KP Singh | 8ea6368 | 2020-08-25 20:29:17 +0200 | [diff] [blame] | 1 | // SPDX-License-Identifier: GPL-2.0 |
| 2 | /* |
| 3 | * Copyright (c) 2019 Facebook |
| 4 | * Copyright 2020 Google LLC. |
| 5 | */ |
| 6 | |
| 7 | #include <linux/rculist.h> |
| 8 | #include <linux/list.h> |
| 9 | #include <linux/hash.h> |
| 10 | #include <linux/types.h> |
| 11 | #include <linux/spinlock.h> |
| 12 | #include <linux/bpf.h> |
| 13 | #include <linux/bpf_local_storage.h> |
| 14 | #include <net/sock.h> |
| 15 | #include <uapi/linux/sock_diag.h> |
| 16 | #include <uapi/linux/btf.h> |
| 17 | #include <linux/bpf_lsm.h> |
| 18 | #include <linux/btf_ids.h> |
| 19 | #include <linux/fdtable.h> |
| 20 | |
| 21 | DEFINE_BPF_STORAGE_CACHE(inode_cache); |
| 22 | |
| 23 | static struct bpf_local_storage __rcu ** |
| 24 | inode_storage_ptr(void *owner) |
| 25 | { |
| 26 | struct inode *inode = owner; |
| 27 | struct bpf_storage_blob *bsb; |
| 28 | |
| 29 | bsb = bpf_inode(inode); |
| 30 | if (!bsb) |
| 31 | return NULL; |
| 32 | return &bsb->storage; |
| 33 | } |
| 34 | |
| 35 | static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode, |
| 36 | struct bpf_map *map, |
| 37 | bool cacheit_lockit) |
| 38 | { |
| 39 | struct bpf_local_storage *inode_storage; |
| 40 | struct bpf_local_storage_map *smap; |
| 41 | struct bpf_storage_blob *bsb; |
| 42 | |
| 43 | bsb = bpf_inode(inode); |
| 44 | if (!bsb) |
| 45 | return NULL; |
| 46 | |
| 47 | inode_storage = rcu_dereference(bsb->storage); |
| 48 | if (!inode_storage) |
| 49 | return NULL; |
| 50 | |
| 51 | smap = (struct bpf_local_storage_map *)map; |
| 52 | return bpf_local_storage_lookup(inode_storage, smap, cacheit_lockit); |
| 53 | } |
| 54 | |
| 55 | void bpf_inode_storage_free(struct inode *inode) |
| 56 | { |
| 57 | struct bpf_local_storage_elem *selem; |
| 58 | struct bpf_local_storage *local_storage; |
| 59 | bool free_inode_storage = false; |
| 60 | struct bpf_storage_blob *bsb; |
| 61 | struct hlist_node *n; |
| 62 | |
| 63 | bsb = bpf_inode(inode); |
| 64 | if (!bsb) |
| 65 | return; |
| 66 | |
| 67 | rcu_read_lock(); |
| 68 | |
| 69 | local_storage = rcu_dereference(bsb->storage); |
| 70 | if (!local_storage) { |
| 71 | rcu_read_unlock(); |
| 72 | return; |
| 73 | } |
| 74 | |
| 75 | /* Netiher the bpf_prog nor the bpf-map's syscall |
| 76 | * could be modifying the local_storage->list now. |
| 77 | * Thus, no elem can be added-to or deleted-from the |
| 78 | * local_storage->list by the bpf_prog or by the bpf-map's syscall. |
| 79 | * |
| 80 | * It is racing with bpf_local_storage_map_free() alone |
| 81 | * when unlinking elem from the local_storage->list and |
| 82 | * the map's bucket->list. |
| 83 | */ |
| 84 | raw_spin_lock_bh(&local_storage->lock); |
| 85 | hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) { |
| 86 | /* Always unlink from map before unlinking from |
| 87 | * local_storage. |
| 88 | */ |
| 89 | bpf_selem_unlink_map(selem); |
| 90 | free_inode_storage = bpf_selem_unlink_storage_nolock( |
| 91 | local_storage, selem, false); |
| 92 | } |
| 93 | raw_spin_unlock_bh(&local_storage->lock); |
| 94 | rcu_read_unlock(); |
| 95 | |
| 96 | /* free_inoode_storage should always be true as long as |
| 97 | * local_storage->list was non-empty. |
| 98 | */ |
| 99 | if (free_inode_storage) |
| 100 | kfree_rcu(local_storage, rcu); |
| 101 | } |
| 102 | |
| 103 | static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key) |
| 104 | { |
| 105 | struct bpf_local_storage_data *sdata; |
| 106 | struct file *f; |
| 107 | int fd; |
| 108 | |
| 109 | fd = *(int *)key; |
| 110 | f = fget_raw(fd); |
| 111 | if (!f) |
| 112 | return NULL; |
| 113 | |
| 114 | sdata = inode_storage_lookup(f->f_inode, map, true); |
| 115 | fput(f); |
| 116 | return sdata ? sdata->data : NULL; |
| 117 | } |
| 118 | |
| 119 | static int bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key, |
| 120 | void *value, u64 map_flags) |
| 121 | { |
| 122 | struct bpf_local_storage_data *sdata; |
| 123 | struct file *f; |
| 124 | int fd; |
| 125 | |
| 126 | fd = *(int *)key; |
| 127 | f = fget_raw(fd); |
| 128 | if (!f || !inode_storage_ptr(f->f_inode)) |
| 129 | return -EBADF; |
| 130 | |
| 131 | sdata = bpf_local_storage_update(f->f_inode, |
| 132 | (struct bpf_local_storage_map *)map, |
| 133 | value, map_flags); |
| 134 | fput(f); |
| 135 | return PTR_ERR_OR_ZERO(sdata); |
| 136 | } |
| 137 | |
| 138 | static int inode_storage_delete(struct inode *inode, struct bpf_map *map) |
| 139 | { |
| 140 | struct bpf_local_storage_data *sdata; |
| 141 | |
| 142 | sdata = inode_storage_lookup(inode, map, false); |
| 143 | if (!sdata) |
| 144 | return -ENOENT; |
| 145 | |
| 146 | bpf_selem_unlink(SELEM(sdata)); |
| 147 | |
| 148 | return 0; |
| 149 | } |
| 150 | |
| 151 | static int bpf_fd_inode_storage_delete_elem(struct bpf_map *map, void *key) |
| 152 | { |
| 153 | struct file *f; |
| 154 | int fd, err; |
| 155 | |
| 156 | fd = *(int *)key; |
| 157 | f = fget_raw(fd); |
| 158 | if (!f) |
| 159 | return -EBADF; |
| 160 | |
| 161 | err = inode_storage_delete(f->f_inode, map); |
| 162 | fput(f); |
| 163 | return err; |
| 164 | } |
| 165 | |
| 166 | BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode, |
| 167 | void *, value, u64, flags) |
| 168 | { |
| 169 | struct bpf_local_storage_data *sdata; |
| 170 | |
| 171 | if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) |
| 172 | return (unsigned long)NULL; |
| 173 | |
| 174 | /* explicitly check that the inode_storage_ptr is not |
| 175 | * NULL as inode_storage_lookup returns NULL in this case and |
| 176 | * bpf_local_storage_update expects the owner to have a |
| 177 | * valid storage pointer. |
| 178 | */ |
| 179 | if (!inode_storage_ptr(inode)) |
| 180 | return (unsigned long)NULL; |
| 181 | |
| 182 | sdata = inode_storage_lookup(inode, map, true); |
| 183 | if (sdata) |
| 184 | return (unsigned long)sdata->data; |
| 185 | |
| 186 | /* This helper must only called from where the inode is gurranteed |
| 187 | * to have a refcount and cannot be freed. |
| 188 | */ |
| 189 | if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) { |
| 190 | sdata = bpf_local_storage_update( |
| 191 | inode, (struct bpf_local_storage_map *)map, value, |
| 192 | BPF_NOEXIST); |
| 193 | return IS_ERR(sdata) ? (unsigned long)NULL : |
| 194 | (unsigned long)sdata->data; |
| 195 | } |
| 196 | |
| 197 | return (unsigned long)NULL; |
| 198 | } |
| 199 | |
| 200 | BPF_CALL_2(bpf_inode_storage_delete, |
| 201 | struct bpf_map *, map, struct inode *, inode) |
| 202 | { |
| 203 | /* This helper must only called from where the inode is gurranteed |
| 204 | * to have a refcount and cannot be freed. |
| 205 | */ |
| 206 | return inode_storage_delete(inode, map); |
| 207 | } |
| 208 | |
| 209 | static int notsupp_get_next_key(struct bpf_map *map, void *key, |
| 210 | void *next_key) |
| 211 | { |
| 212 | return -ENOTSUPP; |
| 213 | } |
| 214 | |
| 215 | static struct bpf_map *inode_storage_map_alloc(union bpf_attr *attr) |
| 216 | { |
| 217 | struct bpf_local_storage_map *smap; |
| 218 | |
| 219 | smap = bpf_local_storage_map_alloc(attr); |
| 220 | if (IS_ERR(smap)) |
| 221 | return ERR_CAST(smap); |
| 222 | |
| 223 | smap->cache_idx = bpf_local_storage_cache_idx_get(&inode_cache); |
| 224 | return &smap->map; |
| 225 | } |
| 226 | |
| 227 | static void inode_storage_map_free(struct bpf_map *map) |
| 228 | { |
| 229 | struct bpf_local_storage_map *smap; |
| 230 | |
| 231 | smap = (struct bpf_local_storage_map *)map; |
| 232 | bpf_local_storage_cache_idx_free(&inode_cache, smap->cache_idx); |
| 233 | bpf_local_storage_map_free(smap); |
| 234 | } |
| 235 | |
| 236 | static int inode_storage_map_btf_id; |
| 237 | const struct bpf_map_ops inode_storage_map_ops = { |
Martin KaFai Lau | f4d0525 | 2020-08-27 18:18:06 -0700 | [diff] [blame] | 238 | .map_meta_equal = bpf_map_meta_equal, |
KP Singh | 8ea6368 | 2020-08-25 20:29:17 +0200 | [diff] [blame] | 239 | .map_alloc_check = bpf_local_storage_map_alloc_check, |
| 240 | .map_alloc = inode_storage_map_alloc, |
| 241 | .map_free = inode_storage_map_free, |
| 242 | .map_get_next_key = notsupp_get_next_key, |
| 243 | .map_lookup_elem = bpf_fd_inode_storage_lookup_elem, |
| 244 | .map_update_elem = bpf_fd_inode_storage_update_elem, |
| 245 | .map_delete_elem = bpf_fd_inode_storage_delete_elem, |
| 246 | .map_check_btf = bpf_local_storage_map_check_btf, |
| 247 | .map_btf_name = "bpf_local_storage_map", |
| 248 | .map_btf_id = &inode_storage_map_btf_id, |
| 249 | .map_owner_storage_ptr = inode_storage_ptr, |
| 250 | }; |
| 251 | |
Lorenz Bauer | 9436ef6 | 2020-09-21 13:12:20 +0100 | [diff] [blame] | 252 | BTF_ID_LIST_SINGLE(bpf_inode_storage_btf_ids, struct, inode) |
KP Singh | 8ea6368 | 2020-08-25 20:29:17 +0200 | [diff] [blame] | 253 | |
| 254 | const struct bpf_func_proto bpf_inode_storage_get_proto = { |
| 255 | .func = bpf_inode_storage_get, |
| 256 | .gpl_only = false, |
| 257 | .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, |
| 258 | .arg1_type = ARG_CONST_MAP_PTR, |
| 259 | .arg2_type = ARG_PTR_TO_BTF_ID, |
Lorenz Bauer | 9436ef6 | 2020-09-21 13:12:20 +0100 | [diff] [blame] | 260 | .arg2_btf_id = &bpf_inode_storage_btf_ids[0], |
KP Singh | 8ea6368 | 2020-08-25 20:29:17 +0200 | [diff] [blame] | 261 | .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, |
| 262 | .arg4_type = ARG_ANYTHING, |
KP Singh | 8ea6368 | 2020-08-25 20:29:17 +0200 | [diff] [blame] | 263 | }; |
| 264 | |
| 265 | const struct bpf_func_proto bpf_inode_storage_delete_proto = { |
| 266 | .func = bpf_inode_storage_delete, |
| 267 | .gpl_only = false, |
| 268 | .ret_type = RET_INTEGER, |
| 269 | .arg1_type = ARG_CONST_MAP_PTR, |
| 270 | .arg2_type = ARG_PTR_TO_BTF_ID, |
Lorenz Bauer | 9436ef6 | 2020-09-21 13:12:20 +0100 | [diff] [blame] | 271 | .arg2_btf_id = &bpf_inode_storage_btf_ids[0], |
KP Singh | 8ea6368 | 2020-08-25 20:29:17 +0200 | [diff] [blame] | 272 | }; |