556 558 1 558 455 420 436 437 434 565 8 561 2 585 584 7 4 24 430 412 1 17 529 2 1 2 20 1 416 566 6 4 557 558 556 1 87 327 1 413 2 414 10 2 4 2 27 1 2 17 9 19 9 17 3 16 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2017 Facebook */ #include <linux/bpf.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/etherdevice.h> #include <linux/filter.h> #include <linux/sched/signal.h> #include <net/bpf_sk_storage.h> #include <net/sock.h> #include <net/tcp.h> #define CREATE_TRACE_POINTS #include <trace/events/bpf_test_run.h> static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *retval, u32 *time) { struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { NULL }; enum bpf_cgroup_storage_type stype; u64 time_start, time_spent = 0; int ret = 0; u32 i; for_each_cgroup_storage_type(stype) { storage[stype] = bpf_cgroup_storage_alloc(prog, stype); if (IS_ERR(storage[stype])) { storage[stype] = NULL; for_each_cgroup_storage_type(stype) bpf_cgroup_storage_free(storage[stype]); return -ENOMEM; } } if (!repeat) repeat = 1; rcu_read_lock(); preempt_disable(); time_start = ktime_get_ns(); for (i = 0; i < repeat; i++) { bpf_cgroup_storage_set(storage); *retval = BPF_PROG_RUN(prog, ctx); if (signal_pending(current)) { ret = -EINTR; break; } if (need_resched()) { time_spent += ktime_get_ns() - time_start; preempt_enable(); rcu_read_unlock(); cond_resched(); rcu_read_lock(); preempt_disable(); time_start = ktime_get_ns(); } } time_spent += ktime_get_ns() - time_start; preempt_enable(); rcu_read_unlock(); do_div(time_spent, repeat); *time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent; for_each_cgroup_storage_type(stype) bpf_cgroup_storage_free(storage[stype]); return ret; } static int bpf_test_finish(const union bpf_attr *kattr, union bpf_attr __user *uattr, const void *data, u32 size, u32 retval, u32 duration) { void __user *data_out = u64_to_user_ptr(kattr->test.data_out); int err = -EFAULT; u32 copy_size = size; /* Clamp copy if the user has provided a size hint, but copy the full * buffer if not to retain old behaviour. */ if (kattr->test.data_size_out && copy_size > kattr->test.data_size_out) { copy_size = kattr->test.data_size_out; err = -ENOSPC; } if (data_out && copy_to_user(data_out, data, copy_size)) goto out; if (copy_to_user(&uattr->test.data_size_out, &size, sizeof(size))) goto out; if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval))) goto out; if (copy_to_user(&uattr->test.duration, &duration, sizeof(duration))) goto out; if (err != -ENOSPC) err = 0; out: trace_bpf_test_finish(&err); return err; } static void *bpf_test_init(const union bpf_attr *kattr, u32 size, u32 headroom, u32 tailroom) { void __user *data_in = u64_to_user_ptr(kattr->test.data_in); void *data; if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom) return ERR_PTR(-EINVAL); size = SKB_DATA_ALIGN(size); data = kzalloc(size + headroom + tailroom, GFP_USER); if (!data) return ERR_PTR(-ENOMEM); if (copy_from_user(data + headroom, data_in, size)) { kfree(data); return ERR_PTR(-EFAULT); } return data; } static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size) { void __user *data_in = u64_to_user_ptr(kattr->test.ctx_in); void __user *data_out = u64_to_user_ptr(kattr->test.ctx_out); u32 size = kattr->test.ctx_size_in; void *data; int err; if (!data_in && !data_out) return NULL; data = kzalloc(max_size, GFP_USER); if (!data) return ERR_PTR(-ENOMEM); if (data_in) { err = bpf_check_uarg_tail_zero(data_in, max_size, size); if (err) { kfree(data); return ERR_PTR(err); } size = min_t(u32, max_size, size); if (copy_from_user(data, data_in, size)) { kfree(data); return ERR_PTR(-EFAULT); } } return data; } static int bpf_ctx_finish(const union bpf_attr *kattr, union bpf_attr __user *uattr, const void *data, u32 size) { void __user *data_out = u64_to_user_ptr(kattr->test.ctx_out); int err = -EFAULT; u32 copy_size = size; if (!data || !data_out) return 0; if (copy_size > kattr->test.ctx_size_out) { copy_size = kattr->test.ctx_size_out; err = -ENOSPC; } if (copy_to_user(data_out, data, copy_size)) goto out; if (copy_to_user(&uattr->test.ctx_size_out, &size, sizeof(size))) goto out; if (err != -ENOSPC) err = 0; out: return err; } /** * range_is_zero - test whether buffer is initialized * @buf: buffer to check * @from: check from this position * @to: check up until (excluding) this position * * This function returns true if the there is a non-zero byte * in the buf in the range [from,to). */ static inline bool range_is_zero(void *buf, size_t from, size_t to) { return !memchr_inv((u8 *)buf + from, 0, to - from); } static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) { struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb; if (!__skb) return 0; /* make sure the fields we don't use are zeroed */ if (!range_is_zero(__skb, 0, offsetof(struct __sk_buff, priority))) return -EINVAL; /* priority is allowed */ if (!range_is_zero(__skb, offsetof(struct __sk_buff, priority) + FIELD_SIZEOF(struct __sk_buff, priority), offsetof(struct __sk_buff, cb))) return -EINVAL; /* cb is allowed */ if (!range_is_zero(__skb, offsetof(struct __sk_buff, cb) + FIELD_SIZEOF(struct __sk_buff, cb), sizeof(struct __sk_buff))) return -EINVAL; skb->priority = __skb->priority; memcpy(&cb->data, __skb->cb, QDISC_CB_PRIV_LEN); return 0; } static void convert_skb_to___skb(struct sk_buff *skb, struct __sk_buff *__skb) { struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb; if (!__skb) return; __skb->priority = skb->priority; memcpy(__skb->cb, &cb->data, QDISC_CB_PRIV_LEN); } int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { bool is_l2 = false, is_direct_pkt_access = false; u32 size = kattr->test.data_size_in; u32 repeat = kattr->test.repeat; struct __sk_buff *ctx = NULL; u32 retval, duration; int hh_len = ETH_HLEN; struct sk_buff *skb; struct sock *sk; void *data; int ret; data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN, SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); if (IS_ERR(data)) return PTR_ERR(data); ctx = bpf_ctx_init(kattr, sizeof(struct __sk_buff)); if (IS_ERR(ctx)) { kfree(data); return PTR_ERR(ctx); } switch (prog->type) { case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: is_l2 = true; /* fall through */ case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_XMIT: is_direct_pkt_access = true; break; default: break; } sk = kzalloc(sizeof(struct sock), GFP_USER); if (!sk) { kfree(data); kfree(ctx); return -ENOMEM; } sock_net_set(sk, current->nsproxy->net_ns); sock_init_data(NULL, sk); skb = build_skb(data, 0); if (!skb) { kfree(data); kfree(ctx); kfree(sk); return -ENOMEM; } skb->sk = sk; skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); __skb_put(skb, size); skb->protocol = eth_type_trans(skb, current->nsproxy->net_ns->loopback_dev); skb_reset_network_header(skb); if (is_l2) __skb_push(skb, hh_len); if (is_direct_pkt_access) bpf_compute_data_pointers(skb); ret = convert___skb_to_skb(skb, ctx); if (ret) goto out; ret = bpf_test_run(prog, skb, repeat, &retval, &duration); if (ret) goto out; if (!is_l2) { if (skb_headroom(skb) < hh_len) { int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb)); if (pskb_expand_head(skb, nhead, 0, GFP_USER)) { ret = -ENOMEM; goto out; } } memset(__skb_push(skb, hh_len), 0, hh_len); } convert_skb_to___skb(skb, ctx); size = skb->len; /* bpf program can never convert linear skb to non-linear */ if (WARN_ON_ONCE(skb_is_nonlinear(skb))) size = skb_headlen(skb); ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration); if (!ret) ret = bpf_ctx_finish(kattr, uattr, ctx, sizeof(struct __sk_buff)); out: kfree_skb(skb); bpf_sk_storage_free(sk); kfree(sk); kfree(ctx); return ret; } int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { u32 size = kattr->test.data_size_in; u32 repeat = kattr->test.repeat; struct netdev_rx_queue *rxqueue; struct xdp_buff xdp = {}; u32 retval, duration; void *data; int ret; if (kattr->test.ctx_in || kattr->test.ctx_out) return -EINVAL; data = bpf_test_init(kattr, size, XDP_PACKET_HEADROOM + NET_IP_ALIGN, 0); if (IS_ERR(data)) return PTR_ERR(data); xdp.data_hard_start = data; xdp.data = data + XDP_PACKET_HEADROOM + NET_IP_ALIGN; xdp.data_meta = xdp.data; xdp.data_end = xdp.data + size; rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0); xdp.rxq = &rxqueue->xdp_rxq; ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration); if (ret) goto out; if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN || xdp.data_end != xdp.data + size) size = xdp.data_end - xdp.data; ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration); out: kfree(data); return ret; } static int verify_user_bpf_flow_keys(struct bpf_flow_keys *ctx) { /* make sure the fields we don't use are zeroed */ if (!range_is_zero(ctx, 0, offsetof(struct bpf_flow_keys, flags))) return -EINVAL; /* flags is allowed */ if (!range_is_zero(ctx, offsetof(struct bpf_flow_keys, flags) + FIELD_SIZEOF(struct bpf_flow_keys, flags), sizeof(struct bpf_flow_keys))) return -EINVAL; return 0; } int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { u32 size = kattr->test.data_size_in; struct bpf_flow_dissector ctx = {}; u32 repeat = kattr->test.repeat; struct bpf_flow_keys *user_ctx; struct bpf_flow_keys flow_keys; u64 time_start, time_spent = 0; const struct ethhdr *eth; unsigned int flags = 0; u32 retval, duration; void *data; int ret; u32 i; if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR) return -EINVAL; if (size < ETH_HLEN) return -EINVAL; data = bpf_test_init(kattr, size, 0, 0); if (IS_ERR(data)) return PTR_ERR(data); eth = (struct ethhdr *)data; if (!repeat) repeat = 1; user_ctx = bpf_ctx_init(kattr, sizeof(struct bpf_flow_keys)); if (IS_ERR(user_ctx)) { kfree(data); return PTR_ERR(user_ctx); } if (user_ctx) { ret = verify_user_bpf_flow_keys(user_ctx); if (ret) goto out; flags = user_ctx->flags; } ctx.flow_keys = &flow_keys; ctx.data = data; ctx.data_end = (__u8 *)data + size; rcu_read_lock(); preempt_disable(); time_start = ktime_get_ns(); for (i = 0; i < repeat; i++) { retval = bpf_flow_dissect(prog, &ctx, eth->h_proto, ETH_HLEN, size, flags); if (signal_pending(current)) { preempt_enable(); rcu_read_unlock(); ret = -EINTR; goto out; } if (need_resched()) { time_spent += ktime_get_ns() - time_start; preempt_enable(); rcu_read_unlock(); cond_resched(); rcu_read_lock(); preempt_disable(); time_start = ktime_get_ns(); } } time_spent += ktime_get_ns() - time_start; preempt_enable(); rcu_read_unlock(); do_div(time_spent, repeat); duration = time_spent > U32_MAX ? U32_MAX : (u32)time_spent; ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys), retval, duration); if (!ret) ret = bpf_ctx_finish(kattr, uattr, user_ctx, sizeof(struct bpf_flow_keys)); out: kfree(user_ctx); kfree(data); return ret; }
1058 201 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Berkeley style UIO structures - Alan Cox 1994. */ #ifndef __LINUX_UIO_H #define __LINUX_UIO_H #include <linux/kernel.h> #include <linux/thread_info.h> #include <crypto/hash.h> #include <uapi/linux/uio.h> struct page; struct pipe_inode_info; struct kvec { void *iov_base; /* and that should *never* hold a userland pointer */ size_t iov_len; }; enum iter_type { /* iter types */ ITER_IOVEC = 4, ITER_KVEC = 8, ITER_BVEC = 16, ITER_PIPE = 32, ITER_DISCARD = 64, }; struct iov_iter { /* * Bit 0 is the read/write bit, set if we're writing. * Bit 1 is the BVEC_FLAG_NO_REF bit, set if type is a bvec and * the caller isn't expecting to drop a page reference when done. */ unsigned int type; size_t iov_offset; size_t count; union { const struct iovec *iov; const struct kvec *kvec; const struct bio_vec *bvec; struct pipe_inode_info *pipe; }; union { unsigned long nr_segs; struct { int idx; int start_idx; }; }; }; static inline enum iter_type iov_iter_type(const struct iov_iter *i) { return i->type & ~(READ | WRITE); } static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; } static inline bool iov_iter_is_kvec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_KVEC; } static inline bool iov_iter_is_bvec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_BVEC; } static inline bool iov_iter_is_pipe(const struct iov_iter *i) { return iov_iter_type(i) == ITER_PIPE; } static inline bool iov_iter_is_discard(const struct iov_iter *i) { return iov_iter_type(i) == ITER_DISCARD; } static inline unsigned char iov_iter_rw(const struct iov_iter *i) { return i->type & (READ | WRITE); } /* * Total number of bytes covered by an iovec. * * NOTE that it is not safe to use this function until all the iovec's * segment lengths have been validated. Because the individual lengths can * overflow a size_t when added together. */ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs) { unsigned long seg; size_t ret = 0; for (seg = 0; seg < nr_segs; seg++) ret += iov[seg].iov_len; return ret; } static inline struct iovec iov_iter_iovec(const struct iov_iter *iter) { return (struct iovec) { .iov_base = iter->iov->iov_base + iter->iov_offset, .iov_len = min(iter->count, iter->iov->iov_len - iter->iov_offset), }; } size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes); void iov_iter_advance(struct iov_iter *i, size_t bytes); void iov_iter_revert(struct iov_iter *i, size_t bytes); int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes); size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i); static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(!check_copy_size(addr, bytes, true))) return 0; else return _copy_to_iter(addr, bytes, i); } static __always_inline __must_check size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(!check_copy_size(addr, bytes, false))) return 0; else return _copy_from_iter(addr, bytes, i); } static __always_inline __must_check bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(!check_copy_size(addr, bytes, false))) return false; else return _copy_from_iter_full(addr, bytes, i); } static __always_inline __must_check size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(!check_copy_size(addr, bytes, false))) return 0; else return _copy_from_iter_nocache(addr, bytes, i); } static __always_inline __must_check bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(!check_copy_size(addr, bytes, false))) return false; else return _copy_from_iter_full_nocache(addr, bytes, i); } #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /* * Note, users like pmem that depend on the stricter semantics of * copy_from_iter_flushcache() than copy_from_iter_nocache() must check for * IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the * destination is flushed from the cache on return. */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #else #define _copy_from_iter_flushcache _copy_from_iter_nocache #endif #ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i); #else #define _copy_to_iter_mcsafe _copy_to_iter #endif static __always_inline __must_check size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(!check_copy_size(addr, bytes, false))) return 0; else return _copy_from_iter_flushcache(addr, bytes, i); } static __always_inline __must_check size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(!check_copy_size(addr, bytes, true))) return 0; else return _copy_to_iter_mcsafe(addr, bytes, i); } size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count); void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count); void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); static inline size_t iov_iter_count(const struct iov_iter *i) { return i->count; } /* * Cap the iov_iter by given limit; note that the second argument is * *not* the new size - it's upper limit for such. Passing it a value * greater than the amount of data in iov_iter is fine - it'll just do * nothing in that case. */ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) { /* * count doesn't have to fit in size_t - comparison extends both * operands to u64 here and any value that would be truncated by * conversion in assignement is by definition greater than all * values of size_t, including old i->count. */ if (i->count > count) i->count = count; } /* * reexpand a previously truncated iterator; count must be no more than how much * we had shrunk it. */ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { i->count = count; } struct csum_state { __wsum csum; size_t off; }; size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csstate, struct iov_iter *i); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, struct iov_iter *i); ssize_t import_iovec(int type, const struct iovec __user * uvector, unsigned nr_segs, unsigned fast_segs, struct iovec **iov, struct iov_iter *i); #ifdef CONFIG_COMPAT struct compat_iovec; ssize_t compat_import_iovec(int type, const struct compat_iovec __user * uvector, unsigned nr_segs, unsigned fast_segs, struct iovec **iov, struct iov_iter *i); #endif int import_single_range(int type, void __user *buf, size_t len, struct iovec *iov, struct iov_iter *i); int iov_iter_for_each_range(struct iov_iter *i, size_t bytes, int (*f)(struct kvec *vec, void *context), void *context); #endif
3458 1146 3456 3012 3455 3458 3456 3458 2589 2591 2590 2157 2221 115 2190 2158 2573 2306 2309 2308 235 235 235 235 235 235 235 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 // SPDX-License-Identifier: GPL-2.0-only /* * Generic helpers for smp ipi calls * * (C) Jens Axboe <jens.axboe@oracle.com> 2008 */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/irq_work.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/gfp.h> #include <linux/smp.h> #include <linux/cpu.h> #include <linux/sched.h> #include <linux/sched/idle.h> #include <linux/hypervisor.h> #include "smpboot.h" enum { CSD_FLAG_LOCK = 0x01, CSD_FLAG_SYNCHRONOUS = 0x02, }; struct call_function_data { call_single_data_t __percpu *csd; cpumask_var_t cpumask; cpumask_var_t cpumask_ipi; }; static DEFINE_PER_CPU_ALIGNED(struct call_function_data, cfd_data); static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue); static void flush_smp_call_function_queue(bool warn_cpu_offline); int smpcfd_prepare_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, cpu_to_node(cpu))) return -ENOMEM; if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL, cpu_to_node(cpu))) { free_cpumask_var(cfd->cpumask); return -ENOMEM; } cfd->csd = alloc_percpu(call_single_data_t); if (!cfd->csd) { free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); return -ENOMEM; } return 0; } int smpcfd_dead_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); free_percpu(cfd->csd); return 0; } int smpcfd_dying_cpu(unsigned int cpu) { /* * The IPIs for the smp-call-function callbacks queued by other * CPUs might arrive late, either due to hardware latencies or * because this CPU disabled interrupts (inside stop-machine) * before the IPIs were sent. So flush out any pending callbacks * explicitly (without waiting for the IPIs to arrive), to * ensure that the outgoing CPU doesn't go offline with work * still pending. */ flush_smp_call_function_queue(false); return 0; } void __init call_function_init(void) { int i; for_each_possible_cpu(i) init_llist_head(&per_cpu(call_single_queue, i)); smpcfd_prepare_cpu(smp_processor_id()); } /* * csd_lock/csd_unlock used to serialize access to per-cpu csd resources * * For non-synchronous ipi calls the csd can still be in use by the * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ static __always_inline void csd_lock_wait(struct __call_single_data *csd) { smp_cond_load_acquire(&csd->flags, !(VAL & CSD_FLAG_LOCK)); } static __always_inline void csd_lock(struct __call_single_data *csd) { csd_lock_wait(csd); csd->flags |= CSD_FLAG_LOCK; /* * prevent CPU from reordering the above assignment * to ->flags with any subsequent assignments to other * fields of the specified call_single_data_t structure: */ smp_wmb(); } static __always_inline void csd_unlock(struct __call_single_data *csd) { WARN_ON(!(csd->flags & CSD_FLAG_LOCK)); /* * ensure we're all done before releasing data: */ smp_store_release(&csd->flags, 0); } static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); /* * Insert a previously allocated call_single_data_t element * for execution on the given CPU. data must already have * ->func, ->info, and ->flags set. */ static int generic_exec_single(int cpu, struct __call_single_data *csd, smp_call_func_t func, void *info) { if (cpu == smp_processor_id()) { unsigned long flags; /* * We can unlock early even for the synchronous on-stack case, * since we're doing this from the same CPU.. */ csd_unlock(csd); local_irq_save(flags); func(info); local_irq_restore(flags); return 0; } if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu)) { csd_unlock(csd); return -ENXIO; } csd->func = func; csd->info = info; /* * The list addition should be visible before sending the IPI * handler locks the list to pull the entry off it because of * normal cache coherency rules implied by spinlocks. * * If IPIs can go out of order to the cache coherency protocol * in an architecture, sufficient synchronisation should be added * to arch code to make it appear to obey cache coherency WRT * locking and barrier primitives. Generic code isn't really * equipped to do the right thing... */ if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu))) arch_send_call_function_single_ipi(cpu); return 0; } /** * generic_smp_call_function_single_interrupt - Execute SMP IPI callbacks * * Invoked by arch to handle an IPI for call function single. * Must be called with interrupts disabled. */ void generic_smp_call_function_single_interrupt(void) { flush_smp_call_function_queue(true); } /** * flush_smp_call_function_queue - Flush pending smp-call-function callbacks * * @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an * offline CPU. Skip this check if set to 'false'. * * Flush any pending smp-call-function callbacks queued on this CPU. This is * invoked by the generic IPI handler, as well as by a CPU about to go offline, * to ensure that all pending IPI callbacks are run before it goes completely * offline. * * Loop through the call_single_queue and run all the queued callbacks. * Must be called with interrupts disabled. */ static void flush_smp_call_function_queue(bool warn_cpu_offline) { struct llist_head *head; struct llist_node *entry; call_single_data_t *csd, *csd_next; static bool warned; lockdep_assert_irqs_disabled(); head = this_cpu_ptr(&call_single_queue); entry = llist_del_all(head); entry = llist_reverse_order(entry); /* There shouldn't be any pending callbacks on an offline CPU. */ if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) && !warned && entry != NULL)) { warned = true; WARN(1, "IPI on offline CPU %d\n", smp_processor_id()); /* * We don't have to use the _safe() variant here * because we are not invoking the IPI handlers yet. */ llist_for_each_entry(csd, entry, llist) pr_warn("IPI callback %pS sent to offline CPU\n", csd->func); } llist_for_each_entry_safe(csd, csd_next, entry, llist) { smp_call_func_t func = csd->func; void *info = csd->info; /* Do we wait until *after* callback? */ if (csd->flags & CSD_FLAG_SYNCHRONOUS) { func(info); csd_unlock(csd); } else { csd_unlock(csd); func(info); } } /* * Handle irq works queued remotely by irq_work_queue_on(). * Smp functions above are typically synchronous so they * better run first since some other CPUs may be busy waiting * for them. */ irq_work_run(); } /* * smp_call_function_single - Run a function on a specific CPU * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed on other CPUs. * * Returns 0 on success, else a negative status code. */ int smp_call_function_single(int cpu, smp_call_func_t func, void *info, int wait) { call_single_data_t *csd; call_single_data_t csd_stack = { .flags = CSD_FLAG_LOCK | CSD_FLAG_SYNCHRONOUS, }; int this_cpu; int err; /* * prevent preemption and reschedule on another processor, * as well as CPU removal */ this_cpu = get_cpu(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled() && !oops_in_progress); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); csd = &csd_stack; if (!wait) { csd = this_cpu_ptr(&csd_data); csd_lock(csd); } err = generic_exec_single(cpu, csd, func, info); if (wait) csd_lock_wait(csd); put_cpu(); return err; } EXPORT_SYMBOL(smp_call_function_single); /** * smp_call_function_single_async(): Run an asynchronous function on a * specific CPU. * @cpu: The CPU to run on. * @csd: Pre-allocated and setup data structure * * Like smp_call_function_single(), but the call is asynchonous and * can thus be done from contexts with disabled interrupts. * * The caller passes his own pre-allocated data structure * (ie: embedded in an object) and is responsible for synchronizing it * such that the IPIs performed on the @csd are strictly serialized. * * NOTE: Be careful, there is unfortunately no current debugging facility to * validate the correctness of this serialization. */ int smp_call_function_single_async(int cpu, struct __call_single_data *csd) { int err = 0; preempt_disable(); /* We could deadlock if we have to wait here with interrupts disabled! */ if (WARN_ON_ONCE(csd->flags & CSD_FLAG_LOCK)) csd_lock_wait(csd); csd->flags = CSD_FLAG_LOCK; smp_wmb(); err = generic_exec_single(cpu, csd, csd->func, csd->info); preempt_enable(); return err; } EXPORT_SYMBOL_GPL(smp_call_function_single_async); /* * smp_call_function_any - Run a function on any of the given cpus * @mask: The mask of cpus it can run on. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed. * * Returns 0 on success, else a negative status code (if no cpus were online). * * Selection preference: * 1) current cpu if in @mask * 2) any cpu of current node if in @mask * 3) any other online cpu in @mask */ int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, void *info, int wait) { unsigned int cpu; const struct cpumask *nodemask; int ret; /* Try for same CPU (cheapest) */ cpu = get_cpu(); if (cpumask_test_cpu(cpu, mask)) goto call; /* Try for same node. */ nodemask = cpumask_of_node(cpu_to_node(cpu)); for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids; cpu = cpumask_next_and(cpu, nodemask, mask)) { if (cpu_online(cpu)) goto call; } /* Any online will do: smp_call_function_single handles nr_cpu_ids. */ cpu = cpumask_any_and(mask, cpu_online_mask); call: ret = smp_call_function_single(cpu, func, info, wait); put_cpu(); return ret; } EXPORT_SYMBOL_GPL(smp_call_function_any); /** * smp_call_function_many(): Run a function on a set of other CPUs. * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * If @wait is true, then returns once @func has returned. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. Preemption * must be disabled when calling this function. */ void smp_call_function_many(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { struct call_function_data *cfd; int cpu, next_cpu, this_cpu = smp_processor_id(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled() && !oops_in_progress && !early_boot_irqs_disabled); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); /* Try to fastpath. So, what's a CPU they want? Ignoring this one. */ cpu = cpumask_first_and(mask, cpu_online_mask); if (cpu == this_cpu) cpu = cpumask_next_and(cpu, mask, cpu_online_mask); /* No online cpus? We're done. */ if (cpu >= nr_cpu_ids) return; /* Do we have another CPU which isn't us? */ next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask); if (next_cpu == this_cpu) next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask); /* Fastpath: do that cpu by itself. */ if (next_cpu >= nr_cpu_ids) { smp_call_function_single(cpu, func, info, wait); return; } cfd = this_cpu_ptr(&cfd_data); cpumask_and(cfd->cpumask, mask, cpu_online_mask); __cpumask_clear_cpu(this_cpu, cfd->cpumask); /* Some callers race with other cpus changing the passed mask */ if (unlikely(!cpumask_weight(cfd->cpumask))) return; cpumask_clear(cfd->cpumask_ipi); for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu); csd_lock(csd); if (wait) csd->flags |= CSD_FLAG_SYNCHRONOUS; csd->func = func; csd->info = info; if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu))) __cpumask_set_cpu(cpu, cfd->cpumask_ipi); } /* Send a message to all CPUs in the map */ arch_send_call_function_ipi_mask(cfd->cpumask_ipi); if (wait) { for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd; csd = per_cpu_ptr(cfd->csd, cpu); csd_lock_wait(csd); } } } EXPORT_SYMBOL(smp_call_function_many); /** * smp_call_function(): Run a function on all other CPUs. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * Returns 0. * * If @wait is true, then returns once @func has returned; otherwise * it returns just before the target cpu calls @func. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. */ void smp_call_function(smp_call_func_t func, void *info, int wait) { preempt_disable(); smp_call_function_many(cpu_online_mask, func, info, wait); preempt_enable(); } EXPORT_SYMBOL(smp_call_function); /* Setup configured maximum number of CPUs to activate */ unsigned int setup_max_cpus = NR_CPUS; EXPORT_SYMBOL(setup_max_cpus); /* * Setup routine for controlling SMP activation * * Command-line option of "nosmp" or "maxcpus=0" will disable SMP * activation entirely (the MPS table probe still happens, though). * * Command-line option of "maxcpus=<NUM>", where <NUM> is an integer * greater than 0, limits the maximum number of CPUs activated in * SMP mode to <NUM>. */ void __weak arch_disable_smp_support(void) { } static int __init nosmp(char *str) { setup_max_cpus = 0; arch_disable_smp_support(); return 0; } early_param("nosmp", nosmp); /* this is hard limit */ static int __init nrcpus(char *str) { int nr_cpus; get_option(&str, &nr_cpus); if (nr_cpus > 0 && nr_cpus < nr_cpu_ids) nr_cpu_ids = nr_cpus; return 0; } early_param("nr_cpus", nrcpus); static int __init maxcpus(char *str) { get_option(&str, &setup_max_cpus); if (setup_max_cpus == 0) arch_disable_smp_support(); return 0; } early_param("maxcpus", maxcpus); /* Setup number of possible processor ids */ unsigned int nr_cpu_ids __read_mostly = NR_CPUS; EXPORT_SYMBOL(nr_cpu_ids); /* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */ void __init setup_nr_cpu_ids(void) { nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1; } /* Called by boot processor to activate the rest. */ void __init smp_init(void) { int num_nodes, num_cpus; unsigned int cpu; idle_threads_init(); cpuhp_threads_init(); pr_info("Bringing up secondary CPUs ...\n"); /* FIXME: This should be done in userspace --RR */ for_each_present_cpu(cpu) { if (num_online_cpus() >= setup_max_cpus) break; if (!cpu_online(cpu)) cpu_up(cpu); } num_nodes = num_online_nodes(); num_cpus = num_online_cpus(); pr_info("Brought up %d node%s, %d CPU%s\n", num_nodes, (num_nodes > 1 ? "s" : ""), num_cpus, (num_cpus > 1 ? "s" : "")); /* Any cleanup work */ smp_cpus_done(setup_max_cpus); } /* * Call a function on all processors. May be used during early boot while * early_boot_irqs_disabled is set. Use local_irq_save/restore() instead * of local_irq_disable/enable(). */ void on_each_cpu(void (*func) (void *info), void *info, int wait) { unsigned long flags; preempt_disable(); smp_call_function(func, info, wait); local_irq_save(flags); func(info); local_irq_restore(flags); preempt_enable(); } EXPORT_SYMBOL(on_each_cpu); /** * on_each_cpu_mask(): Run a function on processors specified by * cpumask, which may include the local processor. * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * If @wait is true, then returns once @func has returned. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. The * exception is that it may be used during early boot while * early_boot_irqs_disabled is set. */ void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { int cpu = get_cpu(); smp_call_function_many(mask, func, info, wait); if (cpumask_test_cpu(cpu, mask)) { unsigned long flags; local_irq_save(flags); func(info); local_irq_restore(flags); } put_cpu(); } EXPORT_SYMBOL(on_each_cpu_mask); /* * on_each_cpu_cond(): Call a function on each processor for which * the supplied function cond_func returns true, optionally waiting * for all the required CPUs to finish. This may include the local * processor. * @cond_func: A callback function that is passed a cpu id and * the the info parameter. The function is called * with preemption disabled. The function should * return a blooean value indicating whether to IPI * the specified CPU. * @func: The function to run on all applicable CPUs. * This must be fast and non-blocking. * @info: An arbitrary pointer to pass to both functions. * @wait: If true, wait (atomically) until function has * completed on other CPUs. * @gfp_flags: GFP flags to use when allocating the cpumask * used internally by the function. * * The function might sleep if the GFP flags indicates a non * atomic allocation is allowed. * * Preemption is disabled to protect against CPUs going offline but not online. * CPUs going online during the call will not be seen or sent an IPI. * * You must not call this function with disabled interrupts or * from a hardware interrupt handler or from a bottom half handler. */ void on_each_cpu_cond_mask(bool (*cond_func)(int cpu, void *info), smp_call_func_t func, void *info, bool wait, gfp_t gfp_flags, const struct cpumask *mask) { cpumask_var_t cpus; int cpu, ret; might_sleep_if(gfpflags_allow_blocking(gfp_flags)); if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) { preempt_disable(); for_each_cpu(cpu, mask) if (cond_func(cpu, info)) __cpumask_set_cpu(cpu, cpus); on_each_cpu_mask(cpus, func, info, wait); preempt_enable(); free_cpumask_var(cpus); } else { /* * No free cpumask, bother. No matter, we'll * just have to IPI them one by one. */ preempt_disable(); for_each_cpu(cpu, mask) if (cond_func(cpu, info)) { ret = smp_call_function_single(cpu, func, info, wait); WARN_ON_ONCE(ret); } preempt_enable(); } } EXPORT_SYMBOL(on_each_cpu_cond_mask); void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), smp_call_func_t func, void *info, bool wait, gfp_t gfp_flags) { on_each_cpu_cond_mask(cond_func, func, info, wait, gfp_flags, cpu_online_mask); } EXPORT_SYMBOL(on_each_cpu_cond); static void do_nothing(void *unused) { } /** * kick_all_cpus_sync - Force all cpus out of idle * * Used to synchronize the update of pm_idle function pointer. It's * called after the pointer is updated and returns after the dummy * callback function has been executed on all cpus. The execution of * the function can only happen on the remote cpus after they have * left the idle function which had been called via pm_idle function * pointer. So it's guaranteed that nothing uses the previous pointer * anymore. */ void kick_all_cpus_sync(void) { /* Make sure the change is visible before we kick the cpus */ smp_mb(); smp_call_function(do_nothing, NULL, 1); } EXPORT_SYMBOL_GPL(kick_all_cpus_sync); /** * wake_up_all_idle_cpus - break all cpus out of idle * wake_up_all_idle_cpus try to break all cpus which is in idle state even * including idle polling cpus, for non-idle cpus, we will do nothing * for them. */ void wake_up_all_idle_cpus(void) { int cpu; preempt_disable(); for_each_online_cpu(cpu) { if (cpu == smp_processor_id()) continue; wake_up_if_idle(cpu); } preempt_enable(); } EXPORT_SYMBOL_GPL(wake_up_all_idle_cpus); /** * smp_call_on_cpu - Call a function on a specific cpu * * Used to call a function on a specific cpu and wait for it to return. * Optionally make sure the call is done on a specified physical cpu via vcpu * pinning in order to support virtualized environments. */ struct smp_call_on_cpu_struct { struct work_struct work; struct completion done; int (*func)(void *); void *data; int ret; int cpu; }; static void smp_call_on_cpu_callback(struct work_struct *work) { struct smp_call_on_cpu_struct *sscs; sscs = container_of(work, struct smp_call_on_cpu_struct, work); if (sscs->cpu >= 0) hypervisor_pin_vcpu(sscs->cpu); sscs->ret = sscs->func(sscs->data); if (sscs->cpu >= 0) hypervisor_pin_vcpu(-1); complete(&sscs->done); } int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys) { struct smp_call_on_cpu_struct sscs = { .done = COMPLETION_INITIALIZER_ONSTACK(sscs.done), .func = func, .data = par, .cpu = phys ? cpu : -1, }; INIT_WORK_ONSTACK(&sscs.work, smp_call_on_cpu_callback); if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; queue_work_on(cpu, system_wq, &sscs.work); wait_for_completion(&sscs.done); return sscs.ret; } EXPORT_SYMBOL_GPL(smp_call_on_cpu);
955 955 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/acl.c * * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> */ #include <linux/quotaops.h> #include "ext4_jbd2.h" #include "ext4.h" #include "xattr.h" #include "acl.h" /* * Convert from filesystem to in-memory representation. */ static struct posix_acl * ext4_acl_from_disk(const void *value, size_t size) { const char *end = (char *)value + size; int n, count; struct posix_acl *acl; if (!value) return NULL; if (size < sizeof(ext4_acl_header)) return ERR_PTR(-EINVAL); if (((ext4_acl_header *)value)->a_version != cpu_to_le32(EXT4_ACL_VERSION)) return ERR_PTR(-EINVAL); value = (char *)value + sizeof(ext4_acl_header); count = ext4_acl_count(size); if (count < 0) return ERR_PTR(-EINVAL); if (count == 0) return NULL; acl = posix_acl_alloc(count, GFP_NOFS); if (!acl) return ERR_PTR(-ENOMEM); for (n = 0; n < count; n++) { ext4_acl_entry *entry = (ext4_acl_entry *)value; if ((char *)value + sizeof(ext4_acl_entry_short) > end) goto fail; acl->a_entries[n].e_tag = le16_to_cpu(entry->e_tag); acl->a_entries[n].e_perm = le16_to_cpu(entry->e_perm); switch (acl->a_entries[n].e_tag) { case ACL_USER_OBJ: case ACL_GROUP_OBJ: case ACL_MASK: case ACL_OTHER: value = (char *)value + sizeof(ext4_acl_entry_short); break; case ACL_USER: value = (char *)value + sizeof(ext4_acl_entry); if ((char *)value > end) goto fail; acl->a_entries[n].e_uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id)); break; case ACL_GROUP: value = (char *)value + sizeof(ext4_acl_entry); if ((char *)value > end) goto fail; acl->a_entries[n].e_gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id)); break; default: goto fail; } } if (value != end) goto fail; return acl; fail: posix_acl_release(acl); return ERR_PTR(-EINVAL); } /* * Convert from in-memory to filesystem representation. */ static void * ext4_acl_to_disk(const struct posix_acl *acl, size_t *size) { ext4_acl_header *ext_acl; char *e; size_t n; *size = ext4_acl_size(acl->a_count); ext_acl = kmalloc(sizeof(ext4_acl_header) + acl->a_count * sizeof(ext4_acl_entry), GFP_NOFS); if (!ext_acl) return ERR_PTR(-ENOMEM); ext_acl->a_version = cpu_to_le32(EXT4_ACL_VERSION); e = (char *)ext_acl + sizeof(ext4_acl_header); for (n = 0; n < acl->a_count; n++) { const struct posix_acl_entry *acl_e = &acl->a_entries[n]; ext4_acl_entry *entry = (ext4_acl_entry *)e; entry->e_tag = cpu_to_le16(acl_e->e_tag); entry->e_perm = cpu_to_le16(acl_e->e_perm); switch (acl_e->e_tag) { case ACL_USER: entry->e_id = cpu_to_le32( from_kuid(&init_user_ns, acl_e->e_uid)); e += sizeof(ext4_acl_entry); break; case ACL_GROUP: entry->e_id = cpu_to_le32( from_kgid(&init_user_ns, acl_e->e_gid)); e += sizeof(ext4_acl_entry); break; case ACL_USER_OBJ: case ACL_GROUP_OBJ: case ACL_MASK: case ACL_OTHER: e += sizeof(ext4_acl_entry_short); break; default: goto fail; } } return (char *)ext_acl; fail: kfree(ext_acl); return ERR_PTR(-EINVAL); } /* * Inode operation get_posix_acl(). * * inode->i_mutex: don't care */ struct posix_acl * ext4_get_acl(struct inode *inode, int type) { int name_index; char *value = NULL; struct posix_acl *acl; int retval; switch (type) { case ACL_TYPE_ACCESS: name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT; break; default: BUG(); } retval = ext4_xattr_get(inode, name_index, "", NULL, 0); if (retval > 0) { value = kmalloc(retval, GFP_NOFS); if (!value) return ERR_PTR(-ENOMEM); retval = ext4_xattr_get(inode, name_index, "", value, retval); } if (retval > 0) acl = ext4_acl_from_disk(value, retval); else if (retval == -ENODATA || retval == -ENOSYS) acl = NULL; else acl = ERR_PTR(retval); kfree(value); return acl; } /* * Set the access or default ACL of an inode. * * inode->i_mutex: down unless called from ext4_new_inode */ static int __ext4_set_acl(handle_t *handle, struct inode *inode, int type, struct posix_acl *acl, int xattr_flags) { int name_index; void *value = NULL; size_t size = 0; int error; switch (type) { case ACL_TYPE_ACCESS: name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT; if (!S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; break; default: return -EINVAL; } if (acl) { value = ext4_acl_to_disk(acl, &size); if (IS_ERR(value)) return (int)PTR_ERR(value); } error = ext4_xattr_set_handle(handle, inode, name_index, "", value, size, xattr_flags); kfree(value); if (!error) { set_cached_acl(inode, type, acl); } return error; } int ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type) { handle_t *handle; int error, credits, retries = 0; size_t acl_size = acl ? ext4_acl_size(acl->a_count) : 0; umode_t mode = inode->i_mode; int update_mode = 0; error = dquot_initialize(inode); if (error) return error; retry: error = ext4_xattr_set_credits(inode, acl_size, false /* is_create */, &credits); if (error) return error; handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits); if (IS_ERR(handle)) return PTR_ERR(handle); if ((type == ACL_TYPE_ACCESS) && acl) { error = posix_acl_update_mode(inode, &mode, &acl); if (error) goto out_stop; if (mode != inode->i_mode) update_mode = 1; } error = __ext4_set_acl(handle, inode, type, acl, 0 /* xattr_flags */); if (!error && update_mode) { inode->i_mode = mode; inode->i_ctime = current_time(inode); ext4_mark_inode_dirty(handle, inode); } out_stop: ext4_journal_stop(handle); if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; return error; } /* * Initialize the ACLs of a new inode. Called from ext4_new_inode. * * dir->i_mutex: down * inode->i_mutex: up (access to inode is still exclusive) */ int ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) { struct posix_acl *default_acl, *acl; int error; error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); if (error) return error; if (default_acl) { error = __ext4_set_acl(handle, inode, ACL_TYPE_DEFAULT, default_acl, XATTR_CREATE); posix_acl_release(default_acl); } else { inode->i_default_acl = NULL; } if (acl) { if (!error) error = __ext4_set_acl(handle, inode, ACL_TYPE_ACCESS, acl, XATTR_CREATE); posix_acl_release(acl); } else { inode->i_acl = NULL; } return error; }
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_MLD_H #define LINUX_MLD_H #include <linux/in6.h> #include <linux/icmpv6.h> /* MLDv1 Query/Report/Done */ struct mld_msg { struct icmp6hdr mld_hdr; struct in6_addr mld_mca; }; #define mld_type mld_hdr.icmp6_type #define mld_code mld_hdr.icmp6_code #define mld_cksum mld_hdr.icmp6_cksum #define mld_maxdelay mld_hdr.icmp6_maxdelay #define mld_reserved mld_hdr.icmp6_dataun.un_data16[1] /* Multicast Listener Discovery version 2 headers */ /* MLDv2 Report */ struct mld2_grec { __u8 grec_type; __u8 grec_auxwords; __be16 grec_nsrcs; struct in6_addr grec_mca; struct in6_addr grec_src[0]; }; struct mld2_report { struct icmp6hdr mld2r_hdr; struct mld2_grec mld2r_grec[0]; }; #define mld2r_type mld2r_hdr.icmp6_type #define mld2r_resv1 mld2r_hdr.icmp6_code #define mld2r_cksum mld2r_hdr.icmp6_cksum #define mld2r_resv2 mld2r_hdr.icmp6_dataun.un_data16[0] #define mld2r_ngrec mld2r_hdr.icmp6_dataun.un_data16[1] /* MLDv2 Query */ struct mld2_query { struct icmp6hdr mld2q_hdr; struct in6_addr mld2q_mca; #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 mld2q_qrv:3, mld2q_suppress:1, mld2q_resv2:4; #elif defined(__BIG_ENDIAN_BITFIELD) __u8 mld2q_resv2:4, mld2q_suppress:1, mld2q_qrv:3; #else #error "Please fix <asm/byteorder.h>" #endif __u8 mld2q_qqic; __be16 mld2q_nsrcs; struct in6_addr mld2q_srcs[0]; }; #define mld2q_type mld2q_hdr.icmp6_type #define mld2q_code mld2q_hdr.icmp6_code #define mld2q_cksum mld2q_hdr.icmp6_cksum #define mld2q_mrc mld2q_hdr.icmp6_maxdelay #define mld2q_resv1 mld2q_hdr.icmp6_dataun.un_data16[1] /* RFC3810, 5.1.3. Maximum Response Code: * * If Maximum Response Code >= 32768, Maximum Response Code represents a * floating-point value as follows: * * 0 1 2 3 4 5 6 7 8 9 A B C D E F * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |1| exp | mant | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ #define MLDV2_MRC_EXP(value) (((value) >> 12) & 0x0007) #define MLDV2_MRC_MAN(value) ((value) & 0x0fff) /* RFC3810, 5.1.9. QQIC (Querier's Query Interval Code): * * If QQIC >= 128, QQIC represents a floating-point value as follows: * * 0 1 2 3 4 5 6 7 * +-+-+-+-+-+-+-+-+ * |1| exp | mant | * +-+-+-+-+-+-+-+-+ */ #define MLDV2_QQIC_EXP(value) (((value) >> 4) & 0x07) #define MLDV2_QQIC_MAN(value) ((value) & 0x0f) #define MLD_EXP_MIN_LIMIT 32768UL #define MLDV1_MRD_MAX_COMPAT (MLD_EXP_MIN_LIMIT - 1) static inline unsigned long mldv2_mrc(const struct mld2_query *mlh2) { /* RFC3810, 5.1.3. Maximum Response Code */ unsigned long ret, mc_mrc = ntohs(mlh2->mld2q_mrc); if (mc_mrc < MLD_EXP_MIN_LIMIT) { ret = mc_mrc; } else { unsigned long mc_man, mc_exp; mc_exp = MLDV2_MRC_EXP(mc_mrc); mc_man = MLDV2_MRC_MAN(mc_mrc); ret = (mc_man | 0x1000) << (mc_exp + 3); } return ret; } #endif
962 964 964 964 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/dir.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/dir.c * * Copyright (C) 1991, 1992 Linus Torvalds * * ext4 directory handling functions * * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 * * Hash Tree Directory indexing (c) 2001 Daniel Phillips * */ #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/slab.h> #include <linux/iversion.h> #include <linux/unicode.h> #include "ext4.h" #include "xattr.h" static int ext4_dx_readdir(struct file *, struct dir_context *); /** * is_dx_dir() - check if a directory is using htree indexing * @inode: directory inode * * Check if the given dir-inode refers to an htree-indexed directory * (or a directory which could potentially get converted to use htree * indexing). * * Return 1 if it is a dx dir, 0 if not */ static int is_dx_dir(struct inode *inode) { struct super_block *sb = inode->i_sb; if (ext4_has_feature_dir_index(inode->i_sb) && ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) || ((inode->i_size >> sb->s_blocksize_bits) == 1) || ext4_has_inline_data(inode))) return 1; return 0; } static bool is_fake_dir_entry(struct ext4_dir_entry_2 *de) { /* Check if . or .. , or skip if namelen is 0 */ if ((de->name_len > 0) && (de->name_len <= 2) && (de->name[0] == '.') && (de->name[1] == '.' || de->name[1] == '\0')) return true; /* Check if this is a csum entry */ if (de->file_type == EXT4_FT_DIR_CSUM) return true; return false; } /* * Return 0 if the directory entry is OK, and 1 if there is a problem * * Note: this is the opposite of what ext2 and ext3 historically returned... * * bh passed here can be an inode block or a dir data block, depending * on the inode inline data flag. */ int __ext4_check_dir_entry(const char *function, unsigned int line, struct inode *dir, struct file *filp, struct ext4_dir_entry_2 *de, struct buffer_head *bh, char *buf, int size, unsigned int offset) { const char *error_msg = NULL; const int rlen = ext4_rec_len_from_disk(de->rec_len, dir->i_sb->s_blocksize); const int next_offset = ((char *) de - buf) + rlen; bool fake = is_fake_dir_entry(de); bool has_csum = ext4_has_metadata_csum(dir->i_sb); if (unlikely(rlen < ext4_dir_rec_len(1, fake ? NULL : dir))) error_msg = "rec_len is smaller than minimal"; else if (unlikely(rlen % 4 != 0)) error_msg = "rec_len % 4 != 0"; else if (unlikely(rlen < ext4_dir_rec_len(de->name_len, fake ? NULL : dir))) error_msg = "rec_len is too small for name_len"; else if (unlikely(((char *) de - buf) + rlen > size)) error_msg = "directory entry overrun"; else if (unlikely(next_offset > size - ext4_dir_rec_len(1, has_csum ? NULL : dir) && next_offset != size)) error_msg = "directory entry too close to block end"; else if (unlikely(le32_to_cpu(de->inode) > le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count))) error_msg = "inode out of bounds"; else return 0; if (filp) ext4_error_file(filp, function, line, bh->b_blocknr, "bad entry in directory: %s - offset=%u, " "inode=%u, rec_len=%d, size=%d fake=%d", error_msg, offset, le32_to_cpu(de->inode), rlen, size, fake); else ext4_error_inode(dir, function, line, bh->b_blocknr, "bad entry in directory: %s - offset=%u, " "inode=%u, rec_len=%d, size=%d fake=%d", error_msg, offset, le32_to_cpu(de->inode), rlen, size, fake); return 1; } static int ext4_readdir(struct file *file, struct dir_context *ctx) { unsigned int offset; int i; struct ext4_dir_entry_2 *de; int err; struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct buffer_head *bh = NULL; struct fscrypt_str fstr = FSTR_INIT(NULL, 0); err = fscrypt_prepare_readdir(inode); if (err) return err; if (is_dx_dir(inode)) { err = ext4_dx_readdir(file, ctx); if (err != ERR_BAD_DX_DIR) { return err; } /* Can we just clear INDEX flag to ignore htree information? */ if (!ext4_has_metadata_csum(sb)) { /* * We don't set the inode dirty flag since it's not * critical that it gets flushed back to the disk. */ ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); } } if (ext4_has_inline_data(inode)) { int has_inline_data = 1; err = ext4_read_inline_dir(file, ctx, &has_inline_data); if (has_inline_data) return err; } if (IS_ENCRYPTED(inode)) { err = fscrypt_fname_alloc_buffer(EXT4_NAME_LEN, &fstr); if (err < 0) return err; } while (ctx->pos < inode->i_size) { struct ext4_map_blocks map; if (fatal_signal_pending(current)) { err = -ERESTARTSYS; goto errout; } cond_resched(); offset = ctx->pos & (sb->s_blocksize - 1); map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb); map.m_len = 1; err = ext4_map_blocks(NULL, inode, &map, 0); if (err == 0) { /* m_len should never be zero but let's avoid * an infinite loop if it somehow is */ if (map.m_len == 0) map.m_len = 1; ctx->pos += map.m_len * sb->s_blocksize; continue; } if (err > 0) { pgoff_t index = map.m_pblk >> (PAGE_SHIFT - inode->i_blkbits); if (!ra_has_index(&file->f_ra, index)) page_cache_sync_readahead( sb->s_bdev->bd_inode->i_mapping, &file->f_ra, file, index, 1); file->f_ra.prev_pos = (loff_t)index << PAGE_SHIFT; bh = ext4_bread(NULL, inode, map.m_lblk, 0); if (IS_ERR(bh)) { err = PTR_ERR(bh); bh = NULL; goto errout; } } if (!bh) { /* corrupt size? Maybe no more blocks to read */ if (ctx->pos > inode->i_blocks << 9) break; ctx->pos += sb->s_blocksize - offset; continue; } /* Check the checksum */ if (!buffer_verified(bh) && !ext4_dirblock_csum_verify(inode, bh)) { EXT4_ERROR_FILE(file, 0, "directory fails checksum " "at offset %llu", (unsigned long long)ctx->pos); ctx->pos += sb->s_blocksize - offset; brelse(bh); bh = NULL; continue; } set_buffer_verified(bh); /* If the dir block has changed since the last call to * readdir(2), then we might be pointing to an invalid * dirent right now. Scan from the start of the block * to make sure. */ if (!inode_eq_iversion(inode, file->f_version)) { for (i = 0; i < sb->s_blocksize && i < offset; ) { de = (struct ext4_dir_entry_2 *) (bh->b_data + i); /* It's too expensive to do a full * dirent test each time round this * loop, but we do have to test at * least that it is non-zero. A * failure will be detected in the * dirent test below. */ if (ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize) < ext4_dir_rec_len(1, inode)) break; i += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); } offset = i; ctx->pos = (ctx->pos & ~(sb->s_blocksize - 1)) | offset; file->f_version = inode_query_iversion(inode); } while (ctx->pos < inode->i_size && offset < sb->s_blocksize) { de = (struct ext4_dir_entry_2 *) (bh->b_data + offset); if (ext4_check_dir_entry(inode, file, de, bh, bh->b_data, bh->b_size, offset)) { /* * On error, skip to the next block */ ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1; break; } offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); if (le32_to_cpu(de->inode)) { if (!IS_ENCRYPTED(inode)) { if (!dir_emit(ctx, de->name, de->name_len, le32_to_cpu(de->inode), get_dtype(sb, de->file_type))) goto done; } else { int save_len = fstr.len; struct fscrypt_str de_name = FSTR_INIT(de->name, de->name_len); /* Directory is encrypted */ err = fscrypt_fname_disk_to_usr(inode, EXT4_DIRENT_HASH(de), EXT4_DIRENT_MINOR_HASH(de), &de_name, &fstr); de_name = fstr; fstr.len = save_len; if (err) goto errout; if (!dir_emit(ctx, de_name.name, de_name.len, le32_to_cpu(de->inode), get_dtype(sb, de->file_type))) goto done; } } ctx->pos += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); } if ((ctx->pos < inode->i_size) && !dir_relax_shared(inode)) goto done; brelse(bh); bh = NULL; offset = 0; } done: err = 0; errout: fscrypt_fname_free_buffer(&fstr); brelse(bh); return err; } static inline int is_32bit_api(void) { #ifdef CONFIG_COMPAT return in_compat_syscall(); #else return (BITS_PER_LONG == 32); #endif } /* * These functions convert from the major/minor hash to an f_pos * value for dx directories * * Upper layer (for example NFS) should specify FMODE_32BITHASH or * FMODE_64BITHASH explicitly. On the other hand, we allow ext4 to be mounted * directly on both 32-bit and 64-bit nodes, under such case, neither * FMODE_32BITHASH nor FMODE_64BITHASH is specified. */ static inline loff_t hash2pos(struct file *filp, __u32 major, __u32 minor) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return major >> 1; else return ((__u64)(major >> 1) << 32) | (__u64)minor; } static inline __u32 pos2maj_hash(struct file *filp, loff_t pos) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return (pos << 1) & 0xffffffff; else return ((pos >> 32) << 1) & 0xffffffff; } static inline __u32 pos2min_hash(struct file *filp, loff_t pos) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return 0; else return pos & 0xffffffff; } /* * Return 32- or 64-bit end-of-file for dx directories */ static inline loff_t ext4_get_htree_eof(struct file *filp) { if ((filp->f_mode & FMODE_32BITHASH) || (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) return EXT4_HTREE_EOF_32BIT; else return EXT4_HTREE_EOF_64BIT; } /* * ext4_dir_llseek() calls generic_file_llseek_size to handle htree * directories, where the "offset" is in terms of the filename hash * value instead of the byte offset. * * Because we may return a 64-bit hash that is well beyond offset limits, * we need to pass the max hash as the maximum allowable offset in * the htree directory case. * * For non-htree, ext4_llseek already chooses the proper max offset. */ static loff_t ext4_dir_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; int dx_dir = is_dx_dir(inode); loff_t ret, htree_max = ext4_get_htree_eof(file); if (likely(dx_dir)) ret = generic_file_llseek_size(file, offset, whence, htree_max, htree_max); else ret = ext4_llseek(file, offset, whence); file->f_version = inode_peek_iversion(inode) - 1; return ret; } /* * This structure holds the nodes of the red-black tree used to store * the directory entry in hash order. */ struct fname { __u32 hash; __u32 minor_hash; struct rb_node rb_hash; struct fname *next; __u32 inode; __u8 name_len; __u8 file_type; char name[0]; }; /* * This functoin implements a non-recursive way of freeing all of the * nodes in the red-black tree. */ static void free_rb_tree_fname(struct rb_root *root) { struct fname *fname, *next; rbtree_postorder_for_each_entry_safe(fname, next, root, rb_hash) while (fname) { struct fname *old = fname; fname = fname->next; kfree(old); } *root = RB_ROOT; } static struct dir_private_info *ext4_htree_create_dir_info(struct file *filp, loff_t pos) { struct dir_private_info *p; p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) return NULL; p->curr_hash = pos2maj_hash(filp, pos); p->curr_minor_hash = pos2min_hash(filp, pos); return p; } void ext4_htree_free_dir_info(struct dir_private_info *p) { free_rb_tree_fname(&p->root); kfree(p); } /* * Given a directory entry, enter it into the fname rb tree. * * When filename encryption is enabled, the dirent will hold the * encrypted filename, while the htree will hold decrypted filename. * The decrypted filename is passed in via ent_name. parameter. */ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, __u32 minor_hash, struct ext4_dir_entry_2 *dirent, struct fscrypt_str *ent_name) { struct rb_node **p, *parent = NULL; struct fname *fname, *new_fn; struct dir_private_info *info; int len; info = dir_file->private_data; p = &info->root.rb_node; /* Create and allocate the fname structure */ len = sizeof(struct fname) + ent_name->len + 1; new_fn = kzalloc(len, GFP_KERNEL); if (!new_fn) return -ENOMEM; new_fn->hash = hash; new_fn->minor_hash = minor_hash; new_fn->inode = le32_to_cpu(dirent->inode); new_fn->name_len = ent_name->len; new_fn->file_type = dirent->file_type; memcpy(new_fn->name, ent_name->name, ent_name->len); new_fn->name[ent_name->len] = 0; while (*p) { parent = *p; fname = rb_entry(parent, struct fname, rb_hash); /* * If the hash and minor hash match up, then we put * them on a linked list. This rarely happens... */ if ((new_fn->hash == fname->hash) && (new_fn->minor_hash == fname->minor_hash)) { new_fn->next = fname->next; fname->next = new_fn; return 0; } if (new_fn->hash < fname->hash) p = &(*p)->rb_left; else if (new_fn->hash > fname->hash) p = &(*p)->rb_right; else if (new_fn->minor_hash < fname->minor_hash) p = &(*p)->rb_left; else /* if (new_fn->minor_hash > fname->minor_hash) */ p = &(*p)->rb_right; } rb_link_node(&new_fn->rb_hash, parent, p); rb_insert_color(&new_fn->rb_hash, &info->root); return 0; } /* * This is a helper function for ext4_dx_readdir. It calls filldir * for all entres on the fname linked list. (Normally there is only * one entry on the linked list, unless there are 62 bit hash collisions.) */ static int call_filldir(struct file *file, struct dir_context *ctx, struct fname *fname) { struct dir_private_info *info = file->private_data; struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; if (!fname) { ext4_msg(sb, KERN_ERR, "%s:%d: inode #%lu: comm %s: " "called with null fname?!?", __func__, __LINE__, inode->i_ino, current->comm); return 0; } ctx->pos = hash2pos(file, fname->hash, fname->minor_hash); while (fname) { if (!dir_emit(ctx, fname->name, fname->name_len, fname->inode, get_dtype(sb, fname->file_type))) { info->extra_fname = fname; return 1; } fname = fname->next; } return 0; } static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) { struct dir_private_info *info = file->private_data; struct inode *inode = file_inode(file); struct fname *fname; int ret = 0; if (!info) { info = ext4_htree_create_dir_info(file, ctx->pos); if (!info) return -ENOMEM; file->private_data = info; } if (ctx->pos == ext4_get_htree_eof(file)) return 0; /* EOF */ /* Some one has messed with f_pos; reset the world */ if (info->last_pos != ctx->pos) { free_rb_tree_fname(&info->root); info->curr_node = NULL; info->extra_fname = NULL; info->curr_hash = pos2maj_hash(file, ctx->pos); info->curr_minor_hash = pos2min_hash(file, ctx->pos); } /* * If there are any leftover names on the hash collision * chain, return them first. */ if (info->extra_fname) { if (call_filldir(file, ctx, info->extra_fname)) goto finished; info->extra_fname = NULL; goto next_node; } else if (!info->curr_node) info->curr_node = rb_first(&info->root); while (1) { /* * Fill the rbtree if we have no more entries, * or the inode has changed since we last read in the * cached entries. */ if ((!info->curr_node) || !inode_eq_iversion(inode, file->f_version)) { info->curr_node = NULL; free_rb_tree_fname(&info->root); file->f_version = inode_query_iversion(inode); ret = ext4_htree_fill_tree(file, info->curr_hash, info->curr_minor_hash, &info->next_hash); if (ret < 0) goto finished; if (ret == 0) { ctx->pos = ext4_get_htree_eof(file); break; } info->curr_node = rb_first(&info->root); } fname = rb_entry(info->curr_node, struct fname, rb_hash); info->curr_hash = fname->hash; info->curr_minor_hash = fname->minor_hash; if (call_filldir(file, ctx, fname)) break; next_node: info->curr_node = rb_next(info->curr_node); if (info->curr_node) { fname = rb_entry(info->curr_node, struct fname, rb_hash); info->curr_hash = fname->hash; info->curr_minor_hash = fname->minor_hash; } else { if (info->next_hash == ~0) { ctx->pos = ext4_get_htree_eof(file); break; } info->curr_hash = info->next_hash; info->curr_minor_hash = 0; } } finished: info->last_pos = ctx->pos; return ret < 0 ? ret : 0; } static int ext4_release_dir(struct inode *inode, struct file *filp) { if (filp->private_data) ext4_htree_free_dir_info(filp->private_data); return 0; } int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf, int buf_size) { struct ext4_dir_entry_2 *de; int rlen; unsigned int offset = 0; char *top; de = (struct ext4_dir_entry_2 *)buf; top = buf + buf_size; while ((char *) de < top) { if (ext4_check_dir_entry(dir, NULL, de, bh, buf, buf_size, offset)) return -EFSCORRUPTED; rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); de = (struct ext4_dir_entry_2 *)((char *)de + rlen); offset += rlen; } if ((char *) de > top) return -EFSCORRUPTED; return 0; } const struct file_operations ext4_dir_operations = { .llseek = ext4_dir_llseek, .read = generic_read_dir, .iterate_shared = ext4_readdir, .unlocked_ioctl = ext4_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext4_compat_ioctl, #endif .fsync = ext4_sync_file, .release = ext4_release_dir, };
509 221 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIME64_H #define _LINUX_TIME64_H #include <linux/math64.h> #include <vdso/time64.h> typedef __s64 time64_t; typedef __u64 timeu64_t; #include <uapi/linux/time.h> struct timespec64 { time64_t tv_sec; /* seconds */ long tv_nsec; /* nanoseconds */ }; struct itimerspec64 { struct timespec64 it_interval; struct timespec64 it_value; }; /* Located here for timespec[64]_valid_strict */ #define TIME64_MAX ((s64)~((u64)1 << 63)) #define TIME64_MIN (-TIME64_MAX - 1) #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) /* * Limits for settimeofday(): * * To prevent setting the time close to the wraparound point time setting * is limited so a reasonable uptime can be accomodated. Uptime of 30 years * should be really sufficient, which means the cutoff is 2232. At that * point the cutoff is just a small part of the larger problem. */ #define TIME_UPTIME_SEC_MAX (30LL * 365 * 24 *3600) #define TIME_SETTOD_SEC_MAX (KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX) static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); } /* * lhs < rhs: return <0 * lhs == rhs: return 0 * lhs > rhs: return >0 */ static inline int timespec64_compare(const struct timespec64 *lhs, const struct timespec64 *rhs) { if (lhs->tv_sec < rhs->tv_sec) return -1; if (lhs->tv_sec > rhs->tv_sec) return 1; return lhs->tv_nsec - rhs->tv_nsec; } extern void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec); static inline struct timespec64 timespec64_add(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); return ts_delta; } /* * sub = lhs - rhs, in normalized form */ static inline struct timespec64 timespec64_sub(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec - rhs.tv_sec, lhs.tv_nsec - rhs.tv_nsec); return ts_delta; } /* * Returns true if the timespec64 is norm, false if denorm: */ static inline bool timespec64_valid(const struct timespec64 *ts) { /* Dates before 1970 are bogus */ if (ts->tv_sec < 0) return false; /* Can't have more nanoseconds then a second */ if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return false; return true; } static inline bool timespec64_valid_strict(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values that could overflow ktime_t */ if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) return false; return true; } static inline bool timespec64_valid_settod(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values which cause overflow issues vs. CLOCK_REALTIME */ if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX) return false; return true; } /** * timespec64_to_ns - Convert timespec64 to nanoseconds * @ts: pointer to the timespec64 variable to be converted * * Returns the scalar nanosecond representation of the timespec64 * parameter. */ static inline s64 timespec64_to_ns(const struct timespec64 *ts) { /* Prevent multiplication overflow */ if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) return KTIME_MAX; return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; } /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Returns the timespec64 representation of the nsec parameter. */ extern struct timespec64 ns_to_timespec64(const s64 nsec); /** * timespec64_add_ns - Adds nanoseconds to a timespec64 * @a: pointer to timespec64 to be incremented * @ns: unsigned nanoseconds value to be added * * This must always be inlined because its used from the x86-64 vdso, * which cannot call other kernel functions. */ static __always_inline void timespec64_add_ns(struct timespec64 *a, u64 ns) { a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); a->tv_nsec = ns; } /* * timespec64_add_safe assumes both values are positive and checks for * overflow. It will return TIME64_MAX in case of overflow. */ extern struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs); #endif /* _LINUX_TIME64_H */
774 774 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 // SPDX-License-Identifier: GPL-2.0 /* * sysctl_net_ipv6.c: sysctl interface to net IPV6 subsystem. * * Changes: * YOSHIFUJI Hideaki @USAGI: added icmp sysctl table. */ #include <linux/mm.h> #include <linux/sysctl.h> #include <linux/in6.h> #include <linux/ipv6.h> #include <linux/slab.h> #include <linux/export.h> #include <net/ndisc.h> #include <net/ipv6.h> #include <net/addrconf.h> #include <net/inet_frag.h> #include <net/netevent.h> #ifdef CONFIG_NETLABEL #include <net/calipso.h> #endif static int two = 2; static int flowlabel_reflect_max = 0x7; static int auto_flowlabels_min; static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int ret; net = container_of(table->data, struct net, ipv6.sysctl.multipath_hash_policy); ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net); return ret; } static struct ctl_table ipv6_table_template[] = { { .procname = "bindv6only", .data = &init_net.ipv6.sysctl.bindv6only, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "anycast_src_echo_reply", .data = &init_net.ipv6.sysctl.anycast_src_echo_reply, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "flowlabel_consistency", .data = &init_net.ipv6.sysctl.flowlabel_consistency, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "auto_flowlabels", .data = &init_net.ipv6.sysctl.auto_flowlabels, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &auto_flowlabels_min, .extra2 = &auto_flowlabels_max }, { .procname = "fwmark_reflect", .data = &init_net.ipv6.sysctl.fwmark_reflect, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "idgen_retries", .data = &init_net.ipv6.sysctl.idgen_retries, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "idgen_delay", .data = &init_net.ipv6.sysctl.idgen_delay, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "flowlabel_state_ranges", .data = &init_net.ipv6.sysctl.flowlabel_state_ranges, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "ip_nonlocal_bind", .data = &init_net.ipv6.sysctl.ip_nonlocal_bind, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "flowlabel_reflect", .data = &init_net.ipv6.sysctl.flowlabel_reflect, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &flowlabel_reflect_max, }, { .procname = "max_dst_opts_number", .data = &init_net.ipv6.sysctl.max_dst_opts_cnt, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "max_hbh_opts_number", .data = &init_net.ipv6.sysctl.max_hbh_opts_cnt, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "max_dst_opts_length", .data = &init_net.ipv6.sysctl.max_dst_opts_len, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "max_hbh_length", .data = &init_net.ipv6.sysctl.max_hbh_opts_len, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "fib_multipath_hash_policy", .data = &init_net.ipv6.sysctl.multipath_hash_policy, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_rt6_multipath_hash_policy, .extra1 = SYSCTL_ZERO, .extra2 = &two, }, { .procname = "seg6_flowlabel", .data = &init_net.ipv6.sysctl.seg6_flowlabel, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { } }; static struct ctl_table ipv6_rotable[] = { { .procname = "mld_max_msf", .data = &sysctl_mld_max_msf, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "mld_qrv", .data = &sysctl_mld_qrv, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE }, #ifdef CONFIG_NETLABEL { .procname = "calipso_cache_enable", .data = &calipso_cache_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "calipso_cache_bucket_size", .data = &calipso_cache_bucketsize, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif /* CONFIG_NETLABEL */ { } }; static int __net_init ipv6_sysctl_net_init(struct net *net) { struct ctl_table *ipv6_table; struct ctl_table *ipv6_route_table; struct ctl_table *ipv6_icmp_table; int err; err = -ENOMEM; ipv6_table = kmemdup(ipv6_table_template, sizeof(ipv6_table_template), GFP_KERNEL); if (!ipv6_table) goto out; ipv6_table[0].data = &net->ipv6.sysctl.bindv6only; ipv6_table[1].data = &net->ipv6.sysctl.anycast_src_echo_reply; ipv6_table[2].data = &net->ipv6.sysctl.flowlabel_consistency; ipv6_table[3].data = &net->ipv6.sysctl.auto_flowlabels; ipv6_table[4].data = &net->ipv6.sysctl.fwmark_reflect; ipv6_table[5].data = &net->ipv6.sysctl.idgen_retries; ipv6_table[6].data = &net->ipv6.sysctl.idgen_delay; ipv6_table[7].data = &net->ipv6.sysctl.flowlabel_state_ranges; ipv6_table[8].data = &net->ipv6.sysctl.ip_nonlocal_bind; ipv6_table[9].data = &net->ipv6.sysctl.flowlabel_reflect; ipv6_table[10].data = &net->ipv6.sysctl.max_dst_opts_cnt; ipv6_table[11].data = &net->ipv6.sysctl.max_hbh_opts_cnt; ipv6_table[12].data = &net->ipv6.sysctl.max_dst_opts_len; ipv6_table[13].data = &net->ipv6.sysctl.max_hbh_opts_len; ipv6_table[14].data = &net->ipv6.sysctl.multipath_hash_policy, ipv6_table[15].data = &net->ipv6.sysctl.seg6_flowlabel; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) goto out_ipv6_table; ipv6_icmp_table = ipv6_icmp_sysctl_init(net); if (!ipv6_icmp_table) goto out_ipv6_route_table; net->ipv6.sysctl.hdr = register_net_sysctl(net, "net/ipv6", ipv6_table); if (!net->ipv6.sysctl.hdr) goto out_ipv6_icmp_table; net->ipv6.sysctl.route_hdr = register_net_sysctl(net, "net/ipv6/route", ipv6_route_table); if (!net->ipv6.sysctl.route_hdr) goto out_unregister_ipv6_table; net->ipv6.sysctl.icmp_hdr = register_net_sysctl(net, "net/ipv6/icmp", ipv6_icmp_table); if (!net->ipv6.sysctl.icmp_hdr) goto out_unregister_route_table; err = 0; out: return err; out_unregister_route_table: unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr); out_unregister_ipv6_table: unregister_net_sysctl_table(net->ipv6.sysctl.hdr); out_ipv6_icmp_table: kfree(ipv6_icmp_table); out_ipv6_route_table: kfree(ipv6_route_table); out_ipv6_table: kfree(ipv6_table); goto out; } static void __net_exit ipv6_sysctl_net_exit(struct net *net) { struct ctl_table *ipv6_table; struct ctl_table *ipv6_route_table; struct ctl_table *ipv6_icmp_table; ipv6_table = net->ipv6.sysctl.hdr->ctl_table_arg; ipv6_route_table = net->ipv6.sysctl.route_hdr->ctl_table_arg; ipv6_icmp_table = net->ipv6.sysctl.icmp_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv6.sysctl.icmp_hdr); unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr); unregister_net_sysctl_table(net->ipv6.sysctl.hdr); kfree(ipv6_table); kfree(ipv6_route_table); kfree(ipv6_icmp_table); } static struct pernet_operations ipv6_sysctl_net_ops = { .init = ipv6_sysctl_net_init, .exit = ipv6_sysctl_net_exit, }; static struct ctl_table_header *ip6_header; int ipv6_sysctl_register(void) { int err = -ENOMEM; ip6_header = register_net_sysctl(&init_net, "net/ipv6", ipv6_rotable); if (!ip6_header) goto out; err = register_pernet_subsys(&ipv6_sysctl_net_ops); if (err) goto err_pernet; out: return err; err_pernet: unregister_net_sysctl_table(ip6_header); goto out; } void ipv6_sysctl_unregister(void) { unregister_net_sysctl_table(ip6_header); unregister_pernet_subsys(&ipv6_sysctl_net_ops); }
1273 1273 390 390 52 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 // SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/dir.c - sysfs core and dir operation implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo <teheo@suse.de> * * Please see Documentation/filesystems/sysfs.txt for more information. */ #define pr_fmt(fmt) "sysfs: " fmt #include <linux/fs.h> #include <linux/kobject.h> #include <linux/slab.h> #include "sysfs.h" DEFINE_SPINLOCK(sysfs_symlink_target_lock); void sysfs_warn_dup(struct kernfs_node *parent, const char *name) { char *buf; buf = kzalloc(PATH_MAX, GFP_KERNEL); if (buf) kernfs_path(parent, buf, PATH_MAX); pr_warn("cannot create duplicate filename '%s/%s'\n", buf, name); dump_stack(); kfree(buf); } /** * sysfs_create_dir_ns - create a directory for an object with a namespace tag * @kobj: object we're creating directory for * @ns: the namespace tag to use */ int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) { struct kernfs_node *parent, *kn; kuid_t uid; kgid_t gid; if (WARN_ON(!kobj)) return -EINVAL; if (kobj->parent) parent = kobj->parent->sd; else parent = sysfs_root_kn; if (!parent) return -ENOENT; kobject_get_ownership(kobj, &uid, &gid); kn = kernfs_create_dir_ns(parent, kobject_name(kobj), S_IRWXU | S_IRUGO | S_IXUGO, uid, gid, kobj, ns); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(parent, kobject_name(kobj)); return PTR_ERR(kn); } kobj->sd = kn; return 0; } /** * sysfs_remove_dir - remove an object's directory. * @kobj: object. * * The only thing special about this is that we remove any files in * the directory before we remove the directory, and we've inlined * what used to be sysfs_rmdir() below, instead of calling separately. */ void sysfs_remove_dir(struct kobject *kobj) { struct kernfs_node *kn = kobj->sd; /* * In general, kboject owner is responsible for ensuring removal * doesn't race with other operations and sysfs doesn't provide any * protection; however, when @kobj is used as a symlink target, the * symlinking entity usually doesn't own @kobj and thus has no * control over removal. @kobj->sd may be removed anytime * and symlink code may end up dereferencing an already freed node. * * sysfs_symlink_target_lock synchronizes @kobj->sd * disassociation against symlink operations so that symlink code * can safely dereference @kobj->sd. */ spin_lock(&sysfs_symlink_target_lock); kobj->sd = NULL; spin_unlock(&sysfs_symlink_target_lock); if (kn) { WARN_ON_ONCE(kernfs_type(kn) != KERNFS_DIR); kernfs_remove(kn); } } int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name, const void *new_ns) { struct kernfs_node *parent; int ret; parent = kernfs_get_parent(kobj->sd); ret = kernfs_rename_ns(kobj->sd, parent, new_name, new_ns); kernfs_put(parent); return ret; } int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj, const void *new_ns) { struct kernfs_node *kn = kobj->sd; struct kernfs_node *new_parent; new_parent = new_parent_kobj && new_parent_kobj->sd ? new_parent_kobj->sd : sysfs_root_kn; return kernfs_rename_ns(kn, new_parent, kn->name, new_ns); } /** * sysfs_create_mount_point - create an always empty directory * @parent_kobj: kobject that will contain this always empty directory * @name: The name of the always empty directory to add */ int sysfs_create_mount_point(struct kobject *parent_kobj, const char *name) { struct kernfs_node *kn, *parent = parent_kobj->sd; kn = kernfs_create_empty_dir(parent, name); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(parent, name); return PTR_ERR(kn); } return 0; } EXPORT_SYMBOL_GPL(sysfs_create_mount_point); /** * sysfs_remove_mount_point - remove an always empty directory. * @parent_kobj: kobject that will contain this always empty directory * @name: The name of the always empty directory to remove * */ void sysfs_remove_mount_point(struct kobject *parent_kobj, const char *name) { struct kernfs_node *parent = parent_kobj->sd; kernfs_remove_by_name_ns(parent, name, NULL); } EXPORT_SYMBOL_GPL(sysfs_remove_mount_point);
6 6 802 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 /* License: GPL */ #include <linux/mutex.h> #include <linux/socket.h> #include <linux/skbuff.h> #include <net/netlink.h> #include <net/net_namespace.h> #include <linux/module.h> #include <net/sock.h> #include <linux/kernel.h> #include <linux/tcp.h> #include <linux/workqueue.h> #include <linux/nospec.h> #include <linux/inet_diag.h> #include <linux/sock_diag.h> static const struct sock_diag_handler *sock_diag_handlers[AF_MAX]; static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh); static DEFINE_MUTEX(sock_diag_table_mutex); static struct workqueue_struct *broadcast_wq; static atomic64_t cookie_gen; u64 sock_gen_cookie(struct sock *sk) { while (1) { u64 res = atomic64_read(&sk->sk_cookie); if (res) return res; res = atomic64_inc_return(&cookie_gen); atomic64_cmpxchg(&sk->sk_cookie, 0, res); } } int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie) { u64 res; if (cookie[0] == INET_DIAG_NOCOOKIE && cookie[1] == INET_DIAG_NOCOOKIE) return 0; res = sock_gen_cookie(sk); if ((u32)res != cookie[0] || (u32)(res >> 32) != cookie[1]) return -ESTALE; return 0; } EXPORT_SYMBOL_GPL(sock_diag_check_cookie); void sock_diag_save_cookie(struct sock *sk, __u32 *cookie) { u64 res = sock_gen_cookie(sk); cookie[0] = (u32)res; cookie[1] = (u32)(res >> 32); } EXPORT_SYMBOL_GPL(sock_diag_save_cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) { u32 mem[SK_MEMINFO_VARS]; sk_get_meminfo(sk, mem); return nla_put(skb, attrtype, sizeof(mem), &mem); } EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype) { struct sock_fprog_kern *fprog; struct sk_filter *filter; struct nlattr *attr; unsigned int flen; int err = 0; if (!may_report_filterinfo) { nla_reserve(skb, attrtype, 0); return 0; } rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (!filter) goto out; fprog = filter->prog->orig_prog; if (!fprog) goto out; flen = bpf_classic_proglen(fprog); attr = nla_reserve(skb, attrtype, flen); if (attr == NULL) { err = -EMSGSIZE; goto out; } memcpy(nla_data(attr), fprog->filter, flen); out: rcu_read_unlock(); return err; } EXPORT_SYMBOL(sock_diag_put_filterinfo); struct broadcast_sk { struct sock *sk; struct work_struct work; }; static size_t sock_diag_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct inet_diag_msg) + nla_total_size(sizeof(u8)) /* INET_DIAG_PROTOCOL */ + nla_total_size_64bit(sizeof(struct tcp_info))); /* INET_DIAG_INFO */ } static void sock_diag_broadcast_destroy_work(struct work_struct *work) { struct broadcast_sk *bsk = container_of(work, struct broadcast_sk, work); struct sock *sk = bsk->sk; const struct sock_diag_handler *hndl; struct sk_buff *skb; const enum sknetlink_groups group = sock_diag_destroy_group(sk); int err = -1; WARN_ON(group == SKNLGRP_NONE); skb = nlmsg_new(sock_diag_nlmsg_size(), GFP_KERNEL); if (!skb) goto out; mutex_lock(&sock_diag_table_mutex); hndl = sock_diag_handlers[sk->sk_family]; if (hndl && hndl->get_info) err = hndl->get_info(skb, sk); mutex_unlock(&sock_diag_table_mutex); if (!err) nlmsg_multicast(sock_net(sk)->diag_nlsk, skb, 0, group, GFP_KERNEL); else kfree_skb(skb); out: sk_destruct(sk); kfree(bsk); } void sock_diag_broadcast_destroy(struct sock *sk) { /* Note, this function is often called from an interrupt context. */ struct broadcast_sk *bsk = kmalloc(sizeof(struct broadcast_sk), GFP_ATOMIC); if (!bsk) return sk_destruct(sk); bsk->sk = sk; INIT_WORK(&bsk->work, sock_diag_broadcast_destroy_work); queue_work(broadcast_wq, &bsk->work); } void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)) { mutex_lock(&sock_diag_table_mutex); inet_rcv_compat = fn; mutex_unlock(&sock_diag_table_mutex); } EXPORT_SYMBOL_GPL(sock_diag_register_inet_compat); void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)) { mutex_lock(&sock_diag_table_mutex); inet_rcv_compat = NULL; mutex_unlock(&sock_diag_table_mutex); } EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat); int sock_diag_register(const struct sock_diag_handler *hndl) { int err = 0; if (hndl->family >= AF_MAX) return -EINVAL; mutex_lock(&sock_diag_table_mutex); if (sock_diag_handlers[hndl->family]) err = -EBUSY; else sock_diag_handlers[hndl->family] = hndl; mutex_unlock(&sock_diag_table_mutex); return err; } EXPORT_SYMBOL_GPL(sock_diag_register); void sock_diag_unregister(const struct sock_diag_handler *hnld) { int family = hnld->family; if (family >= AF_MAX) return; mutex_lock(&sock_diag_table_mutex); BUG_ON(sock_diag_handlers[family] != hnld); sock_diag_handlers[family] = NULL; mutex_unlock(&sock_diag_table_mutex); } EXPORT_SYMBOL_GPL(sock_diag_unregister); static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) { int err; struct sock_diag_req *req = nlmsg_data(nlh); const struct sock_diag_handler *hndl; if (nlmsg_len(nlh) < sizeof(*req)) return -EINVAL; if (req->sdiag_family >= AF_MAX) return -EINVAL; req->sdiag_family = array_index_nospec(req->sdiag_family, AF_MAX); if (sock_diag_handlers[req->sdiag_family] == NULL) sock_load_diag_module(req->sdiag_family, 0); mutex_lock(&sock_diag_table_mutex); hndl = sock_diag_handlers[req->sdiag_family]; if (hndl == NULL) err = -ENOENT; else if (nlh->nlmsg_type == SOCK_DIAG_BY_FAMILY) err = hndl->dump(skb, nlh); else if (nlh->nlmsg_type == SOCK_DESTROY && hndl->destroy) err = hndl->destroy(skb, nlh); else err = -EOPNOTSUPP; mutex_unlock(&sock_diag_table_mutex); return err; } static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { int ret; switch (nlh->nlmsg_type) { case TCPDIAG_GETSOCK: case DCCPDIAG_GETSOCK: if (inet_rcv_compat == NULL) sock_load_diag_module(AF_INET, 0); mutex_lock(&sock_diag_table_mutex); if (inet_rcv_compat != NULL) ret = inet_rcv_compat(skb, nlh); else ret = -EOPNOTSUPP; mutex_unlock(&sock_diag_table_mutex); return ret; case SOCK_DIAG_BY_FAMILY: case SOCK_DESTROY: return __sock_diag_cmd(skb, nlh); default: return -EINVAL; } } static DEFINE_MUTEX(sock_diag_mutex); static void sock_diag_rcv(struct sk_buff *skb) { mutex_lock(&sock_diag_mutex); netlink_rcv_skb(skb, &sock_diag_rcv_msg); mutex_unlock(&sock_diag_mutex); } static int sock_diag_bind(struct net *net, int group) { switch (group) { case SKNLGRP_INET_TCP_DESTROY: case SKNLGRP_INET_UDP_DESTROY: if (!sock_diag_handlers[AF_INET]) sock_load_diag_module(AF_INET, 0); break; case SKNLGRP_INET6_TCP_DESTROY: case SKNLGRP_INET6_UDP_DESTROY: if (!sock_diag_handlers[AF_INET6]) sock_load_diag_module(AF_INET6, 0); break; } return 0; } int sock_diag_destroy(struct sock *sk, int err) { if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (!sk->sk_prot->diag_destroy) return -EOPNOTSUPP; return sk->sk_prot->diag_destroy(sk, err); } EXPORT_SYMBOL_GPL(sock_diag_destroy); static int __net_init diag_net_init(struct net *net) { struct netlink_kernel_cfg cfg = { .groups = SKNLGRP_MAX, .input = sock_diag_rcv, .bind = sock_diag_bind, .flags = NL_CFG_F_NONROOT_RECV, }; net->diag_nlsk = netlink_kernel_create(net, NETLINK_SOCK_DIAG, &cfg); return net->diag_nlsk == NULL ? -ENOMEM : 0; } static void __net_exit diag_net_exit(struct net *net) { netlink_kernel_release(net->diag_nlsk); net->diag_nlsk = NULL; } static struct pernet_operations diag_net_ops = { .init = diag_net_init, .exit = diag_net_exit, }; static int __init sock_diag_init(void) { broadcast_wq = alloc_workqueue("sock_diag_events", 0, 0); BUG_ON(!broadcast_wq); return register_pernet_subsys(&diag_net_ops); } device_initcall(sock_diag_init);
8 27 8 20 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _IPV6_FRAG_H #define _IPV6_FRAG_H #include <linux/kernel.h> #include <net/addrconf.h> #include <net/ipv6.h> #include <net/inet_frag.h> enum ip6_defrag_users { IP6_DEFRAG_LOCAL_DELIVER, IP6_DEFRAG_CONNTRACK_IN, __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX, IP6_DEFRAG_CONNTRACK_OUT, __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX, IP6_DEFRAG_CONNTRACK_BRIDGE_IN, __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX, }; /* * Equivalent of ipv4 struct ip */ struct frag_queue { struct inet_frag_queue q; int iif; __u16 nhoffset; u8 ecn; }; #if IS_ENABLED(CONFIG_IPV6) static inline void ip6frag_init(struct inet_frag_queue *q, const void *a) { struct frag_queue *fq = container_of(q, struct frag_queue, q); const struct frag_v6_compare_key *key = a; q->key.v6 = *key; fq->ecn = 0; } static inline u32 ip6frag_key_hashfn(const void *data, u32 len, u32 seed) { return jhash2(data, sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); } static inline u32 ip6frag_obj_hashfn(const void *data, u32 len, u32 seed) { const struct inet_frag_queue *fq = data; return jhash2((const u32 *)&fq->key.v6, sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); } static inline int ip6frag_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) { const struct frag_v6_compare_key *key = arg->key; const struct inet_frag_queue *fq = ptr; return !!memcmp(&fq->key, key, sizeof(*key)); } static inline void ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) { struct net_device *dev = NULL; struct sk_buff *head; rcu_read_lock(); /* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */ if (READ_ONCE(fq->q.fqdir->dead)) goto out_rcu_unlock; spin_lock(&fq->q.lock); if (fq->q.flags & INET_FRAG_COMPLETE) goto out; inet_frag_kill(&fq->q); dev = dev_get_by_index_rcu(net, fq->iif); if (!dev) goto out; __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); /* Don't send error if the first segment did not arrive. */ if (!(fq->q.flags & INET_FRAG_FIRST_IN)) goto out; /* sk_buff::dev and sk_buff::rbnode are unionized. So we * pull the head out of the tree in order to be able to * deal with head->dev. */ head = inet_frag_pull_head(&fq->q); if (!head) goto out; head->dev = dev; spin_unlock(&fq->q.lock); icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); kfree_skb(head); goto out_rcu_unlock; out: spin_unlock(&fq->q.lock); out_rcu_unlock: rcu_read_unlock(); inet_frag_put(&fq->q); } #endif #endif
18 403 2 393 18 393 386 5 16 361 1812 8 894 654 654 440 337 2 2 2 2 2 2 1 23 47 4 20 16 19 27 33 33 2 8 27 1 29 81 17 3 35 1 2 1 1 30 40 1 1 38 23 2 2 2 17 25 1 24 52 2 1 2 2 45 252 2 4 2 245 8 2 26 20 10 1 10 31 1 1 24 5 27 14 9 4 9 1 9 1 9 72 71 3 12 4 1 1 6 147 145 131 44 44 4045 812 730 2893 252 16 21 23 34 1 2 95 98 6 10 7 1 2 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook */ #include <linux/kernel.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/bpf.h> #include <linux/bpf_perf_event.h> #include <linux/filter.h> #include <linux/uaccess.h> #include <linux/ctype.h> #include <linux/kprobes.h> #include <linux/syscalls.h> #include <linux/error-injection.h> #include <asm/tlb.h> #include "trace_probe.h" #include "trace.h" #define bpf_event_rcu_dereference(p) \ rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex)) #ifdef CONFIG_MODULES struct bpf_trace_module { struct module *module; struct list_head list; }; static LIST_HEAD(bpf_trace_modules); static DEFINE_MUTEX(bpf_module_mutex); static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name) { struct bpf_raw_event_map *btp, *ret = NULL; struct bpf_trace_module *btm; unsigned int i; mutex_lock(&bpf_module_mutex); list_for_each_entry(btm, &bpf_trace_modules, list) { for (i = 0; i < btm->module->num_bpf_raw_events; ++i) { btp = &btm->module->bpf_raw_events[i]; if (!strcmp(btp->tp->name, name)) { if (try_module_get(btm->module)) ret = btp; goto out; } } } out: mutex_unlock(&bpf_module_mutex); return ret; } #else static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name) { return NULL; } #endif /* CONFIG_MODULES */ u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); /** * trace_call_bpf - invoke BPF program * @call: tracepoint event * @ctx: opaque context pointer * * kprobe handlers execute BPF programs via this helper. * Can be used from static tracepoints in the future. * * Return: BPF programs always return an integer which is interpreted by * kprobe handler as: * 0 - return from kprobe (event is filtered out) * 1 - store kprobe event into ring buffer * Other values are reserved and currently alias to 1 */ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { unsigned int ret; if (in_nmi()) /* not supported yet */ return 1; preempt_disable(); if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { /* * since some bpf program is already running on this cpu, * don't call into another bpf program (same or different) * and don't send kprobe event into ring-buffer, * so return zero here */ ret = 0; goto out; } /* * Instead of moving rcu_read_lock/rcu_dereference/rcu_read_unlock * to all call sites, we did a bpf_prog_array_valid() there to check * whether call->prog_array is empty or not, which is * a heurisitc to speed up execution. * * If bpf_prog_array_valid() fetched prog_array was * non-NULL, we go into trace_call_bpf() and do the actual * proper rcu_dereference() under RCU lock. * If it turns out that prog_array is NULL then, we bail out. * For the opposite, if the bpf_prog_array_valid() fetched pointer * was NULL, you'll skip the prog_array with the risk of missing * out of events when it was updated in between this and the * rcu_dereference() which is accepted risk. */ ret = BPF_PROG_RUN_ARRAY_CHECK(call->prog_array, ctx, BPF_PROG_RUN); out: __this_cpu_dec(bpf_prog_active); preempt_enable(); return ret; } EXPORT_SYMBOL_GPL(trace_call_bpf); #ifdef CONFIG_BPF_KPROBE_OVERRIDE BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc) { regs_set_return_value(regs, rc); override_function_with_return(regs); return 0; } static const struct bpf_func_proto bpf_override_return_proto = { .func = bpf_override_return, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; #endif BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr) { int ret; ret = security_locked_down(LOCKDOWN_BPF_READ); if (ret < 0) goto out; ret = probe_kernel_read(dst, unsafe_ptr, size); if (unlikely(ret < 0)) out: memset(dst, 0, size); return ret; } static const struct bpf_func_proto bpf_probe_read_proto = { .func = bpf_probe_read, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src, u32, size) { /* * Ensure we're in user context which is safe for the helper to * run. This helper has no business in a kthread. * * access_ok() should prevent writing to non-user memory, but in * some situations (nommu, temporary switch, etc) access_ok() does * not provide enough validation, hence the check on KERNEL_DS. * * nmi_uaccess_okay() ensures the probe is not run in an interim * state, when the task or mm are switched. This is specifically * required to prevent the use of temporary mm. */ if (unlikely(in_interrupt() || current->flags & (PF_KTHREAD | PF_EXITING))) return -EPERM; if (unlikely(uaccess_kernel())) return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; return probe_user_write(unsafe_ptr, src, size); } static const struct bpf_func_proto bpf_probe_write_user_proto = { .func = bpf_probe_write_user, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, }; static const struct bpf_func_proto *bpf_get_probe_write_proto(void) { pr_warn_ratelimited("%s[%d] is installing a program with bpf_probe_write_user helper that may corrupt user memory!", current->comm, task_pid_nr(current)); return &bpf_probe_write_user_proto; } /* * Only limited trace_printk() conversion specifiers allowed: * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %s */ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, u64, arg2, u64, arg3) { bool str_seen = false; int mod[3] = {}; int fmt_cnt = 0; u64 unsafe_addr; char buf[64]; int i; /* * bpf_check()->check_func_arg()->check_stack_boundary() * guarantees that fmt points to bpf program stack, * fmt_size bytes of it were initialized and fmt_size > 0 */ if (fmt[--fmt_size] != 0) return -EINVAL; /* check format string for allowed specifiers */ for (i = 0; i < fmt_size; i++) { if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) return -EINVAL; if (fmt[i] != '%') continue; if (fmt_cnt >= 3) return -EINVAL; /* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */ i++; if (fmt[i] == 'l') { mod[fmt_cnt]++; i++; } else if (fmt[i] == 'p' || fmt[i] == 's') { mod[fmt_cnt]++; /* disallow any further format extensions */ if (fmt[i + 1] != 0 && !isspace(fmt[i + 1]) && !ispunct(fmt[i + 1])) return -EINVAL; fmt_cnt++; if (fmt[i] == 's') { if (str_seen) /* allow only one '%s' per fmt string */ return -EINVAL; str_seen = true; switch (fmt_cnt) { case 1: unsafe_addr = arg1; arg1 = (long) buf; break; case 2: unsafe_addr = arg2; arg2 = (long) buf; break; case 3: unsafe_addr = arg3; arg3 = (long) buf; break; } buf[0] = 0; strncpy_from_unsafe(buf, (void *) (long) unsafe_addr, sizeof(buf)); } continue; } if (fmt[i] == 'l') { mod[fmt_cnt]++; i++; } if (fmt[i] != 'i' && fmt[i] != 'd' && fmt[i] != 'u' && fmt[i] != 'x') return -EINVAL; fmt_cnt++; } /* Horrid workaround for getting va_list handling working with different * argument type combinations generically for 32 and 64 bit archs. */ #define __BPF_TP_EMIT() __BPF_ARG3_TP() #define __BPF_TP(...) \ __trace_printk(0 /* Fake ip */, \ fmt, ##__VA_ARGS__) #define __BPF_ARG1_TP(...) \ ((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64)) \ ? __BPF_TP(arg1, ##__VA_ARGS__) \ : ((mod[0] == 1 || (mod[0] == 0 && __BITS_PER_LONG == 32)) \ ? __BPF_TP((long)arg1, ##__VA_ARGS__) \ : __BPF_TP((u32)arg1, ##__VA_ARGS__))) #define __BPF_ARG2_TP(...) \ ((mod[1] == 2 || (mod[1] == 1 && __BITS_PER_LONG == 64)) \ ? __BPF_ARG1_TP(arg2, ##__VA_ARGS__) \ : ((mod[1] == 1 || (mod[1] == 0 && __BITS_PER_LONG == 32)) \ ? __BPF_ARG1_TP((long)arg2, ##__VA_ARGS__) \ : __BPF_ARG1_TP((u32)arg2, ##__VA_ARGS__))) #define __BPF_ARG3_TP(...) \ ((mod[2] == 2 || (mod[2] == 1 && __BITS_PER_LONG == 64)) \ ? __BPF_ARG2_TP(arg3, ##__VA_ARGS__) \ : ((mod[2] == 1 || (mod[2] == 0 && __BITS_PER_LONG == 32)) \ ? __BPF_ARG2_TP((long)arg3, ##__VA_ARGS__) \ : __BPF_ARG2_TP((u32)arg3, ##__VA_ARGS__))) return __BPF_TP_EMIT(); } static const struct bpf_func_proto bpf_trace_printk_proto = { .func = bpf_trace_printk, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM, .arg2_type = ARG_CONST_SIZE, }; const struct bpf_func_proto *bpf_get_trace_printk_proto(void) { /* * this program might be calling bpf_trace_printk, * so allocate per-cpu printk buffers */ trace_printk_init_buffers(); return &bpf_trace_printk_proto; } static __always_inline int get_map_perf_counter(struct bpf_map *map, u64 flags, u64 *value, u64 *enabled, u64 *running) { struct bpf_array *array = container_of(map, struct bpf_array, map); unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; struct bpf_event_entry *ee; if (unlikely(flags & ~(BPF_F_INDEX_MASK))) return -EINVAL; if (index == BPF_F_CURRENT_CPU) index = cpu; if (unlikely(index >= array->map.max_entries)) return -E2BIG; ee = READ_ONCE(array->ptrs[index]); if (!ee) return -ENOENT; return perf_event_read_local(ee->event, value, enabled, running); } BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) { u64 value = 0; int err; err = get_map_perf_counter(map, flags, &value, NULL, NULL); /* * this api is ugly since we miss [-22..-2] range of valid * counter values, but that's uapi */ if (err) return err; return value; } static const struct bpf_func_proto bpf_perf_event_read_proto = { .func = bpf_perf_event_read, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_perf_event_read_value, struct bpf_map *, map, u64, flags, struct bpf_perf_event_value *, buf, u32, size) { int err = -EINVAL; if (unlikely(size != sizeof(struct bpf_perf_event_value))) goto clear; err = get_map_perf_counter(map, flags, &buf->counter, &buf->enabled, &buf->running); if (unlikely(err)) goto clear; return 0; clear: memset(buf, 0, size); return err; } static const struct bpf_func_proto bpf_perf_event_read_value_proto = { .func = bpf_perf_event_read_value, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; static __always_inline u64 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, u64 flags, struct perf_sample_data *sd) { struct bpf_array *array = container_of(map, struct bpf_array, map); unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; struct bpf_event_entry *ee; struct perf_event *event; if (index == BPF_F_CURRENT_CPU) index = cpu; if (unlikely(index >= array->map.max_entries)) return -E2BIG; ee = READ_ONCE(array->ptrs[index]); if (!ee) return -ENOENT; event = ee->event; if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE || event->attr.config != PERF_COUNT_SW_BPF_OUTPUT)) return -EINVAL; if (unlikely(event->oncpu != cpu)) return -EOPNOTSUPP; return perf_event_output(event, sd, regs); } /* * Support executing tracepoints in normal, irq, and nmi context that each call * bpf_perf_event_output */ struct bpf_trace_sample_data { struct perf_sample_data sds[3]; }; static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_trace_sds); static DEFINE_PER_CPU(int, bpf_trace_nest_level); BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, u64, flags, void *, data, u64, size) { struct bpf_trace_sample_data *sds = this_cpu_ptr(&bpf_trace_sds); int nest_level = this_cpu_inc_return(bpf_trace_nest_level); struct perf_raw_record raw = { .frag = { .size = size, .data = data, }, }; struct perf_sample_data *sd; int err; if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) { err = -EBUSY; goto out; } sd = &sds->sds[nest_level - 1]; if (unlikely(flags & ~(BPF_F_INDEX_MASK))) { err = -EINVAL; goto out; } perf_sample_data_init(sd, 0, 0); sd->raw = &raw; err = __bpf_perf_event_output(regs, map, flags, sd); out: this_cpu_dec(bpf_trace_nest_level); return err; } static const struct bpf_func_proto bpf_perf_event_output_proto = { .func = bpf_perf_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; static DEFINE_PER_CPU(int, bpf_event_output_nest_level); struct bpf_nested_pt_regs { struct pt_regs regs[3]; }; static DEFINE_PER_CPU(struct bpf_nested_pt_regs, bpf_pt_regs); static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_misc_sds); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { int nest_level = this_cpu_inc_return(bpf_event_output_nest_level); struct perf_raw_frag frag = { .copy = ctx_copy, .size = ctx_size, .data = ctx, }; struct perf_raw_record raw = { .frag = { { .next = ctx_size ? &frag : NULL, }, .size = meta_size, .data = meta, }, }; struct perf_sample_data *sd; struct pt_regs *regs; u64 ret; if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bpf_misc_sds.sds))) { ret = -EBUSY; goto out; } sd = this_cpu_ptr(&bpf_misc_sds.sds[nest_level - 1]); regs = this_cpu_ptr(&bpf_pt_regs.regs[nest_level - 1]); perf_fetch_caller_regs(regs); perf_sample_data_init(sd, 0, 0); sd->raw = &raw; ret = __bpf_perf_event_output(regs, map, flags, sd); out: this_cpu_dec(bpf_event_output_nest_level); return ret; } BPF_CALL_0(bpf_get_current_task) { return (long) current; } static const struct bpf_func_proto bpf_get_current_task_proto = { .func = bpf_get_current_task, .gpl_only = true, .ret_type = RET_INTEGER, }; BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx) { struct bpf_array *array = container_of(map, struct bpf_array, map); struct cgroup *cgrp; if (unlikely(idx >= array->map.max_entries)) return -E2BIG; cgrp = READ_ONCE(array->ptrs[idx]); if (unlikely(!cgrp)) return -EAGAIN; return task_under_cgroup_hierarchy(current, cgrp); } static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = { .func = bpf_current_task_under_cgroup, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_probe_read_str, void *, dst, u32, size, const void *, unsafe_ptr) { int ret; ret = security_locked_down(LOCKDOWN_BPF_READ); if (ret < 0) goto out; /* * The strncpy_from_unsafe() call will likely not fill the entire * buffer, but that's okay in this circumstance as we're probing * arbitrary memory anyway similar to bpf_probe_read() and might * as well probe the stack. Thus, memory is explicitly cleared * only in error case, so that improper users ignoring return * code altogether don't copy garbage; otherwise length of string * is returned that can be used for bpf_perf_event_output() et al. */ ret = strncpy_from_unsafe(dst, unsafe_ptr, size); if (unlikely(ret < 0)) out: memset(dst, 0, size); return ret; } static const struct bpf_func_proto bpf_probe_read_str_proto = { .func = bpf_probe_read_str, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; struct send_signal_irq_work { struct irq_work irq_work; struct task_struct *task; u32 sig; }; static DEFINE_PER_CPU(struct send_signal_irq_work, send_signal_work); static void do_bpf_send_signal(struct irq_work *entry) { struct send_signal_irq_work *work; work = container_of(entry, struct send_signal_irq_work, irq_work); group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, PIDTYPE_TGID); } BPF_CALL_1(bpf_send_signal, u32, sig) { struct send_signal_irq_work *work = NULL; /* Similar to bpf_probe_write_user, task needs to be * in a sound condition and kernel memory access be * permitted in order to send signal to the current * task. */ if (unlikely(current->flags & (PF_KTHREAD | PF_EXITING))) return -EPERM; if (unlikely(uaccess_kernel())) return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; /* Task should not be pid=1 to avoid kernel panic. */ if (unlikely(is_global_init(current))) return -EPERM; if (irqs_disabled()) { /* Do an early check on signal validity. Otherwise, * the error is lost in deferred irq_work. */ if (unlikely(!valid_signal(sig))) return -EINVAL; work = this_cpu_ptr(&send_signal_work); if (work->irq_work.flags & IRQ_WORK_BUSY) return -EBUSY; /* Add the current task, which is the target of sending signal, * to the irq_work. The current task may change when queued * irq works get executed. */ work->task = current; work->sig = sig; irq_work_queue(&work->irq_work); return 0; } return group_send_sig_info(sig, SEND_SIG_PRIV, current, PIDTYPE_TGID); } static const struct bpf_func_proto bpf_send_signal_proto = { .func = bpf_send_signal, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, }; static const struct bpf_func_proto * tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_map_lookup_elem: return &bpf_map_lookup_elem_proto; case BPF_FUNC_map_update_elem: return &bpf_map_update_elem_proto; case BPF_FUNC_map_delete_elem: return &bpf_map_delete_elem_proto; case BPF_FUNC_map_push_elem: return &bpf_map_push_elem_proto; case BPF_FUNC_map_pop_elem: return &bpf_map_pop_elem_proto; case BPF_FUNC_map_peek_elem: return &bpf_map_peek_elem_proto; case BPF_FUNC_probe_read: return &bpf_probe_read_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_current_pid_tgid: return &bpf_get_current_pid_tgid_proto; case BPF_FUNC_get_current_task: return &bpf_get_current_task_proto; case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_current_comm: return &bpf_get_current_comm_proto; case BPF_FUNC_trace_printk: return bpf_get_trace_printk_proto(); case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_get_numa_node_id: return &bpf_get_numa_node_id_proto; case BPF_FUNC_perf_event_read: return &bpf_perf_event_read_proto; case BPF_FUNC_probe_write_user: return bpf_get_probe_write_proto(); case BPF_FUNC_current_task_under_cgroup: return &bpf_current_task_under_cgroup_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_probe_read_str: return &bpf_probe_read_str_proto; #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; #endif case BPF_FUNC_send_signal: return &bpf_send_signal_proto; default: return NULL; } } static const struct bpf_func_proto * kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto; case BPF_FUNC_get_stack: return &bpf_get_stack_proto; case BPF_FUNC_perf_event_read_value: return &bpf_perf_event_read_value_proto; #ifdef CONFIG_BPF_KPROBE_OVERRIDE case BPF_FUNC_override_return: return &bpf_override_return_proto; #endif default: return tracing_func_proto(func_id, prog); } } /* bpf+kprobe programs can access fields of 'struct pt_regs' */ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < 0 || off >= sizeof(struct pt_regs)) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; /* * Assertion for 32 bit to make sure last 8 byte access * (BPF_DW) to the last 4 byte member is disallowed. */ if (off + size > sizeof(struct pt_regs)) return false; return true; } const struct bpf_verifier_ops kprobe_verifier_ops = { .get_func_proto = kprobe_prog_func_proto, .is_valid_access = kprobe_prog_is_valid_access, }; const struct bpf_prog_ops kprobe_prog_ops = { }; BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map, u64, flags, void *, data, u64, size) { struct pt_regs *regs = *(struct pt_regs **)tp_buff; /* * r1 points to perf tracepoint buffer where first 8 bytes are hidden * from bpf program and contain a pointer to 'struct pt_regs'. Fetch it * from there and call the same bpf_perf_event_output() helper inline. */ return ____bpf_perf_event_output(regs, map, flags, data, size); } static const struct bpf_func_proto bpf_perf_event_output_proto_tp = { .func = bpf_perf_event_output_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_3(bpf_get_stackid_tp, void *, tp_buff, struct bpf_map *, map, u64, flags) { struct pt_regs *regs = *(struct pt_regs **)tp_buff; /* * Same comment as in bpf_perf_event_output_tp(), only that this time * the other helper's function body cannot be inlined due to being * external, thus we need to call raw helper function. */ return bpf_get_stackid((unsigned long) regs, (unsigned long) map, flags, 0, 0); } static const struct bpf_func_proto bpf_get_stackid_proto_tp = { .func = bpf_get_stackid_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_get_stack_tp, void *, tp_buff, void *, buf, u32, size, u64, flags) { struct pt_regs *regs = *(struct pt_regs **)tp_buff; return bpf_get_stack((unsigned long) regs, (unsigned long) buf, (unsigned long) size, flags, 0); } static const struct bpf_func_proto bpf_get_stack_proto_tp = { .func = bpf_get_stack_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; static const struct bpf_func_proto * tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; case BPF_FUNC_get_stack: return &bpf_get_stack_proto_tp; default: return tracing_func_proto(func_id, prog); } } static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64)); return true; } const struct bpf_verifier_ops tracepoint_verifier_ops = { .get_func_proto = tp_prog_func_proto, .is_valid_access = tp_prog_is_valid_access, }; const struct bpf_prog_ops tracepoint_prog_ops = { }; BPF_CALL_3(bpf_perf_prog_read_value, struct bpf_perf_event_data_kern *, ctx, struct bpf_perf_event_value *, buf, u32, size) { int err = -EINVAL; if (unlikely(size != sizeof(struct bpf_perf_event_value))) goto clear; err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled, &buf->running); if (unlikely(err)) goto clear; return 0; clear: memset(buf, 0, size); return err; } static const struct bpf_func_proto bpf_perf_prog_read_value_proto = { .func = bpf_perf_prog_read_value, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, }; static const struct bpf_func_proto * pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; case BPF_FUNC_get_stack: return &bpf_get_stack_proto_tp; case BPF_FUNC_perf_prog_read_value: return &bpf_perf_prog_read_value_proto; default: return tracing_func_proto(func_id, prog); } } /* * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp * to avoid potential recursive reuse issue when/if tracepoints are added * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack. * * Since raw tracepoints run despite bpf_prog_active, support concurrent usage * in normal, irq, and nmi context. */ struct bpf_raw_tp_regs { struct pt_regs regs[3]; }; static DEFINE_PER_CPU(struct bpf_raw_tp_regs, bpf_raw_tp_regs); static DEFINE_PER_CPU(int, bpf_raw_tp_nest_level); static struct pt_regs *get_bpf_raw_tp_regs(void) { struct bpf_raw_tp_regs *tp_regs = this_cpu_ptr(&bpf_raw_tp_regs); int nest_level = this_cpu_inc_return(bpf_raw_tp_nest_level); if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(tp_regs->regs))) { this_cpu_dec(bpf_raw_tp_nest_level); return ERR_PTR(-EBUSY); } return &tp_regs->regs[nest_level - 1]; } static void put_bpf_raw_tp_regs(void) { this_cpu_dec(bpf_raw_tp_nest_level); } BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags, void *, data, u64, size) { struct pt_regs *regs = get_bpf_raw_tp_regs(); int ret; if (IS_ERR(regs)) return PTR_ERR(regs); perf_fetch_caller_regs(regs); ret = ____bpf_perf_event_output(regs, map, flags, data, size); put_bpf_raw_tp_regs(); return ret; } static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { .func = bpf_perf_event_output_raw_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags) { struct pt_regs *regs = get_bpf_raw_tp_regs(); int ret; if (IS_ERR(regs)) return PTR_ERR(regs); perf_fetch_caller_regs(regs); /* similar to bpf_perf_event_output_tp, but pt_regs fetched differently */ ret = bpf_get_stackid((unsigned long) regs, (unsigned long) map, flags, 0, 0); put_bpf_raw_tp_regs(); return ret; } static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = { .func = bpf_get_stackid_raw_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_get_stack_raw_tp, struct bpf_raw_tracepoint_args *, args, void *, buf, u32, size, u64, flags) { struct pt_regs *regs = get_bpf_raw_tp_regs(); int ret; if (IS_ERR(regs)) return PTR_ERR(regs); perf_fetch_caller_regs(regs); ret = bpf_get_stack((unsigned long) regs, (unsigned long) buf, (unsigned long) size, flags, 0); put_bpf_raw_tp_regs(); return ret; } static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = { .func = bpf_get_stack_raw_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; static const struct bpf_func_proto * raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto_raw_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_raw_tp; case BPF_FUNC_get_stack: return &bpf_get_stack_proto_raw_tp; default: return tracing_func_proto(func_id, prog); } } static bool raw_tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { /* largest tracepoint in the kernel has 12 args */ if (off < 0 || off >= sizeof(__u64) * 12) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; return true; } const struct bpf_verifier_ops raw_tracepoint_verifier_ops = { .get_func_proto = raw_tp_prog_func_proto, .is_valid_access = raw_tp_prog_is_valid_access, }; const struct bpf_prog_ops raw_tracepoint_prog_ops = { }; static bool raw_tp_writable_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off == 0) { if (size != sizeof(u64) || type != BPF_READ) return false; info->reg_type = PTR_TO_TP_BUFFER; } return raw_tp_prog_is_valid_access(off, size, type, prog, info); } const struct bpf_verifier_ops raw_tracepoint_writable_verifier_ops = { .get_func_proto = raw_tp_prog_func_proto, .is_valid_access = raw_tp_writable_prog_is_valid_access, }; const struct bpf_prog_ops raw_tracepoint_writable_prog_ops = { }; static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_u64 = sizeof(u64); if (off < 0 || off >= sizeof(struct bpf_perf_event_data)) return false; if (type != BPF_READ) return false; if (off % size != 0) { if (sizeof(unsigned long) != 4) return false; if (size != 8) return false; if (off % size != 4) return false; } switch (off) { case bpf_ctx_range(struct bpf_perf_event_data, sample_period): bpf_ctx_record_field_size(info, size_u64); if (!bpf_ctx_narrow_access_ok(off, size, size_u64)) return false; break; case bpf_ctx_range(struct bpf_perf_event_data, addr): bpf_ctx_record_field_size(info, size_u64); if (!bpf_ctx_narrow_access_ok(off, size, size_u64)) return false; break; default: if (size != sizeof(long)) return false; } return true; } static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_perf_event_data, sample_period): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, data), si->dst_reg, si->src_reg, offsetof(struct bpf_perf_event_data_kern, data)); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct perf_sample_data, period, 8, target_size)); break; case offsetof(struct bpf_perf_event_data, addr): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, data), si->dst_reg, si->src_reg, offsetof(struct bpf_perf_event_data_kern, data)); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct perf_sample_data, addr, 8, target_size)); break; default: *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, regs), si->dst_reg, si->src_reg, offsetof(struct bpf_perf_event_data_kern, regs)); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(long), si->dst_reg, si->dst_reg, si->off); break; } return insn - insn_buf; } const struct bpf_verifier_ops perf_event_verifier_ops = { .get_func_proto = pe_prog_func_proto, .is_valid_access = pe_prog_is_valid_access, .convert_ctx_access = pe_prog_convert_ctx_access, }; const struct bpf_prog_ops perf_event_prog_ops = { }; static DEFINE_MUTEX(bpf_event_mutex); #define BPF_TRACE_MAX_PROGS 64 int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog) { struct bpf_prog_array *old_array; struct bpf_prog_array *new_array; int ret = -EEXIST; /* * Kprobe override only works if they are on the function entry, * and only if they are on the opt-in list. */ if (prog->kprobe_override && (!trace_kprobe_on_func_entry(event->tp_event) || !trace_kprobe_error_injectable(event->tp_event))) return -EINVAL; mutex_lock(&bpf_event_mutex); if (event->prog) goto unlock; old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); if (old_array && bpf_prog_array_length(old_array) >= BPF_TRACE_MAX_PROGS) { ret = -E2BIG; goto unlock; } ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array); if (ret < 0) goto unlock; /* set the new array to event->tp_event and set event->prog */ event->prog = prog; rcu_assign_pointer(event->tp_event->prog_array, new_array); bpf_prog_array_free(old_array); unlock: mutex_unlock(&bpf_event_mutex); return ret; } void perf_event_detach_bpf_prog(struct perf_event *event) { struct bpf_prog_array *old_array; struct bpf_prog_array *new_array; int ret; mutex_lock(&bpf_event_mutex); if (!event->prog) goto unlock; old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array); if (ret == -ENOENT) goto unlock; if (ret < 0) { bpf_prog_array_delete_safe(old_array, event->prog); } else { rcu_assign_pointer(event->tp_event->prog_array, new_array); bpf_prog_array_free(old_array); } bpf_prog_put(event->prog); event->prog = NULL; unlock: mutex_unlock(&bpf_event_mutex); } int perf_event_query_prog_array(struct perf_event *event, void __user *info) { struct perf_event_query_bpf __user *uquery = info; struct perf_event_query_bpf query = {}; struct bpf_prog_array *progs; u32 *ids, prog_cnt, ids_len; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (event->attr.type != PERF_TYPE_TRACEPOINT) return -EINVAL; if (copy_from_user(&query, uquery, sizeof(query))) return -EFAULT; ids_len = query.ids_len; if (ids_len > BPF_TRACE_MAX_PROGS) return -E2BIG; ids = kcalloc(ids_len, sizeof(u32), GFP_USER | __GFP_NOWARN); if (!ids) return -ENOMEM; /* * The above kcalloc returns ZERO_SIZE_PTR when ids_len = 0, which * is required when user only wants to check for uquery->prog_cnt. * There is no need to check for it since the case is handled * gracefully in bpf_prog_array_copy_info. */ mutex_lock(&bpf_event_mutex); progs = bpf_event_rcu_dereference(event->tp_event->prog_array); ret = bpf_prog_array_copy_info(progs, ids, ids_len, &prog_cnt); mutex_unlock(&bpf_event_mutex); if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) || copy_to_user(uquery->ids, ids, ids_len * sizeof(u32))) ret = -EFAULT; kfree(ids); return ret; } extern struct bpf_raw_event_map __start__bpf_raw_tp[]; extern struct bpf_raw_event_map __stop__bpf_raw_tp[]; struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name) { struct bpf_raw_event_map *btp = __start__bpf_raw_tp; for (; btp < __stop__bpf_raw_tp; btp++) { if (!strcmp(btp->tp->name, name)) return btp; } return bpf_get_raw_tracepoint_module(name); } void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) { struct module *mod; preempt_disable(); mod = __module_address((unsigned long)btp); module_put(mod); preempt_enable(); } static __always_inline void __bpf_trace_run(struct bpf_prog *prog, u64 *args) { rcu_read_lock(); preempt_disable(); (void) BPF_PROG_RUN(prog, args); preempt_enable(); rcu_read_unlock(); } #define UNPACK(...) __VA_ARGS__ #define REPEAT_1(FN, DL, X, ...) FN(X) #define REPEAT_2(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_1(FN, DL, __VA_ARGS__) #define REPEAT_3(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_2(FN, DL, __VA_ARGS__) #define REPEAT_4(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_3(FN, DL, __VA_ARGS__) #define REPEAT_5(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_4(FN, DL, __VA_ARGS__) #define REPEAT_6(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_5(FN, DL, __VA_ARGS__) #define REPEAT_7(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_6(FN, DL, __VA_ARGS__) #define REPEAT_8(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_7(FN, DL, __VA_ARGS__) #define REPEAT_9(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_8(FN, DL, __VA_ARGS__) #define REPEAT_10(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_9(FN, DL, __VA_ARGS__) #define REPEAT_11(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_10(FN, DL, __VA_ARGS__) #define REPEAT_12(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_11(FN, DL, __VA_ARGS__) #define REPEAT(X, FN, DL, ...) REPEAT_##X(FN, DL, __VA_ARGS__) #define SARG(X) u64 arg##X #define COPY(X) args[X] = arg##X #define __DL_COM (,) #define __DL_SEM (;) #define __SEQ_0_11 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 #define BPF_TRACE_DEFN_x(x) \ void bpf_trace_run##x(struct bpf_prog *prog, \ REPEAT(x, SARG, __DL_COM, __SEQ_0_11)) \ { \ u64 args[x]; \ REPEAT(x, COPY, __DL_SEM, __SEQ_0_11); \ __bpf_trace_run(prog, args); \ } \ EXPORT_SYMBOL_GPL(bpf_trace_run##x) BPF_TRACE_DEFN_x(1); BPF_TRACE_DEFN_x(2); BPF_TRACE_DEFN_x(3); BPF_TRACE_DEFN_x(4); BPF_TRACE_DEFN_x(5); BPF_TRACE_DEFN_x(6); BPF_TRACE_DEFN_x(7); BPF_TRACE_DEFN_x(8); BPF_TRACE_DEFN_x(9); BPF_TRACE_DEFN_x(10); BPF_TRACE_DEFN_x(11); BPF_TRACE_DEFN_x(12); static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog) { struct tracepoint *tp = btp->tp; /* * check that program doesn't access arguments beyond what's * available in this tracepoint */ if (prog->aux->max_ctx_offset > btp->num_args * sizeof(u64)) return -EINVAL; if (prog->aux->max_tp_access > btp->writable_size) return -EINVAL; return tracepoint_probe_register_may_exist(tp, (void *)btp->bpf_func, prog); } int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog) { return __bpf_probe_register(btp, prog); } int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) { return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog); } int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, u64 *probe_addr) { bool is_tracepoint, is_syscall_tp; struct bpf_prog *prog; int flags, err = 0; prog = event->prog; if (!prog) return -ENOENT; /* not supporting BPF_PROG_TYPE_PERF_EVENT yet */ if (prog->type == BPF_PROG_TYPE_PERF_EVENT) return -EOPNOTSUPP; *prog_id = prog->aux->id; flags = event->tp_event->flags; is_tracepoint = flags & TRACE_EVENT_FL_TRACEPOINT; is_syscall_tp = is_syscall_trace_event(event->tp_event); if (is_tracepoint || is_syscall_tp) { *buf = is_tracepoint ? event->tp_event->tp->name : event->tp_event->name; *fd_type = BPF_FD_TYPE_TRACEPOINT; *probe_offset = 0x0; *probe_addr = 0x0; } else { /* kprobe/uprobe */ err = -EOPNOTSUPP; #ifdef CONFIG_KPROBE_EVENTS if (flags & TRACE_EVENT_FL_KPROBE) err = bpf_get_kprobe_info(event, fd_type, buf, probe_offset, probe_addr, event->attr.type == PERF_TYPE_TRACEPOINT); #endif #ifdef CONFIG_UPROBE_EVENTS if (flags & TRACE_EVENT_FL_UPROBE) err = bpf_get_uprobe_info(event, fd_type, buf, probe_offset, event->attr.type == PERF_TYPE_TRACEPOINT); #endif } return err; } static int __init send_signal_irq_work_init(void) { int cpu; struct send_signal_irq_work *work; for_each_possible_cpu(cpu) { work = per_cpu_ptr(&send_signal_work, cpu); init_irq_work(&work->irq_work, do_bpf_send_signal); } return 0; } subsys_initcall(send_signal_irq_work_init); #ifdef CONFIG_MODULES static int bpf_event_notify(struct notifier_block *nb, unsigned long op, void *module) { struct bpf_trace_module *btm, *tmp; struct module *mod = module; if (mod->num_bpf_raw_events == 0 || (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING)) return 0; mutex_lock(&bpf_module_mutex); switch (op) { case MODULE_STATE_COMING: btm = kzalloc(sizeof(*btm), GFP_KERNEL); if (btm) { btm->module = module; list_add(&btm->list, &bpf_trace_modules); } break; case MODULE_STATE_GOING: list_for_each_entry_safe(btm, tmp, &bpf_trace_modules, list) { if (btm->module == module) { list_del(&btm->list); kfree(btm); break; } } break; } mutex_unlock(&bpf_module_mutex); return 0; } static struct notifier_block bpf_module_nb = { .notifier_call = bpf_event_notify, }; static int __init bpf_event_init(void) { register_module_notifier(&bpf_module_nb); return 0; } fs_initcall(bpf_event_init); #endif /* CONFIG_MODULES */
821 1291 429 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 // SPDX-License-Identifier: GPL-2.0-only /* -*- linux-c -*- * sysctl_net.c: sysctl interface to net subsystem. * * Begun April 1, 1996, Mike Shaver. * Added /proc/sys/net directories for each protocol family. [MS] * * Revision 1.2 1996/05/08 20:24:40 shaver * Added bits for NET_BRIDGE and the NET_IPV4_ARP stuff and * NET_IPV4_IP_FORWARD. * * */ #include <linux/mm.h> #include <linux/export.h> #include <linux/sysctl.h> #include <linux/nsproxy.h> #include <net/sock.h> #ifdef CONFIG_INET #include <net/ip.h> #endif #ifdef CONFIG_NET #include <linux/if_ether.h> #endif static struct ctl_table_set * net_ctl_header_lookup(struct ctl_table_root *root) { return &current->nsproxy->net_ns->sysctls; } static int is_seen(struct ctl_table_set *set) { return &current->nsproxy->net_ns->sysctls == set; } /* Return standard mode bits for table entry. */ static int net_ctl_permissions(struct ctl_table_header *head, struct ctl_table *table) { struct net *net = container_of(head->set, struct net, sysctls); /* Allow network administrator to have same access as root. */ if (ns_capable_noaudit(net->user_ns, CAP_NET_ADMIN)) { int mode = (table->mode >> 6) & 7; return (mode << 6) | (mode << 3) | mode; } return table->mode; } static void net_ctl_set_ownership(struct ctl_table_header *head, struct ctl_table *table, kuid_t *uid, kgid_t *gid) { struct net *net = container_of(head->set, struct net, sysctls); kuid_t ns_root_uid; kgid_t ns_root_gid; ns_root_uid = make_kuid(net->user_ns, 0); if (uid_valid(ns_root_uid)) *uid = ns_root_uid; ns_root_gid = make_kgid(net->user_ns, 0); if (gid_valid(ns_root_gid)) *gid = ns_root_gid; } static struct ctl_table_root net_sysctl_root = { .lookup = net_ctl_header_lookup, .permissions = net_ctl_permissions, .set_ownership = net_ctl_set_ownership, }; static int __net_init sysctl_net_init(struct net *net) { setup_sysctl_set(&net->sysctls, &net_sysctl_root, is_seen); return 0; } static void __net_exit sysctl_net_exit(struct net *net) { retire_sysctl_set(&net->sysctls); } static struct pernet_operations sysctl_pernet_ops = { .init = sysctl_net_init, .exit = sysctl_net_exit, }; static struct ctl_table_header *net_header; __init int net_sysctl_init(void) { static struct ctl_table empty[1]; int ret = -ENOMEM; /* Avoid limitations in the sysctl implementation by * registering "/proc/sys/net" as an empty directory not in a * network namespace. */ net_header = register_sysctl("net", empty); if (!net_header) goto out; ret = register_pernet_subsys(&sysctl_pernet_ops); if (ret) goto out1; out: return ret; out1: unregister_sysctl_table(net_header); net_header = NULL; goto out; } struct ctl_table_header *register_net_sysctl(struct net *net, const char *path, struct ctl_table *table) { return __register_sysctl_table(&net->sysctls, path, table); } EXPORT_SYMBOL_GPL(register_net_sysctl); void unregister_net_sysctl_table(struct ctl_table_header *header) { unregister_sysctl_table(header); } EXPORT_SYMBOL_GPL(unregister_net_sysctl_table);
67 1 1381 1 4 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_WAIT_BIT_H #define _LINUX_WAIT_BIT_H /* * Linux wait-bit related types and methods: */ #include <linux/wait.h> struct wait_bit_key { void *flags; int bit_nr; unsigned long timeout; }; struct wait_bit_queue_entry { struct wait_bit_key key; struct wait_queue_entry wq_entry; }; #define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ { .flags = word, .bit_nr = bit, } typedef int wait_bit_action_f(struct wait_bit_key *key, int mode); void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit); int __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); int __wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); void wake_up_bit(void *word, int bit); int out_of_line_wait_on_bit(void *word, int, wait_bit_action_f *action, unsigned int mode); int out_of_line_wait_on_bit_timeout(void *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout); int out_of_line_wait_on_bit_lock(void *word, int, wait_bit_action_f *action, unsigned int mode); struct wait_queue_head *bit_waitqueue(void *word, int bit); extern void __init wait_bit_init(void); int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); #define DEFINE_WAIT_BIT(name, word, bit) \ struct wait_bit_queue_entry name = { \ .key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \ .wq_entry = { \ .private = current, \ .func = wake_bit_function, \ .entry = \ LIST_HEAD_INIT((name).wq_entry.entry), \ }, \ } extern int bit_wait(struct wait_bit_key *key, int mode); extern int bit_wait_io(struct wait_bit_key *key, int mode); extern int bit_wait_timeout(struct wait_bit_key *key, int mode); extern int bit_wait_io_timeout(struct wait_bit_key *key, int mode); /** * wait_on_bit - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * There is a standard hashed waitqueue table for generic use. This * is the part of the hashtable's accessor API that waits on a bit. * For instance, if one were to have waiters on a bitflag, one would * call wait_on_bit() in threads waiting for the bit to clear. * One uses wait_on_bit() where one is waiting for the bit to clear, * but has no intention of setting it. * Returned value will be zero if the bit was cleared, or non-zero * if the process received a signal and the mode permitted wakeup * on that signal. */ static inline int wait_on_bit(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_bit(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, bit_wait, mode); } /** * wait_on_bit_io - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared. This is similar to wait_on_bit(), but calls * io_schedule() instead of schedule() for the actual waiting. * * Returned value will be zero if the bit was cleared, or non-zero * if the process received a signal and the mode permitted wakeup * on that signal. */ static inline int wait_on_bit_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_bit(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, bit_wait_io, mode); } /** * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * @timeout: timeout, in jiffies * * Use the standard hashed waitqueue table to wait for a bit * to be cleared. This is similar to wait_on_bit(), except also takes a * timeout parameter. * * Returned value will be zero if the bit was cleared before the * @timeout elapsed, or non-zero if the @timeout elapsed or process * received a signal and the mode permitted wakeup on that signal. */ static inline int wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, unsigned long timeout) { might_sleep(); if (!test_bit(bit, word)) return 0; return out_of_line_wait_on_bit_timeout(word, bit, bit_wait_timeout, mode, timeout); } /** * wait_on_bit_action - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared, and allow the waiting action to be specified. * This is like wait_on_bit() but allows fine control of how the waiting * is done. * * Returned value will be zero if the bit was cleared, or non-zero * if the process received a signal and the mode permitted wakeup * on that signal. */ static inline int wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, unsigned mode) { might_sleep(); if (!test_bit(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, action, mode); } /** * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * There is a standard hashed waitqueue table for generic use. This * is the part of the hashtable's accessor API that waits on a bit * when one intends to set it, for instance, trying to lock bitflags. * For instance, if one were to have waiters trying to set bitflag * and waiting for it to clear before setting it, one would call * wait_on_bit() in threads waiting to be able to set the bit. * One uses wait_on_bit_lock() where one is waiting for the bit to * clear with the intention of setting it, and when done, clearing it. * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and * the @mode allows that signal to wake the process. */ static inline int wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) return 0; return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode); } /** * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared and then to atomically set it. This is similar * to wait_on_bit(), but calls io_schedule() instead of schedule() * for the actual waiting. * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and * the @mode allows that signal to wake the process. */ static inline int wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) return 0; return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode); } /** * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared and then to set it, and allow the waiting action * to be specified. * This is like wait_on_bit() but allows fine control of how the waiting * is done. * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and * the @mode allows that signal to wake the process. */ static inline int wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) return 0; return out_of_line_wait_on_bit_lock(word, bit, action, mode); } extern void init_wait_var_entry(struct wait_bit_queue_entry *wbq_entry, void *var, int flags); extern void wake_up_var(void *var); extern wait_queue_head_t *__var_waitqueue(void *p); #define ___wait_var_event(var, condition, state, exclusive, ret, cmd) \ ({ \ __label__ __out; \ struct wait_queue_head *__wq_head = __var_waitqueue(var); \ struct wait_bit_queue_entry __wbq_entry; \ long __ret = ret; /* explicit shadow */ \ \ init_wait_var_entry(&__wbq_entry, var, \ exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ for (;;) { \ long __int = prepare_to_wait_event(__wq_head, \ &__wbq_entry.wq_entry, \ state); \ if (condition) \ break; \ \ if (___wait_is_interruptible(state) && __int) { \ __ret = __int; \ goto __out; \ } \ \ cmd; \ } \ finish_wait(__wq_head, &__wbq_entry.wq_entry); \ __out: __ret; \ }) #define __wait_var_event(var, condition) \ ___wait_var_event(var, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ schedule()) #define wait_var_event(var, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __wait_var_event(var, condition); \ } while (0) #define __wait_var_event_killable(var, condition) \ ___wait_var_event(var, condition, TASK_KILLABLE, 0, 0, \ schedule()) #define wait_var_event_killable(var, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_var_event_killable(var, condition); \ __ret; \ }) #define __wait_var_event_timeout(var, condition, timeout) \ ___wait_var_event(var, ___wait_cond_timeout(condition), \ TASK_UNINTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) #define wait_var_event_timeout(var, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_var_event_timeout(var, condition, timeout); \ __ret; \ }) #define __wait_var_event_interruptible(var, condition) \ ___wait_var_event(var, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule()) #define wait_var_event_interruptible(var, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_var_event_interruptible(var, condition); \ __ret; \ }) /** * clear_and_wake_up_bit - clear a bit and wake up anyone waiting on that bit * * @bit: the bit of the word being waited on * @word: the word being waited on, a kernel virtual address * * You can use this helper if bitflags are manipulated atomically rather than * non-atomically under a lock. */ static inline void clear_and_wake_up_bit(int bit, void *word) { clear_bit_unlock(bit, word); /* See wake_up_bit() for which memory barrier you need to use. */ smp_mb__after_atomic(); wake_up_bit(word, bit); } #endif /* _LINUX_WAIT_BIT_H */
411 408 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _TRACE_SYSCALL_H #define _TRACE_SYSCALL_H #include <linux/tracepoint.h> #include <linux/unistd.h> #include <linux/trace_events.h> #include <linux/thread_info.h> #include <asm/ptrace.h> /* * A syscall entry in the ftrace syscalls array. * * @name: name of the syscall * @syscall_nr: number of the syscall * @nb_args: number of parameters it takes * @types: list of types as strings * @args: list of args as strings (args[i] matches types[i]) * @enter_fields: list of fields for syscall_enter trace event * @enter_event: associated syscall_enter trace event * @exit_event: associated syscall_exit trace event */ struct syscall_metadata { const char *name; int syscall_nr; int nb_args; const char **types; const char **args; struct list_head enter_fields; struct trace_event_call *enter_event; struct trace_event_call *exit_event; }; #if defined(CONFIG_TRACEPOINTS) && defined(CONFIG_HAVE_SYSCALL_TRACEPOINTS) static inline void syscall_tracepoint_update(struct task_struct *p) { if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) set_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT); else clear_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT); } #else static inline void syscall_tracepoint_update(struct task_struct *p) { } #endif #endif /* _TRACE_SYSCALL_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PERCPU_COUNTER_H #define _LINUX_PERCPU_COUNTER_H /* * A simple "approximate counter" for use in ext2 and ext3 superblocks. * * WARNING: these things are HUGE. 4 kbytes per counter on 32-way P4. */ #include <linux/spinlock.h> #include <linux/smp.h> #include <linux/list.h> #include <linux/threads.h> #include <linux/percpu.h> #include <linux/types.h> #include <linux/gfp.h> #ifdef CONFIG_SMP struct percpu_counter { raw_spinlock_t lock; s64 count; #ifdef CONFIG_HOTPLUG_CPU struct list_head list; /* All percpu_counters are on a list */ #endif s32 __percpu *counters; }; extern int percpu_counter_batch; int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp, struct lock_class_key *key); #define percpu_counter_init(fbc, value, gfp) \ ({ \ static struct lock_class_key __key; \ \ __percpu_counter_init(fbc, value, gfp, &__key); \ }) void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) { return __percpu_counter_compare(fbc, rhs, percpu_counter_batch); } static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { s64 ret = __percpu_counter_sum(fbc); return ret < 0 ? 0 : ret; } static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { return __percpu_counter_sum(fbc); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) { return fbc->count; } /* * It is possible for the percpu_counter_read() to return a small negative * number for some counter which should never be negative. * */ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc) { /* Prevent reloads of fbc->count */ s64 ret = READ_ONCE(fbc->count); if (ret >= 0) return ret; return 0; } static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return (fbc->counters != NULL); } #else /* !CONFIG_SMP */ struct percpu_counter { s64 count; }; static inline int percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp) { fbc->count = amount; return 0; } static inline void percpu_counter_destroy(struct percpu_counter *fbc) { } static inline void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { fbc->count = amount; } static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) { if (fbc->count > rhs) return 1; else if (fbc->count < rhs) return -1; else return 0; } static inline int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { return percpu_counter_compare(fbc, rhs); } static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { preempt_disable(); fbc->count += amount; preempt_enable(); } static inline void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { percpu_counter_add(fbc, amount); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) { return fbc->count; } /* * percpu_counter is intended to track positive numbers. In the UP case the * number should never be negative. */ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc) { return fbc->count; } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { return percpu_counter_read_positive(fbc); } static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { return percpu_counter_read(fbc); } static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return true; } #endif /* CONFIG_SMP */ static inline void percpu_counter_inc(struct percpu_counter *fbc) { percpu_counter_add(fbc, 1); } static inline void percpu_counter_dec(struct percpu_counter *fbc) { percpu_counter_add(fbc, -1); } static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount) { percpu_counter_add(fbc, -amount); } #endif /* _LINUX_PERCPU_COUNTER_H */
8003 8145 7699 496 12 12 1205 94 94 1397 1397 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 // SPDX-License-Identifier: GPL-2.0-or-later /* Common capabilities, needed by capability.o. */ #include <linux/capability.h> #include <linux/audit.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/lsm_hooks.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/ptrace.h> #include <linux/xattr.h> #include <linux/hugetlb.h> #include <linux/mount.h> #include <linux/sched.h> #include <linux/prctl.h> #include <linux/securebits.h> #include <linux/user_namespace.h> #include <linux/binfmts.h> #include <linux/personality.h> /* * If a non-root user executes a setuid-root binary in * !secure(SECURE_NOROOT) mode, then we raise capabilities. * However if fE is also set, then the intent is for only * the file capabilities to be applied, and the setuid-root * bit is left on either to change the uid (plausible) or * to get full privilege on a kernel without file capabilities * support. So in that case we do not raise capabilities. * * Warn if that happens, once per boot. */ static void warn_setuid_and_fcaps_mixed(const char *fname) { static int warned; if (!warned) { printk(KERN_INFO "warning: `%s' has both setuid-root and" " effective capabilities. Therefore not raising all" " capabilities.\n", fname); warned = 1; } } /** * cap_capable - Determine whether a task has a particular effective capability * @cred: The credentials to use * @ns: The user namespace in which we need the capability * @cap: The capability to check for * @opts: Bitmask of options defined in include/linux/security.h * * Determine whether the nominated task has the specified capability amongst * its effective set, returning 0 if it does, -ve if it does not. * * NOTE WELL: cap_has_capability() cannot be used like the kernel's capable() * and has_capability() functions. That is, it has the reverse semantics: * cap_has_capability() returns 0 when a task has a capability, but the * kernel's capable() and has_capability() returns 1 for this case. */ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, int cap, unsigned int opts) { struct user_namespace *ns = targ_ns; /* See if cred has the capability in the target user namespace * by examining the target user namespace and all of the target * user namespace's parents. */ for (;;) { /* Do we have the necessary capabilities? */ if (ns == cred->user_ns) return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM; /* * If we're already at a lower level than we're looking for, * we're done searching. */ if (ns->level <= cred->user_ns->level) return -EPERM; /* * The owner of the user namespace in the parent of the * user namespace has all caps. */ if ((ns->parent == cred->user_ns) && uid_eq(ns->owner, cred->euid)) return 0; /* * If you have a capability in a parent user ns, then you have * it over all children user namespaces as well. */ ns = ns->parent; } /* We never get here */ } /** * cap_settime - Determine whether the current process may set the system clock * @ts: The time to set * @tz: The timezone to set * * Determine whether the current process may set the system clock and timezone * information, returning 0 if permission granted, -ve if denied. */ int cap_settime(const struct timespec64 *ts, const struct timezone *tz) { if (!capable(CAP_SYS_TIME)) return -EPERM; return 0; } /** * cap_ptrace_access_check - Determine whether the current process may access * another * @child: The process to be accessed * @mode: The mode of attachment. * * If we are in the same or an ancestor user_ns and have all the target * task's capabilities, then ptrace access is allowed. * If we have the ptrace capability to the target user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether a process may access another, returning 0 if permission * granted, -ve if denied. */ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode) { int ret = 0; const struct cred *cred, *child_cred; const kernel_cap_t *caller_caps; rcu_read_lock(); cred = current_cred(); child_cred = __task_cred(child); if (mode & PTRACE_MODE_FSCREDS) caller_caps = &cred->cap_effective; else caller_caps = &cred->cap_permitted; if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, *caller_caps)) goto out; if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_ptrace_traceme - Determine whether another process may trace the current * @parent: The task proposed to be the tracer * * If parent is in the same or an ancestor user_ns and has all current's * capabilities, then ptrace access is allowed. * If parent has the ptrace capability to current's user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether the nominated task is permitted to trace the current * process, returning 0 if permission is granted, -ve if denied. */ int cap_ptrace_traceme(struct task_struct *parent) { int ret = 0; const struct cred *cred, *child_cred; rcu_read_lock(); cred = __task_cred(parent); child_cred = current_cred(); if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) goto out; if (has_ns_capability(parent, child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_capget - Retrieve a task's capability sets * @target: The task from which to retrieve the capability sets * @effective: The place to record the effective set * @inheritable: The place to record the inheritable set * @permitted: The place to record the permitted set * * This function retrieves the capabilities of the nominated task and returns * them to the caller. */ int cap_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { const struct cred *cred; /* Derived from kernel/capability.c:sys_capget. */ rcu_read_lock(); cred = __task_cred(target); *effective = cred->cap_effective; *inheritable = cred->cap_inheritable; *permitted = cred->cap_permitted; rcu_read_unlock(); return 0; } /* * Determine whether the inheritable capabilities are limited to the old * permitted set. Returns 1 if they are limited, 0 if they are not. */ static inline int cap_inh_is_capped(void) { /* they are so limited unless the current task has the CAP_SETPCAP * capability */ if (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) == 0) return 0; return 1; } /** * cap_capset - Validate and apply proposed changes to current's capabilities * @new: The proposed new credentials; alterations should be made here * @old: The current task's current credentials * @effective: A pointer to the proposed new effective capabilities set * @inheritable: A pointer to the proposed new inheritable capabilities set * @permitted: A pointer to the proposed new permitted capabilities set * * This function validates and applies a proposed mass change to the current * process's capability sets. The changes are made to the proposed new * credentials, and assuming no error, will be committed by the caller of LSM. */ int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { if (cap_inh_is_capped() && !cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_permitted))) /* incapable of using this inheritable set */ return -EPERM; if (!cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_bset))) /* no new pI capabilities outside bounding set */ return -EPERM; /* verify restrictions on target's new Permitted set */ if (!cap_issubset(*permitted, old->cap_permitted)) return -EPERM; /* verify the _new_Effective_ is a subset of the _new_Permitted_ */ if (!cap_issubset(*effective, *permitted)) return -EPERM; new->cap_effective = *effective; new->cap_inheritable = *inheritable; new->cap_permitted = *permitted; /* * Mask off ambient bits that are no longer both permitted and * inheritable. */ new->cap_ambient = cap_intersect(new->cap_ambient, cap_intersect(*permitted, *inheritable)); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EINVAL; return 0; } /** * cap_inode_need_killpriv - Determine if inode change affects privileges * @dentry: The inode/dentry in being changed with change marked ATTR_KILL_PRIV * * Determine if an inode having a change applied that's marked ATTR_KILL_PRIV * affects the security markings on that inode, and if it is, should * inode_killpriv() be invoked or the change rejected. * * Returns 1 if security.capability has a value, meaning inode_killpriv() * is required, 0 otherwise, meaning inode_killpriv() is not required. */ int cap_inode_need_killpriv(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); int error; error = __vfs_getxattr(dentry, inode, XATTR_NAME_CAPS, NULL, 0, XATTR_NOSECURITY); return error > 0; } /** * cap_inode_killpriv - Erase the security markings on an inode * @dentry: The inode/dentry to alter * * Erase the privilege-enhancing security markings on an inode. * * Returns 0 if successful, -ve on error. */ int cap_inode_killpriv(struct dentry *dentry) { int error; error = __vfs_removexattr(dentry, XATTR_NAME_CAPS); if (error == -EOPNOTSUPP) error = 0; return error; } static bool rootid_owns_currentns(kuid_t kroot) { struct user_namespace *ns; if (!uid_valid(kroot)) return false; for (ns = current_user_ns(); ; ns = ns->parent) { if (from_kuid(ns, kroot) == 0) return true; if (ns == &init_user_ns) break; } return false; } static __u32 sansflags(__u32 m) { return m & ~VFS_CAP_FLAGS_EFFECTIVE; } static bool is_v2header(size_t size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_2) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_2; } static bool is_v3header(size_t size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_3) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_3; } /* * getsecurity: We are called for security.* before any attempt to read the * xattr from the inode itself. * * This gives us a chance to read the on-disk value and convert it. If we * return -EOPNOTSUPP, then vfs_getxattr() will call the i_op handler. * * Note we are not called by vfs_getxattr_alloc(), but that is only called * by the integrity subsystem, which really wants the unconverted values - * so that's good. */ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc) { int size, ret; kuid_t kroot; u32 nsmagic, magic; uid_t root, mappedroot; char *tmpbuf = NULL; struct vfs_cap_data *cap; struct vfs_ns_cap_data *nscap = NULL; struct dentry *dentry; struct user_namespace *fs_ns; if (strcmp(name, "capability") != 0) return -EOPNOTSUPP; dentry = d_find_any_alias(inode); if (!dentry) return -EINVAL; size = sizeof(struct vfs_ns_cap_data); ret = (int) vfs_getxattr_alloc(dentry, XATTR_NAME_CAPS, &tmpbuf, size, GFP_NOFS); dput(dentry); if (ret < 0 || !tmpbuf) { size = ret; goto out_free; } fs_ns = inode->i_sb->s_user_ns; cap = (struct vfs_cap_data *) tmpbuf; if (is_v2header((size_t) ret, cap)) { root = 0; } else if (is_v3header((size_t) ret, cap)) { nscap = (struct vfs_ns_cap_data *) tmpbuf; root = le32_to_cpu(nscap->rootid); } else { size = -EINVAL; goto out_free; } kroot = make_kuid(fs_ns, root); /* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ mappedroot = from_kuid(current_user_ns(), kroot); if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) { size = sizeof(struct vfs_ns_cap_data); if (alloc) { if (!nscap) { /* v2 -> v3 conversion */ nscap = kzalloc(size, GFP_ATOMIC); if (!nscap) { size = -ENOMEM; goto out_free; } nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); nscap->magic_etc = cpu_to_le32(nsmagic); } else { /* use allocated v3 buffer */ tmpbuf = NULL; } nscap->rootid = cpu_to_le32(mappedroot); *buffer = nscap; } goto out_free; } if (!rootid_owns_currentns(kroot)) { size = -EOVERFLOW; goto out_free; } /* This comes from a parent namespace. Return as a v2 capability */ size = sizeof(struct vfs_cap_data); if (alloc) { if (nscap) { /* v3 -> v2 conversion */ cap = kzalloc(size, GFP_ATOMIC); if (!cap) { size = -ENOMEM; goto out_free; } magic = VFS_CAP_REVISION_2; nsmagic = le32_to_cpu(nscap->magic_etc); if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE) magic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32); cap->magic_etc = cpu_to_le32(magic); } else { /* use unconverted v2 */ tmpbuf = NULL; } *buffer = cap; } out_free: kfree(tmpbuf); return size; } static kuid_t rootid_from_xattr(const void *value, size_t size, struct user_namespace *task_ns) { const struct vfs_ns_cap_data *nscap = value; uid_t rootid = 0; if (size == XATTR_CAPS_SZ_3) rootid = le32_to_cpu(nscap->rootid); return make_kuid(task_ns, rootid); } static bool validheader(size_t size, const struct vfs_cap_data *cap) { return is_v2header(size, cap) || is_v3header(size, cap); } /* * User requested a write of security.capability. If needed, update the * xattr to change from v2 to v3, or to fixup the v3 rootid. * * If all is ok, we return the new size, on error return < 0. */ int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size) { struct vfs_ns_cap_data *nscap; uid_t nsrootid; const struct vfs_cap_data *cap = *ivalue; __u32 magic, nsmagic; struct inode *inode = d_backing_inode(dentry); struct user_namespace *task_ns = current_user_ns(), *fs_ns = inode->i_sb->s_user_ns; kuid_t rootid; size_t newsize; if (!*ivalue) return -EINVAL; if (!validheader(size, cap)) return -EINVAL; if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP)) return -EPERM; if (size == XATTR_CAPS_SZ_2) if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) /* user is privileged, just write the v2 */ return size; rootid = rootid_from_xattr(*ivalue, size, task_ns); if (!uid_valid(rootid)) return -EINVAL; nsrootid = from_kuid(fs_ns, rootid); if (nsrootid == -1) return -EINVAL; newsize = sizeof(struct vfs_ns_cap_data); nscap = kmalloc(newsize, GFP_ATOMIC); if (!nscap) return -ENOMEM; nscap->rootid = cpu_to_le32(nsrootid); nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; nscap->magic_etc = cpu_to_le32(nsmagic); memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); kvfree(*ivalue); *ivalue = nscap; return newsize; } /* * Calculate the new process capability sets from the capability sets attached * to a file. */ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, struct linux_binprm *bprm, bool *effective, bool *has_fcap) { struct cred *new = bprm->cred; unsigned i; int ret = 0; if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE) *effective = true; if (caps->magic_etc & VFS_CAP_REVISION_MASK) *has_fcap = true; CAP_FOR_EACH_U32(i) { __u32 permitted = caps->permitted.cap[i]; __u32 inheritable = caps->inheritable.cap[i]; /* * pP' = (X & fP) | (pI & fI) * The addition of pA' is handled later. */ new->cap_permitted.cap[i] = (new->cap_bset.cap[i] & permitted) | (new->cap_inheritable.cap[i] & inheritable); if (permitted & ~new->cap_permitted.cap[i]) /* insufficient to execute correctly */ ret = -EPERM; } /* * For legacy apps, with no internal support for recognizing they * do not have enough capabilities, we return an error if they are * missing some "forced" (aka file-permitted) capabilities. */ return *effective ? ret : 0; } /* * Extract the on-exec-apply capability sets for an executable file. */ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps) { struct inode *inode = d_backing_inode(dentry); __u32 magic_etc; unsigned tocopy, i; int size; struct vfs_ns_cap_data data, *nscaps = &data; struct vfs_cap_data *caps = (struct vfs_cap_data *) &data; kuid_t rootkuid; struct user_namespace *fs_ns; memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data)); if (!inode) return -ENODATA; fs_ns = inode->i_sb->s_user_ns; size = __vfs_getxattr((struct dentry *)dentry, inode, XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ, XATTR_NOSECURITY); if (size == -ENODATA || size == -EOPNOTSUPP) /* no data, that's ok */ return -ENODATA; if (size < 0) return size; if (size < sizeof(magic_etc)) return -EINVAL; cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps->magic_etc); rootkuid = make_kuid(fs_ns, 0); switch (magic_etc & VFS_CAP_REVISION_MASK) { case VFS_CAP_REVISION_1: if (size != XATTR_CAPS_SZ_1) return -EINVAL; tocopy = VFS_CAP_U32_1; break; case VFS_CAP_REVISION_2: if (size != XATTR_CAPS_SZ_2) return -EINVAL; tocopy = VFS_CAP_U32_2; break; case VFS_CAP_REVISION_3: if (size != XATTR_CAPS_SZ_3) return -EINVAL; tocopy = VFS_CAP_U32_3; rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid)); break; default: return -EINVAL; } /* Limit the caps to the mounter of the filesystem * or the more limited uid specified in the xattr. */ if (!rootid_owns_currentns(rootkuid)) return -ENODATA; CAP_FOR_EACH_U32(i) { if (i >= tocopy) break; cpu_caps->permitted.cap[i] = le32_to_cpu(caps->data[i].permitted); cpu_caps->inheritable.cap[i] = le32_to_cpu(caps->data[i].inheritable); } cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; cpu_caps->rootid = rootkuid; return 0; } /* * Attempt to get the on-exec apply capability sets for an executable file from * its xattrs and, if present, apply them to the proposed credentials being * constructed by execve(). */ static int get_file_caps(struct linux_binprm *bprm, bool *effective, bool *has_fcap) { int rc = 0; struct cpu_vfs_cap_data vcaps; cap_clear(bprm->cred->cap_permitted); if (!file_caps_enabled) return 0; if (!mnt_may_suid(bprm->file->f_path.mnt)) return 0; /* * This check is redundant with mnt_may_suid() but is kept to make * explicit that capability bits are limited to s_user_ns and its * descendants. */ if (!current_in_userns(bprm->file->f_path.mnt->mnt_sb->s_user_ns)) return 0; rc = get_vfs_caps_from_disk(bprm->file->f_path.dentry, &vcaps); if (rc < 0) { if (rc == -EINVAL) printk(KERN_NOTICE "Invalid argument reading file caps for %s\n", bprm->filename); else if (rc == -ENODATA) rc = 0; goto out; } rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective, has_fcap); out: if (rc) cap_clear(bprm->cred->cap_permitted); return rc; } static inline bool root_privileged(void) { return !issecure(SECURE_NOROOT); } static inline bool __is_real(kuid_t uid, struct cred *cred) { return uid_eq(cred->uid, uid); } static inline bool __is_eff(kuid_t uid, struct cred *cred) { return uid_eq(cred->euid, uid); } static inline bool __is_suid(kuid_t uid, struct cred *cred) { return !__is_real(uid, cred) && __is_eff(uid, cred); } /* * handle_privileged_root - Handle case of privileged root * @bprm: The execution parameters, including the proposed creds * @has_fcap: Are any file capabilities set? * @effective: Do we have effective root privilege? * @root_uid: This namespace' root UID WRT initial USER namespace * * Handle the case where root is privileged and hasn't been neutered by * SECURE_NOROOT. If file capabilities are set, they won't be combined with * set UID root and nothing is changed. If we are root, cap_permitted is * updated. If we have become set UID root, the effective bit is set. */ static void handle_privileged_root(struct linux_binprm *bprm, bool has_fcap, bool *effective, kuid_t root_uid) { const struct cred *old = current_cred(); struct cred *new = bprm->cred; if (!root_privileged()) return; /* * If the legacy file capability is set, then don't set privs * for a setuid root binary run by a non-root user. Do set it * for a root user just to cause least surprise to an admin. */ if (has_fcap && __is_suid(root_uid, new)) { warn_setuid_and_fcaps_mixed(bprm->filename); return; } /* * To support inheritance of root-permissions and suid-root * executables under compatibility mode, we override the * capability sets for the file. */ if (__is_eff(root_uid, new) || __is_real(root_uid, new)) { /* pP' = (cap_bset & ~0) | (pI & ~0) */ new->cap_permitted = cap_combine(old->cap_bset, old->cap_inheritable); } /* * If only the real uid is 0, we do not set the effective bit. */ if (__is_eff(root_uid, new)) *effective = true; } #define __cap_gained(field, target, source) \ !cap_issubset(target->cap_##field, source->cap_##field) #define __cap_grew(target, source, cred) \ !cap_issubset(cred->cap_##target, cred->cap_##source) #define __cap_full(field, cred) \ cap_issubset(CAP_FULL_SET, cred->cap_##field) static inline bool __is_setuid(struct cred *new, const struct cred *old) { return !uid_eq(new->euid, old->uid); } static inline bool __is_setgid(struct cred *new, const struct cred *old) { return !gid_eq(new->egid, old->gid); } /* * 1) Audit candidate if current->cap_effective is set * * We do not bother to audit if 3 things are true: * 1) cap_effective has all caps * 2) we became root *OR* are were already root * 3) root is supposed to have all caps (SECURE_NOROOT) * Since this is just a normal root execing a process. * * Number 1 above might fail if you don't have a full bset, but I think * that is interesting information to audit. * * A number of other conditions require logging: * 2) something prevented setuid root getting all caps * 3) non-setuid root gets fcaps * 4) non-setuid root gets ambient */ static inline bool nonroot_raised_pE(struct cred *new, const struct cred *old, kuid_t root, bool has_fcap) { bool ret = false; if ((__cap_grew(effective, ambient, new) && !(__cap_full(effective, new) && (__is_eff(root, new) || __is_real(root, new)) && root_privileged())) || (root_privileged() && __is_suid(root, new) && !__cap_full(effective, new)) || (!__is_setuid(new, old) && ((has_fcap && __cap_gained(permitted, new, old)) || __cap_gained(ambient, new, old)))) ret = true; return ret; } /** * cap_bprm_set_creds - Set up the proposed credentials for execve(). * @bprm: The execution parameters, including the proposed creds * * Set up the proposed credentials for a new execution context being * constructed by execve(). The proposed creds in @bprm->cred is altered, * which won't take effect immediately. Returns 0 if successful, -ve on error. */ int cap_bprm_set_creds(struct linux_binprm *bprm) { const struct cred *old = current_cred(); struct cred *new = bprm->cred; bool effective = false, has_fcap = false, is_setid; int ret; kuid_t root_uid; new->cap_ambient = old->cap_ambient; if (WARN_ON(!cap_ambient_invariant_ok(old))) return -EPERM; ret = get_file_caps(bprm, &effective, &has_fcap); if (ret < 0) return ret; root_uid = make_kuid(new->user_ns, 0); handle_privileged_root(bprm, has_fcap, &effective, root_uid); /* if we have fs caps, clear dangerous personality flags */ if (__cap_gained(permitted, new, old)) bprm->per_clear |= PER_CLEAR_ON_SETID; /* Don't let someone trace a set[ug]id/setpcap binary with the revised * credentials unless they have the appropriate permit. * * In addition, if NO_NEW_PRIVS, then ensure we get no new privs. */ is_setid = __is_setuid(new, old) || __is_setgid(new, old); if ((is_setid || __cap_gained(permitted, new, old)) && ((bprm->unsafe & ~LSM_UNSAFE_PTRACE) || !ptracer_capable(current, new->user_ns))) { /* downgrade; they get no more than they had, and maybe less */ if (!ns_capable(new->user_ns, CAP_SETUID) || (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)) { new->euid = new->uid; new->egid = new->gid; } new->cap_permitted = cap_intersect(new->cap_permitted, old->cap_permitted); } new->suid = new->fsuid = new->euid; new->sgid = new->fsgid = new->egid; /* File caps or setid cancels ambient. */ if (has_fcap || is_setid) cap_clear(new->cap_ambient); /* * Now that we've computed pA', update pP' to give: * pP' = (X & fP) | (pI & fI) | pA' */ new->cap_permitted = cap_combine(new->cap_permitted, new->cap_ambient); /* * Set pE' = (fE ? pP' : pA'). Because pA' is zero if fE is set, * this is the same as pE' = (fE ? pP' : 0) | pA'. */ if (effective) new->cap_effective = new->cap_permitted; else new->cap_effective = new->cap_ambient; if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; if (nonroot_raised_pE(new, old, root_uid, has_fcap)) { ret = audit_log_bprm_fcaps(bprm, new, old); if (ret < 0) return ret; } new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; /* Check for privilege-elevated exec. */ bprm->cap_elevated = 0; if (is_setid || (!__is_real(root_uid, new) && (effective || __cap_grew(permitted, ambient, new)))) bprm->cap_elevated = 1; return 0; } /** * cap_inode_setxattr - Determine whether an xattr may be altered * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * @value: The value that the xattr will be changed to * @size: The size of value * @flags: The replacement flag * * Determine whether an xattr may be altered or set on an inode, returning 0 if * permission is granted, -ve if denied. * * This is used to make sure security xattrs don't get updated or set by those * who aren't privileged to do so. */ int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; /* * For XATTR_NAME_CAPS the check will be done in * cap_convert_nscap(), called by setxattr() */ if (strcmp(name, XATTR_NAME_CAPS) == 0) return 0; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /** * cap_inode_removexattr - Determine whether an xattr may be removed * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * * Determine whether an xattr may be removed from an inode, returning 0 if * permission is granted, -ve if denied. * * This is used to make sure security xattrs don't get removed by those who * aren't privileged to remove them. */ int cap_inode_removexattr(struct dentry *dentry, const char *name) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; if (strcmp(name, XATTR_NAME_CAPS) == 0) { /* security.capability gets namespaced */ struct inode *inode = d_backing_inode(dentry); if (!inode) return -EINVAL; if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP)) return -EPERM; return 0; } if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /* * cap_emulate_setxuid() fixes the effective / permitted capabilities of * a process after a call to setuid, setreuid, or setresuid. * * 1) When set*uiding _from_ one of {r,e,s}uid == 0 _to_ all of * {r,e,s}uid != 0, the permitted and effective capabilities are * cleared. * * 2) When set*uiding _from_ euid == 0 _to_ euid != 0, the effective * capabilities of the process are cleared. * * 3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective * capabilities are set to the permitted capabilities. * * fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should * never happen. * * -astor * * cevans - New behaviour, Oct '99 * A process may, via prctl(), elect to keep its capabilities when it * calls setuid() and switches away from uid==0. Both permitted and * effective sets will be retained. * Without this change, it was impossible for a daemon to drop only some * of its privilege. The call to setuid(!=0) would drop all privileges! * Keeping uid 0 is not an option because uid 0 owns too many vital * files.. * Thanks to Olaf Kirch and Peter Benie for spotting this. */ static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old) { kuid_t root_uid = make_kuid(old->user_ns, 0); if ((uid_eq(old->uid, root_uid) || uid_eq(old->euid, root_uid) || uid_eq(old->suid, root_uid)) && (!uid_eq(new->uid, root_uid) && !uid_eq(new->euid, root_uid) && !uid_eq(new->suid, root_uid))) { if (!issecure(SECURE_KEEP_CAPS)) { cap_clear(new->cap_permitted); cap_clear(new->cap_effective); } /* * Pre-ambient programs expect setresuid to nonroot followed * by exec to drop capabilities. We should make sure that * this remains the case. */ cap_clear(new->cap_ambient); } if (uid_eq(old->euid, root_uid) && !uid_eq(new->euid, root_uid)) cap_clear(new->cap_effective); if (!uid_eq(old->euid, root_uid) && uid_eq(new->euid, root_uid)) new->cap_effective = new->cap_permitted; } /** * cap_task_fix_setuid - Fix up the results of setuid() call * @new: The proposed credentials * @old: The current task's current credentials * @flags: Indications of what has changed * * Fix up the results of setuid() call before the credential changes are * actually applied, returning 0 to grant the changes, -ve to deny them. */ int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { switch (flags) { case LSM_SETID_RE: case LSM_SETID_ID: case LSM_SETID_RES: /* juggle the capabilities to follow [RES]UID changes unless * otherwise suppressed */ if (!issecure(SECURE_NO_SETUID_FIXUP)) cap_emulate_setxuid(new, old); break; case LSM_SETID_FS: /* juggle the capabilties to follow FSUID changes, unless * otherwise suppressed * * FIXME - is fsuser used for all CAP_FS_MASK capabilities? * if not, we might be a bit too harsh here. */ if (!issecure(SECURE_NO_SETUID_FIXUP)) { kuid_t root_uid = make_kuid(old->user_ns, 0); if (uid_eq(old->fsuid, root_uid) && !uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_drop_fs_set(new->cap_effective); if (!uid_eq(old->fsuid, root_uid) && uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_raise_fs_set(new->cap_effective, new->cap_permitted); } break; default: return -EINVAL; } return 0; } /* * Rationale: code calling task_setscheduler, task_setioprio, and * task_setnice, assumes that * . if capable(cap_sys_nice), then those actions should be allowed * . if not capable(cap_sys_nice), but acting on your own processes, * then those actions should be allowed * This is insufficient now since you can call code without suid, but * yet with increased caps. * So we check for increased caps on the target process. */ static int cap_safe_nice(struct task_struct *p) { int is_subset, ret = 0; rcu_read_lock(); is_subset = cap_issubset(__task_cred(p)->cap_permitted, current_cred()->cap_permitted); if (!is_subset && !ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) ret = -EPERM; rcu_read_unlock(); return ret; } /** * cap_task_setscheduler - Detemine if scheduler policy change is permitted * @p: The task to affect * * Detemine if the requested scheduler policy change is permitted for the * specified task, returning 0 if permission is granted, -ve if denied. */ int cap_task_setscheduler(struct task_struct *p) { return cap_safe_nice(p); } /** * cap_task_ioprio - Detemine if I/O priority change is permitted * @p: The task to affect * @ioprio: The I/O priority to set * * Detemine if the requested I/O priority change is permitted for the specified * task, returning 0 if permission is granted, -ve if denied. */ int cap_task_setioprio(struct task_struct *p, int ioprio) { return cap_safe_nice(p); } /** * cap_task_ioprio - Detemine if task priority change is permitted * @p: The task to affect * @nice: The nice value to set * * Detemine if the requested task priority change is permitted for the * specified task, returning 0 if permission is granted, -ve if denied. */ int cap_task_setnice(struct task_struct *p, int nice) { return cap_safe_nice(p); } /* * Implement PR_CAPBSET_DROP. Attempt to remove the specified capability from * the current task's bounding set. Returns 0 on success, -ve on error. */ static int cap_prctl_drop(unsigned long cap) { struct cred *new; if (!ns_capable(current_user_ns(), CAP_SETPCAP)) return -EPERM; if (!cap_valid(cap)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_lower(new->cap_bset, cap); return commit_creds(new); } /** * cap_task_prctl - Implement process control functions for this security module * @option: The process control function requested * @arg2, @arg3, @arg4, @arg5: The argument data for this function * * Allow process control functions (sys_prctl()) to alter capabilities; may * also deny access to other functions not otherwise implemented here. * * Returns 0 or +ve on success, -ENOSYS if this function is not implemented * here, other -ve on error. If -ENOSYS is returned, sys_prctl() and other LSM * modules will consider performing the function. */ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { const struct cred *old = current_cred(); struct cred *new; switch (option) { case PR_CAPBSET_READ: if (!cap_valid(arg2)) return -EINVAL; return !!cap_raised(old->cap_bset, arg2); case PR_CAPBSET_DROP: return cap_prctl_drop(arg2); /* * The next four prctl's remain to assist with transitioning a * system from legacy UID=0 based privilege (when filesystem * capabilities are not in use) to a system using filesystem * capabilities only - as the POSIX.1e draft intended. * * Note: * * PR_SET_SECUREBITS = * issecure_mask(SECURE_KEEP_CAPS_LOCKED) * | issecure_mask(SECURE_NOROOT) * | issecure_mask(SECURE_NOROOT_LOCKED) * | issecure_mask(SECURE_NO_SETUID_FIXUP) * | issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED) * * will ensure that the current process and all of its * children will be locked into a pure * capability-based-privilege environment. */ case PR_SET_SECUREBITS: if ((((old->securebits & SECURE_ALL_LOCKS) >> 1) & (old->securebits ^ arg2)) /*[1]*/ || ((old->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/ || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/ || (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) != 0) /*[4]*/ /* * [1] no changing of bits that are locked * [2] no unlocking of locks * [3] no setting of unsupported bits * [4] doing anything requires privilege (go read about * the "sendmail capabilities bug") */ ) /* cannot change a locked bit */ return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; new->securebits = arg2; return commit_creds(new); case PR_GET_SECUREBITS: return old->securebits; case PR_GET_KEEPCAPS: return !!issecure(SECURE_KEEP_CAPS); case PR_SET_KEEPCAPS: if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */ return -EINVAL; if (issecure(SECURE_KEEP_CAPS_LOCKED)) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2) new->securebits |= issecure_mask(SECURE_KEEP_CAPS); else new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); return commit_creds(new); case PR_CAP_AMBIENT: if (arg2 == PR_CAP_AMBIENT_CLEAR_ALL) { if (arg3 | arg4 | arg5) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_clear(new->cap_ambient); return commit_creds(new); } if (((!cap_valid(arg3)) | arg4 | arg5)) return -EINVAL; if (arg2 == PR_CAP_AMBIENT_IS_SET) { return !!cap_raised(current_cred()->cap_ambient, arg3); } else if (arg2 != PR_CAP_AMBIENT_RAISE && arg2 != PR_CAP_AMBIENT_LOWER) { return -EINVAL; } else { if (arg2 == PR_CAP_AMBIENT_RAISE && (!cap_raised(current_cred()->cap_permitted, arg3) || !cap_raised(current_cred()->cap_inheritable, arg3) || issecure(SECURE_NO_CAP_AMBIENT_RAISE))) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2 == PR_CAP_AMBIENT_RAISE) cap_raise(new->cap_ambient, arg3); else cap_lower(new->cap_ambient, arg3); return commit_creds(new); } default: /* No functionality available - continue with default */ return -ENOSYS; } } /** * cap_vm_enough_memory - Determine whether a new virtual mapping is permitted * @mm: The VM space in which the new mapping is to be made * @pages: The size of the mapping * * Determine whether the allocation of a new virtual mapping by the current * task is permitted, returning 1 if permission is granted, 0 if not. */ int cap_vm_enough_memory(struct mm_struct *mm, long pages) { int cap_sys_admin = 0; if (cap_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN, CAP_OPT_NOAUDIT) == 0) cap_sys_admin = 1; return cap_sys_admin; } /* * cap_mmap_addr - check if able to map given addr * @addr: address attempting to be mapped * * If the process is attempting to map memory below dac_mmap_min_addr they need * CAP_SYS_RAWIO. The other parameters to this function are unused by the * capability security module. Returns 0 if this mapping should be allowed * -EPERM if not. */ int cap_mmap_addr(unsigned long addr) { int ret = 0; if (addr < dac_mmap_min_addr) { ret = cap_capable(current_cred(), &init_user_ns, CAP_SYS_RAWIO, CAP_OPT_NONE); /* set PF_SUPERPRIV if it turns out we allow the low mmap */ if (ret == 0) current->flags |= PF_SUPERPRIV; } return ret; } int cap_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { return 0; } #ifdef CONFIG_SECURITY static struct security_hook_list capability_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(capable, cap_capable), LSM_HOOK_INIT(settime, cap_settime), LSM_HOOK_INIT(ptrace_access_check, cap_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, cap_ptrace_traceme), LSM_HOOK_INIT(capget, cap_capget), LSM_HOOK_INIT(capset, cap_capset), LSM_HOOK_INIT(bprm_set_creds, cap_bprm_set_creds), LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv), LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv), LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity), LSM_HOOK_INIT(mmap_addr, cap_mmap_addr), LSM_HOOK_INIT(mmap_file, cap_mmap_file), LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid), LSM_HOOK_INIT(task_prctl, cap_task_prctl), LSM_HOOK_INIT(task_setscheduler, cap_task_setscheduler), LSM_HOOK_INIT(task_setioprio, cap_task_setioprio), LSM_HOOK_INIT(task_setnice, cap_task_setnice), LSM_HOOK_INIT(vm_enough_memory, cap_vm_enough_memory), }; static int __init capability_init(void) { security_add_hooks(capability_hooks, ARRAY_SIZE(capability_hooks), "capability"); return 0; } DEFINE_LSM(capability) = { .name = "capability", .order = LSM_ORDER_FIRST, .init = capability_init, }; #endif /* CONFIG_SECURITY */
2 509 33 2 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com * Written by Alex Tomas <alex@clusterfs.com> */ #ifndef _EXT4_EXTENTS #define _EXT4_EXTENTS #include "ext4.h" /* * With AGGRESSIVE_TEST defined, the capacity of index/leaf blocks * becomes very small, so index split, in-depth growing and * other hard changes happen much more often. * This is for debug purposes only. */ #define AGGRESSIVE_TEST_ /* * With EXTENTS_STATS defined, the number of blocks and extents * are collected in the truncate path. They'll be shown at * umount time. */ #define EXTENTS_STATS__ /* * If CHECK_BINSEARCH is defined, then the results of the binary search * will also be checked by linear search. */ #define CHECK_BINSEARCH__ /* * If EXT_STATS is defined then stats numbers are collected. * These number will be displayed at umount time. */ #define EXT_STATS_ /* * ext4_inode has i_block array (60 bytes total). * The first 12 bytes store ext4_extent_header; * the remainder stores an array of ext4_extent. * For non-inode extent blocks, ext4_extent_tail * follows the array. */ /* * This is the extent tail on-disk structure. * All other extent structures are 12 bytes long. It turns out that * block_size % 12 >= 4 for at least all powers of 2 greater than 512, which * covers all valid ext4 block sizes. Therefore, this tail structure can be * crammed into the end of the block without having to rebalance the tree. */ struct ext4_extent_tail { __le32 et_checksum; /* crc32c(uuid+inum+extent_block) */ }; /* * This is the extent on-disk structure. * It's used at the bottom of the tree. */ struct ext4_extent { __le32 ee_block; /* first logical block extent covers */ __le16 ee_len; /* number of blocks covered by extent */ __le16 ee_start_hi; /* high 16 bits of physical block */ __le32 ee_start_lo; /* low 32 bits of physical block */ }; /* * This is index on-disk structure. * It's used at all the levels except the bottom. */ struct ext4_extent_idx { __le32 ei_block; /* index covers logical blocks from 'block' */ __le32 ei_leaf_lo; /* pointer to the physical block of the next * * level. leaf or next index could be there */ __le16 ei_leaf_hi; /* high 16 bits of physical block */ __u16 ei_unused; }; /* * Each block (leaves and indexes), even inode-stored has header. */ struct ext4_extent_header { __le16 eh_magic; /* probably will support different formats */ __le16 eh_entries; /* number of valid entries */ __le16 eh_max; /* capacity of store in entries */ __le16 eh_depth; /* has tree real underlying blocks? */ __le32 eh_generation; /* generation of the tree */ }; #define EXT4_EXT_MAGIC cpu_to_le16(0xf30a) #define EXT4_MAX_EXTENT_DEPTH 5 #define EXT4_EXTENT_TAIL_OFFSET(hdr) \ (sizeof(struct ext4_extent_header) + \ (sizeof(struct ext4_extent) * le16_to_cpu((hdr)->eh_max))) static inline struct ext4_extent_tail * find_ext4_extent_tail(struct ext4_extent_header *eh) { return (struct ext4_extent_tail *)(((void *)eh) + EXT4_EXTENT_TAIL_OFFSET(eh)); } /* * Array of ext4_ext_path contains path to some extent. * Creation/lookup routines use it for traversal/splitting/etc. * Truncate uses it to simulate recursive walking. */ struct ext4_ext_path { ext4_fsblk_t p_block; __u16 p_depth; __u16 p_maxdepth; struct ext4_extent *p_ext; struct ext4_extent_idx *p_idx; struct ext4_extent_header *p_hdr; struct buffer_head *p_bh; }; /* * Used to record a portion of a cluster found at the beginning or end * of an extent while traversing the extent tree during space removal. * A partial cluster may be removed if it does not contain blocks shared * with extents that aren't being deleted (tofree state). Otherwise, * it cannot be removed (nofree state). */ struct partial_cluster { ext4_fsblk_t pclu; /* physical cluster number */ ext4_lblk_t lblk; /* logical block number within logical cluster */ enum {initial, tofree, nofree} state; }; /* * structure for external API */ /* * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an * initialized extent. This is 2^15 and not (2^16 - 1), since we use the * MSB of ee_len field in the extent datastructure to signify if this * particular extent is an initialized extent or an unwritten (i.e. * preallocated). * EXT_UNWRITTEN_MAX_LEN is the maximum number of blocks we can have in an * unwritten extent. * If ee_len is <= 0x8000, it is an initialized extent. Otherwise, it is an * unwritten one. In other words, if MSB of ee_len is set, it is an * unwritten extent with only one special scenario when ee_len = 0x8000. * In this case we can not have an unwritten extent of zero length and * thus we make it as a special case of initialized extent with 0x8000 length. * This way we get better extent-to-group alignment for initialized extents. * Hence, the maximum number of blocks we can have in an *initialized* * extent is 2^15 (32768) and in an *unwritten* extent is 2^15-1 (32767). */ #define EXT_INIT_MAX_LEN (1UL << 15) #define EXT_UNWRITTEN_MAX_LEN (EXT_INIT_MAX_LEN - 1) #define EXT_FIRST_EXTENT(__hdr__) \ ((struct ext4_extent *) (((char *) (__hdr__)) + \ sizeof(struct ext4_extent_header))) #define EXT_FIRST_INDEX(__hdr__) \ ((struct ext4_extent_idx *) (((char *) (__hdr__)) + \ sizeof(struct ext4_extent_header))) #define EXT_HAS_FREE_INDEX(__path__) \ (le16_to_cpu((__path__)->p_hdr->eh_entries) \ < le16_to_cpu((__path__)->p_hdr->eh_max)) #define EXT_LAST_EXTENT(__hdr__) \ (EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1) #define EXT_LAST_INDEX(__hdr__) \ (EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1) #define EXT_MAX_EXTENT(__hdr__) \ ((le16_to_cpu((__hdr__)->eh_max)) ? \ ((EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) \ : 0) #define EXT_MAX_INDEX(__hdr__) \ ((le16_to_cpu((__hdr__)->eh_max)) ? \ ((EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) : 0) static inline struct ext4_extent_header *ext_inode_hdr(struct inode *inode) { return (struct ext4_extent_header *) EXT4_I(inode)->i_data; } static inline struct ext4_extent_header *ext_block_hdr(struct buffer_head *bh) { return (struct ext4_extent_header *) bh->b_data; } static inline unsigned short ext_depth(struct inode *inode) { return le16_to_cpu(ext_inode_hdr(inode)->eh_depth); } static inline void ext4_ext_mark_unwritten(struct ext4_extent *ext) { /* We can not have an unwritten extent of zero length! */ BUG_ON((le16_to_cpu(ext->ee_len) & ~EXT_INIT_MAX_LEN) == 0); ext->ee_len |= cpu_to_le16(EXT_INIT_MAX_LEN); } static inline int ext4_ext_is_unwritten(struct ext4_extent *ext) { /* Extent with ee_len of 0x8000 is treated as an initialized extent */ return (le16_to_cpu(ext->ee_len) > EXT_INIT_MAX_LEN); } static inline int ext4_ext_get_actual_len(struct ext4_extent *ext) { return (le16_to_cpu(ext->ee_len) <= EXT_INIT_MAX_LEN ? le16_to_cpu(ext->ee_len) : (le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN)); } static inline void ext4_ext_mark_initialized(struct ext4_extent *ext) { ext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ext)); } /* * ext4_ext_pblock: * combine low and high parts of physical block number into ext4_fsblk_t */ static inline ext4_fsblk_t ext4_ext_pblock(struct ext4_extent *ex) { ext4_fsblk_t block; block = le32_to_cpu(ex->ee_start_lo); block |= ((ext4_fsblk_t) le16_to_cpu(ex->ee_start_hi) << 31) << 1; return block; } /* * ext4_idx_pblock: * combine low and high parts of a leaf physical block number into ext4_fsblk_t */ static inline ext4_fsblk_t ext4_idx_pblock(struct ext4_extent_idx *ix) { ext4_fsblk_t block; block = le32_to_cpu(ix->ei_leaf_lo); block |= ((ext4_fsblk_t) le16_to_cpu(ix->ei_leaf_hi) << 31) << 1; return block; } /* * ext4_ext_store_pblock: * stores a large physical block number into an extent struct, * breaking it into parts */ static inline void ext4_ext_store_pblock(struct ext4_extent *ex, ext4_fsblk_t pb) { ex->ee_start_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff)); ex->ee_start_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff); } /* * ext4_idx_store_pblock: * stores a large physical block number into an index struct, * breaking it into parts */ static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix, ext4_fsblk_t pb) { ix->ei_leaf_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff)); ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff); } #define ext4_ext_dirty(handle, inode, path) \ __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path)) int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct ext4_ext_path *path); #endif /* _EXT4_EXTENTS */
10 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 /* SPDX-License-Identifier: GPL-2.0 */ /* include/net/dsfield.h - Manipulation of the Differentiated Services field */ /* Written 1998-2000 by Werner Almesberger, EPFL ICA */ #ifndef __NET_DSFIELD_H #define __NET_DSFIELD_H #include <linux/types.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <asm/byteorder.h> static inline __u8 ipv4_get_dsfield(const struct iphdr *iph) { return iph->tos; } static inline __u8 ipv6_get_dsfield(const struct ipv6hdr *ipv6h) { return ntohs(*(const __be16 *)ipv6h) >> 4; } static inline void ipv4_change_dsfield(struct iphdr *iph,__u8 mask, __u8 value) { __u32 check = ntohs((__force __be16)iph->check); __u8 dsfield; dsfield = (iph->tos & mask) | value; check += iph->tos; if ((check+1) >> 16) check = (check+1) & 0xffff; check -= dsfield; check += check >> 16; /* adjust carry */ iph->check = (__force __sum16)htons(check); iph->tos = dsfield; } static inline void ipv6_change_dsfield(struct ipv6hdr *ipv6h,__u8 mask, __u8 value) { __be16 *p = (__force __be16 *)ipv6h; *p = (*p & htons((((u16)mask << 4) | 0xf00f))) | htons((u16)value << 4); } #endif
101 788 787 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 // SPDX-License-Identifier: GPL-2.0-only /* * This is the 1999 rewrite of IP Firewalling, aiming for kernel 2.3.x. * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2004 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/slab.h> #include <net/ip.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("iptables filter table"); #define FILTER_VALID_HOOKS ((1 << NF_INET_LOCAL_IN) | \ (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT)) static int __net_init iptable_filter_table_init(struct net *net); static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_FILTER, .table_init = iptable_filter_table_init, }; static unsigned int iptable_filter_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ipt_do_table(skb, state, state->net->ipv4.iptable_filter); } static struct nf_hook_ops *filter_ops __read_mostly; /* Default to forward because I got too much mail already. */ static bool forward __read_mostly = true; module_param(forward, bool, 0000); static int __net_init iptable_filter_table_init(struct net *net) { struct ipt_replace *repl; int err; if (net->ipv4.iptable_filter) return 0; repl = ipt_alloc_initial_table(&packet_filter); if (repl == NULL) return -ENOMEM; /* Entry 1 is the FORWARD hook */ ((struct ipt_standard *)repl->entries)[1].target.verdict = forward ? -NF_ACCEPT - 1 : -NF_DROP - 1; err = ipt_register_table(net, &packet_filter, repl, filter_ops, &net->ipv4.iptable_filter); kfree(repl); return err; } static int __net_init iptable_filter_net_init(struct net *net) { if (net == &init_net || !forward) return iptable_filter_table_init(net); return 0; } static void __net_exit iptable_filter_net_exit(struct net *net) { if (!net->ipv4.iptable_filter) return; ipt_unregister_table(net, net->ipv4.iptable_filter, filter_ops); net->ipv4.iptable_filter = NULL; } static struct pernet_operations iptable_filter_net_ops = { .init = iptable_filter_net_init, .exit = iptable_filter_net_exit, }; static int __init iptable_filter_init(void) { int ret; filter_ops = xt_hook_ops_alloc(&packet_filter, iptable_filter_hook); if (IS_ERR(filter_ops)) return PTR_ERR(filter_ops); ret = register_pernet_subsys(&iptable_filter_net_ops); if (ret < 0) kfree(filter_ops); return ret; } static void __exit iptable_filter_fini(void) { unregister_pernet_subsys(&iptable_filter_net_ops); kfree(filter_ops); } module_init(iptable_filter_init); module_exit(iptable_filter_fini);
1444 102 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_BL_H #define _LINUX_RCULIST_BL_H /* * RCU-protected bl list version. See include/linux/list_bl.h. */ #include <linux/list_bl.h> #include <linux/rcupdate.h> static inline void hlist_bl_set_first_rcu(struct hlist_bl_head *h, struct hlist_bl_node *n) { LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) != LIST_BL_LOCKMASK); rcu_assign_pointer(h->first, (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK)); } static inline struct hlist_bl_node *hlist_bl_first_rcu(struct hlist_bl_head *h) { return (struct hlist_bl_node *) ((unsigned long)rcu_dereference_check(h->first, hlist_bl_is_locked(h)) & ~LIST_BL_LOCKMASK); } /** * hlist_bl_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: hlist_bl_unhashed() on the node returns true after this. It is * useful for RCU based read lockfree traversal if the writer side * must know if the list entry is still hashed or already unhashed. * * In particular, it means that we can not poison the forward pointers * that may still be used for walking the hash list and we can only * zero the pprev pointer so list_unhashed() will return true after * this. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another * list-mutation primitive, such as hlist_bl_add_head_rcu() or * hlist_bl_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_bl_for_each_entry_rcu(). */ static inline void hlist_bl_del_init_rcu(struct hlist_bl_node *n) { if (!hlist_bl_unhashed(n)) { __hlist_bl_del(n); n->pprev = NULL; } } /** * hlist_bl_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: hlist_bl_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_bl_add_head_rcu() * or hlist_bl_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_bl_for_each_entry(). */ static inline void hlist_bl_del_rcu(struct hlist_bl_node *n) { __hlist_bl_del(n); n->pprev = LIST_POISON2; } /** * hlist_bl_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist_bl, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_bl_add_head_rcu() * or hlist_bl_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_bl_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_bl_add_head_rcu(struct hlist_bl_node *n, struct hlist_bl_head *h) { struct hlist_bl_node *first; /* don't need hlist_bl_first_rcu because we're under lock */ first = hlist_bl_first(h); n->next = first; if (first) first->pprev = &n->next; n->pprev = &h->first; /* need _rcu because we can have concurrent lock free readers */ hlist_bl_set_first_rcu(h, n); } /** * hlist_bl_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_bl_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_bl_node within the struct. * */ #define hlist_bl_for_each_entry_rcu(tpos, pos, head, member) \ for (pos = hlist_bl_first_rcu(head); \ pos && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(pos->next)) #endif
571 12 12 6 6 46 46 19 27 411 410 28 15 32 9 26 15 33 33 32 34 15 29 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 /* * cgroup_freezer.c - control group freezer subsystem * * Copyright IBM Corporation, 2007 * * Author : Cedric Le Goater <clg@fr.ibm.com> * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2.1 of the GNU Lesser General Public License * as published by the Free Software Foundation. * * This program is distributed in the hope that it would be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. */ #include <linux/export.h> #include <linux/slab.h> #include <linux/cgroup.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <linux/freezer.h> #include <linux/seq_file.h> #include <linux/mutex.h> /* * A cgroup is freezing if any FREEZING flags are set. FREEZING_SELF is * set if "FROZEN" is written to freezer.state cgroupfs file, and cleared * for "THAWED". FREEZING_PARENT is set if the parent freezer is FREEZING * for whatever reason. IOW, a cgroup has FREEZING_PARENT set if one of * its ancestors has FREEZING_SELF set. */ enum freezer_state_flags { CGROUP_FREEZER_ONLINE = (1 << 0), /* freezer is fully online */ CGROUP_FREEZING_SELF = (1 << 1), /* this freezer is freezing */ CGROUP_FREEZING_PARENT = (1 << 2), /* the parent freezer is freezing */ CGROUP_FROZEN = (1 << 3), /* this and its descendants frozen */ /* mask for all FREEZING flags */ CGROUP_FREEZING = CGROUP_FREEZING_SELF | CGROUP_FREEZING_PARENT, }; struct freezer { struct cgroup_subsys_state css; unsigned int state; }; static DEFINE_MUTEX(freezer_mutex); static inline struct freezer *css_freezer(struct cgroup_subsys_state *css) { return css ? container_of(css, struct freezer, css) : NULL; } static inline struct freezer *task_freezer(struct task_struct *task) { return css_freezer(task_css(task, freezer_cgrp_id)); } static struct freezer *parent_freezer(struct freezer *freezer) { return css_freezer(freezer->css.parent); } bool cgroup_freezing(struct task_struct *task) { bool ret; rcu_read_lock(); ret = task_freezer(task)->state & CGROUP_FREEZING; rcu_read_unlock(); return ret; } static const char *freezer_state_strs(unsigned int state) { if (state & CGROUP_FROZEN) return "FROZEN"; if (state & CGROUP_FREEZING) return "FREEZING"; return "THAWED"; }; static struct cgroup_subsys_state * freezer_css_alloc(struct cgroup_subsys_state *parent_css) { struct freezer *freezer; freezer = kzalloc(sizeof(struct freezer), GFP_KERNEL); if (!freezer) return ERR_PTR(-ENOMEM); return &freezer->css; } /** * freezer_css_online - commit creation of a freezer css * @css: css being created * * We're committing to creation of @css. Mark it online and inherit * parent's freezing state while holding both parent's and our * freezer->lock. */ static int freezer_css_online(struct cgroup_subsys_state *css) { struct freezer *freezer = css_freezer(css); struct freezer *parent = parent_freezer(freezer); mutex_lock(&freezer_mutex); freezer->state |= CGROUP_FREEZER_ONLINE; if (parent && (parent->state & CGROUP_FREEZING)) { freezer->state |= CGROUP_FREEZING_PARENT | CGROUP_FROZEN; atomic_inc(&system_freezing_cnt); } mutex_unlock(&freezer_mutex); return 0; } /** * freezer_css_offline - initiate destruction of a freezer css * @css: css being destroyed * * @css is going away. Mark it dead and decrement system_freezing_count if * it was holding one. */ static void freezer_css_offline(struct cgroup_subsys_state *css) { struct freezer *freezer = css_freezer(css); mutex_lock(&freezer_mutex); if (freezer->state & CGROUP_FREEZING) atomic_dec(&system_freezing_cnt); freezer->state = 0; mutex_unlock(&freezer_mutex); } static void freezer_css_free(struct cgroup_subsys_state *css) { kfree(css_freezer(css)); } /* * Tasks can be migrated into a different freezer anytime regardless of its * current state. freezer_attach() is responsible for making new tasks * conform to the current state. * * Freezer state changes and task migration are synchronized via * @freezer->lock. freezer_attach() makes the new tasks conform to the * current state and all following state changes can see the new tasks. */ static void freezer_attach(struct cgroup_taskset *tset) { struct task_struct *task; struct cgroup_subsys_state *new_css; mutex_lock(&freezer_mutex); /* * Make the new tasks conform to the current state of @new_css. * For simplicity, when migrating any task to a FROZEN cgroup, we * revert it to FREEZING and let update_if_frozen() determine the * correct state later. * * Tasks in @tset are on @new_css but may not conform to its * current state before executing the following - !frozen tasks may * be visible in a FROZEN cgroup and frozen tasks in a THAWED one. */ cgroup_taskset_for_each(task, new_css, tset) { struct freezer *freezer = css_freezer(new_css); if (!(freezer->state & CGROUP_FREEZING)) { __thaw_task(task); } else { freeze_task(task); /* clear FROZEN and propagate upwards */ while (freezer && (freezer->state & CGROUP_FROZEN)) { freezer->state &= ~CGROUP_FROZEN; freezer = parent_freezer(freezer); } } } mutex_unlock(&freezer_mutex); } /** * freezer_fork - cgroup post fork callback * @task: a task which has just been forked * * @task has just been created and should conform to the current state of * the cgroup_freezer it belongs to. This function may race against * freezer_attach(). Losing to freezer_attach() means that we don't have * to do anything as freezer_attach() will put @task into the appropriate * state. */ static void freezer_fork(struct task_struct *task) { struct freezer *freezer; /* * The root cgroup is non-freezable, so we can skip locking the * freezer. This is safe regardless of race with task migration. * If we didn't race or won, skipping is obviously the right thing * to do. If we lost and root is the new cgroup, noop is still the * right thing to do. */ if (task_css_is_root(task, freezer_cgrp_id)) return; mutex_lock(&freezer_mutex); rcu_read_lock(); freezer = task_freezer(task); if (freezer->state & CGROUP_FREEZING) freeze_task(task); rcu_read_unlock(); mutex_unlock(&freezer_mutex); } /** * update_if_frozen - update whether a cgroup finished freezing * @css: css of interest * * Once FREEZING is initiated, transition to FROZEN is lazily updated by * calling this function. If the current state is FREEZING but not FROZEN, * this function checks whether all tasks of this cgroup and the descendant * cgroups finished freezing and, if so, sets FROZEN. * * The caller is responsible for grabbing RCU read lock and calling * update_if_frozen() on all descendants prior to invoking this function. * * Task states and freezer state might disagree while tasks are being * migrated into or out of @css, so we can't verify task states against * @freezer state here. See freezer_attach() for details. */ static void update_if_frozen(struct cgroup_subsys_state *css) { struct freezer *freezer = css_freezer(css); struct cgroup_subsys_state *pos; struct css_task_iter it; struct task_struct *task; lockdep_assert_held(&freezer_mutex); if (!(freezer->state & CGROUP_FREEZING) || (freezer->state & CGROUP_FROZEN)) return; /* are all (live) children frozen? */ rcu_read_lock(); css_for_each_child(pos, css) { struct freezer *child = css_freezer(pos); if ((child->state & CGROUP_FREEZER_ONLINE) && !(child->state & CGROUP_FROZEN)) { rcu_read_unlock(); return; } } rcu_read_unlock(); /* are all tasks frozen? */ css_task_iter_start(css, 0, &it); while ((task = css_task_iter_next(&it))) { if (freezing(task)) { /* * freezer_should_skip() indicates that the task * should be skipped when determining freezing * completion. Consider it frozen in addition to * the usual frozen condition. */ if (!frozen(task) && !freezer_should_skip(task)) goto out_iter_end; } } freezer->state |= CGROUP_FROZEN; out_iter_end: css_task_iter_end(&it); } static int freezer_read(struct seq_file *m, void *v) { struct cgroup_subsys_state *css = seq_css(m), *pos; mutex_lock(&freezer_mutex); rcu_read_lock(); /* update states bottom-up */ css_for_each_descendant_post(pos, css) { if (!css_tryget_online(pos)) continue; rcu_read_unlock(); update_if_frozen(pos); rcu_read_lock(); css_put(pos); } rcu_read_unlock(); mutex_unlock(&freezer_mutex); seq_puts(m, freezer_state_strs(css_freezer(css)->state)); seq_putc(m, '\n'); return 0; } static void freeze_cgroup(struct freezer *freezer) { struct css_task_iter it; struct task_struct *task; css_task_iter_start(&freezer->css, 0, &it); while ((task = css_task_iter_next(&it))) freeze_task(task); css_task_iter_end(&it); } static void unfreeze_cgroup(struct freezer *freezer) { struct css_task_iter it; struct task_struct *task; css_task_iter_start(&freezer->css, 0, &it); while ((task = css_task_iter_next(&it))) __thaw_task(task); css_task_iter_end(&it); } /** * freezer_apply_state - apply state change to a single cgroup_freezer * @freezer: freezer to apply state change to * @freeze: whether to freeze or unfreeze * @state: CGROUP_FREEZING_* flag to set or clear * * Set or clear @state on @cgroup according to @freeze, and perform * freezing or thawing as necessary. */ static void freezer_apply_state(struct freezer *freezer, bool freeze, unsigned int state) { /* also synchronizes against task migration, see freezer_attach() */ lockdep_assert_held(&freezer_mutex); if (!(freezer->state & CGROUP_FREEZER_ONLINE)) return; if (freeze) { if (!(freezer->state & CGROUP_FREEZING)) atomic_inc(&system_freezing_cnt); freezer->state |= state; freeze_cgroup(freezer); } else { bool was_freezing = freezer->state & CGROUP_FREEZING; freezer->state &= ~state; if (!(freezer->state & CGROUP_FREEZING)) { if (was_freezing) atomic_dec(&system_freezing_cnt); freezer->state &= ~CGROUP_FROZEN; unfreeze_cgroup(freezer); } } } /** * freezer_change_state - change the freezing state of a cgroup_freezer * @freezer: freezer of interest * @freeze: whether to freeze or thaw * * Freeze or thaw @freezer according to @freeze. The operations are * recursive - all descendants of @freezer will be affected. */ static void freezer_change_state(struct freezer *freezer, bool freeze) { struct cgroup_subsys_state *pos; /* * Update all its descendants in pre-order traversal. Each * descendant will try to inherit its parent's FREEZING state as * CGROUP_FREEZING_PARENT. */ mutex_lock(&freezer_mutex); rcu_read_lock(); css_for_each_descendant_pre(pos, &freezer->css) { struct freezer *pos_f = css_freezer(pos); struct freezer *parent = parent_freezer(pos_f); if (!css_tryget_online(pos)) continue; rcu_read_unlock(); if (pos_f == freezer) freezer_apply_state(pos_f, freeze, CGROUP_FREEZING_SELF); else freezer_apply_state(pos_f, parent->state & CGROUP_FREEZING, CGROUP_FREEZING_PARENT); rcu_read_lock(); css_put(pos); } rcu_read_unlock(); mutex_unlock(&freezer_mutex); } static ssize_t freezer_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { bool freeze; buf = strstrip(buf); if (strcmp(buf, freezer_state_strs(0)) == 0) freeze = false; else if (strcmp(buf, freezer_state_strs(CGROUP_FROZEN)) == 0) freeze = true; else return -EINVAL; freezer_change_state(css_freezer(of_css(of)), freeze); return nbytes; } static u64 freezer_self_freezing_read(struct cgroup_subsys_state *css, struct cftype *cft) { struct freezer *freezer = css_freezer(css); return (bool)(freezer->state & CGROUP_FREEZING_SELF); } static u64 freezer_parent_freezing_read(struct cgroup_subsys_state *css, struct cftype *cft) { struct freezer *freezer = css_freezer(css); return (bool)(freezer->state & CGROUP_FREEZING_PARENT); } static struct cftype files[] = { { .name = "state", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = freezer_read, .write = freezer_write, }, { .name = "self_freezing", .flags = CFTYPE_NOT_ON_ROOT, .read_u64 = freezer_self_freezing_read, }, { .name = "parent_freezing", .flags = CFTYPE_NOT_ON_ROOT, .read_u64 = freezer_parent_freezing_read, }, { } /* terminate */ }; struct cgroup_subsys freezer_cgrp_subsys = { .css_alloc = freezer_css_alloc, .css_online = freezer_css_online, .css_offline = freezer_css_offline, .css_free = freezer_css_free, .attach = freezer_attach, .fork = freezer_fork, .legacy_cftypes = files, };
1011 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 /* * Resizable virtual memory filesystem for Linux. * * Copyright (C) 2000 Linus Torvalds. * 2000 Transmeta Corp. * 2000-2001 Christoph Rohland * 2000-2001 SAP AG * 2002 Red Hat Inc. * Copyright (C) 2002-2011 Hugh Dickins. * Copyright (C) 2011 Google Inc. * Copyright (C) 2002-2005 VERITAS Software Corporation. * Copyright (C) 2004 Andi Kleen, SuSE Labs * * Extended attribute support for tmpfs: * Copyright (c) 2004, Luke Kenneth Casson Leighton <lkcl@lkcl.net> * Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> * * tiny-shmem: * Copyright (c) 2004, 2008 Matt Mackall <mpm@selenic.com> * * This file is released under the GPL. */ #include <linux/fs.h> #include <linux/init.h> #include <linux/vfs.h> #include <linux/mount.h> #include <linux/ramfs.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/random.h> #include <linux/sched/signal.h> #include <linux/export.h> #include <linux/swap.h> #include <linux/uio.h> #include <linux/khugepaged.h> #include <linux/hugetlb.h> #include <linux/frontswap.h> #include <linux/fs_parser.h> #include <asm/tlbflush.h> /* for arch/microblaze update_mmu_cache() */ static struct vfsmount *shm_mnt; #ifdef CONFIG_SHMEM /* * This virtual memory filesystem is heavily based on the ramfs. It * extends ramfs by the ability to use swap and honor resource limits * which makes it a completely usable filesystem. */ #include <linux/xattr.h> #include <linux/exportfs.h> #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include <linux/mman.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/shmem_fs.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/pagevec.h> #include <linux/percpu_counter.h> #include <linux/falloc.h> #include <linux/splice.h> #include <linux/security.h> #include <linux/swapops.h> #include <linux/mempolicy.h> #include <linux/namei.h> #include <linux/ctype.h> #include <linux/migrate.h> #include <linux/highmem.h> #include <linux/seq_file.h> #include <linux/magic.h> #include <linux/syscalls.h> #include <linux/fcntl.h> #include <uapi/linux/memfd.h> #include <linux/userfaultfd_k.h> #include <linux/rmap.h> #include <linux/uuid.h> #include <linux/uaccess.h> #include <asm/pgtable.h> #include "internal.h" #define BLOCKS_PER_PAGE (PAGE_SIZE/512) #define VM_ACCT(size) (PAGE_ALIGN(size) >> PAGE_SHIFT) /* Pretend that each entry is of this size in directory's i_size */ #define BOGO_DIRENT_SIZE 20 /* Symlink up to this size is kmalloc'ed instead of using a swappable page */ #define SHORT_SYMLINK_LEN 128 /* * shmem_fallocate communicates with shmem_fault or shmem_writepage via * inode->i_private (with i_mutex making sure that it has only one user at * a time): we would prefer not to enlarge the shmem inode just for that. */ struct shmem_falloc { wait_queue_head_t *waitq; /* faults into hole wait for punch to end */ pgoff_t start; /* start of range currently being fallocated */ pgoff_t next; /* the next page offset to be fallocated */ pgoff_t nr_falloced; /* how many new pages have been fallocated */ pgoff_t nr_unswapped; /* how often writepage refused to swap out */ }; struct shmem_options { unsigned long long blocks; unsigned long long inodes; struct mempolicy *mpol; kuid_t uid; kgid_t gid; umode_t mode; int huge; int seen; #define SHMEM_SEEN_BLOCKS 1 #define SHMEM_SEEN_INODES 2 #define SHMEM_SEEN_HUGE 4 }; #ifdef CONFIG_TMPFS static unsigned long shmem_default_max_blocks(void) { return totalram_pages() / 2; } static unsigned long shmem_default_max_inodes(void) { unsigned long nr_pages = totalram_pages(); return min(nr_pages - totalhigh_pages(), nr_pages / 2); } #endif static bool shmem_should_replace_page(struct page *page, gfp_t gfp); static int shmem_replace_page(struct page **pagep, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index); static int shmem_swapin_page(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, vm_fault_t *fault_type); static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, struct vm_fault *vmf, vm_fault_t *fault_type); int shmem_getpage(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp) { return shmem_getpage_gfp(inode, index, pagep, sgp, mapping_gfp_mask(inode->i_mapping), NULL, NULL, NULL); } static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) { return sb->s_fs_info; } /* * shmem_file_setup pre-accounts the whole fixed size of a VM object, * for shared memory and for shared anonymous (/dev/zero) mappings * (unless MAP_NORESERVE and sysctl_overcommit_memory <= 1), * consistent with the pre-accounting of private mappings ... */ static inline int shmem_acct_size(unsigned long flags, loff_t size) { return (flags & VM_NORESERVE) ? 0 : security_vm_enough_memory_mm(current->mm, VM_ACCT(size)); } static inline void shmem_unacct_size(unsigned long flags, loff_t size) { if (!(flags & VM_NORESERVE)) vm_unacct_memory(VM_ACCT(size)); } static inline int shmem_reacct_size(unsigned long flags, loff_t oldsize, loff_t newsize) { if (!(flags & VM_NORESERVE)) { if (VM_ACCT(newsize) > VM_ACCT(oldsize)) return security_vm_enough_memory_mm(current->mm, VM_ACCT(newsize) - VM_ACCT(oldsize)); else if (VM_ACCT(newsize) < VM_ACCT(oldsize)) vm_unacct_memory(VM_ACCT(oldsize) - VM_ACCT(newsize)); } return 0; } /* * ... whereas tmpfs objects are accounted incrementally as * pages are allocated, in order to allow large sparse files. * shmem_getpage reports shmem_acct_block failure as -ENOSPC not -ENOMEM, * so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM. */ static inline int shmem_acct_block(unsigned long flags, long pages) { if (!(flags & VM_NORESERVE)) return 0; return security_vm_enough_memory_mm(current->mm, pages * VM_ACCT(PAGE_SIZE)); } static inline void shmem_unacct_blocks(unsigned long flags, long pages) { if (flags & VM_NORESERVE) vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE)); } static inline bool shmem_inode_acct_block(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); if (shmem_acct_block(info->flags, pages)) return false; if (sbinfo->max_blocks) { if (percpu_counter_compare(&sbinfo->used_blocks, sbinfo->max_blocks - pages) > 0) goto unacct; percpu_counter_add(&sbinfo->used_blocks, pages); } return true; unacct: shmem_unacct_blocks(info->flags, pages); return false; } static inline void shmem_inode_unacct_blocks(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); if (sbinfo->max_blocks) percpu_counter_sub(&sbinfo->used_blocks, pages); shmem_unacct_blocks(info->flags, pages); } static const struct super_operations shmem_ops; static const struct address_space_operations shmem_aops; static const struct file_operations shmem_file_operations; static const struct inode_operations shmem_inode_operations; static const struct inode_operations shmem_dir_inode_operations; static const struct inode_operations shmem_special_inode_operations; static const struct vm_operations_struct shmem_vm_ops; static struct file_system_type shmem_fs_type; bool vma_is_shmem(struct vm_area_struct *vma) { return vma->vm_ops == &shmem_vm_ops; } static LIST_HEAD(shmem_swaplist); static DEFINE_MUTEX(shmem_swaplist_mutex); static int shmem_reserve_inode(struct super_block *sb) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); if (sbinfo->max_inodes) { spin_lock(&sbinfo->stat_lock); if (!sbinfo->free_inodes) { spin_unlock(&sbinfo->stat_lock); return -ENOSPC; } sbinfo->free_inodes--; spin_unlock(&sbinfo->stat_lock); } return 0; } static void shmem_free_inode(struct super_block *sb) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); if (sbinfo->max_inodes) { spin_lock(&sbinfo->stat_lock); sbinfo->free_inodes++; spin_unlock(&sbinfo->stat_lock); } } /** * shmem_recalc_inode - recalculate the block usage of an inode * @inode: inode to recalc * * We have to calculate the free blocks since the mm can drop * undirtied hole pages behind our back. * * But normally info->alloced == inode->i_mapping->nrpages + info->swapped * So mm freed is info->alloced - (inode->i_mapping->nrpages + info->swapped) * * It has to be called with the spinlock held. */ static void shmem_recalc_inode(struct inode *inode) { struct shmem_inode_info *info = SHMEM_I(inode); long freed; freed = info->alloced - info->swapped - inode->i_mapping->nrpages; if (freed > 0) { info->alloced -= freed; inode->i_blocks -= freed * BLOCKS_PER_PAGE; shmem_inode_unacct_blocks(inode, freed); } } bool shmem_charge(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); unsigned long flags; if (!shmem_inode_acct_block(inode, pages)) return false; /* nrpages adjustment first, then shmem_recalc_inode() when balanced */ inode->i_mapping->nrpages += pages; spin_lock_irqsave(&info->lock, flags); info->alloced += pages; inode->i_blocks += pages * BLOCKS_PER_PAGE; shmem_recalc_inode(inode); spin_unlock_irqrestore(&info->lock, flags); return true; } void shmem_uncharge(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); unsigned long flags; /* nrpages adjustment done by __delete_from_page_cache() or caller */ spin_lock_irqsave(&info->lock, flags); info->alloced -= pages; inode->i_blocks -= pages * BLOCKS_PER_PAGE; shmem_recalc_inode(inode); spin_unlock_irqrestore(&info->lock, flags); shmem_inode_unacct_blocks(inode, pages); } /* * Replace item expected in xarray by a new item, while holding xa_lock. */ static int shmem_replace_entry(struct address_space *mapping, pgoff_t index, void *expected, void *replacement) { XA_STATE(xas, &mapping->i_pages, index); void *item; VM_BUG_ON(!expected); VM_BUG_ON(!replacement); item = xas_load(&xas); if (item != expected) return -ENOENT; xas_store(&xas, replacement); return 0; } /* * Sometimes, before we decide whether to proceed or to fail, we must check * that an entry was not already brought back from swap by a racing thread. * * Checking page is not enough: by the time a SwapCache page is locked, it * might be reused, and again be SwapCache, using the same swap as before. */ static bool shmem_confirm_swap(struct address_space *mapping, pgoff_t index, swp_entry_t swap) { return xa_load(&mapping->i_pages, index) == swp_to_radix_entry(swap); } /* * Definitions for "huge tmpfs": tmpfs mounted with the huge= option * * SHMEM_HUGE_NEVER: * disables huge pages for the mount; * SHMEM_HUGE_ALWAYS: * enables huge pages for the mount; * SHMEM_HUGE_WITHIN_SIZE: * only allocate huge pages if the page will be fully within i_size, * also respect fadvise()/madvise() hints; * SHMEM_HUGE_ADVISE: * only allocate huge pages if requested with fadvise()/madvise(); */ #define SHMEM_HUGE_NEVER 0 #define SHMEM_HUGE_ALWAYS 1 #define SHMEM_HUGE_WITHIN_SIZE 2 #define SHMEM_HUGE_ADVISE 3 /* * Special values. * Only can be set via /sys/kernel/mm/transparent_hugepage/shmem_enabled: * * SHMEM_HUGE_DENY: * disables huge on shm_mnt and all mounts, for emergency use; * SHMEM_HUGE_FORCE: * enables huge on shm_mnt and all mounts, w/o needing option, for testing; * */ #define SHMEM_HUGE_DENY (-1) #define SHMEM_HUGE_FORCE (-2) #ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE /* ifdef here to avoid bloating shmem.o when not necessary */ static int shmem_huge __read_mostly; #if defined(CONFIG_SYSFS) static int shmem_parse_huge(const char *str) { if (!strcmp(str, "never")) return SHMEM_HUGE_NEVER; if (!strcmp(str, "always")) return SHMEM_HUGE_ALWAYS; if (!strcmp(str, "within_size")) return SHMEM_HUGE_WITHIN_SIZE; if (!strcmp(str, "advise")) return SHMEM_HUGE_ADVISE; if (!strcmp(str, "deny")) return SHMEM_HUGE_DENY; if (!strcmp(str, "force")) return SHMEM_HUGE_FORCE; return -EINVAL; } #endif #if defined(CONFIG_SYSFS) || defined(CONFIG_TMPFS) static const char *shmem_format_huge(int huge) { switch (huge) { case SHMEM_HUGE_NEVER: return "never"; case SHMEM_HUGE_ALWAYS: return "always"; case SHMEM_HUGE_WITHIN_SIZE: return "within_size"; case SHMEM_HUGE_ADVISE: return "advise"; case SHMEM_HUGE_DENY: return "deny"; case SHMEM_HUGE_FORCE: return "force"; default: VM_BUG_ON(1); return "bad_val"; } } #endif static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_split) { LIST_HEAD(list), *pos, *next; LIST_HEAD(to_remove); struct inode *inode; struct shmem_inode_info *info; struct page *page; unsigned long batch = sc ? sc->nr_to_scan : 128; int split = 0; if (list_empty(&sbinfo->shrinklist)) return SHRINK_STOP; spin_lock(&sbinfo->shrinklist_lock); list_for_each_safe(pos, next, &sbinfo->shrinklist) { info = list_entry(pos, struct shmem_inode_info, shrinklist); /* pin the inode */ inode = igrab(&info->vfs_inode); /* inode is about to be evicted */ if (!inode) { list_del_init(&info->shrinklist); goto next; } /* Check if there's anything to gain */ if (round_up(inode->i_size, PAGE_SIZE) == round_up(inode->i_size, HPAGE_PMD_SIZE)) { list_move(&info->shrinklist, &to_remove); goto next; } list_move(&info->shrinklist, &list); next: sbinfo->shrinklist_len--; if (!--batch) break; } spin_unlock(&sbinfo->shrinklist_lock); list_for_each_safe(pos, next, &to_remove) { info = list_entry(pos, struct shmem_inode_info, shrinklist); inode = &info->vfs_inode; list_del_init(&info->shrinklist); iput(inode); } list_for_each_safe(pos, next, &list) { int ret; info = list_entry(pos, struct shmem_inode_info, shrinklist); inode = &info->vfs_inode; if (nr_to_split && split >= nr_to_split) goto move_back; page = find_get_page(inode->i_mapping, (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT); if (!page) goto drop; /* No huge page at the end of the file: nothing to split */ if (!PageTransHuge(page)) { put_page(page); goto drop; } /* * Move the inode on the list back to shrinklist if we failed * to lock the page at this time. * * Waiting for the lock may lead to deadlock in the * reclaim path. */ if (!trylock_page(page)) { put_page(page); goto move_back; } ret = split_huge_page(page); unlock_page(page); put_page(page); /* If split failed move the inode on the list back to shrinklist */ if (ret) goto move_back; split++; drop: list_del_init(&info->shrinklist); goto put; move_back: /* * Make sure the inode is either on the global list or deleted * from any local list before iput() since it could be deleted * in another thread once we put the inode (then the local list * is corrupted). */ spin_lock(&sbinfo->shrinklist_lock); list_move(&info->shrinklist, &sbinfo->shrinklist); sbinfo->shrinklist_len++; spin_unlock(&sbinfo->shrinklist_lock); put: iput(inode); } return split; } static long shmem_unused_huge_scan(struct super_block *sb, struct shrink_control *sc) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); if (!READ_ONCE(sbinfo->shrinklist_len)) return SHRINK_STOP; return shmem_unused_huge_shrink(sbinfo, sc, 0); } static long shmem_unused_huge_count(struct super_block *sb, struct shrink_control *sc) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); return READ_ONCE(sbinfo->shrinklist_len); } #else /* !CONFIG_TRANSPARENT_HUGE_PAGECACHE */ #define shmem_huge SHMEM_HUGE_DENY static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_split) { return 0; } #endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE */ static inline bool is_huge_enabled(struct shmem_sb_info *sbinfo) { if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE) && (shmem_huge == SHMEM_HUGE_FORCE || sbinfo->huge) && shmem_huge != SHMEM_HUGE_DENY) return true; return false; } /* * Like add_to_page_cache_locked, but error if expected item has gone. */ static int shmem_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t index, void *expected, gfp_t gfp) { XA_STATE_ORDER(xas, &mapping->i_pages, index, compound_order(page)); unsigned long i = 0; unsigned long nr = compound_nr(page); VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(index != round_down(index, nr), page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageSwapBacked(page), page); VM_BUG_ON(expected && PageTransHuge(page)); page_ref_add(page, nr); page->mapping = mapping; page->index = index; do { void *entry; xas_lock_irq(&xas); entry = xas_find_conflict(&xas); if (entry != expected) xas_set_err(&xas, -EEXIST); xas_create_range(&xas); if (xas_error(&xas)) goto unlock; next: xas_store(&xas, page); if (++i < nr) { xas_next(&xas); goto next; } if (PageTransHuge(page)) { count_vm_event(THP_FILE_ALLOC); __inc_node_page_state(page, NR_SHMEM_THPS); } mapping->nrpages += nr; __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr); __mod_node_page_state(page_pgdat(page), NR_SHMEM, nr); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); if (xas_error(&xas)) { page->mapping = NULL; page_ref_sub(page, nr); return xas_error(&xas); } return 0; } /* * Like delete_from_page_cache, but substitutes swap for page. */ static void shmem_delete_from_page_cache(struct page *page, void *radswap) { struct address_space *mapping = page->mapping; int error; VM_BUG_ON_PAGE(PageCompound(page), page); xa_lock_irq(&mapping->i_pages); error = shmem_replace_entry(mapping, page->index, page, radswap); page->mapping = NULL; mapping->nrpages--; __dec_node_page_state(page, NR_FILE_PAGES); __dec_node_page_state(page, NR_SHMEM); xa_unlock_irq(&mapping->i_pages); put_page(page); BUG_ON(error); } /* * Remove swap entry from page cache, free the swap and its page cache. */ static int shmem_free_swap(struct address_space *mapping, pgoff_t index, void *radswap) { void *old; old = xa_cmpxchg_irq(&mapping->i_pages, index, radswap, NULL, 0); if (old != radswap) return -ENOENT; free_swap_and_cache(radix_to_swp_entry(radswap)); return 0; } /* * Determine (in bytes) how many of the shmem object's pages mapped by the * given offsets are swapped out. * * This is safe to call without i_mutex or the i_pages lock thanks to RCU, * as long as the inode doesn't go away and racy results are not a problem. */ unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; unsigned long swapped = 0; rcu_read_lock(); xas_for_each(&xas, page, end - 1) { if (xas_retry(&xas, page)) continue; if (xa_is_value(page)) swapped++; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); return swapped << PAGE_SHIFT; } /* * Determine (in bytes) how many of the shmem object's pages mapped by the * given vma is swapped out. * * This is safe to call without i_mutex or the i_pages lock thanks to RCU, * as long as the inode doesn't go away and racy results are not a problem. */ unsigned long shmem_swap_usage(struct vm_area_struct *vma) { struct inode *inode = file_inode(vma->vm_file); struct shmem_inode_info *info = SHMEM_I(inode); struct address_space *mapping = inode->i_mapping; unsigned long swapped; /* Be careful as we don't hold info->lock */ swapped = READ_ONCE(info->swapped); /* * The easier cases are when the shmem object has nothing in swap, or * the vma maps it whole. Then we can simply use the stats that we * already track. */ if (!swapped) return 0; if (!vma->vm_pgoff && vma->vm_end - vma->vm_start >= inode->i_size) return swapped << PAGE_SHIFT; /* Here comes the more involved part */ return shmem_partial_swap_usage(mapping, linear_page_index(vma, vma->vm_start), linear_page_index(vma, vma->vm_end)); } /* * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists. */ void shmem_unlock_mapping(struct address_space *mapping) { struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index = 0; pagevec_init(&pvec); /* * Minor point, but we might as well stop if someone else SHM_LOCKs it. */ while (!mapping_unevictable(mapping)) { /* * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it * has finished, if it hits a row of PAGEVEC_SIZE swap entries. */ pvec.nr = find_get_entries(mapping, index, PAGEVEC_SIZE, pvec.pages, indices); if (!pvec.nr) break; index = indices[pvec.nr - 1] + 1; pagevec_remove_exceptionals(&pvec); check_move_unevictable_pages(&pvec); pagevec_release(&pvec); cond_resched(); } } /* * Remove range of pages and swap entries from page cache, and free them. * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate. */ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, bool unfalloc) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); pgoff_t start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; pgoff_t end = (lend + 1) >> PAGE_SHIFT; unsigned int partial_start = lstart & (PAGE_SIZE - 1); unsigned int partial_end = (lend + 1) & (PAGE_SIZE - 1); struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; long nr_swaps_freed = 0; pgoff_t index; int i; if (lend == -1) end = -1; /* unsigned, so actually very big */ pagevec_init(&pvec); index = start; while (index < end) { pvec.nr = find_get_entries(mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), pvec.pages, indices); if (!pvec.nr) break; for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; index = indices[i]; if (index >= end) break; if (xa_is_value(page)) { if (unfalloc) continue; nr_swaps_freed += !shmem_free_swap(mapping, index, page); continue; } VM_BUG_ON_PAGE(page_to_pgoff(page) != index, page); if (!trylock_page(page)) continue; if (PageTransTail(page)) { /* Middle of THP: zero out the page */ clear_highpage(page); unlock_page(page); continue; } else if (PageTransHuge(page)) { if (index == round_down(end, HPAGE_PMD_NR)) { /* * Range ends in the middle of THP: * zero out the page */ clear_highpage(page); unlock_page(page); continue; } index += HPAGE_PMD_NR - 1; i += HPAGE_PMD_NR - 1; } if (!unfalloc || !PageUptodate(page)) { VM_BUG_ON_PAGE(PageTail(page), page); if (page_mapping(page) == mapping) { VM_BUG_ON_PAGE(PageWriteback(page), page); truncate_inode_page(mapping, page); } } unlock_page(page); } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); cond_resched(); index++; } if (partial_start) { struct page *page = NULL; shmem_getpage(inode, start - 1, &page, SGP_READ); if (page) { unsigned int top = PAGE_SIZE; if (start > end) { top = partial_end; partial_end = 0; } zero_user_segment(page, partial_start, top); set_page_dirty(page); unlock_page(page); put_page(page); } } if (partial_end) { struct page *page = NULL; shmem_getpage(inode, end, &page, SGP_READ); if (page) { zero_user_segment(page, 0, partial_end); set_page_dirty(page); unlock_page(page); put_page(page); } } if (start >= end) return; index = start; while (index < end) { cond_resched(); pvec.nr = find_get_entries(mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), pvec.pages, indices); if (!pvec.nr) { /* If all gone or hole-punch or unfalloc, we're done */ if (index == start || end != -1) break; /* But if truncating, restart to make sure all gone */ index = start; continue; } for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; index = indices[i]; if (index >= end) break; if (xa_is_value(page)) { if (unfalloc) continue; if (shmem_free_swap(mapping, index, page)) { /* Swap was replaced by page: retry */ index--; break; } nr_swaps_freed++; continue; } lock_page(page); if (PageTransTail(page)) { /* Middle of THP: zero out the page */ clear_highpage(page); unlock_page(page); /* * Partial thp truncate due 'start' in middle * of THP: don't need to look on these pages * again on !pvec.nr restart. */ if (index != round_down(end, HPAGE_PMD_NR)) start++; continue; } else if (PageTransHuge(page)) { if (index == round_down(end, HPAGE_PMD_NR)) { /* * Range ends in the middle of THP: * zero out the page */ clear_highpage(page); unlock_page(page); continue; } index += HPAGE_PMD_NR - 1; i += HPAGE_PMD_NR - 1; } if (!unfalloc || !PageUptodate(page)) { VM_BUG_ON_PAGE(PageTail(page), page); if (page_mapping(page) == mapping) { VM_BUG_ON_PAGE(PageWriteback(page), page); truncate_inode_page(mapping, page); } else { /* Page was replaced by swap: retry */ unlock_page(page); index--; break; } } unlock_page(page); } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); index++; } spin_lock_irq(&info->lock); info->swapped -= nr_swaps_freed; shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); } void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { shmem_undo_range(inode, lstart, lend, false); inode->i_ctime = inode->i_mtime = current_time(inode); } EXPORT_SYMBOL_GPL(shmem_truncate_range); static int shmem_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = path->dentry->d_inode; struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sb_info = SHMEM_SB(inode->i_sb); if (info->alloced - info->swapped != inode->i_mapping->nrpages) { spin_lock_irq(&info->lock); shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); } generic_fillattr(inode, stat); if (is_huge_enabled(sb_info)) stat->blksize = HPAGE_PMD_SIZE; return 0; } static int shmem_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); int error; error = setattr_prepare(dentry, attr); if (error) return error; if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) { loff_t oldsize = inode->i_size; loff_t newsize = attr->ia_size; /* protected by i_mutex */ if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) || (newsize > oldsize && (info->seals & F_SEAL_GROW))) return -EPERM; if (newsize != oldsize) { error = shmem_reacct_size(SHMEM_I(inode)->flags, oldsize, newsize); if (error) return error; i_size_write(inode, newsize); inode->i_ctime = inode->i_mtime = current_time(inode); } if (newsize <= oldsize) { loff_t holebegin = round_up(newsize, PAGE_SIZE); if (oldsize > holebegin) unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); if (info->alloced) shmem_truncate_range(inode, newsize, (loff_t)-1); /* unmap again to remove racily COWed private pages */ if (oldsize > holebegin) unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); /* * Part of the huge page can be beyond i_size: subject * to shrink under memory pressure. */ if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) { spin_lock(&sbinfo->shrinklist_lock); /* * _careful to defend against unlocked access to * ->shrink_list in shmem_unused_huge_shrink() */ if (list_empty_careful(&info->shrinklist)) { list_add_tail(&info->shrinklist, &sbinfo->shrinklist); sbinfo->shrinklist_len++; } spin_unlock(&sbinfo->shrinklist_lock); } } } setattr_copy(inode, attr); if (attr->ia_valid & ATTR_MODE) error = posix_acl_chmod(inode, inode->i_mode); return error; } static void shmem_evict_inode(struct inode *inode) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); if (inode->i_mapping->a_ops == &shmem_aops) { shmem_unacct_size(info->flags, inode->i_size); inode->i_size = 0; shmem_truncate_range(inode, 0, (loff_t)-1); if (!list_empty(&info->shrinklist)) { spin_lock(&sbinfo->shrinklist_lock); if (!list_empty(&info->shrinklist)) { list_del_init(&info->shrinklist); sbinfo->shrinklist_len--; } spin_unlock(&sbinfo->shrinklist_lock); } while (!list_empty(&info->swaplist)) { /* Wait while shmem_unuse() is scanning this inode... */ wait_var_event(&info->stop_eviction, !atomic_read(&info->stop_eviction)); mutex_lock(&shmem_swaplist_mutex); /* ...but beware of the race if we peeked too early */ if (!atomic_read(&info->stop_eviction)) list_del_init(&info->swaplist); mutex_unlock(&shmem_swaplist_mutex); } } simple_xattrs_free(&info->xattrs); WARN_ON(inode->i_blocks); shmem_free_inode(inode->i_sb); clear_inode(inode); } extern struct swap_info_struct *swap_info[]; static int shmem_find_swap_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices, unsigned int type, bool frontswap) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; swp_entry_t entry; unsigned int ret = 0; if (!nr_entries) return 0; rcu_read_lock(); xas_for_each(&xas, page, ULONG_MAX) { if (xas_retry(&xas, page)) continue; if (!xa_is_value(page)) continue; entry = radix_to_swp_entry(page); if (swp_type(entry) != type) continue; if (frontswap && !frontswap_test(swap_info[type], swp_offset(entry))) continue; indices[ret] = xas.xa_index; entries[ret] = page; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } if (++ret == nr_entries) break; } rcu_read_unlock(); return ret; } /* * Move the swapped pages for an inode to page cache. Returns the count * of pages swapped in, or the error in case of failure. */ static int shmem_unuse_swap_entries(struct inode *inode, struct pagevec pvec, pgoff_t *indices) { int i = 0; int ret = 0; int error = 0; struct address_space *mapping = inode->i_mapping; for (i = 0; i < pvec.nr; i++) { struct page *page = pvec.pages[i]; if (!xa_is_value(page)) continue; error = shmem_swapin_page(inode, indices[i], &page, SGP_CACHE, mapping_gfp_mask(mapping), NULL, NULL); if (error == 0) { unlock_page(page); put_page(page); ret++; } if (error == -ENOMEM) break; error = 0; } return error ? error : ret; } /* * If swap found in inode, free it and move page from swapcache to filecache. */ static int shmem_unuse_inode(struct inode *inode, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { struct address_space *mapping = inode->i_mapping; pgoff_t start = 0; struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; bool frontswap_partial = (frontswap && *fs_pages_to_unuse > 0); int ret = 0; pagevec_init(&pvec); do { unsigned int nr_entries = PAGEVEC_SIZE; if (frontswap_partial && *fs_pages_to_unuse < PAGEVEC_SIZE) nr_entries = *fs_pages_to_unuse; pvec.nr = shmem_find_swap_entries(mapping, start, nr_entries, pvec.pages, indices, type, frontswap); if (pvec.nr == 0) { ret = 0; break; } ret = shmem_unuse_swap_entries(inode, pvec, indices); if (ret < 0) break; if (frontswap_partial) { *fs_pages_to_unuse -= ret; if (*fs_pages_to_unuse == 0) { ret = FRONTSWAP_PAGES_UNUSED; break; } } start = indices[pvec.nr - 1]; } while (true); return ret; } /* * Read all the shared memory data that resides in the swap * device 'type' back into memory, so the swap device can be * unused. */ int shmem_unuse(unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { struct shmem_inode_info *info, *next; int error = 0; if (list_empty(&shmem_swaplist)) return 0; mutex_lock(&shmem_swaplist_mutex); list_for_each_entry_safe(info, next, &shmem_swaplist, swaplist) { if (!info->swapped) { list_del_init(&info->swaplist); continue; } /* * Drop the swaplist mutex while searching the inode for swap; * but before doing so, make sure shmem_evict_inode() will not * remove placeholder inode from swaplist, nor let it be freed * (igrab() would protect from unlink, but not from unmount). */ atomic_inc(&info->stop_eviction); mutex_unlock(&shmem_swaplist_mutex); error = shmem_unuse_inode(&info->vfs_inode, type, frontswap, fs_pages_to_unuse); cond_resched(); mutex_lock(&shmem_swaplist_mutex); next = list_next_entry(info, swaplist); if (!info->swapped) list_del_init(&info->swaplist); if (atomic_dec_and_test(&info->stop_eviction)) wake_up_var(&info->stop_eviction); if (error) break; } mutex_unlock(&shmem_swaplist_mutex); return error; } /* * Move the page from the page cache to the swap cache. */ static int shmem_writepage(struct page *page, struct writeback_control *wbc) { struct shmem_inode_info *info; struct address_space *mapping; struct inode *inode; swp_entry_t swap; pgoff_t index; VM_BUG_ON_PAGE(PageCompound(page), page); BUG_ON(!PageLocked(page)); mapping = page->mapping; index = page->index; inode = mapping->host; info = SHMEM_I(inode); if (info->flags & VM_LOCKED) goto redirty; if (!total_swap_pages) goto redirty; /* * Our capabilities prevent regular writeback or sync from ever calling * shmem_writepage; but a stacking filesystem might use ->writepage of * its underlying filesystem, in which case tmpfs should write out to * swap only in response to memory pressure, and not for the writeback * threads or sync. */ if (!wbc->for_reclaim) { WARN_ON_ONCE(1); /* Still happens? Tell us about it! */ goto redirty; } /* * This is somewhat ridiculous, but without plumbing a SWAP_MAP_FALLOC * value into swapfile.c, the only way we can correctly account for a * fallocated page arriving here is now to initialize it and write it. * * That's okay for a page already fallocated earlier, but if we have * not yet completed the fallocation, then (a) we want to keep track * of this page in case we have to undo it, and (b) it may not be a * good idea to continue anyway, once we're pushing into swap. So * reactivate the page, and let shmem_fallocate() quit when too many. */ if (!PageUptodate(page)) { if (inode->i_private) { struct shmem_falloc *shmem_falloc; spin_lock(&inode->i_lock); shmem_falloc = inode->i_private; if (shmem_falloc && !shmem_falloc->waitq && index >= shmem_falloc->start && index < shmem_falloc->next) shmem_falloc->nr_unswapped++; else shmem_falloc = NULL; spin_unlock(&inode->i_lock); if (shmem_falloc) goto redirty; } clear_highpage(page); flush_dcache_page(page); SetPageUptodate(page); } swap = get_swap_page(page); if (!swap.val) goto redirty; /* * Add inode to shmem_unuse()'s list of swapped-out inodes, * if it's not already there. Do it now before the page is * moved to swap cache, when its pagelock no longer protects * the inode from eviction. But don't unlock the mutex until * we've incremented swapped, because shmem_unuse_inode() will * prune a !swapped inode from the swaplist under this mutex. */ mutex_lock(&shmem_swaplist_mutex); if (list_empty(&info->swaplist)) list_add(&info->swaplist, &shmem_swaplist); if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) { spin_lock_irq(&info->lock); shmem_recalc_inode(inode); info->swapped++; spin_unlock_irq(&info->lock); swap_shmem_alloc(swap); shmem_delete_from_page_cache(page, swp_to_radix_entry(swap)); mutex_unlock(&shmem_swaplist_mutex); BUG_ON(page_mapped(page)); swap_writepage(page, wbc); return 0; } mutex_unlock(&shmem_swaplist_mutex); put_swap_page(page, swap); redirty: set_page_dirty(page); if (wbc->for_reclaim) return AOP_WRITEPAGE_ACTIVATE; /* Return with page locked */ unlock_page(page); return 0; } #if defined(CONFIG_NUMA) && defined(CONFIG_TMPFS) static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) { char buffer[64]; if (!mpol || mpol->mode == MPOL_DEFAULT) return; /* show nothing */ mpol_to_str(buffer, sizeof(buffer), mpol); seq_printf(seq, ",mpol=%s", buffer); } static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) { struct mempolicy *mpol = NULL; if (sbinfo->mpol) { spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */ mpol = sbinfo->mpol; mpol_get(mpol); spin_unlock(&sbinfo->stat_lock); } return mpol; } #else /* !CONFIG_NUMA || !CONFIG_TMPFS */ static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) { } static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) { return NULL; } #endif /* CONFIG_NUMA && CONFIG_TMPFS */ #ifndef CONFIG_NUMA #define vm_policy vm_private_data #endif static void shmem_pseudo_vma_init(struct vm_area_struct *vma, struct shmem_inode_info *info, pgoff_t index) { /* Create a pseudo vma that just contains the policy */ vma_init(vma, NULL); /* Bias interleave by inode number to distribute better across nodes */ vma->vm_pgoff = index + info->vfs_inode.i_ino; vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index); } static void shmem_pseudo_vma_destroy(struct vm_area_struct *vma) { /* Drop reference taken by mpol_shared_policy_lookup() */ mpol_cond_put(vma->vm_policy); } static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; struct page *page; struct vm_fault vmf; shmem_pseudo_vma_init(&pvma, info, index); vmf.vma = &pvma; vmf.address = 0; page = swap_cluster_readahead(swap, gfp, &vmf); shmem_pseudo_vma_destroy(&pvma); return page; } static struct page *shmem_alloc_hugepage(gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; struct address_space *mapping = info->vfs_inode.i_mapping; pgoff_t hindex; struct page *page; if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) return NULL; hindex = round_down(index, HPAGE_PMD_NR); if (xa_find(&mapping->i_pages, &hindex, hindex + HPAGE_PMD_NR - 1, XA_PRESENT)) return NULL; shmem_pseudo_vma_init(&pvma, info, hindex); page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true); shmem_pseudo_vma_destroy(&pvma); if (page) prep_transhuge_page(page); return page; } static struct page *shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; struct page *page; shmem_pseudo_vma_init(&pvma, info, index); page = alloc_page_vma(gfp, &pvma, 0); shmem_pseudo_vma_destroy(&pvma); return page; } static struct page *shmem_alloc_and_acct_page(gfp_t gfp, struct inode *inode, pgoff_t index, bool huge) { struct shmem_inode_info *info = SHMEM_I(inode); struct page *page; int nr; int err = -ENOSPC; if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) huge = false; nr = huge ? HPAGE_PMD_NR : 1; if (!shmem_inode_acct_block(inode, nr)) goto failed; if (huge) page = shmem_alloc_hugepage(gfp, info, index); else page = shmem_alloc_page(gfp, info, index); if (page) { __SetPageLocked(page); __SetPageSwapBacked(page); return page; } err = -ENOMEM; shmem_inode_unacct_blocks(inode, nr); failed: return ERR_PTR(err); } /* * When a page is moved from swapcache to shmem filecache (either by the * usual swapin of shmem_getpage_gfp(), or by the less common swapoff of * shmem_unuse_inode()), it may have been read in earlier from swap, in * ignorance of the mapping it belongs to. If that mapping has special * constraints (like the gma500 GEM driver, which requires RAM below 4GB), * we may need to copy to a suitable page before moving to filecache. * * In a future release, this may well be extended to respect cpuset and * NUMA mempolicy, and applied also to anonymous pages in do_swap_page(); * but for now it is a simple matter of zone. */ static bool shmem_should_replace_page(struct page *page, gfp_t gfp) { return page_zonenum(page) > gfp_zone(gfp); } static int shmem_replace_page(struct page **pagep, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct page *oldpage, *newpage; struct address_space *swap_mapping; swp_entry_t entry; pgoff_t swap_index; int error; oldpage = *pagep; entry.val = page_private(oldpage); swap_index = swp_offset(entry); swap_mapping = page_mapping(oldpage); /* * We have arrived here because our zones are constrained, so don't * limit chance of success by further cpuset and node constraints. */ gfp &= ~GFP_CONSTRAINT_MASK; newpage = shmem_alloc_page(gfp, info, index); if (!newpage) return -ENOMEM; get_page(newpage); copy_highpage(newpage, oldpage); flush_dcache_page(newpage); __SetPageLocked(newpage); __SetPageSwapBacked(newpage); SetPageUptodate(newpage); set_page_private(newpage, entry.val); SetPageSwapCache(newpage); /* * Our caller will very soon move newpage out of swapcache, but it's * a nice clean interface for us to replace oldpage by newpage there. */ xa_lock_irq(&swap_mapping->i_pages); error = shmem_replace_entry(swap_mapping, swap_index, oldpage, newpage); if (!error) { __inc_node_page_state(newpage, NR_FILE_PAGES); __dec_node_page_state(oldpage, NR_FILE_PAGES); } xa_unlock_irq(&swap_mapping->i_pages); if (unlikely(error)) { /* * Is this possible? I think not, now that our callers check * both PageSwapCache and page_private after getting page lock; * but be defensive. Reverse old to newpage for clear and free. */ oldpage = newpage; } else { mem_cgroup_migrate(oldpage, newpage); lru_cache_add_anon(newpage); *pagep = newpage; } ClearPageSwapCache(oldpage); set_page_private(oldpage, 0); unlock_page(oldpage); put_page(oldpage); put_page(oldpage); return error; } /* * Swap in the page pointed to by *pagep. * Caller has to make sure that *pagep contains a valid swapped page. * Returns 0 and the page in pagep if success. On failure, returns the * the error code and NULL in *pagep. */ static int shmem_swapin_page(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, vm_fault_t *fault_type) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); struct mm_struct *charge_mm = vma ? vma->vm_mm : current->mm; struct mem_cgroup *memcg; struct page *page; swp_entry_t swap; int error; VM_BUG_ON(!*pagep || !xa_is_value(*pagep)); swap = radix_to_swp_entry(*pagep); *pagep = NULL; /* Look it up and read it in.. */ page = lookup_swap_cache(swap, NULL, 0); if (!page) { /* Or update major stats only when swapin succeeds?? */ if (fault_type) { *fault_type |= VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); count_memcg_event_mm(charge_mm, PGMAJFAULT); } /* Here we actually start the io */ page = shmem_swapin(swap, gfp, info, index); if (!page) { error = -ENOMEM; goto failed; } } /* We have to do this with page locked to prevent races */ lock_page(page); if (!PageSwapCache(page) || page_private(page) != swap.val || !shmem_confirm_swap(mapping, index, swap)) { error = -EEXIST; goto unlock; } if (!PageUptodate(page)) { error = -EIO; goto failed; } wait_on_page_writeback(page); if (shmem_should_replace_page(page, gfp)) { error = shmem_replace_page(&page, gfp, info, index); if (error) goto failed; } error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg, false); if (!error) { error = shmem_add_to_page_cache(page, mapping, index, swp_to_radix_entry(swap), gfp); /* * We already confirmed swap under page lock, and make * no memory allocation here, so usually no possibility * of error; but free_swap_and_cache() only trylocks a * page, so it is just possible that the entry has been * truncated or holepunched since swap was confirmed. * shmem_undo_range() will have done some of the * unaccounting, now delete_from_swap_cache() will do * the rest. */ if (error) { mem_cgroup_cancel_charge(page, memcg, false); delete_from_swap_cache(page); } } if (error) goto failed; mem_cgroup_commit_charge(page, memcg, true, false); spin_lock_irq(&info->lock); info->swapped--; shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); if (sgp == SGP_WRITE) mark_page_accessed(page); delete_from_swap_cache(page); set_page_dirty(page); swap_free(swap); *pagep = page; return 0; failed: if (!shmem_confirm_swap(mapping, index, swap)) error = -EEXIST; unlock: if (page) { unlock_page(page); put_page(page); } return error; } /* * shmem_getpage_gfp - find page in cache, or get from swap, or allocate * * If we allocate a new one we do not mark it dirty. That's up to the * vm. If we swap it in we mark it dirty since we also free the swap * entry since a page cannot live in both the swap and page cache. * * vma, vmf, and fault_type are only supplied by shmem_fault: * otherwise they are NULL. */ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, struct vm_fault *vmf, vm_fault_t *fault_type) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo; struct mm_struct *charge_mm; struct mem_cgroup *memcg; struct page *page; enum sgp_type sgp_huge = sgp; pgoff_t hindex = index; int error; int once = 0; int alloced = 0; if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT)) return -EFBIG; if (sgp == SGP_NOHUGE || sgp == SGP_HUGE) sgp = SGP_CACHE; repeat: if (sgp <= SGP_CACHE && ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { return -EINVAL; } sbinfo = SHMEM_SB(inode->i_sb); charge_mm = vma ? vma->vm_mm : current->mm; page = find_lock_entry(mapping, index); if (page && vma && userfaultfd_minor(vma)) { if (!xa_is_value(page)) { unlock_page(page); put_page(page); } *fault_type = handle_userfault(vmf, VM_UFFD_MINOR); return 0; } if (xa_is_value(page)) { error = shmem_swapin_page(inode, index, &page, sgp, gfp, vma, fault_type); if (error == -EEXIST) goto repeat; *pagep = page; return error; } if (page && sgp == SGP_WRITE) mark_page_accessed(page); /* fallocated page? */ if (page && !PageUptodate(page)) { if (sgp != SGP_READ) goto clear; unlock_page(page); put_page(page); page = NULL; } if (page || sgp == SGP_READ) { *pagep = page; return 0; } /* * Fast cache lookup did not find it: * bring it back from swap or allocate. */ if (vma && userfaultfd_missing(vma)) { *fault_type = handle_userfault(vmf, VM_UFFD_MISSING); return 0; } /* shmem_symlink() */ if (mapping->a_ops != &shmem_aops) goto alloc_nohuge; if (shmem_huge == SHMEM_HUGE_DENY || sgp_huge == SGP_NOHUGE) goto alloc_nohuge; if (shmem_huge == SHMEM_HUGE_FORCE) goto alloc_huge; switch (sbinfo->huge) { loff_t i_size; pgoff_t off; case SHMEM_HUGE_NEVER: goto alloc_nohuge; case SHMEM_HUGE_WITHIN_SIZE: off = round_up(index, HPAGE_PMD_NR); i_size = round_up(i_size_read(inode), PAGE_SIZE); if (i_size >= HPAGE_PMD_SIZE && i_size >> PAGE_SHIFT >= off) goto alloc_huge; /* fallthrough */ case SHMEM_HUGE_ADVISE: if (sgp_huge == SGP_HUGE) goto alloc_huge; /* TODO: implement fadvise() hints */ goto alloc_nohuge; } alloc_huge: page = shmem_alloc_and_acct_page(gfp, inode, index, true); if (IS_ERR(page)) { alloc_nohuge: page = shmem_alloc_and_acct_page(gfp, inode, index, false); } if (IS_ERR(page)) { int retry = 5; error = PTR_ERR(page); page = NULL; if (error != -ENOSPC) goto unlock; /* * Try to reclaim some space by splitting a huge page * beyond i_size on the filesystem. */ while (retry--) { int ret; ret = shmem_unused_huge_shrink(sbinfo, NULL, 1); if (ret == SHRINK_STOP) break;