_dec_and_test(&link->refcnt)) |
| return; |
| |
| if (in_atomic()) { |
| INIT_WORK(&link->work, bpf_link_put_deferred); |
| schedule_work(&link->work); |
| } else { |
| bpf_link_free(link); |
| } |
| } |
| EXPORT_SYMBOL(bpf_link_put); |
| |
| static int bpf_link_release(struct inode *inode, struct file *filp) |
| { |
| struct bpf_link *link = filp->private_data; |
| |
| bpf_link_put(link); |
| return 0; |
| } |
| |
| #ifdef CONFIG_PROC_FS |
| #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) |
| #define BPF_MAP_TYPE(_id, _ops) |
| #define BPF_LINK_TYPE(_id, _name) [_id] = #_name, |
| static const char *bpf_link_type_strs[] = { |
| [BPF_LINK_TYPE_UNSPEC] = "<invalid>", |
| #include <linux/bpf_types.h> |
| }; |
| #undef BPF_PROG_TYPE |
| #undef BPF_MAP_TYPE |
| #undef BPF_LINK_TYPE |
| |
| static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) |
| { |
| const struct bpf_link *link = filp->private_data; |
| const struct bpf_prog *prog = link->prog; |
| char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; |
| |
| bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); |
| seq_printf(m, |
| "link_type:\t%s\n" |
| "link_id:\t%u\n" |
| "prog_tag:\t%s\n" |
| "prog_id:\t%u\n", |
| bpf_link_type_strs[link->type], |
| link->id, |
| prog_tag, |
| prog->aux->id); |
| if (link->ops->show_fdinfo) |
| link->ops->show_fdinfo(link, m); |
| } |
| #endif |
| |
| static const struct file_operations bpf_link_fops = { |
| #ifdef CONFIG_PROC_FS |
| .show_fdinfo = bpf_link_show_fdinfo, |
| #endif |
| .release = bpf_link_release, |
| .read = bpf_dummy_read, |
| .write = bpf_dummy_write, |
| }; |
| |
| static int bpf_link_alloc_id(struct bpf_link *link) |
| { |
| int id; |
| |
| idr_preload(GFP_KERNEL); |
| spin_lock_bh(&link_idr_lock); |
| id = idr_alloc_cyclic(&link_idr, link, 1, INT_MAX, GFP_ATOMIC); |
| spin_unlock_bh(&link_idr_lock); |
| idr_preload_end(); |
| |
| return id; |
| } |
| |
| /* Prepare bpf_link to be exposed to user-space by allocating anon_inode file, |
| * reserving unused FD and allocating ID from link_idr. This is to be paired |
| * with bpf_link_settle() to install FD and ID and expose bpf_link to |
| * user-space, if bpf_link is successfully attached. If not, bpf_link and |
| * pre-allocated resources are to be freed with bpf_cleanup() call. All the |
| * transient state is passed around in struct bpf_link_primer. |
| * This is preferred way to create and initialize bpf_link, especially when |
| * there are complicated and expensive operations in between creating bpf_link |
| * itself and attaching it to BPF hook. By using bpf_link_prime() and |
| * bpf_link_settle() kernel code using bpf_link doesn't have to perform |
| * expensive (and potentially failing) roll back operations in a rare case |
| * that file, FD, or ID can't be allocated. |
| */ |
| int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer) |
| { |
| struct file *file; |
| int fd, id; |
| |
| fd = get_unused_fd_flags(O_CLOEXEC); |
| if (fd < 0) |
| return fd; |
| |
| |
| id = bpf_link_alloc_id(link); |
| if (id < 0) { |
| put_unused_fd(fd); |
| return id; |
| } |
| |
| file = anon_inode_getfile("bpf_link", &bpf_link_fops, link, O_CLOEXEC); |
| if (IS_ERR(file)) { |
| bpf_link_free_id(id); |
| put_unused_fd(fd); |
| return PTR_ERR(file); |
| } |
| |
| primer->link = link; |
| primer->file = file; |
| primer->fd = fd; |
| primer->id = id; |
| return 0; |
| } |
| |
| int bpf_link_settle(struct bpf_link_primer *primer) |
| { |
| /* make bpf_link fetchable by ID */ |
| spin_lock_bh(&link_idr_lock); |
| primer->link->id = primer->id; |
| spin_unlock_bh(&link_idr_lock); |
| /* make bpf_link fetchable by FD */ |
| fd_install(primer->fd, primer->file); |
| /* pass through installed FD */ |
| return primer->fd; |
| } |
| |
| int bpf_link_new_fd(struct bpf_link *link) |
| { |
| return anon_inode_getfd("bpf-link", &bpf_link_fops, link, O_CLOEXEC); |
| } |
| |
| struct bpf_link *bpf_link_get_from_fd(u32 ufd) |
| { |
| struct fd f = fdget(ufd); |
| struct bpf_link *link; |
| |
| if (!f.file) |
| return ERR_PTR(-EBADF); |
| if (f.file->f_op != &bpf_link_fops) { |
| fdput(f); |
| return ERR_PTR(-EINVAL); |
| } |
| |
| link = f.file->private_data; |
| bpf_link_inc(link); |
| fdput(f); |
| |
| return link; |
| } |
| EXPORT_SYMBOL(bpf_link_get_from_fd); |
| |
| static void bpf_tracing_link_release(struct bpf_link *link) |
| { |
| struct bpf_tracing_link *tr_link = |
| container_of(link, struct bpf_tracing_link, link.link); |
| |
| WARN_ON_ONCE(bpf_trampoline_unlink_prog(&tr_link->link, |
| tr_link->trampoline)); |
| |
| bpf_trampoline_put(tr_link->trampoline); |
| |
| /* tgt_prog is NULL if target is a kernel function */ |
| if (tr_link->tgt_prog) |
| bpf_prog_put(tr_link->tgt_prog); |
| } |
| |
| static void bpf_tracing_link_dealloc(struct bpf_link *link) |
| { |
| struct bpf_tracing_link *tr_link = |
| container_of(link, struct bpf_tracing_link, link.link); |
| |
| kfree(tr_link); |
| } |
| |
| static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link, |
| struct seq_file *seq) |
| { |
| struct bpf_tracing_link *tr_link = |
| container_of(link, struct bpf_tracing_link, link.link); |
| |
| seq_printf(seq, |
| "attach_type:\t%d\n", |
| tr_link->attach_type); |
| } |
| |
| static int bpf_tracing_link_fill_link_info(const struct bpf_link *link, |
| struct bpf_link_info *info) |
| { |
| struct bpf_tracing_link *tr_link = |
| container_of(link, struct bpf_tracing_link, link.link); |
| |
| info->tracing.attach_type = tr_link->attach_type; |
| bpf_trampoline_unpack_key(tr_link->trampoline->key, |
| &info->tracing.target_obj_id, |
| &info->tracing.target_btf_id); |
| |
| return 0; |
| } |
| |
| static const struct bpf_link_ops bpf_tracing_link_lops = { |
| .release = bpf_tracing_link_release, |
| .dealloc = bpf_tracing_link_dealloc, |
| .show_fdinfo = bpf_tracing_link_show_fdinfo, |
| .fill_link_info = bpf_tracing_link_fill_link_info, |
| }; |
| |
| static int bpf_tracing_prog_attach(struct bpf_prog *prog, |
| int tgt_prog_fd, |
| u32 btf_id, |
| u64 bpf_cookie) |
| { |
| struct bpf_link_primer link_primer; |
| struct bpf_prog *tgt_prog = NULL; |
| struct bpf_trampoline *tr = NULL; |
| struct bpf_tracing_link *link; |
| u64 key = 0; |
| int err; |
| |
| switch (prog->type) { |
| case BPF_PROG_TYPE_TRACING: |
| if (prog->expected_attach_type != BPF_TRACE_FENTRY && |
| prog->expected_attach_type != BPF_TRACE_FEXIT && |
| prog->expected_attach_type != BPF_MODIFY_RETURN) { |
| err = -EINVAL; |
| goto out_put_prog; |
| } |
| break; |
| case BPF_PROG_TYPE_EXT: |
| if (prog->expected_attach_type != 0) { |
| err = -EINVAL; |
| goto out_put_prog; |
| } |
| break; |
| case BPF_PROG_TYPE_LSM: |
| if (prog->expected_attach_type != BPF_LSM_MAC) { |
| err = -EINVAL; |
| goto out_put_prog; |
| } |
| break; |
| default: |
| err = -EINVAL; |
| goto out_put_prog; |
| } |
| |
| if (!!tgt_prog_fd != !!btf_id) { |
| err = -EINVAL; |
| goto out_put_prog; |
| } |
| |
| if (tgt_prog_fd) { |
| /* For now we only allow new targets for BPF_PROG_TYPE_EXT */ |
| if (prog->type != BPF_PROG_TYPE_EXT) { |
| err = -EINVAL; |
| goto out_put_prog; |
| } |
| |
| tgt_prog = bpf_prog_get(tgt_prog_fd); |
| if (IS_ERR(tgt_prog)) { |
| err = PTR_ERR(tgt_prog); |
| tgt_prog = NULL; |
| goto out_put_prog; |
| } |
| |
| key = bpf_trampoline_compute_key(tgt_prog, NULL, btf_id); |
| } |
| |
| link = kzalloc(sizeof(*link), GFP_USER); |
| if (!link) { |
| err = -ENOMEM; |
| goto out_put_prog; |
| } |
| bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING, |
| &bpf_tracing_link_lops, prog); |
| link->attach_type = prog->expected_attach_type; |
| link->link.cookie = bpf_cookie; |
| |
| mutex_lock(&prog->aux->dst_mutex); |
| |
| /* There are a few possible cases here: |
| * |
| * - if prog->aux->dst_trampoline is set, the program was just loaded |
| * and not yet attached to anything, so we can use the values stored |
| * in prog->aux |
| * |
| * - if prog->aux->dst_trampoline is NULL, the program has already been |
| * attached to a target and its initial target was cleared (below) |
| * |
| * - if tgt_prog != NULL, the caller specified tgt_prog_fd + |
| * target_btf_id using the link_create API. |
| * |
| * - if tgt_prog == NULL when this function was called using the old |
| * raw_tracepoint_open API, and we need a target from prog->aux |
| * |
| * - if prog->aux->dst_trampoline and tgt_prog is NULL, the program |
| * was detached and is going for re-attachment. |
| * |
| * - if prog->aux->dst_trampoline is NULL and tgt_prog and prog->aux->attach_btf |
| * are NULL, then program was already attached and user did not provide |
| * tgt_prog_fd so we have no way to find out or create trampoline |
| */ |
| if (!prog->aux->dst_trampoline && !tgt_prog) { |
| /* |
| * Allow re-attach for TRACING and LSM programs. If it's |
| * currently linked, bpf_trampoline_link_prog will fail. |
| * EXT programs need to specify tgt_prog_fd, so they |
| * re-attach in separate code path. |
| */ |
| if (prog->type != BPF_PROG_TYPE_TRACING && |
| prog->type != BPF_PROG_TYPE_LSM) { |
| err = -EINVAL; |
| goto out_unlock; |
| } |
| /* We can allow re-attach only if we have valid attach_btf. */ |
| if (!prog->aux->attach_btf) { |
| err = -EINVAL; |
| goto out_unlock; |
| } |
| btf_id = prog->aux->attach_btf_id; |
| key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, btf_id); |
| } |
| |
| if (!prog->aux->dst_trampoline || |
| (key && key != prog->aux->dst_trampoline->key)) { |
| /* If there is no saved target, or the specified target is |
| * different from the destination specified at load time, we |
| * need a new trampoline and a check for compatibility |
| */ |
| struct bpf_attach_target_info tgt_info = {}; |
| |
| |