| 4 26 91 91 2 90 18 16 15 4 4 4 2 2 2 2 106 110 109 110 109 112 66 2 65 2 66 16 2 14 16 13 77 89 2 90 27 27 10 17 9 2 16 16 27 9 9 4 4 1 4 2 4 1 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Pluggable TCP congestion control support and newReno * congestion control. * Based on ideas from I/O scheduler support and Web100. * * Copyright (C) 2005 Stephen Hemminger <shemminger@osdl.org> */ #define pr_fmt(fmt) "TCP: " fmt #include <linux/module.h> #include <linux/mm.h> #include <linux/types.h> #include <linux/list.h> #include <linux/gfp.h> #include <linux/jhash.h> #include <net/tcp.h> #include <trace/events/tcp.h> static DEFINE_SPINLOCK(tcp_cong_list_lock); static LIST_HEAD(tcp_cong_list); /* Simple linear search, don't expect many entries! */ struct tcp_congestion_ops *tcp_ca_find(const char *name) { struct tcp_congestion_ops *e; list_for_each_entry_rcu(e, &tcp_cong_list, list) { if (strcmp(e->name, name) == 0) return e; } return NULL; } void tcp_set_ca_state(struct sock *sk, const u8 ca_state) { struct inet_connection_sock *icsk = inet_csk(sk); trace_tcp_cong_state_set(sk, ca_state); if (icsk->icsk_ca_ops->set_state) icsk->icsk_ca_ops->set_state(sk, ca_state); icsk->icsk_ca_state = ca_state; } /* Must be called with rcu lock held */ static struct tcp_congestion_ops *tcp_ca_find_autoload(const char *name) { struct tcp_congestion_ops *ca = tcp_ca_find(name); #ifdef CONFIG_MODULES if (!ca && capable(CAP_NET_ADMIN)) { rcu_read_unlock(); request_module("tcp_%s", name); rcu_read_lock(); ca = tcp_ca_find(name); } #endif return ca; } /* Simple linear search, not much in here. */ struct tcp_congestion_ops *tcp_ca_find_key(u32 key) { struct tcp_congestion_ops *e; list_for_each_entry_rcu(e, &tcp_cong_list, list) { if (e->key == key) return e; } return NULL; } int tcp_validate_congestion_control(struct tcp_congestion_ops *ca) { /* all algorithms must implement these */ if (!ca->ssthresh || !ca->undo_cwnd || !(ca->cong_avoid || ca->cong_control)) { pr_err("%s does not implement required ops\n", ca->name); return -EINVAL; } return 0; } /* Attach new congestion control algorithm to the list * of available options. */ int tcp_register_congestion_control(struct tcp_congestion_ops *ca) { int ret; ret = tcp_validate_congestion_control(ca); if (ret) return ret; ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name)); spin_lock(&tcp_cong_list_lock); if (ca->key == TCP_CA_UNSPEC || tcp_ca_find_key(ca->key)) { pr_notice("%s already registered or non-unique key\n", ca->name); ret = -EEXIST; } else { list_add_tail_rcu(&ca->list, &tcp_cong_list); pr_debug("%s registered\n", ca->name); } spin_unlock(&tcp_cong_list_lock); return ret; } EXPORT_SYMBOL_GPL(tcp_register_congestion_control); /* * Remove congestion control algorithm, called from * the module's remove function. Module ref counts are used * to ensure that this can't be done till all sockets using * that method are closed. */ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca) { spin_lock(&tcp_cong_list_lock); list_del_rcu(&ca->list); spin_unlock(&tcp_cong_list_lock); /* Wait for outstanding readers to complete before the * module gets removed entirely. * * A try_module_get() should fail by now as our module is * in "going" state since no refs are held anymore and * module_exit() handler being called. */ synchronize_rcu(); } EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control); /* Replace a registered old ca with a new one. * * The new ca must have the same name as the old one, that has been * registered. */ int tcp_update_congestion_control(struct tcp_congestion_ops *ca, struct tcp_congestion_ops *old_ca) { struct tcp_congestion_ops *existing; int ret = 0; ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name)); spin_lock(&tcp_cong_list_lock); existing = tcp_ca_find_key(old_ca->key); if (ca->key == TCP_CA_UNSPEC || !existing || strcmp(existing->name, ca->name)) { pr_notice("%s not registered or non-unique key\n", ca->name); ret = -EINVAL; } else if (existing != old_ca) { pr_notice("invalid old congestion control algorithm to replace\n"); ret = -EINVAL; } else { /* Add the new one before removing the old one to keep * one implementation available all the time. */ list_add_tail_rcu(&ca->list, &tcp_cong_list); list_del_rcu(&existing->list); pr_debug("%s updated\n", ca->name); } spin_unlock(&tcp_cong_list_lock); /* Wait for outstanding readers to complete before the * module or struct_ops gets removed entirely. */ if (!ret) synchronize_rcu(); return ret; } u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca) { const struct tcp_congestion_ops *ca; u32 key = TCP_CA_UNSPEC; might_sleep(); rcu_read_lock(); ca = tcp_ca_find_autoload(name); if (ca) { key = ca->key; *ecn_ca = ca->flags & TCP_CONG_NEEDS_ECN; } rcu_read_unlock(); return key; } char *tcp_ca_get_name_by_key(u32 key, char *buffer) { const struct tcp_congestion_ops *ca; char *ret = NULL; rcu_read_lock(); ca = tcp_ca_find_key(key); if (ca) { strscpy(buffer, ca->name, TCP_CA_NAME_MAX); ret = buffer; } rcu_read_unlock(); return ret; } /* Assign choice of congestion control. */ void tcp_assign_congestion_control(struct sock *sk) { struct net *net = sock_net(sk); struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_congestion_ops *ca; rcu_read_lock(); ca = rcu_dereference(net->ipv4.tcp_congestion_control); if (unlikely(!bpf_try_module_get(ca, ca->owner))) ca = &tcp_reno; icsk->icsk_ca_ops = ca; rcu_read_unlock(); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); if (ca->flags & TCP_CONG_NEEDS_ECN) INET_ECN_xmit(sk); else INET_ECN_dontxmit(sk); } void tcp_init_congestion_control(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_sk(sk)->prior_ssthresh = 0; if (icsk->icsk_ca_ops->init) icsk->icsk_ca_ops->init(sk); if (tcp_ca_needs_ecn(sk)) INET_ECN_xmit(sk); else INET_ECN_dontxmit(sk); icsk->icsk_ca_initialized = 1; } static void tcp_reinit_congestion_control(struct sock *sk, const struct tcp_congestion_ops *ca) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_cleanup_congestion_control(sk); icsk->icsk_ca_ops = ca; icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); if (ca->flags & TCP_CONG_NEEDS_ECN) INET_ECN_xmit(sk); else INET_ECN_dontxmit(sk); if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) tcp_init_congestion_control(sk); } /* Manage refcounts on socket close. */ void tcp_cleanup_congestion_control(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_initialized && icsk->icsk_ca_ops->release) icsk->icsk_ca_ops->release(sk); icsk->icsk_ca_initialized = 0; bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); } /* Used by sysctl to change default congestion control */ int tcp_set_default_congestion_control(struct net *net, const char *name) { struct tcp_congestion_ops *ca; const struct tcp_congestion_ops *prev; int ret; rcu_read_lock(); ca = tcp_ca_find_autoload(name); if (!ca) { ret = -ENOENT; } else if (!bpf_try_module_get(ca, ca->owner)) { ret = -EBUSY; } else if (!net_eq(net, &init_net) && !(ca->flags & TCP_CONG_NON_RESTRICTED)) { /* Only init netns can set default to a restricted algorithm */ ret = -EPERM; } else { prev = xchg(&net->ipv4.tcp_congestion_control, ca); if (prev) bpf_module_put(prev, prev->owner); ca->flags |= TCP_CONG_NON_RESTRICTED; ret = 0; } rcu_read_unlock(); return ret; } /* Set default value from kernel configuration at bootup */ static int __init tcp_congestion_default(void) { return tcp_set_default_congestion_control(&init_net, CONFIG_DEFAULT_TCP_CONG); } late_initcall(tcp_congestion_default); /* Build string with list of available congestion control values */ void tcp_get_available_congestion_control(char *buf, size_t maxlen) { struct tcp_congestion_ops *ca; size_t offs = 0; rcu_read_lock(); list_for_each_entry_rcu(ca, &tcp_cong_list, list) { offs += snprintf(buf + offs, maxlen - offs, "%s%s", offs == 0 ? "" : " ", ca->name); if (WARN_ON_ONCE(offs >= maxlen)) break; } rcu_read_unlock(); } /* Get current default congestion control */ void tcp_get_default_congestion_control(struct net *net, char *name) { const struct tcp_congestion_ops *ca; rcu_read_lock(); ca = rcu_dereference(net->ipv4.tcp_congestion_control); strscpy(name, ca->name, TCP_CA_NAME_MAX); rcu_read_unlock(); } /* Built list of non-restricted congestion control values */ void tcp_get_allowed_congestion_control(char *buf, size_t maxlen) { struct tcp_congestion_ops *ca; size_t offs = 0; *buf = '\0'; rcu_read_lock(); list_for_each_entry_rcu(ca, &tcp_cong_list, list) { if (!(ca->flags & TCP_CONG_NON_RESTRICTED)) continue; offs += snprintf(buf + offs, maxlen - offs, "%s%s", offs == 0 ? "" : " ", ca->name); if (WARN_ON_ONCE(offs >= maxlen)) break; } rcu_read_unlock(); } /* Change list of non-restricted congestion control */ int tcp_set_allowed_congestion_control(char *val) { struct tcp_congestion_ops *ca; char *saved_clone, *clone, *name; int ret = 0; saved_clone = clone = kstrdup(val, GFP_USER); if (!clone) return -ENOMEM; spin_lock(&tcp_cong_list_lock); /* pass 1 check for bad entries */ while ((name = strsep(&clone, " ")) && *name) { ca = tcp_ca_find(name); if (!ca) { ret = -ENOENT; goto out; } } /* pass 2 clear old values */ list_for_each_entry_rcu(ca, &tcp_cong_list, list) ca->flags &= ~TCP_CONG_NON_RESTRICTED; /* pass 3 mark as allowed */ while ((name = strsep(&val, " ")) && *name) { ca = tcp_ca_find(name); WARN_ON(!ca); if (ca) ca->flags |= TCP_CONG_NON_RESTRICTED; } out: spin_unlock(&tcp_cong_list_lock); kfree(saved_clone); return ret; } /* Change congestion control for socket. If load is false, then it is the * responsibility of the caller to call tcp_init_congestion_control or * tcp_reinit_congestion_control (if the current congestion control was * already initialized. */ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool cap_net_admin) { struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_congestion_ops *ca; int err = 0; if (icsk->icsk_ca_dst_locked) return -EPERM; rcu_read_lock(); if (!load) ca = tcp_ca_find(name); else ca = tcp_ca_find_autoload(name); /* No change asking for existing value */ if (ca == icsk->icsk_ca_ops) { icsk->icsk_ca_setsockopt = 1; goto out; } if (!ca) err = -ENOENT; else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) err = -EPERM; else if (!bpf_try_module_get(ca, ca->owner)) err = -EBUSY; else tcp_reinit_congestion_control(sk, ca); out: rcu_read_unlock(); return err; } /* Slow start is used when congestion window is no greater than the slow start * threshold. We base on RFC2581 and also handle stretch ACKs properly. * We do not implement RFC3465 Appropriate Byte Counting (ABC) per se but * something better;) a packet is only considered (s)acked in its entirety to * defend the ACK attacks described in the RFC. Slow start processes a stretch * ACK of degree N as if N acks of degree 1 are received back to back except * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and * returns the leftover acks to adjust cwnd in congestion avoidance mode. */ __bpf_kfunc u32 tcp_slow_start(struct tcp_sock *tp, u32 acked) { u32 cwnd = min(tcp_snd_cwnd(tp) + acked, tp->snd_ssthresh); acked -= cwnd - tcp_snd_cwnd(tp); tcp_snd_cwnd_set(tp, min(cwnd, tp->snd_cwnd_clamp)); return acked; } EXPORT_SYMBOL_GPL(tcp_slow_start); /* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w), * for every packet that was ACKed. */ __bpf_kfunc void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked) { /* If credits accumulated at a higher w, apply them gently now. */ if (tp->snd_cwnd_cnt >= w) { tp->snd_cwnd_cnt = 0; tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) + 1); } tp->snd_cwnd_cnt += acked; if (tp->snd_cwnd_cnt >= w) { u32 delta = tp->snd_cwnd_cnt / w; tp->snd_cwnd_cnt -= delta * w; tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) + delta); } tcp_snd_cwnd_set(tp, min(tcp_snd_cwnd(tp), tp->snd_cwnd_clamp)); } EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai); /* * TCP Reno congestion control * This is special case used for fallback as well. */ /* This is Jacobson's slow start and congestion avoidance. * SIGCOMM '88, p. 328. */ __bpf_kfunc void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); if (!tcp_is_cwnd_limited(sk)) return; /* In "safe" area, increase. */ if (tcp_in_slow_start(tp)) { acked = tcp_slow_start(tp, acked); if (!acked) return; } /* In dangerous area, increase slowly. */ tcp_cong_avoid_ai(tp, tcp_snd_cwnd(tp), acked); } EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid); /* Slow start threshold is half the congestion window (min 2) */ __bpf_kfunc u32 tcp_reno_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); return max(tcp_snd_cwnd(tp) >> 1U, 2U); } EXPORT_SYMBOL_GPL(tcp_reno_ssthresh); __bpf_kfunc u32 tcp_reno_undo_cwnd(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); return max(tcp_snd_cwnd(tp), tp->prior_cwnd); } EXPORT_SYMBOL_GPL(tcp_reno_undo_cwnd); struct tcp_congestion_ops tcp_reno = { .flags = TCP_CONG_NON_RESTRICTED, .name = "reno", .owner = THIS_MODULE, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_reno_cong_avoid, .undo_cwnd = tcp_reno_undo_cwnd, }; |
| 6 6 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * * Copyright Tomi Manninen OH2BNS (oh2bns@sral.fi) */ #include <linux/types.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/timer.h> #include <net/ax25.h> #include <linux/skbuff.h> #include <net/netrom.h> #include <linux/init.h> static void nr_loopback_timer(struct timer_list *); static struct sk_buff_head loopback_queue; static DEFINE_TIMER(loopback_timer, nr_loopback_timer); void __init nr_loopback_init(void) { skb_queue_head_init(&loopback_queue); } static inline int nr_loopback_running(void) { return timer_pending(&loopback_timer); } int nr_loopback_queue(struct sk_buff *skb) { struct sk_buff *skbn; if ((skbn = alloc_skb(skb->len, GFP_ATOMIC)) != NULL) { skb_copy_from_linear_data(skb, skb_put(skbn, skb->len), skb->len); skb_reset_transport_header(skbn); skb_queue_tail(&loopback_queue, skbn); if (!nr_loopback_running()) mod_timer(&loopback_timer, jiffies + 10); } kfree_skb(skb); return 1; } static void nr_loopback_timer(struct timer_list *unused) { struct sk_buff *skb; ax25_address *nr_dest; struct net_device *dev; if ((skb = skb_dequeue(&loopback_queue)) != NULL) { nr_dest = (ax25_address *)(skb->data + 7); dev = nr_dev_get(nr_dest); if (dev == NULL || nr_rx_frame(skb, dev) == 0) kfree_skb(skb); dev_put(dev); if (!skb_queue_empty(&loopback_queue) && !nr_loopback_running()) mod_timer(&loopback_timer, jiffies + 10); } } void nr_loopback_clear(void) { del_timer_sync(&loopback_timer); skb_queue_purge(&loopback_queue); } |
| 1 7 2 7 7 7 7 7 6 7 7 7 6 4 1 4 4 2 4 7 7 7 7 7 7 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 9 5 4 4 9 19 19 1 18 12 18 19 14 12 14 13 1 14 10 10 6 8 7 8 10 18 18 14 14 20 18 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ #include <linux/mm.h> #include <linux/llist.h> #include <linux/bpf.h> #include <linux/irq_work.h> #include <linux/bpf_mem_alloc.h> #include <linux/memcontrol.h> #include <asm/local.h> /* Any context (including NMI) BPF specific memory allocator. * * Tracing BPF programs can attach to kprobe and fentry. Hence they * run in unknown context where calling plain kmalloc() might not be safe. * * Front-end kmalloc() with per-cpu per-bucket cache of free elements. * Refill this cache asynchronously from irq_work. * * CPU_0 buckets * 16 32 64 96 128 196 256 512 1024 2048 4096 * ... * CPU_N buckets * 16 32 64 96 128 196 256 512 1024 2048 4096 * * The buckets are prefilled at the start. * BPF programs always run with migration disabled. * It's safe to allocate from cache of the current cpu with irqs disabled. * Free-ing is always done into bucket of the current cpu as well. * irq_work trims extra free elements from buckets with kfree * and refills them with kmalloc, so global kmalloc logic takes care * of freeing objects allocated by one cpu and freed on another. * * Every allocated objected is padded with extra 8 bytes that contains * struct llist_node. */ #define LLIST_NODE_SZ sizeof(struct llist_node) #define BPF_MEM_ALLOC_SIZE_MAX 4096 /* similar to kmalloc, but sizeof == 8 bucket is gone */ static u8 size_index[24] __ro_after_init = { 3, /* 8 */ 3, /* 16 */ 4, /* 24 */ 4, /* 32 */ 5, /* 40 */ 5, /* 48 */ 5, /* 56 */ 5, /* 64 */ 1, /* 72 */ 1, /* 80 */ 1, /* 88 */ 1, /* 96 */ 6, /* 104 */ 6, /* 112 */ 6, /* 120 */ 6, /* 128 */ 2, /* 136 */ 2, /* 144 */ 2, /* 152 */ 2, /* 160 */ 2, /* 168 */ 2, /* 176 */ 2, /* 184 */ 2 /* 192 */ }; static int bpf_mem_cache_idx(size_t size) { if (!size || size > BPF_MEM_ALLOC_SIZE_MAX) return -1; if (size <= 192) return size_index[(size - 1) / 8] - 1; return fls(size - 1) - 2; } #define NUM_CACHES 11 struct bpf_mem_cache { /* per-cpu list of free objects of size 'unit_size'. * All accesses are done with interrupts disabled and 'active' counter * protection with __llist_add() and __llist_del_first(). */ struct llist_head free_llist; local_t active; /* Operations on the free_list from unit_alloc/unit_free/bpf_mem_refill * are sequenced by per-cpu 'active' counter. But unit_free() cannot * fail. When 'active' is busy the unit_free() will add an object to * free_llist_extra. */ struct llist_head free_llist_extra; struct irq_work refill_work; struct obj_cgroup *objcg; int unit_size; /* count of objects in free_llist */ int free_cnt; int low_watermark, high_watermark, batch; int percpu_size; bool draining; struct bpf_mem_cache *tgt; /* list of objects to be freed after RCU GP */ struct llist_head free_by_rcu; struct llist_node *free_by_rcu_tail; struct llist_head waiting_for_gp; struct llist_node *waiting_for_gp_tail; struct rcu_head rcu; atomic_t call_rcu_in_progress; struct llist_head free_llist_extra_rcu; /* list of objects to be freed after RCU tasks trace GP */ struct llist_head free_by_rcu_ttrace; struct llist_head waiting_for_gp_ttrace; struct rcu_head rcu_ttrace; atomic_t call_rcu_ttrace_in_progress; }; struct bpf_mem_caches { struct bpf_mem_cache cache[NUM_CACHES]; }; static const u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096}; static struct llist_node notrace *__llist_del_first(struct llist_head *head) { struct llist_node *entry, *next; entry = head->first; if (!entry) return NULL; next = entry->next; head->first = next; return entry; } static void *__alloc(struct bpf_mem_cache *c, int node, gfp_t flags) { if (c->percpu_size) { void __percpu **obj = kmalloc_node(c->percpu_size, flags, node); void __percpu *pptr = __alloc_percpu_gfp(c->unit_size, 8, flags); if (!obj || !pptr) { free_percpu(pptr); kfree(obj); return NULL; } obj[1] = pptr; return obj; } return kmalloc_node(c->unit_size, flags | __GFP_ZERO, node); } static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c) { #ifdef CONFIG_MEMCG if (c->objcg) return get_mem_cgroup_from_objcg(c->objcg); return root_mem_cgroup; #else return NULL; #endif } static void inc_active(struct bpf_mem_cache *c, unsigned long *flags) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) /* In RT irq_work runs in per-cpu kthread, so disable * interrupts to avoid preemption and interrupts and * reduce the chance of bpf prog executing on this cpu * when active counter is busy. */ local_irq_save(*flags); /* alloc_bulk runs from irq_work which will not preempt a bpf * program that does unit_alloc/unit_free since IRQs are * disabled there. There is no race to increment 'active' * counter. It protects free_llist from corruption in case NMI * bpf prog preempted this loop. */ WARN_ON_ONCE(local_inc_return(&c->active) != 1); } static void dec_active(struct bpf_mem_cache *c, unsigned long *flags) { local_dec(&c->active); if (IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_restore(*flags); } static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj) { unsigned long flags; inc_active(c, &flags); __llist_add(obj, &c->free_llist); c->free_cnt++; dec_active(c, &flags); } /* Mostly runs from irq_work except __init phase. */ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node, bool atomic) { struct mem_cgroup *memcg = NULL, *old_memcg; gfp_t gfp; void *obj; int i; gfp = __GFP_NOWARN | __GFP_ACCOUNT; gfp |= atomic ? GFP_NOWAIT : GFP_KERNEL; for (i = 0; i < cnt; i++) { /* * For every 'c' llist_del_first(&c->free_by_rcu_ttrace); is * done only by one CPU == current CPU. Other CPUs might * llist_add() and llist_del_all() in parallel. */ obj = llist_del_first(&c->free_by_rcu_ttrace); if (!obj) break; add_obj_to_free_list(c, obj); } if (i >= cnt) return; for (; i < cnt; i++) { obj = llist_del_first(&c->waiting_for_gp_ttrace); if (!obj) break; add_obj_to_free_list(c, obj); } if (i >= cnt) return; memcg = get_memcg(c); old_memcg = set_active_memcg(memcg); for (; i < cnt; i++) { /* Allocate, but don't deplete atomic reserves that typical * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc * will allocate from the current numa node which is what we * want here. */ obj = __alloc(c, node, gfp); if (!obj) break; add_obj_to_free_list(c, obj); } set_active_memcg(old_memcg); mem_cgroup_put(memcg); } static void free_one(void *obj, bool percpu) { if (percpu) free_percpu(((void __percpu **)obj)[1]); kfree(obj); } static int free_all(struct llist_node *llnode, bool percpu) { struct llist_node *pos, *t; int cnt = 0; llist_for_each_safe(pos, t, llnode) { free_one(pos, percpu); cnt++; } return cnt; } static void __free_rcu(struct rcu_head *head) { struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu_ttrace); free_all(llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size); atomic_set(&c->call_rcu_ttrace_in_progress, 0); } static void __free_rcu_tasks_trace(struct rcu_head *head) { /* If RCU Tasks Trace grace period implies RCU grace period, * there is no need to invoke call_rcu(). */ if (rcu_trace_implies_rcu_gp()) __free_rcu(head); else call_rcu(head, __free_rcu); } static void enque_to_free(struct bpf_mem_cache *c, void *obj) { struct llist_node *llnode = obj; /* bpf_mem_cache is a per-cpu object. Freeing happens in irq_work. * Nothing races to add to free_by_rcu_ttrace list. */ llist_add(llnode, &c->free_by_rcu_ttrace); } static void do_call_rcu_ttrace(struct bpf_mem_cache *c) { struct llist_node *llnode, *t; if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1)) { if (unlikely(READ_ONCE(c->draining))) { llnode = llist_del_all(&c->free_by_rcu_ttrace); free_all(llnode, !!c->percpu_size); } return; } WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace)); llist_for_each_safe(llnode, t, llist_del_all(&c->free_by_rcu_ttrace)) llist_add(llnode, &c->waiting_for_gp_ttrace); if (unlikely(READ_ONCE(c->draining))) { __free_rcu(&c->rcu_ttrace); return; } /* Use call_rcu_tasks_trace() to wait for sleepable progs to finish. * If RCU Tasks Trace grace period implies RCU grace period, free * these elements directly, else use call_rcu() to wait for normal * progs to finish and finally do free_one() on each element. */ call_rcu_tasks_trace(&c->rcu_ttrace, __free_rcu_tasks_trace); } static void free_bulk(struct bpf_mem_cache *c) { struct bpf_mem_cache *tgt = c->tgt; struct llist_node *llnode, *t; unsigned long flags; int cnt; WARN_ON_ONCE(tgt->unit_size != c->unit_size); WARN_ON_ONCE(tgt->percpu_size != c->percpu_size); do { inc_active(c, &flags); llnode = __llist_del_first(&c->free_llist); if (llnode) cnt = --c->free_cnt; else cnt = 0; dec_active(c, &flags); if (llnode) enque_to_free(tgt, llnode); } while (cnt > (c->high_watermark + c->low_watermark) / 2); /* and drain free_llist_extra */ llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra)) enque_to_free(tgt, llnode); do_call_rcu_ttrace(tgt); } static void __free_by_rcu(struct rcu_head *head) { struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu); struct bpf_mem_cache *tgt = c->tgt; struct llist_node *llnode; WARN_ON_ONCE(tgt->unit_size != c->unit_size); WARN_ON_ONCE(tgt->percpu_size != c->percpu_size); llnode = llist_del_all(&c->waiting_for_gp); if (!llnode) goto out; llist_add_batch(llnode, c->waiting_for_gp_tail, &tgt->free_by_rcu_ttrace); /* Objects went through regular RCU GP. Send them to RCU tasks trace */ do_call_rcu_ttrace(tgt); out: atomic_set(&c->call_rcu_in_progress, 0); } static void check_free_by_rcu(struct bpf_mem_cache *c) { struct llist_node *llnode, *t; unsigned long flags; /* drain free_llist_extra_rcu */ if (unlikely(!llist_empty(&c->free_llist_extra_rcu))) { inc_active(c, &flags); llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra_rcu)) if (__llist_add(llnode, &c->free_by_rcu)) c->free_by_rcu_tail = llnode; dec_active(c, &flags); } if (llist_empty(&c->free_by_rcu)) return; if (atomic_xchg(&c->call_rcu_in_progress, 1)) { /* * Instead of kmalloc-ing new rcu_head and triggering 10k * call_rcu() to hit rcutree.qhimark and force RCU to notice * the overload just ask RCU to hurry up. There could be many * objects in free_by_rcu list. * This hint reduces memory consumption for an artificial * benchmark from 2 Gbyte to 150 Mbyte. */ rcu_request_urgent_qs_task(current); return; } WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp)); inc_active(c, &flags); WRITE_ONCE(c->waiting_for_gp.first, __llist_del_all(&c->free_by_rcu)); c->waiting_for_gp_tail = c->free_by_rcu_tail; dec_active(c, &flags); if (unlikely(READ_ONCE(c->draining))) { free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size); atomic_set(&c->call_rcu_in_progress, 0); } else { call_rcu_hurry(&c->rcu, __free_by_rcu); } } static void bpf_mem_refill(struct irq_work *work) { struct bpf_mem_cache *c = container_of(work, struct bpf_mem_cache, refill_work); int cnt; /* Racy access to free_cnt. It doesn't need to be 100% accurate */ cnt = c->free_cnt; if (cnt < c->low_watermark) /* irq_work runs on this cpu and kmalloc will allocate * from the current numa node which is what we want here. */ alloc_bulk(c, c->batch, NUMA_NO_NODE, true); else if (cnt > c->high_watermark) free_bulk(c); check_free_by_rcu(c); } static void notrace irq_work_raise(struct bpf_mem_cache *c) { irq_work_queue(&c->refill_work); } /* For typical bpf map case that uses bpf_mem_cache_alloc and single bucket * the freelist cache will be elem_size * 64 (or less) on each cpu. * * For bpf programs that don't have statically known allocation sizes and * assuming (low_mark + high_mark) / 2 as an average number of elements per * bucket and all buckets are used the total amount of memory in freelists * on each cpu will be: * 64*16 + 64*32 + 64*64 + 64*96 + 64*128 + 64*196 + 64*256 + 32*512 + 16*1024 + 8*2048 + 4*4096 * == ~ 116 Kbyte using below heuristic. * Initialized, but unused bpf allocator (not bpf map specific one) will * consume ~ 11 Kbyte per cpu. * Typical case will be between 11K and 116K closer to 11K. * bpf progs can and should share bpf_mem_cache when possible. * * Percpu allocation is typically rare. To avoid potential unnecessary large * memory consumption, set low_mark = 1 and high_mark = 3, resulting in c->batch = 1. */ static void init_refill_work(struct bpf_mem_cache *c) { init_irq_work(&c->refill_work, bpf_mem_refill); if (c->percpu_size) { c->low_watermark = 1; c->high_watermark = 3; } else if (c->unit_size <= 256) { c->low_watermark = 32; c->high_watermark = 96; } else { /* When page_size == 4k, order-0 cache will have low_mark == 2 * and high_mark == 6 with batch alloc of 3 individual pages at * a time. * 8k allocs and above low == 1, high == 3, batch == 1. */ c->low_watermark = max(32 * 256 / c->unit_size, 1); c->high_watermark = max(96 * 256 / c->unit_size, 3); } c->batch = max((c->high_watermark - c->low_watermark) / 4 * 3, 1); } static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) { int cnt = 1; /* To avoid consuming memory, for non-percpu allocation, assume that * 1st run of bpf prog won't be doing more than 4 map_update_elem from * irq disabled region if unit size is less than or equal to 256. * For all other cases, let us just do one allocation. */ if (!c->percpu_size && c->unit_size <= 256) cnt = 4; alloc_bulk(c, cnt, cpu_to_node(cpu), false); } /* When size != 0 bpf_mem_cache for each cpu. * This is typical bpf hash map use case when all elements have equal size. * * When size == 0 allocate 11 bpf_mem_cache-s for each cpu, then rely on * kmalloc/kfree. Max allocation size is 4096 in this case. * This is bpf_dynptr and bpf_kptr use case. */ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) { struct bpf_mem_caches *cc; struct bpf_mem_caches __percpu *pcc; struct bpf_mem_cache *c; struct bpf_mem_cache __percpu *pc; struct obj_cgroup *objcg = NULL; int cpu, i, unit_size, percpu_size = 0; if (percpu && size == 0) return -EINVAL; /* room for llist_node and per-cpu pointer */ if (percpu) percpu_size = LLIST_NODE_SZ + sizeof(void *); ma->percpu = percpu; if (size) { pc = __alloc_percpu_gfp(sizeof(*pc), 8, GFP_KERNEL); if (!pc) return -ENOMEM; if (!percpu) size += LLIST_NODE_SZ; /* room for llist_node */ unit_size = size; #ifdef CONFIG_MEMCG if (memcg_bpf_enabled()) objcg = get_obj_cgroup_from_current(); #endif ma->objcg = objcg; for_each_possible_cpu(cpu) { c = per_cpu_ptr(pc, cpu); c->unit_size = unit_size; c->objcg = objcg; c->percpu_size = percpu_size; c->tgt = c; init_refill_work(c); prefill_mem_cache(c, cpu); } ma->cache = pc; return 0; } pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL); if (!pcc) return -ENOMEM; #ifdef CONFIG_MEMCG objcg = get_obj_cgroup_from_current(); #endif ma->objcg = objcg; for_each_possible_cpu(cpu) { cc = per_cpu_ptr(pcc, cpu); for (i = 0; i < NUM_CACHES; i++) { c = &cc->cache[i]; c->unit_size = sizes[i]; c->objcg = objcg; c->percpu_size = percpu_size; c->tgt = c; init_refill_work(c); prefill_mem_cache(c, cpu); } } ma->caches = pcc; return 0; } int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg) { struct bpf_mem_caches __percpu *pcc; pcc = __alloc_percpu_gfp(sizeof(struct bpf_mem_caches), 8, GFP_KERNEL); if (!pcc) return -ENOMEM; ma->caches = pcc; ma->objcg = objcg; ma->percpu = true; return 0; } int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size) { struct bpf_mem_caches *cc; struct bpf_mem_caches __percpu *pcc; int cpu, i, unit_size, percpu_size; struct obj_cgroup *objcg; struct bpf_mem_cache *c; i = bpf_mem_cache_idx(size); if (i < 0) return -EINVAL; /* room for llist_node and per-cpu pointer */ percpu_size = LLIST_NODE_SZ + sizeof(void *); unit_size = sizes[i]; objcg = ma->objcg; pcc = ma->caches; for_each_possible_cpu(cpu) { cc = per_cpu_ptr(pcc, cpu); c = &cc->cache[i]; if (c->unit_size) break; c->unit_size = unit_size; c->objcg = objcg; c->percpu_size = percpu_size; c->tgt = c; init_refill_work(c); prefill_mem_cache(c, cpu); } return 0; } static void drain_mem_cache(struct bpf_mem_cache *c) { bool percpu = !!c->percpu_size; /* No progs are using this bpf_mem_cache, but htab_map_free() called * bpf_mem_cache_free() for all remaining elements and they can be in * free_by_rcu_ttrace or in waiting_for_gp_ttrace lists, so drain those lists now. * * Except for waiting_for_gp_ttrace list, there are no concurrent operations * on these lists, so it is safe to use __llist_del_all(). */ free_all(llist_del_all(&c->free_by_rcu_ttrace), percpu); free_all(llist_del_all(&c->waiting_for_gp_ttrace), percpu); free_all(__llist_del_all(&c->free_llist), percpu); free_all(__llist_del_all(&c->free_llist_extra), percpu); free_all(__llist_del_all(&c->free_by_rcu), percpu); free_all(__llist_del_all(&c->free_llist_extra_rcu), percpu); free_all(llist_del_all(&c->waiting_for_gp), percpu); } static void check_mem_cache(struct bpf_mem_cache *c) { WARN_ON_ONCE(!llist_empty(&c->free_by_rcu_ttrace)); WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace)); WARN_ON_ONCE(!llist_empty(&c->free_llist)); WARN_ON_ONCE(!llist_empty(&c->free_llist_extra)); WARN_ON_ONCE(!llist_empty(&c->free_by_rcu)); WARN_ON_ONCE(!llist_empty(&c->free_llist_extra_rcu)); WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp)); } static void check_leaked_objs(struct bpf_mem_alloc *ma) { struct bpf_mem_caches *cc; struct bpf_mem_cache *c; int cpu, i; if (ma->cache) { for_each_possible_cpu(cpu) { c = per_cpu_ptr(ma->cache, cpu); check_mem_cache(c); } } if (ma->caches) { for_each_possible_cpu(cpu) { cc = per_cpu_ptr(ma->caches, cpu); for (i = 0; i < NUM_CACHES; i++) { c = &cc->cache[i]; check_mem_cache(c); } } } } static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma) { check_leaked_objs(ma); free_percpu(ma->cache); free_percpu(ma->caches); ma->cache = NULL; ma->caches = NULL; } static void free_mem_alloc(struct bpf_mem_alloc *ma) { /* waiting_for_gp[_ttrace] lists were drained, but RCU callbacks * might still execute. Wait for them. * * rcu_barrier_tasks_trace() doesn't imply synchronize_rcu_tasks_trace(), * but rcu_barrier_tasks_trace() and rcu_barrier() below are only used * to wait for the pending __free_rcu_tasks_trace() and __free_rcu(), * so if call_rcu(head, __free_rcu) is skipped due to * rcu_trace_implies_rcu_gp(), it will be OK to skip rcu_barrier() by * using rcu_trace_implies_rcu_gp() as well. */ rcu_barrier(); /* wait for __free_by_rcu */ rcu_barrier_tasks_trace(); /* wait for __free_rcu */ if (!rcu_trace_implies_rcu_gp()) rcu_barrier(); free_mem_alloc_no_barrier(ma); } static void free_mem_alloc_deferred(struct work_struct *work) { struct bpf_mem_alloc *ma = container_of(work, struct bpf_mem_alloc, work); free_mem_alloc(ma); kfree(ma); } static void destroy_mem_alloc(struct bpf_mem_alloc *ma, int rcu_in_progress) { struct bpf_mem_alloc *copy; if (!rcu_in_progress) { /* Fast path. No callbacks are pending, hence no need to do * rcu_barrier-s. */ free_mem_alloc_no_barrier(ma); return; } copy = kmemdup(ma, sizeof(*ma), GFP_KERNEL); if (!copy) { /* Slow path with inline barrier-s */ free_mem_alloc(ma); return; } /* Defer barriers into worker to let the rest of map memory to be freed */ memset(ma, 0, sizeof(*ma)); INIT_WORK(©->work, free_mem_alloc_deferred); queue_work(system_unbound_wq, ©->work); } void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma) { struct bpf_mem_caches *cc; struct bpf_mem_cache *c; int cpu, i, rcu_in_progress; if (ma->cache) { rcu_in_progress = 0; for_each_possible_cpu(cpu) { c = per_cpu_ptr(ma->cache, cpu); WRITE_ONCE(c->draining, true); irq_work_sync(&c->refill_work); drain_mem_cache(c); rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress); rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } obj_cgroup_put(ma->objcg); destroy_mem_alloc(ma, rcu_in_progress); } if (ma->caches) { rcu_in_progress = 0; for_each_possible_cpu(cpu) { cc = per_cpu_ptr(ma->caches, cpu); for (i = 0; i < NUM_CACHES; i++) { c = &cc->cache[i]; WRITE_ONCE(c->draining, true); irq_work_sync(&c->refill_work); drain_mem_cache(c); rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress); rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } } obj_cgroup_put(ma->objcg); destroy_mem_alloc(ma, rcu_in_progress); } } /* notrace is necessary here and in other functions to make sure * bpf programs cannot attach to them and cause llist corruptions. */ static void notrace *unit_alloc(struct bpf_mem_cache *c) { struct llist_node *llnode = NULL; unsigned long flags; int cnt = 0; /* Disable irqs to prevent the following race for majority of prog types: * prog_A * bpf_mem_alloc * preemption or irq -> prog_B * bpf_mem_alloc * * but prog_B could be a perf_event NMI prog. * Use per-cpu 'active' counter to order free_list access between * unit_alloc/unit_free/bpf_mem_refill. */ local_irq_save(flags); if (local_inc_return(&c->active) == 1) { llnode = __llist_del_first(&c->free_llist); if (llnode) { cnt = --c->free_cnt; *(struct bpf_mem_cache **)llnode = c; } } local_dec(&c->active); WARN_ON(cnt < 0); if (cnt < c->low_watermark) irq_work_raise(c); /* Enable IRQ after the enqueue of irq work completes, so irq work * will run after IRQ is enabled and free_llist may be refilled by * irq work before other task preempts current task. */ local_irq_restore(flags); return llnode; } /* Though 'ptr' object could have been allocated on a different cpu * add it to the free_llist of the current cpu. * Let kfree() logic deal with it when it's later called from irq_work. */ static void notrace unit_free(struct bpf_mem_cache *c, void *ptr) { struct llist_node *llnode = ptr - LLIST_NODE_SZ; unsigned long flags; int cnt = 0; BUILD_BUG_ON(LLIST_NODE_SZ > 8); /* * Remember bpf_mem_cache that allocated this object. * The hint is not accurate. */ c->tgt = *(struct bpf_mem_cache **)llnode; local_irq_save(flags); if (local_inc_return(&c->active) == 1) { __llist_add(llnode, &c->free_llist); cnt = ++c->free_cnt; } else { /* unit_free() cannot fail. Therefore add an object to atomic * llist. free_bulk() will drain it. Though free_llist_extra is * a per-cpu list we have to use atomic llist_add here, since * it also can be interrupted by bpf nmi prog that does another * unit_free() into the same free_llist_extra. */ llist_add(llnode, &c->free_llist_extra); } local_dec(&c->active); if (cnt > c->high_watermark) /* free few objects from current cpu into global kmalloc pool */ irq_work_raise(c); /* Enable IRQ after irq_work_raise() completes, otherwise when current * task is preempted by task which does unit_alloc(), unit_alloc() may * return NULL unexpectedly because irq work is already pending but can * not been triggered and free_llist can not be refilled timely. */ local_irq_restore(flags); } static void notrace unit_free_rcu(struct bpf_mem_cache *c, void *ptr) { struct llist_node *llnode = ptr - LLIST_NODE_SZ; unsigned long flags; c->tgt = *(struct bpf_mem_cache **)llnode; local_irq_save(flags); if (local_inc_return(&c->active) == 1) { if (__llist_add(llnode, &c->free_by_rcu)) c->free_by_rcu_tail = llnode; } else { llist_add(llnode, &c->free_llist_extra_rcu); } local_dec(&c->active); if (!atomic_read(&c->call_rcu_in_progress)) irq_work_raise(c); local_irq_restore(flags); } /* Called from BPF program or from sys_bpf syscall. * In both cases migration is disabled. */ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size) { int idx; void *ret; if (!size) return NULL; if (!ma->percpu) size += LLIST_NODE_SZ; idx = bpf_mem_cache_idx(size); if (idx < 0) return NULL; ret = unit_alloc(this_cpu_ptr(ma->caches)->cache + idx); return !ret ? NULL : ret + LLIST_NODE_SZ; } void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr) { struct bpf_mem_cache *c; int idx; if (!ptr) return; c = *(void **)(ptr - LLIST_NODE_SZ); idx = bpf_mem_cache_idx(c->unit_size); if (WARN_ON_ONCE(idx < 0)) return; unit_free(this_cpu_ptr(ma->caches)->cache + idx, ptr); } void notrace bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr) { struct bpf_mem_cache *c; int idx; if (!ptr) return; c = *(void **)(ptr - LLIST_NODE_SZ); idx = bpf_mem_cache_idx(c->unit_size); if (WARN_ON_ONCE(idx < 0)) return; unit_free_rcu(this_cpu_ptr(ma->caches)->cache + idx, ptr); } void notrace *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma) { void *ret; ret = unit_alloc(this_cpu_ptr(ma->cache)); return !ret ? NULL : ret + LLIST_NODE_SZ; } void notrace bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr) { if (!ptr) return; unit_free(this_cpu_ptr(ma->cache), ptr); } void notrace bpf_mem_cache_free_rcu(struct bpf_mem_alloc *ma, void *ptr) { if (!ptr) return; unit_free_rcu(this_cpu_ptr(ma->cache), ptr); } /* Directly does a kfree() without putting 'ptr' back to the free_llist * for reuse and without waiting for a rcu_tasks_trace gp. * The caller must first go through the rcu_tasks_trace gp for 'ptr' * before calling bpf_mem_cache_raw_free(). * It could be used when the rcu_tasks_trace callback does not have * a hold on the original bpf_mem_alloc object that allocated the * 'ptr'. This should only be used in the uncommon code path. * Otherwise, the bpf_mem_alloc's free_llist cannot be refilled * and may affect performance. */ void bpf_mem_cache_raw_free(void *ptr) { if (!ptr) return; kfree(ptr - LLIST_NODE_SZ); } /* When flags == GFP_KERNEL, it signals that the caller will not cause * deadlock when using kmalloc. bpf_mem_cache_alloc_flags() will use * kmalloc if the free_llist is empty. */ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags) { struct bpf_mem_cache *c; void *ret; c = this_cpu_ptr(ma->cache); ret = unit_alloc(c); if (!ret && flags == GFP_KERNEL) { struct mem_cgroup *memcg, *old_memcg; memcg = get_memcg(c); old_memcg = set_active_memcg(memcg); ret = __alloc(c, NUMA_NO_NODE, GFP_KERNEL | __GFP_NOWARN | __GFP_ACCOUNT); if (ret) *(struct bpf_mem_cache **)ret = c; set_active_memcg(old_memcg); mem_cgroup_put(memcg); } return !ret ? NULL : ret + LLIST_NODE_SZ; } int bpf_mem_alloc_check_size(bool percpu, size_t size) { /* The size of percpu allocation doesn't have LLIST_NODE_SZ overhead */ if ((percpu && size > BPF_MEM_ALLOC_SIZE_MAX) || (!percpu && size > BPF_MEM_ALLOC_SIZE_MAX - LLIST_NODE_SZ)) return -E2BIG; return 0; } |
| 5 3 4 4 1 3 3 3 1 1 1 6 6 1 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * CMAC: Cipher Block Mode for Authentication * * Copyright © 2013 Jussi Kivilinna <jussi.kivilinna@iki.fi> * * Based on work by: * Copyright © 2013 Tom St Denis <tstdenis@elliptictech.com> * Based on crypto/xcbc.c: * Copyright © 2006 USAGI/WIDE Project, * Author: Kazunori Miyazawa <miyazawa@linux-ipv6.org> */ #include <crypto/internal/cipher.h> #include <crypto/internal/hash.h> #include <linux/err.h> #include <linux/kernel.h> #include <linux/module.h> /* * +------------------------ * | <parent tfm> * +------------------------ * | cmac_tfm_ctx * +------------------------ * | consts (block size * 2) * +------------------------ */ struct cmac_tfm_ctx { struct crypto_cipher *child; __be64 consts[]; }; /* * +------------------------ * | <shash desc> * +------------------------ * | cmac_desc_ctx * +------------------------ * | odds (block size) * +------------------------ * | prev (block size) * +------------------------ */ struct cmac_desc_ctx { unsigned int len; u8 odds[]; }; static int crypto_cmac_digest_setkey(struct crypto_shash *parent, const u8 *inkey, unsigned int keylen) { struct cmac_tfm_ctx *ctx = crypto_shash_ctx(parent); unsigned int bs = crypto_shash_blocksize(parent); __be64 *consts = ctx->consts; u64 _const[2]; int i, err = 0; u8 msb_mask, gfmask; err = crypto_cipher_setkey(ctx->child, inkey, keylen); if (err) return err; /* encrypt the zero block */ memset(consts, 0, bs); crypto_cipher_encrypt_one(ctx->child, (u8 *)consts, (u8 *)consts); switch (bs) { case 16: gfmask = 0x87; _const[0] = be64_to_cpu(consts[1]); _const[1] = be64_to_cpu(consts[0]); /* gf(2^128) multiply zero-ciphertext with u and u^2 */ for (i = 0; i < 4; i += 2) { msb_mask = ((s64)_const[1] >> 63) & gfmask; _const[1] = (_const[1] << 1) | (_const[0] >> 63); _const[0] = (_const[0] << 1) ^ msb_mask; consts[i + 0] = cpu_to_be64(_const[1]); consts[i + 1] = cpu_to_be64(_const[0]); } break; case 8: gfmask = 0x1B; _const[0] = be64_to_cpu(consts[0]); /* gf(2^64) multiply zero-ciphertext with u and u^2 */ for (i = 0; i < 2; i++) { msb_mask = ((s64)_const[0] >> 63) & gfmask; _const[0] = (_const[0] << 1) ^ msb_mask; consts[i] = cpu_to_be64(_const[0]); } break; } return 0; } static int crypto_cmac_digest_init(struct shash_desc *pdesc) { struct cmac_desc_ctx *ctx = shash_desc_ctx(pdesc); int bs = crypto_shash_blocksize(pdesc->tfm); u8 *prev = &ctx->odds[bs]; ctx->len = 0; memset(prev, 0, bs); return 0; } static int crypto_cmac_digest_update(struct shash_desc *pdesc, const u8 *p, unsigned int len) { struct crypto_shash *parent = pdesc->tfm; struct cmac_tfm_ctx *tctx = crypto_shash_ctx(parent); struct cmac_desc_ctx *ctx = shash_desc_ctx(pdesc); struct crypto_cipher *tfm = tctx->child; int bs = crypto_shash_blocksize(parent); u8 *odds = ctx->odds; u8 *prev = odds + bs; /* checking the data can fill the block */ if ((ctx->len + len) <= bs) { memcpy(odds + ctx->len, p, len); ctx->len += len; return 0; } /* filling odds with new data and encrypting it */ memcpy(odds + ctx->len, p, bs - ctx->len); len -= bs - ctx->len; p += bs - ctx->len; crypto_xor(prev, odds, bs); crypto_cipher_encrypt_one(tfm, prev, prev); /* clearing the length */ ctx->len = 0; /* encrypting the rest of data */ while (len > bs) { crypto_xor(prev, p, bs); crypto_cipher_encrypt_one(tfm, prev, prev); p += bs; len -= bs; } /* keeping the surplus of blocksize */ if (len) { memcpy(odds, p, len); ctx->len = len; } return 0; } static int crypto_cmac_digest_final(struct shash_desc *pdesc, u8 *out) { struct crypto_shash *parent = pdesc->tfm; struct cmac_tfm_ctx *tctx = crypto_shash_ctx(parent); struct cmac_desc_ctx *ctx = shash_desc_ctx(pdesc); struct crypto_cipher *tfm = tctx->child; int bs = crypto_shash_blocksize(parent); u8 *odds = ctx->odds; u8 *prev = odds + bs; unsigned int offset = 0; if (ctx->len != bs) { unsigned int rlen; u8 *p = odds + ctx->len; *p = 0x80; p++; rlen = bs - ctx->len - 1; if (rlen) memset(p, 0, rlen); offset += bs; } crypto_xor(prev, odds, bs); crypto_xor(prev, (const u8 *)tctx->consts + offset, bs); crypto_cipher_encrypt_one(tfm, out, prev); return 0; } static int cmac_init_tfm(struct crypto_shash *tfm) { struct shash_instance *inst = shash_alg_instance(tfm); struct cmac_tfm_ctx *ctx = crypto_shash_ctx(tfm); struct crypto_cipher_spawn *spawn; struct crypto_cipher *cipher; spawn = shash_instance_ctx(inst); cipher = crypto_spawn_cipher(spawn); if (IS_ERR(cipher)) return PTR_ERR(cipher); ctx->child = cipher; return 0; } static int cmac_clone_tfm(struct crypto_shash *tfm, struct crypto_shash *otfm) { struct cmac_tfm_ctx *octx = crypto_shash_ctx(otfm); struct cmac_tfm_ctx *ctx = crypto_shash_ctx(tfm); struct crypto_cipher *cipher; cipher = crypto_clone_cipher(octx->child); if (IS_ERR(cipher)) return PTR_ERR(cipher); ctx->child = cipher; return 0; } static void cmac_exit_tfm(struct crypto_shash *tfm) { struct cmac_tfm_ctx *ctx = crypto_shash_ctx(tfm); crypto_free_cipher(ctx->child); } static int cmac_create(struct crypto_template *tmpl, struct rtattr **tb) { struct shash_instance *inst; struct crypto_cipher_spawn *spawn; struct crypto_alg *alg; u32 mask; int err; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SHASH, &mask); if (err) return err; inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL); if (!inst) return -ENOMEM; spawn = shash_instance_ctx(inst); err = crypto_grab_cipher(spawn, shash_crypto_instance(inst), crypto_attr_alg_name(tb[1]), 0, mask); if (err) goto err_free_inst; alg = crypto_spawn_cipher_alg(spawn); switch (alg->cra_blocksize) { case 16: case 8: break; default: err = -EINVAL; goto err_free_inst; } err = crypto_inst_setname(shash_crypto_instance(inst), tmpl->name, alg); if (err) goto err_free_inst; inst->alg.base.cra_priority = alg->cra_priority; inst->alg.base.cra_blocksize = alg->cra_blocksize; inst->alg.base.cra_ctxsize = sizeof(struct cmac_tfm_ctx) + alg->cra_blocksize * 2; inst->alg.digestsize = alg->cra_blocksize; inst->alg.descsize = sizeof(struct cmac_desc_ctx) + alg->cra_blocksize * 2; inst->alg.init = crypto_cmac_digest_init; inst->alg.update = crypto_cmac_digest_update; inst->alg.final = crypto_cmac_digest_final; inst->alg.setkey = crypto_cmac_digest_setkey; inst->alg.init_tfm = cmac_init_tfm; inst->alg.clone_tfm = cmac_clone_tfm; inst->alg.exit_tfm = cmac_exit_tfm; inst->free = shash_free_singlespawn_instance; err = shash_register_instance(tmpl, inst); if (err) { err_free_inst: shash_free_singlespawn_instance(inst); } return err; } static struct crypto_template crypto_cmac_tmpl = { .name = "cmac", .create = cmac_create, .module = THIS_MODULE, }; static int __init crypto_cmac_module_init(void) { return crypto_register_template(&crypto_cmac_tmpl); } static void __exit crypto_cmac_module_exit(void) { crypto_unregister_template(&crypto_cmac_tmpl); } subsys_initcall(crypto_cmac_module_init); module_exit(crypto_cmac_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CMAC keyed hash algorithm"); MODULE_ALIAS_CRYPTO("cmac"); MODULE_IMPORT_NS("CRYPTO_INTERNAL"); |
| 1 2 1 1 1 1 1 1 1 1 1 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2023 Bootlin * */ #include "common.h" #include "netlink.h" #include <linux/phy.h> #include <linux/phy_link_topology.h> #include <linux/sfp.h> struct phy_req_info { struct ethnl_req_info base; struct phy_device_node *pdn; }; #define PHY_REQINFO(__req_base) \ container_of(__req_base, struct phy_req_info, base) const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1] = { [ETHTOOL_A_PHY_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; /* Caller holds rtnl */ static ssize_t ethnl_phy_reply_size(const struct ethnl_req_info *req_base, struct netlink_ext_ack *extack) { struct phy_req_info *req_info = PHY_REQINFO(req_base); struct phy_device_node *pdn = req_info->pdn; struct phy_device *phydev = pdn->phy; size_t size = 0; ASSERT_RTNL(); /* ETHTOOL_A_PHY_INDEX */ size += nla_total_size(sizeof(u32)); /* ETHTOOL_A_DRVNAME */ if (phydev->drv) size += nla_total_size(strlen(phydev->drv->name) + 1); /* ETHTOOL_A_NAME */ size += nla_total_size(strlen(dev_name(&phydev->mdio.dev)) + 1); /* ETHTOOL_A_PHY_UPSTREAM_TYPE */ size += nla_total_size(sizeof(u32)); if (phy_on_sfp(phydev)) { const char *upstream_sfp_name = sfp_get_name(pdn->parent_sfp_bus); /* ETHTOOL_A_PHY_UPSTREAM_SFP_NAME */ if (upstream_sfp_name) size += nla_total_size(strlen(upstream_sfp_name) + 1); /* ETHTOOL_A_PHY_UPSTREAM_INDEX */ size += nla_total_size(sizeof(u32)); } /* ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME */ if (phydev->sfp_bus) { const char *sfp_name = sfp_get_name(phydev->sfp_bus); if (sfp_name) size += nla_total_size(strlen(sfp_name) + 1); } return size; } static int ethnl_phy_fill_reply(const struct ethnl_req_info *req_base, struct sk_buff *skb) { struct phy_req_info *req_info = PHY_REQINFO(req_base); struct phy_device_node *pdn = req_info->pdn; struct phy_device *phydev = pdn->phy; enum phy_upstream ptype; ptype = pdn->upstream_type; if (nla_put_u32(skb, ETHTOOL_A_PHY_INDEX, phydev->phyindex) || nla_put_string(skb, ETHTOOL_A_PHY_NAME, dev_name(&phydev->mdio.dev)) || nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_TYPE, ptype)) return -EMSGSIZE; if (phydev->drv && nla_put_string(skb, ETHTOOL_A_PHY_DRVNAME, phydev->drv->name)) return -EMSGSIZE; if (ptype == PHY_UPSTREAM_PHY) { struct phy_device *upstream = pdn->upstream.phydev; const char *sfp_upstream_name; /* Parent index */ if (nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_INDEX, upstream->phyindex)) return -EMSGSIZE; if (pdn->parent_sfp_bus) { sfp_upstream_name = sfp_get_name(pdn->parent_sfp_bus); if (sfp_upstream_name && nla_put_string(skb, ETHTOOL_A_PHY_UPSTREAM_SFP_NAME, sfp_upstream_name)) return -EMSGSIZE; } } if (phydev->sfp_bus) { const char *sfp_name = sfp_get_name(phydev->sfp_bus); if (sfp_name && nla_put_string(skb, ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME, sfp_name)) return -EMSGSIZE; } return 0; } static int ethnl_phy_parse_request(struct ethnl_req_info *req_base, struct nlattr **tb, struct netlink_ext_ack *extack) { struct phy_link_topology *topo = req_base->dev->link_topo; struct phy_req_info *req_info = PHY_REQINFO(req_base); struct phy_device *phydev; phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PHY_HEADER], extack); if (!phydev) return 0; if (IS_ERR(phydev)) return PTR_ERR(phydev); if (!topo) return 0; req_info->pdn = xa_load(&topo->phys, phydev->phyindex); return 0; } int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info) { struct phy_req_info req_info = {}; struct nlattr **tb = info->attrs; struct sk_buff *rskb; void *reply_payload; int reply_len; int ret; ret = ethnl_parse_header_dev_get(&req_info.base, tb[ETHTOOL_A_PHY_HEADER], genl_info_net(info), info->extack, true); if (ret < 0) return ret; rtnl_lock(); ret = ethnl_phy_parse_request(&req_info.base, tb, info->extack); if (ret < 0) goto err_unlock_rtnl; /* No PHY, return early */ if (!req_info.pdn) goto err_unlock_rtnl; ret = ethnl_phy_reply_size(&req_info.base, info->extack); if (ret < 0) goto err_unlock_rtnl; reply_len = ret + ethnl_reply_header_size(); rskb = ethnl_reply_init(reply_len, req_info.base.dev, ETHTOOL_MSG_PHY_GET_REPLY, ETHTOOL_A_PHY_HEADER, info, &reply_payload); if (!rskb) { ret = -ENOMEM; goto err_unlock_rtnl; } ret = ethnl_phy_fill_reply(&req_info.base, rskb); if (ret) goto err_free_msg; rtnl_unlock(); ethnl_parse_header_dev_put(&req_info.base); genlmsg_end(rskb, reply_payload); return genlmsg_reply(rskb, info); err_free_msg: nlmsg_free(rskb); err_unlock_rtnl: rtnl_unlock(); ethnl_parse_header_dev_put(&req_info.base); return ret; } struct ethnl_phy_dump_ctx { struct phy_req_info *phy_req_info; unsigned long ifindex; unsigned long phy_index; }; int ethnl_phy_start(struct netlink_callback *cb) { const struct genl_info *info = genl_info_dump(cb); struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; int ret; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); ctx->phy_req_info = kzalloc(sizeof(*ctx->phy_req_info), GFP_KERNEL); if (!ctx->phy_req_info) return -ENOMEM; ret = ethnl_parse_header_dev_get(&ctx->phy_req_info->base, info->attrs[ETHTOOL_A_PHY_HEADER], sock_net(cb->skb->sk), cb->extack, false); ctx->ifindex = 0; ctx->phy_index = 0; if (ret) kfree(ctx->phy_req_info); return ret; } int ethnl_phy_done(struct netlink_callback *cb) { struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; if (ctx->phy_req_info->base.dev) ethnl_parse_header_dev_put(&ctx->phy_req_info->base); kfree(ctx->phy_req_info); return 0; } static int ethnl_phy_dump_one_dev(struct sk_buff *skb, struct net_device *dev, struct netlink_callback *cb) { struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; struct phy_req_info *pri = ctx->phy_req_info; struct phy_device_node *pdn; int ret = 0; void *ehdr; if (!dev->link_topo) return 0; xa_for_each_start(&dev->link_topo->phys, ctx->phy_index, pdn, ctx->phy_index) { ehdr = ethnl_dump_put(skb, cb, ETHTOOL_MSG_PHY_GET_REPLY); if (!ehdr) { ret = -EMSGSIZE; break; } ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_PHY_HEADER); if (ret < 0) { genlmsg_cancel(skb, ehdr); break; } pri->pdn = pdn; ret = ethnl_phy_fill_reply(&pri->base, skb); if (ret < 0) { genlmsg_cancel(skb, ehdr); break; } genlmsg_end(skb, ehdr); } return ret; } int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; struct net *net = sock_net(skb->sk); struct net_device *dev; int ret = 0; rtnl_lock(); if (ctx->phy_req_info->base.dev) { ret = ethnl_phy_dump_one_dev(skb, ctx->phy_req_info->base.dev, cb); } else { for_each_netdev_dump(net, dev, ctx->ifindex) { ret = ethnl_phy_dump_one_dev(skb, dev, cb); if (ret) break; ctx->phy_index = 0; } } rtnl_unlock(); return ret; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * win_minmax.h: windowed min/max tracker by Kathleen Nichols. * */ #ifndef MINMAX_H #define MINMAX_H #include <linux/types.h> /* A single data point for our parameterized min-max tracker */ struct minmax_sample { u32 t; /* time measurement was taken */ u32 v; /* value measured */ }; /* State for the parameterized min-max tracker */ struct minmax { struct minmax_sample s[3]; }; static inline u32 minmax_get(const struct minmax *m) { return m->s[0].v; } static inline u32 minmax_reset(struct minmax *m, u32 t, u32 meas) { struct minmax_sample val = { .t = t, .v = meas }; m->s[2] = m->s[1] = m->s[0] = val; return m->s[0].v; } u32 minmax_running_max(struct minmax *m, u32 win, u32 t, u32 meas); u32 minmax_running_min(struct minmax *m, u32 win, u32 t, u32 meas); #endif |
| 1 1 1 1 1 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved. */ #include <linux/skbuff.h> #include "rxe.h" #include "rxe_loc.h" #include "rxe_queue.h" static char *resp_state_name[] = { [RESPST_NONE] = "NONE", [RESPST_GET_REQ] = "GET_REQ", [RESPST_CHK_PSN] = "CHK_PSN", [RESPST_CHK_OP_SEQ] = "CHK_OP_SEQ", [RESPST_CHK_OP_VALID] = "CHK_OP_VALID", [RESPST_CHK_RESOURCE] = "CHK_RESOURCE", [RESPST_CHK_LENGTH] = "CHK_LENGTH", [RESPST_CHK_RKEY] = "CHK_RKEY", [RESPST_EXECUTE] = "EXECUTE", [RESPST_READ_REPLY] = "READ_REPLY", [RESPST_ATOMIC_REPLY] = "ATOMIC_REPLY", [RESPST_ATOMIC_WRITE_REPLY] = "ATOMIC_WRITE_REPLY", [RESPST_PROCESS_FLUSH] = "PROCESS_FLUSH", [RESPST_COMPLETE] = "COMPLETE", [RESPST_ACKNOWLEDGE] = "ACKNOWLEDGE", [RESPST_CLEANUP] = "CLEANUP", [RESPST_DUPLICATE_REQUEST] = "DUPLICATE_REQUEST", [RESPST_ERR_MALFORMED_WQE] = "ERR_MALFORMED_WQE", [RESPST_ERR_UNSUPPORTED_OPCODE] = "ERR_UNSUPPORTED_OPCODE", [RESPST_ERR_MISALIGNED_ATOMIC] = "ERR_MISALIGNED_ATOMIC", [RESPST_ERR_PSN_OUT_OF_SEQ] = "ERR_PSN_OUT_OF_SEQ", [RESPST_ERR_MISSING_OPCODE_FIRST] = "ERR_MISSING_OPCODE_FIRST", [RESPST_ERR_MISSING_OPCODE_LAST_C] = "ERR_MISSING_OPCODE_LAST_C", [RESPST_ERR_MISSING_OPCODE_LAST_D1E] = "ERR_MISSING_OPCODE_LAST_D1E", [RESPST_ERR_TOO_MANY_RDMA_ATM_REQ] = "ERR_TOO_MANY_RDMA_ATM_REQ", [RESPST_ERR_RNR] = "ERR_RNR", [RESPST_ERR_RKEY_VIOLATION] = "ERR_RKEY_VIOLATION", [RESPST_ERR_INVALIDATE_RKEY] = "ERR_INVALIDATE_RKEY_VIOLATION", [RESPST_ERR_LENGTH] = "ERR_LENGTH", [RESPST_ERR_CQ_OVERFLOW] = "ERR_CQ_OVERFLOW", [RESPST_ERROR] = "ERROR", [RESPST_DONE] = "DONE", [RESPST_EXIT] = "EXIT", }; /* rxe_recv calls here to add a request packet to the input queue */ void rxe_resp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb) { skb_queue_tail(&qp->req_pkts, skb); rxe_sched_task(&qp->recv_task); } static inline enum resp_states get_req(struct rxe_qp *qp, struct rxe_pkt_info **pkt_p) { struct sk_buff *skb; skb = skb_peek(&qp->req_pkts); if (!skb) return RESPST_EXIT; *pkt_p = SKB_TO_PKT(skb); return (qp->resp.res) ? RESPST_READ_REPLY : RESPST_CHK_PSN; } static enum resp_states check_psn(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { int diff = psn_compare(pkt->psn, qp->resp.psn); struct rxe_dev *rxe = to_rdev(qp->ibqp.device); switch (qp_type(qp)) { case IB_QPT_RC: if (diff > 0) { if (qp->resp.sent_psn_nak) return RESPST_CLEANUP; qp->resp.sent_psn_nak = 1; rxe_counter_inc(rxe, RXE_CNT_OUT_OF_SEQ_REQ); return RESPST_ERR_PSN_OUT_OF_SEQ; } else if (diff < 0) { rxe_counter_inc(rxe, RXE_CNT_DUP_REQ); return RESPST_DUPLICATE_REQUEST; } if (qp->resp.sent_psn_nak) qp->resp.sent_psn_nak = 0; break; case IB_QPT_UC: if (qp->resp.drop_msg || diff != 0) { if (pkt->mask & RXE_START_MASK) { qp->resp.drop_msg = 0; return RESPST_CHK_OP_SEQ; } qp->resp.drop_msg = 1; return RESPST_CLEANUP; } break; default: break; } return RESPST_CHK_OP_SEQ; } static enum resp_states check_op_seq(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { switch (qp_type(qp)) { case IB_QPT_RC: switch (qp->resp.opcode) { case IB_OPCODE_RC_SEND_FIRST: case IB_OPCODE_RC_SEND_MIDDLE: switch (pkt->opcode) { case IB_OPCODE_RC_SEND_MIDDLE: case IB_OPCODE_RC_SEND_LAST: case IB_OPCODE_RC_SEND_LAST_WITH_IMMEDIATE: case IB_OPCODE_RC_SEND_LAST_WITH_INVALIDATE: return RESPST_CHK_OP_VALID; default: return RESPST_ERR_MISSING_OPCODE_LAST_C; } case IB_OPCODE_RC_RDMA_WRITE_FIRST: case IB_OPCODE_RC_RDMA_WRITE_MIDDLE: switch (pkt->opcode) { case IB_OPCODE_RC_RDMA_WRITE_MIDDLE: case IB_OPCODE_RC_RDMA_WRITE_LAST: case IB_OPCODE_RC_RDMA_WRITE_LAST_WITH_IMMEDIATE: return RESPST_CHK_OP_VALID; default: return RESPST_ERR_MISSING_OPCODE_LAST_C; } default: switch (pkt->opcode) { case IB_OPCODE_RC_SEND_MIDDLE: case IB_OPCODE_RC_SEND_LAST: case IB_OPCODE_RC_SEND_LAST_WITH_IMMEDIATE: case IB_OPCODE_RC_SEND_LAST_WITH_INVALIDATE: case IB_OPCODE_RC_RDMA_WRITE_MIDDLE: case IB_OPCODE_RC_RDMA_WRITE_LAST: case IB_OPCODE_RC_RDMA_WRITE_LAST_WITH_IMMEDIATE: return RESPST_ERR_MISSING_OPCODE_FIRST; default: return RESPST_CHK_OP_VALID; } } break; case IB_QPT_UC: switch (qp->resp.opcode) { case IB_OPCODE_UC_SEND_FIRST: case IB_OPCODE_UC_SEND_MIDDLE: switch (pkt->opcode) { case IB_OPCODE_UC_SEND_MIDDLE: case IB_OPCODE_UC_SEND_LAST: case IB_OPCODE_UC_SEND_LAST_WITH_IMMEDIATE: return RESPST_CHK_OP_VALID; default: return RESPST_ERR_MISSING_OPCODE_LAST_D1E; } case IB_OPCODE_UC_RDMA_WRITE_FIRST: case IB_OPCODE_UC_RDMA_WRITE_MIDDLE: switch (pkt->opcode) { case IB_OPCODE_UC_RDMA_WRITE_MIDDLE: case IB_OPCODE_UC_RDMA_WRITE_LAST: case IB_OPCODE_UC_RDMA_WRITE_LAST_WITH_IMMEDIATE: return RESPST_CHK_OP_VALID; default: return RESPST_ERR_MISSING_OPCODE_LAST_D1E; } default: switch (pkt->opcode) { case IB_OPCODE_UC_SEND_MIDDLE: case IB_OPCODE_UC_SEND_LAST: case IB_OPCODE_UC_SEND_LAST_WITH_IMMEDIATE: case IB_OPCODE_UC_RDMA_WRITE_MIDDLE: case IB_OPCODE_UC_RDMA_WRITE_LAST: case IB_OPCODE_UC_RDMA_WRITE_LAST_WITH_IMMEDIATE: qp->resp.drop_msg = 1; return RESPST_CLEANUP; default: return RESPST_CHK_OP_VALID; } } break; default: return RESPST_CHK_OP_VALID; } } static bool check_qp_attr_access(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { if (((pkt->mask & RXE_READ_MASK) && !(qp->attr.qp_access_flags & IB_ACCESS_REMOTE_READ)) || ((pkt->mask & (RXE_WRITE_MASK | RXE_ATOMIC_WRITE_MASK)) && !(qp->attr.qp_access_flags & IB_ACCESS_REMOTE_WRITE)) || ((pkt->mask & RXE_ATOMIC_MASK) && !(qp->attr.qp_access_flags & IB_ACCESS_REMOTE_ATOMIC))) return false; if (pkt->mask & RXE_FLUSH_MASK) { u32 flush_type = feth_plt(pkt); if ((flush_type & IB_FLUSH_GLOBAL && !(qp->attr.qp_access_flags & IB_ACCESS_FLUSH_GLOBAL)) || (flush_type & IB_FLUSH_PERSISTENT && !(qp->attr.qp_access_flags & IB_ACCESS_FLUSH_PERSISTENT))) return false; } return true; } static enum resp_states check_op_valid(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { switch (qp_type(qp)) { case IB_QPT_RC: if (!check_qp_attr_access(qp, pkt)) return RESPST_ERR_UNSUPPORTED_OPCODE; break; case IB_QPT_UC: if ((pkt->mask & RXE_WRITE_MASK) && !(qp->attr.qp_access_flags & IB_ACCESS_REMOTE_WRITE)) { qp->resp.drop_msg = 1; return RESPST_CLEANUP; } break; case IB_QPT_UD: case IB_QPT_GSI: break; default: WARN_ON_ONCE(1); break; } return RESPST_CHK_RESOURCE; } static enum resp_states get_srq_wqe(struct rxe_qp *qp) { struct rxe_srq *srq = qp->srq; struct rxe_queue *q = srq->rq.queue; struct rxe_recv_wqe *wqe; struct ib_event ev; unsigned int count; size_t size; unsigned long flags; if (srq->error) return RESPST_ERR_RNR; spin_lock_irqsave(&srq->rq.consumer_lock, flags); wqe = queue_head(q, QUEUE_TYPE_FROM_CLIENT); if (!wqe) { spin_unlock_irqrestore(&srq->rq.consumer_lock, flags); return RESPST_ERR_RNR; } /* don't trust user space data */ if (unlikely(wqe->dma.num_sge > srq->rq.max_sge)) { spin_unlock_irqrestore(&srq->rq.consumer_lock, flags); rxe_dbg_qp(qp, "invalid num_sge in SRQ entry\n"); return RESPST_ERR_MALFORMED_WQE; } size = sizeof(*wqe) + wqe->dma.num_sge*sizeof(struct rxe_sge); memcpy(&qp->resp.srq_wqe, wqe, size); qp->resp.wqe = &qp->resp.srq_wqe.wqe; queue_advance_consumer(q, QUEUE_TYPE_FROM_CLIENT); count = queue_count(q, QUEUE_TYPE_FROM_CLIENT); if (srq->limit && srq->ibsrq.event_handler && (count < srq->limit)) { srq->limit = 0; goto event; } spin_unlock_irqrestore(&srq->rq.consumer_lock, flags); return RESPST_CHK_LENGTH; event: spin_unlock_irqrestore(&srq->rq.consumer_lock, flags); ev.device = qp->ibqp.device; ev.element.srq = qp->ibqp.srq; ev.event = IB_EVENT_SRQ_LIMIT_REACHED; srq->ibsrq.event_handler(&ev, srq->ibsrq.srq_context); return RESPST_CHK_LENGTH; } static enum resp_states check_resource(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { struct rxe_srq *srq = qp->srq; if (pkt->mask & (RXE_READ_OR_ATOMIC_MASK | RXE_ATOMIC_WRITE_MASK)) { /* it is the requesters job to not send * too many read/atomic ops, we just * recycle the responder resource queue */ if (likely(qp->attr.max_dest_rd_atomic > 0)) return RESPST_CHK_LENGTH; else return RESPST_ERR_TOO_MANY_RDMA_ATM_REQ; } if (pkt->mask & RXE_RWR_MASK) { if (srq) return get_srq_wqe(qp); qp->resp.wqe = queue_head(qp->rq.queue, QUEUE_TYPE_FROM_CLIENT); return (qp->resp.wqe) ? RESPST_CHK_LENGTH : RESPST_ERR_RNR; } return RESPST_CHK_LENGTH; } static enum resp_states rxe_resp_check_length(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { /* * See IBA C9-92 * For UD QPs we only check if the packet will fit in the * receive buffer later. For RDMA operations additional * length checks are performed in check_rkey. */ if ((qp_type(qp) == IB_QPT_GSI) || (qp_type(qp) == IB_QPT_UD)) { unsigned int payload = payload_size(pkt); unsigned int recv_buffer_len = 0; int i; for (i = 0; i < qp->resp.wqe->dma.num_sge; i++) recv_buffer_len += qp->resp.wqe->dma.sge[i].length; if (payload + sizeof(union rdma_network_hdr) > recv_buffer_len) { rxe_dbg_qp(qp, "The receive buffer is too small for this UD packet.\n"); return RESPST_ERR_LENGTH; } } if (pkt->mask & RXE_PAYLOAD_MASK && ((qp_type(qp) == IB_QPT_RC) || (qp_type(qp) == IB_QPT_UC))) { unsigned int mtu = qp->mtu; unsigned int payload = payload_size(pkt); if ((pkt->mask & RXE_START_MASK) && (pkt->mask & RXE_END_MASK)) { if (unlikely(payload > mtu)) { rxe_dbg_qp(qp, "only packet too long\n"); return RESPST_ERR_LENGTH; } } else if ((pkt->mask & RXE_START_MASK) || (pkt->mask & RXE_MIDDLE_MASK)) { if (unlikely(payload != mtu)) { rxe_dbg_qp(qp, "first or middle packet not mtu\n"); return RESPST_ERR_LENGTH; } } else if (pkt->mask & RXE_END_MASK) { if (unlikely((payload == 0) || (payload > mtu))) { rxe_dbg_qp(qp, "last packet zero or too long\n"); return RESPST_ERR_LENGTH; } } } /* See IBA C9-94 */ if (pkt->mask & RXE_RETH_MASK) { if (reth_len(pkt) > (1U << 31)) { rxe_dbg_qp(qp, "dma length too long\n"); return RESPST_ERR_LENGTH; } } if (pkt->mask & RXE_RDMA_OP_MASK) return RESPST_CHK_RKEY; else return RESPST_EXECUTE; } /* if the reth length field is zero we can assume nothing * about the rkey value and should not validate or use it. * Instead set qp->resp.rkey to 0 which is an invalid rkey * value since the minimum index part is 1. */ static void qp_resp_from_reth(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { unsigned int length = reth_len(pkt); qp->resp.va = reth_va(pkt); qp->resp.offset = 0; qp->resp.resid = length; qp->resp.length = length; if (pkt->mask & RXE_READ_OR_WRITE_MASK && length == 0) qp->resp.rkey = 0; else qp->resp.rkey = reth_rkey(pkt); } static void qp_resp_from_atmeth(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { qp->resp.va = atmeth_va(pkt); qp->resp.offset = 0; qp->resp.rkey = atmeth_rkey(pkt); qp->resp.resid = sizeof(u64); } /* resolve the packet rkey to qp->resp.mr or set qp->resp.mr to NULL * if an invalid rkey is received or the rdma length is zero. For middle * or last packets use the stored value of mr. */ static enum resp_states check_rkey(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { struct rxe_mr *mr = NULL; struct rxe_mw *mw = NULL; u64 va; u32 rkey; u32 resid; u32 pktlen; int mtu = qp->mtu; enum resp_states state; int access = 0; /* parse RETH or ATMETH header for first/only packets * for va, length, rkey, etc. or use current value for * middle/last packets. */ if (pkt->mask & (RXE_READ_OR_WRITE_MASK | RXE_ATOMIC_WRITE_MASK)) { if (pkt->mask & RXE_RETH_MASK) qp_resp_from_reth(qp, pkt); access = (pkt->mask & RXE_READ_MASK) ? IB_ACCESS_REMOTE_READ : IB_ACCESS_REMOTE_WRITE; } else if (pkt->mask & RXE_FLUSH_MASK) { u32 flush_type = feth_plt(pkt); if (pkt->mask & RXE_RETH_MASK) qp_resp_from_reth(qp, pkt); if (flush_type & IB_FLUSH_GLOBAL) access |= IB_ACCESS_FLUSH_GLOBAL; if (flush_type & IB_FLUSH_PERSISTENT) access |= IB_ACCESS_FLUSH_PERSISTENT; } else if (pkt->mask & RXE_ATOMIC_MASK) { qp_resp_from_atmeth(qp, pkt); access = IB_ACCESS_REMOTE_ATOMIC; } else { /* shouldn't happen */ WARN_ON(1); } /* A zero-byte read or write op is not required to * set an addr or rkey. See C9-88 */ if ((pkt->mask & RXE_READ_OR_WRITE_MASK) && (pkt->mask & RXE_RETH_MASK) && reth_len(pkt) == 0) { qp->resp.mr = NULL; return RESPST_EXECUTE; } va = qp->resp.va; rkey = qp->resp.rkey; resid = qp->resp.resid; pktlen = payload_size(pkt); if (rkey_is_mw(rkey)) { mw = rxe_lookup_mw(qp, access, rkey); if (!mw) { rxe_dbg_qp(qp, "no MW matches rkey %#x\n", rkey); state = RESPST_ERR_RKEY_VIOLATION; goto err; } mr = mw->mr; if (!mr) { rxe_dbg_qp(qp, "MW doesn't have an MR\n"); state = RESPST_ERR_RKEY_VIOLATION; goto err; } if (mw->access & IB_ZERO_BASED) qp->resp.offset = mw->addr; rxe_get(mr); rxe_put(mw); mw = NULL; } else { mr = lookup_mr(qp->pd, access, rkey, RXE_LOOKUP_REMOTE); if (!mr) { rxe_dbg_qp(qp, "no MR matches rkey %#x\n", rkey); state = RESPST_ERR_RKEY_VIOLATION; goto err; } } if (pkt->mask & RXE_FLUSH_MASK) { /* FLUSH MR may not set va or resid * no need to check range since we will flush whole mr */ if (feth_sel(pkt) == IB_FLUSH_MR) goto skip_check_range; } if (mr_check_range(mr, va + qp->resp.offset, resid)) { state = RESPST_ERR_RKEY_VIOLATION; goto err; } skip_check_range: if (pkt->mask & (RXE_WRITE_MASK | RXE_ATOMIC_WRITE_MASK)) { if (resid > mtu) { if (pktlen != mtu || bth_pad(pkt)) { state = RESPST_ERR_LENGTH; goto err; } } else { if (pktlen != resid) { state = RESPST_ERR_LENGTH; goto err; } if ((bth_pad(pkt) != (0x3 & (-resid)))) { /* This case may not be exactly that * but nothing else fits. */ state = RESPST_ERR_LENGTH; goto err; } } } WARN_ON_ONCE(qp->resp.mr); qp->resp.mr = mr; return RESPST_EXECUTE; err: qp->resp.mr = NULL; if (mr) rxe_put(mr); if (mw) rxe_put(mw); return state; } static enum resp_states send_data_in(struct rxe_qp *qp, void *data_addr, int data_len) { int err; err = copy_data(qp->pd, IB_ACCESS_LOCAL_WRITE, &qp->resp.wqe->dma, data_addr, data_len, RXE_TO_MR_OBJ); if (unlikely(err)) return (err == -ENOSPC) ? RESPST_ERR_LENGTH : RESPST_ERR_MALFORMED_WQE; return RESPST_NONE; } static enum resp_states write_data_in(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { enum resp_states rc = RESPST_NONE; int err; int data_len = payload_size(pkt); err = rxe_mr_copy(qp->resp.mr, qp->resp.va + qp->resp.offset, payload_addr(pkt), data_len, RXE_TO_MR_OBJ); if (err) { rc = RESPST_ERR_RKEY_VIOLATION; goto out; } qp->resp.va += data_len; qp->resp.resid -= data_len; out: return rc; } static struct resp_res *rxe_prepare_res(struct rxe_qp *qp, struct rxe_pkt_info *pkt, int type) { struct resp_res *res; u32 pkts; res = &qp->resp.resources[qp->resp.res_head]; rxe_advance_resp_resource(qp); free_rd_atomic_resource(res); res->type = type; res->replay = 0; switch (type) { case RXE_READ_MASK: res->read.va = qp->resp.va + qp->resp.offset; res->read.va_org = qp->resp.va + qp->resp.offset; res->read.resid = qp->resp.resid; res->read.length = qp->resp.resid; res->read.rkey = qp->resp.rkey; pkts = max_t(u32, (reth_len(pkt) + qp->mtu - 1)/qp->mtu, 1); res->first_psn = pkt->psn; res->cur_psn = pkt->psn; res->last_psn = (pkt->psn + pkts - 1) & BTH_PSN_MASK; res->state = rdatm_res_state_new; break; case RXE_ATOMIC_MASK: case RXE_ATOMIC_WRITE_MASK: res->first_psn = pkt->psn; res->last_psn = pkt->psn; res->cur_psn = pkt->psn; break; case RXE_FLUSH_MASK: res->flush.va = qp->resp.va + qp->resp.offset; res->flush.length = qp->resp.length; res->flush.type = feth_plt(pkt); res->flush.level = feth_sel(pkt); } return res; } static enum resp_states process_flush(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { u64 length, start; struct rxe_mr *mr = qp->resp.mr; struct resp_res *res = qp->resp.res; /* oA19-14, oA19-15 */ if (res && res->replay) return RESPST_ACKNOWLEDGE; else if (!res) { res = rxe_prepare_res(qp, pkt, RXE_FLUSH_MASK); qp->resp.res = res; } if (res->flush.level == IB_FLUSH_RANGE) { start = res->flush.va; length = res->flush.length; } else { /* level == IB_FLUSH_MR */ start = mr->ibmr.iova; length = mr->ibmr.length; } if (res->flush.type & IB_FLUSH_PERSISTENT) { if (rxe_flush_pmem_iova(mr, start, length)) return RESPST_ERR_RKEY_VIOLATION; /* Make data persistent. */ wmb(); } else if (res->flush.type & IB_FLUSH_GLOBAL) { /* Make data global visibility. */ wmb(); } qp->resp.msn++; /* next expected psn, read handles this separately */ qp->resp.psn = (pkt->psn + 1) & BTH_PSN_MASK; qp->resp.ack_psn = qp->resp.psn; qp->resp.opcode = pkt->opcode; qp->resp.status = IB_WC_SUCCESS; return RESPST_ACKNOWLEDGE; } static enum resp_states atomic_reply(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { struct rxe_mr *mr = qp->resp.mr; struct resp_res *res = qp->resp.res; int err; if (!res) { res = rxe_prepare_res(qp, pkt, RXE_ATOMIC_MASK); qp->resp.res = res; } if (!res->replay) { u64 iova = qp->resp.va + qp->resp.offset; err = rxe_mr_do_atomic_op(mr, iova, pkt->opcode, atmeth_comp(pkt), atmeth_swap_add(pkt), &res->atomic.orig_val); if (err) return err; qp->resp.msn++; /* next expected psn, read handles this separately */ qp->resp.psn = (pkt->psn + 1) & BTH_PSN_MASK; qp->resp.ack_psn = qp->resp.psn; qp->resp.opcode = pkt->opcode; qp->resp.status = IB_WC_SUCCESS; } return RESPST_ACKNOWLEDGE; } static enum resp_states atomic_write_reply(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { struct resp_res *res = qp->resp.res; struct rxe_mr *mr; u64 value; u64 iova; int err; if (!res) { res = rxe_prepare_res(qp, pkt, RXE_ATOMIC_WRITE_MASK); qp->resp.res = res; } if (res->replay) return RESPST_ACKNOWLEDGE; mr = qp->resp.mr; value = *(u64 *)payload_addr(pkt); iova = qp->resp.va + qp->resp.offset; err = rxe_mr_do_atomic_write(mr, iova, value); if (err) return err; qp->resp.resid = 0; qp->resp.msn++; /* next expected psn, read handles this separately */ qp->resp.psn = (pkt->psn + 1) & BTH_PSN_MASK; qp->resp.ack_psn = qp->resp.psn; qp->resp.opcode = pkt->opcode; qp->resp.status = IB_WC_SUCCESS; return RESPST_ACKNOWLEDGE; } static struct sk_buff *prepare_ack_packet(struct rxe_qp *qp, struct rxe_pkt_info *ack, int opcode, int payload, u32 psn, u8 syndrome) { struct rxe_dev *rxe = to_rdev(qp->ibqp.device); struct sk_buff *skb; int paylen; int pad; int err; /* * allocate packet */ pad = (-payload) & 0x3; paylen = rxe_opcode[opcode].length + payload + pad + RXE_ICRC_SIZE; skb = rxe_init_packet(rxe, &qp->pri_av, paylen, ack); if (!skb) return NULL; ack->qp = qp; ack->opcode = opcode; ack->mask = rxe_opcode[opcode].mask; ack->paylen = paylen; ack->psn = psn; bth_init(ack, opcode, 0, 0, pad, IB_DEFAULT_PKEY_FULL, qp->attr.dest_qp_num, 0, psn); if (ack->mask & RXE_AETH_MASK) { aeth_set_syn(ack, syndrome); aeth_set_msn(ack, qp->resp.msn); } if (ack->mask & RXE_ATMACK_MASK) atmack_set_orig(ack, qp->resp.res->atomic.orig_val); err = rxe_prepare(&qp->pri_av, ack, skb); if (err) { kfree_skb(skb); return NULL; } return skb; } /** * rxe_recheck_mr - revalidate MR from rkey and get a reference * @qp: the qp * @rkey: the rkey * * This code allows the MR to be invalidated or deregistered or * the MW if one was used to be invalidated or deallocated. * It is assumed that the access permissions if originally good * are OK and the mappings to be unchanged. * * TODO: If someone reregisters an MR to change its size or * access permissions during the processing of an RDMA read * we should kill the responder resource and complete the * operation with an error. * * Return: mr on success else NULL */ static struct rxe_mr *rxe_recheck_mr(struct rxe_qp *qp, u32 rkey) { struct rxe_dev *rxe = to_rdev(qp->ibqp.device); struct rxe_mr *mr; struct rxe_mw *mw; if (rkey_is_mw(rkey)) { mw = rxe_pool_get_index(&rxe->mw_pool, rkey >> 8); if (!mw) return NULL; mr = mw->mr; if (mw->rkey != rkey || mw->state != RXE_MW_STATE_VALID || !mr || mr->state != RXE_MR_STATE_VALID) { rxe_put(mw); return NULL; } rxe_get(mr); rxe_put(mw); return mr; } mr = rxe_pool_get_index(&rxe->mr_pool, rkey >> 8); if (!mr) return NULL; if (mr->rkey != rkey || mr->state != RXE_MR_STATE_VALID) { rxe_put(mr); return NULL; } return mr; } /* RDMA read response. If res is not NULL, then we have a current RDMA request * being processed or replayed. */ static enum resp_states read_reply(struct rxe_qp *qp, struct rxe_pkt_info *req_pkt) { struct rxe_pkt_info ack_pkt; struct sk_buff *skb; int mtu = qp->mtu; enum resp_states state; int payload; int opcode; int err; struct resp_res *res = qp->resp.res; struct rxe_mr *mr; if (!res) { res = rxe_prepare_res(qp, req_pkt, RXE_READ_MASK); qp->resp.res = res; } if (res->state == rdatm_res_state_new) { if (!res->replay || qp->resp.length == 0) { /* if length == 0 mr will be NULL (is ok) * otherwise qp->resp.mr holds a ref on mr * which we transfer to mr and drop below. */ mr = qp->resp.mr; qp->resp.mr = NULL; } else { mr = rxe_recheck_mr(qp, res->read.rkey); if (!mr) return RESPST_ERR_RKEY_VIOLATION; } if (res->read.resid <= mtu) opcode = IB_OPCODE_RC_RDMA_READ_RESPONSE_ONLY; else opcode = IB_OPCODE_RC_RDMA_READ_RESPONSE_FIRST; } else { /* re-lookup mr from rkey on all later packets. * length will be non-zero. This can fail if someone * modifies or destroys the mr since the first packet. */ mr = rxe_recheck_mr(qp, res->read.rkey); if (!mr) return RESPST_ERR_RKEY_VIOLATION; if (res->read.resid > mtu) opcode = IB_OPCODE_RC_RDMA_READ_RESPONSE_MIDDLE; else opcode = IB_OPCODE_RC_RDMA_READ_RESPONSE_LAST; } res->state = rdatm_res_state_next; payload = min_t(int, res->read.resid, mtu); skb = prepare_ack_packet(qp, &ack_pkt, opcode, payload, res->cur_psn, AETH_ACK_UNLIMITED); if (!skb) { state = RESPST_ERR_RNR; goto err_out; } err = rxe_mr_copy(mr, res->read.va, payload_addr(&ack_pkt), payload, RXE_FROM_MR_OBJ); if (err) { kfree_skb(skb); state = RESPST_ERR_RKEY_VIOLATION; goto err_out; } if (bth_pad(&ack_pkt)) { u8 *pad = payload_addr(&ack_pkt) + payload; memset(pad, 0, bth_pad(&ack_pkt)); } /* rxe_xmit_packet always consumes the skb */ err = rxe_xmit_packet(qp, &ack_pkt, skb); if (err) { state = RESPST_ERR_RNR; goto err_out; } res->read.va += payload; res->read.resid -= payload; res->cur_psn = (res->cur_psn + 1) & BTH_PSN_MASK; if (res->read.resid > 0) { state = RESPST_DONE; } else { qp->resp.res = NULL; if (!res->replay) qp->resp.opcode = -1; if (psn_compare(res->cur_psn, qp->resp.psn) >= 0) qp->resp.psn = res->cur_psn; state = RESPST_CLEANUP; } err_out: if (mr) rxe_put(mr); return state; } static int invalidate_rkey(struct rxe_qp *qp, u32 rkey) { if (rkey_is_mw(rkey)) return rxe_invalidate_mw(qp, rkey); else return rxe_invalidate_mr(qp, rkey); } /* Executes a new request. A retried request never reach that function (send * and writes are discarded, and reads and atomics are retried elsewhere. */ static enum resp_states execute(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { enum resp_states err; struct sk_buff *skb = PKT_TO_SKB(pkt); union rdma_network_hdr hdr; if (pkt->mask & RXE_SEND_MASK) { if (qp_type(qp) == IB_QPT_UD || qp_type(qp) == IB_QPT_GSI) { if (skb->protocol == htons(ETH_P_IP)) { memset(&hdr.reserved, 0, sizeof(hdr.reserved)); memcpy(&hdr.roce4grh, ip_hdr(skb), sizeof(hdr.roce4grh)); err = send_data_in(qp, &hdr, sizeof(hdr)); } else { err = send_data_in(qp, ipv6_hdr(skb), sizeof(hdr)); } if (err) return err; } err = send_data_in(qp, payload_addr(pkt), payload_size(pkt)); if (err) return err; } else if (pkt->mask & RXE_WRITE_MASK) { err = write_data_in(qp, pkt); if (err) return err; } else if (pkt->mask & RXE_READ_MASK) { /* For RDMA Read we can increment the msn now. See C9-148. */ qp->resp.msn++; return RESPST_READ_REPLY; } else if (pkt->mask & RXE_ATOMIC_MASK) { return RESPST_ATOMIC_REPLY; } else if (pkt->mask & RXE_ATOMIC_WRITE_MASK) { return RESPST_ATOMIC_WRITE_REPLY; } else if (pkt->mask & RXE_FLUSH_MASK) { return RESPST_PROCESS_FLUSH; } else { /* Unreachable */ WARN_ON_ONCE(1); } if (pkt->mask & RXE_IETH_MASK) { u32 rkey = ieth_rkey(pkt); err = invalidate_rkey(qp, rkey); if (err) return RESPST_ERR_INVALIDATE_RKEY; } if (pkt->mask & RXE_END_MASK) /* We successfully processed this new request. */ qp->resp.msn++; /* next expected psn, read handles this separately */ qp->resp.psn = (pkt->psn + 1) & BTH_PSN_MASK; qp->resp.ack_psn = qp->resp.psn; qp->resp.opcode = pkt->opcode; qp->resp.status = IB_WC_SUCCESS; if (pkt->mask & RXE_COMP_MASK) return RESPST_COMPLETE; else if (qp_type(qp) == IB_QPT_RC) return RESPST_ACKNOWLEDGE; else return RESPST_CLEANUP; } static enum resp_states do_complete(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { struct rxe_cqe cqe; struct ib_wc *wc = &cqe.ibwc; struct ib_uverbs_wc *uwc = &cqe.uibwc; struct rxe_recv_wqe *wqe = qp->resp.wqe; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); unsigned long flags; if (!wqe) goto finish; memset(&cqe, 0, sizeof(cqe)); if (qp->rcq->is_user) { uwc->status = qp->resp.status; uwc->qp_num = qp->ibqp.qp_num; uwc->wr_id = wqe->wr_id; } else { wc->status = qp->resp.status; wc->qp = &qp->ibqp; wc->wr_id = wqe->wr_id; } if (wc->status == IB_WC_SUCCESS) { rxe_counter_inc(rxe, RXE_CNT_RDMA_RECV); wc->opcode = (pkt->mask & RXE_IMMDT_MASK && pkt->mask & RXE_WRITE_MASK) ? IB_WC_RECV_RDMA_WITH_IMM : IB_WC_RECV; wc->byte_len = (pkt->mask & RXE_IMMDT_MASK && pkt->mask & RXE_WRITE_MASK) ? qp->resp.length : wqe->dma.length - wqe->dma.resid; /* fields after byte_len are different between kernel and user * space */ if (qp->rcq->is_user) { uwc->wc_flags = IB_WC_GRH; if (pkt->mask & RXE_IMMDT_MASK) { uwc->wc_flags |= IB_WC_WITH_IMM; uwc->ex.imm_data = immdt_imm(pkt); } if (pkt->mask & RXE_IETH_MASK) { uwc->wc_flags |= IB_WC_WITH_INVALIDATE; uwc->ex.invalidate_rkey = ieth_rkey(pkt); } if (pkt->mask & RXE_DETH_MASK) uwc->src_qp = deth_sqp(pkt); uwc->port_num = qp->attr.port_num; } else { struct sk_buff *skb = PKT_TO_SKB(pkt); wc->wc_flags = IB_WC_GRH | IB_WC_WITH_NETWORK_HDR_TYPE; if (skb->protocol == htons(ETH_P_IP)) wc->network_hdr_type = RDMA_NETWORK_IPV4; else wc->network_hdr_type = RDMA_NETWORK_IPV6; if (is_vlan_dev(skb->dev)) { wc->wc_flags |= IB_WC_WITH_VLAN; wc->vlan_id = vlan_dev_vlan_id(skb->dev); } if (pkt->mask & RXE_IMMDT_MASK) { wc->wc_flags |= IB_WC_WITH_IMM; wc->ex.imm_data = immdt_imm(pkt); } if (pkt->mask & RXE_IETH_MASK) { wc->wc_flags |= IB_WC_WITH_INVALIDATE; wc->ex.invalidate_rkey = ieth_rkey(pkt); } if (pkt->mask & RXE_DETH_MASK) wc->src_qp = deth_sqp(pkt); wc->port_num = qp->attr.port_num; } } else { if (wc->status != IB_WC_WR_FLUSH_ERR) rxe_err_qp(qp, "non-flush error status = %d\n", wc->status); } /* have copy for srq and reference for !srq */ if (!qp->srq) queue_advance_consumer(qp->rq.queue, QUEUE_TYPE_FROM_CLIENT); qp->resp.wqe = NULL; if (rxe_cq_post(qp->rcq, &cqe, pkt ? bth_se(pkt) : 1)) return RESPST_ERR_CQ_OVERFLOW; finish: spin_lock_irqsave(&qp->state_lock, flags); if (unlikely(qp_state(qp) == IB_QPS_ERR)) { spin_unlock_irqrestore(&qp->state_lock, flags); return RESPST_CHK_RESOURCE; } spin_unlock_irqrestore(&qp->state_lock, flags); if (unlikely(!pkt)) return RESPST_DONE; if (qp_type(qp) == IB_QPT_RC) return RESPST_ACKNOWLEDGE; else return RESPST_CLEANUP; } static int send_common_ack(struct rxe_qp *qp, u8 syndrome, u32 psn, int opcode, const char *msg) { int err; struct rxe_pkt_info ack_pkt; struct sk_buff *skb; skb = prepare_ack_packet(qp, &ack_pkt, opcode, 0, psn, syndrome); if (!skb) return -ENOMEM; err = rxe_xmit_packet(qp, &ack_pkt, skb); if (err) rxe_dbg_qp(qp, "Failed sending %s\n", msg); return err; } static int send_ack(struct rxe_qp *qp, u8 syndrome, u32 psn) { return send_common_ack(qp, syndrome, psn, IB_OPCODE_RC_ACKNOWLEDGE, "ACK"); } static int send_atomic_ack(struct rxe_qp *qp, u8 syndrome, u32 psn) { int ret = send_common_ack(qp, syndrome, psn, IB_OPCODE_RC_ATOMIC_ACKNOWLEDGE, "ATOMIC ACK"); /* have to clear this since it is used to trigger * long read replies */ qp->resp.res = NULL; return ret; } static int send_read_response_ack(struct rxe_qp *qp, u8 syndrome, u32 psn) { int ret = send_common_ack(qp, syndrome, psn, IB_OPCODE_RC_RDMA_READ_RESPONSE_ONLY, "RDMA READ response of length zero ACK"); /* have to clear this since it is used to trigger * long read replies */ qp->resp.res = NULL; return ret; } static enum resp_states acknowledge(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { if (qp_type(qp) != IB_QPT_RC) return RESPST_CLEANUP; if (qp->resp.aeth_syndrome != AETH_ACK_UNLIMITED) send_ack(qp, qp->resp.aeth_syndrome, pkt->psn); else if (pkt->mask & RXE_ATOMIC_MASK) send_atomic_ack(qp, AETH_ACK_UNLIMITED, pkt->psn); else if (pkt->mask & (RXE_FLUSH_MASK | RXE_ATOMIC_WRITE_MASK)) send_read_response_ack(qp, AETH_ACK_UNLIMITED, pkt->psn); else if (bth_ack(pkt)) send_ack(qp, AETH_ACK_UNLIMITED, pkt->psn); return RESPST_CLEANUP; } static enum resp_states cleanup(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { struct sk_buff *skb; if (pkt) { skb = skb_dequeue(&qp->req_pkts); rxe_put(qp); kfree_skb(skb); ib_device_put(qp->ibqp.device); } if (qp->resp.mr) { rxe_put(qp->resp.mr); qp->resp.mr = NULL; } return RESPST_DONE; } static struct resp_res *find_resource(struct rxe_qp *qp, u32 psn) { int i; for (i = 0; i < qp->attr.max_dest_rd_atomic; i++) { struct resp_res *res = &qp->resp.resources[i]; if (res->type == 0) continue; if (psn_compare(psn, res->first_psn) >= 0 && psn_compare(psn, res->last_psn) <= 0) { return res; } } return NULL; } static enum resp_states duplicate_request(struct rxe_qp *qp, struct rxe_pkt_info *pkt) { enum resp_states rc; u32 prev_psn = (qp->resp.ack_psn - 1) & BTH_PSN_MASK; if (pkt->mask & RXE_SEND_MASK || pkt->mask & RXE_WRITE_MASK) { /* SEND. Ack again and cleanup. C9-105. */ send_ack(qp, AETH_ACK_UNLIMITED, prev_psn); return RESPST_CLEANUP; } else if (pkt->mask & RXE_FLUSH_MASK) { struct resp_res *res; /* Find the operation in our list of responder resources. */ res = find_resource(qp, pkt->psn); if (res) { res->replay = 1; res->cur_psn = pkt->psn; qp->resp.res = res; rc = RESPST_PROCESS_FLUSH; goto out; } /* Resource not found. Class D error. Drop the request. */ rc = RESPST_CLEANUP; goto out; } else if (pkt->mask & RXE_READ_MASK) { struct resp_res *res; res = find_resource(qp, pkt->psn); if (!res) { /* Resource not found. Class D error. Drop the * request. */ rc = RESPST_CLEANUP; goto out; } else { /* Ensure this new request is the same as the previous * one or a subset of it. */ u64 iova = reth_va(pkt); u32 resid = reth_len(pkt); if (iova < res->read.va_org || resid > res->read.length || (iova + resid) > (res->read.va_org + res->read.length)) { rc = RESPST_CLEANUP; goto out; } if (reth_rkey(pkt) != res->read.rkey) { rc = RESPST_CLEANUP; goto out; } res->cur_psn = pkt->psn; res->state = (pkt->psn == res->first_psn) ? rdatm_res_state_new : rdatm_res_state_replay; res->replay = 1; /* Reset the resource, except length. */ res->read.va_org = iova; res->read.va = iova; res->read.resid = resid; /* Replay the RDMA read reply. */ qp->resp.res = res; rc = RESPST_READ_REPLY; goto out; } } else { struct resp_res *res; /* Find the operation in our list of responder resources. */ res = find_resource(qp, pkt->psn); if (res) { res->replay = 1; res->cur_psn = pkt->psn; qp->resp.res = res; rc = pkt->mask & RXE_ATOMIC_MASK ? RESPST_ATOMIC_REPLY : RESPST_ATOMIC_WRITE_REPLY; goto out; } /* Resource not found. Class D error. Drop the request. */ rc = RESPST_CLEANUP; goto out; } out: return rc; } /* Process a class A or C. Both are treated the same in this implementation. */ static void do_class_ac_error(struct rxe_qp *qp, u8 syndrome, enum ib_wc_status status) { qp->resp.aeth_syndrome = syndrome; qp->resp.status = status; /* indicate that we should go through the ERROR state */ qp->resp.goto_error = 1; } static enum resp_states do_class_d1e_error(struct rxe_qp *qp) { /* UC */ if (qp->srq) { /* Class E */ qp->resp.drop_msg = 1; if (qp->resp.wqe) { qp->resp.status = IB_WC_REM_INV_REQ_ERR; return RESPST_COMPLETE; } else { return RESPST_CLEANUP; } } else { /* Class D1. This packet may be the start of a * new message and could be valid. The previous * message is invalid and ignored. reset the * recv wr to its original state */ if (qp->resp.wqe) { qp->resp.wqe->dma.resid = qp->resp.wqe->dma.length; qp->resp.wqe->dma.cur_sge = 0; qp->resp.wqe->dma.sge_offset = 0; qp->resp.opcode = -1; } if (qp->resp.mr) { rxe_put(qp->resp.mr); qp->resp.mr = NULL; } return RESPST_CLEANUP; } } /* drain incoming request packet queue */ static void drain_req_pkts(struct rxe_qp *qp) { struct sk_buff *skb; while ((skb = skb_dequeue(&qp->req_pkts))) { rxe_put(qp); kfree_skb(skb); ib_device_put(qp->ibqp.device); } } /* complete receive wqe with flush error */ static int flush_recv_wqe(struct rxe_qp *qp, struct rxe_recv_wqe *wqe) { struct rxe_cqe cqe = {}; struct ib_wc *wc = &cqe.ibwc; struct ib_uverbs_wc *uwc = &cqe.uibwc; int err; if (qp->rcq->is_user) { uwc->wr_id = wqe->wr_id; uwc->status = IB_WC_WR_FLUSH_ERR; uwc->qp_num = qp_num(qp); } else { wc->wr_id = wqe->wr_id; wc->status = IB_WC_WR_FLUSH_ERR; wc->qp = &qp->ibqp; } err = rxe_cq_post(qp->rcq, &cqe, 0); if (err) rxe_dbg_cq(qp->rcq, "post cq failed err = %d\n", err); return err; } /* drain and optionally complete the recive queue * if unable to complete a wqe stop completing and * just flush the remaining wqes */ static void flush_recv_queue(struct rxe_qp *qp, bool notify) { struct rxe_queue *q = qp->rq.queue; struct rxe_recv_wqe *wqe; int err; if (qp->srq) { if (notify && qp->ibqp.event_handler) { struct ib_event ev; ev.device = qp->ibqp.device; ev.element.qp = &qp->ibqp; ev.event = IB_EVENT_QP_LAST_WQE_REACHED; qp->ibqp.event_handler(&ev, qp->ibqp.qp_context); } return; } /* recv queue not created. nothing to do. */ if (!qp->rq.queue) return; while ((wqe = queue_head(q, q->type))) { if (notify) { err = flush_recv_wqe(qp, wqe); if (err) notify = 0; } queue_advance_consumer(q, q->type); } qp->resp.wqe = NULL; } int rxe_receiver(struct rxe_qp *qp) { struct rxe_dev *rxe = to_rdev(qp->ibqp.device); enum resp_states state; struct rxe_pkt_info *pkt = NULL; int ret; unsigned long flags; spin_lock_irqsave(&qp->state_lock, flags); if (!qp->valid || qp_state(qp) == IB_QPS_ERR || qp_state(qp) == IB_QPS_RESET) { bool notify = qp->valid && (qp_state(qp) == IB_QPS_ERR); drain_req_pkts(qp); flush_recv_queue(qp, notify); spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } spin_unlock_irqrestore(&qp->state_lock, flags); qp->resp.aeth_syndrome = AETH_ACK_UNLIMITED; state = RESPST_GET_REQ; while (1) { rxe_dbg_qp(qp, "state = %s\n", resp_state_name[state]); switch (state) { case RESPST_GET_REQ: state = get_req(qp, &pkt); break; case RESPST_CHK_PSN: state = check_psn(qp, pkt); break; case RESPST_CHK_OP_SEQ: state = check_op_seq(qp, pkt); break; case RESPST_CHK_OP_VALID: state = check_op_valid(qp, pkt); break; case RESPST_CHK_RESOURCE: state = check_resource(qp, pkt); break; case RESPST_CHK_LENGTH: state = rxe_resp_check_length(qp, pkt); break; case RESPST_CHK_RKEY: state = check_rkey(qp, pkt); break; case RESPST_EXECUTE: state = execute(qp, pkt); break; case RESPST_COMPLETE: state = do_complete(qp, pkt); break; case RESPST_READ_REPLY: state = read_reply(qp, pkt); break; case RESPST_ATOMIC_REPLY: state = atomic_reply(qp, pkt); break; case RESPST_ATOMIC_WRITE_REPLY: state = atomic_write_reply(qp, pkt); break; case RESPST_PROCESS_FLUSH: state = process_flush(qp, pkt); break; case RESPST_ACKNOWLEDGE: state = acknowledge(qp, pkt); break; case RESPST_CLEANUP: state = cleanup(qp, pkt); break; case RESPST_DUPLICATE_REQUEST: state = duplicate_request(qp, pkt); break; case RESPST_ERR_PSN_OUT_OF_SEQ: /* RC only - Class B. Drop packet. */ send_ack(qp, AETH_NAK_PSN_SEQ_ERROR, qp->resp.psn); state = RESPST_CLEANUP; break; case RESPST_ERR_TOO_MANY_RDMA_ATM_REQ: case RESPST_ERR_MISSING_OPCODE_FIRST: case RESPST_ERR_MISSING_OPCODE_LAST_C: case RESPST_ERR_UNSUPPORTED_OPCODE: case RESPST_ERR_MISALIGNED_ATOMIC: /* RC Only - Class C. */ do_class_ac_error(qp, AETH_NAK_INVALID_REQ, IB_WC_REM_INV_REQ_ERR); state = RESPST_COMPLETE; break; case RESPST_ERR_MISSING_OPCODE_LAST_D1E: state = do_class_d1e_error(qp); break; case RESPST_ERR_RNR: if (qp_type(qp) == IB_QPT_RC) { rxe_counter_inc(rxe, RXE_CNT_SND_RNR); /* RC - class B */ send_ack(qp, AETH_RNR_NAK | (~AETH_TYPE_MASK & qp->attr.min_rnr_timer), pkt->psn); } else { /* UD/UC - class D */ qp->resp.drop_msg = 1; } state = RESPST_CLEANUP; break; case RESPST_ERR_RKEY_VIOLATION: if (qp_type(qp) == IB_QPT_RC) { /* Class C */ do_class_ac_error(qp, AETH_NAK_REM_ACC_ERR, IB_WC_REM_ACCESS_ERR); state = RESPST_COMPLETE; } else { qp->resp.drop_msg = 1; if (qp->srq) { /* UC/SRQ Class D */ qp->resp.status = IB_WC_REM_ACCESS_ERR; state = RESPST_COMPLETE; } else { /* UC/non-SRQ Class E. */ state = RESPST_CLEANUP; } } break; case RESPST_ERR_INVALIDATE_RKEY: /* RC - Class J. */ qp->resp.goto_error = 1; qp->resp.status = IB_WC_REM_INV_REQ_ERR; state = RESPST_COMPLETE; break; case RESPST_ERR_LENGTH: if (qp_type(qp) == IB_QPT_RC) { /* Class C */ do_class_ac_error(qp, AETH_NAK_INVALID_REQ, IB_WC_REM_INV_REQ_ERR); state = RESPST_COMPLETE; } else if (qp->srq) { /* UC/UD - class E */ qp->resp.status = IB_WC_REM_INV_REQ_ERR; state = RESPST_COMPLETE; } else { /* UC/UD - class D */ qp->resp.drop_msg = 1; state = RESPST_CLEANUP; } break; case RESPST_ERR_MALFORMED_WQE: /* All, Class A. */ do_class_ac_error(qp, AETH_NAK_REM_OP_ERR, IB_WC_LOC_QP_OP_ERR); state = RESPST_COMPLETE; break; case RESPST_ERR_CQ_OVERFLOW: /* All - Class G */ state = RESPST_ERROR; break; case RESPST_DONE: if (qp->resp.goto_error) { state = RESPST_ERROR; break; } goto done; case RESPST_EXIT: if (qp->resp.goto_error) { state = RESPST_ERROR; break; } goto exit; case RESPST_ERROR: qp->resp.goto_error = 0; rxe_dbg_qp(qp, "moved to error state\n"); rxe_qp_error(qp); goto exit; default: WARN_ON_ONCE(1); } } /* A non-zero return value will cause rxe_do_task to * exit its loop and end the work item. A zero return * will continue looping and return to rxe_responder */ done: ret = 0; goto out; exit: ret = -EAGAIN; out: return ret; } |
| 2 2 2 2 52 37 3 12 16 46 3 5 2 1 1 2 1 2 1 1 1 1 9 2 1 1 1 1 1 1 1 4 2 1 1 1 1 1 1 1 1 1 1 1 2 2 2 1 1 13 2 1 1 1 1 1 1 1 4 2 2 1 2 2 1 2 2 2 1 1 6 7 1 4 3 6 4 1 2 1 2 3 1 3 4 3 4 4 4 4 12 36 36 2 2 4 1 3 4 1 5 5 1 1 1 1 1 1 2 1 1 2 1 7 2 8 1 7 1 1 2 1 1 1 2 1 1 5 1 4 2 2 4 4 1 1 1 4 2 2 2 2 6 7 1 6 6 6 6 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Netlink interface for IEEE 802.15.4 stack * * Copyright 2007, 2008 Siemens AG * * Written by: * Sergey Lapin <slapin@ossfans.org> * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> * Maxim Osipov <maxim.osipov@siemens.com> */ #include <linux/gfp.h> #include <linux/kernel.h> #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/ieee802154.h> #include <net/netlink.h> #include <net/genetlink.h> #include <net/sock.h> #include <linux/nl802154.h> #include <linux/export.h> #include <net/af_ieee802154.h> #include <net/ieee802154_netdev.h> #include <net/cfg802154.h> #include "ieee802154.h" static int nla_put_hwaddr(struct sk_buff *msg, int type, __le64 hwaddr, int padattr) { return nla_put_u64_64bit(msg, type, swab64((__force u64)hwaddr), padattr); } static __le64 nla_get_hwaddr(const struct nlattr *nla) { return ieee802154_devaddr_from_raw(nla_data(nla)); } static int nla_put_shortaddr(struct sk_buff *msg, int type, __le16 addr) { return nla_put_u16(msg, type, le16_to_cpu(addr)); } static __le16 nla_get_shortaddr(const struct nlattr *nla) { return cpu_to_le16(nla_get_u16(nla)); } static int ieee802154_nl_start_confirm(struct net_device *dev, u8 status) { struct sk_buff *msg; pr_debug("%s\n", __func__); msg = ieee802154_nl_create(0, IEEE802154_START_CONF); if (!msg) return -ENOBUFS; if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, dev->dev_addr) || nla_put_u8(msg, IEEE802154_ATTR_STATUS, status)) goto nla_put_failure; return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP); nla_put_failure: nlmsg_free(msg); return -ENOBUFS; } static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags, struct net_device *dev) { void *hdr; struct wpan_phy *phy; struct ieee802154_mlme_ops *ops; __le16 short_addr, pan_id; pr_debug("%s\n", __func__); hdr = genlmsg_put(msg, 0, seq, &nl802154_family, flags, IEEE802154_LIST_IFACE); if (!hdr) goto out; ops = ieee802154_mlme_ops(dev); phy = dev->ieee802154_ptr->wpan_phy; BUG_ON(!phy); get_device(&phy->dev); rtnl_lock(); short_addr = dev->ieee802154_ptr->short_addr; pan_id = dev->ieee802154_ptr->pan_id; rtnl_unlock(); if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) || nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, dev->dev_addr) || nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) || nla_put_shortaddr(msg, IEEE802154_ATTR_PAN_ID, pan_id)) goto nla_put_failure; if (ops->get_mac_params) { struct ieee802154_mac_params params; rtnl_lock(); ops->get_mac_params(dev, ¶ms); rtnl_unlock(); if (nla_put_s8(msg, IEEE802154_ATTR_TXPOWER, params.transmit_power / 100) || nla_put_u8(msg, IEEE802154_ATTR_LBT_ENABLED, params.lbt) || nla_put_u8(msg, IEEE802154_ATTR_CCA_MODE, params.cca.mode) || nla_put_s32(msg, IEEE802154_ATTR_CCA_ED_LEVEL, params.cca_ed_level / 100) || nla_put_u8(msg, IEEE802154_ATTR_CSMA_RETRIES, params.csma_retries) || nla_put_u8(msg, IEEE802154_ATTR_CSMA_MIN_BE, params.min_be) || nla_put_u8(msg, IEEE802154_ATTR_CSMA_MAX_BE, params.max_be) || nla_put_s8(msg, IEEE802154_ATTR_FRAME_RETRIES, params.frame_retries)) goto nla_put_failure; } wpan_phy_put(phy); genlmsg_end(msg, hdr); return 0; nla_put_failure: wpan_phy_put(phy); genlmsg_cancel(msg, hdr); out: return -EMSGSIZE; } /* Requests from userspace */ static struct net_device *ieee802154_nl_get_dev(struct genl_info *info) { struct net_device *dev; if (info->attrs[IEEE802154_ATTR_DEV_NAME]) { char name[IFNAMSIZ + 1]; nla_strscpy(name, info->attrs[IEEE802154_ATTR_DEV_NAME], sizeof(name)); dev = dev_get_by_name(&init_net, name); } else if (info->attrs[IEEE802154_ATTR_DEV_INDEX]) { dev = dev_get_by_index(&init_net, nla_get_u32(info->attrs[IEEE802154_ATTR_DEV_INDEX])); } else { return NULL; } if (!dev) return NULL; if (dev->type != ARPHRD_IEEE802154) { dev_put(dev); return NULL; } return dev; } int ieee802154_associate_req(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev; struct ieee802154_addr addr; u8 page; int ret = -EOPNOTSUPP; if (!info->attrs[IEEE802154_ATTR_CHANNEL] || !info->attrs[IEEE802154_ATTR_COORD_PAN_ID] || (!info->attrs[IEEE802154_ATTR_COORD_HW_ADDR] && !info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]) || !info->attrs[IEEE802154_ATTR_CAPABILITY]) return -EINVAL; dev = ieee802154_nl_get_dev(info); if (!dev) return -ENODEV; if (!ieee802154_mlme_ops(dev)->assoc_req) goto out; if (info->attrs[IEEE802154_ATTR_COORD_HW_ADDR]) { addr.mode = IEEE802154_ADDR_LONG; addr.extended_addr = nla_get_hwaddr( info->attrs[IEEE802154_ATTR_COORD_HW_ADDR]); } else { addr.mode = IEEE802154_ADDR_SHORT; addr.short_addr = nla_get_shortaddr( info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]); } addr.pan_id = nla_get_shortaddr( info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); page = nla_get_u8_default(info->attrs[IEEE802154_ATTR_PAGE], 0); ret = ieee802154_mlme_ops(dev)->assoc_req(dev, &addr, nla_get_u8(info->attrs[IEEE802154_ATTR_CHANNEL]), page, nla_get_u8(info->attrs[IEEE802154_ATTR_CAPABILITY])); out: dev_put(dev); return ret; } int ieee802154_associate_resp(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev; struct ieee802154_addr addr; int ret = -EOPNOTSUPP; if (!info->attrs[IEEE802154_ATTR_STATUS] || !info->attrs[IEEE802154_ATTR_DEST_HW_ADDR] || !info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]) return -EINVAL; dev = ieee802154_nl_get_dev(info); if (!dev) return -ENODEV; if (!ieee802154_mlme_ops(dev)->assoc_resp) goto out; addr.mode = IEEE802154_ADDR_LONG; addr.extended_addr = nla_get_hwaddr( info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]); rtnl_lock(); addr.pan_id = dev->ieee802154_ptr->pan_id; rtnl_unlock(); ret = ieee802154_mlme_ops(dev)->assoc_resp(dev, &addr, nla_get_shortaddr(info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]), nla_get_u8(info->attrs[IEEE802154_ATTR_STATUS])); out: dev_put(dev); return ret; } int ieee802154_disassociate_req(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev; struct ieee802154_addr addr; int ret = -EOPNOTSUPP; if ((!info->attrs[IEEE802154_ATTR_DEST_HW_ADDR] && !info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]) || !info->attrs[IEEE802154_ATTR_REASON]) return -EINVAL; dev = ieee802154_nl_get_dev(info); if (!dev) return -ENODEV; if (!ieee802154_mlme_ops(dev)->disassoc_req) goto out; if (info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]) { addr.mode = IEEE802154_ADDR_LONG; addr.extended_addr = nla_get_hwaddr( info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]); } else { addr.mode = IEEE802154_ADDR_SHORT; addr.short_addr = nla_get_shortaddr( info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]); } rtnl_lock(); addr.pan_id = dev->ieee802154_ptr->pan_id; rtnl_unlock(); ret = ieee802154_mlme_ops(dev)->disassoc_req(dev, &addr, nla_get_u8(info->attrs[IEEE802154_ATTR_REASON])); out: dev_put(dev); return ret; } /* PANid, channel, beacon_order = 15, superframe_order = 15, * PAN_coordinator, battery_life_extension = 0, * coord_realignment = 0, security_enable = 0 */ int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev; struct ieee802154_addr addr; u8 channel, bcn_ord, sf_ord; u8 page; int pan_coord, blx, coord_realign; int ret = -EBUSY; if (!info->attrs[IEEE802154_ATTR_COORD_PAN_ID] || !info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR] || !info->attrs[IEEE802154_ATTR_CHANNEL] || !info->attrs[IEEE802154_ATTR_BCN_ORD] || !info->attrs[IEEE802154_ATTR_SF_ORD] || !info->attrs[IEEE802154_ATTR_PAN_COORD] || !info->attrs[IEEE802154_ATTR_BAT_EXT] || !info->attrs[IEEE802154_ATTR_COORD_REALIGN] ) return -EINVAL; dev = ieee802154_nl_get_dev(info); if (!dev) return -ENODEV; if (netif_running(dev)) goto out; if (!ieee802154_mlme_ops(dev)->start_req) { ret = -EOPNOTSUPP; goto out; } addr.mode = IEEE802154_ADDR_SHORT; addr.short_addr = nla_get_shortaddr( info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]); addr.pan_id = nla_get_shortaddr( info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); channel = nla_get_u8(info->attrs[IEEE802154_ATTR_CHANNEL]); bcn_ord = nla_get_u8(info->attrs[IEEE802154_ATTR_BCN_ORD]); sf_ord = nla_get_u8(info->attrs[IEEE802154_ATTR_SF_ORD]); pan_coord = nla_get_u8(info->attrs[IEEE802154_ATTR_PAN_COORD]); blx = nla_get_u8(info->attrs[IEEE802154_ATTR_BAT_EXT]); coord_realign = nla_get_u8(info->attrs[IEEE802154_ATTR_COORD_REALIGN]); page = nla_get_u8_default(info->attrs[IEEE802154_ATTR_PAGE], 0); if (addr.short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST)) { ieee802154_nl_start_confirm(dev, IEEE802154_NO_SHORT_ADDRESS); dev_put(dev); return -EINVAL; } rtnl_lock(); ret = ieee802154_mlme_ops(dev)->start_req(dev, &addr, channel, page, bcn_ord, sf_ord, pan_coord, blx, coord_realign); rtnl_unlock(); /* FIXME: add validation for unused parameters to be sane * for SoftMAC */ ieee802154_nl_start_confirm(dev, IEEE802154_SUCCESS); out: dev_put(dev); return ret; } int ieee802154_scan_req(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev; int ret = -EOPNOTSUPP; u8 type; u32 channels; u8 duration; u8 page; if (!info->attrs[IEEE802154_ATTR_SCAN_TYPE] || !info->attrs[IEEE802154_ATTR_CHANNELS] || !info->attrs[IEEE802154_ATTR_DURATION]) return -EINVAL; dev = ieee802154_nl_get_dev(info); if (!dev) return -ENODEV; if (!ieee802154_mlme_ops(dev)->scan_req) goto out; type = nla_get_u8(info->attrs[IEEE802154_ATTR_SCAN_TYPE]); channels = nla_get_u32(info->attrs[IEEE802154_ATTR_CHANNELS]); duration = nla_get_u8(info->attrs[IEEE802154_ATTR_DURATION]); page = nla_get_u8_default(info->attrs[IEEE802154_ATTR_PAGE], 0); ret = ieee802154_mlme_ops(dev)->scan_req(dev, type, channels, page, duration); out: dev_put(dev); return ret; } int ieee802154_list_iface(struct sk_buff *skb, struct genl_info *info) { /* Request for interface name, index, type, IEEE address, * PAN Id, short address */ struct sk_buff *msg; struct net_device *dev = NULL; int rc = -ENOBUFS; pr_debug("%s\n", __func__); dev = ieee802154_nl_get_dev(info); if (!dev) return -ENODEV; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) goto out_dev; rc = ieee802154_nl_fill_iface(msg, info->snd_portid, info->snd_seq, 0, dev); if (rc < 0) goto out_free; dev_put(dev); return genlmsg_reply(msg, info); out_free: nlmsg_free(msg); out_dev: dev_put(dev); return rc; } int ieee802154_dump_iface(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct net_device *dev; int idx; int s_idx = cb->args[0]; pr_debug("%s\n", __func__); idx = 0; for_each_netdev(net, dev) { if (idx < s_idx || dev->type != ARPHRD_IEEE802154) goto cont; if (ieee802154_nl_fill_iface(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, dev) < 0) break; cont: idx++; } cb->args[0] = idx; return skb->len; } int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev = NULL; struct ieee802154_mlme_ops *ops; struct ieee802154_mac_params params; struct wpan_phy *phy; int rc = -EINVAL; pr_debug("%s\n", __func__); dev = ieee802154_nl_get_dev(info); if (!dev) return -ENODEV; ops = ieee802154_mlme_ops(dev); if (!ops->get_mac_params || !ops->set_mac_params) { rc = -EOPNOTSUPP; goto out; } if (netif_running(dev)) { rc = -EBUSY; goto out; } if (!info->attrs[IEEE802154_ATTR_LBT_ENABLED] && !info->attrs[IEEE802154_ATTR_CCA_MODE] && !info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL] && !info->attrs[IEEE802154_ATTR_CSMA_RETRIES] && !info->attrs[IEEE802154_ATTR_CSMA_MIN_BE] && !info->attrs[IEEE802154_ATTR_CSMA_MAX_BE] && !info->attrs[IEEE802154_ATTR_FRAME_RETRIES]) goto out; phy = dev->ieee802154_ptr->wpan_phy; get_device(&phy->dev); rtnl_lock(); ops->get_mac_params(dev, ¶ms); if (info->attrs[IEEE802154_ATTR_TXPOWER]) params.transmit_power = nla_get_s8(info->attrs[IEEE802154_ATTR_TXPOWER]) * 100; if (info->attrs[IEEE802154_ATTR_LBT_ENABLED]) params.lbt = nla_get_u8(info->attrs[IEEE802154_ATTR_LBT_ENABLED]); if (info->attrs[IEEE802154_ATTR_CCA_MODE]) params.cca.mode = nla_get_u8(info->attrs[IEEE802154_ATTR_CCA_MODE]); if (info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]) params.cca_ed_level = nla_get_s32(info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]) * 100; if (info->attrs[IEEE802154_ATTR_CSMA_RETRIES]) params.csma_retries = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_RETRIES]); if (info->attrs[IEEE802154_ATTR_CSMA_MIN_BE]) params.min_be = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_MIN_BE]); if (info->attrs[IEEE802154_ATTR_CSMA_MAX_BE]) params.max_be = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_MAX_BE]); if (info->attrs[IEEE802154_ATTR_FRAME_RETRIES]) params.frame_retries = nla_get_s8(info->attrs[IEEE802154_ATTR_FRAME_RETRIES]); rc = ops->set_mac_params(dev, ¶ms); rtnl_unlock(); wpan_phy_put(phy); dev_put(dev); return 0; out: dev_put(dev); return rc; } static int ieee802154_llsec_parse_key_id(struct genl_info *info, struct ieee802154_llsec_key_id *desc) { memset(desc, 0, sizeof(*desc)); if (!info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE]) return -EINVAL; desc->mode = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE]); if (desc->mode == IEEE802154_SCF_KEY_IMPLICIT) { if (!info->attrs[IEEE802154_ATTR_PAN_ID]) return -EINVAL; desc->device_addr.pan_id = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_PAN_ID]); if (info->attrs[IEEE802154_ATTR_SHORT_ADDR]) { desc->device_addr.mode = IEEE802154_ADDR_SHORT; desc->device_addr.short_addr = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_SHORT_ADDR]); } else { if (!info->attrs[IEEE802154_ATTR_HW_ADDR]) return -EINVAL; desc->device_addr.mode = IEEE802154_ADDR_LONG; desc->device_addr.extended_addr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]); } } if (desc->mode != IEEE802154_SCF_KEY_IMPLICIT && !info->attrs[IEEE802154_ATTR_LLSEC_KEY_ID]) return -EINVAL; if (desc->mode == IEEE802154_SCF_KEY_SHORT_INDEX && !info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT]) return -EINVAL; if (desc->mode == IEEE802154_SCF_KEY_HW_INDEX && !info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED]) return -EINVAL; if (desc->mode != IEEE802154_SCF_KEY_IMPLICIT) desc->id = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_KEY_ID]); switch (desc->mode) { case IEEE802154_SCF_KEY_SHORT_INDEX: { u32 source = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT]); desc->short_source = cpu_to_le32(source); break; } case IEEE802154_SCF_KEY_HW_INDEX: desc->extended_source = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED]); break; } return 0; } static int ieee802154_llsec_fill_key_id(struct sk_buff *msg, const struct ieee802154_llsec_key_id *desc) { if (nla_put_u8(msg, IEEE802154_ATTR_LLSEC_KEY_MODE, desc->mode)) return -EMSGSIZE; if (desc->mode == IEEE802154_SCF_KEY_IMPLICIT) { if (nla_put_shortaddr(msg, IEEE802154_ATTR_PAN_ID, desc->device_addr.pan_id)) return -EMSGSIZE; if (desc->device_addr.mode == IEEE802154_ADDR_SHORT && nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR, desc->device_addr.short_addr)) return -EMSGSIZE; if (desc->device_addr.mode == IEEE802154_ADDR_LONG && nla_put_hwaddr(msg, IEEE802154_ATTR_HW_ADDR, desc->device_addr.extended_addr, IEEE802154_ATTR_PAD)) return -EMSGSIZE; } if (desc->mode != IEEE802154_SCF_KEY_IMPLICIT && nla_put_u8(msg, IEEE802154_ATTR_LLSEC_KEY_ID, desc->id)) return -EMSGSIZE; if (desc->mode == IEEE802154_SCF_KEY_SHORT_INDEX && nla_put_u32(msg, IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT, le32_to_cpu(desc->short_source))) return -EMSGSIZE; if (desc->mode == IEEE802154_SCF_KEY_HW_INDEX && nla_put_hwaddr(msg, IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED, desc->extended_source, IEEE802154_ATTR_PAD)) return -EMSGSIZE; return 0; } int ieee802154_llsec_getparams(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; struct net_device *dev = NULL; int rc = -ENOBUFS; struct ieee802154_mlme_ops *ops; void *hdr; struct ieee802154_llsec_params params; pr_debug("%s\n", __func__); dev = ieee802154_nl_get_dev(info); if (!dev) return -ENODEV; ops = ieee802154_mlme_ops(dev); if (!ops->llsec) { rc = -EOPNOTSUPP; goto out_dev; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) goto out_dev; hdr = genlmsg_put(msg, 0, info->snd_seq, &nl802154_family, 0, IEEE802154_LLSEC_GETPARAMS); if (!hdr) goto out_free; rc = ops->llsec->get_params(dev, ¶ms); if (rc < 0) goto out_free; if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || nla_put_u8(msg, IEEE802154_ATTR_LLSEC_ENABLED, params.enabled) || nla_put_u8(msg, IEEE802154_ATTR_LLSEC_SECLEVEL, params.out_level) || nla_put_u32(msg, IEEE802154_ATTR_LLSEC_FRAME_COUNTER, be32_to_cpu(params.frame_counter)) || ieee802154_llsec_fill_key_id(msg, ¶ms.out_key)) { rc = -ENOBUFS; goto out_free; } dev_put(dev); return ieee802154_nl_reply(msg, info); out_free: nlmsg_free(msg); out_dev: dev_put(dev); return rc; } int ieee802154_llsec_setparams(struct sk_buff *skb, struct genl_info *info) { struct net_device *dev = NULL; int rc = -EINVAL; struct ieee802154_mlme_ops *ops; struct ieee802154_llsec_params params; int changed = 0; pr_debug("%s\n", __func__); dev = ieee802154_nl_get_dev(info); if (!dev) return -ENODEV; if (!info->attrs[IEEE802154_ATTR_LLSEC_ENABLED] && !info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE] && !info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL]) goto out; ops = ieee802154_mlme_ops(dev); if (!ops->llsec) { rc = -EOPNOTSUPP; goto out; } if (info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL] && nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL]) > 7) goto out; if (info->attrs[IEEE802154_ATTR_LLSEC_ENABLED]) { params.enabled = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_ENABLED]); changed |= IEEE802154_LLSEC_PARAM_ENABLED; } if (info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE]) { if (ieee802154_llsec_parse_key_id(info, ¶ms.out_key)) goto out; changed |= IEEE802154_LLSEC_PARAM_OUT_KEY; } if (info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL]) { params.out_level = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL]); changed |= IEEE802154_LLSEC_PARAM_OUT_LEVEL; } if (info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER]) { u32 fc = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER]); params.frame_counter = cpu_to_be32(fc); changed |= IEEE802154_LLSEC_PARAM_FRAME_COUNTER; } rc = ops->llsec->set_params(dev, ¶ms, changed); dev_put(dev); return rc; out: dev_put(dev); return rc; } struct llsec_dump_data { struct sk_buff *skb; int s_idx, s_idx2; int portid; int nlmsg_seq; struct net_device *dev; struct ieee802154_mlme_ops *ops; struct ieee802154_llsec_table *table; }; static int ieee802154_llsec_dump_table(struct sk_buff *skb, struct netlink_callback *cb, int (*step)(struct llsec_dump_data *)) { struct net *net = sock_net(skb->sk); struct net_device *dev; struct llsec_dump_data data; int idx = 0; int first_dev = cb->args[0]; int rc; for_each_netdev(net, dev) { if (idx < first_dev || dev->type != ARPHRD_IEEE802154) goto skip; data.ops = ieee802154_mlme_ops(dev); if (!data.ops->llsec) goto skip; data.skb = skb; data.s_idx = cb->args[1]; data.s_idx2 = cb->args[2]; data.dev = dev; data.portid = NETLINK_CB(cb->skb).portid; data.nlmsg_seq = cb->nlh->nlmsg_seq; data.ops->llsec->lock_table(dev); data.ops->llsec->get_table(data.dev, &data.table); rc = step(&data); data.ops->llsec->unlock_table(dev); if (rc < 0) break; skip: idx++; } cb->args[0] = idx; return skb->len; } static int ieee802154_nl_llsec_change(struct sk_buff *skb, struct genl_info *info, int (*fn)(struct net_device*, struct genl_info*)) { struct net_device *dev = NULL; int rc = -EINVAL; dev = ieee802154_nl_get_dev(info); if (!dev) return -ENODEV; if (!ieee802154_mlme_ops(dev)->llsec) rc = -EOPNOTSUPP; else rc = fn(dev, info); dev_put(dev); return rc; } static int ieee802154_llsec_parse_key(struct genl_info *info, struct ieee802154_llsec_key *key) { u8 frames; u32 commands[256 / 32]; memset(key, 0, sizeof(*key)); if (!info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES] || !info->attrs[IEEE802154_ATTR_LLSEC_KEY_BYTES]) return -EINVAL; frames = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES]); if ((frames & BIT(IEEE802154_FC_TYPE_MAC_CMD)) && !info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS]) return -EINVAL; if (info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS]) { nla_memcpy(commands, info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS], 256 / 8); if (commands[0] || commands[1] || commands[2] || commands[3] || commands[4] || commands[5] || commands[6] || commands[7] >= BIT(IEEE802154_CMD_GTS_REQ + 1)) return -EINVAL; key->cmd_frame_ids = commands[7]; } key->frame_types = frames; nla_memcpy(key->key, info->attrs[IEEE802154_ATTR_LLSEC_KEY_BYTES], IEEE802154_LLSEC_KEY_SIZE); return 0; } static int llsec_add_key(struct net_device *dev, struct genl_info *info) { struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); struct ieee802154_llsec_key key; struct ieee802154_llsec_key_id id; if (ieee802154_llsec_parse_key(info, &key) || ieee802154_llsec_parse_key_id(info, &id)) return -EINVAL; return ops->llsec->add_key(dev, &id, &key); } int ieee802154_llsec_add_key(struct sk_buff *skb, struct genl_info *info) { if ((info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) != (NLM_F_CREATE | NLM_F_EXCL)) return -EINVAL; return ieee802154_nl_llsec_change(skb, info, llsec_add_key); } static int llsec_remove_key(struct net_device *dev, struct genl_info *info) { struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); struct ieee802154_llsec_key_id id; if (ieee802154_llsec_parse_key_id(info, &id)) return -EINVAL; return ops->llsec->del_key(dev, &id); } int ieee802154_llsec_del_key(struct sk_buff *skb, struct genl_info *info) { return ieee802154_nl_llsec_change(skb, info, llsec_remove_key); } static int ieee802154_nl_fill_key(struct sk_buff *msg, u32 portid, u32 seq, const struct ieee802154_llsec_key_entry *key, const struct net_device *dev) { void *hdr; u32 commands[256 / 32]; hdr = genlmsg_put(msg, 0, seq, &nl802154_family, NLM_F_MULTI, IEEE802154_LLSEC_LIST_KEY); if (!hdr) goto out; if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || ieee802154_llsec_fill_key_id(msg, &key->id) || nla_put_u8(msg, IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES, key->key->frame_types)) goto nla_put_failure; if (key->key->frame_types & BIT(IEEE802154_FC_TYPE_MAC_CMD)) { memset(commands, 0, sizeof(commands)); commands[7] = key->key->cmd_frame_ids; if (nla_put(msg, IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS, sizeof(commands), commands)) goto nla_put_failure; } if (nla_put(msg, IEEE802154_ATTR_LLSEC_KEY_BYTES, IEEE802154_LLSEC_KEY_SIZE, key->key->key)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); out: return -EMSGSIZE; } static int llsec_iter_keys(struct llsec_dump_data *data) { struct ieee802154_llsec_key_entry *pos; int rc = 0, idx = 0; list_for_each_entry(pos, &data->table->keys, list) { if (idx++ < data->s_idx) continue; if (ieee802154_nl_fill_key(data->skb, data->portid, data->nlmsg_seq, pos, data->dev)) { rc = -EMSGSIZE; break; } data->s_idx++; } return rc; } int ieee802154_llsec_dump_keys(struct sk_buff *skb, struct netlink_callback *cb) { return ieee802154_llsec_dump_table(skb, cb, llsec_iter_keys); } static int llsec_parse_dev(struct genl_info *info, struct ieee802154_llsec_device *dev) { memset(dev, 0, sizeof(*dev)); if (!info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER] || !info->attrs[IEEE802154_ATTR_HW_ADDR] || !info->attrs[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE] || !info->attrs[IEEE802154_ATTR_LLSEC_DEV_KEY_MODE] || (!!info->attrs[IEEE802154_ATTR_PAN_ID] != !!info->attrs[IEEE802154_ATTR_SHORT_ADDR])) return -EINVAL; if (info->attrs[IEEE802154_ATTR_PAN_ID]) { dev->pan_id = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_PAN_ID]); dev->short_addr = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_SHORT_ADDR]); } else { dev->short_addr = cpu_to_le16(IEEE802154_ADDR_UNDEF); } dev->hwaddr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]); dev->frame_counter = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER]); dev->seclevel_exempt = !!nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE]); dev->key_mode = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_DEV_KEY_MODE]); if (dev->key_mode >= __IEEE802154_LLSEC_DEVKEY_MAX) return -EINVAL; return 0; } static int llsec_add_dev(struct net_device *dev, struct genl_info *info) { struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); struct ieee802154_llsec_device desc; if (llsec_parse_dev(info, &desc)) return -EINVAL; return ops->llsec->add_dev(dev, &desc); } int ieee802154_llsec_add_dev(struct sk_buff *skb, struct genl_info *info) { if ((info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) != (NLM_F_CREATE | NLM_F_EXCL)) return -EINVAL; return ieee802154_nl_llsec_change(skb, info, llsec_add_dev); } static int llsec_del_dev(struct net_device *dev, struct genl_info *info) { struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); __le64 devaddr; if (!info->attrs[IEEE802154_ATTR_HW_ADDR]) return -EINVAL; devaddr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]); return ops->llsec->del_dev(dev, devaddr); } int ieee802154_llsec_del_dev(struct sk_buff *skb, struct genl_info *info) { return ieee802154_nl_llsec_change(skb, info, llsec_del_dev); } static int ieee802154_nl_fill_dev(struct sk_buff *msg, u32 portid, u32 seq, const struct ieee802154_llsec_device *desc, const struct net_device *dev) { void *hdr; hdr = genlmsg_put(msg, 0, seq, &nl802154_family, NLM_F_MULTI, IEEE802154_LLSEC_LIST_DEV); if (!hdr) goto out; if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || nla_put_shortaddr(msg, IEEE802154_ATTR_PAN_ID, desc->pan_id) || nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR, desc->short_addr) || nla_put_hwaddr(msg, IEEE802154_ATTR_HW_ADDR, desc->hwaddr, IEEE802154_ATTR_PAD) || nla_put_u32(msg, IEEE802154_ATTR_LLSEC_FRAME_COUNTER, desc->frame_counter) || nla_put_u8(msg, IEEE802154_ATTR_LLSEC_DEV_OVERRIDE, desc->seclevel_exempt) || nla_put_u8(msg, IEEE802154_ATTR_LLSEC_DEV_KEY_MODE, desc->key_mode)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); out: return -EMSGSIZE; } static int llsec_iter_devs(struct llsec_dump_data *data) { struct ieee802154_llsec_device *pos; int rc = 0, idx = 0; list_for_each_entry(pos, &data->table->devices, list) { if (idx++ < data->s_idx) continue; if (ieee802154_nl_fill_dev(data->skb, data->portid, data->nlmsg_seq, pos, data->dev)) { rc = -EMSGSIZE; break; } data->s_idx++; } return rc; } int ieee802154_llsec_dump_devs(struct sk_buff *skb, struct netlink_callback *cb) { return ieee802154_llsec_dump_table(skb, cb, llsec_iter_devs); } static int llsec_add_devkey(struct net_device *dev, struct genl_info *info) { struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); struct ieee802154_llsec_device_key key; __le64 devaddr; if (!info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER] || !info->attrs[IEEE802154_ATTR_HW_ADDR] || ieee802154_llsec_parse_key_id(info, &key.key_id)) return -EINVAL; devaddr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]); key.frame_counter = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER]); return ops->llsec->add_devkey(dev, devaddr, &key); } int ieee802154_llsec_add_devkey(struct sk_buff *skb, struct genl_info *info) { if ((info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) != (NLM_F_CREATE | NLM_F_EXCL)) return -EINVAL; return ieee802154_nl_llsec_change(skb, info, llsec_add_devkey); } static int llsec_del_devkey(struct net_device *dev, struct genl_info *info) { struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); struct ieee802154_llsec_device_key key; __le64 devaddr; if (!info->attrs[IEEE802154_ATTR_HW_ADDR] || ieee802154_llsec_parse_key_id(info, &key.key_id)) return -EINVAL; devaddr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]); return ops->llsec->del_devkey(dev, devaddr, &key); } int ieee802154_llsec_del_devkey(struct sk_buff *skb, struct genl_info *info) { return ieee802154_nl_llsec_change(skb, info, llsec_del_devkey); } static int ieee802154_nl_fill_devkey(struct sk_buff *msg, u32 portid, u32 seq, __le64 devaddr, const struct ieee802154_llsec_device_key *devkey, const struct net_device *dev) { void *hdr; hdr = genlmsg_put(msg, 0, seq, &nl802154_family, NLM_F_MULTI, IEEE802154_LLSEC_LIST_DEVKEY); if (!hdr) goto out; if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || nla_put_hwaddr(msg, IEEE802154_ATTR_HW_ADDR, devaddr, IEEE802154_ATTR_PAD) || nla_put_u32(msg, IEEE802154_ATTR_LLSEC_FRAME_COUNTER, devkey->frame_counter) || ieee802154_llsec_fill_key_id(msg, &devkey->key_id)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); out: return -EMSGSIZE; } static int llsec_iter_devkeys(struct llsec_dump_data *data) { struct ieee802154_llsec_device *dpos; struct ieee802154_llsec_device_key *kpos; int idx = 0, idx2; list_for_each_entry(dpos, &data->table->devices, list) { if (idx++ < data->s_idx) continue; idx2 = 0; list_for_each_entry(kpos, &dpos->keys, list) { if (idx2++ < data->s_idx2) continue; if (ieee802154_nl_fill_devkey(data->skb, data->portid, data->nlmsg_seq, dpos->hwaddr, kpos, data->dev)) { return -EMSGSIZE; } data->s_idx2++; } data->s_idx++; } return 0; } int ieee802154_llsec_dump_devkeys(struct sk_buff *skb, struct netlink_callback *cb) { return ieee802154_llsec_dump_table(skb, cb, llsec_iter_devkeys); } static int llsec_parse_seclevel(struct genl_info *info, struct ieee802154_llsec_seclevel *sl) { memset(sl, 0, sizeof(*sl)); if (!info->attrs[IEEE802154_ATTR_LLSEC_FRAME_TYPE] || !info->attrs[IEEE802154_ATTR_LLSEC_SECLEVELS] || !info->attrs[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE]) return -EINVAL; sl->frame_type = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_FRAME_TYPE]); if (sl->frame_type == IEEE802154_FC_TYPE_MAC_CMD) { if (!info->attrs[IEEE802154_ATTR_LLSEC_CMD_FRAME_ID]) return -EINVAL; sl->cmd_frame_id = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_CMD_FRAME_ID]); } sl->sec_levels = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_SECLEVELS]); sl->device_override = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE]); return 0; } static int llsec_add_seclevel(struct net_device *dev, struct genl_info *info) { struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); struct ieee802154_llsec_seclevel sl; if (llsec_parse_seclevel(info, &sl)) return -EINVAL; return ops->llsec->add_seclevel(dev, &sl); } int ieee802154_llsec_add_seclevel(struct sk_buff *skb, struct genl_info *info) { if ((info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) != (NLM_F_CREATE | NLM_F_EXCL)) return -EINVAL; return ieee802154_nl_llsec_change(skb, info, llsec_add_seclevel); } static int llsec_del_seclevel(struct net_device *dev, struct genl_info *info) { struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); struct ieee802154_llsec_seclevel sl; if (llsec_parse_seclevel(info, &sl)) return -EINVAL; return ops->llsec->del_seclevel(dev, &sl); } int ieee802154_llsec_del_seclevel(struct sk_buff *skb, struct genl_info *info) { return ieee802154_nl_llsec_change(skb, info, llsec_del_seclevel); } static int ieee802154_nl_fill_seclevel(struct sk_buff *msg, u32 portid, u32 seq, const struct ieee802154_llsec_seclevel *sl, const struct net_device *dev) { void *hdr; hdr = genlmsg_put(msg, 0, seq, &nl802154_family, NLM_F_MULTI, IEEE802154_LLSEC_LIST_SECLEVEL); if (!hdr) goto out; if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || nla_put_u8(msg, IEEE802154_ATTR_LLSEC_FRAME_TYPE, sl->frame_type) || nla_put_u8(msg, IEEE802154_ATTR_LLSEC_SECLEVELS, sl->sec_levels) || nla_put_u8(msg, IEEE802154_ATTR_LLSEC_DEV_OVERRIDE, sl->device_override)) goto nla_put_failure; if (sl->frame_type == IEEE802154_FC_TYPE_MAC_CMD && nla_put_u8(msg, IEEE802154_ATTR_LLSEC_CMD_FRAME_ID, sl->cmd_frame_id)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); out: return -EMSGSIZE; } static int llsec_iter_seclevels(struct llsec_dump_data *data) { struct ieee802154_llsec_seclevel *pos; int rc = 0, idx = 0; list_for_each_entry(pos, &data->table->security_levels, list) { if (idx++ < data->s_idx) continue; if (ieee802154_nl_fill_seclevel(data->skb, data->portid, data->nlmsg_seq, pos, data->dev)) { rc = -EMSGSIZE; break; } data->s_idx++; } return rc; } int ieee802154_llsec_dump_seclevels(struct sk_buff *skb, struct netlink_callback *cb) { return ieee802154_llsec_dump_table(skb, cb, llsec_iter_seclevels); } |
| 117 41 43 131 131 2 37 2 133 20 19 20 18 133 120 146 122 128 128 3 126 2641 2619 146 249 57 19 2639 2620 130 17 2638 18 2650 144 144 251 2651 125 38 20 130 130 3 129 19 129 132 131 132 130 128 1 1 1 1 1 1 123 122 126 122 8 20 126 3 3 4 125 126 128 128 126 127 20 20 116 3 125 44 2634 142 2651 2629 124 121 2 136 2543 302 132 132 132 131 126 120 121 18 121 124 120 2 122 120 121 2 123 122 1 5 5 3 2 2 2 2 136 17 31 120 118 5 19 20 3 20 19 20 19 120 118 119 116 20 19 3 20 20 19 3 3 16 20 17 17 16 16 3 17 17 17 20 20 17 20 4 20 20 20 20 20 20 20 19 18 20 23 123 20 20 20 20 20 20 19 20 20 18 18 18 17 18 20 19 1 17 7 6 2 8 20 9 20 9 10 4 13 1 13 8 6 13 4 17 3 15 4 18 3 18 18 16 143 137 28 143 143 1 1 1 1 10 6 8 10 10 9 9 4 10 20 3 18 20 1 1 10 1 1 1 1 20 17 3 20 20 20 20 20 19 3 20 19 20 20 20 20 20 20 20 20 20 20 20 20 20 19 4 9 10 9 4 10 2 10 10 10 9 2624 2638 2621 2520 2107 2112 2638 2640 2621 2618 10 10 10 1 1 10 10 10 10 10 10 10 10 10 10 9 9 9 9 8 3 9 10 5 18 1 18 18 19 3 19 18 2 19 19 19 4 16 19 19 19 18 19 19 19 18 19 18 14 3 9 12 3 9 12 9 3 16 19 16 3 9 19 20 5 19 39 38 2 38 39 102 8 123 7 4 141 144 144 142 144 30 8 8 8 8 2 2 2 1 1 91 1 2 2 2 2 2 2 8 8 8 6 2 8 8 124 105 71 16 117 18 122 123 92 1 122 3 14 118 122 17 2 2 2 2 29 1 4 1 32 3 65 128 24 22 24 140 20 123 57 24 24 2 124 8 124 7 139 3 105 39 122 19 5 120 145 124 144 142 141 33 141 137 139 16 142 24 125 139 138 139 122 44 2 15 18 18 18 17 16 18 130 130 15 15 15 14 2 15 15 129 231 231 17 228 227 230 15 233 234 231 15 131 130 130 3 129 131 130 130 131 130 131 130 130 707 706 709 129 131 10 705 134 702 129 707 713 710 130 131 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 15 16 16 16 16 16 2 16 16 2 282 91 391 89 90 16 2 18 18 2 16 16 16 15 16 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 37 34 3 3 37 35 120 120 122 121 121 6 120 121 120 126 124 123 123 120 122 142 142 141 25 25 124 119 46 119 118 35 10 12 231 231 6 6 232 232 38 39 128 130 95 131 131 1 91 127 131 1 1 1 1 135 2 2 2 2 2 18 18 1 121 123 92 35 2406 2416 2410 2410 3 586 590 2407 3 2406 129 131 129 127 131 130 130 127 131 130 128 130 127 129 128 131 129 131 130 130 129 130 131 128 129 130 131 131 130 128 127 131 129 130 131 130 130 131 131 130 130 131 131 124 128 131 128 130 131 131 128 131 126 131 129 131 126 131 127 130 129 128 131 131 131 131 131 131 131 131 131 131 | 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 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 | // SPDX-License-Identifier: GPL-2.0+ /* * Maple Tree implementation * Copyright (c) 2018-2022 Oracle Corporation * Authors: Liam R. Howlett <Liam.Howlett@oracle.com> * Matthew Wilcox <willy@infradead.org> * Copyright (c) 2023 ByteDance * Author: Peng Zhang <zhangpeng.00@bytedance.com> */ /* * DOC: Interesting implementation details of the Maple Tree * * Each node type has a number of slots for entries and a number of slots for * pivots. In the case of dense nodes, the pivots are implied by the position * and are simply the slot index + the minimum of the node. * * In regular B-Tree terms, pivots are called keys. The term pivot is used to * indicate that the tree is specifying ranges. Pivots may appear in the * subtree with an entry attached to the value whereas keys are unique to a * specific position of a B-tree. Pivot values are inclusive of the slot with * the same index. * * * The following illustrates the layout of a range64 nodes slots and pivots. * * * Slots -> | 0 | 1 | 2 | ... | 12 | 13 | 14 | 15 | * ┬ ┬ ┬ ┬ ┬ ┬ ┬ ┬ ┬ * │ │ │ │ │ │ │ │ └─ Implied maximum * │ │ │ │ │ │ │ └─ Pivot 14 * │ │ │ │ │ │ └─ Pivot 13 * │ │ │ │ │ └─ Pivot 12 * │ │ │ │ └─ Pivot 11 * │ │ │ └─ Pivot 2 * │ │ └─ Pivot 1 * │ └─ Pivot 0 * └─ Implied minimum * * Slot contents: * Internal (non-leaf) nodes contain pointers to other nodes. * Leaf nodes contain entries. * * The location of interest is often referred to as an offset. All offsets have * a slot, but the last offset has an implied pivot from the node above (or * UINT_MAX for the root node. * * Ranges complicate certain write activities. When modifying any of * the B-tree variants, it is known that one entry will either be added or * deleted. When modifying the Maple Tree, one store operation may overwrite * the entire data set, or one half of the tree, or the middle half of the tree. * */ #include <linux/maple_tree.h> #include <linux/xarray.h> #include <linux/types.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/limits.h> #include <asm/barrier.h> #define CREATE_TRACE_POINTS #include <trace/events/maple_tree.h> /* * Kernel pointer hashing renders much of the maple tree dump useless as tagged * pointers get hashed to arbitrary values. * * If CONFIG_DEBUG_VM_MAPLE_TREE is set we are in a debug mode where it is * permissible to bypass this. Otherwise remain cautious and retain the hashing. * * Userland doesn't know about %px so also use %p there. */ #if defined(__KERNEL__) && defined(CONFIG_DEBUG_VM_MAPLE_TREE) #define PTR_FMT "%px" #else #define PTR_FMT "%p" #endif #define MA_ROOT_PARENT 1 /* * Maple state flags * * MA_STATE_BULK - Bulk insert mode * * MA_STATE_REBALANCE - Indicate a rebalance during bulk insert * * MA_STATE_PREALLOC - Preallocated nodes, WARN_ON allocation */ #define MA_STATE_BULK 1 #define MA_STATE_REBALANCE 2 #define MA_STATE_PREALLOC 4 #define ma_parent_ptr(x) ((struct maple_pnode *)(x)) #define mas_tree_parent(x) ((unsigned long)(x->tree) | MA_ROOT_PARENT) #define ma_mnode_ptr(x) ((struct maple_node *)(x)) #define ma_enode_ptr(x) ((struct maple_enode *)(x)) static struct kmem_cache *maple_node_cache; #ifdef CONFIG_DEBUG_MAPLE_TREE static const unsigned long mt_max[] = { [maple_dense] = MAPLE_NODE_SLOTS, [maple_leaf_64] = ULONG_MAX, [maple_range_64] = ULONG_MAX, [maple_arange_64] = ULONG_MAX, }; #define mt_node_max(x) mt_max[mte_node_type(x)] #endif static const unsigned char mt_slots[] = { [maple_dense] = MAPLE_NODE_SLOTS, [maple_leaf_64] = MAPLE_RANGE64_SLOTS, [maple_range_64] = MAPLE_RANGE64_SLOTS, [maple_arange_64] = MAPLE_ARANGE64_SLOTS, }; #define mt_slot_count(x) mt_slots[mte_node_type(x)] static const unsigned char mt_pivots[] = { [maple_dense] = 0, [maple_leaf_64] = MAPLE_RANGE64_SLOTS - 1, [maple_range_64] = MAPLE_RANGE64_SLOTS - 1, [maple_arange_64] = MAPLE_ARANGE64_SLOTS - 1, }; #define mt_pivot_count(x) mt_pivots[mte_node_type(x)] static const unsigned char mt_min_slots[] = { [maple_dense] = MAPLE_NODE_SLOTS / 2, [maple_leaf_64] = (MAPLE_RANGE64_SLOTS / 2) - 2, [maple_range_64] = (MAPLE_RANGE64_SLOTS / 2) - 2, [maple_arange_64] = (MAPLE_ARANGE64_SLOTS / 2) - 1, }; #define mt_min_slot_count(x) mt_min_slots[mte_node_type(x)] #define MAPLE_BIG_NODE_SLOTS (MAPLE_RANGE64_SLOTS * 2 + 2) #define MAPLE_BIG_NODE_GAPS (MAPLE_ARANGE64_SLOTS * 2 + 1) struct maple_big_node { unsigned long pivot[MAPLE_BIG_NODE_SLOTS - 1]; union { struct maple_enode *slot[MAPLE_BIG_NODE_SLOTS]; struct { unsigned long padding[MAPLE_BIG_NODE_GAPS]; unsigned long gap[MAPLE_BIG_NODE_GAPS]; }; }; unsigned char b_end; enum maple_type type; }; /* * The maple_subtree_state is used to build a tree to replace a segment of an * existing tree in a more atomic way. Any walkers of the older tree will hit a * dead node and restart on updates. */ struct maple_subtree_state { struct ma_state *orig_l; /* Original left side of subtree */ struct ma_state *orig_r; /* Original right side of subtree */ struct ma_state *l; /* New left side of subtree */ struct ma_state *m; /* New middle of subtree (rare) */ struct ma_state *r; /* New right side of subtree */ struct ma_topiary *free; /* nodes to be freed */ struct ma_topiary *destroy; /* Nodes to be destroyed (walked and freed) */ struct maple_big_node *bn; }; #ifdef CONFIG_KASAN_STACK /* Prevent mas_wr_bnode() from exceeding the stack frame limit */ #define noinline_for_kasan noinline_for_stack #else #define noinline_for_kasan inline #endif /* Functions */ static inline struct maple_node *mt_alloc_one(gfp_t gfp) { return kmem_cache_alloc(maple_node_cache, gfp); } static inline int mt_alloc_bulk(gfp_t gfp, size_t size, void **nodes) { return kmem_cache_alloc_bulk(maple_node_cache, gfp, size, nodes); } static inline void mt_free_one(struct maple_node *node) { kmem_cache_free(maple_node_cache, node); } static inline void mt_free_bulk(size_t size, void __rcu **nodes) { kmem_cache_free_bulk(maple_node_cache, size, (void **)nodes); } static void mt_free_rcu(struct rcu_head *head) { struct maple_node *node = container_of(head, struct maple_node, rcu); kmem_cache_free(maple_node_cache, node); } /* * ma_free_rcu() - Use rcu callback to free a maple node * @node: The node to free * * The maple tree uses the parent pointer to indicate this node is no longer in * use and will be freed. */ static void ma_free_rcu(struct maple_node *node) { WARN_ON(node->parent != ma_parent_ptr(node)); call_rcu(&node->rcu, mt_free_rcu); } static void mas_set_height(struct ma_state *mas) { unsigned int new_flags = mas->tree->ma_flags; new_flags &= ~MT_FLAGS_HEIGHT_MASK; MAS_BUG_ON(mas, mas->depth > MAPLE_HEIGHT_MAX); new_flags |= mas->depth << MT_FLAGS_HEIGHT_OFFSET; mas->tree->ma_flags = new_flags; } static unsigned int mas_mt_height(struct ma_state *mas) { return mt_height(mas->tree); } static inline unsigned int mt_attr(struct maple_tree *mt) { return mt->ma_flags & ~MT_FLAGS_HEIGHT_MASK; } static __always_inline enum maple_type mte_node_type( const struct maple_enode *entry) { return ((unsigned long)entry >> MAPLE_NODE_TYPE_SHIFT) & MAPLE_NODE_TYPE_MASK; } static __always_inline bool ma_is_dense(const enum maple_type type) { return type < maple_leaf_64; } static __always_inline bool ma_is_leaf(const enum maple_type type) { return type < maple_range_64; } static __always_inline bool mte_is_leaf(const struct maple_enode *entry) { return ma_is_leaf(mte_node_type(entry)); } /* * We also reserve values with the bottom two bits set to '10' which are * below 4096 */ static __always_inline bool mt_is_reserved(const void *entry) { return ((unsigned long)entry < MAPLE_RESERVED_RANGE) && xa_is_internal(entry); } static __always_inline void mas_set_err(struct ma_state *mas, long err) { mas->node = MA_ERROR(err); mas->status = ma_error; } static __always_inline bool mas_is_ptr(const struct ma_state *mas) { return mas->status == ma_root; } static __always_inline bool mas_is_start(const struct ma_state *mas) { return mas->status == ma_start; } static __always_inline bool mas_is_none(const struct ma_state *mas) { return mas->status == ma_none; } static __always_inline bool mas_is_paused(const struct ma_state *mas) { return mas->status == ma_pause; } static __always_inline bool mas_is_overflow(struct ma_state *mas) { return mas->status == ma_overflow; } static inline bool mas_is_underflow(struct ma_state *mas) { return mas->status == ma_underflow; } static __always_inline struct maple_node *mte_to_node( const struct maple_enode *entry) { return (struct maple_node *)((unsigned long)entry & ~MAPLE_NODE_MASK); } /* * mte_to_mat() - Convert a maple encoded node to a maple topiary node. * @entry: The maple encoded node * * Return: a maple topiary pointer */ static inline struct maple_topiary *mte_to_mat(const struct maple_enode *entry) { return (struct maple_topiary *) ((unsigned long)entry & ~MAPLE_NODE_MASK); } /* * mas_mn() - Get the maple state node. * @mas: The maple state * * Return: the maple node (not encoded - bare pointer). */ static inline struct maple_node *mas_mn(const struct ma_state *mas) { return mte_to_node(mas->node); } /* * mte_set_node_dead() - Set a maple encoded node as dead. * @mn: The maple encoded node. */ static inline void mte_set_node_dead(struct maple_enode *mn) { mte_to_node(mn)->parent = ma_parent_ptr(mte_to_node(mn)); smp_wmb(); /* Needed for RCU */ } /* Bit 1 indicates the root is a node */ #define MAPLE_ROOT_NODE 0x02 /* maple_type stored bit 3-6 */ #define MAPLE_ENODE_TYPE_SHIFT 0x03 /* Bit 2 means a NULL somewhere below */ #define MAPLE_ENODE_NULL 0x04 static inline struct maple_enode *mt_mk_node(const struct maple_node *node, enum maple_type type) { return (void *)((unsigned long)node | (type << MAPLE_ENODE_TYPE_SHIFT) | MAPLE_ENODE_NULL); } static inline void *mte_mk_root(const struct maple_enode *node) { return (void *)((unsigned long)node | MAPLE_ROOT_NODE); } static inline void *mte_safe_root(const struct maple_enode *node) { return (void *)((unsigned long)node & ~MAPLE_ROOT_NODE); } static inline void __maybe_unused *mte_set_full(const struct maple_enode *node) { return (void *)((unsigned long)node & ~MAPLE_ENODE_NULL); } static inline void __maybe_unused *mte_clear_full(const struct maple_enode *node) { return (void *)((unsigned long)node | MAPLE_ENODE_NULL); } static inline bool __maybe_unused mte_has_null(const struct maple_enode *node) { return (unsigned long)node & MAPLE_ENODE_NULL; } static __always_inline bool ma_is_root(struct maple_node *node) { return ((unsigned long)node->parent & MA_ROOT_PARENT); } static __always_inline bool mte_is_root(const struct maple_enode *node) { return ma_is_root(mte_to_node(node)); } static inline bool mas_is_root_limits(const struct ma_state *mas) { return !mas->min && mas->max == ULONG_MAX; } static __always_inline bool mt_is_alloc(struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_ALLOC_RANGE); } /* * The Parent Pointer * Excluding root, the parent pointer is 256B aligned like all other tree nodes. * When storing a 32 or 64 bit values, the offset can fit into 5 bits. The 16 * bit values need an extra bit to store the offset. This extra bit comes from * a reuse of the last bit in the node type. This is possible by using bit 1 to * indicate if bit 2 is part of the type or the slot. * * Note types: * 0x??1 = Root * 0x?00 = 16 bit nodes * 0x010 = 32 bit nodes * 0x110 = 64 bit nodes * * Slot size and alignment * 0b??1 : Root * 0b?00 : 16 bit values, type in 0-1, slot in 2-7 * 0b010 : 32 bit values, type in 0-2, slot in 3-7 * 0b110 : 64 bit values, type in 0-2, slot in 3-7 */ #define MAPLE_PARENT_ROOT 0x01 #define MAPLE_PARENT_SLOT_SHIFT 0x03 #define MAPLE_PARENT_SLOT_MASK 0xF8 #define MAPLE_PARENT_16B_SLOT_SHIFT 0x02 #define MAPLE_PARENT_16B_SLOT_MASK 0xFC #define MAPLE_PARENT_RANGE64 0x06 #define MAPLE_PARENT_RANGE32 0x04 #define MAPLE_PARENT_NOT_RANGE16 0x02 /* * mte_parent_shift() - Get the parent shift for the slot storage. * @parent: The parent pointer cast as an unsigned long * Return: The shift into that pointer to the star to of the slot */ static inline unsigned long mte_parent_shift(unsigned long parent) { /* Note bit 1 == 0 means 16B */ if (likely(parent & MAPLE_PARENT_NOT_RANGE16)) return MAPLE_PARENT_SLOT_SHIFT; return MAPLE_PARENT_16B_SLOT_SHIFT; } /* * mte_parent_slot_mask() - Get the slot mask for the parent. * @parent: The parent pointer cast as an unsigned long. * Return: The slot mask for that parent. */ static inline unsigned long mte_parent_slot_mask(unsigned long parent) { /* Note bit 1 == 0 means 16B */ if (likely(parent & MAPLE_PARENT_NOT_RANGE16)) return MAPLE_PARENT_SLOT_MASK; return MAPLE_PARENT_16B_SLOT_MASK; } /* * mas_parent_type() - Return the maple_type of the parent from the stored * parent type. * @mas: The maple state * @enode: The maple_enode to extract the parent's enum * Return: The node->parent maple_type */ static inline enum maple_type mas_parent_type(struct ma_state *mas, struct maple_enode *enode) { unsigned long p_type; p_type = (unsigned long)mte_to_node(enode)->parent; if (WARN_ON(p_type & MAPLE_PARENT_ROOT)) return 0; p_type &= MAPLE_NODE_MASK; p_type &= ~mte_parent_slot_mask(p_type); switch (p_type) { case MAPLE_PARENT_RANGE64: /* or MAPLE_PARENT_ARANGE64 */ if (mt_is_alloc(mas->tree)) return maple_arange_64; return maple_range_64; } return 0; } /* * mas_set_parent() - Set the parent node and encode the slot * @mas: The maple state * @enode: The encoded maple node. * @parent: The encoded maple node that is the parent of @enode. * @slot: The slot that @enode resides in @parent. * * Slot number is encoded in the enode->parent bit 3-6 or 2-6, depending on the * parent type. */ static inline void mas_set_parent(struct ma_state *mas, struct maple_enode *enode, const struct maple_enode *parent, unsigned char slot) { unsigned long val = (unsigned long)parent; unsigned long shift; unsigned long type; enum maple_type p_type = mte_node_type(parent); MAS_BUG_ON(mas, p_type == maple_dense); MAS_BUG_ON(mas, p_type == maple_leaf_64); switch (p_type) { case maple_range_64: case maple_arange_64: shift = MAPLE_PARENT_SLOT_SHIFT; type = MAPLE_PARENT_RANGE64; break; default: case maple_dense: case maple_leaf_64: shift = type = 0; break; } val &= ~MAPLE_NODE_MASK; /* Clear all node metadata in parent */ val |= (slot << shift) | type; mte_to_node(enode)->parent = ma_parent_ptr(val); } /* * mte_parent_slot() - get the parent slot of @enode. * @enode: The encoded maple node. * * Return: The slot in the parent node where @enode resides. */ static __always_inline unsigned int mte_parent_slot(const struct maple_enode *enode) { unsigned long val = (unsigned long)mte_to_node(enode)->parent; if (unlikely(val & MA_ROOT_PARENT)) return 0; /* * Okay to use MAPLE_PARENT_16B_SLOT_MASK as the last bit will be lost * by shift if the parent shift is MAPLE_PARENT_SLOT_SHIFT */ return (val & MAPLE_PARENT_16B_SLOT_MASK) >> mte_parent_shift(val); } /* * mte_parent() - Get the parent of @node. * @enode: The encoded maple node. * * Return: The parent maple node. */ static __always_inline struct maple_node *mte_parent(const struct maple_enode *enode) { return (void *)((unsigned long) (mte_to_node(enode)->parent) & ~MAPLE_NODE_MASK); } /* * ma_dead_node() - check if the @enode is dead. * @enode: The encoded maple node * * Return: true if dead, false otherwise. */ static __always_inline bool ma_dead_node(const struct maple_node *node) { struct maple_node *parent; /* Do not reorder reads from the node prior to the parent check */ smp_rmb(); parent = (void *)((unsigned long) node->parent & ~MAPLE_NODE_MASK); return (parent == node); } /* * mte_dead_node() - check if the @enode is dead. * @enode: The encoded maple node * * Return: true if dead, false otherwise. */ static __always_inline bool mte_dead_node(const struct maple_enode *enode) { struct maple_node *parent, *node; node = mte_to_node(enode); /* Do not reorder reads from the node prior to the parent check */ smp_rmb(); parent = mte_parent(enode); return (parent == node); } /* * mas_allocated() - Get the number of nodes allocated in a maple state. * @mas: The maple state * * The ma_state alloc member is overloaded to hold a pointer to the first * allocated node or to the number of requested nodes to allocate. If bit 0 is * set, then the alloc contains the number of requested nodes. If there is an * allocated node, then the total allocated nodes is in that node. * * Return: The total number of nodes allocated */ static inline unsigned long mas_allocated(const struct ma_state *mas) { if (!mas->alloc || ((unsigned long)mas->alloc & 0x1)) return 0; return mas->alloc->total; } /* * mas_set_alloc_req() - Set the requested number of allocations. * @mas: the maple state * @count: the number of allocations. * * The requested number of allocations is either in the first allocated node, * located in @mas->alloc->request_count, or directly in @mas->alloc if there is * no allocated node. Set the request either in the node or do the necessary * encoding to store in @mas->alloc directly. */ static inline void mas_set_alloc_req(struct ma_state *mas, unsigned long count) { if (!mas->alloc || ((unsigned long)mas->alloc & 0x1)) { if (!count) mas->alloc = NULL; else mas->alloc = (struct maple_alloc *)(((count) << 1U) | 1U); return; } mas->alloc->request_count = count; } /* * mas_alloc_req() - get the requested number of allocations. * @mas: The maple state * * The alloc count is either stored directly in @mas, or in * @mas->alloc->request_count if there is at least one node allocated. Decode * the request count if it's stored directly in @mas->alloc. * * Return: The allocation request count. */ static inline unsigned int mas_alloc_req(const struct ma_state *mas) { if ((unsigned long)mas->alloc & 0x1) return (unsigned long)(mas->alloc) >> 1; else if (mas->alloc) return mas->alloc->request_count; return 0; } /* * ma_pivots() - Get a pointer to the maple node pivots. * @node: the maple node * @type: the node type * * In the event of a dead node, this array may be %NULL * * Return: A pointer to the maple node pivots */ static inline unsigned long *ma_pivots(struct maple_node *node, enum maple_type type) { switch (type) { case maple_arange_64: return node->ma64.pivot; case maple_range_64: case maple_leaf_64: return node->mr64.pivot; case maple_dense: return NULL; } return NULL; } /* * ma_gaps() - Get a pointer to the maple node gaps. * @node: the maple node * @type: the node type * * Return: A pointer to the maple node gaps */ static inline unsigned long *ma_gaps(struct maple_node *node, enum maple_type type) { switch (type) { case maple_arange_64: return node->ma64.gap; case maple_range_64: case maple_leaf_64: case maple_dense: return NULL; } return NULL; } /* * mas_safe_pivot() - get the pivot at @piv or mas->max. * @mas: The maple state * @pivots: The pointer to the maple node pivots * @piv: The pivot to fetch * @type: The maple node type * * Return: The pivot at @piv within the limit of the @pivots array, @mas->max * otherwise. */ static __always_inline unsigned long mas_safe_pivot(const struct ma_state *mas, unsigned long *pivots, unsigned char piv, enum maple_type type) { if (piv >= mt_pivots[type]) return mas->max; return pivots[piv]; } /* * mas_safe_min() - Return the minimum for a given offset. * @mas: The maple state * @pivots: The pointer to the maple node pivots * @offset: The offset into the pivot array * * Return: The minimum range value that is contained in @offset. */ static inline unsigned long mas_safe_min(struct ma_state *mas, unsigned long *pivots, unsigned char offset) { if (likely(offset)) return pivots[offset - 1] + 1; return mas->min; } /* * mte_set_pivot() - Set a pivot to a value in an encoded maple node. * @mn: The encoded maple node * @piv: The pivot offset * @val: The value of the pivot */ static inline void mte_set_pivot(struct maple_enode *mn, unsigned char piv, unsigned long val) { struct maple_node *node = mte_to_node(mn); enum maple_type type = mte_node_type(mn); BUG_ON(piv >= mt_pivots[type]); switch (type) { case maple_range_64: case maple_leaf_64: node->mr64.pivot[piv] = val; break; case maple_arange_64: node->ma64.pivot[piv] = val; break; case maple_dense: break; } } /* * ma_slots() - Get a pointer to the maple node slots. * @mn: The maple node * @mt: The maple node type * * Return: A pointer to the maple node slots */ static inline void __rcu **ma_slots(struct maple_node *mn, enum maple_type mt) { switch (mt) { case maple_arange_64: return mn->ma64.slot; case maple_range_64: case maple_leaf_64: return mn->mr64.slot; case maple_dense: return mn->slot; } return NULL; } static inline bool mt_write_locked(const struct maple_tree *mt) { return mt_external_lock(mt) ? mt_write_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock); } static __always_inline bool mt_locked(const struct maple_tree *mt) { return mt_external_lock(mt) ? mt_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock); } static __always_inline void *mt_slot(const struct maple_tree *mt, void __rcu **slots, unsigned char offset) { return rcu_dereference_check(slots[offset], mt_locked(mt)); } static __always_inline void *mt_slot_locked(struct maple_tree *mt, void __rcu **slots, unsigned char offset) { return rcu_dereference_protected(slots[offset], mt_write_locked(mt)); } /* * mas_slot_locked() - Get the slot value when holding the maple tree lock. * @mas: The maple state * @slots: The pointer to the slots * @offset: The offset into the slots array to fetch * * Return: The entry stored in @slots at the @offset. */ static __always_inline void *mas_slot_locked(struct ma_state *mas, void __rcu **slots, unsigned char offset) { return mt_slot_locked(mas->tree, slots, offset); } /* * mas_slot() - Get the slot value when not holding the maple tree lock. * @mas: The maple state * @slots: The pointer to the slots * @offset: The offset into the slots array to fetch * * Return: The entry stored in @slots at the @offset */ static __always_inline void *mas_slot(struct ma_state *mas, void __rcu **slots, unsigned char offset) { return mt_slot(mas->tree, slots, offset); } /* * mas_root() - Get the maple tree root. * @mas: The maple state. * * Return: The pointer to the root of the tree */ static __always_inline void *mas_root(struct ma_state *mas) { return rcu_dereference_check(mas->tree->ma_root, mt_locked(mas->tree)); } static inline void *mt_root_locked(struct maple_tree *mt) { return rcu_dereference_protected(mt->ma_root, mt_write_locked(mt)); } /* * mas_root_locked() - Get the maple tree root when holding the maple tree lock. * @mas: The maple state. * * Return: The pointer to the root of the tree */ static inline void *mas_root_locked(struct ma_state *mas) { return mt_root_locked(mas->tree); } static inline struct maple_metadata *ma_meta(struct maple_node *mn, enum maple_type mt) { switch (mt) { case maple_arange_64: return &mn->ma64.meta; default: return &mn->mr64.meta; } } /* * ma_set_meta() - Set the metadata information of a node. * @mn: The maple node * @mt: The maple node type * @offset: The offset of the highest sub-gap in this node. * @end: The end of the data in this node. */ static inline void ma_set_meta(struct maple_node *mn, enum maple_type mt, unsigned char offset, unsigned char end) { struct maple_metadata *meta = ma_meta(mn, mt); meta->gap = offset; meta->end = end; } /* * mt_clear_meta() - clear the metadata information of a node, if it exists * @mt: The maple tree * @mn: The maple node * @type: The maple node type */ static inline void mt_clear_meta(struct maple_tree *mt, struct maple_node *mn, enum maple_type type) { struct maple_metadata *meta; unsigned long *pivots; void __rcu **slots; void *next; switch (type) { case maple_range_64: pivots = mn->mr64.pivot; if (unlikely(pivots[MAPLE_RANGE64_SLOTS - 2])) { slots = mn->mr64.slot; next = mt_slot_locked(mt, slots, MAPLE_RANGE64_SLOTS - 1); if (unlikely((mte_to_node(next) && mte_node_type(next)))) return; /* no metadata, could be node */ } fallthrough; case maple_arange_64: meta = ma_meta(mn, type); break; default: return; } meta->gap = 0; meta->end = 0; } /* * ma_meta_end() - Get the data end of a node from the metadata * @mn: The maple node * @mt: The maple node type */ static inline unsigned char ma_meta_end(struct maple_node *mn, enum maple_type mt) { struct maple_metadata *meta = ma_meta(mn, mt); return meta->end; } /* * ma_meta_gap() - Get the largest gap location of a node from the metadata * @mn: The maple node */ static inline unsigned char ma_meta_gap(struct maple_node *mn) { return mn->ma64.meta.gap; } /* * ma_set_meta_gap() - Set the largest gap location in a nodes metadata * @mn: The maple node * @mt: The maple node type * @offset: The location of the largest gap. */ static inline void ma_set_meta_gap(struct maple_node *mn, enum maple_type mt, unsigned char offset) { struct maple_metadata *meta = ma_meta(mn, mt); meta->gap = offset; } /* * mat_add() - Add a @dead_enode to the ma_topiary of a list of dead nodes. * @mat: the ma_topiary, a linked list of dead nodes. * @dead_enode: the node to be marked as dead and added to the tail of the list * * Add the @dead_enode to the linked list in @mat. */ static inline void mat_add(struct ma_topiary *mat, struct maple_enode *dead_enode) { mte_set_node_dead(dead_enode); mte_to_mat(dead_enode)->next = NULL; if (!mat->tail) { mat->tail = mat->head = dead_enode; return; } mte_to_mat(mat->tail)->next = dead_enode; mat->tail = dead_enode; } static void mt_free_walk(struct rcu_head *head); static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free); /* * mas_mat_destroy() - Free all nodes and subtrees in a dead list. * @mas: the maple state * @mat: the ma_topiary linked list of dead nodes to free. * * Destroy walk a dead list. */ static void mas_mat_destroy(struct ma_state *mas, struct ma_topiary *mat) { struct maple_enode *next; struct maple_node *node; bool in_rcu = mt_in_rcu(mas->tree); while (mat->head) { next = mte_to_mat(mat->head)->next; node = mte_to_node(mat->head); mt_destroy_walk(mat->head, mas->tree, !in_rcu); if (in_rcu) call_rcu(&node->rcu, mt_free_walk); mat->head = next; } } /* * mas_descend() - Descend into the slot stored in the ma_state. * @mas: the maple state. * * Note: Not RCU safe, only use in write side or debug code. */ static inline void mas_descend(struct ma_state *mas) { enum maple_type type; unsigned long *pivots; struct maple_node *node; void __rcu **slots; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); slots = ma_slots(node, type); if (mas->offset) mas->min = pivots[mas->offset - 1] + 1; mas->max = mas_safe_pivot(mas, pivots, mas->offset, type); mas->node = mas_slot(mas, slots, mas->offset); } /* * mte_set_gap() - Set a maple node gap. * @mn: The encoded maple node * @gap: The offset of the gap to set * @val: The gap value */ static inline void mte_set_gap(const struct maple_enode *mn, unsigned char gap, unsigned long val) { switch (mte_node_type(mn)) { default: break; case maple_arange_64: mte_to_node(mn)->ma64.gap[gap] = val; break; } } /* * mas_ascend() - Walk up a level of the tree. * @mas: The maple state * * Sets the @mas->max and @mas->min to the correct values when walking up. This * may cause several levels of walking up to find the correct min and max. * May find a dead node which will cause a premature return. * Return: 1 on dead node, 0 otherwise */ static int mas_ascend(struct ma_state *mas) { struct maple_enode *p_enode; /* parent enode. */ struct maple_enode *a_enode; /* ancestor enode. */ struct maple_node *a_node; /* ancestor node. */ struct maple_node *p_node; /* parent node. */ unsigned char a_slot; enum maple_type a_type; unsigned long min, max; unsigned long *pivots; bool set_max = false, set_min = false; a_node = mas_mn(mas); if (ma_is_root(a_node)) { mas->offset = 0; return 0; } p_node = mte_parent(mas->node); if (unlikely(a_node == p_node)) return 1; a_type = mas_parent_type(mas, mas->node); mas->offset = mte_parent_slot(mas->node); a_enode = mt_mk_node(p_node, a_type); /* Check to make sure all parent information is still accurate */ if (p_node != mte_parent(mas->node)) return 1; mas->node = a_enode; if (mte_is_root(a_enode)) { mas->max = ULONG_MAX; mas->min = 0; return 0; } min = 0; max = ULONG_MAX; if (!mas->offset) { min = mas->min; set_min = true; } if (mas->max == ULONG_MAX) set_max = true; do { p_enode = a_enode; a_type = mas_parent_type(mas, p_enode); a_node = mte_parent(p_enode); a_slot = mte_parent_slot(p_enode); a_enode = mt_mk_node(a_node, a_type); pivots = ma_pivots(a_node, a_type); if (unlikely(ma_dead_node(a_node))) return 1; if (!set_min && a_slot) { set_min = true; min = pivots[a_slot - 1] + 1; } if (!set_max && a_slot < mt_pivots[a_type]) { set_max = true; max = pivots[a_slot]; } if (unlikely(ma_dead_node(a_node))) return 1; if (unlikely(ma_is_root(a_node))) break; } while (!set_min || !set_max); mas->max = max; mas->min = min; return 0; } /* * mas_pop_node() - Get a previously allocated maple node from the maple state. * @mas: The maple state * * Return: A pointer to a maple node. */ static inline struct maple_node *mas_pop_node(struct ma_state *mas) { struct maple_alloc *ret, *node = mas->alloc; unsigned long total = mas_allocated(mas); unsigned int req = mas_alloc_req(mas); /* nothing or a request pending. */ if (WARN_ON(!total)) return NULL; if (total == 1) { /* single allocation in this ma_state */ mas->alloc = NULL; ret = node; goto single_node; } if (node->node_count == 1) { /* Single allocation in this node. */ mas->alloc = node->slot[0]; mas->alloc->total = node->total - 1; ret = node; goto new_head; } node->total--; ret = node->slot[--node->node_count]; node->slot[node->node_count] = NULL; single_node: new_head: if (req) { req++; mas_set_alloc_req(mas, req); } memset(ret, 0, sizeof(*ret)); return (struct maple_node *)ret; } /* * mas_push_node() - Push a node back on the maple state allocation. * @mas: The maple state * @used: The used maple node * * Stores the maple node back into @mas->alloc for reuse. Updates allocated and * requested node count as necessary. */ static inline void mas_push_node(struct ma_state *mas, struct maple_node *used) { struct maple_alloc *reuse = (struct maple_alloc *)used; struct maple_alloc *head = mas->alloc; unsigned long count; unsigned int requested = mas_alloc_req(mas); count = mas_allocated(mas); reuse->request_count = 0; reuse->node_count = 0; if (count) { if (head->node_count < MAPLE_ALLOC_SLOTS) { head->slot[head->node_count++] = reuse; head->total++; goto done; } reuse->slot[0] = head; reuse->node_count = 1; } reuse->total = count + 1; mas->alloc = reuse; done: if (requested > 1) mas_set_alloc_req(mas, requested - 1); } /* * mas_alloc_nodes() - Allocate nodes into a maple state * @mas: The maple state * @gfp: The GFP Flags */ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp) { struct maple_alloc *node; unsigned long allocated = mas_allocated(mas); unsigned int requested = mas_alloc_req(mas); unsigned int count; void **slots = NULL; unsigned int max_req = 0; if (!requested) return; mas_set_alloc_req(mas, 0); if (mas->mas_flags & MA_STATE_PREALLOC) { if (allocated) return; BUG_ON(!allocated); WARN_ON(!allocated); } if (!allocated || mas->alloc->node_count == MAPLE_ALLOC_SLOTS) { node = (struct maple_alloc *)mt_alloc_one(gfp); if (!node) goto nomem_one; if (allocated) { node->slot[0] = mas->alloc; node->node_count = 1; } else { node->node_count = 0; } mas->alloc = node; node->total = ++allocated; node->request_count = 0; requested--; } node = mas->alloc; while (requested) { max_req = MAPLE_ALLOC_SLOTS - node->node_count; slots = (void **)&node->slot[node->node_count]; max_req = min(requested, max_req); count = mt_alloc_bulk(gfp, max_req, slots); if (!count) goto nomem_bulk; if (node->node_count == 0) { node->slot[0]->node_count = 0; node->slot[0]->request_count = 0; } node->node_count += count; allocated += count; /* find a non-full node*/ do { node = node->slot[0]; } while (unlikely(node->node_count == MAPLE_ALLOC_SLOTS)); requested -= count; } mas->alloc->total = allocated; return; nomem_bulk: /* Clean up potential freed allocations on bulk failure */ memset(slots, 0, max_req * sizeof(unsigned long)); mas->alloc->total = allocated; nomem_one: mas_set_alloc_req(mas, requested); mas_set_err(mas, -ENOMEM); } /* * mas_free() - Free an encoded maple node * @mas: The maple state * @used: The encoded maple node to free. * * Uses rcu free if necessary, pushes @used back on the maple state allocations * otherwise. */ static inline void mas_free(struct ma_state *mas, struct maple_enode *used) { struct maple_node *tmp = mte_to_node(used); if (mt_in_rcu(mas->tree)) ma_free_rcu(tmp); else mas_push_node(mas, tmp); } /* * mas_node_count_gfp() - Check if enough nodes are allocated and request more * if there is not enough nodes. * @mas: The maple state * @count: The number of nodes needed * @gfp: the gfp flags */ static void mas_node_count_gfp(struct ma_state *mas, int count, gfp_t gfp) { unsigned long allocated = mas_allocated(mas); if (allocated < count) { mas_set_alloc_req(mas, count - allocated); mas_alloc_nodes(mas, gfp); } } /* * mas_node_count() - Check if enough nodes are allocated and request more if * there is not enough nodes. * @mas: The maple state * @count: The number of nodes needed * * Note: Uses GFP_NOWAIT | __GFP_NOWARN for gfp flags. */ static void mas_node_count(struct ma_state *mas, int count) { return mas_node_count_gfp(mas, count, GFP_NOWAIT | __GFP_NOWARN); } /* * mas_start() - Sets up maple state for operations. * @mas: The maple state. * * If mas->status == mas_start, then set the min, max and depth to * defaults. * * Return: * - If mas->node is an error or not mas_start, return NULL. * - If it's an empty tree: NULL & mas->status == ma_none * - If it's a single entry: The entry & mas->status == ma_root * - If it's a tree: NULL & mas->status == ma_active */ static inline struct maple_enode *mas_start(struct ma_state *mas) { if (likely(mas_is_start(mas))) { struct maple_enode *root; mas->min = 0; mas->max = ULONG_MAX; retry: mas->depth = 0; root = mas_root(mas); /* Tree with nodes */ if (likely(xa_is_node(root))) { mas->depth = 1; mas->status = ma_active; mas->node = mte_safe_root(root); mas->offset = 0; if (mte_dead_node(mas->node)) goto retry; return NULL; } mas->node = NULL; /* empty tree */ if (unlikely(!root)) { mas->status = ma_none; mas->offset = MAPLE_NODE_SLOTS; return NULL; } /* Single entry tree */ mas->status = ma_root; mas->offset = MAPLE_NODE_SLOTS; /* Single entry tree. */ if (mas->index > 0) return NULL; return root; } return NULL; } /* * ma_data_end() - Find the end of the data in a node. * @node: The maple node * @type: The maple node type * @pivots: The array of pivots in the node * @max: The maximum value in the node * * Uses metadata to find the end of the data when possible. * Return: The zero indexed last slot with data (may be null). */ static __always_inline unsigned char ma_data_end(struct maple_node *node, enum maple_type type, unsigned long *pivots, unsigned long max) { unsigned char offset; if (!pivots) return 0; if (type == maple_arange_64) return ma_meta_end(node, type); offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); if (likely(pivots[offset] == max)) return offset; return mt_pivots[type]; } /* * mas_data_end() - Find the end of the data (slot). * @mas: the maple state * * This method is optimized to check the metadata of a node if the node type * supports data end metadata. * * Return: The zero indexed last slot with data (may be null). */ static inline unsigned char mas_data_end(struct ma_state *mas) { enum maple_type type; struct maple_node *node; unsigned char offset; unsigned long *pivots; type = mte_node_type(mas->node); node = mas_mn(mas); if (type == maple_arange_64) return ma_meta_end(node, type); pivots = ma_pivots(node, type); if (unlikely(ma_dead_node(node))) return 0; offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); if (likely(pivots[offset] == mas->max)) return offset; return mt_pivots[type]; } /* * mas_leaf_max_gap() - Returns the largest gap in a leaf node * @mas: the maple state * * Return: The maximum gap in the leaf. */ static unsigned long mas_leaf_max_gap(struct ma_state *mas) { enum maple_type mt; unsigned long pstart, gap, max_gap; struct maple_node *mn; unsigned long *pivots; void __rcu **slots; unsigned char i; unsigned char max_piv; mt = mte_node_type(mas->node); mn = mas_mn(mas); slots = ma_slots(mn, mt); max_gap = 0; if (unlikely(ma_is_dense(mt))) { gap = 0; for (i = 0; i < mt_slots[mt]; i++) { if (slots[i]) { if (gap > max_gap) max_gap = gap; gap = 0; } else { gap++; } } if (gap > max_gap) max_gap = gap; return max_gap; } /* * Check the first implied pivot optimizes the loop below and slot 1 may * be skipped if there is a gap in slot 0. */ pivots = ma_pivots(mn, mt); if (likely(!slots[0])) { max_gap = pivots[0] - mas->min + 1; i = 2; } else { i = 1; } /* reduce max_piv as the special case is checked before the loop */ max_piv = ma_data_end(mn, mt, pivots, mas->max) - 1; /* * Check end implied pivot which can only be a gap on the right most * node. */ if (unlikely(mas->max == ULONG_MAX) && !slots[max_piv + 1]) { gap = ULONG_MAX - pivots[max_piv]; if (gap > max_gap) max_gap = gap; if (max_gap > pivots[max_piv] - mas->min) return max_gap; } for (; i <= max_piv; i++) { /* data == no gap. */ if (likely(slots[i])) continue; pstart = pivots[i - 1]; gap = pivots[i] - pstart; if (gap > max_gap) max_gap = gap; /* There cannot be two gaps in a row. */ i++; } return max_gap; } /* * ma_max_gap() - Get the maximum gap in a maple node (non-leaf) * @node: The maple node * @gaps: The pointer to the gaps * @mt: The maple node type * @off: Pointer to store the offset location of the gap. * * Uses the metadata data end to scan backwards across set gaps. * * Return: The maximum gap value */ static inline unsigned long ma_max_gap(struct maple_node *node, unsigned long *gaps, enum maple_type mt, unsigned char *off) { unsigned char offset, i; unsigned long max_gap = 0; i = offset = ma_meta_end(node, mt); do { if (gaps[i] > max_gap) { max_gap = gaps[i]; offset = i; } } while (i--); *off = offset; return max_gap; } /* * mas_max_gap() - find the largest gap in a non-leaf node and set the slot. * @mas: The maple state. * * Return: The gap value. */ static inline unsigned long mas_max_gap(struct ma_state *mas) { unsigned long *gaps; unsigned char offset; enum maple_type mt; struct maple_node *node; mt = mte_node_type(mas->node); if (ma_is_leaf(mt)) return mas_leaf_max_gap(mas); node = mas_mn(mas); MAS_BUG_ON(mas, mt != maple_arange_64); offset = ma_meta_gap(node); gaps = ma_gaps(node, mt); return gaps[offset]; } /* * mas_parent_gap() - Set the parent gap and any gaps above, as needed * @mas: The maple state * @offset: The gap offset in the parent to set * @new: The new gap value. * * Set the parent gap then continue to set the gap upwards, using the metadata * of the parent to see if it is necessary to check the node above. */ static inline void mas_parent_gap(struct ma_state *mas, unsigned char offset, unsigned long new) { unsigned long meta_gap = 0; struct maple_node *pnode; struct maple_enode *penode; unsigned long *pgaps; unsigned char meta_offset; enum maple_type pmt; pnode = mte_parent(mas->node); pmt = mas_parent_type(mas, mas->node); penode = mt_mk_node(pnode, pmt); pgaps = ma_gaps(pnode, pmt); ascend: MAS_BUG_ON(mas, pmt != maple_arange_64); meta_offset = ma_meta_gap(pnode); meta_gap = pgaps[meta_offset]; pgaps[offset] = new; if (meta_gap == new) return; if (offset != meta_offset) { if (meta_gap > new) return; ma_set_meta_gap(pnode, pmt, offset); } else if (new < meta_gap) { new = ma_max_gap(pnode, pgaps, pmt, &meta_offset); ma_set_meta_gap(pnode, pmt, meta_offset); } if (ma_is_root(pnode)) return; /* Go to the parent node. */ pnode = mte_parent(penode); pmt = mas_parent_type(mas, penode); pgaps = ma_gaps(pnode, pmt); offset = mte_parent_slot(penode); penode = mt_mk_node(pnode, pmt); goto ascend; } /* * mas_update_gap() - Update a nodes gaps and propagate up if necessary. * @mas: the maple state. */ static inline void mas_update_gap(struct ma_state *mas) { unsigned char pslot; unsigned long p_gap; unsigned long max_gap; if (!mt_is_alloc(mas->tree)) return; if (mte_is_root(mas->node)) return; max_gap = mas_max_gap(mas); pslot = mte_parent_slot(mas->node); p_gap = ma_gaps(mte_parent(mas->node), mas_parent_type(mas, mas->node))[pslot]; if (p_gap != max_gap) mas_parent_gap(mas, pslot, max_gap); } /* * mas_adopt_children() - Set the parent pointer of all nodes in @parent to * @parent with the slot encoded. * @mas: the maple state (for the tree) * @parent: the maple encoded node containing the children. */ static inline void mas_adopt_children(struct ma_state *mas, struct maple_enode *parent) { enum maple_type type = mte_node_type(parent); struct maple_node *node = mte_to_node(parent); void __rcu **slots = ma_slots(node, type); unsigned long *pivots = ma_pivots(node, type); struct maple_enode *child; unsigned char offset; offset = ma_data_end(node, type, pivots, mas->max); do { child = mas_slot_locked(mas, slots, offset); mas_set_parent(mas, child, parent, offset); } while (offset--); } /* * mas_put_in_tree() - Put a new node in the tree, smp_wmb(), and mark the old * node as dead. * @mas: the maple state with the new node * @old_enode: The old maple encoded node to replace. */ static inline void mas_put_in_tree(struct ma_state *mas, struct maple_enode *old_enode) __must_hold(mas->tree->ma_lock) { unsigned char offset; void __rcu **slots; if (mte_is_root(mas->node)) { mas_mn(mas)->parent = ma_parent_ptr(mas_tree_parent(mas)); rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); mas_set_height(mas); } else { offset = mte_parent_slot(mas->node); slots = ma_slots(mte_parent(mas->node), mas_parent_type(mas, mas->node)); rcu_assign_pointer(slots[offset], mas->node); } mte_set_node_dead(old_enode); } /* * mas_replace_node() - Replace a node by putting it in the tree, marking it * dead, and freeing it. * the parent encoding to locate the maple node in the tree. * @mas: the ma_state with @mas->node pointing to the new node. * @old_enode: The old maple encoded node. */ static inline void mas_replace_node(struct ma_state *mas, struct maple_enode *old_enode) __must_hold(mas->tree->ma_lock) { mas_put_in_tree(mas, old_enode); mas_free(mas, old_enode); } /* * mas_find_child() - Find a child who has the parent @mas->node. * @mas: the maple state with the parent. * @child: the maple state to store the child. */ static inline bool mas_find_child(struct ma_state *mas, struct ma_state *child) __must_hold(mas->tree->ma_lock) { enum maple_type mt; unsigned char offset; unsigned char end; unsigned long *pivots; struct maple_enode *entry; struct maple_node *node; void __rcu **slots; mt = mte_node_type(mas->node); node = mas_mn(mas); slots = ma_slots(node, mt); pivots = ma_pivots(node, mt); end = ma_data_end(node, mt, pivots, mas->max); for (offset = mas->offset; offset <= end; offset++) { entry = mas_slot_locked(mas, slots, offset); if (mte_parent(entry) == node) { *child = *mas; mas->offset = offset + 1; child->offset = offset; mas_descend(child); child->offset = 0; return true; } } return false; } /* * mab_shift_right() - Shift the data in mab right. Note, does not clean out the * old data or set b_node->b_end. * @b_node: the maple_big_node * @shift: the shift count */ static inline void mab_shift_right(struct maple_big_node *b_node, unsigned char shift) { unsigned long size = b_node->b_end * sizeof(unsigned long); memmove(b_node->pivot + shift, b_node->pivot, size); memmove(b_node->slot + shift, b_node->slot, size); if (b_node->type == maple_arange_64) memmove(b_node->gap + shift, b_node->gap, size); } /* * mab_middle_node() - Check if a middle node is needed (unlikely) * @b_node: the maple_big_node that contains the data. * @split: the potential split location * @slot_count: the size that can be stored in a single node being considered. * * Return: true if a middle node is required. */ static inline bool mab_middle_node(struct maple_big_node *b_node, int split, unsigned char slot_count) { unsigned char size = b_node->b_end; if (size >= 2 * slot_count) return true; if (!b_node->slot[split] && (size >= 2 * slot_count - 1)) return true; return false; } /* * mab_no_null_split() - ensure the split doesn't fall on a NULL * @b_node: the maple_big_node with the data * @split: the suggested split location * @slot_count: the number of slots in the node being considered. * * Return: the split location. */ static inline int mab_no_null_split(struct maple_big_node *b_node, unsigned char split, unsigned char slot_count) { if (!b_node->slot[split]) { /* * If the split is less than the max slot && the right side will * still be sufficient, then increment the split on NULL. */ if ((split < slot_count - 1) && (b_node->b_end - split) > (mt_min_slots[b_node->type])) split++; else split--; } return split; } /* * mab_calc_split() - Calculate the split location and if there needs to be two * splits. * @mas: The maple state * @bn: The maple_big_node with the data * @mid_split: The second split, if required. 0 otherwise. * * Return: The first split location. The middle split is set in @mid_split. */ static inline int mab_calc_split(struct ma_state *mas, struct maple_big_node *bn, unsigned char *mid_split, unsigned long min) { unsigned char b_end = bn->b_end; int split = b_end / 2; /* Assume equal split. */ unsigned char slot_min, slot_count = mt_slots[bn->type]; /* * To support gap tracking, all NULL entries are kept together and a node cannot * end on a NULL entry, with the exception of the left-most leaf. The * limitation means that the split of a node must be checked for this condition * and be able to put more data in one direction or the other. */ if (unlikely((mas->mas_flags & MA_STATE_BULK))) { *mid_split = 0; split = b_end - mt_min_slots[bn->type]; if (!ma_is_leaf(bn->type)) return split; mas->mas_flags |= MA_STATE_REBALANCE; if (!bn->slot[split]) split--; return split; } /* * Although extremely rare, it is possible to enter what is known as the 3-way * split scenario. The 3-way split comes about by means of a store of a range * that overwrites the end and beginning of two full nodes. The result is a set * of entries that cannot be stored in 2 nodes. Sometimes, these two nodes can * also be located in different parent nodes which are also full. This can * carry upwards all the way to the root in the worst case. */ if (unlikely(mab_middle_node(bn, split, slot_count))) { split = b_end / 3; *mid_split = split * 2; } else { slot_min = mt_min_slots[bn->type]; *mid_split = 0; /* * Avoid having a range less than the slot count unless it * causes one node to be deficient. * NOTE: mt_min_slots is 1 based, b_end and split are zero. */ while ((split < slot_count - 1) && ((bn->pivot[split] - min) < slot_count - 1) && (b_end - split > slot_min)) split++; } /* Avoid ending a node on a NULL entry */ split = mab_no_null_split(bn, split, slot_count); if (unlikely(*mid_split)) *mid_split = mab_no_null_split(bn, *mid_split, slot_count); return split; } /* * mas_mab_cp() - Copy data from a maple state inclusively to a maple_big_node * and set @b_node->b_end to the next free slot. * @mas: The maple state * @mas_start: The starting slot to copy * @mas_end: The end slot to copy (inclusively) * @b_node: The maple_big_node to place the data * @mab_start: The starting location in maple_big_node to store the data. */ static inline void mas_mab_cp(struct ma_state *mas, unsigned char mas_start, unsigned char mas_end, struct maple_big_node *b_node, unsigned char mab_start) { enum maple_type mt; struct maple_node *node; void __rcu **slots; unsigned long *pivots, *gaps; int i = mas_start, j = mab_start; unsigned char piv_end; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); if (!i) { b_node->pivot[j] = pivots[i++]; if (unlikely(i > mas_end)) goto complete; j++; } piv_end = min(mas_end, mt_pivots[mt]); for (; i < piv_end; i++, j++) { b_node->pivot[j] = pivots[i]; if (unlikely(!b_node->pivot[j])) goto complete; if (unlikely(mas->max == b_node->pivot[j])) goto complete; } b_node->pivot[j] = mas_safe_pivot(mas, pivots, i, mt); complete: b_node->b_end = ++j; j -= mab_start; slots = ma_slots(node, mt); memcpy(b_node->slot + mab_start, slots + mas_start, sizeof(void *) * j); if (!ma_is_leaf(mt) && mt_is_alloc(mas->tree)) { gaps = ma_gaps(node, mt); memcpy(b_node->gap + mab_start, gaps + mas_start, sizeof(unsigned long) * j); } } /* * mas_leaf_set_meta() - Set the metadata of a leaf if possible. * @node: The maple node * @mt: The maple type * @end: The node end */ static inline void mas_leaf_set_meta(struct maple_node *node, enum maple_type mt, unsigned char end) { if (end < mt_slots[mt] - 1) ma_set_meta(node, mt, 0, end); } /* * mab_mas_cp() - Copy data from maple_big_node to a maple encoded node. * @b_node: the maple_big_node that has the data * @mab_start: the start location in @b_node. * @mab_end: The end location in @b_node (inclusively) * @mas: The maple state with the maple encoded node. */ static inline void mab_mas_cp(struct maple_big_node *b_node, unsigned char mab_start, unsigned char mab_end, struct ma_state *mas, bool new_max) { int i, j = 0; enum maple_type mt = mte_node_type(mas->node); struct maple_node *node = mte_to_node(mas->node); void __rcu **slots = ma_slots(node, mt); unsigned long *pivots = ma_pivots(node, mt); unsigned long *gaps = NULL; unsigned char end; if (mab_end - mab_start > mt_pivots[mt]) mab_end--; if (!pivots[mt_pivots[mt] - 1]) slots[mt_pivots[mt]] = NULL; i = mab_start; do { pivots[j++] = b_node->pivot[i++]; } while (i <= mab_end && likely(b_node->pivot[i])); memcpy(slots, b_node->slot + mab_start, sizeof(void *) * (i - mab_start)); if (new_max) mas->max = b_node->pivot[i - 1]; end = j - 1; if (likely(!ma_is_leaf(mt) && mt_is_alloc(mas->tree))) { unsigned long max_gap = 0; unsigned char offset = 0; gaps = ma_gaps(node, mt); do { gaps[--j] = b_node->gap[--i]; if (gaps[j] > max_gap) { offset = j; max_gap = gaps[j]; } } while (j); ma_set_meta(node, mt, offset, end); } else { mas_leaf_set_meta(node, mt, end); } } /* * mas_bulk_rebalance() - Rebalance the end of a tree after a bulk insert. * @mas: The maple state * @end: The maple node end * @mt: The maple node type */ static inline void mas_bulk_rebalance(struct ma_state *mas, unsigned char end, enum maple_type mt) { if (!(mas->mas_flags & MA_STATE_BULK)) return; if (mte_is_root(mas->node)) return; if (end > mt_min_slots[mt]) { mas->mas_flags &= ~MA_STATE_REBALANCE; return; } } /* * mas_store_b_node() - Store an @entry into the b_node while also copying the * data from a maple encoded node. * @wr_mas: the maple write state * @b_node: the maple_big_node to fill with data * @offset_end: the offset to end copying * * Return: The actual end of the data stored in @b_node */ static noinline_for_kasan void mas_store_b_node(struct ma_wr_state *wr_mas, struct maple_big_node *b_node, unsigned char offset_end) { unsigned char slot; unsigned char b_end; /* Possible underflow of piv will wrap back to 0 before use. */ unsigned long piv; struct ma_state *mas = wr_mas->mas; b_node->type = wr_mas->type; b_end = 0; slot = mas->offset; if (slot) { /* Copy start data up to insert. */ mas_mab_cp(mas, 0, slot - 1, b_node, 0); b_end = b_node->b_end; piv = b_node->pivot[b_end - 1]; } else piv = mas->min - 1; if (piv + 1 < mas->index) { /* Handle range starting after old range */ b_node->slot[b_end] = wr_mas->content; if (!wr_mas->content) b_node->gap[b_end] = mas->index - 1 - piv; b_node->pivot[b_end++] = mas->index - 1; } /* Store the new entry. */ mas->offset = b_end; b_node->slot[b_end] = wr_mas->entry; b_node->pivot[b_end] = mas->last; /* Appended. */ if (mas->last >= mas->max) goto b_end; /* Handle new range ending before old range ends */ piv = mas_safe_pivot(mas, wr_mas->pivots, offset_end, wr_mas->type); if (piv > mas->last) { if (piv == ULONG_MAX) mas_bulk_rebalance(mas, b_node->b_end, wr_mas->type); if (offset_end != slot) wr_mas->content = mas_slot_locked(mas, wr_mas->slots, offset_end); b_node->slot[++b_end] = wr_mas->content; if (!wr_mas->content) b_node->gap[b_end] = piv - mas->last + 1; b_node->pivot[b_end] = piv; } slot = offset_end + 1; if (slot > mas->end) goto b_end; /* Copy end data to the end of the node. */ mas_mab_cp(mas, slot, mas->end + 1, b_node, ++b_end); b_node->b_end--; return; b_end: b_node->b_end = b_end; } /* * mas_prev_sibling() - Find the previous node with the same parent. * @mas: the maple state * * Return: True if there is a previous sibling, false otherwise. */ static inline bool mas_prev_sibling(struct ma_state *mas) { unsigned int p_slot = mte_parent_slot(mas->node); /* For root node, p_slot is set to 0 by mte_parent_slot(). */ if (!p_slot) return false; mas_ascend(mas); mas->offset = p_slot - 1; mas_descend(mas); return true; } /* * mas_next_sibling() - Find the next node with the same parent. * @mas: the maple state * * Return: true if there is a next sibling, false otherwise. */ static inline bool mas_next_sibling(struct ma_state *mas) { MA_STATE(parent, mas->tree, mas->index, mas->last); if (mte_is_root(mas->node)) return false; parent = *mas; mas_ascend(&parent); parent.offset = mte_parent_slot(mas->node) + 1; if (parent.offset > mas_data_end(&parent)) return false; *mas = parent; mas_descend(mas); return true; } /* * mas_node_or_none() - Set the enode and state. * @mas: the maple state * @enode: The encoded maple node. * * Set the node to the enode and the status. */ static inline void mas_node_or_none(struct ma_state *mas, struct maple_enode *enode) { if (enode) { mas->node = enode; mas->status = ma_active; } else { mas->node = NULL; mas->status = ma_none; } } /* * mas_wr_node_walk() - Find the correct offset for the index in the @mas. * If @mas->index cannot be found within the containing * node, we traverse to the last entry in the node. * @wr_mas: The maple write state * * Uses mas_slot_locked() and does not need to worry about dead nodes. */ static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char count, offset; if (unlikely(ma_is_dense(wr_mas->type))) { wr_mas->r_max = wr_mas->r_min = mas->index; mas->offset = mas->index = mas->min; return; } wr_mas->node = mas_mn(wr_mas->mas); wr_mas->pivots = ma_pivots(wr_mas->node, wr_mas->type); count = mas->end = ma_data_end(wr_mas->node, wr_mas->type, wr_mas->pivots, mas->max); offset = mas->offset; while (offset < count && mas->index > wr_mas->pivots[offset]) offset++; wr_mas->r_max = offset < count ? wr_mas->pivots[offset] : mas->max; wr_mas->r_min = mas_safe_min(mas, wr_mas->pivots, offset); wr_mas->offset_end = mas->offset = offset; } /* * mast_rebalance_next() - Rebalance against the next node * @mast: The maple subtree state */ static inline void mast_rebalance_next(struct maple_subtree_state *mast) { unsigned char b_end = mast->bn->b_end; mas_mab_cp(mast->orig_r, 0, mt_slot_count(mast->orig_r->node), mast->bn, b_end); mast->orig_r->last = mast->orig_r->max; } /* * mast_rebalance_prev() - Rebalance against the previous node * @mast: The maple subtree state */ static inline void mast_rebalance_prev(struct maple_subtree_state *mast) { unsigned char end = mas_data_end(mast->orig_l) + 1; unsigned char b_end = mast->bn->b_end; mab_shift_right(mast->bn, end); mas_mab_cp(mast->orig_l, 0, end - 1, mast->bn, 0); mast->l->min = mast->orig_l->min; mast->orig_l->index = mast->orig_l->min; mast->bn->b_end = end + b_end; mast->l->offset += end; } /* * mast_spanning_rebalance() - Rebalance nodes with nearest neighbour favouring * the node to the right. Checking the nodes to the right then the left at each * level upwards until root is reached. * Data is copied into the @mast->bn. * @mast: The maple_subtree_state. */ static inline bool mast_spanning_rebalance(struct maple_subtree_state *mast) { struct ma_state r_tmp = *mast->orig_r; struct ma_state l_tmp = *mast->orig_l; unsigned char depth = 0; do { mas_ascend(mast->orig_r); mas_ascend(mast->orig_l); depth++; if (mast->orig_r->offset < mas_data_end(mast->orig_r)) { mast->orig_r->offset++; do { mas_descend(mast->orig_r); mast->orig_r->offset = 0; } while (--depth); mast_rebalance_next(mast); *mast->orig_l = l_tmp; return true; } else if (mast->orig_l->offset != 0) { mast->orig_l->offset--; do { mas_descend(mast->orig_l); mast->orig_l->offset = mas_data_end(mast->orig_l); } while (--depth); mast_rebalance_prev(mast); *mast->orig_r = r_tmp; return true; } } while (!mte_is_root(mast->orig_r->node)); *mast->orig_r = r_tmp; *mast->orig_l = l_tmp; return false; } /* * mast_ascend() - Ascend the original left and right maple states. * @mast: the maple subtree state. * * Ascend the original left and right sides. Set the offsets to point to the * data already in the new tree (@mast->l and @mast->r). */ static inline void mast_ascend(struct maple_subtree_state *mast) { MA_WR_STATE(wr_mas, mast->orig_r, NULL); mas_ascend(mast->orig_l); mas_ascend(mast->orig_r); mast->orig_r->offset = 0; mast->orig_r->index = mast->r->max; /* last should be larger than or equal to index */ if (mast->orig_r->last < mast->orig_r->index) mast->orig_r->last = mast->orig_r->index; wr_mas.type = mte_node_type(mast->orig_r->node); mas_wr_node_walk(&wr_mas); /* Set up the left side of things */ mast->orig_l->offset = 0; mast->orig_l->index = mast->l->min; wr_mas.mas = mast->orig_l; wr_mas.type = mte_node_type(mast->orig_l->node); mas_wr_node_walk(&wr_mas); mast->bn->type = wr_mas.type; } /* * mas_new_ma_node() - Create and return a new maple node. Helper function. * @mas: the maple state with the allocations. * @b_node: the maple_big_node with the type encoding. * * Use the node type from the maple_big_node to allocate a new node from the * ma_state. This function exists mainly for code readability. * * Return: A new maple encoded node */ static inline struct maple_enode *mas_new_ma_node(struct ma_state *mas, struct maple_big_node *b_node) { return mt_mk_node(ma_mnode_ptr(mas_pop_node(mas)), b_node->type); } /* * mas_mab_to_node() - Set up right and middle nodes * * @mas: the maple state that contains the allocations. * @b_node: the node which contains the data. * @left: The pointer which will have the left node * @right: The pointer which may have the right node * @middle: the pointer which may have the middle node (rare) * @mid_split: the split location for the middle node * * Return: the split of left. */ static inline unsigned char mas_mab_to_node(struct ma_state *mas, struct maple_big_node *b_node, struct maple_enode **left, struct maple_enode **right, struct maple_enode **middle, unsigned char *mid_split, unsigned long min) { unsigned char split = 0; unsigned char slot_count = mt_slots[b_node->type]; *left = mas_new_ma_node(mas, b_node); *right = NULL; *middle = NULL; *mid_split = 0; if (b_node->b_end < slot_count) { split = b_node->b_end; } else { split = mab_calc_split(mas, b_node, mid_split, min); *right = mas_new_ma_node(mas, b_node); } if (*mid_split) *middle = mas_new_ma_node(mas, b_node); return split; } /* * mab_set_b_end() - Add entry to b_node at b_node->b_end and increment the end * pointer. * @b_node: the big node to add the entry * @mas: the maple state to get the pivot (mas->max) * @entry: the entry to add, if NULL nothing happens. */ static inline void mab_set_b_end(struct maple_big_node *b_node, struct ma_state *mas, void *entry) { if (!entry) return; b_node->slot[b_node->b_end] = entry; if (mt_is_alloc(mas->tree)) b_node->gap[b_node->b_end] = mas_max_gap(mas); b_node->pivot[b_node->b_end++] = mas->max; } /* * mas_set_split_parent() - combine_then_separate helper function. Sets the parent * of @mas->node to either @left or @right, depending on @slot and @split * * @mas: the maple state with the node that needs a parent * @left: possible parent 1 * @right: possible parent 2 * @slot: the slot the mas->node was placed * @split: the split location between @left and @right */ static inline void mas_set_split_parent(struct ma_state *mas, struct maple_enode *left, struct maple_enode *right, unsigned char *slot, unsigned char split) { if (mas_is_none(mas)) return; if ((*slot) <= split) mas_set_parent(mas, mas->node, left, *slot); else if (right) mas_set_parent(mas, mas->node, right, (*slot) - split - 1); (*slot)++; } /* * mte_mid_split_check() - Check if the next node passes the mid-split * @l: Pointer to left encoded maple node. * @m: Pointer to middle encoded maple node. * @r: Pointer to right encoded maple node. * @slot: The offset * @split: The split location. * @mid_split: The middle split. */ static inline void mte_mid_split_check(struct maple_enode **l, struct maple_enode **r, struct maple_enode *right, unsigned char slot, unsigned char *split, unsigned char mid_split) { if (*r == right) return; if (slot < mid_split) return; *l = *r; *r = right; *split = mid_split; } /* * mast_set_split_parents() - Helper function to set three nodes parents. Slot * is taken from @mast->l. * @mast: the maple subtree state * @left: the left node * @right: the right node * @split: the split location. */ static inline void mast_set_split_parents(struct maple_subtree_state *mast, struct maple_enode *left, struct maple_enode *middle, struct maple_enode *right, unsigned char split, unsigned char mid_split) { unsigned char slot; struct maple_enode *l = left; struct maple_enode *r = right; if (mas_is_none(mast->l)) return; if (middle) r = middle; slot = mast->l->offset; mte_mid_split_check(&l, &r, right, slot, &split, mid_split); mas_set_split_parent(mast->l, l, r, &slot, split); mte_mid_split_check(&l, &r, right, slot, &split, mid_split); mas_set_split_parent(mast->m, l, r, &slot, split); mte_mid_split_check(&l, &r, right, slot, &split, mid_split); mas_set_split_parent(mast->r, l, r, &slot, split); } /* * mas_topiary_node() - Dispose of a single node * @mas: The maple state for pushing nodes * @in_rcu: If the tree is in rcu mode * * The node will either be RCU freed or pushed back on the maple state. */ static inline void mas_topiary_node(struct ma_state *mas, struct ma_state *tmp_mas, bool in_rcu) { struct maple_node *tmp; struct maple_enode *enode; if (mas_is_none(tmp_mas)) return; enode = tmp_mas->node; tmp = mte_to_node(enode); mte_set_node_dead(enode); if (in_rcu) ma_free_rcu(tmp); else mas_push_node(mas, tmp); } /* * mas_topiary_replace() - Replace the data with new data, then repair the * parent links within the new tree. Iterate over the dead sub-tree and collect * the dead subtrees and topiary the nodes that are no longer of use. * * The new tree will have up to three children with the correct parent. Keep * track of the new entries as they need to be followed to find the next level * of new entries. * * The old tree will have up to three children with the old parent. Keep track * of the old entries as they may have more nodes below replaced. Nodes within * [index, last] are dead subtrees, others need to be freed and followed. * * @mas: The maple state pointing at the new data * @old_enode: The maple encoded node being replaced * */ static inline void mas_topiary_replace(struct ma_state *mas, struct maple_enode *old_enode) { struct ma_state tmp[3], tmp_next[3]; MA_TOPIARY(subtrees, mas->tree); bool in_rcu; int i, n; /* Place data in tree & then mark node as old */ mas_put_in_tree(mas, old_enode); /* Update the parent pointers in the tree */ tmp[0] = *mas; tmp[0].offset = 0; tmp[1].status = ma_none; tmp[2].status = ma_none; while (!mte_is_leaf(tmp[0].node)) { n = 0; for (i = 0; i < 3; i++) { if (mas_is_none(&tmp[i])) continue; while (n < 3) { if (!mas_find_child(&tmp[i], &tmp_next[n])) break; n++; } mas_adopt_children(&tmp[i], tmp[i].node); } if (MAS_WARN_ON(mas, n == 0)) break; while (n < 3) tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) tmp[i] = tmp_next[i]; } /* Collect the old nodes that need to be discarded */ if (mte_is_leaf(old_enode)) return mas_free(mas, old_enode); tmp[0] = *mas; tmp[0].offset = 0; tmp[0].node = old_enode; tmp[1].status = ma_none; tmp[2].status = ma_none; in_rcu = mt_in_rcu(mas->tree); do { n = 0; for (i = 0; i < 3; i++) { if (mas_is_none(&tmp[i])) continue; while (n < 3) { if (!mas_find_child(&tmp[i], &tmp_next[n])) break; if ((tmp_next[n].min >= tmp_next->index) && (tmp_next[n].max <= tmp_next->last)) { mat_add(&subtrees, tmp_next[n].node); tmp_next[n].status = ma_none; } else { n++; } } } if (MAS_WARN_ON(mas, n == 0)) break; while (n < 3) tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) { mas_topiary_node(mas, &tmp[i], in_rcu); tmp[i] = tmp_next[i]; } } while (!mte_is_leaf(tmp[0].node)); for (i = 0; i < 3; i++) mas_topiary_node(mas, &tmp[i], in_rcu); mas_mat_destroy(mas, &subtrees); } /* * mas_wmb_replace() - Write memory barrier and replace * @mas: The maple state * @old_enode: The old maple encoded node that is being replaced. * * Updates gap as necessary. */ static inline void mas_wmb_replace(struct ma_state *mas, struct maple_enode *old_enode) { /* Insert the new data in the tree */ mas_topiary_replace(mas, old_enode); if (mte_is_leaf(mas->node)) return; mas_update_gap(mas); } /* * mast_cp_to_nodes() - Copy data out to nodes. * @mast: The maple subtree state * @left: The left encoded maple node * @middle: The middle encoded maple node * @right: The right encoded maple node * @split: The location to split between left and (middle ? middle : right) * @mid_split: The location to split between middle and right. */ static inline void mast_cp_to_nodes(struct maple_subtree_state *mast, struct maple_enode *left, struct maple_enode *middle, struct maple_enode *right, unsigned char split, unsigned char mid_split) { bool new_lmax = true; mas_node_or_none(mast->l, left); mas_node_or_none(mast->m, middle); mas_node_or_none(mast->r, right); mast->l->min = mast->orig_l->min; if (split == mast->bn->b_end) { mast->l->max = mast->orig_r->max; new_lmax = false; } mab_mas_cp(mast->bn, 0, split, mast->l, new_lmax); if (middle) { mab_mas_cp(mast->bn, 1 + split, mid_split, mast->m, true); mast->m->min = mast->bn->pivot[split] + 1; split = mid_split; } mast->r->max = mast->orig_r->max; if (right) { mab_mas_cp(mast->bn, 1 + split, mast->bn->b_end, mast->r, false); mast->r->min = mast->bn->pivot[split] + 1; } } /* * mast_combine_cp_left - Copy in the original left side of the tree into the * combined data set in the maple subtree state big node. * @mast: The maple subtree state */ static inline void mast_combine_cp_left(struct maple_subtree_state *mast) { unsigned char l_slot = mast->orig_l->offset; if (!l_slot) return; mas_mab_cp(mast->orig_l, 0, l_slot - 1, mast->bn, 0); } /* * mast_combine_cp_right: Copy in the original right side of the tree into the * combined data set in the maple subtree state big node. * @mast: The maple subtree state */ static inline void mast_combine_cp_right(struct maple_subtree_state *mast) { if (mast->bn->pivot[mast->bn->b_end - 1] >= mast->orig_r->max) return; mas_mab_cp(mast->orig_r, mast->orig_r->offset + 1, mt_slot_count(mast->orig_r->node), mast->bn, mast->bn->b_end); mast->orig_r->last = mast->orig_r->max; } /* * mast_sufficient: Check if the maple subtree state has enough data in the big * node to create at least one sufficient node * @mast: the maple subtree state */ static inline bool mast_sufficient(struct maple_subtree_state *mast) { if (mast->bn->b_end > mt_min_slot_count(mast->orig_l->node)) return true; return false; } /* * mast_overflow: Check if there is too much data in the subtree state for a * single node. * @mast: The maple subtree state */ static inline bool mast_overflow(struct maple_subtree_state *mast) { if (mast->bn->b_end >= mt_slot_count(mast->orig_l->node)) return true; return false; } static inline void *mtree_range_walk(struct ma_state *mas) { unsigned long *pivots; unsigned char offset; struct maple_node *node; struct maple_enode *next, *last; enum maple_type type; void __rcu **slots; unsigned char end; unsigned long max, min; unsigned long prev_max, prev_min; next = mas->node; min = mas->min; max = mas->max; do { last = next; node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); end = ma_data_end(node, type, pivots, max); prev_min = min; prev_max = max; if (pivots[0] >= mas->index) { offset = 0; max = pivots[0]; goto next; } offset = 1; while (offset < end) { if (pivots[offset] >= mas->index) { max = pivots[offset]; break; } offset++; } min = pivots[offset - 1] + 1; next: slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); if (unlikely(ma_dead_node(node))) goto dead_node; } while (!ma_is_leaf(type)); mas->end = end; mas->offset = offset; mas->index = min; mas->last = max; mas->min = prev_min; mas->max = prev_max; mas->node = last; return (void *)next; dead_node: mas_reset(mas); return NULL; } /* * mas_spanning_rebalance() - Rebalance across two nodes which may not be peers. * @mas: The starting maple state * @mast: The maple_subtree_state, keeps track of 4 maple states. * @count: The estimated count of iterations needed. * * Follow the tree upwards from @l_mas and @r_mas for @count, or until the root * is hit. First @b_node is split into two entries which are inserted into the * next iteration of the loop. @b_node is returned populated with the final * iteration. @mas is used to obtain allocations. orig_l_mas keeps track of the * nodes that will remain active by using orig_l_mas->index and orig_l_mas->last * to account of what has been copied into the new sub-tree. The update of * orig_l_mas->last is used in mas_consume to find the slots that will need to * be either freed or destroyed. orig_l_mas->depth keeps track of the height of * the new sub-tree in case the sub-tree becomes the full tree. */ static void mas_spanning_rebalance(struct ma_state *mas, struct maple_subtree_state *mast, unsigned char count) { unsigned char split, mid_split; unsigned char slot = 0; struct maple_enode *left = NULL, *middle = NULL, *right = NULL; struct maple_enode *old_enode; MA_STATE(l_mas, mas->tree, mas->index, mas->index); MA_STATE(r_mas, mas->tree, mas->index, mas->last); MA_STATE(m_mas, mas->tree, mas->index, mas->index); /* * The tree needs to be rebalanced and leaves need to be kept at the same level. * Rebalancing is done by use of the ``struct maple_topiary``. */ mast->l = &l_mas; mast->m = &m_mas; mast->r = &r_mas; l_mas.status = r_mas.status = m_mas.status = ma_none; /* Check if this is not root and has sufficient data. */ if (((mast->orig_l->min != 0) || (mast->orig_r->max != ULONG_MAX)) && unlikely(mast->bn->b_end <= mt_min_slots[mast->bn->type])) mast_spanning_rebalance(mast); l_mas.depth = 0; /* * Each level of the tree is examined and balanced, pushing data to the left or * right, or rebalancing against left or right nodes is employed to avoid * rippling up the tree to limit the amount of churn. Once a new sub-section of * the tree is created, there may be a mix of new and old nodes. The old nodes * will have the incorrect parent pointers and currently be in two trees: the * original tree and the partially new tree. To remedy the parent pointers in * the old tree, the new data is swapped into the active tree and a walk down * the tree is performed and the parent pointers are updated. * See mas_topiary_replace() for more information. */ while (count--) { mast->bn->b_end--; mast->bn->type = mte_node_type(mast->orig_l->node); split = mas_mab_to_node(mas, mast->bn, &left, &right, &middle, &mid_split, mast->orig_l->min); mast_set_split_parents(mast, left, middle, right, split, mid_split); mast_cp_to_nodes(mast, left, middle, right, split, mid_split); /* * Copy data from next level in the tree to mast->bn from next * iteration */ memset(mast->bn, 0, sizeof(struct maple_big_node)); mast->bn->type = mte_node_type(left); l_mas.depth++; /* Root already stored in l->node. */ if (mas_is_root_limits(mast->l)) goto new_root; mast_ascend(mast); mast_combine_cp_left(mast); l_mas.offset = mast->bn->b_end; mab_set_b_end(mast->bn, &l_mas, left); mab_set_b_end(mast->bn, &m_mas, middle); mab_set_b_end(mast->bn, &r_mas, right); /* Copy anything necessary out of the right node. */ mast_combine_cp_right(mast); mast->orig_l->last = mast->orig_l->max; if (mast_sufficient(mast)) continue; if (mast_overflow(mast)) continue; /* May be a new root stored in mast->bn */ if (mas_is_root_limits(mast->orig_l)) break; mast_spanning_rebalance(mast); /* rebalancing from other nodes may require another loop. */ if (!count) count++; } l_mas.node = mt_mk_node(ma_mnode_ptr(mas_pop_node(mas)), mte_node_type(mast->orig_l->node)); l_mas.depth++; mab_mas_cp(mast->bn, 0, mt_slots[mast->bn->type] - 1, &l_mas, true); mas_set_parent(mas, left, l_mas.node, slot); if (middle) mas_set_parent(mas, middle, l_mas.node, ++slot); if (right) mas_set_parent(mas, right, l_mas.node, ++slot); if (mas_is_root_limits(mast->l)) { new_root: mas_mn(mast->l)->parent = ma_parent_ptr(mas_tree_parent(mas)); while (!mte_is_root(mast->orig_l->node)) mast_ascend(mast); } else { mas_mn(&l_mas)->parent = mas_mn(mast->orig_l)->parent; } old_enode = mast->orig_l->node; mas->depth = l_mas.depth; mas->node = l_mas.node; mas->min = l_mas.min; mas->max = l_mas.max; mas->offset = l_mas.offset; mas_wmb_replace(mas, old_enode); mtree_range_walk(mas); return; } /* * mas_rebalance() - Rebalance a given node. * @mas: The maple state * @b_node: The big maple node. * * Rebalance two nodes into a single node or two new nodes that are sufficient. * Continue upwards until tree is sufficient. */ static inline void mas_rebalance(struct ma_state *mas, struct maple_big_node *b_node) { char empty_count = mas_mt_height(mas); struct maple_subtree_state mast; unsigned char shift, b_end = ++b_node->b_end; MA_STATE(l_mas, mas->tree, mas->index, mas->last); MA_STATE(r_mas, mas->tree, mas->index, mas->last); trace_ma_op(__func__, mas); /* * Rebalancing occurs if a node is insufficient. Data is rebalanced * against the node to the right if it exists, otherwise the node to the * left of this node is rebalanced against this node. If rebalancing * causes just one node to be produced instead of two, then the parent * is also examined and rebalanced if it is insufficient. Every level * tries to combine the data in the same way. If one node contains the * entire range of the tree, then that node is used as a new root node. */ mast.orig_l = &l_mas; mast.orig_r = &r_mas; mast.bn = b_node; mast.bn->type = mte_node_type(mas->node); l_mas = r_mas = *mas; if (mas_next_sibling(&r_mas)) { mas_mab_cp(&r_mas, 0, mt_slot_count(r_mas.node), b_node, b_end); r_mas.last = r_mas.index = r_mas.max; } else { mas_prev_sibling(&l_mas); shift = mas_data_end(&l_mas) + 1; mab_shift_right(b_node, shift); mas->offset += shift; mas_mab_cp(&l_mas, 0, shift - 1, b_node, 0); b_node->b_end = shift + b_end; l_mas.index = l_mas.last = l_mas.min; } return mas_spanning_rebalance(mas, &mast, empty_count); } /* * mas_destroy_rebalance() - Rebalance left-most node while destroying the maple * state. * @mas: The maple state * @end: The end of the left-most node. * * During a mass-insert event (such as forking), it may be necessary to * rebalance the left-most node when it is not sufficient. */ static inline void mas_destroy_rebalance(struct ma_state *mas, unsigned char end) { enum maple_type mt = mte_node_type(mas->node); struct maple_node reuse, *newnode, *parent, *new_left, *left, *node; struct maple_enode *eparent, *old_eparent; unsigned char offset, tmp, split = mt_slots[mt] / 2; void __rcu **l_slots, **slots; unsigned long *l_pivs, *pivs, gap; bool in_rcu = mt_in_rcu(mas->tree); MA_STATE(l_mas, mas->tree, mas->index, mas->last); l_mas = *mas; mas_prev_sibling(&l_mas); /* set up node. */ if (in_rcu) { newnode = mas_pop_node(mas); } else { newnode = &reuse; } node = mas_mn(mas); newnode->parent = node->parent; slots = ma_slots(newnode, mt); pivs = ma_pivots(newnode, mt); left = mas_mn(&l_mas); l_slots = ma_slots(left, mt); l_pivs = ma_pivots(left, mt); if (!l_slots[split]) split++; tmp = mas_data_end(&l_mas) - split; memcpy(slots, l_slots + split + 1, sizeof(void *) * tmp); memcpy(pivs, l_pivs + split + 1, sizeof(unsigned long) * tmp); pivs[tmp] = l_mas.max; memcpy(slots + tmp, ma_slots(node, mt), sizeof(void *) * end); memcpy(pivs + tmp, ma_pivots(node, mt), sizeof(unsigned long) * end); l_mas.max = l_pivs[split]; mas->min = l_mas.max + 1; old_eparent = mt_mk_node(mte_parent(l_mas.node), mas_parent_type(&l_mas, l_mas.node)); tmp += end; if (!in_rcu) { unsigned char max_p = mt_pivots[mt]; unsigned char max_s = mt_slots[mt]; if (tmp < max_p) memset(pivs + tmp, 0, sizeof(unsigned long) * (max_p - tmp)); if (tmp < mt_slots[mt]) memset(slots + tmp, 0, sizeof(void *) * (max_s - tmp)); memcpy(node, newnode, sizeof(struct maple_node)); ma_set_meta(node, mt, 0, tmp - 1); mte_set_pivot(old_eparent, mte_parent_slot(l_mas.node), l_pivs[split]); /* Remove data from l_pivs. */ tmp = split + 1; memset(l_pivs + tmp, 0, sizeof(unsigned long) * (max_p - tmp)); memset(l_slots + tmp, 0, sizeof(void *) * (max_s - tmp)); ma_set_meta(left, mt, 0, split); eparent = old_eparent; goto done; } /* RCU requires replacing both l_mas, mas, and parent. */ mas->node = mt_mk_node(newnode, mt); ma_set_meta(newnode, mt, 0, tmp); new_left = mas_pop_node(mas); new_left->parent = left->parent; mt = mte_node_type(l_mas.node); slots = ma_slots(new_left, mt); pivs = ma_pivots(new_left, mt); memcpy(slots, l_slots, sizeof(void *) * split); memcpy(pivs, l_pivs, sizeof(unsigned long) * split); ma_set_meta(new_left, mt, 0, split); l_mas.node = mt_mk_node(new_left, mt); /* replace parent. */ offset = mte_parent_slot(mas->node); mt = mas_parent_type(&l_mas, l_mas.node); parent = mas_pop_node(mas); slots = ma_slots(parent, mt); pivs = ma_pivots(parent, mt); memcpy(parent, mte_to_node(old_eparent), sizeof(struct maple_node)); rcu_assign_pointer(slots[offset], mas->node); rcu_assign_pointer(slots[offset - 1], l_mas.node); pivs[offset - 1] = l_mas.max; eparent = mt_mk_node(parent, mt); done: gap = mas_leaf_max_gap(mas); mte_set_gap(eparent, mte_parent_slot(mas->node), gap); gap = mas_leaf_max_gap(&l_mas); mte_set_gap(eparent, mte_parent_slot(l_mas.node), gap); mas_ascend(mas); if (in_rcu) { mas_replace_node(mas, old_eparent); mas_adopt_children(mas, mas->node); } mas_update_gap(mas); } /* * mas_split_final_node() - Split the final node in a subtree operation. * @mast: the maple subtree state * @mas: The maple state * @height: The height of the tree in case it's a new root. */ static inline void mas_split_final_node(struct maple_subtree_state *mast, struct ma_state *mas, int height) { struct maple_enode *ancestor; if (mte_is_root(mas->node)) { if (mt_is_alloc(mas->tree)) mast->bn->type = maple_arange_64; else mast->bn->type = maple_range_64; mas->depth = height; } /* * Only a single node is used here, could be root. * The Big_node data should just fit in a single node. */ ancestor = mas_new_ma_node(mas, mast->bn); mas_set_parent(mas, mast->l->node, ancestor, mast->l->offset); mas_set_parent(mas, mast->r->node, ancestor, mast->r->offset); mte_to_node(ancestor)->parent = mas_mn(mas)->parent; mast->l->node = ancestor; mab_mas_cp(mast->bn, 0, mt_slots[mast->bn->type] - 1, mast->l, true); mas->offset = mast->bn->b_end - 1; } /* * mast_fill_bnode() - Copy data into the big node in the subtree state * @mast: The maple subtree state * @mas: the maple state * @skip: The number of entries to skip for new nodes insertion. */ static inline void mast_fill_bnode(struct maple_subtree_state *mast, struct ma_state *mas, unsigned char skip) { bool cp = true; unsigned char split; memset(mast->bn, 0, sizeof(struct maple_big_node)); if (mte_is_root(mas->node)) { cp = false; } else { mas_ascend(mas); mas->offset = mte_parent_slot(mas->node); } if (cp && mast->l->offset) mas_mab_cp(mas, 0, mast->l->offset - 1, mast->bn, 0); split = mast->bn->b_end; mab_set_b_end(mast->bn, mast->l, mast->l->node); mast->r->offset = mast->bn->b_end; mab_set_b_end(mast->bn, mast->r, mast->r->node); if (mast->bn->pivot[mast->bn->b_end - 1] == mas->max) cp = false; if (cp) mas_mab_cp(mas, split + skip, mt_slot_count(mas->node) - 1, mast->bn, mast->bn->b_end); mast->bn->b_end--; mast->bn->type = mte_node_type(mas->node); } /* * mast_split_data() - Split the data in the subtree state big node into regular * nodes. * @mast: The maple subtree state * @mas: The maple state * @split: The location to split the big node */ static inline void mast_split_data(struct maple_subtree_state *mast, struct ma_state *mas, unsigned char split) { unsigned char p_slot; mab_mas_cp(mast->bn, 0, split, mast->l, true); mte_set_pivot(mast->r->node, 0, mast->r->max); mab_mas_cp(mast->bn, split + 1, mast->bn->b_end, mast->r, false); mast->l->offset = mte_parent_slot(mas->node); mast->l->max = mast->bn->pivot[split]; mast->r->min = mast->l->max + 1; if (mte_is_leaf(mas->node)) return; p_slot = mast->orig_l->offset; mas_set_split_parent(mast->orig_l, mast->l->node, mast->r->node, &p_slot, split); mas_set_split_parent(mast->orig_r, mast->l->node, mast->r->node, &p_slot, split); } /* * mas_push_data() - Instead of splitting a node, it is beneficial to push the * data to the right or left node if there is room. * @mas: The maple state * @height: The current height of the maple state * @mast: The maple subtree state * @left: Push left or not. * * Keeping the height of the tree low means faster lookups. * * Return: True if pushed, false otherwise. */ static inline bool mas_push_data(struct ma_state *mas, int height, struct maple_subtree_state *mast, bool left) { unsigned char slot_total = mast->bn->b_end; unsigned char end, space, split; MA_STATE(tmp_mas, mas->tree, mas->index, mas->last); tmp_mas = *mas; tmp_mas.depth = mast->l->depth; if (left && !mas_prev_sibling(&tmp_mas)) return false; else if (!left && !mas_next_sibling(&tmp_mas)) return false; end = mas_data_end(&tmp_mas); slot_total += end; space = 2 * mt_slot_count(mas->node) - 2; /* -2 instead of -1 to ensure there isn't a triple split */ if (ma_is_leaf(mast->bn->type)) space--; if (mas->max == ULONG_MAX) space--; if (slot_total >= space) return false; /* Get the data; Fill mast->bn */ mast->bn->b_end++; if (left) { mab_shift_right(mast->bn, end + 1); mas_mab_cp(&tmp_mas, 0, end, mast->bn, 0); mast->bn->b_end = slot_total + 1; } else { mas_mab_cp(&tmp_mas, 0, end, mast->bn, mast->bn->b_end); } /* Configure mast for splitting of mast->bn */ split = mt_slots[mast->bn->type] - 2; if (left) { /* Switch mas to prev node */ *mas = tmp_mas; /* Start using mast->l for the left side. */ tmp_mas.node = mast->l->node; *mast->l = tmp_mas; } else { tmp_mas.node = mast->r->node; *mast->r = tmp_mas; split = slot_total - split; } split = mab_no_null_split(mast->bn, split, mt_slots[mast->bn->type]); /* Update parent slot for split calculation. */ if (left) mast->orig_l->offset += end + 1; mast_split_data(mast, mas, split); mast_fill_bnode(mast, mas, 2); mas_split_final_node(mast, mas, height + 1); return true; } /* * mas_split() - Split data that is too big for one node into two. * @mas: The maple state * @b_node: The maple big node */ static void mas_split(struct ma_state *mas, struct maple_big_node *b_node) { struct maple_subtree_state mast; int height = 0; unsigned char mid_split, split = 0; struct maple_enode *old; /* * Splitting is handled differently from any other B-tree; the Maple * Tree splits upwards. Splitting up means that the split operation * occurs when the walk of the tree hits the leaves and not on the way * down. The reason for splitting up is that it is impossible to know * how much space will be needed until the leaf is (or leaves are) * reached. Since overwriting data is allowed and a range could * overwrite more than one range or result in changing one entry into 3 * entries, it is impossible to know if a split is required until the * data is examined. * * Splitting is a balancing act between keeping allocations to a minimum * and avoiding a 'jitter' event where a tree is expanded to make room * for an entry followed by a contraction when the entry is removed. To * accomplish the balance, there are empty slots remaining in both left * and right nodes after a split. */ MA_STATE(l_mas, mas->tree, mas->index, mas->last); MA_STATE(r_mas, mas->tree, mas->index, mas->last); MA_STATE(prev_l_mas, mas->tree, mas->index, mas->last); MA_STATE(prev_r_mas, mas->tree, mas->index, mas->last); trace_ma_op(__func__, mas); mas->depth = mas_mt_height(mas); mast.l = &l_mas; mast.r = &r_mas; mast.orig_l = &prev_l_mas; mast.orig_r = &prev_r_mas; mast.bn = b_node; while (height++ <= mas->depth) { if (mt_slots[b_node->type] > b_node->b_end) { mas_split_final_node(&mast, mas, height); break; } l_mas = r_mas = *mas; l_mas.node = mas_new_ma_node(mas, b_node); r_mas.node = mas_new_ma_node(mas, b_node); /* * Another way that 'jitter' is avoided is to terminate a split up early if the * left or right node has space to spare. This is referred to as "pushing left" * or "pushing right" and is similar to the B* tree, except the nodes left or * right can rarely be reused due to RCU, but the ripple upwards is halted which * is a significant savings. */ /* Try to push left. */ if (mas_push_data(mas, height, &mast, true)) break; /* Try to push right. */ if (mas_push_data(mas, height, &mast, false)) break; split = mab_calc_split(mas, b_node, &mid_split, prev_l_mas.min); mast_split_data(&mast, mas, split); /* * Usually correct, mab_mas_cp in the above call overwrites * r->max. */ mast.r->max = mas->max; mast_fill_bnode(&mast, mas, 1); prev_l_mas = *mast.l; prev_r_mas = *mast.r; } /* Set the original node as dead */ old = mas->node; mas->node = l_mas.node; mas_wmb_replace(mas, old); mtree_range_walk(mas); return; } /* * mas_commit_b_node() - Commit the big node into the tree. * @wr_mas: The maple write state * @b_node: The maple big node */ static noinline_for_kasan void mas_commit_b_node(struct ma_wr_state *wr_mas, struct maple_big_node *b_node) { enum store_type type = wr_mas->mas->store_type; WARN_ON_ONCE(type != wr_rebalance && type != wr_split_store); if (type == wr_rebalance) return mas_rebalance(wr_mas->mas, b_node); return mas_split(wr_mas->mas, b_node); } /* * mas_root_expand() - Expand a root to a node * @mas: The maple state * @entry: The entry to store into the tree */ static inline void mas_root_expand(struct ma_state *mas, void *entry) { void *contents = mas_root_locked(mas); enum maple_type type = maple_leaf_64; struct maple_node *node; void __rcu **slots; unsigned long *pivots; int slot = 0; node = mas_pop_node(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); mas->status = ma_active; if (mas->index) { if (contents) { rcu_assign_pointer(slots[slot], contents); if (likely(mas->index > 1)) slot++; } pivots[slot++] = mas->index - 1; } rcu_assign_pointer(slots[slot], entry); mas->offset = slot; pivots[slot] = mas->last; if (mas->last != ULONG_MAX) pivots[++slot] = ULONG_MAX; mas->depth = 1; mas_set_height(mas); ma_set_meta(node, maple_leaf_64, 0, slot); /* swap the new root into the tree */ rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); return; } /* * mas_store_root() - Storing value into root. * @mas: The maple state * @entry: The entry to store. * * There is no root node now and we are storing a value into the root - this * function either assigns the pointer or expands into a node. */ static inline void mas_store_root(struct ma_state *mas, void *entry) { if (!entry) { if (!mas->index) rcu_assign_pointer(mas->tree->ma_root, NULL); } else if (likely((mas->last != 0) || (mas->index != 0))) mas_root_expand(mas, entry); else if (((unsigned long) (entry) & 3) == 2) mas_root_expand(mas, entry); else { rcu_assign_pointer(mas->tree->ma_root, entry); mas->status = ma_start; } } /* * mas_is_span_wr() - Check if the write needs to be treated as a write that * spans the node. * @wr_mas: The maple write state * * Spanning writes are writes that start in one node and end in another OR if * the write of a %NULL will cause the node to end with a %NULL. * * Return: True if this is a spanning write, false otherwise. */ static bool mas_is_span_wr(struct ma_wr_state *wr_mas) { unsigned long max = wr_mas->r_max; unsigned long last = wr_mas->mas->last; enum maple_type type = wr_mas->type; void *entry = wr_mas->entry; /* Contained in this pivot, fast path */ if (last < max) return false; if (ma_is_leaf(type)) { max = wr_mas->mas->max; if (last < max) return false; } if (last == max) { /* * The last entry of leaf node cannot be NULL unless it is the * rightmost node (writing ULONG_MAX), otherwise it spans slots. */ if (entry || last == ULONG_MAX) return false; } trace_ma_write(__func__, wr_mas->mas, wr_mas->r_max, entry); return true; } static inline void mas_wr_walk_descend(struct ma_wr_state *wr_mas) { wr_mas->type = mte_node_type(wr_mas->mas->node); mas_wr_node_walk(wr_mas); wr_mas->slots = ma_slots(wr_mas->node, wr_mas->type); } static inline void mas_wr_walk_traverse(struct ma_wr_state *wr_mas) { wr_mas->mas->max = wr_mas->r_max; wr_mas->mas->min = wr_mas->r_min; wr_mas->mas->node = wr_mas->content; wr_mas->mas->offset = 0; wr_mas->mas->depth++; } /* * mas_wr_walk() - Walk the tree for a write. * @wr_mas: The maple write state * * Uses mas_slot_locked() and does not need to worry about dead nodes. * * Return: True if it's contained in a node, false on spanning write. */ static bool mas_wr_walk(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; while (true) { mas_wr_walk_descend(wr_mas); if (unlikely(mas_is_span_wr(wr_mas))) return false; wr_mas->content = mas_slot_locked(mas, wr_mas->slots, mas->offset); if (ma_is_leaf(wr_mas->type)) return true; mas_wr_walk_traverse(wr_mas); } return true; } static void mas_wr_walk_index(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; while (true) { mas_wr_walk_descend(wr_mas); wr_mas->content = mas_slot_locked(mas, wr_mas->slots, mas->offset); if (ma_is_leaf(wr_mas->type)) return; mas_wr_walk_traverse(wr_mas); } } /* * mas_extend_spanning_null() - Extend a store of a %NULL to include surrounding %NULLs. * @l_wr_mas: The left maple write state * @r_wr_mas: The right maple write state */ static inline void mas_extend_spanning_null(struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas) { struct ma_state *r_mas = r_wr_mas->mas; struct ma_state *l_mas = l_wr_mas->mas; unsigned char l_slot; l_slot = l_mas->offset; if (!l_wr_mas->content) l_mas->index = l_wr_mas->r_min; if ((l_mas->index == l_wr_mas->r_min) && (l_slot && !mas_slot_locked(l_mas, l_wr_mas->slots, l_slot - 1))) { if (l_slot > 1) l_mas->index = l_wr_mas->pivots[l_slot - 2] + 1; else l_mas->index = l_mas->min; l_mas->offset = l_slot - 1; } if (!r_wr_mas->content) { if (r_mas->last < r_wr_mas->r_max) r_mas->last = r_wr_mas->r_max; r_mas->offset++; } else if ((r_mas->last == r_wr_mas->r_max) && (r_mas->last < r_mas->max) && !mas_slot_locked(r_mas, r_wr_mas->slots, r_mas->offset + 1)) { r_mas->last = mas_safe_pivot(r_mas, r_wr_mas->pivots, r_wr_mas->type, r_mas->offset + 1); r_mas->offset++; } } static inline void *mas_state_walk(struct ma_state *mas) { void *entry; entry = mas_start(mas); if (mas_is_none(mas)) return NULL; if (mas_is_ptr(mas)) return entry; return mtree_range_walk(mas); } /* * mtree_lookup_walk() - Internal quick lookup that does not keep maple state up * to date. * * @mas: The maple state. * * Note: Leaves mas in undesirable state. * Return: The entry for @mas->index or %NULL on dead node. */ static inline void *mtree_lookup_walk(struct ma_state *mas) { unsigned long *pivots; unsigned char offset; struct maple_node *node; struct maple_enode *next; enum maple_type type; void __rcu **slots; unsigned char end; next = mas->node; do { node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); end = mt_pivots[type]; offset = 0; do { if (pivots[offset] >= mas->index) break; } while (++offset < end); slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); if (unlikely(ma_dead_node(node))) goto dead_node; } while (!ma_is_leaf(type)); return (void *)next; dead_node: mas_reset(mas); return NULL; } static void mte_destroy_walk(struct maple_enode *, struct maple_tree *); /* * mas_new_root() - Create a new root node that only contains the entry passed * in. * @mas: The maple state * @entry: The entry to store. * * Only valid when the index == 0 and the last == ULONG_MAX */ static inline void mas_new_root(struct ma_state *mas, void *entry) { struct maple_enode *root = mas_root_locked(mas); enum maple_type type = maple_leaf_64; struct maple_node *node; void __rcu **slots; unsigned long *pivots; WARN_ON_ONCE(mas->index || mas->last != ULONG_MAX); if (!entry) { mas->depth = 0; mas_set_height(mas); rcu_assign_pointer(mas->tree->ma_root, entry); mas->status = ma_start; goto done; } node = mas_pop_node(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); mas->status = ma_active; rcu_assign_pointer(slots[0], entry); pivots[0] = mas->last; mas->depth = 1; mas_set_height(mas); rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); done: if (xa_is_node(root)) mte_destroy_walk(root, mas->tree); return; } /* * mas_wr_spanning_store() - Create a subtree with the store operation completed * and new nodes where necessary, then place the sub-tree in the actual tree. * Note that mas is expected to point to the node which caused the store to * span. * @wr_mas: The maple write state */ static noinline void mas_wr_spanning_store(struct ma_wr_state *wr_mas) { struct maple_subtree_state mast; struct maple_big_node b_node; struct ma_state *mas; unsigned char height; /* Left and Right side of spanning store */ MA_STATE(l_mas, NULL, 0, 0); MA_STATE(r_mas, NULL, 0, 0); MA_WR_STATE(r_wr_mas, &r_mas, wr_mas->entry); MA_WR_STATE(l_wr_mas, &l_mas, wr_mas->entry); /* * A store operation that spans multiple nodes is called a spanning * store and is handled early in the store call stack by the function * mas_is_span_wr(). When a spanning store is identified, the maple * state is duplicated. The first maple state walks the left tree path * to ``index``, the duplicate walks the right tree path to ``last``. * The data in the two nodes are combined into a single node, two nodes, * or possibly three nodes (see the 3-way split above). A ``NULL`` * written to the last entry of a node is considered a spanning store as * a rebalance is required for the operation to complete and an overflow * of data may happen. */ mas = wr_mas->mas; trace_ma_op(__func__, mas); if (unlikely(!mas->index && mas->last == ULONG_MAX)) return mas_new_root(mas, wr_mas->entry); /* * Node rebalancing may occur due to this store, so there may be three new * entries per level plus a new root. */ height = mas_mt_height(mas); /* * Set up right side. Need to get to the next offset after the spanning * store to ensure it's not NULL and to combine both the next node and * the node with the start together. */ r_mas = *mas; /* Avoid overflow, walk to next slot in the tree. */ if (r_mas.last + 1) r_mas.last++; r_mas.index = r_mas.last; mas_wr_walk_index(&r_wr_mas); r_mas.last = r_mas.index = mas->last; /* Set up left side. */ l_mas = *mas; mas_wr_walk_index(&l_wr_mas); if (!wr_mas->entry) { mas_extend_spanning_null(&l_wr_mas, &r_wr_mas); mas->offset = l_mas.offset; mas->index = l_mas.index; mas->last = l_mas.last = r_mas.last; } /* expanding NULLs may make this cover the entire range */ if (!l_mas.index && r_mas.last == ULONG_MAX) { mas_set_range(mas, 0, ULONG_MAX); return mas_new_root(mas, wr_mas->entry); } memset(&b_node, 0, sizeof(struct maple_big_node)); /* Copy l_mas and store the value in b_node. */ mas_store_b_node(&l_wr_mas, &b_node, l_mas.end); /* Copy r_mas into b_node if there is anything to copy. */ if (r_mas.max > r_mas.last) mas_mab_cp(&r_mas, r_mas.offset, r_mas.end, &b_node, b_node.b_end + 1); else b_node.b_end++; /* Stop spanning searches by searching for just index. */ l_mas.index = l_mas.last = mas->index; mast.bn = &b_node; mast.orig_l = &l_mas; mast.orig_r = &r_mas; /* Combine l_mas and r_mas and split them up evenly again. */ return mas_spanning_rebalance(mas, &mast, height + 1); } /* * mas_wr_node_store() - Attempt to store the value in a node * @wr_mas: The maple write state * * Attempts to reuse the node, but may allocate. */ static inline void mas_wr_node_store(struct ma_wr_state *wr_mas, unsigned char new_end) { struct ma_state *mas = wr_mas->mas; void __rcu **dst_slots; unsigned long *dst_pivots; unsigned char dst_offset, offset_end = wr_mas->offset_end; struct maple_node reuse, *newnode; unsigned char copy_size, node_pivots = mt_pivots[wr_mas->type]; bool in_rcu = mt_in_rcu(mas->tree); if (mas->last == wr_mas->end_piv) offset_end++; /* don't copy this offset */ else if (unlikely(wr_mas->r_max == ULONG_MAX)) mas_bulk_rebalance(mas, mas->end, wr_mas->type); /* set up node. */ if (in_rcu) { newnode = mas_pop_node(mas); } else { memset(&reuse, 0, sizeof(struct maple_node)); newnode = &reuse; } newnode->parent = mas_mn(mas)->parent; dst_pivots = ma_pivots(newnode, wr_mas->type); dst_slots = ma_slots(newnode, wr_mas->type); /* Copy from start to insert point */ memcpy(dst_pivots, wr_mas->pivots, sizeof(unsigned long) * mas->offset); memcpy(dst_slots, wr_mas->slots, sizeof(void *) * mas->offset); /* Handle insert of new range starting after old range */ if (wr_mas->r_min < mas->index) { rcu_assign_pointer(dst_slots[mas->offset], wr_mas->content); dst_pivots[mas->offset++] = mas->index - 1; } /* Store the new entry and range end. */ if (mas->offset < node_pivots) dst_pivots[mas->offset] = mas->last; rcu_assign_pointer(dst_slots[mas->offset], wr_mas->entry); /* * this range wrote to the end of the node or it overwrote the rest of * the data */ if (offset_end > mas->end) goto done; dst_offset = mas->offset + 1; /* Copy to the end of node if necessary. */ copy_size = mas->end - offset_end + 1; memcpy(dst_slots + dst_offset, wr_mas->slots + offset_end, sizeof(void *) * copy_size); memcpy(dst_pivots + dst_offset, wr_mas->pivots + offset_end, sizeof(unsigned long) * (copy_size - 1)); if (new_end < node_pivots) dst_pivots[new_end] = mas->max; done: mas_leaf_set_meta(newnode, maple_leaf_64, new_end); if (in_rcu) { struct maple_enode *old_enode = mas->node; mas->node = mt_mk_node(newnode, wr_mas->type); mas_replace_node(mas, old_enode); } else { memcpy(wr_mas->node, newnode, sizeof(struct maple_node)); } trace_ma_write(__func__, mas, 0, wr_mas->entry); mas_update_gap(mas); mas->end = new_end; return; } /* * mas_wr_slot_store: Attempt to store a value in a slot. * @wr_mas: the maple write state */ static inline void mas_wr_slot_store(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char offset = mas->offset; void __rcu **slots = wr_mas->slots; bool gap = false; gap |= !mt_slot_locked(mas->tree, slots, offset); gap |= !mt_slot_locked(mas->tree, slots, offset + 1); if (wr_mas->offset_end - offset == 1) { if (mas->index == wr_mas->r_min) { /* Overwriting the range and a part of the next one */ rcu_assign_pointer(slots[offset], wr_mas->entry); wr_mas->pivots[offset] = mas->last; } else { /* Overwriting a part of the range and the next one */ rcu_assign_pointer(slots[offset + 1], wr_mas->entry); wr_mas->pivots[offset] = mas->index - 1; mas->offset++; /* Keep mas accurate. */ } } else { WARN_ON_ONCE(mt_in_rcu(mas->tree)); /* * Expand the range, only partially overwriting the previous and * next ranges */ gap |= !mt_slot_locked(mas->tree, slots, offset + 2); rcu_assign_pointer(slots[offset + 1], wr_mas->entry); wr_mas->pivots[offset] = mas->index - 1; wr_mas->pivots[offset + 1] = mas->last; mas->offset++; /* Keep mas accurate. */ } trace_ma_write(__func__, mas, 0, wr_mas->entry); /* * Only update gap when the new entry is empty or there is an empty * entry in the original two ranges. */ if (!wr_mas->entry || gap) mas_update_gap(mas); return; } static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; if (!wr_mas->slots[wr_mas->offset_end]) { /* If this one is null, the next and prev are not */ mas->last = wr_mas->end_piv; } else { /* Check next slot(s) if we are overwriting the end */ if ((mas->last == wr_mas->end_piv) && (mas->end != wr_mas->offset_end) && !wr_mas->slots[wr_mas->offset_end + 1]) { wr_mas->offset_end++; if (wr_mas->offset_end == mas->end) mas->last = mas->max; else mas->last = wr_mas->pivots[wr_mas->offset_end]; wr_mas->end_piv = mas->last; } } if (!wr_mas->content) { /* If this one is null, the next and prev are not */ mas->index = wr_mas->r_min; } else { /* Check prev slot if we are overwriting the start */ if (mas->index == wr_mas->r_min && mas->offset && !wr_mas->slots[mas->offset - 1]) { mas->offset--; wr_mas->r_min = mas->index = mas_safe_min(mas, wr_mas->pivots, mas->offset); wr_mas->r_max = wr_mas->pivots[mas->offset]; } } } static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas) { while ((wr_mas->offset_end < wr_mas->mas->end) && (wr_mas->mas->last > wr_mas->pivots[wr_mas->offset_end])) wr_mas->offset_end++; if (wr_mas->offset_end < wr_mas->mas->end) wr_mas->end_piv = wr_mas->pivots[wr_mas->offset_end]; else wr_mas->end_piv = wr_mas->mas->max; } static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end = mas->end + 2; new_end -= wr_mas->offset_end - mas->offset; if (wr_mas->r_min == mas->index) new_end--; if (wr_mas->end_piv == mas->last) new_end--; return new_end; } /* * mas_wr_append: Attempt to append * @wr_mas: the maple write state * @new_end: The end of the node after the modification * * This is currently unsafe in rcu mode since the end of the node may be cached * by readers while the node contents may be updated which could result in * inaccurate information. */ static inline void mas_wr_append(struct ma_wr_state *wr_mas, unsigned char new_end) { struct ma_state *mas = wr_mas->mas; void __rcu **slots; unsigned char end = mas->end; if (new_end < mt_pivots[wr_mas->type]) { wr_mas->pivots[new_end] = wr_mas->pivots[end]; ma_set_meta(wr_mas->node, wr_mas->type, 0, new_end); } slots = wr_mas->slots; if (new_end == end + 1) { if (mas->last == wr_mas->r_max) { /* Append to end of range */ rcu_assign_pointer(slots[new_end], wr_mas->entry); wr_mas->pivots[end] = mas->index - 1; mas->offset = new_end; } else { /* Append to start of range */ rcu_assign_pointer(slots[new_end], wr_mas->content); wr_mas->pivots[end] = mas->last; rcu_assign_pointer(slots[end], wr_mas->entry); } } else { /* Append to the range without touching any boundaries. */ rcu_assign_pointer(slots[new_end], wr_mas->content); wr_mas->pivots[end + 1] = mas->last; rcu_assign_pointer(slots[end + 1], wr_mas->entry); wr_mas->pivots[end] = mas->index - 1; mas->offset = end + 1; } if (!wr_mas->content || !wr_mas->entry) mas_update_gap(mas); mas->end = new_end; trace_ma_write(__func__, mas, new_end, wr_mas->entry); return; } /* * mas_wr_bnode() - Slow path for a modification. * @wr_mas: The write maple state * * This is where split, rebalance end up. */ static void mas_wr_bnode(struct ma_wr_state *wr_mas) { struct maple_big_node b_node; trace_ma_write(__func__, wr_mas->mas, 0, wr_mas->entry); memset(&b_node, 0, sizeof(struct maple_big_node)); mas_store_b_node(wr_mas, &b_node, wr_mas->offset_end); mas_commit_b_node(wr_mas, &b_node); } /* * mas_wr_store_entry() - Internal call to store a value * @wr_mas: The maple write state */ static inline void mas_wr_store_entry(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end = mas_wr_new_end(wr_mas); switch (mas->store_type) { case wr_invalid: MT_BUG_ON(mas->tree, 1); return; case wr_new_root: mas_new_root(mas, wr_mas->entry); break; case wr_store_root: mas_store_root(mas, wr_mas->entry); break; case wr_exact_fit: rcu_assign_pointer(wr_mas->slots[mas->offset], wr_mas->entry); if (!!wr_mas->entry ^ !!wr_mas->content) mas_update_gap(mas); break; case wr_append: mas_wr_append(wr_mas, new_end); break; case wr_slot_store: mas_wr_slot_store(wr_mas); break; case wr_node_store: mas_wr_node_store(wr_mas, new_end); break; case wr_spanning_store: mas_wr_spanning_store(wr_mas); break; case wr_split_store: case wr_rebalance: mas_wr_bnode(wr_mas); break; } return; } static inline void mas_wr_prealloc_setup(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; if (!mas_is_active(mas)) { if (mas_is_start(mas)) goto set_content; if (unlikely(mas_is_paused(mas))) goto reset; if (unlikely(mas_is_none(mas))) goto reset; if (unlikely(mas_is_overflow(mas))) goto reset; if (unlikely(mas_is_underflow(mas))) goto reset; } /* * A less strict version of mas_is_span_wr() where we allow spanning * writes within this node. This is to stop partial walks in * mas_prealloc() from being reset. */ if (mas->last > mas->max) goto reset; if (wr_mas->entry) goto set_content; if (mte_is_leaf(mas->node) && mas->last == mas->max) goto reset; goto set_content; reset: mas_reset(mas); set_content: wr_mas->content = mas_start(mas); } /** * mas_prealloc_calc() - Calculate number of nodes needed for a * given store oepration * @mas: The maple state * @entry: The entry to store into the tree * * Return: Number of nodes required for preallocation. */ static inline int mas_prealloc_calc(struct ma_state *mas, void *entry) { int ret = mas_mt_height(mas) * 3 + 1; switch (mas->store_type) { case wr_invalid: WARN_ON_ONCE(1); break; case wr_new_root: ret = 1; break; case wr_store_root: if (likely((mas->last != 0) || (mas->index != 0))) ret = 1; else if (((unsigned long) (entry) & 3) == 2) ret = 1; else ret = 0; break; case wr_spanning_store: ret = mas_mt_height(mas) * 3 + 1; break; case wr_split_store: ret = mas_mt_height(mas) * 2 + 1; break; case wr_rebalance: ret = mas_mt_height(mas) * 2 - 1; break; case wr_node_store: ret = mt_in_rcu(mas->tree) ? 1 : 0; break; case wr_append: case wr_exact_fit: case wr_slot_store: ret = 0; } return ret; } /* * mas_wr_store_type() - Determine the store type for a given * store operation. * @wr_mas: The maple write state * * Return: the type of store needed for the operation */ static inline enum store_type mas_wr_store_type(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end; if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) return wr_store_root; if (unlikely(!mas_wr_walk(wr_mas))) return wr_spanning_store; /* At this point, we are at the leaf node that needs to be altered. */ mas_wr_end_piv(wr_mas); if (!wr_mas->entry) mas_wr_extend_null(wr_mas); if ((wr_mas->r_min == mas->index) && (wr_mas->r_max == mas->last)) return wr_exact_fit; if (unlikely(!mas->index && mas->last == ULONG_MAX)) return wr_new_root; new_end = mas_wr_new_end(wr_mas); /* Potential spanning rebalance collapsing a node */ if (new_end < mt_min_slots[wr_mas->type]) { if (!mte_is_root(mas->node) && !(mas->mas_flags & MA_STATE_BULK)) return wr_rebalance; return wr_node_store; } if (new_end >= mt_slots[wr_mas->type]) return wr_split_store; if (!mt_in_rcu(mas->tree) && (mas->offset == mas->end)) return wr_append; if ((new_end == mas->end) && (!mt_in_rcu(mas->tree) || (wr_mas->offset_end - mas->offset == 1))) return wr_slot_store; return wr_node_store; } /** * mas_wr_preallocate() - Preallocate enough nodes for a store operation * @wr_mas: The maple write state * @entry: The entry that will be stored * */ static inline void mas_wr_preallocate(struct ma_wr_state *wr_mas, void *entry) { struct ma_state *mas = wr_mas->mas; int request; mas_wr_prealloc_setup(wr_mas); mas->store_type = mas_wr_store_type(wr_mas); request = mas_prealloc_calc(mas, entry); if (!request) return; mas_node_count(mas, request); } /** * mas_insert() - Internal call to insert a value * @mas: The maple state * @entry: The entry to store * * Return: %NULL or the contents that already exists at the requested index * otherwise. The maple state needs to be checked for error conditions. */ static inline void *mas_insert(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); /* * Inserting a new range inserts either 0, 1, or 2 pivots within the * tree. If the insert fits exactly into an existing gap with a value * of NULL, then the slot only needs to be written with the new value. * If the range being inserted is adjacent to another range, then only a * single pivot needs to be inserted (as well as writing the entry). If * the new range is within a gap but does not touch any other ranges, * then two pivots need to be inserted: the start - 1, and the end. As * usual, the entry must be written. Most operations require a new node * to be allocated and replace an existing node to ensure RCU safety, * when in RCU mode. The exception to requiring a newly allocated node * is when inserting at the end of a node (appending). When done * carefully, appending can reuse the node in place. */ wr_mas.content = mas_start(mas); if (wr_mas.content) goto exists; mas_wr_preallocate(&wr_mas, entry); if (mas_is_err(mas)) return NULL; /* spanning writes always overwrite something */ if (mas->store_type == wr_spanning_store) goto exists; /* At this point, we are at the leaf node that needs to be altered. */ if (mas->store_type != wr_new_root && mas->store_type != wr_store_root) { wr_mas.offset_end = mas->offset; wr_mas.end_piv = wr_mas.r_max; if (wr_mas.content || (mas->last > wr_mas.r_max)) goto exists; } mas_wr_store_entry(&wr_mas); return wr_mas.content; exists: mas_set_err(mas, -EEXIST); return wr_mas.content; } /** * mas_alloc_cyclic() - Internal call to find somewhere to store an entry * @mas: The maple state. * @startp: Pointer to ID. * @range_lo: Lower bound of range to search. * @range_hi: Upper bound of range to search. * @entry: The entry to store. * @next: Pointer to next ID to allocate. * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 if the allocation succeeded without wrapping, 1 if the * allocation succeeded after wrapping, or -EBUSY if there are no * free entries. */ int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp) { unsigned long min = range_lo; int ret = 0; range_lo = max(min, *next); ret = mas_empty_area(mas, range_lo, range_hi, 1); if ((mas->tree->ma_flags & MT_FLAGS_ALLOC_WRAPPED) && ret == 0) { mas->tree->ma_flags &= ~MT_FLAGS_ALLOC_WRAPPED; ret = 1; } if (ret < 0 && range_lo > min) { mas_reset(mas); ret = mas_empty_area(mas, min, range_hi, 1); if (ret == 0) ret = 1; } if (ret < 0) return ret; do { mas_insert(mas, entry); } while (mas_nomem(mas, gfp)); if (mas_is_err(mas)) return xa_err(mas->node); *startp = mas->index; *next = *startp + 1; if (*next == 0) mas->tree->ma_flags |= MT_FLAGS_ALLOC_WRAPPED; mas_destroy(mas); return ret; } EXPORT_SYMBOL(mas_alloc_cyclic); static __always_inline void mas_rewalk(struct ma_state *mas, unsigned long index) { retry: mas_set(mas, index); mas_state_walk(mas); if (mas_is_start(mas)) goto retry; } static __always_inline bool mas_rewalk_if_dead(struct ma_state *mas, struct maple_node *node, const unsigned long index) { if (unlikely(ma_dead_node(node))) { mas_rewalk(mas, index); return true; } return false; } /* * mas_prev_node() - Find the prev non-null entry at the same level in the * tree. The prev value will be mas->node[mas->offset] or the status will be * ma_none. * @mas: The maple state * @min: The lower limit to search * * The prev node value will be mas->node[mas->offset] or the status will be * ma_none. * Return: 1 if the node is dead, 0 otherwise. */ static int mas_prev_node(struct ma_state *mas, unsigned long min) { enum maple_type mt; int offset, level; void __rcu **slots; struct maple_node *node; unsigned long *pivots; unsigned long max; node = mas_mn(mas); if (!mas->min) goto no_entry; max = mas->min - 1; if (max < min) goto no_entry; level = 0; do { if (ma_is_root(node)) goto no_entry; /* Walk up. */ if (unlikely(mas_ascend(mas))) return 1; offset = mas->offset; level++; node = mas_mn(mas); } while (!offset); offset--; mt = mte_node_type(mas->node); while (level > 1) { level--; slots = ma_slots(node, mt); mas->node = mas_slot(mas, slots, offset); if (unlikely(ma_dead_node(node))) return 1; mt = mte_node_type(mas->node); node = mas_mn(mas); pivots = ma_pivots(node, mt); offset = ma_data_end(node, mt, pivots, max); if (unlikely(ma_dead_node(node))) return 1; } slots = ma_slots(node, mt); mas->node = mas_slot(mas, slots, offset); pivots = ma_pivots(node, mt); if (unlikely(ma_dead_node(node))) return 1; if (likely(offset)) mas->min = pivots[offset - 1] + 1; mas->max = max; mas->offset = mas_data_end(mas); if (unlikely(mte_dead_node(mas->node))) return 1; mas->end = mas->offset; return 0; no_entry: if (unlikely(ma_dead_node(node))) return 1; mas->status = ma_underflow; return 0; } /* * mas_prev_slot() - Get the entry in the previous slot * * @mas: The maple state * @min: The minimum starting range * @empty: Can be empty * * Return: The entry in the previous slot which is possibly NULL */ static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty) { void *entry; void __rcu **slots; unsigned long pivot; enum maple_type type; unsigned long *pivots; struct maple_node *node; unsigned long save_point = mas->index; retry: node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (mas->min <= min) { pivot = mas_safe_min(mas, pivots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (pivot <= min) goto underflow; } again: if (likely(mas->offset)) { mas->offset--; mas->last = mas->index - 1; mas->index = mas_safe_min(mas, pivots, mas->offset); } else { if (mas->index <= min) goto underflow; if (mas_prev_node(mas, min)) { mas_rewalk(mas, save_point); goto retry; } if (WARN_ON_ONCE(mas_is_underflow(mas))) return NULL; mas->last = mas->max; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); mas->index = pivots[mas->offset - 1] + 1; } slots = ma_slots(node, type); entry = mas_slot(mas, slots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (likely(entry)) return entry; if (!empty) { if (mas->index <= min) { mas->status = ma_underflow; return NULL; } goto again; } return entry; underflow: mas->status = ma_underflow; return NULL; } /* * mas_next_node() - Get the next node at the same level in the tree. * @mas: The maple state * @node: The maple node * @max: The maximum pivot value to check. * * The next value will be mas->node[mas->offset] or the status will have * overflowed. * Return: 1 on dead node, 0 otherwise. */ static int mas_next_node(struct ma_state *mas, struct maple_node *node, unsigned long max) { unsigned long min; unsigned long *pivots; struct maple_enode *enode; struct maple_node *tmp; int level = 0; unsigned char node_end; enum maple_type mt; void __rcu **slots; if (mas->max >= max) goto overflow; min = mas->max + 1; level = 0; do { if (ma_is_root(node)) goto overflow; /* Walk up. */ if (unlikely(mas_ascend(mas))) return 1; level++; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); node_end = ma_data_end(node, mt, pivots, mas->max); if (unlikely(ma_dead_node(node))) return 1; } while (unlikely(mas->offset == node_end)); slots = ma_slots(node, mt); mas->offset++; enode = mas_slot(mas, slots, mas->offset); if (unlikely(ma_dead_node(node))) return 1; if (level > 1) mas->offset = 0; while (unlikely(level > 1)) { level--; mas->node = enode; node = mas_mn(mas); mt = mte_node_type(mas->node); slots = ma_slots(node, mt); enode = mas_slot(mas, slots, 0); if (unlikely(ma_dead_node(node))) return 1; } if (!mas->offset) pivots = ma_pivots(node, mt); mas->max = mas_safe_pivot(mas, pivots, mas->offset, mt); tmp = mte_to_node(enode); mt = mte_node_type(enode); pivots = ma_pivots(tmp, mt); mas->end = ma_data_end(tmp, mt, pivots, mas->max); if (unlikely(ma_dead_node(node))) return 1; mas->node = enode; mas->min = min; return 0; overflow: if (unlikely(ma_dead_node(node))) return 1; mas->status = ma_overflow; return 0; } /* * mas_next_slot() - Get the entry in the next slot * * @mas: The maple state * @max: The maximum starting range * @empty: Can be empty * * Return: The entry in the next slot which is possibly NULL */ static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty) { void __rcu **slots; unsigned long *pivots; unsigned long pivot; enum maple_type type; struct maple_node *node; unsigned long save_point = mas->last; void *entry; retry: node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (mas->max >= max) { if (likely(mas->offset < mas->end)) pivot = pivots[mas->offset]; else pivot = mas->max; if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (pivot >= max) { /* Was at the limit, next will extend beyond */ mas->status = ma_overflow; return NULL; } } if (likely(mas->offset < mas->end)) { mas->index = pivots[mas->offset] + 1; again: mas->offset++; if (likely(mas->offset < mas->end)) mas->last = pivots[mas->offset]; else mas->last = mas->max; } else { if (mas->last >= max) { mas->status = ma_overflow; return NULL; } if (mas_next_node(mas, node, max)) { mas_rewalk(mas, save_point); goto retry; } if (WARN_ON_ONCE(mas_is_overflow(mas))) return NULL; mas->offset = 0; mas->index = mas->min; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); mas->last = pivots[0]; } slots = ma_slots(node, type); entry = mt_slot(mas->tree, slots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (entry) return entry; if (!empty) { if (mas->last >= max) { mas->status = ma_overflow; return NULL; } mas->index = mas->last + 1; goto again; } return entry; } /* * mas_next_entry() - Internal function to get the next entry. * @mas: The maple state * @limit: The maximum range start. * * Set the @mas->node to the next entry and the range_start to * the beginning value for the entry. Does not check beyond @limit. * Sets @mas->index and @mas->last to the range, Does not update @mas->index and * @mas->last on overflow. * Restarts on dead nodes. * * Return: the next entry or %NULL. */ static inline void *mas_next_entry(struct ma_state *mas, unsigned long limit) { if (mas->last >= limit) { mas->status = ma_overflow; return NULL; } return mas_next_slot(mas, limit, false); } /* * mas_rev_awalk() - Internal function. Reverse allocation walk. Find the * highest gap address of a given size in a given node and descend. * @mas: The maple state * @size: The needed size. * * Return: True if found in a leaf, false otherwise. * */ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size, unsigned long *gap_min, unsigned long *gap_max) { enum maple_type type = mte_node_type(mas->node); struct maple_node *node = mas_mn(mas); unsigned long *pivots, *gaps; void __rcu **slots; unsigned long gap = 0; unsigned long max, min; unsigned char offset; if (unlikely(mas_is_err(mas))) return true; if (ma_is_dense(type)) { /* dense nodes. */ mas->offset = (unsigned char)(mas->index - mas->min); return true; } pivots = ma_pivots(node, type); slots = ma_slots(node, type); gaps = ma_gaps(node, type); offset = mas->offset; min = mas_safe_min(mas, pivots, offset); /* Skip out of bounds. */ while (mas->last < min) min = mas_safe_min(mas, pivots, --offset); max = mas_safe_pivot(mas, pivots, offset, type); while (mas->index <= max) { gap = 0; if (gaps) gap = gaps[offset]; else if (!mas_slot(mas, slots, offset)) gap = max - min + 1; if (gap) { if ((size <= gap) && (size <= mas->last - min + 1)) break; if (!gaps) { /* Skip the next slot, it cannot be a gap. */ if (offset < 2) goto ascend; offset -= 2; max = pivots[offset]; min = mas_safe_min(mas, pivots, offset); continue; } } if (!offset) goto ascend; offset--; max = min - 1; min = mas_safe_min(mas, pivots, offset); } if (unlikely((mas->index > max) || (size - 1 > max - mas->index))) goto no_space; if (unlikely(ma_is_leaf(type))) { mas->offset = offset; *gap_min = min; *gap_max = min + gap - 1; return true; } /* descend, only happens under lock. */ mas->node = mas_slot(mas, slots, offset); mas->min = min; mas->max = max; mas->offset = mas_data_end(mas); return false; ascend: if (!mte_is_root(mas->node)) return false; no_space: mas_set_err(mas, -EBUSY); return false; } static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size) { enum maple_type type = mte_node_type(mas->node); unsigned long pivot, min, gap = 0; unsigned char offset, data_end; unsigned long *gaps, *pivots; void __rcu **slots; struct maple_node *node; bool found = false; if (ma_is_dense(type)) { mas->offset = (unsigned char)(mas->index - mas->min); return true; } node = mas_mn(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); gaps = ma_gaps(node, type); offset = mas->offset; min = mas_safe_min(mas, pivots, offset); data_end = ma_data_end(node, type, pivots, mas->max); for (; offset <= data_end; offset++) { pivot = mas_safe_pivot(mas, pivots, offset, type); /* Not within lower bounds */ if (mas->index > pivot) goto next_slot; if (gaps) gap = gaps[offset]; else if (!mas_slot(mas, slots, offset)) gap = min(pivot, mas->last) - max(mas->index, min) + 1; else goto next_slot; if (gap >= size) { if (ma_is_leaf(type)) { found = true; goto done; } if (mas->index <= pivot) { mas->node = mas_slot(mas, slots, offset); mas->min = min; mas->max = pivot; offset = 0; break; } } next_slot: min = pivot + 1; if (mas->last <= pivot) { mas_set_err(mas, -EBUSY); return true; } } if (mte_is_root(mas->node)) found = true; done: mas->offset = offset; return found; } /** * mas_walk() - Search for @mas->index in the tree. * @mas: The maple state. * * mas->index and mas->last will be set to the range if there is a value. If * mas->status is ma_none, reset to ma_start * * Return: the entry at the location or %NULL. */ void *mas_walk(struct ma_state *mas) { void *entry; if (!mas_is_active(mas) || !mas_is_start(mas)) mas->status = ma_start; retry: entry = mas_state_walk(mas); if (mas_is_start(mas)) { goto retry; } else if (mas_is_none(mas)) { mas->index = 0; mas->last = ULONG_MAX; } else if (mas_is_ptr(mas)) { if (!mas->index) { mas->last = 0; return entry; } mas->index = 1; mas->last = ULONG_MAX; mas->status = ma_none; return NULL; } return entry; } EXPORT_SYMBOL_GPL(mas_walk); static inline bool mas_rewind_node(struct ma_state *mas) { unsigned char slot; do { if (mte_is_root(mas->node)) { slot = mas->offset; if (!slot) return false; } else { mas_ascend(mas); slot = mas->offset; } } while (!slot); mas->offset = --slot; return true; } /* * mas_skip_node() - Internal function. Skip over a node. * @mas: The maple state. * * Return: true if there is another node, false otherwise. */ static inline bool mas_skip_node(struct ma_state *mas) { if (mas_is_err(mas)) return false; do { if (mte_is_root(mas->node)) { if (mas->offset >= mas_data_end(mas)) { mas_set_err(mas, -EBUSY); return false; } } else { mas_ascend(mas); } } while (mas->offset >= mas_data_end(mas)); mas->offset++; return true; } /* * mas_awalk() - Allocation walk. Search from low address to high, for a gap of * @size * @mas: The maple state * @size: The size of the gap required * * Search between @mas->index and @mas->last for a gap of @size. */ static inline void mas_awalk(struct ma_state *mas, unsigned long size) { struct maple_enode *last = NULL; /* * There are 4 options: * go to child (descend) * go back to parent (ascend) * no gap found. (return, slot == MAPLE_NODE_SLOTS) * found the gap. (return, slot != MAPLE_NODE_SLOTS) */ while (!mas_is_err(mas) && !mas_anode_descend(mas, size)) { if (last == mas->node) mas_skip_node(mas); else last = mas->node; } } /* * mas_sparse_area() - Internal function. Return upper or lower limit when * searching for a gap in an empty tree. * @mas: The maple state * @min: the minimum range * @max: The maximum range * @size: The size of the gap * @fwd: Searching forward or back */ static inline int mas_sparse_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size, bool fwd) { if (!unlikely(mas_is_none(mas)) && min == 0) { min++; /* * At this time, min is increased, we need to recheck whether * the size is satisfied. */ if (min > max || max - min + 1 < size) return -EBUSY; } /* mas_is_ptr */ if (fwd) { mas->index = min; mas->last = min + size - 1; } else { mas->last = max; mas->index = max - size + 1; } return 0; } /* * mas_empty_area() - Get the lowest address within the range that is * sufficient for the size requested. * @mas: The maple state * @min: The lowest value of the range * @max: The highest value of the range * @size: The size needed */ int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size) { unsigned char offset; unsigned long *pivots; enum maple_type mt; struct maple_node *node; if (min > max) return -EINVAL; if (size == 0 || max - min < size - 1) return -EINVAL; if (mas_is_start(mas)) mas_start(mas); else if (mas->offset >= 2) mas->offset -= 2; else if (!mas_skip_node(mas)) return -EBUSY; /* Empty set */ if (mas_is_none(mas) || mas_is_ptr(mas)) return mas_sparse_area(mas, min, max, size, true); /* The start of the window can only be within these values */ mas->index = min; mas->last = max; mas_awalk(mas, size); if (unlikely(mas_is_err(mas))) return xa_err(mas->node); offset = mas->offset; if (unlikely(offset == MAPLE_NODE_SLOTS)) return -EBUSY; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); min = mas_safe_min(mas, pivots, offset); if (mas->index < min) mas->index = min; mas->last = mas->index + size - 1; mas->end = ma_data_end(node, mt, pivots, mas->max); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area); /* * mas_empty_area_rev() - Get the highest address within the range that is * sufficient for the size requested. * @mas: The maple state * @min: The lowest value of the range * @max: The highest value of the range * @size: The size needed */ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size) { struct maple_enode *last = mas->node; if (min > max) return -EINVAL; if (size == 0 || max - min < size - 1) return -EINVAL; if (mas_is_start(mas)) mas_start(mas); else if ((mas->offset < 2) && (!mas_rewind_node(mas))) return -EBUSY; if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) return mas_sparse_area(mas, min, max, size, false); else if (mas->offset >= 2) mas->offset -= 2; else mas->offset = mas_data_end(mas); /* The start of the window can only be within these values. */ mas->index = min; mas->last = max; while (!mas_rev_awalk(mas, size, &min, &max)) { if (last == mas->node) { if (!mas_rewind_node(mas)) return -EBUSY; } else { last = mas->node; } } if (mas_is_err(mas)) return xa_err(mas->node); if (unlikely(mas->offset == MAPLE_NODE_SLOTS)) return -EBUSY; /* Trim the upper limit to the max. */ if (max < mas->last) mas->last = max; mas->index = mas->last - size + 1; mas->end = mas_data_end(mas); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area_rev); /* * mte_dead_leaves() - Mark all leaves of a node as dead. * @enode: the encoded node * @mt: the maple tree * @slots: Pointer to the slot array * * Must hold the write lock. * * Return: The number of leaves marked as dead. */ static inline unsigned char mte_dead_leaves(struct maple_enode *enode, struct maple_tree *mt, void __rcu **slots) { struct maple_node *node; enum maple_type type; void *entry; int offset; for (offset = 0; offset < mt_slot_count(enode); offset++) { entry = mt_slot(mt, slots, offset); type = mte_node_type(entry); node = mte_to_node(entry); /* Use both node and type to catch LE & BE metadata */ if (!node || !type) break; mte_set_node_dead(entry); node->type = type; rcu_assign_pointer(slots[offset], node); } return offset; } /** * mte_dead_walk() - Walk down a dead tree to just before the leaves * @enode: The maple encoded node * @offset: The starting offset * * Note: This can only be used from the RCU callback context. */ static void __rcu **mte_dead_walk(struct maple_enode **enode, unsigned char offset) { struct maple_node *node, *next; void __rcu **slots = NULL; next = mte_to_node(*enode); do { *enode = ma_enode_ptr(next); node = mte_to_node(*enode); slots = ma_slots(node, node->type); next = rcu_dereference_protected(slots[offset], lock_is_held(&rcu_callback_map)); offset = 0; } while (!ma_is_leaf(next->type)); return slots; } /** * mt_free_walk() - Walk & free a tree in the RCU callback context * @head: The RCU head that's within the node. * * Note: This can only be used from the RCU callback context. */ static void mt_free_walk(struct rcu_head *head) { void __rcu **slots; struct maple_node *node, *start; struct maple_enode *enode; unsigned char offset; enum maple_type type; node = container_of(head, struct maple_node, rcu); if (ma_is_leaf(node->type)) goto free_leaf; start = node; enode = mt_mk_node(node, node->type); slots = mte_dead_walk(&enode, 0); node = mte_to_node(enode); do { mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; enode = node->piv_parent; if (mte_to_node(enode) == node) goto free_leaf; type = mte_node_type(enode); slots = ma_slots(mte_to_node(enode), type); if ((offset < mt_slots[type]) && rcu_dereference_protected(slots[offset], lock_is_held(&rcu_callback_map))) slots = mte_dead_walk(&enode, offset); node = mte_to_node(enode); } while ((node != start) || (node->slot_len < offset)); slots = ma_slots(node, node->type); mt_free_bulk(node->slot_len, slots); free_leaf: mt_free_rcu(&node->rcu); } static inline void __rcu **mte_destroy_descend(struct maple_enode **enode, struct maple_tree *mt, struct maple_enode *prev, unsigned char offset) { struct maple_node *node; struct maple_enode *next = *enode; void __rcu **slots = NULL; enum maple_type type; unsigned char next_offset = 0; do { *enode = next; node = mte_to_node(*enode); type = mte_node_type(*enode); slots = ma_slots(node, type); next = mt_slot_locked(mt, slots, next_offset); if ((mte_dead_node(next))) next = mt_slot_locked(mt, slots, ++next_offset); mte_set_node_dead(*enode); node->type = type; node->piv_parent = prev; node->parent_slot = offset; offset = next_offset; next_offset = 0; prev = *enode; } while (!mte_is_leaf(next)); return slots; } static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free) { void __rcu **slots; struct maple_node *node = mte_to_node(enode); struct maple_enode *start; if (mte_is_leaf(enode)) { node->type = mte_node_type(enode); goto free_leaf; } start = enode; slots = mte_destroy_descend(&enode, mt, start, 0); node = mte_to_node(enode); // Updated in the above call. do { enum maple_type type; unsigned char offset; struct maple_enode *parent, *tmp; node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; enode = node->piv_parent; if (mte_to_node(enode) == node) goto free_leaf; type = mte_node_type(enode); slots = ma_slots(mte_to_node(enode), type); if (offset >= mt_slots[type]) goto next; tmp = mt_slot_locked(mt, slots, offset); if (mte_node_type(tmp) && mte_to_node(tmp)) { parent = enode; enode = tmp; slots = mte_destroy_descend(&enode, mt, parent, offset); } next: node = mte_to_node(enode); } while (start != enode); node = mte_to_node(enode); node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); free_leaf: if (free) mt_free_rcu(&node->rcu); else mt_clear_meta(mt, node, node->type); } /* * mte_destroy_walk() - Free a tree or sub-tree. * @enode: the encoded maple node (maple_enode) to start * @mt: the tree to free - needed for node types. * * Must hold the write lock. */ static inline void mte_destroy_walk(struct maple_enode *enode, struct maple_tree *mt) { struct maple_node *node = mte_to_node(enode); if (mt_in_rcu(mt)) { mt_destroy_walk(enode, mt, false); call_rcu(&node->rcu, mt_free_walk); } else { mt_destroy_walk(enode, mt, true); } } /* Interface */ /** * mas_store() - Store an @entry. * @mas: The maple state. * @entry: The entry to store. * * The @mas->index and @mas->last is used to set the range for the @entry. * * Return: the first entry between mas->index and mas->last or %NULL. */ void *mas_store(struct ma_state *mas, void *entry) { int request; MA_WR_STATE(wr_mas, mas, entry); trace_ma_write(__func__, mas, 0, entry); #ifdef CONFIG_DEBUG_MAPLE_TREE if (MAS_WARN_ON(mas, mas->index > mas->last)) pr_err("Error %lX > %lX " PTR_FMT "\n", mas->index, mas->last, entry); if (mas->index > mas->last) { mas_set_err(mas, -EINVAL); return NULL; } #endif /* * Storing is the same operation as insert with the added caveat that it * can overwrite entries. Although this seems simple enough, one may * want to examine what happens if a single store operation was to * overwrite multiple entries within a self-balancing B-Tree. */ mas_wr_prealloc_setup(&wr_mas); mas->store_type = mas_wr_store_type(&wr_mas); if (mas->mas_flags & MA_STATE_PREALLOC) { mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); return wr_mas.content; } request = mas_prealloc_calc(mas, entry); if (!request) goto store; mas_node_count(mas, request); if (mas_is_err(mas)) return NULL; store: mas_wr_store_entry(&wr_mas); mas_destroy(mas); return wr_mas.content; } EXPORT_SYMBOL_GPL(mas_store); /** * mas_store_gfp() - Store a value into the tree. * @mas: The maple state * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations if necessary. * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp) { unsigned long index = mas->index; unsigned long last = mas->last; MA_WR_STATE(wr_mas, mas, entry); int ret = 0; retry: mas_wr_preallocate(&wr_mas, entry); if (unlikely(mas_nomem(mas, gfp))) { if (!entry) __mas_set_range(mas, index, last); goto retry; } if (mas_is_err(mas)) { ret = xa_err(mas->node); goto out; } mas_wr_store_entry(&wr_mas); out: mas_destroy(mas); return ret; } EXPORT_SYMBOL_GPL(mas_store_gfp); /** * mas_store_prealloc() - Store a value into the tree using memory * preallocated in the maple state. * @mas: The maple state * @entry: The entry to store. */ void mas_store_prealloc(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); if (mas->store_type == wr_store_root) { mas_wr_prealloc_setup(&wr_mas); goto store; } mas_wr_walk_descend(&wr_mas); if (mas->store_type != wr_spanning_store) { /* set wr_mas->content to current slot */ wr_mas.content = mas_slot_locked(mas, wr_mas.slots, mas->offset); mas_wr_end_piv(&wr_mas); } store: trace_ma_write(__func__, mas, 0, entry); mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); mas_destroy(mas); } EXPORT_SYMBOL_GPL(mas_store_prealloc); /** * mas_preallocate() - Preallocate enough nodes for a store operation * @mas: The maple state * @entry: The entry that will be stored * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -ENOMEM if memory could not be allocated. */ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) { MA_WR_STATE(wr_mas, mas, entry); int ret = 0; int request; mas_wr_prealloc_setup(&wr_mas); mas->store_type = mas_wr_store_type(&wr_mas); request = mas_prealloc_calc(mas, entry); if (!request) return ret; mas_node_count_gfp(mas, request, gfp); if (mas_is_err(mas)) { mas_set_alloc_req(mas, 0); ret = xa_err(mas->node); mas_destroy(mas); mas_reset(mas); return ret; } mas->mas_flags |= MA_STATE_PREALLOC; return ret; } EXPORT_SYMBOL_GPL(mas_preallocate); /* * mas_destroy() - destroy a maple state. * @mas: The maple state * * Upon completion, check the left-most node and rebalance against the node to * the right if necessary. Frees any allocated nodes associated with this maple * state. */ void mas_destroy(struct ma_state *mas) { struct maple_alloc *node; unsigned long total; /* * When using mas_for_each() to insert an expected number of elements, * it is possible that the number inserted is less than the expected * number. To fix an invalid final node, a check is performed here to * rebalance the previous node with the final node. */ if (mas->mas_flags & MA_STATE_REBALANCE) { unsigned char end; if (mas_is_err(mas)) mas_reset(mas); mas_start(mas); mtree_range_walk(mas); end = mas->end + 1; if (end < mt_min_slot_count(mas->node) - 1) mas_destroy_rebalance(mas, end); mas->mas_flags &= ~MA_STATE_REBALANCE; } mas->mas_flags &= ~(MA_STATE_BULK|MA_STATE_PREALLOC); total = mas_allocated(mas); while (total) { node = mas->alloc; mas->alloc = node->slot[0]; if (node->node_count > 1) { size_t count = node->node_count - 1; mt_free_bulk(count, (void __rcu **)&node->slot[1]); total -= count; } mt_free_one(ma_mnode_ptr(node)); total--; } mas->alloc = NULL; } EXPORT_SYMBOL_GPL(mas_destroy); /* * mas_expected_entries() - Set the expected number of entries that will be inserted. * @mas: The maple state * @nr_entries: The number of expected entries. * * This will attempt to pre-allocate enough nodes to store the expected number * of entries. The allocations will occur using the bulk allocator interface * for speed. Please call mas_destroy() on the @mas after inserting the entries * to ensure any unused nodes are freed. * * Return: 0 on success, -ENOMEM if memory could not be allocated. */ int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries) { int nonleaf_cap = MAPLE_ARANGE64_SLOTS - 2; struct maple_enode *enode = mas->node; int nr_nodes; int ret; /* * Sometimes it is necessary to duplicate a tree to a new tree, such as * forking a process and duplicating the VMAs from one tree to a new * tree. When such a situation arises, it is known that the new tree is * not going to be used until the entire tree is populated. For * performance reasons, it is best to use a bulk load with RCU disabled. * This allows for optimistic splitting that favours the left and reuse * of nodes during the operation. */ /* Optimize splitting for bulk insert in-order */ mas->mas_flags |= MA_STATE_BULK; /* * Avoid overflow, assume a gap between each entry and a trailing null. * If this is wrong, it just means allocation can happen during * insertion of entries. */ nr_nodes = max(nr_entries, nr_entries * 2 + 1); if (!mt_is_alloc(mas->tree)) nonleaf_cap = MAPLE_RANGE64_SLOTS - 2; /* Leaves; reduce slots to keep space for expansion */ nr_nodes = DIV_ROUND_UP(nr_nodes, MAPLE_RANGE64_SLOTS - 2); /* Internal nodes */ nr_nodes += DIV_ROUND_UP(nr_nodes, nonleaf_cap); /* Add working room for split (2 nodes) + new parents */ mas_node_count_gfp(mas, nr_nodes + 3, GFP_KERNEL); /* Detect if allocations run out */ mas->mas_flags |= MA_STATE_PREALLOC; if (!mas_is_err(mas)) return 0; ret = xa_err(mas->node); mas->node = enode; mas_destroy(mas); return ret; } EXPORT_SYMBOL_GPL(mas_expected_entries); static bool mas_next_setup(struct ma_state *mas, unsigned long max, void **entry) { bool was_none = mas_is_none(mas); if (unlikely(mas->last >= max)) { mas->status = ma_overflow; return true; } switch (mas->status) { case ma_active: return false; case ma_none: fallthrough; case ma_pause: mas->status = ma_start; fallthrough; case ma_start: mas_walk(mas); /* Retries on dead nodes handled by mas_walk */ break; case ma_overflow: /* Overflowed before, but the max changed */ mas->status = ma_active; break; case ma_underflow: /* The user expects the mas to be one before where it is */ mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (likely(mas_is_active(mas))) /* Fast path */ return false; if (mas_is_ptr(mas)) { *entry = NULL; if (was_none && mas->index == 0) { mas->index = mas->last = 0; return true; } mas->index = 1; mas->last = ULONG_MAX; mas->status = ma_none; return true; } if (mas_is_none(mas)) return true; return false; } /** * mas_next() - Get the next entry. * @mas: The maple state * @max: The maximum index to check. * * Returns the next entry after @mas->index. * Must hold rcu_read_lock or the write lock. * Can return the zero entry. * * Return: The next entry or %NULL */ void *mas_next(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_next_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, false); } EXPORT_SYMBOL_GPL(mas_next); /** * mas_next_range() - Advance the maple state to the next range * @mas: The maple state * @max: The maximum index to check. * * Sets @mas->index and @mas->last to the range. * Must hold rcu_read_lock or the write lock. * Can return the zero entry. * * Return: The next entry or %NULL */ void *mas_next_range(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_next_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_next_range); /** * mt_next() - get the next value in the maple tree * @mt: The maple tree * @index: The start index * @max: The maximum index to check * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * Return: The entry higher than @index or %NULL if nothing is found. */ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max) { void *entry = NULL; MA_STATE(mas, mt, index, index); rcu_read_lock(); entry = mas_next(&mas, max); rcu_read_unlock(); return entry; } EXPORT_SYMBOL_GPL(mt_next); static bool mas_prev_setup(struct ma_state *mas, unsigned long min, void **entry) { if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } switch (mas->status) { case ma_active: return false; case ma_start: break; case ma_none: fallthrough; case ma_pause: mas->status = ma_start; break; case ma_underflow: /* underflowed before but the min changed */ mas->status = ma_active; break; case ma_overflow: /* User expects mas to be one after where it is */ mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) mas_walk(mas); if (unlikely(mas_is_ptr(mas))) { if (!mas->index) { mas->status = ma_none; return true; } mas->index = mas->last = 0; *entry = mas_root(mas); return true; } if (mas_is_none(mas)) { if (mas->index) { /* Walked to out-of-range pointer? */ mas->index = mas->last = 0; mas->status = ma_root; *entry = mas_root(mas); return true; } return true; } return false; } /** * mas_prev() - Get the previous entry * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * Will reset mas to ma_start if the status is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. */ void *mas_prev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_prev_setup(mas, min, &entry)) return entry; return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_prev); /** * mas_prev_range() - Advance to the previous range * @mas: The maple state * @min: The minimum value to check. * * Sets @mas->index and @mas->last to the range. * Must hold rcu_read_lock or the write lock. * Will reset mas to ma_start if the node is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. */ void *mas_prev_range(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_prev_setup(mas, min, &entry)) return entry; return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_prev_range); /** * mt_prev() - get the previous value in the maple tree * @mt: The maple tree * @index: The start index * @min: The minimum index to check * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * Return: The entry before @index or %NULL if nothing is found. */ void *mt_prev(struct maple_tree *mt, unsigned long index, unsigned long min) { void *entry = NULL; MA_STATE(mas, mt, index, index); rcu_read_lock(); entry = mas_prev(&mas, min); rcu_read_unlock(); return entry; } EXPORT_SYMBOL_GPL(mt_prev); /** * mas_pause() - Pause a mas_find/mas_for_each to drop the lock. * @mas: The maple state to pause * * Some users need to pause a walk and drop the lock they're holding in * order to yield to a higher priority thread or carry out an operation * on an entry. Those users should call this function before they drop * the lock. It resets the @mas to be suitable for the next iteration * of the loop after the user has reacquired the lock. If most entries * found during a walk require you to call mas_pause(), the mt_for_each() * iterator may be more appropriate. * */ void mas_pause(struct ma_state *mas) { mas->status = ma_pause; mas->node = NULL; } EXPORT_SYMBOL_GPL(mas_pause); /** * mas_find_setup() - Internal function to set up mas_find*(). * @mas: The maple state * @max: The maximum index * @entry: Pointer to the entry * * Returns: True if entry is the answer, false otherwise. */ static __always_inline bool mas_find_setup(struct ma_state *mas, unsigned long max, void **entry) { switch (mas->status) { case ma_active: if (mas->last < max) return false; return true; case ma_start: break; case ma_pause: if (unlikely(mas->last >= max)) return true; mas->index = ++mas->last; mas->status = ma_start; break; case ma_none: if (unlikely(mas->last >= max)) return true; mas->index = mas->last; mas->status = ma_start; break; case ma_underflow: /* mas is pointing at entry before unable to go lower */ if (unlikely(mas->index >= max)) { mas->status = ma_overflow; return true; } mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; break; case ma_overflow: if (unlikely(mas->last >= max)) return true; mas->status = ma_active; *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) { /* First run or continue */ if (mas->index > max) return true; *entry = mas_walk(mas); if (*entry) return true; } if (unlikely(mas_is_ptr(mas))) goto ptr_out_of_range; if (unlikely(mas_is_none(mas))) return true; if (mas->index == max) return true; return false; ptr_out_of_range: mas->status = ma_none; mas->index = 1; mas->last = ULONG_MAX; return true; } /** * mas_find() - On the first call, find the entry at or after mas->index up to * %max. Otherwise, find the entry after mas->index. * @mas: The maple state * @max: The maximum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ void *mas_find(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_find_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ entry = mas_next_slot(mas, max, false); /* Ignore overflow */ mas->status = ma_active; return entry; } EXPORT_SYMBOL_GPL(mas_find); /** * mas_find_range() - On the first call, find the entry at or after * mas->index up to %max. Otherwise, advance to the next slot mas->index. * @mas: The maple state * @max: The maximum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ void *mas_find_range(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_find_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_find_range); /** * mas_find_rev_setup() - Internal function to set up mas_find_*_rev() * @mas: The maple state * @min: The minimum index * @entry: Pointer to the entry * * Returns: True if entry is the answer, false otherwise. */ static bool mas_find_rev_setup(struct ma_state *mas, unsigned long min, void **entry) { switch (mas->status) { case ma_active: goto active; case ma_start: break; case ma_pause: if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } mas->last = --mas->index; mas->status = ma_start; break; case ma_none: if (mas->index <= min) goto none; mas->last = mas->index; mas->status = ma_start; break; case ma_overflow: /* user expects the mas to be one after where it is */ if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } mas->status = ma_active; break; case ma_underflow: /* user expects the mas to be one before where it is */ if (unlikely(mas->index <= min)) return true; mas->status = ma_active; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) { /* First run or continue */ if (mas->index < min) return true; *entry = mas_walk(mas); if (*entry) return true; } if (unlikely(mas_is_ptr(mas))) goto none; if (unlikely(mas_is_none(mas))) { /* * Walked to the location, and there was nothing so the previous * location is 0. */ mas->last = mas->index = 0; mas->status = ma_root; *entry = mas_root(mas); return true; } active: if (mas->index < min) return true; return false; none: mas->status = ma_none; return true; } /** * mas_find_rev: On the first call, find the first non-null entry at or below * mas->index down to %min. Otherwise find the first non-null entry below * mas->index down to %min. * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ void *mas_find_rev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_find_rev); /** * mas_find_range_rev: On the first call, find the first non-null entry at or * below mas->index down to %min. Otherwise advance to the previous slot after * mas->index down to %min. * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ void *mas_find_range_rev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_find_range_rev); /** * mas_erase() - Find the range in which index resides and erase the entire * range. * @mas: The maple state * * Must hold the write lock. * Searches for @mas->index, sets @mas->index and @mas->last to the range and * erases that range. * * Return: the entry that was erased or %NULL, @mas->index and @mas->last are updated. */ void *mas_erase(struct ma_state *mas) { void *entry; unsigned long index = mas->index; MA_WR_STATE(wr_mas, mas, NULL); if (!mas_is_active(mas) || !mas_is_start(mas)) mas->status = ma_start; write_retry: entry = mas_state_walk(mas); if (!entry) return NULL; /* Must reset to ensure spanning writes of last slot are detected */ mas_reset(mas); mas_wr_preallocate(&wr_mas, NULL); if (mas_nomem(mas, GFP_KERNEL)) { /* in case the range of entry changed when unlocked */ mas->index = mas->last = index; goto write_retry; } if (mas_is_err(mas)) goto out; mas_wr_store_entry(&wr_mas); out: mas_destroy(mas); return entry; } EXPORT_SYMBOL_GPL(mas_erase); /** * mas_nomem() - Check if there was an error allocating and do the allocation * if necessary If there are allocations, then free them. * @mas: The maple state * @gfp: The GFP_FLAGS to use for allocations * Return: true on allocation, false otherwise. */ bool mas_nomem(struct ma_state *mas, gfp_t gfp) __must_hold(mas->tree->ma_lock) { if (likely(mas->node != MA_ERROR(-ENOMEM))) return false; if (gfpflags_allow_blocking(gfp) && !mt_external_lock(mas->tree)) { mtree_unlock(mas->tree); mas_alloc_nodes(mas, gfp); mtree_lock(mas->tree); } else { mas_alloc_nodes(mas, gfp); } if (!mas_allocated(mas)) return false; mas->status = ma_start; return true; } void __init maple_tree_init(void) { maple_node_cache = kmem_cache_create("maple_node", sizeof(struct maple_node), sizeof(struct maple_node), SLAB_PANIC, NULL); } /** * mtree_load() - Load a value stored in a maple tree * @mt: The maple tree * @index: The index to load * * Return: the entry or %NULL */ void *mtree_load(struct maple_tree *mt, unsigned long index) { MA_STATE(mas, mt, index, index); void *entry; trace_ma_read(__func__, &mas); rcu_read_lock(); retry: entry = mas_start(&mas); if (unlikely(mas_is_none(&mas))) goto unlock; if (unlikely(mas_is_ptr(&mas))) { if (index) entry = NULL; goto unlock; } entry = mtree_lookup_walk(&mas); if (!entry && unlikely(mas_is_start(&mas))) goto retry; unlock: rcu_read_unlock(); if (xa_is_zero(entry)) return NULL; return entry; } EXPORT_SYMBOL(mtree_load); /** * mtree_store_range() - Store an entry at a given range. * @mt: The maple tree * @index: The start of the range * @last: The end of the range * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mtree_store_range(struct maple_tree *mt, unsigned long index, unsigned long last, void *entry, gfp_t gfp) { MA_STATE(mas, mt, index, last); int ret = 0; trace_ma_write(__func__, &mas, 0, entry); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (index > last) return -EINVAL; mtree_lock(mt); ret = mas_store_gfp(&mas, entry, gfp); mtree_unlock(mt); return ret; } EXPORT_SYMBOL(mtree_store_range); /** * mtree_store() - Store an entry at a given index. * @mt: The maple tree * @index: The index to store the value * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mtree_store(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp) { return mtree_store_range(mt, index, index, entry, gfp); } EXPORT_SYMBOL(mtree_store); /** * mtree_insert_range() - Insert an entry at a given range if there is no value. * @mt: The maple tree * @first: The start of the range * @last: The end of the range * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -EEXISTS if the range is occupied, -EINVAL on invalid * request, -ENOMEM if memory could not be allocated. */ int mtree_insert_range(struct maple_tree *mt, unsigned long first, unsigned long last, void *entry, gfp_t gfp) { MA_STATE(ms, mt, first, last); int ret = 0; if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (first > last) return -EINVAL; mtree_lock(mt); retry: mas_insert(&ms, entry); if (mas_nomem(&ms, gfp)) goto retry; mtree_unlock(mt); if (mas_is_err(&ms)) ret = xa_err(ms.node); mas_destroy(&ms); return ret; } EXPORT_SYMBOL(mtree_insert_range); /** * mtree_insert() - Insert an entry at a given index if there is no value. * @mt: The maple tree * @index : The index to store the value * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -EEXISTS if the range is occupied, -EINVAL on invalid * request, -ENOMEM if memory could not be allocated. */ int mtree_insert(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp) { return mtree_insert_range(mt, index, index, entry, gfp); } EXPORT_SYMBOL(mtree_insert); int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); retry: ret = mas_empty_area(&mas, min, max, size); if (ret) goto unlock; mas_insert(&mas, entry); /* * mas_nomem() may release the lock, causing the allocated area * to be unavailable, so try to allocate a free area again. */ if (mas_nomem(&mas, gfp)) goto retry; if (mas_is_err(&mas)) ret = xa_err(mas.node); else *startp = mas.index; unlock: mtree_unlock(mt); mas_destroy(&mas); return ret; } EXPORT_SYMBOL(mtree_alloc_range); /** * mtree_alloc_cyclic() - Find somewhere to store this entry in the tree. * @mt: The maple tree. * @startp: Pointer to ID. * @range_lo: Lower bound of range to search. * @range_hi: Upper bound of range to search. * @entry: The entry to store. * @next: Pointer to next ID to allocate. * @gfp: The GFP_FLAGS to use for allocations. * * Finds an empty entry in @mt after @next, stores the new index into * the @id pointer, stores the entry at that index, then updates @next. * * @mt must be initialized with the MT_FLAGS_ALLOC_RANGE flag. * * Context: Any context. Takes and releases the mt.lock. May sleep if * the @gfp flags permit. * * Return: 0 if the allocation succeeded without wrapping, 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated, -EINVAL if @mt cannot be used, or -EBUSY if there are no * free entries. */ int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp) { int ret; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); ret = mas_alloc_cyclic(&mas, startp, entry, range_lo, range_hi, next, gfp); mtree_unlock(mt); return ret; } EXPORT_SYMBOL(mtree_alloc_cyclic); int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); retry: ret = mas_empty_area_rev(&mas, min, max, size); if (ret) goto unlock; mas_insert(&mas, entry); /* * mas_nomem() may release the lock, causing the allocated area * to be unavailable, so try to allocate a free area again. */ if (mas_nomem(&mas, gfp)) goto retry; if (mas_is_err(&mas)) ret = xa_err(mas.node); else *startp = mas.index; unlock: mtree_unlock(mt); mas_destroy(&mas); return ret; } EXPORT_SYMBOL(mtree_alloc_rrange); /** * mtree_erase() - Find an index and erase the entire range. * @mt: The maple tree * @index: The index to erase * * Erasing is the same as a walk to an entry then a store of a NULL to that * ENTIRE range. In fact, it is implemented as such using the advanced API. * * Return: The entry stored at the @index or %NULL */ void *mtree_erase(struct maple_tree *mt, unsigned long index) { void *entry = NULL; MA_STATE(mas, mt, index, index); trace_ma_op(__func__, &mas); mtree_lock(mt); entry = mas_erase(&mas); mtree_unlock(mt); return entry; } EXPORT_SYMBOL(mtree_erase); /* * mas_dup_free() - Free an incomplete duplication of a tree. * @mas: The maple state of a incomplete tree. * * The parameter @mas->node passed in indicates that the allocation failed on * this node. This function frees all nodes starting from @mas->node in the * reverse order of mas_dup_build(). There is no need to hold the source tree * lock at this time. */ static void mas_dup_free(struct ma_state *mas) { struct maple_node *node; enum maple_type type; void __rcu **slots; unsigned char count, i; /* Maybe the first node allocation failed. */ if (mas_is_none(mas)) return; while (!mte_is_root(mas->node)) { mas_ascend(mas); if (mas->offset) { mas->offset--; do { mas_descend(mas); mas->offset = mas_data_end(mas); } while (!mte_is_leaf(mas->node)); mas_ascend(mas); } node = mte_to_node(mas->node); type = mte_node_type(mas->node); slots = ma_slots(node, type); count = mas_data_end(mas) + 1; for (i = 0; i < count; i++) ((unsigned long *)slots)[i] &= ~MAPLE_NODE_MASK; mt_free_bulk(count, slots); } node = mte_to_node(mas->node); mt_free_one(node); } /* * mas_copy_node() - Copy a maple node and replace the parent. * @mas: The maple state of source tree. * @new_mas: The maple state of new tree. * @parent: The parent of the new node. * * Copy @mas->node to @new_mas->node, set @parent to be the parent of * @new_mas->node. If memory allocation fails, @mas is set to -ENOMEM. */ static inline void mas_copy_node(struct ma_state *mas, struct ma_state *new_mas, struct maple_pnode *parent) { struct maple_node *node = mte_to_node(mas->node); struct maple_node *new_node = mte_to_node(new_mas->node); unsigned long val; /* Copy the node completely. */ memcpy(new_node, node, sizeof(struct maple_node)); /* Update the parent node pointer. */ val = (unsigned long)node->parent & MAPLE_NODE_MASK; new_node->parent = ma_parent_ptr(val | (unsigned long)parent); } /* * mas_dup_alloc() - Allocate child nodes for a maple node. * @mas: The maple state of source tree. * @new_mas: The maple state of new tree. * @gfp: The GFP_FLAGS to use for allocations. * * This function allocates child nodes for @new_mas->node during the duplication * process. If memory allocation fails, @mas is set to -ENOMEM. */ static inline void mas_dup_alloc(struct ma_state *mas, struct ma_state *new_mas, gfp_t gfp) { struct maple_node *node = mte_to_node(mas->node); struct maple_node *new_node = mte_to_node(new_mas->node); enum maple_type type; unsigned char request, count, i; void __rcu **slots; void __rcu **new_slots; unsigned long val; /* Allocate memory for child nodes. */ type = mte_node_type(mas->node); new_slots = ma_slots(new_node, type); request = mas_data_end(mas) + 1; count = mt_alloc_bulk(gfp, request, (void **)new_slots); if (unlikely(count < request)) { memset(new_slots, 0, request * sizeof(void *)); mas_set_err(mas, -ENOMEM); return; } /* Restore node type information in slots. */ slots = ma_slots(node, type); for (i = 0; i < count; i++) { val = (unsigned long)mt_slot_locked(mas->tree, slots, i); val &= MAPLE_NODE_MASK; ((unsigned long *)new_slots)[i] |= val; } } /* * mas_dup_build() - Build a new maple tree from a source tree * @mas: The maple state of source tree, need to be in MAS_START state. * @new_mas: The maple state of new tree, need to be in MAS_START state. * @gfp: The GFP_FLAGS to use for allocations. * * This function builds a new tree in DFS preorder. If the memory allocation * fails, the error code -ENOMEM will be set in @mas, and @new_mas points to the * last node. mas_dup_free() will free the incomplete duplication of a tree. * * Note that the attributes of the two trees need to be exactly the same, and the * new tree needs to be empty, otherwise -EINVAL will be set in @mas. */ static inline void mas_dup_build(struct ma_state *mas, struct ma_state *new_mas, gfp_t gfp) { struct maple_node *node; struct maple_pnode *parent = NULL; struct maple_enode *root; enum maple_type type; if (unlikely(mt_attr(mas->tree) != mt_attr(new_mas->tree)) || unlikely(!mtree_empty(new_mas->tree))) { mas_set_err(mas, -EINVAL); return; } root = mas_start(mas); if (mas_is_ptr(mas) || mas_is_none(mas)) goto set_new_tree; node = mt_alloc_one(gfp); if (!node) { new_mas->status = ma_none; mas_set_err(mas, -ENOMEM); return; } type = mte_node_type(mas->node); root = mt_mk_node(node, type); new_mas->node = root; new_mas->min = 0; new_mas->max = ULONG_MAX; root = mte_mk_root(root); while (1) { mas_copy_node(mas, new_mas, parent); if (!mte_is_leaf(mas->node)) { /* Only allocate child nodes for non-leaf nodes. */ mas_dup_alloc(mas, new_mas, gfp); if (unlikely(mas_is_err(mas))) return; } else { /* * This is the last leaf node and duplication is * completed. */ if (mas->max == ULONG_MAX) goto done; /* This is not the last leaf node and needs to go up. */ do { mas_ascend(mas); mas_ascend(new_mas); } while (mas->offset == mas_data_end(mas)); /* Move to the next subtree. */ mas->offset++; new_mas->offset++; } mas_descend(mas); parent = ma_parent_ptr(mte_to_node(new_mas->node)); mas_descend(new_mas); mas->offset = 0; new_mas->offset = 0; } done: /* Specially handle the parent of the root node. */ mte_to_node(root)->parent = ma_parent_ptr(mas_tree_parent(new_mas)); set_new_tree: /* Make them the same height */ new_mas->tree->ma_flags = mas->tree->ma_flags; rcu_assign_pointer(new_mas->tree->ma_root, root); } /** * __mt_dup(): Duplicate an entire maple tree * @mt: The source maple tree * @new: The new maple tree * @gfp: The GFP_FLAGS to use for allocations * * This function duplicates a maple tree in Depth-First Search (DFS) pre-order * traversal. It uses memcpy() to copy nodes in the source tree and allocate * new child nodes in non-leaf nodes. The new node is exactly the same as the * source node except for all the addresses stored in it. It will be faster than * traversing all elements in the source tree and inserting them one by one into * the new tree. * The user needs to ensure that the attributes of the source tree and the new * tree are the same, and the new tree needs to be an empty tree, otherwise * -EINVAL will be returned. * Note that the user needs to manually lock the source tree and the new tree. * * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If * the attributes of the two trees are different or the new tree is not an empty * tree. */ int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); MA_STATE(new_mas, new, 0, 0); mas_dup_build(&mas, &new_mas, gfp); if (unlikely(mas_is_err(&mas))) { ret = xa_err(mas.node); if (ret == -ENOMEM) mas_dup_free(&new_mas); } return ret; } EXPORT_SYMBOL(__mt_dup); /** * mtree_dup(): Duplicate an entire maple tree * @mt: The source maple tree * @new: The new maple tree * @gfp: The GFP_FLAGS to use for allocations * * This function duplicates a maple tree in Depth-First Search (DFS) pre-order * traversal. It uses memcpy() to copy nodes in the source tree and allocate * new child nodes in non-leaf nodes. The new node is exactly the same as the * source node except for all the addresses stored in it. It will be faster than * traversing all elements in the source tree and inserting them one by one into * the new tree. * The user needs to ensure that the attributes of the source tree and the new * tree are the same, and the new tree needs to be an empty tree, otherwise * -EINVAL will be returned. * * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If * the attributes of the two trees are different or the new tree is not an empty * tree. */ int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); MA_STATE(new_mas, new, 0, 0); mas_lock(&new_mas); mas_lock_nested(&mas, SINGLE_DEPTH_NESTING); mas_dup_build(&mas, &new_mas, gfp); mas_unlock(&mas); if (unlikely(mas_is_err(&mas))) { ret = xa_err(mas.node); if (ret == -ENOMEM) mas_dup_free(&new_mas); } mas_unlock(&new_mas); return ret; } EXPORT_SYMBOL(mtree_dup); /** * __mt_destroy() - Walk and free all nodes of a locked maple tree. * @mt: The maple tree * * Note: Does not handle locking. */ void __mt_destroy(struct maple_tree *mt) { void *root = mt_root_locked(mt); rcu_assign_pointer(mt->ma_root, NULL); if (xa_is_node(root)) mte_destroy_walk(root, mt); mt->ma_flags = mt_attr(mt); } EXPORT_SYMBOL_GPL(__mt_destroy); /** * mtree_destroy() - Destroy a maple tree * @mt: The maple tree * * Frees all resources used by the tree. Handles locking. */ void mtree_destroy(struct maple_tree *mt) { mtree_lock(mt); __mt_destroy(mt); mtree_unlock(mt); } EXPORT_SYMBOL(mtree_destroy); /** * mt_find() - Search from the start up until an entry is found. * @mt: The maple tree * @index: Pointer which contains the start location of the search * @max: The maximum value of the search range * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * In case that an entry is found @index is updated to point to the next * possible entry independent whether the found entry is occupying a * single index or a range if indices. * * Return: The entry at or after the @index or %NULL */ void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max) { MA_STATE(mas, mt, *index, *index); void *entry; #ifdef CONFIG_DEBUG_MAPLE_TREE unsigned long copy = *index; #endif trace_ma_read(__func__, &mas); if ((*index) > max) return NULL; rcu_read_lock(); retry: entry = mas_state_walk(&mas); if (mas_is_start(&mas)) goto retry; if (unlikely(xa_is_zero(entry))) entry = NULL; if (entry) goto unlock; while (mas_is_active(&mas) && (mas.last < max)) { entry = mas_next_entry(&mas, max); if (likely(entry && !xa_is_zero(entry))) break; } if (unlikely(xa_is_zero(entry))) entry = NULL; unlock: rcu_read_unlock(); if (likely(entry)) { *index = mas.last + 1; #ifdef CONFIG_DEBUG_MAPLE_TREE if (MT_WARN_ON(mt, (*index) && ((*index) <= copy))) pr_err("index not increased! %lx <= %lx\n", *index, copy); #endif } return entry; } EXPORT_SYMBOL(mt_find); /** * mt_find_after() - Search from the start up until an entry is found. * @mt: The maple tree * @index: Pointer which contains the start location of the search * @max: The maximum value to check * * Same as mt_find() except that it checks @index for 0 before * searching. If @index == 0, the search is aborted. This covers a wrap * around of @index to 0 in an iterator loop. * * Return: The entry at or after the @index or %NULL */ void *mt_find_after(struct maple_tree *mt, unsigned long *index, unsigned long max) { if (!(*index)) return NULL; return mt_find(mt, index, max); } EXPORT_SYMBOL(mt_find_after); #ifdef CONFIG_DEBUG_MAPLE_TREE atomic_t maple_tree_tests_run; EXPORT_SYMBOL_GPL(maple_tree_tests_run); atomic_t maple_tree_tests_passed; EXPORT_SYMBOL_GPL(maple_tree_tests_passed); #ifndef __KERNEL__ extern void kmem_cache_set_non_kernel(struct kmem_cache *, unsigned int); void mt_set_non_kernel(unsigned int val) { kmem_cache_set_non_kernel(maple_node_cache, val); } extern void kmem_cache_set_callback(struct kmem_cache *cachep, void (*callback)(void *)); void mt_set_callback(void (*callback)(void *)) { kmem_cache_set_callback(maple_node_cache, callback); } extern void kmem_cache_set_private(struct kmem_cache *cachep, void *private); void mt_set_private(void *private) { kmem_cache_set_private(maple_node_cache, private); } extern unsigned long kmem_cache_get_alloc(struct kmem_cache *); unsigned long mt_get_alloc_size(void) { return kmem_cache_get_alloc(maple_node_cache); } extern void kmem_cache_zero_nr_tallocated(struct kmem_cache *); void mt_zero_nr_tallocated(void) { kmem_cache_zero_nr_tallocated(maple_node_cache); } extern unsigned int kmem_cache_nr_tallocated(struct kmem_cache *); unsigned int mt_nr_tallocated(void) { return kmem_cache_nr_tallocated(maple_node_cache); } extern unsigned int kmem_cache_nr_allocated(struct kmem_cache *); unsigned int mt_nr_allocated(void) { return kmem_cache_nr_allocated(maple_node_cache); } void mt_cache_shrink(void) { } #else /* * mt_cache_shrink() - For testing, don't use this. * * Certain testcases can trigger an OOM when combined with other memory * debugging configuration options. This function is used to reduce the * possibility of an out of memory even due to kmem_cache objects remaining * around for longer than usual. */ void mt_cache_shrink(void) { kmem_cache_shrink(maple_node_cache); } EXPORT_SYMBOL_GPL(mt_cache_shrink); #endif /* not defined __KERNEL__ */ /* * mas_get_slot() - Get the entry in the maple state node stored at @offset. * @mas: The maple state * @offset: The offset into the slot array to fetch. * * Return: The entry stored at @offset. */ static inline struct maple_enode *mas_get_slot(struct ma_state *mas, unsigned char offset) { return mas_slot(mas, ma_slots(mas_mn(mas), mte_node_type(mas->node)), offset); } /* Depth first search, post-order */ static void mas_dfs_postorder(struct ma_state *mas, unsigned long max) { struct maple_enode *p, *mn = mas->node; unsigned long p_min, p_max; mas_next_node(mas, mas_mn(mas), max); if (!mas_is_overflow(mas)) return; if (mte_is_root(mn)) return; mas->node = mn; mas_ascend(mas); do { p = mas->node; p_min = mas->min; p_max = mas->max; mas_prev_node(mas, 0); } while (!mas_is_underflow(mas)); mas->node = p; mas->max = p_max; mas->min = p_min; } /* Tree validations */ static void mt_dump_node(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format); static void mt_dump_range(unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { static const char spaces[] = " "; switch(format) { case mt_dump_hex: if (min == max) pr_info("%.*s%lx: ", depth * 2, spaces, min); else pr_info("%.*s%lx-%lx: ", depth * 2, spaces, min, max); break; case mt_dump_dec: if (min == max) pr_info("%.*s%lu: ", depth * 2, spaces, min); else pr_info("%.*s%lu-%lu: ", depth * 2, spaces, min, max); } } static void mt_dump_entry(void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { mt_dump_range(min, max, depth, format); if (xa_is_value(entry)) pr_cont("value %ld (0x%lx) [" PTR_FMT "]\n", xa_to_value(entry), xa_to_value(entry), entry); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else if (mt_is_reserved(entry)) pr_cont("UNKNOWN ENTRY (" PTR_FMT ")\n", entry); else pr_cont(PTR_FMT "\n", entry); } static void mt_dump_range64(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_range_64 *node = &mte_to_node(entry)->mr64; bool leaf = mte_is_leaf(entry); unsigned long first = min; int i; pr_cont(" contents: "); for (i = 0; i < MAPLE_RANGE64_SLOTS - 1; i++) { switch(format) { case mt_dump_hex: pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]); } } pr_cont(PTR_FMT "\n", node->slot[i]); for (i = 0; i < MAPLE_RANGE64_SLOTS; i++) { unsigned long last = max; if (i < (MAPLE_RANGE64_SLOTS - 1)) last = node->pivot[i]; else if (!node->slot[i] && max != mt_node_max(entry)) break; if (last == 0 && i > 0) break; if (leaf) mt_dump_entry(mt_slot(mt, node->slot, i), first, last, depth + 1, format); else if (node->slot[i]) mt_dump_node(mt, mt_slot(mt, node->slot, i), first, last, depth + 1, format); if (last == max) break; if (last > max) { switch(format) { case mt_dump_hex: pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; case mt_dump_dec: pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); } } first = last + 1; } } static void mt_dump_arange64(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_arange_64 *node = &mte_to_node(entry)->ma64; unsigned long first = min; int i; pr_cont(" contents: "); for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) { switch (format) { case mt_dump_hex: pr_cont("%lx ", node->gap[i]); break; case mt_dump_dec: pr_cont("%lu ", node->gap[i]); } } pr_cont("| %02X %02X| ", node->meta.end, node->meta.gap); for (i = 0; i < MAPLE_ARANGE64_SLOTS - 1; i++) { switch (format) { case mt_dump_hex: pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]); } } pr_cont(PTR_FMT "\n", node->slot[i]); for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) { unsigned long last = max; if (i < (MAPLE_ARANGE64_SLOTS - 1)) last = node->pivot[i]; else if (!node->slot[i]) break; if (last == 0 && i > 0) break; if (node->slot[i]) mt_dump_node(mt, mt_slot(mt, node->slot, i), first, last, depth + 1, format); if (last == max) break; if (last > max) { switch(format) { case mt_dump_hex: pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; case mt_dump_dec: pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); } } first = last + 1; } } static void mt_dump_node(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_node *node = mte_to_node(entry); unsigned int type = mte_node_type(entry); unsigned int i; mt_dump_range(min, max, depth, format); pr_cont("node " PTR_FMT " depth %d type %d parent " PTR_FMT, node, depth, type, node ? node->parent : NULL); switch (type) { case maple_dense: pr_cont("\n"); for (i = 0; i < MAPLE_NODE_SLOTS; i++) { if (min + i > max) pr_cont("OUT OF RANGE: "); mt_dump_entry(mt_slot(mt, node->slot, i), min + i, min + i, depth, format); } break; case maple_leaf_64: case maple_range_64: mt_dump_range64(mt, entry, min, max, depth, format); break; case maple_arange_64: mt_dump_arange64(mt, entry, min, max, depth, format); break; default: pr_cont(" UNKNOWN TYPE\n"); } } void mt_dump(const struct maple_tree *mt, enum mt_dump_format format) { void *entry = rcu_dereference_check(mt->ma_root, mt_locked(mt)); pr_info("maple_tree(" PTR_FMT ") flags %X, height %u root " PTR_FMT "\n", mt, mt->ma_flags, mt_height(mt), entry); if (xa_is_node(entry)) mt_dump_node(mt, entry, 0, mt_node_max(entry), 0, format); else if (entry) mt_dump_entry(entry, 0, 0, 0, format); else pr_info("(empty)\n"); } EXPORT_SYMBOL_GPL(mt_dump); /* * Calculate the maximum gap in a node and check if that's what is reported in * the parent (unless root). */ static void mas_validate_gaps(struct ma_state *mas) { struct maple_enode *mte = mas->node; struct maple_node *p_mn, *node = mte_to_node(mte); enum maple_type mt = mte_node_type(mas->node); unsigned long gap = 0, max_gap = 0; unsigned long p_end, p_start = mas->min; unsigned char p_slot, offset; unsigned long *gaps = NULL; unsigned long *pivots = ma_pivots(node, mt); unsigned int i; if (ma_is_dense(mt)) { for (i = 0; i < mt_slot_count(mte); i++) { if (mas_get_slot(mas, i)) { if (gap > max_gap) max_gap = gap; gap = 0; continue; } gap++; } goto counted; } gaps = ma_gaps(node, mt); for (i = 0; i < mt_slot_count(mte); i++) { p_end = mas_safe_pivot(mas, pivots, i, mt); if (!gaps) { if (!mas_get_slot(mas, i)) gap = p_end - p_start + 1; } else { void *entry = mas_get_slot(mas, i); gap = gaps[i]; MT_BUG_ON(mas->tree, !entry); if (gap > p_end - p_start + 1) { pr_err(PTR_FMT "[%u] %lu >= %lu - %lu + 1 (%lu)\n", mas_mn(mas), i, gap, p_end, p_start, p_end - p_start + 1); MT_BUG_ON(mas->tree, gap > p_end - p_start + 1); } } if (gap > max_gap) max_gap = gap; p_start = p_end + 1; if (p_end >= mas->max) break; } counted: if (mt == maple_arange_64) { MT_BUG_ON(mas->tree, !gaps); offset = ma_meta_gap(node); if (offset > i) { pr_err("gap offset " PTR_FMT "[%u] is invalid\n", node, offset); MT_BUG_ON(mas->tree, 1); } if (gaps[offset] != max_gap) { pr_err("gap " PTR_FMT "[%u] is not the largest gap %lu\n", node, offset, max_gap); MT_BUG_ON(mas->tree, 1); } for (i++ ; i < mt_slot_count(mte); i++) { if (gaps[i] != 0) { pr_err("gap " PTR_FMT "[%u] beyond node limit != 0\n", node, i); MT_BUG_ON(mas->tree, 1); } } } if (mte_is_root(mte)) return; p_slot = mte_parent_slot(mas->node); p_mn = mte_parent(mte); MT_BUG_ON(mas->tree, max_gap > mas->max); if (ma_gaps(p_mn, mas_parent_type(mas, mte))[p_slot] != max_gap) { pr_err("gap " PTR_FMT "[%u] != %lu\n", p_mn, p_slot, max_gap); mt_dump(mas->tree, mt_dump_hex); MT_BUG_ON(mas->tree, 1); } } static void mas_validate_parent_slot(struct ma_state *mas) { struct maple_node *parent; struct maple_enode *node; enum maple_type p_type; unsigned char p_slot; void __rcu **slots; int i; if (mte_is_root(mas->node)) return; p_slot = mte_parent_slot(mas->node); p_type = mas_parent_type(mas, mas->node); parent = mte_parent(mas->node); slots = ma_slots(parent, p_type); MT_BUG_ON(mas->tree, mas_mn(mas) == parent); /* Check prev/next parent slot for duplicate node entry */ for (i = 0; i < mt_slots[p_type]; i++) { node = mas_slot(mas, slots, i); if (i == p_slot) { if (node != mas->node) pr_err("parent " PTR_FMT "[%u] does not have " PTR_FMT "\n", parent, i, mas_mn(mas)); MT_BUG_ON(mas->tree, node != mas->node); } else if (node == mas->node) { pr_err("Invalid child " PTR_FMT " at parent " PTR_FMT "[%u] p_slot %u\n", mas_mn(mas), parent, i, p_slot); MT_BUG_ON(mas->tree, node == mas->node); } } } static void mas_validate_child_slot(struct ma_state *mas) { enum maple_type type = mte_node_type(mas->node); void __rcu **slots = ma_slots(mte_to_node(mas->node), type); unsigned long *pivots = ma_pivots(mte_to_node(mas->node), type); struct maple_enode *child; unsigned char i; if (mte_is_leaf(mas->node)) return; for (i = 0; i < mt_slots[type]; i++) { child = mas_slot(mas, slots, i); if (!child) { pr_err("Non-leaf node lacks child at " PTR_FMT "[%u]\n", mas_mn(mas), i); MT_BUG_ON(mas->tree, 1); } if (mte_parent_slot(child) != i) { pr_err("Slot error at " PTR_FMT "[%u]: child " PTR_FMT " has pslot %u\n", mas_mn(mas), i, mte_to_node(child), mte_parent_slot(child)); MT_BUG_ON(mas->tree, 1); } if (mte_parent(child) != mte_to_node(mas->node)) { pr_err("child " PTR_FMT " has parent " PTR_FMT " not " PTR_FMT "\n", mte_to_node(child), mte_parent(child), mte_to_node(mas->node)); MT_BUG_ON(mas->tree, 1); } if (i < mt_pivots[type] && pivots[i] == mas->max) break; } } /* * Validate all pivots are within mas->min and mas->max, check metadata ends * where the maximum ends and ensure there is no slots or pivots set outside of * the end of the data. */ static void mas_validate_limits(struct ma_state *mas) { int i; unsigned long prev_piv = 0; enum maple_type type = mte_node_type(mas->node); void __rcu **slots = ma_slots(mte_to_node(mas->node), type); unsigned long *pivots = ma_pivots(mas_mn(mas), type); for (i = 0; i < mt_slots[type]; i++) { unsigned long piv; piv = mas_safe_pivot(mas, pivots, i, type); if (!piv && (i != 0)) { pr_err("Missing node limit pivot at " PTR_FMT "[%u]", mas_mn(mas), i); MAS_WARN_ON(mas, 1); } if (prev_piv > piv) { pr_err(PTR_FMT "[%u] piv %lu < prev_piv %lu\n", mas_mn(mas), i, piv, prev_piv); MAS_WARN_ON(mas, piv < prev_piv); } if (piv < mas->min) { pr_err(PTR_FMT "[%u] %lu < %lu\n", mas_mn(mas), i, piv, mas->min); MAS_WARN_ON(mas, piv < mas->min); } if (piv > mas->max) { pr_err(PTR_FMT "[%u] %lu > %lu\n", mas_mn(mas), i, piv, mas->max); MAS_WARN_ON(mas, piv > mas->max); } prev_piv = piv; if (piv == mas->max) break; } if (mas_data_end(mas) != i) { pr_err("node" PTR_FMT ": data_end %u != the last slot offset %u\n", mas_mn(mas), mas_data_end(mas), i); MT_BUG_ON(mas->tree, 1); } for (i += 1; i < mt_slots[type]; i++) { void *entry = mas_slot(mas, slots, i); if (entry && (i != mt_slots[type] - 1)) { pr_err(PTR_FMT "[%u] should not have entry " PTR_FMT "\n", mas_mn(mas), i, entry); MT_BUG_ON(mas->tree, entry != NULL); } if (i < mt_pivots[type]) { unsigned long piv = pivots[i]; if (!piv) continue; pr_err(PTR_FMT "[%u] should not have piv %lu\n", mas_mn(mas), i, piv); MAS_WARN_ON(mas, i < mt_pivots[type] - 1); } } } static void mt_validate_nulls(struct maple_tree *mt) { void *entry, *last = (void *)1; unsigned char offset = 0; void __rcu **slots; MA_STATE(mas, mt, 0, 0); mas_start(&mas); if (mas_is_none(&mas) || (mas_is_ptr(&mas))) return; while (!mte_is_leaf(mas.node)) mas_descend(&mas); slots = ma_slots(mte_to_node(mas.node), mte_node_type(mas.node)); do { entry = mas_slot(&mas, slots, offset); if (!last && !entry) { pr_err("Sequential nulls end at " PTR_FMT "[%u]\n", mas_mn(&mas), offset); } MT_BUG_ON(mt, !last && !entry); last = entry; if (offset == mas_data_end(&mas)) { mas_next_node(&mas, mas_mn(&mas), ULONG_MAX); if (mas_is_overflow(&mas)) return; offset = 0; slots = ma_slots(mte_to_node(mas.node), mte_node_type(mas.node)); } else { offset++; } } while (!mas_is_overflow(&mas)); } /* * validate a maple tree by checking: * 1. The limits (pivots are within mas->min to mas->max) * 2. The gap is correctly set in the parents */ void mt_validate(struct maple_tree *mt) __must_hold(mas->tree->ma_lock) { unsigned char end; MA_STATE(mas, mt, 0, 0); mas_start(&mas); if (!mas_is_active(&mas)) return; while (!mte_is_leaf(mas.node)) mas_descend(&mas); while (!mas_is_overflow(&mas)) { MAS_WARN_ON(&mas, mte_dead_node(mas.node)); end = mas_data_end(&mas); if (MAS_WARN_ON(&mas, (end < mt_min_slot_count(mas.node)) && (mas.max != ULONG_MAX))) { pr_err("Invalid size %u of " PTR_FMT "\n", end, mas_mn(&mas)); } mas_validate_parent_slot(&mas); mas_validate_limits(&mas); mas_validate_child_slot(&mas); if (mt_is_alloc(mt)) mas_validate_gaps(&mas); mas_dfs_postorder(&mas, ULONG_MAX); } mt_validate_nulls(mt); } EXPORT_SYMBOL_GPL(mt_validate); void mas_dump(const struct ma_state *mas) { pr_err("MAS: tree=" PTR_FMT " enode=" PTR_FMT " ", mas->tree, mas->node); switch (mas->status) { case ma_active: pr_err("(ma_active)"); break; case ma_none: pr_err("(ma_none)"); break; case ma_root: pr_err("(ma_root)"); break; case ma_start: pr_err("(ma_start) "); break; case ma_pause: pr_err("(ma_pause) "); break; case ma_overflow: pr_err("(ma_overflow) "); break; case ma_underflow: pr_err("(ma_underflow) "); break; case ma_error: pr_err("(ma_error) "); break; } pr_err("Store Type: "); switch (mas->store_type) { case wr_invalid: pr_err("invalid store type\n"); break; case wr_new_root: pr_err("new_root\n"); break; case wr_store_root: pr_err("store_root\n"); break; case wr_exact_fit: pr_err("exact_fit\n"); break; case wr_split_store: pr_err("split_store\n"); break; case wr_slot_store: pr_err("slot_store\n"); break; case wr_append: pr_err("append\n"); break; case wr_node_store: pr_err("node_store\n"); break; case wr_spanning_store: pr_err("spanning_store\n"); break; case wr_rebalance: pr_err("rebalance\n"); break; } pr_err("[%u/%u] index=%lx last=%lx\n", mas->offset, mas->end, mas->index, mas->last); pr_err(" min=%lx max=%lx alloc=" PTR_FMT ", depth=%u, flags=%x\n", mas->min, mas->max, mas->alloc, mas->depth, mas->mas_flags); if (mas->index > mas->last) pr_err("Check index & last\n"); } EXPORT_SYMBOL_GPL(mas_dump); void mas_wr_dump(const struct ma_wr_state *wr_mas) { pr_err("WR_MAS: node=" PTR_FMT " r_min=%lx r_max=%lx\n", wr_mas->node, wr_mas->r_min, wr_mas->r_max); pr_err(" type=%u off_end=%u, node_end=%u, end_piv=%lx\n", wr_mas->type, wr_mas->offset_end, wr_mas->mas->end, wr_mas->end_piv); } EXPORT_SYMBOL_GPL(mas_wr_dump); #endif /* CONFIG_DEBUG_MAPLE_TREE */ |
| 1 1 1 5 5 1 1 1 1 1 1 1 2 1 33 28 3 2 2 30 1 | 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 | /* * Copyright (c) 2006, 2019 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/kernel.h> #include <linux/in.h> #include <linux/if.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/if_arp.h> #include <linux/delay.h> #include <linux/slab.h> #include <linux/module.h> #include <net/addrconf.h> #include "rds_single_path.h" #include "rds.h" #include "ib.h" #include "ib_mr.h" static unsigned int rds_ib_mr_1m_pool_size = RDS_MR_1M_POOL_SIZE; static unsigned int rds_ib_mr_8k_pool_size = RDS_MR_8K_POOL_SIZE; unsigned int rds_ib_retry_count = RDS_IB_DEFAULT_RETRY_COUNT; static atomic_t rds_ib_unloading; module_param(rds_ib_mr_1m_pool_size, int, 0444); MODULE_PARM_DESC(rds_ib_mr_1m_pool_size, " Max number of 1M mr per HCA"); module_param(rds_ib_mr_8k_pool_size, int, 0444); MODULE_PARM_DESC(rds_ib_mr_8k_pool_size, " Max number of 8K mr per HCA"); module_param(rds_ib_retry_count, int, 0444); MODULE_PARM_DESC(rds_ib_retry_count, " Number of hw retries before reporting an error"); /* * we have a clumsy combination of RCU and a rwsem protecting this list * because it is used both in the get_mr fast path and while blocking in * the FMR flushing path. */ DECLARE_RWSEM(rds_ib_devices_lock); struct list_head rds_ib_devices; /* NOTE: if also grabbing ibdev lock, grab this first */ DEFINE_SPINLOCK(ib_nodev_conns_lock); LIST_HEAD(ib_nodev_conns); static void rds_ib_nodev_connect(void) { struct rds_ib_connection *ic; spin_lock(&ib_nodev_conns_lock); list_for_each_entry(ic, &ib_nodev_conns, ib_node) rds_conn_connect_if_down(ic->conn); spin_unlock(&ib_nodev_conns_lock); } static void rds_ib_dev_shutdown(struct rds_ib_device *rds_ibdev) { struct rds_ib_connection *ic; unsigned long flags; spin_lock_irqsave(&rds_ibdev->spinlock, flags); list_for_each_entry(ic, &rds_ibdev->conn_list, ib_node) rds_conn_path_drop(&ic->conn->c_path[0], true); spin_unlock_irqrestore(&rds_ibdev->spinlock, flags); } /* * rds_ib_destroy_mr_pool() blocks on a few things and mrs drop references * from interrupt context so we push freing off into a work struct in krdsd. */ static void rds_ib_dev_free(struct work_struct *work) { struct rds_ib_ipaddr *i_ipaddr, *i_next; struct rds_ib_device *rds_ibdev = container_of(work, struct rds_ib_device, free_work); if (rds_ibdev->mr_8k_pool) rds_ib_destroy_mr_pool(rds_ibdev->mr_8k_pool); if (rds_ibdev->mr_1m_pool) rds_ib_destroy_mr_pool(rds_ibdev->mr_1m_pool); if (rds_ibdev->pd) ib_dealloc_pd(rds_ibdev->pd); list_for_each_entry_safe(i_ipaddr, i_next, &rds_ibdev->ipaddr_list, list) { list_del(&i_ipaddr->list); kfree(i_ipaddr); } kfree(rds_ibdev->vector_load); kfree(rds_ibdev); } void rds_ib_dev_put(struct rds_ib_device *rds_ibdev) { BUG_ON(refcount_read(&rds_ibdev->refcount) == 0); if (refcount_dec_and_test(&rds_ibdev->refcount)) queue_work(rds_wq, &rds_ibdev->free_work); } static int rds_ib_add_one(struct ib_device *device) { struct rds_ib_device *rds_ibdev; int ret; /* Only handle IB (no iWARP) devices */ if (device->node_type != RDMA_NODE_IB_CA) return -EOPNOTSUPP; /* Device must support FRWR */ if (!(device->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS)) return -EOPNOTSUPP; rds_ibdev = kzalloc_node(sizeof(struct rds_ib_device), GFP_KERNEL, ibdev_to_node(device)); if (!rds_ibdev) return -ENOMEM; spin_lock_init(&rds_ibdev->spinlock); refcount_set(&rds_ibdev->refcount, 1); INIT_WORK(&rds_ibdev->free_work, rds_ib_dev_free); INIT_LIST_HEAD(&rds_ibdev->ipaddr_list); INIT_LIST_HEAD(&rds_ibdev->conn_list); rds_ibdev->max_wrs = device->attrs.max_qp_wr; rds_ibdev->max_sge = min(device->attrs.max_send_sge, RDS_IB_MAX_SGE); rds_ibdev->odp_capable = !!(device->attrs.kernel_cap_flags & IBK_ON_DEMAND_PAGING) && !!(device->attrs.odp_caps.per_transport_caps.rc_odp_caps & IB_ODP_SUPPORT_WRITE) && !!(device->attrs.odp_caps.per_transport_caps.rc_odp_caps & IB_ODP_SUPPORT_READ); rds_ibdev->max_1m_mrs = device->attrs.max_mr ? min_t(unsigned int, (device->attrs.max_mr / 2), rds_ib_mr_1m_pool_size) : rds_ib_mr_1m_pool_size; rds_ibdev->max_8k_mrs = device->attrs.max_mr ? min_t(unsigned int, ((device->attrs.max_mr / 2) * RDS_MR_8K_SCALE), rds_ib_mr_8k_pool_size) : rds_ib_mr_8k_pool_size; rds_ibdev->max_initiator_depth = device->attrs.max_qp_init_rd_atom; rds_ibdev->max_responder_resources = device->attrs.max_qp_rd_atom; rds_ibdev->vector_load = kcalloc(device->num_comp_vectors, sizeof(int), GFP_KERNEL); if (!rds_ibdev->vector_load) { pr_err("RDS/IB: %s failed to allocate vector memory\n", __func__); ret = -ENOMEM; goto put_dev; } rds_ibdev->dev = device; rds_ibdev->pd = ib_alloc_pd(device, 0); if (IS_ERR(rds_ibdev->pd)) { ret = PTR_ERR(rds_ibdev->pd); rds_ibdev->pd = NULL; goto put_dev; } rds_ibdev->mr_1m_pool = rds_ib_create_mr_pool(rds_ibdev, RDS_IB_MR_1M_POOL); if (IS_ERR(rds_ibdev->mr_1m_pool)) { ret = PTR_ERR(rds_ibdev->mr_1m_pool); rds_ibdev->mr_1m_pool = NULL; goto put_dev; } rds_ibdev->mr_8k_pool = rds_ib_create_mr_pool(rds_ibdev, RDS_IB_MR_8K_POOL); if (IS_ERR(rds_ibdev->mr_8k_pool)) { ret = PTR_ERR(rds_ibdev->mr_8k_pool); rds_ibdev->mr_8k_pool = NULL; goto put_dev; } rdsdebug("RDS/IB: max_mr = %d, max_wrs = %d, max_sge = %d, max_1m_mrs = %d, max_8k_mrs = %d\n", device->attrs.max_mr, rds_ibdev->max_wrs, rds_ibdev->max_sge, rds_ibdev->max_1m_mrs, rds_ibdev->max_8k_mrs); pr_info("RDS/IB: %s: added\n", device->name); down_write(&rds_ib_devices_lock); list_add_tail_rcu(&rds_ibdev->list, &rds_ib_devices); up_write(&rds_ib_devices_lock); refcount_inc(&rds_ibdev->refcount); ib_set_client_data(device, &rds_ib_client, rds_ibdev); rds_ib_nodev_connect(); return 0; put_dev: rds_ib_dev_put(rds_ibdev); return ret; } /* * New connections use this to find the device to associate with the * connection. It's not in the fast path so we're not concerned about the * performance of the IB call. (As of this writing, it uses an interrupt * blocking spinlock to serialize walking a per-device list of all registered * clients.) * * RCU is used to handle incoming connections racing with device teardown. * Rather than use a lock to serialize removal from the client_data and * getting a new reference, we use an RCU grace period. The destruction * path removes the device from client_data and then waits for all RCU * readers to finish. * * A new connection can get NULL from this if its arriving on a * device that is in the process of being removed. */ struct rds_ib_device *rds_ib_get_client_data(struct ib_device *device) { struct rds_ib_device *rds_ibdev; rcu_read_lock(); rds_ibdev = ib_get_client_data(device, &rds_ib_client); if (rds_ibdev) refcount_inc(&rds_ibdev->refcount); rcu_read_unlock(); return rds_ibdev; } /* * The IB stack is letting us know that a device is going away. This can * happen if the underlying HCA driver is removed or if PCI hotplug is removing * the pci function, for example. * * This can be called at any time and can be racing with any other RDS path. */ static void rds_ib_remove_one(struct ib_device *device, void *client_data) { struct rds_ib_device *rds_ibdev = client_data; rds_ib_dev_shutdown(rds_ibdev); /* stop connection attempts from getting a reference to this device. */ ib_set_client_data(device, &rds_ib_client, NULL); down_write(&rds_ib_devices_lock); list_del_rcu(&rds_ibdev->list); up_write(&rds_ib_devices_lock); /* * This synchronize rcu is waiting for readers of both the ib * client data and the devices list to finish before we drop * both of those references. */ synchronize_rcu(); rds_ib_dev_put(rds_ibdev); rds_ib_dev_put(rds_ibdev); } struct ib_client rds_ib_client = { .name = "rds_ib", .add = rds_ib_add_one, .remove = rds_ib_remove_one }; static int rds_ib_conn_info_visitor(struct rds_connection *conn, void *buffer) { struct rds_info_rdma_connection *iinfo = buffer; struct rds_ib_connection *ic = conn->c_transport_data; /* We will only ever look at IB transports */ if (conn->c_trans != &rds_ib_transport) return 0; if (conn->c_isv6) return 0; iinfo->src_addr = conn->c_laddr.s6_addr32[3]; iinfo->dst_addr = conn->c_faddr.s6_addr32[3]; if (ic) { iinfo->tos = conn->c_tos; iinfo->sl = ic->i_sl; } memset(&iinfo->src_gid, 0, sizeof(iinfo->src_gid)); memset(&iinfo->dst_gid, 0, sizeof(iinfo->dst_gid)); if (rds_conn_state(conn) == RDS_CONN_UP) { struct rds_ib_device *rds_ibdev; rdma_read_gids(ic->i_cm_id, (union ib_gid *)&iinfo->src_gid, (union ib_gid *)&iinfo->dst_gid); rds_ibdev = ic->rds_ibdev; iinfo->max_send_wr = ic->i_send_ring.w_nr; iinfo->max_recv_wr = ic->i_recv_ring.w_nr; iinfo->max_send_sge = rds_ibdev->max_sge; rds_ib_get_mr_info(rds_ibdev, iinfo); iinfo->cache_allocs = atomic_read(&ic->i_cache_allocs); } return 1; } #if IS_ENABLED(CONFIG_IPV6) /* IPv6 version of rds_ib_conn_info_visitor(). */ static int rds6_ib_conn_info_visitor(struct rds_connection *conn, void *buffer) { struct rds6_info_rdma_connection *iinfo6 = buffer; struct rds_ib_connection *ic = conn->c_transport_data; /* We will only ever look at IB transports */ if (conn->c_trans != &rds_ib_transport) return 0; iinfo6->src_addr = conn->c_laddr; iinfo6->dst_addr = conn->c_faddr; if (ic) { iinfo6->tos = conn->c_tos; iinfo6->sl = ic->i_sl; } memset(&iinfo6->src_gid, 0, sizeof(iinfo6->src_gid)); memset(&iinfo6->dst_gid, 0, sizeof(iinfo6->dst_gid)); if (rds_conn_state(conn) == RDS_CONN_UP) { struct rds_ib_device *rds_ibdev; rdma_read_gids(ic->i_cm_id, (union ib_gid *)&iinfo6->src_gid, (union ib_gid *)&iinfo6->dst_gid); rds_ibdev = ic->rds_ibdev; iinfo6->max_send_wr = ic->i_send_ring.w_nr; iinfo6->max_recv_wr = ic->i_recv_ring.w_nr; iinfo6->max_send_sge = rds_ibdev->max_sge; rds6_ib_get_mr_info(rds_ibdev, iinfo6); iinfo6->cache_allocs = atomic_read(&ic->i_cache_allocs); } return 1; } #endif static void rds_ib_ic_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { u64 buffer[(sizeof(struct rds_info_rdma_connection) + 7) / 8]; rds_for_each_conn_info(sock, len, iter, lens, rds_ib_conn_info_visitor, buffer, sizeof(struct rds_info_rdma_connection)); } #if IS_ENABLED(CONFIG_IPV6) /* IPv6 version of rds_ib_ic_info(). */ static void rds6_ib_ic_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { u64 buffer[(sizeof(struct rds6_info_rdma_connection) + 7) / 8]; rds_for_each_conn_info(sock, len, iter, lens, rds6_ib_conn_info_visitor, buffer, sizeof(struct rds6_info_rdma_connection)); } #endif /* * Early RDS/IB was built to only bind to an address if there is an IPoIB * device with that address set. * * If it were me, I'd advocate for something more flexible. Sending and * receiving should be device-agnostic. Transports would try and maintain * connections between peers who have messages queued. Userspace would be * allowed to influence which paths have priority. We could call userspace * asserting this policy "routing". */ static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr, __u32 scope_id) { int ret; struct rdma_cm_id *cm_id; #if IS_ENABLED(CONFIG_IPV6) struct sockaddr_in6 sin6; #endif struct sockaddr_in sin; struct sockaddr *sa; bool isv4; isv4 = ipv6_addr_v4mapped(addr); /* Create a CMA ID and try to bind it. This catches both * IB and iWARP capable NICs. */ cm_id = rdma_create_id(&init_net, rds_rdma_cm_event_handler, NULL, RDMA_PS_TCP, IB_QPT_RC); if (IS_ERR(cm_id)) return PTR_ERR(cm_id); if (isv4) { memset(&sin, 0, sizeof(sin)); sin.sin_family = AF_INET; sin.sin_addr.s_addr = addr->s6_addr32[3]; sa = (struct sockaddr *)&sin; } else { #if IS_ENABLED(CONFIG_IPV6) memset(&sin6, 0, sizeof(sin6)); sin6.sin6_family = AF_INET6; sin6.sin6_addr = *addr; sin6.sin6_scope_id = scope_id; sa = (struct sockaddr *)&sin6; /* XXX Do a special IPv6 link local address check here. The * reason is that rdma_bind_addr() always succeeds with IPv6 * link local address regardless it is indeed configured in a * system. */ if (ipv6_addr_type(addr) & IPV6_ADDR_LINKLOCAL) { struct net_device *dev; if (scope_id == 0) { ret = -EADDRNOTAVAIL; goto out; } /* Use init_net for now as RDS is not network * name space aware. */ dev = dev_get_by_index(&init_net, scope_id); if (!dev) { ret = -EADDRNOTAVAIL; goto out; } if (!ipv6_chk_addr(&init_net, addr, dev, 1)) { dev_put(dev); ret = -EADDRNOTAVAIL; goto out; } dev_put(dev); } #else ret = -EADDRNOTAVAIL; goto out; #endif } /* rdma_bind_addr will only succeed for IB & iWARP devices */ ret = rdma_bind_addr(cm_id, sa); /* due to this, we will claim to support iWARP devices unless we check node_type. */ if (ret || !cm_id->device || cm_id->device->node_type != RDMA_NODE_IB_CA) ret = -EADDRNOTAVAIL; rdsdebug("addr %pI6c%%%u ret %d node type %d\n", addr, scope_id, ret, cm_id->device ? cm_id->device->node_type : -1); out: rdma_destroy_id(cm_id); return ret; } static void rds_ib_unregister_client(void) { ib_unregister_client(&rds_ib_client); /* wait for rds_ib_dev_free() to complete */ flush_workqueue(rds_wq); } static void rds_ib_set_unloading(void) { atomic_set(&rds_ib_unloading, 1); } static bool rds_ib_is_unloading(struct rds_connection *conn) { struct rds_conn_path *cp = &conn->c_path[0]; return (test_bit(RDS_DESTROY_PENDING, &cp->cp_flags) || atomic_read(&rds_ib_unloading) != 0); } void rds_ib_exit(void) { rds_ib_set_unloading(); synchronize_rcu(); rds_info_deregister_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info); #if IS_ENABLED(CONFIG_IPV6) rds_info_deregister_func(RDS6_INFO_IB_CONNECTIONS, rds6_ib_ic_info); #endif rds_ib_unregister_client(); rds_ib_destroy_nodev_conns(); rds_ib_sysctl_exit(); rds_ib_recv_exit(); rds_trans_unregister(&rds_ib_transport); rds_ib_mr_exit(); } static u8 rds_ib_get_tos_map(u8 tos) { /* 1:1 user to transport map for RDMA transport. * In future, if custom map is desired, hook can export * user configurable map. */ return tos; } struct rds_transport rds_ib_transport = { .laddr_check = rds_ib_laddr_check, .xmit_path_complete = rds_ib_xmit_path_complete, .xmit = rds_ib_xmit, .xmit_rdma = rds_ib_xmit_rdma, .xmit_atomic = rds_ib_xmit_atomic, .recv_path = rds_ib_recv_path, .conn_alloc = rds_ib_conn_alloc, .conn_free = rds_ib_conn_free, .conn_path_connect = rds_ib_conn_path_connect, .conn_path_shutdown = rds_ib_conn_path_shutdown, .inc_copy_to_user = rds_ib_inc_copy_to_user, .inc_free = rds_ib_inc_free, .cm_initiate_connect = rds_ib_cm_initiate_connect, .cm_handle_connect = rds_ib_cm_handle_connect, .cm_connect_complete = rds_ib_cm_connect_complete, .stats_info_copy = rds_ib_stats_info_copy, .exit = rds_ib_exit, .get_mr = rds_ib_get_mr, .sync_mr = rds_ib_sync_mr, .free_mr = rds_ib_free_mr, .flush_mrs = rds_ib_flush_mrs, .get_tos_map = rds_ib_get_tos_map, .t_owner = THIS_MODULE, .t_name = "infiniband", .t_unloading = rds_ib_is_unloading, .t_type = RDS_TRANS_IB }; int rds_ib_init(void) { int ret; INIT_LIST_HEAD(&rds_ib_devices); ret = rds_ib_mr_init(); if (ret) goto out; ret = ib_register_client(&rds_ib_client); if (ret) goto out_mr_exit; ret = rds_ib_sysctl_init(); if (ret) goto out_ibreg; ret = rds_ib_recv_init(); if (ret) goto out_sysctl; rds_trans_register(&rds_ib_transport); rds_info_register_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info); #if IS_ENABLED(CONFIG_IPV6) rds_info_register_func(RDS6_INFO_IB_CONNECTIONS, rds6_ib_ic_info); #endif goto out; out_sysctl: rds_ib_sysctl_exit(); out_ibreg: rds_ib_unregister_client(); out_mr_exit: rds_ib_mr_exit(); out: return ret; } MODULE_LICENSE("GPL"); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #ifndef _NFT_SET_PIPAPO_H #include <linux/log2.h> #include <net/ipv6.h> /* For the maximum length of a field */ /* Count of concatenated fields depends on count of 32-bit nftables registers */ #define NFT_PIPAPO_MAX_FIELDS NFT_REG32_COUNT /* Restrict usage to multiple fields, make sure rbtree is used otherwise */ #define NFT_PIPAPO_MIN_FIELDS 2 /* Largest supported field size */ #define NFT_PIPAPO_MAX_BYTES (sizeof(struct in6_addr)) #define NFT_PIPAPO_MAX_BITS (NFT_PIPAPO_MAX_BYTES * BITS_PER_BYTE) /* Bits to be grouped together in table buckets depending on set size */ #define NFT_PIPAPO_GROUP_BITS_INIT NFT_PIPAPO_GROUP_BITS_SMALL_SET #define NFT_PIPAPO_GROUP_BITS_SMALL_SET 8 #define NFT_PIPAPO_GROUP_BITS_LARGE_SET 4 #define NFT_PIPAPO_GROUP_BITS_ARE_8_OR_4 \ BUILD_BUG_ON((NFT_PIPAPO_GROUP_BITS_SMALL_SET != 8) || \ (NFT_PIPAPO_GROUP_BITS_LARGE_SET != 4)) #define NFT_PIPAPO_GROUPS_PER_BYTE(f) (BITS_PER_BYTE / (f)->bb) /* If a lookup table gets bigger than NFT_PIPAPO_LT_SIZE_HIGH, switch to the * small group width, and switch to the big group width if the table gets * smaller than NFT_PIPAPO_LT_SIZE_LOW. * * Picking 2MiB as threshold (for a single table) avoids as much as possible * crossing page boundaries on most architectures (x86-64 and MIPS huge pages, * ARMv7 supersections, POWER "large" pages, SPARC Level 1 regions, etc.), which * keeps performance nice in case kvmalloc() gives us non-contiguous areas. */ #define NFT_PIPAPO_LT_SIZE_THRESHOLD (1 << 21) #define NFT_PIPAPO_LT_SIZE_HYSTERESIS (1 << 16) #define NFT_PIPAPO_LT_SIZE_HIGH NFT_PIPAPO_LT_SIZE_THRESHOLD #define NFT_PIPAPO_LT_SIZE_LOW NFT_PIPAPO_LT_SIZE_THRESHOLD - \ NFT_PIPAPO_LT_SIZE_HYSTERESIS /* Fields are padded to 32 bits in input registers */ #define NFT_PIPAPO_GROUPS_PADDED_SIZE(f) \ (round_up((f)->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f), sizeof(u32))) #define NFT_PIPAPO_GROUPS_PADDING(f) \ (NFT_PIPAPO_GROUPS_PADDED_SIZE(f) - (f)->groups / \ NFT_PIPAPO_GROUPS_PER_BYTE(f)) /* Number of buckets given by 2 ^ n, with n bucket bits */ #define NFT_PIPAPO_BUCKETS(bb) (1 << (bb)) /* Each n-bit range maps to up to n * 2 rules */ #define NFT_PIPAPO_MAP_NBITS (const_ilog2(NFT_PIPAPO_MAX_BITS * 2)) /* Use the rest of mapping table buckets for rule indices, but it makes no sense * to exceed 32 bits */ #if BITS_PER_LONG == 64 #define NFT_PIPAPO_MAP_TOBITS 32 #else #define NFT_PIPAPO_MAP_TOBITS (BITS_PER_LONG - NFT_PIPAPO_MAP_NBITS) #endif /* ...which gives us the highest allowed index for a rule */ #define NFT_PIPAPO_RULE0_MAX ((1UL << (NFT_PIPAPO_MAP_TOBITS - 1)) \ - (1UL << NFT_PIPAPO_MAP_NBITS)) /* Definitions for vectorised implementations */ #ifdef NFT_PIPAPO_ALIGN #define NFT_PIPAPO_ALIGN_HEADROOM \ (NFT_PIPAPO_ALIGN - ARCH_KMALLOC_MINALIGN) #define NFT_PIPAPO_LT_ALIGN(lt) (PTR_ALIGN((lt), NFT_PIPAPO_ALIGN)) #else #define NFT_PIPAPO_ALIGN_HEADROOM 0 #define NFT_PIPAPO_LT_ALIGN(lt) (lt) #endif /* NFT_PIPAPO_ALIGN */ #define nft_pipapo_for_each_field(field, index, match) \ for ((field) = (match)->f, (index) = 0; \ (index) < (match)->field_count; \ (index)++, (field)++) /** * union nft_pipapo_map_bucket - Bucket of mapping table * @to: First rule number (in next field) this rule maps to * @n: Number of rules (in next field) this rule maps to * @e: If there's no next field, pointer to element this rule maps to */ union nft_pipapo_map_bucket { struct { #if BITS_PER_LONG == 64 static_assert(NFT_PIPAPO_MAP_TOBITS <= 32); u32 to; static_assert(NFT_PIPAPO_MAP_NBITS <= 32); u32 n; #else unsigned long to:NFT_PIPAPO_MAP_TOBITS; unsigned long n:NFT_PIPAPO_MAP_NBITS; #endif }; struct nft_pipapo_elem *e; }; /** * struct nft_pipapo_field - Lookup, mapping tables and related data for a field * @rules: Number of inserted rules * @bsize: Size of each bucket in lookup table, in longs * @rules_alloc: Number of allocated rules, always >= rules * @groups: Amount of bit groups * @bb: Number of bits grouped together in lookup table buckets * @lt: Lookup table: 'groups' rows of buckets * @mt: Mapping table: one bucket per rule */ struct nft_pipapo_field { unsigned int rules; unsigned int bsize; unsigned int rules_alloc; u8 groups; u8 bb; unsigned long *lt; union nft_pipapo_map_bucket *mt; }; /** * struct nft_pipapo_scratch - percpu data used for lookup and matching * @map_index: Current working bitmap index, toggled between field matches * @align_off: Offset to get the originally allocated address * @map: store partial matching results during lookup */ struct nft_pipapo_scratch { u8 map_index; u32 align_off; unsigned long map[]; }; /** * struct nft_pipapo_match - Data used for lookup and matching * @field_count: Amount of fields in set * @bsize_max: Maximum lookup table bucket size of all fields, in longs * @scratch: Preallocated per-CPU maps for partial matching results * @rcu: Matching data is swapped on commits * @f: Fields, with lookup and mapping tables */ struct nft_pipapo_match { u8 field_count; unsigned int bsize_max; struct nft_pipapo_scratch * __percpu *scratch; struct rcu_head rcu; struct nft_pipapo_field f[] __counted_by(field_count); }; /** * struct nft_pipapo - Representation of a set * @match: Currently in-use matching data * @clone: Copy where pending insertions and deletions are kept * @width: Total bytes to be matched for one packet, including padding * @last_gc: Timestamp of last garbage collection run, jiffies */ struct nft_pipapo { struct nft_pipapo_match __rcu *match; struct nft_pipapo_match *clone; int width; unsigned long last_gc; }; struct nft_pipapo_elem; /** * struct nft_pipapo_elem - API-facing representation of single set element * @priv: element placeholder * @ext: nftables API extensions */ struct nft_pipapo_elem { struct nft_elem_priv priv; struct nft_set_ext ext; }; int pipapo_refill(unsigned long *map, unsigned int len, unsigned int rules, unsigned long *dst, const union nft_pipapo_map_bucket *mt, bool match_only); /** * pipapo_and_field_buckets_4bit() - Intersect 4-bit buckets * @f: Field including lookup table * @dst: Area to store result * @data: Input data selecting table buckets */ static inline void pipapo_and_field_buckets_4bit(const struct nft_pipapo_field *f, unsigned long *dst, const u8 *data) { unsigned long *lt = NFT_PIPAPO_LT_ALIGN(f->lt); int group; for (group = 0; group < f->groups; group += BITS_PER_BYTE / 4, data++) { u8 v; v = *data >> 4; __bitmap_and(dst, dst, lt + v * f->bsize, f->bsize * BITS_PER_LONG); lt += f->bsize * NFT_PIPAPO_BUCKETS(4); v = *data & 0x0f; __bitmap_and(dst, dst, lt + v * f->bsize, f->bsize * BITS_PER_LONG); lt += f->bsize * NFT_PIPAPO_BUCKETS(4); } } /** * pipapo_and_field_buckets_8bit() - Intersect 8-bit buckets * @f: Field including lookup table * @dst: Area to store result * @data: Input data selecting table buckets */ static inline void pipapo_and_field_buckets_8bit(const struct nft_pipapo_field *f, unsigned long *dst, const u8 *data) { unsigned long *lt = NFT_PIPAPO_LT_ALIGN(f->lt); int group; for (group = 0; group < f->groups; group++, data++) { __bitmap_and(dst, dst, lt + *data * f->bsize, f->bsize * BITS_PER_LONG); lt += f->bsize * NFT_PIPAPO_BUCKETS(8); } } /** * pipapo_estimate_size() - Estimate worst-case for set size * @desc: Set description, element count and field description used here * * The size for this set type can vary dramatically, as it depends on the number * of rules (composing netmasks) the entries expand to. We compute the worst * case here. * * In general, for a non-ranged entry or a single composing netmask, we need * one bit in each of the sixteen NFT_PIPAPO_BUCKETS, for each 4-bit group (that * is, each input bit needs four bits of matching data), plus a bucket in the * mapping table for each field. * * Return: worst-case set size in bytes, 0 on any overflow */ static u64 pipapo_estimate_size(const struct nft_set_desc *desc) { unsigned long entry_size; u64 size; int i; for (i = 0, entry_size = 0; i < desc->field_count; i++) { unsigned long rules; if (desc->field_len[i] > NFT_PIPAPO_MAX_BYTES) return 0; /* Worst-case ranges for each concatenated field: each n-bit * field can expand to up to n * 2 rules in each bucket, and * each rule also needs a mapping bucket. */ rules = ilog2(desc->field_len[i] * BITS_PER_BYTE) * 2; entry_size += rules * NFT_PIPAPO_BUCKETS(NFT_PIPAPO_GROUP_BITS_INIT) / BITS_PER_BYTE; entry_size += rules * sizeof(union nft_pipapo_map_bucket); } /* Rules in lookup and mapping tables are needed for each entry */ size = desc->size * entry_size; if (size && div_u64(size, desc->size) != entry_size) return 0; size += sizeof(struct nft_pipapo) + sizeof(struct nft_pipapo_match) * 2; size += sizeof(struct nft_pipapo_field) * desc->field_count; return size; } /** * pipapo_resmap_init() - Initialise result map before first use * @m: Matching data, including mapping table * @res_map: Result map * * Initialize all bits covered by the first field to one, so that after * the first step, only the matching bits of the first bit group remain. * * If other fields have a large bitmap, set remainder of res_map to 0. */ static inline void pipapo_resmap_init(const struct nft_pipapo_match *m, unsigned long *res_map) { const struct nft_pipapo_field *f = m->f; int i; for (i = 0; i < f->bsize; i++) res_map[i] = ULONG_MAX; for (i = f->bsize; i < m->bsize_max; i++) res_map[i] = 0ul; } #endif /* _NFT_SET_PIPAPO_H */ |
| 1 1 2 1 1 2 2 5 5 5 1 1 4 4 1 1 2 1 2 3 1 1 2 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2022 Bobby Eshleman <bobby.eshleman@bytedance.com> * * Based off of net/unix/unix_bpf.c */ #include <linux/bpf.h> #include <linux/module.h> #include <linux/skmsg.h> #include <linux/socket.h> #include <linux/wait.h> #include <net/af_vsock.h> #include <net/sock.h> #define vsock_sk_has_data(__sk, __psock) \ ({ !skb_queue_empty(&(__sk)->sk_receive_queue) || \ !skb_queue_empty(&(__psock)->ingress_skb) || \ !list_empty(&(__psock)->ingress_msg); \ }) static struct proto *vsock_prot_saved __read_mostly; static DEFINE_SPINLOCK(vsock_prot_lock); static struct proto vsock_bpf_prot; static bool vsock_has_data(struct sock *sk, struct sk_psock *psock) { struct vsock_sock *vsk = vsock_sk(sk); s64 ret; ret = vsock_connectible_has_data(vsk); if (ret > 0) return true; return vsock_sk_has_data(sk, psock); } static bool vsock_msg_wait_data(struct sock *sk, struct sk_psock *psock, long timeo) { bool ret; DEFINE_WAIT_FUNC(wait, woken_wake_function); if (sk->sk_shutdown & RCV_SHUTDOWN) return true; if (!timeo) return false; add_wait_queue(sk_sleep(sk), &wait); sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); ret = vsock_has_data(sk, psock); if (!ret) { wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); ret = vsock_has_data(sk, psock); } sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); return ret; } static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags) { struct socket *sock = sk->sk_socket; int err; if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) err = __vsock_connectible_recvmsg(sock, msg, len, flags); else if (sk->sk_type == SOCK_DGRAM) err = __vsock_dgram_recvmsg(sock, msg, len, flags); else err = -EPROTOTYPE; return err; } static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct sk_psock *psock; struct vsock_sock *vsk; int copied; psock = sk_psock_get(sk); if (unlikely(!psock)) return __vsock_recvmsg(sk, msg, len, flags); lock_sock(sk); vsk = vsock_sk(sk); if (!vsk->transport) { copied = -ENODEV; goto out; } if (vsock_has_data(sk, psock) && sk_psock_queue_empty(psock)) { release_sock(sk); sk_psock_put(sk, psock); return __vsock_recvmsg(sk, msg, len, flags); } copied = sk_msg_recvmsg(sk, psock, msg, len, flags); while (copied == 0) { long timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); if (!vsock_msg_wait_data(sk, psock, timeo)) { copied = -EAGAIN; break; } if (sk_psock_queue_empty(psock)) { release_sock(sk); sk_psock_put(sk, psock); return __vsock_recvmsg(sk, msg, len, flags); } copied = sk_msg_recvmsg(sk, psock, msg, len, flags); } out: release_sock(sk); sk_psock_put(sk, psock); return copied; } static void vsock_bpf_rebuild_protos(struct proto *prot, const struct proto *base) { *prot = *base; prot->close = sock_map_close; prot->recvmsg = vsock_bpf_recvmsg; prot->sock_is_readable = sk_msg_is_readable; } static void vsock_bpf_check_needs_rebuild(struct proto *ops) { /* Paired with the smp_store_release() below. */ if (unlikely(ops != smp_load_acquire(&vsock_prot_saved))) { spin_lock_bh(&vsock_prot_lock); if (likely(ops != vsock_prot_saved)) { vsock_bpf_rebuild_protos(&vsock_bpf_prot, ops); /* Make sure proto function pointers are updated before publishing the * pointer to the struct. */ smp_store_release(&vsock_prot_saved, ops); } spin_unlock_bh(&vsock_prot_lock); } } int vsock_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { struct vsock_sock *vsk; if (restore) { sk->sk_write_space = psock->saved_write_space; sock_replace_proto(sk, psock->sk_proto); return 0; } vsk = vsock_sk(sk); if (!vsk->transport) return -ENODEV; if (!vsk->transport->read_skb) return -EOPNOTSUPP; vsock_bpf_check_needs_rebuild(psock->sk_proto); sock_replace_proto(sk, &vsock_bpf_prot); return 0; } void __init vsock_bpf_build_proto(void) { vsock_bpf_rebuild_protos(&vsock_bpf_prot, &vsock_proto); } |
| 2 36 139 139 31 135 25 73 82 137 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Cryptographic scatter and gather helpers. * * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> * Copyright (c) 2002 Adam J. Richter <adam@yggdrasil.com> * Copyright (c) 2004 Jean-Luc Cooke <jlcooke@certainkey.com> * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_SCATTERWALK_H #define _CRYPTO_SCATTERWALK_H #include <crypto/algapi.h> #include <linux/highmem.h> #include <linux/mm.h> #include <linux/scatterlist.h> static inline void scatterwalk_crypto_chain(struct scatterlist *head, struct scatterlist *sg, int num) { if (sg) sg_chain(head, num, sg); else sg_mark_end(head); } static inline unsigned int scatterwalk_pagelen(struct scatter_walk *walk) { unsigned int len = walk->sg->offset + walk->sg->length - walk->offset; unsigned int len_this_page = offset_in_page(~walk->offset) + 1; return len_this_page > len ? len : len_this_page; } static inline unsigned int scatterwalk_clamp(struct scatter_walk *walk, unsigned int nbytes) { unsigned int len_this_page = scatterwalk_pagelen(walk); return nbytes > len_this_page ? len_this_page : nbytes; } static inline void scatterwalk_advance(struct scatter_walk *walk, unsigned int nbytes) { walk->offset += nbytes; } static inline struct page *scatterwalk_page(struct scatter_walk *walk) { return sg_page(walk->sg) + (walk->offset >> PAGE_SHIFT); } static inline void scatterwalk_unmap(void *vaddr) { kunmap_local(vaddr); } static inline void scatterwalk_start(struct scatter_walk *walk, struct scatterlist *sg) { walk->sg = sg; walk->offset = sg->offset; } static inline void *scatterwalk_map(struct scatter_walk *walk) { return kmap_local_page(scatterwalk_page(walk)) + offset_in_page(walk->offset); } static inline void scatterwalk_pagedone(struct scatter_walk *walk, int out, unsigned int more) { if (out) { struct page *page; page = sg_page(walk->sg) + ((walk->offset - 1) >> PAGE_SHIFT); flush_dcache_page(page); } if (more && walk->offset >= walk->sg->offset + walk->sg->length) scatterwalk_start(walk, sg_next(walk->sg)); } static inline void scatterwalk_done(struct scatter_walk *walk, int out, int more) { if (!more || walk->offset >= walk->sg->offset + walk->sg->length || !(walk->offset & (PAGE_SIZE - 1))) scatterwalk_pagedone(walk, out, more); } void scatterwalk_copychunks(void *buf, struct scatter_walk *walk, size_t nbytes, int out); void scatterwalk_map_and_copy(void *buf, struct scatterlist *sg, unsigned int start, unsigned int nbytes, int out); struct scatterlist *scatterwalk_ffwd(struct scatterlist dst[2], struct scatterlist *src, unsigned int len); #endif /* _CRYPTO_SCATTERWALK_H */ |
| 1089 356 7 7 404 407 406 173 175 4 6 1441 18 1428 169 2 169 496 40 1 2 5 16 88 90 87 93 4 92 76 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * * This file contains the interface functions for the various time related * system calls: time, stime, gettimeofday, settimeofday, adjtime * * Modification history: * * 1993-09-02 Philip Gladstone * Created file with time related functions from sched/core.c and adjtimex() * 1993-10-08 Torsten Duwe * adjtime interface update and CMOS clock write code * 1995-08-13 Torsten Duwe * kernel PLL updated to 1994-12-13 specs (rfc-1589) * 1999-01-16 Ulrich Windl * Introduced error checking for many cases in adjtimex(). * Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * Allow time_constant larger than MAXTC(6) for NTP v4 (MAXTC == 10) * (Even though the technical memorandum forbids it) * 2004-07-14 Christoph Lameter * Added getnstimeofday to allow the posix timer functions to return * with nanosecond accuracy */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/timex.h> #include <linux/capability.h> #include <linux/timekeeper_internal.h> #include <linux/errno.h> #include <linux/syscalls.h> #include <linux/security.h> #include <linux/fs.h> #include <linux/math64.h> #include <linux/ptrace.h> #include <linux/uaccess.h> #include <linux/compat.h> #include <asm/unistd.h> #include <generated/timeconst.h> #include "timekeeping.h" /* * The timezone where the local system is located. Used as a default by some * programs who obtain this value by using gettimeofday. */ struct timezone sys_tz; EXPORT_SYMBOL(sys_tz); #ifdef __ARCH_WANT_SYS_TIME /* * sys_time() can be implemented in user-level using * sys_gettimeofday(). Is this for backwards compatibility? If so, * why not move it into the appropriate arch directory (for those * architectures that need it). */ SYSCALL_DEFINE1(time, __kernel_old_time_t __user *, tloc) { __kernel_old_time_t i = (__kernel_old_time_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) return -EFAULT; } force_successful_syscall_return(); return i; } /* * sys_stime() can be implemented in user-level using * sys_settimeofday(). Is this for backwards compatibility? If so, * why not move it into the appropriate arch directory (for those * architectures that need it). */ SYSCALL_DEFINE1(stime, __kernel_old_time_t __user *, tptr) { struct timespec64 tv; int err; if (get_user(tv.tv_sec, tptr)) return -EFAULT; tv.tv_nsec = 0; err = security_settime64(&tv, NULL); if (err) return err; do_settimeofday64(&tv); return 0; } #endif /* __ARCH_WANT_SYS_TIME */ #ifdef CONFIG_COMPAT_32BIT_TIME #ifdef __ARCH_WANT_SYS_TIME32 /* old_time32_t is a 32 bit "long" and needs to get converted. */ SYSCALL_DEFINE1(time32, old_time32_t __user *, tloc) { old_time32_t i; i = (old_time32_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) return -EFAULT; } force_successful_syscall_return(); return i; } SYSCALL_DEFINE1(stime32, old_time32_t __user *, tptr) { struct timespec64 tv; int err; if (get_user(tv.tv_sec, tptr)) return -EFAULT; tv.tv_nsec = 0; err = security_settime64(&tv, NULL); if (err) return err; do_settimeofday64(&tv); return 0; } #endif /* __ARCH_WANT_SYS_TIME32 */ #endif SYSCALL_DEFINE2(gettimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { if (likely(tv != NULL)) { struct timespec64 ts; ktime_get_real_ts64(&ts); if (put_user(ts.tv_sec, &tv->tv_sec) || put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (unlikely(tz != NULL)) { if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) return -EFAULT; } return 0; } /* * In case for some reason the CMOS clock has not already been running * in UTC, but in some local time: The first time we set the timezone, * we will warp the clock so that it is ticking UTC time instead of * local time. Presumably, if someone is setting the timezone then we * are running in an environment where the programs understand about * timezones. This should be done at boot time in the /etc/rc script, * as soon as possible, so that the clock can be set right. Otherwise, * various programs will get confused when the clock gets warped. */ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz) { static int firsttime = 1; int error = 0; if (tv && !timespec64_valid_settod(tv)) return -EINVAL; error = security_settime64(tv, tz); if (error) return error; if (tz) { /* Verify we're within the +-15 hrs range */ if (tz->tz_minuteswest > 15*60 || tz->tz_minuteswest < -15*60) return -EINVAL; sys_tz = *tz; update_vsyscall_tz(); if (firsttime) { firsttime = 0; if (!tv) timekeeping_warp_clock(); } } if (tv) return do_settimeofday64(tv); return 0; } SYSCALL_DEFINE2(settimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; struct timezone new_tz; if (tv) { if (get_user(new_ts.tv_sec, &tv->tv_sec) || get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) return -EFAULT; } return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(gettimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { if (tv) { struct timespec64 ts; ktime_get_real_ts64(&ts); if (put_user(ts.tv_sec, &tv->tv_sec) || put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (tz) { if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) return -EFAULT; } return 0; } COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; struct timezone new_tz; if (tv) { if (get_user(new_ts.tv_sec, &tv->tv_sec) || get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) return -EFAULT; } return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } #endif #ifdef CONFIG_64BIT SYSCALL_DEFINE1(adjtimex, struct __kernel_timex __user *, txc_p) { struct __kernel_timex txc; /* Local copy of parameter */ int ret; /* Copy the user data space into the kernel copy * structure. But bear in mind that the structures * may change */ if (copy_from_user(&txc, txc_p, sizeof(struct __kernel_timex))) return -EFAULT; ret = do_adjtimex(&txc); return copy_to_user(txc_p, &txc, sizeof(struct __kernel_timex)) ? -EFAULT : ret; } #endif #ifdef CONFIG_COMPAT_32BIT_TIME int get_old_timex32(struct __kernel_timex *txc, const struct old_timex32 __user *utp) { struct old_timex32 tx32; memset(txc, 0, sizeof(struct __kernel_timex)); if (copy_from_user(&tx32, utp, sizeof(struct old_timex32))) return -EFAULT; txc->modes = tx32.modes; txc->offset = tx32.offset; txc->freq = tx32.freq; txc->maxerror = tx32.maxerror; txc->esterror = tx32.esterror; txc->status = tx32.status; txc->constant = tx32.constant; txc->precision = tx32.precision; txc->tolerance = tx32.tolerance; txc->time.tv_sec = tx32.time.tv_sec; txc->time.tv_usec = tx32.time.tv_usec; txc->tick = tx32.tick; txc->ppsfreq = tx32.ppsfreq; txc->jitter = tx32.jitter; txc->shift = tx32.shift; txc->stabil = tx32.stabil; txc->jitcnt = tx32.jitcnt; txc->calcnt = tx32.calcnt; txc->errcnt = tx32.errcnt; txc->stbcnt = tx32.stbcnt; return 0; } int put_old_timex32(struct old_timex32 __user *utp, const struct __kernel_timex *txc) { struct old_timex32 tx32; memset(&tx32, 0, sizeof(struct old_timex32)); tx32.modes = txc->modes; tx32.offset = txc->offset; tx32.freq = txc->freq; tx32.maxerror = txc->maxerror; tx32.esterror = txc->esterror; tx32.status = txc->status; tx32.constant = txc->constant; tx32.precision = txc->precision; tx32.tolerance = txc->tolerance; tx32.time.tv_sec = txc->time.tv_sec; tx32.time.tv_usec = txc->time.tv_usec; tx32.tick = txc->tick; tx32.ppsfreq = txc->ppsfreq; tx32.jitter = txc->jitter; tx32.shift = txc->shift; tx32.stabil = txc->stabil; tx32.jitcnt = txc->jitcnt; tx32.calcnt = txc->calcnt; tx32.errcnt = txc->errcnt; tx32.stbcnt = txc->stbcnt; tx32.tai = txc->tai; if (copy_to_user(utp, &tx32, sizeof(struct old_timex32))) return -EFAULT; return 0; } SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp) { struct __kernel_timex txc; int err, ret; err = get_old_timex32(&txc, utp); if (err) return err; ret = do_adjtimex(&txc); err = put_old_timex32(utp, &txc); if (err) return err; return ret; } #endif /** * jiffies_to_msecs - Convert jiffies to milliseconds * @j: jiffies value * * Avoid unnecessary multiplications/divisions in the * two most common HZ cases. * * Return: milliseconds value */ unsigned int jiffies_to_msecs(const unsigned long j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; #elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC); #else # if BITS_PER_LONG == 32 return (HZ_TO_MSEC_MUL32 * j + (1ULL << HZ_TO_MSEC_SHR32) - 1) >> HZ_TO_MSEC_SHR32; # else return DIV_ROUND_UP(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); # endif #endif } EXPORT_SYMBOL(jiffies_to_msecs); /** * jiffies_to_usecs - Convert jiffies to microseconds * @j: jiffies value * * Return: microseconds value */ unsigned int jiffies_to_usecs(const unsigned long j) { /* * Hz usually doesn't go much further MSEC_PER_SEC. * jiffies_to_usecs() and usecs_to_jiffies() depend on that. */ BUILD_BUG_ON(HZ > USEC_PER_SEC); #if !(USEC_PER_SEC % HZ) return (USEC_PER_SEC / HZ) * j; #else # if BITS_PER_LONG == 32 return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32; # else return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN; # endif #endif } EXPORT_SYMBOL(jiffies_to_usecs); /** * mktime64 - Converts date to seconds. * @year0: year to convert * @mon0: month to convert * @day: day to convert * @hour: hour to convert * @min: minute to convert * @sec: second to convert * * Converts Gregorian date to seconds since 1970-01-01 00:00:00. * Assumes input in normal date format, i.e. 1980-12-31 23:59:59 * => year=1980, mon=12, day=31, hour=23, min=59, sec=59. * * [For the Julian calendar (which was used in Russia before 1917, * Britain & colonies before 1752, anywhere else before 1582, * and is still in use by some communities) leave out the * -year/100+year/400 terms, and add 10.] * * This algorithm was first published by Gauss (I think). * * A leap second can be indicated by calling this function with sec as * 60 (allowable under ISO 8601). The leap second is treated the same * as the following second since they don't exist in UNIX time. * * An encoding of midnight at the end of the day as 24:00:00 - ie. midnight * tomorrow - (allowable under ISO 8601) is supported. * * Return: seconds since the epoch time for the given input date */ time64_t mktime64(const unsigned int year0, const unsigned int mon0, const unsigned int day, const unsigned int hour, const unsigned int min, const unsigned int sec) { unsigned int mon = mon0, year = year0; /* 1..12 -> 11,12,1..10 */ if (0 >= (int) (mon -= 2)) { mon += 12; /* Puts Feb last since it has leap day */ year -= 1; } return ((((time64_t) (year/4 - year/100 + year/400 + 367*mon/12 + day) + year*365 - 719499 )*24 + hour /* now have hours - midnight tomorrow handled here */ )*60 + min /* now have minutes */ )*60 + sec; /* finally seconds */ } EXPORT_SYMBOL(mktime64); struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec) { struct timespec64 ts = ns_to_timespec64(nsec); struct __kernel_old_timeval tv; tv.tv_sec = ts.tv_sec; tv.tv_usec = (suseconds_t)ts.tv_nsec / 1000; return tv; } EXPORT_SYMBOL(ns_to_kernel_old_timeval); /** * set_normalized_timespec64 - set timespec sec and nsec parts and normalize * * @ts: pointer to timespec variable to be set * @sec: seconds to set * @nsec: nanoseconds to set * * Set seconds and nanoseconds field of a timespec variable and * normalize to the timespec storage format * * Note: The tv_nsec part is always in the range of 0 <= tv_nsec < NSEC_PER_SEC. * For negative values only the tv_sec field is negative ! */ void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec) { while (nsec >= NSEC_PER_SEC) { /* * The following asm() prevents the compiler from * optimising this loop into a modulo operation. See * also __iter_div_u64_rem() in include/linux/time.h */ asm("" : "+rm"(nsec)); nsec -= NSEC_PER_SEC; ++sec; } while (nsec < 0) { asm("" : "+rm"(nsec)); nsec += NSEC_PER_SEC; --sec; } ts->tv_sec = sec; ts->tv_nsec = nsec; } EXPORT_SYMBOL(set_normalized_timespec64); /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Return: the timespec64 representation of the nsec parameter. */ struct timespec64 ns_to_timespec64(s64 nsec) { struct timespec64 ts = { 0, 0 }; s32 rem; if (likely(nsec > 0)) { ts.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); ts.tv_nsec = rem; } else if (nsec < 0) { /* * With negative times, tv_sec points to the earlier * second, and tv_nsec counts the nanoseconds since * then, so tv_nsec is always a positive number. */ ts.tv_sec = -div_u64_rem(-nsec - 1, NSEC_PER_SEC, &rem) - 1; ts.tv_nsec = NSEC_PER_SEC - rem - 1; } return ts; } EXPORT_SYMBOL(ns_to_timespec64); /** * __msecs_to_jiffies: - convert milliseconds to jiffies * @m: time in milliseconds * * conversion is done as follows: * * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET) * * - 'too large' values [that would result in larger than * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. * * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows. * for the details see _msecs_to_jiffies() * * msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the * code, __msecs_to_jiffies() is called if the value passed does not * allow constant folding and the actual conversion must be done at * runtime. * The _msecs_to_jiffies helpers are the HZ dependent conversion * routines found in include/linux/jiffies.h * * Return: jiffies value */ unsigned long __msecs_to_jiffies(const unsigned int m) { /* * Negative value, means infinite timeout: */ if ((int)m < 0) return MAX_JIFFY_OFFSET; return _msecs_to_jiffies(m); } EXPORT_SYMBOL(__msecs_to_jiffies); /** * __usecs_to_jiffies: - convert microseconds to jiffies * @u: time in milliseconds * * Return: jiffies value */ unsigned long __usecs_to_jiffies(const unsigned int u) { if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; return _usecs_to_jiffies(u); } EXPORT_SYMBOL(__usecs_to_jiffies); /** * timespec64_to_jiffies - convert a timespec64 value to jiffies * @value: pointer to &struct timespec64 * * The TICK_NSEC - 1 rounds up the value to the next resolution. Note * that a remainder subtract here would not do the right thing as the * resolution values don't fall on second boundaries. I.e. the line: * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding. * Note that due to the small error in the multiplier here, this * rounding is incorrect for sufficiently large values of tv_nsec, but * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're * OK. * * Rather, we just shift the bits off the right. * * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec * value to a scaled second value. * * Return: jiffies value */ unsigned long timespec64_to_jiffies(const struct timespec64 *value) { u64 sec = value->tv_sec; long nsec = value->tv_nsec + TICK_NSEC - 1; if (sec >= MAX_SEC_IN_JIFFIES){ sec = MAX_SEC_IN_JIFFIES; nsec = 0; } return ((sec * SEC_CONVERSION) + (((u64)nsec * NSEC_CONVERSION) >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; } EXPORT_SYMBOL(timespec64_to_jiffies); /** * jiffies_to_timespec64 - convert jiffies value to &struct timespec64 * @jiffies: jiffies value * @value: pointer to &struct timespec64 */ void jiffies_to_timespec64(const unsigned long jiffies, struct timespec64 *value) { /* * Convert jiffies to nanoseconds and separate with * one divide. */ u32 rem; value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC, NSEC_PER_SEC, &rem); value->tv_nsec = rem; } EXPORT_SYMBOL(jiffies_to_timespec64); /* * Convert jiffies/jiffies_64 to clock_t and back. */ /** * jiffies_to_clock_t - Convert jiffies to clock_t * @x: jiffies value * * Return: jiffies converted to clock_t (CLOCKS_PER_SEC) */ clock_t jiffies_to_clock_t(unsigned long x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ return x * (USER_HZ / HZ); # else return x / (HZ / USER_HZ); # endif #else return div_u64((u64)x * TICK_NSEC, NSEC_PER_SEC / USER_HZ); #endif } EXPORT_SYMBOL(jiffies_to_clock_t); /** * clock_t_to_jiffies - Convert clock_t to jiffies * @x: clock_t value * * Return: clock_t value converted to jiffies */ unsigned long clock_t_to_jiffies(unsigned long x) { #if (HZ % USER_HZ)==0 if (x >= ~0UL / (HZ / USER_HZ)) return ~0UL; return x * (HZ / USER_HZ); #else /* Don't worry about loss of precision here .. */ if (x >= ~0UL / HZ * USER_HZ) return ~0UL; /* .. but do try to contain it here */ return div_u64((u64)x * HZ, USER_HZ); #endif } EXPORT_SYMBOL(clock_t_to_jiffies); /** * jiffies_64_to_clock_t - Convert jiffies_64 to clock_t * @x: jiffies_64 value * * Return: jiffies_64 value converted to 64-bit "clock_t" (CLOCKS_PER_SEC) */ u64 jiffies_64_to_clock_t(u64 x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ x = div_u64(x * USER_HZ, HZ); # elif HZ > USER_HZ x = div_u64(x, HZ / USER_HZ); # else /* Nothing to do */ # endif #else /* * There are better ways that don't overflow early, * but even this doesn't overflow in hundreds of years * in 64 bits, so.. */ x = div_u64(x * TICK_NSEC, (NSEC_PER_SEC / USER_HZ)); #endif return x; } EXPORT_SYMBOL(jiffies_64_to_clock_t); /** * nsec_to_clock_t - Convert nsec value to clock_t * @x: nsec value * * Return: nsec value converted to 64-bit "clock_t" (CLOCKS_PER_SEC) */ u64 nsec_to_clock_t(u64 x) { #if (NSEC_PER_SEC % USER_HZ) == 0 return div_u64(x, NSEC_PER_SEC / USER_HZ); #elif (USER_HZ % 512) == 0 return div_u64(x * USER_HZ / 512, NSEC_PER_SEC / 512); #else /* * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024, * overflow after 64.99 years. * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ... */ return div_u64(x * 9, (9ull * NSEC_PER_SEC + (USER_HZ / 2)) / USER_HZ); #endif } /** * jiffies64_to_nsecs - Convert jiffies64 to nanoseconds * @j: jiffies64 value * * Return: nanoseconds value */ u64 jiffies64_to_nsecs(u64 j) { #if !(NSEC_PER_SEC % HZ) return (NSEC_PER_SEC / HZ) * j; # else return div_u64(j * HZ_TO_NSEC_NUM, HZ_TO_NSEC_DEN); #endif } EXPORT_SYMBOL(jiffies64_to_nsecs); /** * jiffies64_to_msecs - Convert jiffies64 to milliseconds * @j: jiffies64 value * * Return: milliseconds value */ u64 jiffies64_to_msecs(const u64 j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; #else return div_u64(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); #endif } EXPORT_SYMBOL(jiffies64_to_msecs); /** * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64 * * @n: nsecs in u64 * * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. * And this doesn't return MAX_JIFFY_OFFSET since this function is designed * for scheduler, not for use in device drivers to calculate timeout value. * * note: * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years * * Return: nsecs converted to jiffies64 value */ u64 nsecs_to_jiffies64(u64 n) { #if (NSEC_PER_SEC % HZ) == 0 /* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */ return div_u64(n, NSEC_PER_SEC / HZ); #elif (HZ % 512) == 0 /* overflow after 292 years if HZ = 1024 */ return div_u64(n * HZ / 512, NSEC_PER_SEC / 512); #else /* * Generic case - optimized for cases where HZ is a multiple of 3. * overflow after 64.99 years, exact for HZ = 60, 72, 90, 120 etc. */ return div_u64(n * 9, (9ull * NSEC_PER_SEC + HZ / 2) / HZ); #endif } EXPORT_SYMBOL(nsecs_to_jiffies64); /** * nsecs_to_jiffies - Convert nsecs in u64 to jiffies * * @n: nsecs in u64 * * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. * And this doesn't return MAX_JIFFY_OFFSET since this function is designed * for scheduler, not for use in device drivers to calculate timeout value. * * note: * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years * * Return: nsecs converted to jiffies value */ unsigned long nsecs_to_jiffies(u64 n) { return (unsigned long)nsecs_to_jiffies64(n); } EXPORT_SYMBOL_GPL(nsecs_to_jiffies); /** * timespec64_add_safe - Add two timespec64 values and do a safety check * for overflow. * @lhs: first (left) timespec64 to add * @rhs: second (right) timespec64 to add * * It's assumed that both values are valid (>= 0). * And, each timespec64 is in normalized form. * * Return: sum of @lhs + @rhs */ struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs) { struct timespec64 res; set_normalized_timespec64(&res, (timeu64_t) lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); if (unlikely(res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec)) { res.tv_sec = TIME64_MAX; res.tv_nsec = 0; } return res; } /** * get_timespec64 - get user's time value into kernel space * @ts: destination &struct timespec64 * @uts: user's time value as &struct __kernel_timespec * * Handles compat or 32-bit modes. * * Return: 0 on success or negative errno on error */ int get_timespec64(struct timespec64 *ts, const struct __kernel_timespec __user *uts) { struct __kernel_timespec kts; int ret; ret = copy_from_user(&kts, uts, sizeof(kts)); if (ret) return -EFAULT; ts->tv_sec = kts.tv_sec; /* Zero out the padding in compat mode */ if (in_compat_syscall()) kts.tv_nsec &= 0xFFFFFFFFUL; /* In 32-bit mode, this drops the padding */ ts->tv_nsec = kts.tv_nsec; return 0; } EXPORT_SYMBOL_GPL(get_timespec64); /** * put_timespec64 - convert timespec64 value to __kernel_timespec format and * copy the latter to userspace * @ts: input &struct timespec64 * @uts: user's &struct __kernel_timespec * * Return: 0 on success or negative errno on error */ int put_timespec64(const struct timespec64 *ts, struct __kernel_timespec __user *uts) { struct __kernel_timespec kts = { .tv_sec = ts->tv_sec, .tv_nsec = ts->tv_nsec }; return copy_to_user(uts, &kts, sizeof(kts)) ? -EFAULT : 0; } EXPORT_SYMBOL_GPL(put_timespec64); static int __get_old_timespec32(struct timespec64 *ts64, const struct old_timespec32 __user *cts) { struct old_timespec32 ts; int ret; ret = copy_from_user(&ts, cts, sizeof(ts)); if (ret) return -EFAULT; ts64->tv_sec = ts.tv_sec; ts64->tv_nsec = ts.tv_nsec; return 0; } static int __put_old_timespec32(const struct timespec64 *ts64, struct old_timespec32 __user *cts) { struct old_timespec32 ts = { .tv_sec = ts64->tv_sec, .tv_nsec = ts64->tv_nsec }; return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0; } /** * get_old_timespec32 - get user's old-format time value into kernel space * @ts: destination &struct timespec64 * @uts: user's old-format time value (&struct old_timespec32) * * Handles X86_X32_ABI compatibility conversion. * * Return: 0 on success or negative errno on error */ int get_old_timespec32(struct timespec64 *ts, const void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0; else return __get_old_timespec32(ts, uts); } EXPORT_SYMBOL_GPL(get_old_timespec32); /** * put_old_timespec32 - convert timespec64 value to &struct old_timespec32 and * copy the latter to userspace * @ts: input &struct timespec64 * @uts: user's &struct old_timespec32 * * Handles X86_X32_ABI compatibility conversion. * * Return: 0 on success or negative errno on error */ int put_old_timespec32(const struct timespec64 *ts, void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0; else return __put_old_timespec32(ts, uts); } EXPORT_SYMBOL_GPL(put_old_timespec32); /** * get_itimerspec64 - get user's &struct __kernel_itimerspec into kernel space * @it: destination &struct itimerspec64 * @uit: user's &struct __kernel_itimerspec * * Return: 0 on success or negative errno on error */ int get_itimerspec64(struct itimerspec64 *it, const struct __kernel_itimerspec __user *uit) { int ret; ret = get_timespec64(&it->it_interval, &uit->it_interval); if (ret) return ret; ret = get_timespec64(&it->it_value, &uit->it_value); return ret; } EXPORT_SYMBOL_GPL(get_itimerspec64); /** * put_itimerspec64 - convert &struct itimerspec64 to __kernel_itimerspec format * and copy the latter to userspace * @it: input &struct itimerspec64 * @uit: user's &struct __kernel_itimerspec * * Return: 0 on success or negative errno on error */ int put_itimerspec64(const struct itimerspec64 *it, struct __kernel_itimerspec __user *uit) { int ret; ret = put_timespec64(&it->it_interval, &uit->it_interval); if (ret) return ret; ret = put_timespec64(&it->it_value, &uit->it_value); return ret; } EXPORT_SYMBOL_GPL(put_itimerspec64); /** * get_old_itimerspec32 - get user's &struct old_itimerspec32 into kernel space * @its: destination &struct itimerspec64 * @uits: user's &struct old_itimerspec32 * * Return: 0 on success or negative errno on error */ int get_old_itimerspec32(struct itimerspec64 *its, const struct old_itimerspec32 __user *uits) { if (__get_old_timespec32(&its->it_interval, &uits->it_interval) || __get_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(get_old_itimerspec32); /** * put_old_itimerspec32 - convert &struct itimerspec64 to &struct * old_itimerspec32 and copy the latter to userspace * @its: input &struct itimerspec64 * @uits: user's &struct old_itimerspec32 * * Return: 0 on success or negative errno on error */ int put_old_itimerspec32(const struct itimerspec64 *its, struct old_itimerspec32 __user *uits) { if (__put_old_timespec32(&its->it_interval, &uits->it_interval) || __put_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(put_old_itimerspec32); |
| 1 1 1 1 8 9 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ /* Kernel module implementing an IP set type: the bitmap:port type */ #include <linux/module.h> #include <linux/ip.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/netlink.h> #include <linux/jiffies.h> #include <linux/timer.h> #include <net/netlink.h> #include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_bitmap.h> #include <linux/netfilter/ipset/ip_set_getport.h> #define IPSET_TYPE_REV_MIN 0 /* 1 Counter support added */ /* 2 Comment support added */ #define IPSET_TYPE_REV_MAX 3 /* skbinfo support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); IP_SET_MODULE_DESC("bitmap:port", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_bitmap:port"); #define MTYPE bitmap_port /* Type structure */ struct bitmap_port { unsigned long *members; /* the set members */ u16 first_port; /* host byte order, included in range */ u16 last_port; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ size_t memsize; /* members size */ struct timer_list gc; /* garbage collection */ struct ip_set *set; /* attached to this ip_set */ unsigned char extensions[] /* data extensions */ __aligned(__alignof__(u64)); }; /* ADT structure for generic function args */ struct bitmap_port_adt_elem { u16 id; }; static u16 port_to_id(const struct bitmap_port *m, u16 port) { return port - m->first_port; } /* Common functions */ static int bitmap_port_do_test(const struct bitmap_port_adt_elem *e, const struct bitmap_port *map, size_t dsize) { return !!test_bit(e->id, map->members); } static int bitmap_port_gc_test(u16 id, const struct bitmap_port *map, size_t dsize) { return !!test_bit(id, map->members); } static int bitmap_port_do_add(const struct bitmap_port_adt_elem *e, struct bitmap_port *map, u32 flags, size_t dsize) { return !!test_bit(e->id, map->members); } static int bitmap_port_do_del(const struct bitmap_port_adt_elem *e, struct bitmap_port *map) { return !test_and_clear_bit(e->id, map->members); } static int bitmap_port_do_list(struct sk_buff *skb, const struct bitmap_port *map, u32 id, size_t dsize) { return nla_put_net16(skb, IPSET_ATTR_PORT, htons(map->first_port + id)); } static int bitmap_port_do_head(struct sk_buff *skb, const struct bitmap_port *map) { return nla_put_net16(skb, IPSET_ATTR_PORT, htons(map->first_port)) || nla_put_net16(skb, IPSET_ATTR_PORT_TO, htons(map->last_port)); } static bool ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src, __be16 *port) { bool ret; u8 proto; switch (pf) { case NFPROTO_IPV4: ret = ip_set_get_ip4_port(skb, src, port, &proto); break; case NFPROTO_IPV6: ret = ip_set_get_ip6_port(skb, src, port, &proto); break; default: return false; } if (!ret) return ret; switch (proto) { case IPPROTO_TCP: case IPPROTO_UDP: return true; default: return false; } } static int bitmap_port_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { struct bitmap_port *map = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct bitmap_port_adt_elem e = { .id = 0 }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); __be16 __port; u16 port = 0; if (!ip_set_get_ip_port(skb, opt->family, opt->flags & IPSET_DIM_ONE_SRC, &__port)) return -EINVAL; port = ntohs(__port); if (port < map->first_port || port > map->last_port) return -IPSET_ERR_BITMAP_RANGE; e.id = port_to_id(map, port); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int bitmap_port_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { struct bitmap_port *map = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct bitmap_port_adt_elem e = { .id = 0 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 port; /* wraparound */ u16 port_to; int ret = 0; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO))) return -IPSET_ERR_PROTOCOL; port = ip_set_get_h16(tb[IPSET_ATTR_PORT]); if (port < map->first_port || port > map->last_port) return -IPSET_ERR_BITMAP_RANGE; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; if (adt == IPSET_TEST) { e.id = port_to_id(map, port); return adtfn(set, &e, &ext, &ext, flags); } if (tb[IPSET_ATTR_PORT_TO]) { port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) { swap(port, port_to); if (port < map->first_port) return -IPSET_ERR_BITMAP_RANGE; } } else { port_to = port; } if (port_to > map->last_port) return -IPSET_ERR_BITMAP_RANGE; for (; port <= port_to; port++) { e.id = port_to_id(map, port); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } return ret; } static bool bitmap_port_same_set(const struct ip_set *a, const struct ip_set *b) { const struct bitmap_port *x = a->data; const struct bitmap_port *y = b->data; return x->first_port == y->first_port && x->last_port == y->last_port && a->timeout == b->timeout && a->extensions == b->extensions; } /* Plain variant */ struct bitmap_port_elem { }; #include "ip_set_bitmap_gen.h" /* Create bitmap:ip type of sets */ static bool init_map_port(struct ip_set *set, struct bitmap_port *map, u16 first_port, u16 last_port) { map->members = bitmap_zalloc(map->elements, GFP_KERNEL | __GFP_NOWARN); if (!map->members) return false; map->first_port = first_port; map->last_port = last_port; set->timeout = IPSET_NO_TIMEOUT; map->set = set; set->data = map; set->family = NFPROTO_UNSPEC; return true; } static int bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[], u32 flags) { struct bitmap_port *map; u16 first_port, last_port; u32 elements; if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT_TO) || !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; first_port = ip_set_get_h16(tb[IPSET_ATTR_PORT]); last_port = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (first_port > last_port) swap(first_port, last_port); elements = last_port - first_port + 1; set->dsize = ip_set_elem_len(set, tb, 0, 0); map = ip_set_alloc(sizeof(*map) + elements * set->dsize); if (!map) return -ENOMEM; map->elements = elements; map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_port; if (!init_map_port(set, map, first_port, last_port)) { ip_set_free(map); return -ENOMEM; } if (tb[IPSET_ATTR_TIMEOUT]) { set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); bitmap_port_gc_init(set, bitmap_port_gc); } return 0; } static struct ip_set_type bitmap_port_type = { .name = "bitmap:port", .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_PORT, .dimension = IPSET_DIM_ONE, .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, .create = bitmap_port_create, .create_policy = { [IPSET_ATTR_PORT] = { .type = NLA_U16 }, [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .adt_policy = { [IPSET_ATTR_PORT] = { .type = NLA_U16 }, [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, }, .me = THIS_MODULE, }; static int __init bitmap_port_init(void) { return ip_set_type_register(&bitmap_port_type); } static void __exit bitmap_port_fini(void) { rcu_barrier(); ip_set_type_unregister(&bitmap_port_type); } module_init(bitmap_port_init); module_exit(bitmap_port_fini); |
| 3 1 2 3 1 2 3 1 1 3 1 1 5 1 5 7 1 1 1 2 8 4 4 8 3 5 3 3 1 2 4 3 2 1 1 3 3 1 9 8 8 8 6 6 6 5 17 1 1 1 1 4 6 3 1 5 3 1 1 3 1 3 6 3 9 9 9 9 5 5 5 4 1 4 1 5 6 6 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/ife.c Inter-FE action based on ForCES WG InterFE LFB * * Refer to: * draft-ietf-forces-interfelfb-03 * and * netdev01 paper: * "Distributing Linux Traffic Control Classifier-Action * Subsystem" * Authors: Jamal Hadi Salim and Damascene M. Joachimpillai * * copyright Jamal Hadi Salim (2015) */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/module.h> #include <linux/init.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <uapi/linux/tc_act/tc_ife.h> #include <net/tc_act/tc_ife.h> #include <linux/etherdevice.h> #include <net/ife.h> #include <net/tc_wrapper.h> static int max_metacnt = IFE_META_MAX + 1; static struct tc_action_ops act_ife_ops; static const struct nla_policy ife_policy[TCA_IFE_MAX + 1] = { [TCA_IFE_PARMS] = { .len = sizeof(struct tc_ife)}, [TCA_IFE_DMAC] = { .len = ETH_ALEN}, [TCA_IFE_SMAC] = { .len = ETH_ALEN}, [TCA_IFE_TYPE] = { .type = NLA_U16}, }; int ife_encode_meta_u16(u16 metaval, void *skbdata, struct tcf_meta_info *mi) { u16 edata = 0; if (mi->metaval) edata = *(u16 *)mi->metaval; else if (metaval) edata = metaval; if (!edata) /* will not encode */ return 0; edata = htons(edata); return ife_tlv_meta_encode(skbdata, mi->metaid, 2, &edata); } EXPORT_SYMBOL_GPL(ife_encode_meta_u16); int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi) { if (mi->metaval) return nla_put_u32(skb, mi->metaid, *(u32 *)mi->metaval); else return nla_put(skb, mi->metaid, 0, NULL); } EXPORT_SYMBOL_GPL(ife_get_meta_u32); int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi) { if (metaval || mi->metaval) return 8; /* T+L+V == 2+2+4 */ return 0; } EXPORT_SYMBOL_GPL(ife_check_meta_u32); int ife_check_meta_u16(u16 metaval, struct tcf_meta_info *mi) { if (metaval || mi->metaval) return 8; /* T+L+(V) == 2+2+(2+2bytepad) */ return 0; } EXPORT_SYMBOL_GPL(ife_check_meta_u16); int ife_encode_meta_u32(u32 metaval, void *skbdata, struct tcf_meta_info *mi) { u32 edata = metaval; if (mi->metaval) edata = *(u32 *)mi->metaval; else if (metaval) edata = metaval; if (!edata) /* will not encode */ return 0; edata = htonl(edata); return ife_tlv_meta_encode(skbdata, mi->metaid, 4, &edata); } EXPORT_SYMBOL_GPL(ife_encode_meta_u32); int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi) { if (mi->metaval) return nla_put_u16(skb, mi->metaid, *(u16 *)mi->metaval); else return nla_put(skb, mi->metaid, 0, NULL); } EXPORT_SYMBOL_GPL(ife_get_meta_u16); int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval, gfp_t gfp) { mi->metaval = kmemdup(metaval, sizeof(u32), gfp); if (!mi->metaval) return -ENOMEM; return 0; } EXPORT_SYMBOL_GPL(ife_alloc_meta_u32); int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval, gfp_t gfp) { mi->metaval = kmemdup(metaval, sizeof(u16), gfp); if (!mi->metaval) return -ENOMEM; return 0; } EXPORT_SYMBOL_GPL(ife_alloc_meta_u16); void ife_release_meta_gen(struct tcf_meta_info *mi) { kfree(mi->metaval); } EXPORT_SYMBOL_GPL(ife_release_meta_gen); int ife_validate_meta_u32(void *val, int len) { if (len == sizeof(u32)) return 0; return -EINVAL; } EXPORT_SYMBOL_GPL(ife_validate_meta_u32); int ife_validate_meta_u16(void *val, int len) { /* length will not include padding */ if (len == sizeof(u16)) return 0; return -EINVAL; } EXPORT_SYMBOL_GPL(ife_validate_meta_u16); static LIST_HEAD(ifeoplist); static DEFINE_RWLOCK(ife_mod_lock); static struct tcf_meta_ops *find_ife_oplist(u16 metaid) { struct tcf_meta_ops *o; read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { if (o->metaid == metaid) { if (!try_module_get(o->owner)) o = NULL; read_unlock(&ife_mod_lock); return o; } } read_unlock(&ife_mod_lock); return NULL; } int register_ife_op(struct tcf_meta_ops *mops) { struct tcf_meta_ops *m; if (!mops->metaid || !mops->metatype || !mops->name || !mops->check_presence || !mops->encode || !mops->decode || !mops->get || !mops->alloc) return -EINVAL; write_lock(&ife_mod_lock); list_for_each_entry(m, &ifeoplist, list) { if (m->metaid == mops->metaid || (strcmp(mops->name, m->name) == 0)) { write_unlock(&ife_mod_lock); return -EEXIST; } } if (!mops->release) mops->release = ife_release_meta_gen; list_add_tail(&mops->list, &ifeoplist); write_unlock(&ife_mod_lock); return 0; } EXPORT_SYMBOL_GPL(unregister_ife_op); int unregister_ife_op(struct tcf_meta_ops *mops) { struct tcf_meta_ops *m; int err = -ENOENT; write_lock(&ife_mod_lock); list_for_each_entry(m, &ifeoplist, list) { if (m->metaid == mops->metaid) { list_del(&mops->list); err = 0; break; } } write_unlock(&ife_mod_lock); return err; } EXPORT_SYMBOL_GPL(register_ife_op); static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len) { int ret = 0; /* XXX: unfortunately cant use nla_policy at this point * because a length of 0 is valid in the case of * "allow". "use" semantics do enforce for proper * length and i couldve use nla_policy but it makes it hard * to use it just for that.. */ if (ops->validate) return ops->validate(val, len); if (ops->metatype == NLA_U32) ret = ife_validate_meta_u32(val, len); else if (ops->metatype == NLA_U16) ret = ife_validate_meta_u16(val, len); return ret; } #ifdef CONFIG_MODULES static const char *ife_meta_id2name(u32 metaid) { switch (metaid) { case IFE_META_SKBMARK: return "skbmark"; case IFE_META_PRIO: return "skbprio"; case IFE_META_TCINDEX: return "tcindex"; default: return "unknown"; } } #endif /* called when adding new meta information */ static int load_metaops_and_vet(u32 metaid, void *val, int len, bool rtnl_held) { struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret = 0; if (!ops) { ret = -ENOENT; #ifdef CONFIG_MODULES if (rtnl_held) rtnl_unlock(); request_module("ife-meta-%s", ife_meta_id2name(metaid)); if (rtnl_held) rtnl_lock(); ops = find_ife_oplist(metaid); #endif } if (ops) { ret = 0; if (len) ret = ife_validate_metatype(ops, val, len); module_put(ops->owner); } return ret; } /* called when adding new meta information */ static int __add_metainfo(const struct tcf_meta_ops *ops, struct tcf_ife_info *ife, u32 metaid, void *metaval, int len, bool atomic, bool exists) { struct tcf_meta_info *mi = NULL; int ret = 0; mi = kzalloc(sizeof(*mi), atomic ? GFP_ATOMIC : GFP_KERNEL); if (!mi) return -ENOMEM; mi->metaid = metaid; mi->ops = ops; if (len > 0) { ret = ops->alloc(mi, metaval, atomic ? GFP_ATOMIC : GFP_KERNEL); if (ret != 0) { kfree(mi); return ret; } } if (exists) spin_lock_bh(&ife->tcf_lock); list_add_tail(&mi->metalist, &ife->metalist); if (exists) spin_unlock_bh(&ife->tcf_lock); return ret; } static int add_metainfo_and_get_ops(const struct tcf_meta_ops *ops, struct tcf_ife_info *ife, u32 metaid, bool exists) { int ret; if (!try_module_get(ops->owner)) return -ENOENT; ret = __add_metainfo(ops, ife, metaid, NULL, 0, true, exists); if (ret) module_put(ops->owner); return ret; } static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, int len, bool exists) { const struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret; if (!ops) return -ENOENT; ret = __add_metainfo(ops, ife, metaid, metaval, len, false, exists); if (ret) /*put back what find_ife_oplist took */ module_put(ops->owner); return ret; } static int use_all_metadata(struct tcf_ife_info *ife, bool exists) { struct tcf_meta_ops *o; int rc = 0; int installed = 0; read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { rc = add_metainfo_and_get_ops(o, ife, o->metaid, exists); if (rc == 0) installed += 1; } read_unlock(&ife_mod_lock); if (installed) return 0; else return -EINVAL; } static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife) { struct tcf_meta_info *e; struct nlattr *nest; unsigned char *b = skb_tail_pointer(skb); int total_encoded = 0; /*can only happen on decode */ if (list_empty(&ife->metalist)) return 0; nest = nla_nest_start_noflag(skb, TCA_IFE_METALST); if (!nest) goto out_nlmsg_trim; list_for_each_entry(e, &ife->metalist, metalist) { if (!e->ops->get(skb, e)) total_encoded += 1; } if (!total_encoded) goto out_nlmsg_trim; nla_nest_end(skb, nest); return 0; out_nlmsg_trim: nlmsg_trim(skb, b); return -1; } /* under ife->tcf_lock */ static void _tcf_ife_cleanup(struct tc_action *a) { struct tcf_ife_info *ife = to_ife(a); struct tcf_meta_info *e, *n; list_for_each_entry_safe(e, n, &ife->metalist, metalist) { list_del(&e->metalist); if (e->metaval) { if (e->ops->release) e->ops->release(e); else kfree(e->metaval); } module_put(e->ops->owner); kfree(e); } } static void tcf_ife_cleanup(struct tc_action *a) { struct tcf_ife_info *ife = to_ife(a); struct tcf_ife_params *p; spin_lock_bh(&ife->tcf_lock); _tcf_ife_cleanup(a); spin_unlock_bh(&ife->tcf_lock); p = rcu_dereference_protected(ife->params, 1); if (p) kfree_rcu(p, rcu); } static int load_metalist(struct nlattr **tb, bool rtnl_held) { int i; for (i = 1; i < max_metacnt; i++) { if (tb[i]) { void *val = nla_data(tb[i]); int len = nla_len(tb[i]); int rc; rc = load_metaops_and_vet(i, val, len, rtnl_held); if (rc != 0) return rc; } } return 0; } static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, bool exists, bool rtnl_held) { int len = 0; int rc = 0; int i = 0; void *val; for (i = 1; i < max_metacnt; i++) { if (tb[i]) { val = nla_data(tb[i]); len = nla_len(tb[i]); rc = add_metainfo(ife, i, val, len, exists); if (rc) return rc; } } return rc; } static int tcf_ife_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_ife_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_IFE_MAX + 1]; struct nlattr *tb2[IFE_META_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tcf_ife_params *p; struct tcf_ife_info *ife; u16 ife_type = ETH_P_IFE; struct tc_ife *parm; u8 *daddr = NULL; u8 *saddr = NULL; bool exists = false; int ret = 0; u32 index; int err; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "IFE requires attributes to be passed"); return -EINVAL; } err = nla_parse_nested_deprecated(tb, TCA_IFE_MAX, nla, ife_policy, NULL); if (err < 0) return err; if (!tb[TCA_IFE_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_IFE_PARMS]); /* IFE_DECODE is 0 and indicates the opposite of IFE_ENCODE because * they cannot run as the same time. Check on all other values which * are not supported right now. */ if (parm->flags & ~IFE_ENCODE) return -EINVAL; p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) return -ENOMEM; if (tb[TCA_IFE_METALST]) { err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, tb[TCA_IFE_METALST], NULL, NULL); if (err) { kfree(p); return err; } err = load_metalist(tb2, !(flags & TCA_ACT_FLAGS_NO_RTNL)); if (err) { kfree(p); return err; } } index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) { kfree(p); return err; } exists = err; if (exists && bind) { kfree(p); return ACT_P_BOUND; } if (!exists) { ret = tcf_idr_create(tn, index, est, a, &act_ife_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); kfree(p); return ret; } ret = ACT_P_CREATED; } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); kfree(p); return -EEXIST; } ife = to_ife(*a); if (ret == ACT_P_CREATED) INIT_LIST_HEAD(&ife->metalist); err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; p->flags = parm->flags; if (parm->flags & IFE_ENCODE) { if (tb[TCA_IFE_TYPE]) ife_type = nla_get_u16(tb[TCA_IFE_TYPE]); if (tb[TCA_IFE_DMAC]) daddr = nla_data(tb[TCA_IFE_DMAC]); if (tb[TCA_IFE_SMAC]) saddr = nla_data(tb[TCA_IFE_SMAC]); } if (parm->flags & IFE_ENCODE) { if (daddr) ether_addr_copy(p->eth_dst, daddr); else eth_zero_addr(p->eth_dst); if (saddr) ether_addr_copy(p->eth_src, saddr); else eth_zero_addr(p->eth_src); p->eth_type = ife_type; } if (tb[TCA_IFE_METALST]) { err = populate_metalist(ife, tb2, exists, !(flags & TCA_ACT_FLAGS_NO_RTNL)); if (err) goto metadata_parse_err; } else { /* if no passed metadata allow list or passed allow-all * then here we process by adding as many supported metadatum * as we can. You better have at least one else we are * going to bail out */ err = use_all_metadata(ife, exists); if (err) goto metadata_parse_err; } if (exists) spin_lock_bh(&ife->tcf_lock); /* protected by tcf_lock when modifying existing action */ goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); p = rcu_replace_pointer(ife->params, p, 1); if (exists) spin_unlock_bh(&ife->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (p) kfree_rcu(p, rcu); return ret; metadata_parse_err: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: kfree(p); tcf_idr_release(*a, bind); return err; } static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_ife_info *ife = to_ife(a); struct tcf_ife_params *p; struct tc_ife opt = { .index = ife->tcf_index, .refcnt = refcount_read(&ife->tcf_refcnt) - ref, .bindcnt = atomic_read(&ife->tcf_bindcnt) - bind, }; struct tcf_t t; spin_lock_bh(&ife->tcf_lock); opt.action = ife->tcf_action; p = rcu_dereference_protected(ife->params, lockdep_is_held(&ife->tcf_lock)); opt.flags = p->flags; if (nla_put(skb, TCA_IFE_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &ife->tcf_tm); if (nla_put_64bit(skb, TCA_IFE_TM, sizeof(t), &t, TCA_IFE_PAD)) goto nla_put_failure; if (!is_zero_ether_addr(p->eth_dst)) { if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, p->eth_dst)) goto nla_put_failure; } if (!is_zero_ether_addr(p->eth_src)) { if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, p->eth_src)) goto nla_put_failure; } if (nla_put(skb, TCA_IFE_TYPE, 2, &p->eth_type)) goto nla_put_failure; if (dump_metalist(skb, ife)) { /*ignore failure to dump metalist */ pr_info("Failed to dump metalist\n"); } spin_unlock_bh(&ife->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&ife->tcf_lock); nlmsg_trim(skb, b); return -1; } static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, u16 metaid, u16 mlen, void *mdata) { struct tcf_meta_info *e; /* XXX: use hash to speed up */ list_for_each_entry(e, &ife->metalist, metalist) { if (metaid == e->metaid) { if (e->ops) { /* We check for decode presence already */ return e->ops->decode(skb, mdata, mlen); } } } return -ENOENT; } static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; u8 *ifehdr_end; u8 *tlv_data; u16 metalen; bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); if (skb_at_tc_ingress(skb)) skb_push(skb, skb->dev->hard_header_len); tlv_data = ife_decode(skb, &metalen); if (unlikely(!tlv_data)) { qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } ifehdr_end = tlv_data + metalen; for (; tlv_data < ifehdr_end; tlv_data = ife_tlv_meta_next(tlv_data)) { u8 *curr_data; u16 mtype; u16 dlen; curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype, &dlen, NULL); if (!curr_data) { qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) { /* abuse overlimits to count when we receive metadata * but dont have an ops for it */ pr_info_ratelimited("Unknown metaid %d dlen %d\n", mtype, dlen); qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats)); } } if (WARN_ON(tlv_data != ifehdr_end)) { qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } skb->protocol = eth_type_trans(skb, skb->dev); skb_reset_network_header(skb); return action; } /*XXX: check if we can do this at install time instead of current * send data path **/ static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife) { struct tcf_meta_info *e, *n; int tot_run_sz = 0, run_sz = 0; list_for_each_entry_safe(e, n, &ife->metalist, metalist) { if (e->ops->check_presence) { run_sz = e->ops->check_presence(skb, e); tot_run_sz += run_sz; } } return tot_run_sz; } static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res, struct tcf_ife_params *p) { struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; struct ethhdr *oethh; /* outer ether header */ struct tcf_meta_info *e; /* OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA where ORIGDATA = original ethernet header ... */ u16 metalen = ife_get_sz(skb, ife); int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN; unsigned int skboff = 0; int new_len = skb->len + hdrm; bool exceed_mtu = false; void *ife_meta; int err = 0; if (!skb_at_tc_ingress(skb)) { if (new_len > skb->dev->mtu) exceed_mtu = true; } bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); if (!metalen) { /* no metadata to send */ /* abuse overlimits to count when we allow packet * with no metadata */ qstats_overlimit_inc(this_cpu_ptr(ife->common.cpu_qstats)); return action; } /* could be stupid policy setup or mtu config * so lets be conservative.. */ if ((action == TC_ACT_SHOT) || exceed_mtu) { qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } if (skb_at_tc_ingress(skb)) skb_push(skb, skb->dev->hard_header_len); ife_meta = ife_encode(skb, metalen); spin_lock(&ife->tcf_lock); /* XXX: we dont have a clever way of telling encode to * not repeat some of the computations that are done by * ops->presence_check... */ list_for_each_entry(e, &ife->metalist, metalist) { if (e->ops->encode) { err = e->ops->encode(skb, (void *)(ife_meta + skboff), e); } if (err < 0) { /* too corrupt to keep around if overwritten */ spin_unlock(&ife->tcf_lock); qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } skboff += err; } spin_unlock(&ife->tcf_lock); oethh = (struct ethhdr *)skb->data; if (!is_zero_ether_addr(p->eth_src)) ether_addr_copy(oethh->h_source, p->eth_src); if (!is_zero_ether_addr(p->eth_dst)) ether_addr_copy(oethh->h_dest, p->eth_dst); oethh->h_proto = htons(p->eth_type); if (skb_at_tc_ingress(skb)) skb_pull(skb, skb->dev->hard_header_len); return action; } TC_INDIRECT_SCOPE int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_ife_info *ife = to_ife(a); struct tcf_ife_params *p; int ret; p = rcu_dereference_bh(ife->params); if (p->flags & IFE_ENCODE) { ret = tcf_ife_encode(skb, a, res, p); return ret; } return tcf_ife_decode(skb, a, res); } static struct tc_action_ops act_ife_ops = { .kind = "ife", .id = TCA_ID_IFE, .owner = THIS_MODULE, .act = tcf_ife_act, .dump = tcf_ife_dump, .cleanup = tcf_ife_cleanup, .init = tcf_ife_init, .size = sizeof(struct tcf_ife_info), }; MODULE_ALIAS_NET_ACT("ife"); static __net_init int ife_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_ife_ops.net_id); return tc_action_net_init(net, tn, &act_ife_ops); } static void __net_exit ife_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_ife_ops.net_id); } static struct pernet_operations ife_net_ops = { .init = ife_init_net, .exit_batch = ife_exit_net, .id = &act_ife_ops.net_id, .size = sizeof(struct tc_action_net), }; static int __init ife_init_module(void) { return tcf_register_action(&act_ife_ops, &ife_net_ops); } static void __exit ife_cleanup_module(void) { tcf_unregister_action(&act_ife_ops, &ife_net_ops); } module_init(ife_init_module); module_exit(ife_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2015)"); MODULE_DESCRIPTION("Inter-FE LFB action"); MODULE_LICENSE("GPL"); |
| 2 2 2 2 2 2 2 2 2 4 4 4 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 Syncookies implementation for the Linux kernel * * Authors: * Glenn Griffin <ggriffin.kernel@gmail.com> * * Based on IPv4 implementation by Andi Kleen * linux/net/ipv4/syncookies.c */ #include <linux/tcp.h> #include <linux/random.h> #include <linux/siphash.h> #include <linux/kernel.h> #include <net/secure_seq.h> #include <net/ipv6.h> #include <net/tcp.h> #define COOKIEBITS 24 /* Upper bits store count */ #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1) static siphash_aligned_key_t syncookie6_secret[2]; /* RFC 2460, Section 8.3: * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..] * * Due to IPV6_MIN_MTU=1280 the lowest possible MSS is 1220, which allows * using higher values than ipv4 tcp syncookies. * The other values are chosen based on ethernet (1500 and 9k MTU), plus * one that accounts for common encap (PPPoe) overhead. Table must be sorted. */ static __u16 const msstab[] = { 1280 - 60, /* IPV6_MIN_MTU - 60 */ 1480 - 60, 1500 - 60, 9000 - 60, }; static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *daddr, __be16 sport, __be16 dport, u32 count, int c) { const struct { struct in6_addr saddr; struct in6_addr daddr; u32 count; __be16 sport; __be16 dport; } __aligned(SIPHASH_ALIGNMENT) combined = { .saddr = *saddr, .daddr = *daddr, .count = count, .sport = sport, .dport = dport }; net_get_random_once(syncookie6_secret, sizeof(syncookie6_secret)); return siphash(&combined, offsetofend(typeof(combined), dport), &syncookie6_secret[c]); } static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr, const struct in6_addr *daddr, __be16 sport, __be16 dport, __u32 sseq, __u32 data) { u32 count = tcp_cookie_time(); return (cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq + (count << COOKIEBITS) + ((cookie_hash(saddr, daddr, sport, dport, count, 1) + data) & COOKIEMASK)); } static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr, const struct in6_addr *daddr, __be16 sport, __be16 dport, __u32 sseq) { __u32 diff, count = tcp_cookie_time(); cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq; diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS); if (diff >= MAX_SYNCOOKIE_AGE) return (__u32)-1; return (cookie - cookie_hash(saddr, daddr, sport, dport, count - diff, 1)) & COOKIEMASK; } u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, const struct tcphdr *th, __u16 *mssp) { int mssind; const __u16 mss = *mssp; for (mssind = ARRAY_SIZE(msstab) - 1; mssind ; mssind--) if (mss >= msstab[mssind]) break; *mssp = msstab[mssind]; return secure_tcp_syn_cookie(&iph->saddr, &iph->daddr, th->source, th->dest, ntohl(th->seq), mssind); } EXPORT_SYMBOL_GPL(__cookie_v6_init_sequence); __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mssp) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); return __cookie_v6_init_sequence(iph, th, mssp); } int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th) { __u32 cookie = ntohl(th->ack_seq) - 1; __u32 seq = ntohl(th->seq) - 1; __u32 mssind; mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr, th->source, th->dest, seq); return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0; } EXPORT_SYMBOL_GPL(__cookie_v6_check); static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk, struct sk_buff *skb) { struct tcp_options_received tcp_opt; u32 tsoff = 0; int mss; if (tcp_synq_no_recent_overflow(sk)) goto out; mss = __cookie_v6_check(ipv6_hdr(skb), tcp_hdr(skb)); if (!mss) { __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED); goto out; } __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESRECV); /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); tcp_parse_options(net, skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { tsoff = secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32); tcp_opt.rcv_tsecr -= tsoff; } if (!cookie_timestamp_decode(net, &tcp_opt)) goto out; return cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb, &tcp_opt, mss, tsoff); out: return ERR_PTR(-EINVAL); } struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct inet_request_sock *ireq; struct net *net = sock_net(sk); struct request_sock *req; struct dst_entry *dst; struct sock *ret = sk; __u8 rcv_wscale; int full_space; SKB_DR(reason); if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) || !th->ack || th->rst) goto out; if (cookie_bpf_ok(skb)) { req = cookie_bpf_check(sk, skb); } else { req = cookie_tcp_check(net, sk, skb); if (IS_ERR(req)) goto out; } if (!req) { SKB_DR_SET(reason, NO_SOCKET); goto out_drop; } ireq = inet_rsk(req); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; if (security_inet_conn_request(sk, skb, req)) { SKB_DR_SET(reason, SECURITY_HOOK); goto out_free; } if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { refcount_inc(&skb->users); ireq->pktopts = skb; } /* So that link locals have meaning */ if (!sk->sk_bound_dev_if && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq->ir_iif = tcp_v6_iif(skb); tcp_ao_syncookie(sk, skb, req, AF_INET6); /* * We need to lookup the dst_entry to get the correct window size. * This is taken from tcp_v6_syn_recv_sock. Somebody please enlighten * me if there is a preferred way. */ { struct in6_addr *final_p, final; struct flowi6 fl6; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; fl6.daddr = ireq->ir_v6_rmt_addr; final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); fl6.saddr = ireq->ir_v6_loc_addr; fl6.flowi6_oif = ireq->ir_iif; fl6.flowi6_mark = ireq->ir_mark; fl6.fl6_dport = ireq->ir_rmt_port; fl6.fl6_sport = inet_sk(sk)->inet_sport; fl6.flowi6_uid = sk->sk_uid; security_req_classify_flow(req, flowi6_to_flowi_common(&fl6)); dst = ip6_dst_lookup_flow(net, sk, &fl6, final_p); if (IS_ERR(dst)) { SKB_DR_SET(reason, IP_OUTNOROUTES); goto out_free; } } req->rsk_window_clamp = READ_ONCE(tp->window_clamp) ? :dst_metric(dst, RTAX_WINDOW); /* limit the window selection if the user enforce a smaller rx buffer */ full_space = tcp_full_space(sk); if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) req->rsk_window_clamp = full_space; tcp_select_initial_window(sk, full_space, req->mss, &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); /* req->syncookie is set true only if ACK is validated * by BPF kfunc, then, rcv_wscale is already configured. */ if (!req->syncookie) ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok &= cookie_ecn_ok(net, dst); ret = tcp_get_cookie_sock(sk, skb, req, dst); if (!ret) { SKB_DR_SET(reason, NO_SOCKET); goto out_drop; } out: return ret; out_free: reqsk_free(req); out_drop: sk_skb_reason_drop(sk, skb, reason); return NULL; } |
| 1 32 181 180 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* SCTP kernel Implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (C) 1999-2001 Cisco, Motorola * * This file is part of the SCTP kernel implementation * * These are the definitions needed for the command object. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Ardelle Fan <ardelle.fan@intel.com> * Sridhar Samudrala <sri@us.ibm.com> */ #ifndef __net_sctp_command_h__ #define __net_sctp_command_h__ #include <net/sctp/constants.h> #include <net/sctp/structs.h> enum sctp_verb { SCTP_CMD_NOP = 0, /* Do nothing. */ SCTP_CMD_NEW_ASOC, /* Register a new association. */ SCTP_CMD_DELETE_TCB, /* Delete the current association. */ SCTP_CMD_NEW_STATE, /* Enter a new state. */ SCTP_CMD_REPORT_TSN, /* Record the arrival of a TSN. */ SCTP_CMD_GEN_SACK, /* Send a Selective ACK (maybe). */ SCTP_CMD_PROCESS_SACK, /* Process an inbound SACK. */ SCTP_CMD_GEN_INIT_ACK, /* Generate an INIT ACK chunk. */ SCTP_CMD_PEER_INIT, /* Process a INIT from the peer. */ SCTP_CMD_GEN_COOKIE_ECHO, /* Generate a COOKIE ECHO chunk. */ SCTP_CMD_CHUNK_ULP, /* Send a chunk to the sockets layer. */ SCTP_CMD_EVENT_ULP, /* Send a notification to the sockets layer. */ SCTP_CMD_REPLY, /* Send a chunk to our peer. */ SCTP_CMD_SEND_PKT, /* Send a full packet to our peer. */ SCTP_CMD_RETRAN, /* Mark a transport for retransmission. */ SCTP_CMD_ECN_CE, /* Do delayed CE processing. */ SCTP_CMD_ECN_ECNE, /* Do delayed ECNE processing. */ SCTP_CMD_ECN_CWR, /* Do delayed CWR processing. */ SCTP_CMD_TIMER_START, /* Start a timer. */ SCTP_CMD_TIMER_START_ONCE, /* Start a timer once */ SCTP_CMD_TIMER_RESTART, /* Restart a timer. */ SCTP_CMD_TIMER_STOP, /* Stop a timer. */ SCTP_CMD_INIT_CHOOSE_TRANSPORT, /* Choose transport for an INIT. */ SCTP_CMD_INIT_COUNTER_RESET, /* Reset init counter. */ SCTP_CMD_INIT_COUNTER_INC, /* Increment init counter. */ SCTP_CMD_INIT_RESTART, /* High level, do init timer work. */ SCTP_CMD_COOKIEECHO_RESTART, /* High level, do cookie-echo timer work. */ SCTP_CMD_INIT_FAILED, /* High level, do init failure work. */ SCTP_CMD_REPORT_DUP, /* Report a duplicate TSN. */ SCTP_CMD_STRIKE, /* Mark a strike against a transport. */ SCTP_CMD_HB_TIMERS_START, /* Start the heartbeat timers. */ SCTP_CMD_HB_TIMER_UPDATE, /* Update a heartbeat timers. */ SCTP_CMD_HB_TIMERS_STOP, /* Stop the heartbeat timers. */ SCTP_CMD_PROBE_TIMER_UPDATE, /* Update a probe timer. */ SCTP_CMD_TRANSPORT_HB_SENT, /* Reset the status of a transport. */ SCTP_CMD_TRANSPORT_IDLE, /* Do manipulations on idle transport */ SCTP_CMD_TRANSPORT_ON, /* Mark the transport as active. */ SCTP_CMD_REPORT_ERROR, /* Pass this error back out of the sm. */ SCTP_CMD_REPORT_BAD_TAG, /* Verification tags didn't match. */ SCTP_CMD_PROCESS_CTSN, /* Sideeffect from shutdown. */ SCTP_CMD_ASSOC_FAILED, /* Handle association failure. */ SCTP_CMD_DISCARD_PACKET, /* Discard the whole packet. */ SCTP_CMD_GEN_SHUTDOWN, /* Generate a SHUTDOWN chunk. */ SCTP_CMD_PURGE_OUTQUEUE, /* Purge all data waiting to be sent. */ SCTP_CMD_SETUP_T2, /* Hi-level, setup T2-shutdown parms. */ SCTP_CMD_RTO_PENDING, /* Set transport's rto_pending. */ SCTP_CMD_PART_DELIVER, /* Partial data delivery considerations. */ SCTP_CMD_RENEGE, /* Renege data on an association. */ SCTP_CMD_SETUP_T4, /* ADDIP, setup T4 RTO timer parms. */ SCTP_CMD_PROCESS_OPERR, /* Process an ERROR chunk. */ SCTP_CMD_REPORT_FWDTSN, /* Report new cumulative TSN Ack. */ SCTP_CMD_PROCESS_FWDTSN, /* Skips were reported, so process further. */ SCTP_CMD_CLEAR_INIT_TAG, /* Clears association peer's inittag. */ SCTP_CMD_DEL_NON_PRIMARY, /* Removes non-primary peer transports. */ SCTP_CMD_T3_RTX_TIMERS_STOP, /* Stops T3-rtx pending timers */ SCTP_CMD_FORCE_PRIM_RETRAN, /* Forces retrans. over primary path. */ SCTP_CMD_SET_SK_ERR, /* Set sk_err */ SCTP_CMD_ASSOC_CHANGE, /* generate and send assoc_change event */ SCTP_CMD_ADAPTATION_IND, /* generate and send adaptation event */ SCTP_CMD_PEER_NO_AUTH, /* generate and send authentication event */ SCTP_CMD_ASSOC_SHKEY, /* generate the association shared keys */ SCTP_CMD_T1_RETRAN, /* Mark for retransmission after T1 timeout */ SCTP_CMD_UPDATE_INITTAG, /* Update peer inittag */ SCTP_CMD_SEND_MSG, /* Send the whole use message */ SCTP_CMD_PURGE_ASCONF_QUEUE, /* Purge all asconf queues.*/ SCTP_CMD_SET_ASOC, /* Restore association context */ SCTP_CMD_LAST }; /* How many commands can you put in an struct sctp_cmd_seq? * This is a rather arbitrary number, ideally derived from a careful * analysis of the state functions, but in reality just taken from * thin air in the hopes othat we don't trigger a kernel panic. */ #define SCTP_MAX_NUM_COMMANDS 20 union sctp_arg { void *zero_all; /* Set to NULL to clear the entire union */ __s32 i32; __u32 u32; __be32 be32; __u16 u16; __u8 u8; int error; __be16 err; enum sctp_state state; enum sctp_event_timeout to; struct sctp_chunk *chunk; struct sctp_association *asoc; struct sctp_transport *transport; struct sctp_bind_addr *bp; struct sctp_init_chunk *init; struct sctp_ulpevent *ulpevent; struct sctp_packet *packet; struct sctp_sackhdr *sackh; struct sctp_datamsg *msg; }; /* We are simulating ML type constructors here. * * SCTP_ARG_CONSTRUCTOR(NAME, TYPE, ELT) builds a function called * SCTP_NAME() which takes an argument of type TYPE and returns an * union sctp_arg. It does this by inserting the sole argument into * the ELT union element of a local union sctp_arg. * * E.g., SCTP_ARG_CONSTRUCTOR(I32, __s32, i32) builds SCTP_I32(arg), * which takes an __s32 and returns a union sctp_arg containing the * __s32. So, after foo = SCTP_I32(arg), foo.i32 == arg. */ #define SCTP_ARG_CONSTRUCTOR(name, type, elt) \ static inline union sctp_arg \ SCTP_## name (type arg) \ { union sctp_arg retval;\ retval.zero_all = NULL;\ retval.elt = arg;\ return retval;\ } SCTP_ARG_CONSTRUCTOR(I32, __s32, i32) SCTP_ARG_CONSTRUCTOR(U32, __u32, u32) SCTP_ARG_CONSTRUCTOR(BE32, __be32, be32) SCTP_ARG_CONSTRUCTOR(U16, __u16, u16) SCTP_ARG_CONSTRUCTOR(U8, __u8, u8) SCTP_ARG_CONSTRUCTOR(ERROR, int, error) SCTP_ARG_CONSTRUCTOR(PERR, __be16, err) /* protocol error */ SCTP_ARG_CONSTRUCTOR(STATE, enum sctp_state, state) SCTP_ARG_CONSTRUCTOR(TO, enum sctp_event_timeout, to) SCTP_ARG_CONSTRUCTOR(CHUNK, struct sctp_chunk *, chunk) SCTP_ARG_CONSTRUCTOR(ASOC, struct sctp_association *, asoc) SCTP_ARG_CONSTRUCTOR(TRANSPORT, struct sctp_transport *, transport) SCTP_ARG_CONSTRUCTOR(BA, struct sctp_bind_addr *, bp) SCTP_ARG_CONSTRUCTOR(PEER_INIT, struct sctp_init_chunk *, init) SCTP_ARG_CONSTRUCTOR(ULPEVENT, struct sctp_ulpevent *, ulpevent) SCTP_ARG_CONSTRUCTOR(PACKET, struct sctp_packet *, packet) SCTP_ARG_CONSTRUCTOR(SACKH, struct sctp_sackhdr *, sackh) SCTP_ARG_CONSTRUCTOR(DATAMSG, struct sctp_datamsg *, msg) static inline union sctp_arg SCTP_FORCE(void) { return SCTP_I32(1); } static inline union sctp_arg SCTP_NOFORCE(void) { return SCTP_I32(0); } static inline union sctp_arg SCTP_NULL(void) { union sctp_arg retval; retval.zero_all = NULL; return retval; } struct sctp_cmd { union sctp_arg obj; enum sctp_verb verb; }; struct sctp_cmd_seq { struct sctp_cmd cmds[SCTP_MAX_NUM_COMMANDS]; struct sctp_cmd *last_used_slot; struct sctp_cmd *next_cmd; }; /* Initialize a block of memory as a command sequence. * Return 0 if the initialization fails. */ static inline int sctp_init_cmd_seq(struct sctp_cmd_seq *seq) { /* cmds[] is filled backwards to simplify the overflow BUG() check */ seq->last_used_slot = seq->cmds + SCTP_MAX_NUM_COMMANDS; seq->next_cmd = seq->last_used_slot; return 1; /* We always succeed. */ } /* Add a command to an struct sctp_cmd_seq. * * Use the SCTP_* constructors defined by SCTP_ARG_CONSTRUCTOR() above * to wrap data which goes in the obj argument. */ static inline void sctp_add_cmd_sf(struct sctp_cmd_seq *seq, enum sctp_verb verb, union sctp_arg obj) { struct sctp_cmd *cmd = seq->last_used_slot - 1; BUG_ON(cmd < seq->cmds); cmd->verb = verb; cmd->obj = obj; seq->last_used_slot = cmd; } /* Return the next command structure in an sctp_cmd_seq. * Return NULL at the end of the sequence. */ static inline struct sctp_cmd *sctp_next_cmd(struct sctp_cmd_seq *seq) { if (seq->next_cmd <= seq->last_used_slot) return NULL; return --seq->next_cmd; } #endif /* __net_sctp_command_h__ */ |
| 4 2 2 3 3 4 2 2 4 4 9 6 6 6 6 6 1 5 5 84 88 88 2 5 87 82 82 13 5 3 1 5 6 85 22 65 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 1 5 5 9 9 9 9 9 2 2 13 13 13 13 13 13 1 1 1 1 13 13 1 13 8 7 8 1 7 5 6 4 13 13 13 12 1 7 12 13 1 13 9 9 9 9 9 9 9 7 7 9 9 10 8 8 8 2 7 8 8 8 8 8 8 8 2 2 2 2 2 7 1 1 8 171 171 1 157 159 8 2 3 3 3 3 30 64 39 91 12 12 89 91 91 19 72 42 13 12 12 12 90 9 8 68 1 11 11 91 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (C) 2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ #ifndef _IP_SET_HASH_GEN_H #define _IP_SET_HASH_GEN_H #include <linux/rcupdate.h> #include <linux/rcupdate_wait.h> #include <linux/jhash.h> #include <linux/types.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/ipset/ip_set.h> #define __ipset_dereference(p) \ rcu_dereference_protected(p, 1) #define ipset_dereference_nfnl(p) \ rcu_dereference_protected(p, \ lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) #define ipset_dereference_set(p, set) \ rcu_dereference_protected(p, \ lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ lockdep_is_held(&(set)->lock)) #define ipset_dereference_bh_nfnl(p) \ rcu_dereference_bh_check(p, \ lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) /* Hashing which uses arrays to resolve clashing. The hash table is resized * (doubled) when searching becomes too long. * Internally jhash is used with the assumption that the size of the * stored data is a multiple of sizeof(u32). * * Readers and resizing * * Resizing can be triggered by userspace command only, and those * are serialized by the nfnl mutex. During resizing the set is * read-locked, so the only possible concurrent operations are * the kernel side readers. Those must be protected by proper RCU locking. */ /* Number of elements to store in an initial array block */ #define AHASH_INIT_SIZE 2 /* Max number of elements to store in an array block */ #define AHASH_MAX_SIZE (6 * AHASH_INIT_SIZE) /* Max muber of elements in the array block when tuned */ #define AHASH_MAX_TUNED 64 #define AHASH_MAX(h) ((h)->bucketsize) /* A hash bucket */ struct hbucket { struct rcu_head rcu; /* for call_rcu */ /* Which positions are used in the array */ DECLARE_BITMAP(used, AHASH_MAX_TUNED); u8 size; /* size of the array */ u8 pos; /* position of the first free entry */ unsigned char value[] /* the array of the values */ __aligned(__alignof__(u64)); }; /* Region size for locking == 2^HTABLE_REGION_BITS */ #define HTABLE_REGION_BITS 10 #define ahash_numof_locks(htable_bits) \ ((htable_bits) < HTABLE_REGION_BITS ? 1 \ : jhash_size((htable_bits) - HTABLE_REGION_BITS)) #define ahash_sizeof_regions(htable_bits) \ (ahash_numof_locks(htable_bits) * sizeof(struct ip_set_region)) #define ahash_region(n, htable_bits) \ ((n) % ahash_numof_locks(htable_bits)) #define ahash_bucket_start(h, htable_bits) \ ((htable_bits) < HTABLE_REGION_BITS ? 0 \ : (h) * jhash_size(HTABLE_REGION_BITS)) #define ahash_bucket_end(h, htable_bits) \ ((htable_bits) < HTABLE_REGION_BITS ? jhash_size(htable_bits) \ : ((h) + 1) * jhash_size(HTABLE_REGION_BITS)) struct htable_gc { struct delayed_work dwork; struct ip_set *set; /* Set the gc belongs to */ u32 region; /* Last gc run position */ }; /* The hash table: the table size stored here in order to make resizing easy */ struct htable { atomic_t ref; /* References for resizing */ atomic_t uref; /* References for dumping and gc */ u8 htable_bits; /* size of hash table == 2^htable_bits */ u32 maxelem; /* Maxelem per region */ struct ip_set_region *hregion; /* Region locks and ext sizes */ struct hbucket __rcu *bucket[]; /* hashtable buckets */ }; #define hbucket(h, i) ((h)->bucket[i]) #define ext_size(n, dsize) \ (sizeof(struct hbucket) + (n) * (dsize)) #ifndef IPSET_NET_COUNT #define IPSET_NET_COUNT 1 #endif /* Book-keeping of the prefixes added to the set */ struct net_prefixes { u32 nets[IPSET_NET_COUNT]; /* number of elements for this cidr */ u8 cidr[IPSET_NET_COUNT]; /* the cidr value */ }; /* Compute the hash table size */ static size_t htable_size(u8 hbits) { size_t hsize; /* We must fit both into u32 in jhash and INT_MAX in kvmalloc_node() */ if (hbits > 31) return 0; hsize = jhash_size(hbits); if ((INT_MAX - sizeof(struct htable)) / sizeof(struct hbucket *) < hsize) return 0; return hsize * sizeof(struct hbucket *) + sizeof(struct htable); } #ifdef IP_SET_HASH_WITH_NETS #if IPSET_NET_COUNT > 1 #define __CIDR(cidr, i) (cidr[i]) #else #define __CIDR(cidr, i) (cidr) #endif /* cidr + 1 is stored in net_prefixes to support /0 */ #define NCIDR_PUT(cidr) ((cidr) + 1) #define NCIDR_GET(cidr) ((cidr) - 1) #ifdef IP_SET_HASH_WITH_NETS_PACKED /* When cidr is packed with nomatch, cidr - 1 is stored in the data entry */ #define DCIDR_PUT(cidr) ((cidr) - 1) #define DCIDR_GET(cidr, i) (__CIDR(cidr, i) + 1) #else #define DCIDR_PUT(cidr) (cidr) #define DCIDR_GET(cidr, i) __CIDR(cidr, i) #endif #define INIT_CIDR(cidr, host_mask) \ DCIDR_PUT(((cidr) ? NCIDR_GET(cidr) : host_mask)) #ifdef IP_SET_HASH_WITH_NET0 /* cidr from 0 to HOST_MASK value and c = cidr + 1 */ #define NLEN (HOST_MASK + 1) #define CIDR_POS(c) ((c) - 1) #else /* cidr from 1 to HOST_MASK value and c = cidr + 1 */ #define NLEN HOST_MASK #define CIDR_POS(c) ((c) - 2) #endif #else #define NLEN 0 #endif /* IP_SET_HASH_WITH_NETS */ #define SET_ELEM_EXPIRED(set, d) \ (SET_WITH_TIMEOUT(set) && \ ip_set_timeout_expired(ext_timeout(d, set))) #if defined(IP_SET_HASH_WITH_NETMASK) || defined(IP_SET_HASH_WITH_BITMASK) static const union nf_inet_addr onesmask = { .all[0] = 0xffffffff, .all[1] = 0xffffffff, .all[2] = 0xffffffff, .all[3] = 0xffffffff }; static const union nf_inet_addr zeromask = {}; #endif #endif /* _IP_SET_HASH_GEN_H */ #ifndef MTYPE #error "MTYPE is not defined!" #endif #ifndef HTYPE #error "HTYPE is not defined!" #endif #ifndef HOST_MASK #error "HOST_MASK is not defined!" #endif /* Family dependent templates */ #undef ahash_data #undef mtype_data_equal #undef mtype_do_data_match #undef mtype_data_set_flags #undef mtype_data_reset_elem #undef mtype_data_reset_flags #undef mtype_data_netmask #undef mtype_data_list #undef mtype_data_next #undef mtype_elem #undef mtype_ahash_destroy #undef mtype_ext_cleanup #undef mtype_add_cidr #undef mtype_del_cidr #undef mtype_ahash_memsize #undef mtype_flush #undef mtype_destroy #undef mtype_same_set #undef mtype_kadt #undef mtype_uadt #undef mtype_add #undef mtype_del #undef mtype_test_cidrs #undef mtype_test #undef mtype_uref #undef mtype_resize #undef mtype_ext_size #undef mtype_resize_ad #undef mtype_head #undef mtype_list #undef mtype_gc_do #undef mtype_gc #undef mtype_gc_init #undef mtype_cancel_gc #undef mtype_variant #undef mtype_data_match #undef htype #undef HKEY #define mtype_data_equal IPSET_TOKEN(MTYPE, _data_equal) #ifdef IP_SET_HASH_WITH_NETS #define mtype_do_data_match IPSET_TOKEN(MTYPE, _do_data_match) #else #define mtype_do_data_match(d) 1 #endif #define mtype_data_set_flags IPSET_TOKEN(MTYPE, _data_set_flags) #define mtype_data_reset_elem IPSET_TOKEN(MTYPE, _data_reset_elem) #define mtype_data_reset_flags IPSET_TOKEN(MTYPE, _data_reset_flags) #define mtype_data_netmask IPSET_TOKEN(MTYPE, _data_netmask) #define mtype_data_list IPSET_TOKEN(MTYPE, _data_list) #define mtype_data_next IPSET_TOKEN(MTYPE, _data_next) #define mtype_elem IPSET_TOKEN(MTYPE, _elem) #define mtype_ahash_destroy IPSET_TOKEN(MTYPE, _ahash_destroy) #define mtype_ext_cleanup IPSET_TOKEN(MTYPE, _ext_cleanup) #define mtype_add_cidr IPSET_TOKEN(MTYPE, _add_cidr) #define mtype_del_cidr IPSET_TOKEN(MTYPE, _del_cidr) #define mtype_ahash_memsize IPSET_TOKEN(MTYPE, _ahash_memsize) #define mtype_flush IPSET_TOKEN(MTYPE, _flush) #define mtype_destroy IPSET_TOKEN(MTYPE, _destroy) #define mtype_same_set IPSET_TOKEN(MTYPE, _same_set) #define mtype_kadt IPSET_TOKEN(MTYPE, _kadt) #define mtype_uadt IPSET_TOKEN(MTYPE, _uadt) #define mtype_add IPSET_TOKEN(MTYPE, _add) #define mtype_del IPSET_TOKEN(MTYPE, _del) #define mtype_test_cidrs IPSET_TOKEN(MTYPE, _test_cidrs) #define mtype_test IPSET_TOKEN(MTYPE, _test) #define mtype_uref IPSET_TOKEN(MTYPE, _uref) #define mtype_resize IPSET_TOKEN(MTYPE, _resize) #define mtype_ext_size IPSET_TOKEN(MTYPE, _ext_size) #define mtype_resize_ad IPSET_TOKEN(MTYPE, _resize_ad) #define mtype_head IPSET_TOKEN(MTYPE, _head) #define mtype_list IPSET_TOKEN(MTYPE, _list) #define mtype_gc_do IPSET_TOKEN(MTYPE, _gc_do) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) #define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype_variant IPSET_TOKEN(MTYPE, _variant) #define mtype_data_match IPSET_TOKEN(MTYPE, _data_match) #ifndef HKEY_DATALEN #define HKEY_DATALEN sizeof(struct mtype_elem) #endif #define htype MTYPE #define HKEY(data, initval, htable_bits) \ ({ \ const u32 *__k = (const u32 *)data; \ u32 __l = HKEY_DATALEN / sizeof(u32); \ \ BUILD_BUG_ON(HKEY_DATALEN % sizeof(u32) != 0); \ \ jhash2(__k, __l, initval) & jhash_mask(htable_bits); \ }) /* The generic hash structure */ struct htype { struct htable __rcu *table; /* the hash table */ struct htable_gc gc; /* gc workqueue */ u32 maxelem; /* max elements in the hash */ u32 initval; /* random jhash init value */ #ifdef IP_SET_HASH_WITH_MARKMASK u32 markmask; /* markmask value for mark mask to store */ #endif u8 bucketsize; /* max elements in an array block */ #if defined(IP_SET_HASH_WITH_NETMASK) || defined(IP_SET_HASH_WITH_BITMASK) u8 netmask; /* netmask value for subnets to store */ union nf_inet_addr bitmask; /* stores bitmask */ #endif struct list_head ad; /* Resize add|del backlist */ struct mtype_elem next; /* temporary storage for uadd */ #ifdef IP_SET_HASH_WITH_NETS struct net_prefixes nets[NLEN]; /* book-keeping of prefixes */ #endif }; /* ADD|DEL entries saved during resize */ struct mtype_resize_ad { struct list_head list; enum ipset_adt ad; /* ADD|DEL element */ struct mtype_elem d; /* Element value */ struct ip_set_ext ext; /* Extensions for ADD */ struct ip_set_ext mext; /* Target extensions for ADD */ u32 flags; /* Flags for ADD */ }; #ifdef IP_SET_HASH_WITH_NETS /* Network cidr size book keeping when the hash stores different * sized networks. cidr == real cidr + 1 to support /0. */ static void mtype_add_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { int i, j; spin_lock_bh(&set->lock); /* Add in increasing prefix order, so larger cidr first */ for (i = 0, j = -1; i < NLEN && h->nets[i].cidr[n]; i++) { if (j != -1) { continue; } else if (h->nets[i].cidr[n] < cidr) { j = i; } else if (h->nets[i].cidr[n] == cidr) { h->nets[CIDR_POS(cidr)].nets[n]++; goto unlock; } } if (j != -1) { for (; i > j; i--) h->nets[i].cidr[n] = h->nets[i - 1].cidr[n]; } h->nets[i].cidr[n] = cidr; h->nets[CIDR_POS(cidr)].nets[n] = 1; unlock: spin_unlock_bh(&set->lock); } static void mtype_del_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { u8 i, j, net_end = NLEN - 1; spin_lock_bh(&set->lock); for (i = 0; i < NLEN; i++) { if (h->nets[i].cidr[n] != cidr) continue; h->nets[CIDR_POS(cidr)].nets[n]--; if (h->nets[CIDR_POS(cidr)].nets[n] > 0) goto unlock; for (j = i; j < net_end && h->nets[j].cidr[n]; j++) h->nets[j].cidr[n] = h->nets[j + 1].cidr[n]; h->nets[j].cidr[n] = 0; goto unlock; } unlock: spin_unlock_bh(&set->lock); } #endif /* Calculate the actual memory size of the set data */ static size_t mtype_ahash_memsize(const struct htype *h, const struct htable *t) { return sizeof(*h) + sizeof(*t) + ahash_sizeof_regions(t->htable_bits); } /* Get the ith element from the array block n */ #define ahash_data(n, i, dsize) \ ((struct mtype_elem *)((n)->value + ((i) * (dsize)))) static void mtype_ext_cleanup(struct ip_set *set, struct hbucket *n) { int i; for (i = 0; i < n->pos; i++) if (test_bit(i, n->used)) ip_set_ext_destroy(set, ahash_data(n, i, set->dsize)); } /* Flush a hash type of set: destroy all elements */ static void mtype_flush(struct ip_set *set) { struct htype *h = set->data; struct htable *t; struct hbucket *n; u32 r, i; t = ipset_dereference_nfnl(h->table); for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) { spin_lock_bh(&t->hregion[r].lock); for (i = ahash_bucket_start(r, t->htable_bits); i < ahash_bucket_end(r, t->htable_bits); i++) { n = __ipset_dereference(hbucket(t, i)); if (!n) continue; if (set->extensions & IPSET_EXT_DESTROY) mtype_ext_cleanup(set, n); /* FIXME: use slab cache */ rcu_assign_pointer(hbucket(t, i), NULL); kfree_rcu(n, rcu); } t->hregion[r].ext_size = 0; t->hregion[r].elements = 0; spin_unlock_bh(&t->hregion[r].lock); } #ifdef IP_SET_HASH_WITH_NETS memset(h->nets, 0, sizeof(h->nets)); #endif } /* Destroy the hashtable part of the set */ static void mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) { struct hbucket *n; u32 i; for (i = 0; i < jhash_size(t->htable_bits); i++) { n = (__force struct hbucket *)hbucket(t, i); if (!n) continue; if (set->extensions & IPSET_EXT_DESTROY && ext_destroy) mtype_ext_cleanup(set, n); /* FIXME: use slab cache */ kfree(n); } ip_set_free(t->hregion); ip_set_free(t); } /* Destroy a hash type of set */ static void mtype_destroy(struct ip_set *set) { struct htype *h = set->data; struct list_head *l, *lt; mtype_ahash_destroy(set, (__force struct htable *)h->table, true); list_for_each_safe(l, lt, &h->ad) { list_del(l); kfree(l); } kfree(h); set->data = NULL; } static bool mtype_same_set(const struct ip_set *a, const struct ip_set *b) { const struct htype *x = a->data; const struct htype *y = b->data; /* Resizing changes htable_bits, so we ignore it */ return x->maxelem == y->maxelem && a->timeout == b->timeout && #if defined(IP_SET_HASH_WITH_NETMASK) || defined(IP_SET_HASH_WITH_BITMASK) nf_inet_addr_cmp(&x->bitmask, &y->bitmask) && #endif #ifdef IP_SET_HASH_WITH_MARKMASK x->markmask == y->markmask && #endif a->extensions == b->extensions; } static void mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) { struct hbucket *n, *tmp; struct mtype_elem *data; u32 i, j, d; size_t dsize = set->dsize; #ifdef IP_SET_HASH_WITH_NETS u8 k; #endif u8 htable_bits = t->htable_bits; spin_lock_bh(&t->hregion[r].lock); for (i = ahash_bucket_start(r, htable_bits); i < ahash_bucket_end(r, htable_bits); i++) { n = __ipset_dereference(hbucket(t, i)); if (!n) continue; for (j = 0, d = 0; j < n->pos; j++) { if (!test_bit(j, n->used)) { d++; continue; } data = ahash_data(n, j, dsize); if (!ip_set_timeout_expired(ext_timeout(data, set))) continue; pr_debug("expired %u/%u\n", i, j); clear_bit(j, n->used); smp_mb__after_atomic(); #ifdef IP_SET_HASH_WITH_NETS for (k = 0; k < IPSET_NET_COUNT; k++) mtype_del_cidr(set, h, NCIDR_PUT(DCIDR_GET(data->cidr, k)), k); #endif t->hregion[r].elements--; ip_set_ext_destroy(set, data); d++; } if (d >= AHASH_INIT_SIZE) { if (d >= n->size) { t->hregion[r].ext_size -= ext_size(n->size, dsize); rcu_assign_pointer(hbucket(t, i), NULL); kfree_rcu(n, rcu); continue; } tmp = kzalloc(sizeof(*tmp) + (n->size - AHASH_INIT_SIZE) * dsize, GFP_ATOMIC); if (!tmp) /* Still try to delete expired elements. */ continue; tmp->size = n->size - AHASH_INIT_SIZE; for (j = 0, d = 0; j < n->pos; j++) { if (!test_bit(j, n->used)) continue; data = ahash_data(n, j, dsize); memcpy(tmp->value + d * dsize, data, dsize); set_bit(d, tmp->used); d++; } tmp->pos = d; t->hregion[r].ext_size -= ext_size(AHASH_INIT_SIZE, dsize); rcu_assign_pointer(hbucket(t, i), tmp); kfree_rcu(n, rcu); } } spin_unlock_bh(&t->hregion[r].lock); } static void mtype_gc(struct work_struct *work) { struct htable_gc *gc; struct ip_set *set; struct htype *h; struct htable *t; u32 r, numof_locks; unsigned int next_run; gc = container_of(work, struct htable_gc, dwork.work); set = gc->set; h = set->data; spin_lock_bh(&set->lock); t = ipset_dereference_set(h->table, set); atomic_inc(&t->uref); numof_locks = ahash_numof_locks(t->htable_bits); r = gc->region++; if (r >= numof_locks) { r = gc->region = 0; } next_run = (IPSET_GC_PERIOD(set->timeout) * HZ) / numof_locks; if (next_run < HZ/10) next_run = HZ/10; spin_unlock_bh(&set->lock); mtype_gc_do(set, h, t, r); if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { pr_debug("Table destroy after resize by expire: %p\n", t); mtype_ahash_destroy(set, t, false); } queue_delayed_work(system_power_efficient_wq, &gc->dwork, next_run); } static void mtype_gc_init(struct htable_gc *gc) { INIT_DEFERRABLE_WORK(&gc->dwork, mtype_gc); queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ); } static void mtype_cancel_gc(struct ip_set *set) { struct htype *h = set->data; if (SET_WITH_TIMEOUT(set)) cancel_delayed_work_sync(&h->gc.dwork); } static int mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags); static int mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags); /* Resize a hash: create a new hash table with doubling the hashsize * and inserting the elements to it. Repeat until we succeed or * fail due to memory pressures. */ static int mtype_resize(struct ip_set *set, bool retried) { struct htype *h = set->data; struct htable *t, *orig; u8 htable_bits; size_t hsize, dsize = set->dsize; #ifdef IP_SET_HASH_WITH_NETS u8 flags; struct mtype_elem *tmp; #endif struct mtype_elem *data; struct mtype_elem *d; struct hbucket *n, *m; struct list_head *l, *lt; struct mtype_resize_ad *x; u32 i, j, r, nr, key; int ret; #ifdef IP_SET_HASH_WITH_NETS tmp = kmalloc(dsize, GFP_KERNEL); if (!tmp) return -ENOMEM; #endif orig = ipset_dereference_bh_nfnl(h->table); htable_bits = orig->htable_bits; retry: ret = 0; htable_bits++; if (!htable_bits) goto hbwarn; hsize = htable_size(htable_bits); if (!hsize) goto hbwarn; t = ip_set_alloc(hsize); if (!t) { ret = -ENOMEM; goto out; } t->hregion = ip_set_alloc(ahash_sizeof_regions(htable_bits)); if (!t->hregion) { ip_set_free(t); ret = -ENOMEM; goto out; } t->htable_bits = htable_bits; t->maxelem = h->maxelem / ahash_numof_locks(htable_bits); for (i = 0; i < ahash_numof_locks(htable_bits); i++) spin_lock_init(&t->hregion[i].lock); /* There can't be another parallel resizing, * but dumping, gc, kernel side add/del are possible */ orig = ipset_dereference_bh_nfnl(h->table); atomic_set(&orig->ref, 1); atomic_inc(&orig->uref); pr_debug("attempt to resize set %s from %u to %u, t %p\n", set->name, orig->htable_bits, htable_bits, orig); for (r = 0; r < ahash_numof_locks(orig->htable_bits); r++) { /* Expire may replace a hbucket with another one */ rcu_read_lock_bh(); for (i = ahash_bucket_start(r, orig->htable_bits); i < ahash_bucket_end(r, orig->htable_bits); i++) { n = __ipset_dereference(hbucket(orig, i)); if (!n) continue; for (j = 0; j < n->pos; j++) { if (!test_bit(j, n->used)) continue; data = ahash_data(n, j, dsize); if (SET_ELEM_EXPIRED(set, data)) continue; #ifdef IP_SET_HASH_WITH_NETS /* We have readers running parallel with us, * so the live data cannot be modified. */ flags = 0; memcpy(tmp, data, dsize); data = tmp; mtype_data_reset_flags(data, &flags); #endif key = HKEY(data, h->initval, htable_bits); m = __ipset_dereference(hbucket(t, key)); nr = ahash_region(key, htable_bits); if (!m) { m = kzalloc(sizeof(*m) + AHASH_INIT_SIZE * dsize, GFP_ATOMIC); if (!m) { ret = -ENOMEM; goto cleanup; } m->size = AHASH_INIT_SIZE; t->hregion[nr].ext_size += ext_size(AHASH_INIT_SIZE, dsize); RCU_INIT_POINTER(hbucket(t, key), m); } else if (m->pos >= m->size) { struct hbucket *ht; if (m->size >= AHASH_MAX(h)) { ret = -EAGAIN; } else { ht = kzalloc(sizeof(*ht) + (m->size + AHASH_INIT_SIZE) * dsize, GFP_ATOMIC); if (!ht) ret = -ENOMEM; } if (ret < 0) goto cleanup; memcpy(ht, m, sizeof(struct hbucket) + m->size * dsize); ht->size = m->size + AHASH_INIT_SIZE; t->hregion[nr].ext_size += ext_size(AHASH_INIT_SIZE, dsize); kfree(m); m = ht; RCU_INIT_POINTER(hbucket(t, key), ht); } d = ahash_data(m, m->pos, dsize); memcpy(d, data, dsize); set_bit(m->pos++, m->used); t->hregion[nr].elements++; #ifdef IP_SET_HASH_WITH_NETS mtype_data_reset_flags(d, &flags); #endif } } rcu_read_unlock_bh(); } /* There can't be any other writer. */ rcu_assign_pointer(h->table, t); /* Give time to other readers of the set */ synchronize_rcu(); pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name, orig->htable_bits, orig, t->htable_bits, t); /* Add/delete elements processed by the SET target during resize. * Kernel-side add cannot trigger a resize and userspace actions * are serialized by the mutex. */ list_for_each_safe(l, lt, &h->ad) { x = list_entry(l, struct mtype_resize_ad, list); if (x->ad == IPSET_ADD) { mtype_add(set, &x->d, &x->ext, &x->mext, x->flags); } else { mtype_del(set, &x->d, NULL, NULL, 0); } list_del(l); kfree(l); } /* If there's nobody else using the table, destroy it */ if (atomic_dec_and_test(&orig->uref)) { pr_debug("Table destroy by resize %p\n", orig); mtype_ahash_destroy(set, orig, false); } out: #ifdef IP_SET_HASH_WITH_NETS kfree(tmp); #endif return ret; cleanup: rcu_read_unlock_bh(); atomic_set(&orig->ref, 0); atomic_dec(&orig->uref); mtype_ahash_destroy(set, t, false); if (ret == -EAGAIN) goto retry; goto out; hbwarn: /* In case we have plenty of memory :-) */ pr_warn("Cannot increase the hashsize of set %s further\n", set->name); ret = -IPSET_ERR_HASH_FULL; goto out; } /* Get the current number of elements and ext_size in the set */ static void mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size) { struct htype *h = set->data; const struct htable *t; u32 i, j, r; struct hbucket *n; struct mtype_elem *data; t = rcu_dereference_bh(h->table); for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) { for (i = ahash_bucket_start(r, t->htable_bits); i < ahash_bucket_end(r, t->htable_bits); i++) { n = rcu_dereference_bh(hbucket(t, i)); if (!n) continue; for (j = 0; j < n->pos; j++) { if (!test_bit(j, n->used)) continue; data = ahash_data(n, j, set->dsize); if (!SET_ELEM_EXPIRED(set, data)) (*elements)++; } } *ext_size += t->hregion[r].ext_size; } } /* Add an element to a hash and update the internal counters when succeeded, * otherwise report the proper error code. */ static int mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) { struct htype *h = set->data; struct htable *t; const struct mtype_elem *d = value; struct mtype_elem *data; struct hbucket *n, *old = ERR_PTR(-ENOENT); int i, j = -1, ret; bool flag_exist = flags & IPSET_FLAG_EXIST; bool deleted = false, forceadd = false, reuse = false; u32 r, key, multi = 0, elements, maxelem; rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); key = HKEY(value, h->initval, t->htable_bits); r = ahash_region(key, t->htable_bits); atomic_inc(&t->uref); elements = t->hregion[r].elements; maxelem = t->maxelem; if (elements >= maxelem) { u32 e; if (SET_WITH_TIMEOUT(set)) { rcu_read_unlock_bh(); mtype_gc_do(set, h, t, r); rcu_read_lock_bh(); } maxelem = h->maxelem; elements = 0; for (e = 0; e < ahash_numof_locks(t->htable_bits); e++) elements += t->hregion[e].elements; if (elements >= maxelem && SET_WITH_FORCEADD(set)) forceadd = true; } rcu_read_unlock_bh(); spin_lock_bh(&t->hregion[r].lock); n = rcu_dereference_bh(hbucket(t, key)); if (!n) { if (forceadd || elements >= maxelem) goto set_full; old = NULL; n = kzalloc(sizeof(*n) + AHASH_INIT_SIZE * set->dsize, GFP_ATOMIC); if (!n) { ret = -ENOMEM; goto unlock; } n->size = AHASH_INIT_SIZE; t->hregion[r].ext_size += ext_size(AHASH_INIT_SIZE, set->dsize); goto copy_elem; } for (i = 0; i < n->pos; i++) { if (!test_bit(i, n->used)) { /* Reuse first deleted entry */ if (j == -1) { deleted = reuse = true; j = i; } continue; } data = ahash_data(n, i, set->dsize); if (mtype_data_equal(data, d, &multi)) { if (flag_exist || SET_ELEM_EXPIRED(set, data)) { /* Just the extensions could be overwritten */ j = i; goto overwrite_extensions; } ret = -IPSET_ERR_EXIST; goto unlock; } /* Reuse first timed out entry */ if (SET_ELEM_EXPIRED(set, data) && j == -1) { j = i; reuse = true; } } if (reuse || forceadd) { if (j == -1) j = 0; data = ahash_data(n, j, set->dsize); if (!deleted) { #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) mtype_del_cidr(set, h, NCIDR_PUT(DCIDR_GET(data->cidr, i)), i); #endif ip_set_ext_destroy(set, data); t->hregion[r].elements--; } goto copy_data; } if (elements >= maxelem) goto set_full; /* Create a new slot */ if (n->pos >= n->size) { #ifdef IP_SET_HASH_WITH_MULTI if (h->bucketsize >= AHASH_MAX_TUNED) goto set_full; else if (h->bucketsize <= multi) h->bucketsize += AHASH_INIT_SIZE; #endif if (n->size >= AHASH_MAX(h)) { /* Trigger rehashing */ mtype_data_next(&h->next, d); ret = -EAGAIN; goto resize; } old = n; n = kzalloc(sizeof(*n) + (old->size + AHASH_INIT_SIZE) * set->dsize, GFP_ATOMIC); if (!n) { ret = -ENOMEM; goto unlock; } memcpy(n, old, sizeof(struct hbucket) + old->size * set->dsize); n->size = old->size + AHASH_INIT_SIZE; t->hregion[r].ext_size += ext_size(AHASH_INIT_SIZE, set->dsize); } copy_elem: j = n->pos++; data = ahash_data(n, j, set->dsize); copy_data: t->hregion[r].elements++; #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) mtype_add_cidr(set, h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i); #endif memcpy(data, d, sizeof(struct mtype_elem)); overwrite_extensions: #ifdef IP_SET_HASH_WITH_NETS mtype_data_set_flags(data, flags); #endif if (SET_WITH_COUNTER(set)) ip_set_init_counter(ext_counter(data, set), ext); if (SET_WITH_COMMENT(set)) ip_set_init_comment(set, ext_comment(data, set), ext); if (SET_WITH_SKBINFO(set)) ip_set_init_skbinfo(ext_skbinfo(data, set), ext); /* Must come last for the case when timed out entry is reused */ if (SET_WITH_TIMEOUT(set)) ip_set_timeout_set(ext_timeout(data, set), ext->timeout); smp_mb__before_atomic(); set_bit(j, n->used); if (old != ERR_PTR(-ENOENT)) { rcu_assign_pointer(hbucket(t, key), n); if (old) kfree_rcu(old, rcu); } ret = 0; resize: spin_unlock_bh(&t->hregion[r].lock); if (atomic_read(&t->ref) && ext->target) { /* Resize is in process and kernel side add, save values */ struct mtype_resize_ad *x; x = kzalloc(sizeof(struct mtype_resize_ad), GFP_ATOMIC); if (!x) /* Don't bother */ goto out; x->ad = IPSET_ADD; memcpy(&x->d, value, sizeof(struct mtype_elem)); memcpy(&x->ext, ext, sizeof(struct ip_set_ext)); memcpy(&x->mext, mext, sizeof(struct ip_set_ext)); x->flags = flags; spin_lock_bh(&set->lock); list_add_tail(&x->list, &h->ad); spin_unlock_bh(&set->lock); } goto out; set_full: if (net_ratelimit()) pr_warn("Set %s is full, maxelem %u reached\n", set->name, maxelem); ret = -IPSET_ERR_HASH_FULL; unlock: spin_unlock_bh(&t->hregion[r].lock); out: if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { pr_debug("Table destroy after resize by add: %p\n", t); mtype_ahash_destroy(set, t, false); } return ret; } /* Delete an element from the hash and free up space if possible. */ static int mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) { struct htype *h = set->data; struct htable *t; const struct mtype_elem *d = value; struct mtype_elem *data; struct hbucket *n; struct mtype_resize_ad *x = NULL; int i, j, k, r, ret = -IPSET_ERR_EXIST; u32 key, multi = 0; size_t dsize = set->dsize; /* Userspace add and resize is excluded by the mutex. * Kernespace add does not trigger resize. */ rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); key = HKEY(value, h->initval, t->htable_bits); r = ahash_region(key, t->htable_bits); atomic_inc(&t->uref); rcu_read_unlock_bh(); spin_lock_bh(&t->hregion[r].lock); n = rcu_dereference_bh(hbucket(t, key)); if (!n) goto out; for (i = 0, k = 0; i < n->pos; i++) { if (!test_bit(i, n->used)) { k++; continue; } data = ahash_data(n, i, dsize); if (!mtype_data_equal(data, d, &multi)) continue; if (SET_ELEM_EXPIRED(set, data)) goto out; ret = 0; clear_bit(i, n->used); smp_mb__after_atomic(); if (i + 1 == n->pos) n->pos--; t->hregion[r].elements--; #ifdef IP_SET_HASH_WITH_NETS for (j = 0; j < IPSET_NET_COUNT; j++) mtype_del_cidr(set, h, NCIDR_PUT(DCIDR_GET(d->cidr, j)), j); #endif ip_set_ext_destroy(set, data); if (atomic_read(&t->ref) && ext->target) { /* Resize is in process and kernel side del, * save values */ x = kzalloc(sizeof(struct mtype_resize_ad), GFP_ATOMIC); if (x) { x->ad = IPSET_DEL; memcpy(&x->d, value, sizeof(struct mtype_elem)); x->flags = flags; } } for (; i < n->pos; i++) { if (!test_bit(i, n->used)) k++; } if (n->pos == 0 && k == 0) { t->hregion[r].ext_size -= ext_size(n->size, dsize); rcu_assign_pointer(hbucket(t, key), NULL); kfree_rcu(n, rcu); } else if (k >= AHASH_INIT_SIZE) { struct hbucket *tmp = kzalloc(sizeof(*tmp) + (n->size - AHASH_INIT_SIZE) * dsize, GFP_ATOMIC); if (!tmp) goto out; tmp->size = n->size - AHASH_INIT_SIZE; for (j = 0, k = 0; j < n->pos; j++) { if (!test_bit(j, n->used)) continue; data = ahash_data(n, j, dsize); memcpy(tmp->value + k * dsize, data, dsize); set_bit(k, tmp->used); k++; } tmp->pos = k; t->hregion[r].ext_size -= ext_size(AHASH_INIT_SIZE, dsize); rcu_assign_pointer(hbucket(t, key), tmp); kfree_rcu(n, rcu); } goto out; } out: spin_unlock_bh(&t->hregion[r].lock); if (x) { spin_lock_bh(&set->lock); list_add(&x->list, &h->ad); spin_unlock_bh(&set->lock); } if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { pr_debug("Table destroy after resize by del: %p\n", t); mtype_ahash_destroy(set, t, false); } return ret; } static int mtype_data_match(struct mtype_elem *data, const struct ip_set_ext *ext, struct ip_set_ext *mext, struct ip_set *set, u32 flags) { if (!ip_set_match_extensions(set, ext, mext, flags, data)) return 0; /* nomatch entries return -ENOTEMPTY */ return mtype_do_data_match(data); } #ifdef IP_SET_HASH_WITH_NETS /* Special test function which takes into account the different network * sizes added to the set */ static int mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) { struct htype *h = set->data; struct htable *t = rcu_dereference_bh(h->table); struct hbucket *n; struct mtype_elem *data; #if IPSET_NET_COUNT == 2 struct mtype_elem orig = *d; int ret, i, j = 0, k; #else int ret, i, j = 0; #endif u32 key, multi = 0; pr_debug("test by nets\n"); for (; j < NLEN && h->nets[j].cidr[0] && !multi; j++) { #if IPSET_NET_COUNT == 2 mtype_data_reset_elem(d, &orig); mtype_data_netmask(d, NCIDR_GET(h->nets[j].cidr[0]), false); for (k = 0; k < NLEN && h->nets[k].cidr[1] && !multi; k++) { mtype_data_netmask(d, NCIDR_GET(h->nets[k].cidr[1]), true); #else mtype_data_netmask(d, NCIDR_GET(h->nets[j].cidr[0])); #endif key = HKEY(d, h->initval, t->htable_bits); n = rcu_dereference_bh(hbucket(t, key)); if (!n) continue; for (i = 0; i < n->pos; i++) { if (!test_bit(i, n->used)) continue; data = ahash_data(n, i, set->dsize); if (!mtype_data_equal(data, d, &multi)) continue; ret = mtype_data_match(data, ext, mext, set, flags); if (ret != 0) return ret; #ifdef IP_SET_HASH_WITH_MULTI /* No match, reset multiple match flag */ multi = 0; #endif } #if IPSET_NET_COUNT == 2 } #endif } return 0; } #endif /* Test whether the element is added to the set */ static int mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags) { struct htype *h = set->data; struct htable *t; struct mtype_elem *d = value; struct hbucket *n; struct mtype_elem *data; int i, ret = 0; u32 key, multi = 0; rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); #ifdef IP_SET_HASH_WITH_NETS /* If we test an IP address and not a network address, * try all possible network sizes */ for (i = 0; i < IPSET_NET_COUNT; i++) if (DCIDR_GET(d->cidr, i) != HOST_MASK) break; if (i == IPSET_NET_COUNT) { ret = mtype_test_cidrs(set, d, ext, mext, flags); goto out; } #endif key = HKEY(d, h->initval, t->htable_bits); n = rcu_dereference_bh(hbucket(t, key)); if (!n) { ret = 0; goto out; } for (i = 0; i < n->pos; i++) { if (!test_bit(i, n->used)) continue; data = ahash_data(n, i, set->dsize); if (!mtype_data_equal(data, d, &multi)) continue; ret = mtype_data_match(data, ext, mext, set, flags); if (ret != 0) goto out; } out: rcu_read_unlock_bh(); return ret; } /* Reply a HEADER request: fill out the header part of the set */ static int mtype_head(struct ip_set *set, struct sk_buff *skb) { struct htype *h = set->data; const struct htable *t; struct nlattr *nested; size_t memsize; u32 elements = 0; size_t ext_size = 0; u8 htable_bits; rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); mtype_ext_size(set, &elements, &ext_size); memsize = mtype_ahash_memsize(h, t) + ext_size + set->ext_size; htable_bits = t->htable_bits; rcu_read_unlock_bh(); nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; if (nla_put_net32(skb, IPSET_ATTR_HASHSIZE, htonl(jhash_size(htable_bits))) || nla_put_net32(skb, IPSET_ATTR_MAXELEM, htonl(h->maxelem))) goto nla_put_failure; #ifdef IP_SET_HASH_WITH_BITMASK /* if netmask is set to anything other than HOST_MASK we know that the user supplied netmask * and not bitmask. These two are mutually exclusive. */ if (h->netmask == HOST_MASK && !nf_inet_addr_cmp(&onesmask, &h->bitmask)) { if (set->family == NFPROTO_IPV4) { if (nla_put_ipaddr4(skb, IPSET_ATTR_BITMASK, h->bitmask.ip)) goto nla_put_failure; } else if (set->family == NFPROTO_IPV6) { if (nla_put_ipaddr6(skb, IPSET_ATTR_BITMASK, &h->bitmask.in6)) goto nla_put_failure; } } #endif #ifdef IP_SET_HASH_WITH_NETMASK if (h->netmask != HOST_MASK && nla_put_u8(skb, IPSET_ATTR_NETMASK, h->netmask)) goto nla_put_failure; #endif #ifdef IP_SET_HASH_WITH_MARKMASK if (nla_put_u32(skb, IPSET_ATTR_MARKMASK, h->markmask)) goto nla_put_failure; #endif if (set->flags & IPSET_CREATE_FLAG_BUCKETSIZE) { if (nla_put_u8(skb, IPSET_ATTR_BUCKETSIZE, h->bucketsize) || nla_put_net32(skb, IPSET_ATTR_INITVAL, htonl(h->initval))) goto nla_put_failure; } if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) || nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) goto nla_put_failure; nla_nest_end(skb, nested); return 0; nla_put_failure: return -EMSGSIZE; } /* Make possible to run dumping parallel with resizing */ static void mtype_uref(struct ip_set *set, struct netlink_callback *cb, bool start) { struct htype *h = set->data; struct htable *t; if (start) { rcu_read_lock_bh(); t = ipset_dereference_bh_nfnl(h->table); atomic_inc(&t->uref); cb->args[IPSET_CB_PRIVATE] = (unsigned long)t; rcu_read_unlock_bh(); } else if (cb->args[IPSET_CB_PRIVATE]) { t = (struct htable *)cb->args[IPSET_CB_PRIVATE]; if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { pr_debug("Table destroy after resize " " by dump: %p\n", t); mtype_ahash_destroy(set, t, false); } cb->args[IPSET_CB_PRIVATE] = 0; } } /* Reply a LIST/SAVE request: dump the elements of the specified set */ static int mtype_list(const struct ip_set *set, struct sk_buff *skb, struct netlink_callback *cb) { const struct htable *t; struct nlattr *atd, *nested; const struct hbucket *n; const struct mtype_elem *e; u32 first = cb->args[IPSET_CB_ARG0]; /* We assume that one hash bucket fills into one page */ void *incomplete; int i, ret = 0; atd = nla_nest_start(skb, IPSET_ATTR_ADT); if (!atd) return -EMSGSIZE; pr_debug("list hash set %s\n", set->name); t = (const struct htable *)cb->args[IPSET_CB_PRIVATE]; /* Expire may replace a hbucket with another one */ rcu_read_lock(); for (; cb->args[IPSET_CB_ARG0] < jhash_size(t->htable_bits); cb->args[IPSET_CB_ARG0]++) { cond_resched_rcu(); incomplete = skb_tail_pointer(skb); n = rcu_dereference(hbucket(t, cb->args[IPSET_CB_ARG0])); pr_debug("cb->arg bucket: %lu, t %p n %p\n", cb->args[IPSET_CB_ARG0], t, n); if (!n) continue; for (i = 0; i < n->pos; i++) { if (!test_bit(i, n->used)) continue; e = ahash_data(n, i, set->dsize); if (SET_ELEM_EXPIRED(set, e)) continue; pr_debug("list hash %lu hbucket %p i %u, data %p\n", cb->args[IPSET_CB_ARG0], n, i, e); nested = nla_nest_start(skb, IPSET_ATTR_DATA); if (!nested) { if (cb->args[IPSET_CB_ARG0] == first) { nla_nest_cancel(skb, atd); ret = -EMSGSIZE; goto out; } goto nla_put_failure; } if (mtype_data_list(skb, e)) goto nla_put_failure; if (ip_set_put_extensions(skb, set, e, true)) goto nla_put_failure; nla_nest_end(skb, nested); } } nla_nest_end(skb, atd); /* Set listing finished */ cb->args[IPSET_CB_ARG0] = 0; goto out; nla_put_failure: nlmsg_trim(skb, incomplete); if (unlikely(first == cb->args[IPSET_CB_ARG0])) { pr_warn("Can't list set %s: one bucket does not fit into a message. Please report it!\n", set->name); cb->args[IPSET_CB_ARG0] = 0; ret = -EMSGSIZE; } else { nla_nest_end(skb, atd); } out: rcu_read_unlock(); return ret; } static int IPSET_TOKEN(MTYPE, _kadt)(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt); static int IPSET_TOKEN(MTYPE, _uadt)(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried); static const struct ip_set_type_variant mtype_variant = { .kadt = mtype_kadt, .uadt = mtype_uadt, .adt = { [IPSET_ADD] = mtype_add, [IPSET_DEL] = mtype_del, [IPSET_TEST] = mtype_test, }, .destroy = mtype_destroy, .flush = mtype_flush, .head = mtype_head, .list = mtype_list, .uref = mtype_uref, .resize = mtype_resize, .same_set = mtype_same_set, .cancel_gc = mtype_cancel_gc, .region_lock = true, }; #ifdef IP_SET_EMIT_CREATE static int IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, struct nlattr *tb[], u32 flags) { u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; #ifdef IP_SET_HASH_WITH_MARKMASK u32 markmask; #endif u8 hbits; #if defined(IP_SET_HASH_WITH_NETMASK) || defined(IP_SET_HASH_WITH_BITMASK) int ret __attribute__((unused)) = 0; u8 netmask = set->family == NFPROTO_IPV4 ? 32 : 128; union nf_inet_addr bitmask = onesmask; #endif size_t hsize; struct htype *h; struct htable *t; u32 i; pr_debug("Create set %s with family %s\n", set->name, set->family == NFPROTO_IPV4 ? "inet" : "inet6"); #ifdef IP_SET_PROTO_UNDEF if (set->family != NFPROTO_UNSPEC) return -IPSET_ERR_INVALID_FAMILY; #else if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) return -IPSET_ERR_INVALID_FAMILY; #endif if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) || !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; #ifdef IP_SET_HASH_WITH_MARKMASK /* Separated condition in order to avoid directive in argument list */ if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_MARKMASK))) return -IPSET_ERR_PROTOCOL; markmask = 0xffffffff; if (tb[IPSET_ATTR_MARKMASK]) { markmask = ntohl(nla_get_be32(tb[IPSET_ATTR_MARKMASK])); if (markmask == 0) return -IPSET_ERR_INVALID_MARKMASK; } #endif #ifdef IP_SET_HASH_WITH_NETMASK if (tb[IPSET_ATTR_NETMASK]) { netmask = nla_get_u8(tb[IPSET_ATTR_NETMASK]); if ((set->family == NFPROTO_IPV4 && netmask > 32) || (set->family == NFPROTO_IPV6 && netmask > 128) || netmask == 0) return -IPSET_ERR_INVALID_NETMASK; /* we convert netmask to bitmask and store it */ if (set->family == NFPROTO_IPV4) bitmask.ip = ip_set_netmask(netmask); else ip6_netmask(&bitmask, netmask); } #endif #ifdef IP_SET_HASH_WITH_BITMASK if (tb[IPSET_ATTR_BITMASK]) { /* bitmask and netmask do the same thing, allow only one of these options */ if (tb[IPSET_ATTR_NETMASK]) return -IPSET_ERR_BITMASK_NETMASK_EXCL; if (set->family == NFPROTO_IPV4) { ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_BITMASK], &bitmask.ip); if (ret || !bitmask.ip) return -IPSET_ERR_INVALID_NETMASK; } else if (set->family == NFPROTO_IPV6) { ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_BITMASK], &bitmask); if (ret || ipv6_addr_any(&bitmask.in6)) return -IPSET_ERR_INVALID_NETMASK; } if (nf_inet_addr_cmp(&bitmask, &zeromask)) return -IPSET_ERR_INVALID_NETMASK; } #endif if (tb[IPSET_ATTR_HASHSIZE]) { hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]); if (hashsize < IPSET_MIMINAL_HASHSIZE) hashsize = IPSET_MIMINAL_HASHSIZE; } if (tb[IPSET_ATTR_MAXELEM]) maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]); hsize = sizeof(*h); h = kzalloc(hsize, GFP_KERNEL); if (!h) return -ENOMEM; /* Compute htable_bits from the user input parameter hashsize. * Assume that hashsize == 2^htable_bits, * otherwise round up to the first 2^n value. */ hbits = fls(hashsize - 1); hsize = htable_size(hbits); if (hsize == 0) { kfree(h); return -ENOMEM; } t = ip_set_alloc(hsize); if (!t) { kfree(h); return -ENOMEM; } t->hregion = ip_set_alloc(ahash_sizeof_regions(hbits)); if (!t->hregion) { ip_set_free(t); kfree(h); return -ENOMEM; } h->gc.set = set; for (i = 0; i < ahash_numof_locks(hbits); i++) spin_lock_init(&t->hregion[i].lock); h->maxelem = maxelem; #if defined(IP_SET_HASH_WITH_NETMASK) || defined(IP_SET_HASH_WITH_BITMASK) h->bitmask = bitmask; h->netmask = netmask; #endif #ifdef IP_SET_HASH_WITH_MARKMASK h->markmask = markmask; #endif if (tb[IPSET_ATTR_INITVAL]) h->initval = ntohl(nla_get_be32(tb[IPSET_ATTR_INITVAL])); else get_random_bytes(&h->initval, sizeof(h->initval)); h->bucketsize = AHASH_MAX_SIZE; if (tb[IPSET_ATTR_BUCKETSIZE]) { h->bucketsize = nla_get_u8(tb[IPSET_ATTR_BUCKETSIZE]); if (h->bucketsize < AHASH_INIT_SIZE) h->bucketsize = AHASH_INIT_SIZE; else if (h->bucketsize > AHASH_MAX_SIZE) h->bucketsize = AHASH_MAX_SIZE; else if (h->bucketsize % 2) h->bucketsize += 1; } t->htable_bits = hbits; t->maxelem = h->maxelem / ahash_numof_locks(hbits); RCU_INIT_POINTER(h->table, t); INIT_LIST_HEAD(&h->ad); set->data = h; #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) { #endif set->variant = &IPSET_TOKEN(HTYPE, 4_variant); set->dsize = ip_set_elem_len(set, tb, sizeof(struct IPSET_TOKEN(HTYPE, 4_elem)), __alignof__(struct IPSET_TOKEN(HTYPE, 4_elem))); #ifndef IP_SET_PROTO_UNDEF } else { set->variant = &IPSET_TOKEN(HTYPE, 6_variant); set->dsize = ip_set_elem_len(set, tb, sizeof(struct IPSET_TOKEN(HTYPE, 6_elem)), __alignof__(struct IPSET_TOKEN(HTYPE, 6_elem))); } #endif set->timeout = IPSET_NO_TIMEOUT; if (tb[IPSET_ATTR_TIMEOUT]) { set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) #endif IPSET_TOKEN(HTYPE, 4_gc_init)(&h->gc); #ifndef IP_SET_PROTO_UNDEF else IPSET_TOKEN(HTYPE, 6_gc_init)(&h->gc); #endif } pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n", set->name, jhash_size(t->htable_bits), t->htable_bits, h->maxelem, set->data, t); return 0; } #endif /* IP_SET_EMIT_CREATE */ #undef HKEY_DATALEN |
| 1 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Trace point definitions for core RDMA functions. * * Author: Chuck Lever <chuck.lever@oracle.com> * * Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM rdma_core #if !defined(_TRACE_RDMA_CORE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_RDMA_CORE_H #include <linux/tracepoint.h> #include <rdma/ib_verbs.h> /* * enum ib_poll_context, from include/rdma/ib_verbs.h */ #define IB_POLL_CTX_LIST \ ib_poll_ctx(DIRECT) \ ib_poll_ctx(SOFTIRQ) \ ib_poll_ctx(WORKQUEUE) \ ib_poll_ctx_end(UNBOUND_WORKQUEUE) #undef ib_poll_ctx #undef ib_poll_ctx_end #define ib_poll_ctx(x) TRACE_DEFINE_ENUM(IB_POLL_##x); #define ib_poll_ctx_end(x) TRACE_DEFINE_ENUM(IB_POLL_##x); IB_POLL_CTX_LIST #undef ib_poll_ctx #undef ib_poll_ctx_end #define ib_poll_ctx(x) { IB_POLL_##x, #x }, #define ib_poll_ctx_end(x) { IB_POLL_##x, #x } #define rdma_show_ib_poll_ctx(x) \ __print_symbolic(x, IB_POLL_CTX_LIST) /** ** Completion Queue events **/ TRACE_EVENT(cq_schedule, TP_PROTO( struct ib_cq *cq ), TP_ARGS(cq), TP_STRUCT__entry( __field(u32, cq_id) ), TP_fast_assign( cq->timestamp = ktime_get(); cq->interrupt = true; __entry->cq_id = cq->res.id; ), TP_printk("cq.id=%u", __entry->cq_id) ); TRACE_EVENT(cq_reschedule, TP_PROTO( struct ib_cq *cq ), TP_ARGS(cq), TP_STRUCT__entry( __field(u32, cq_id) ), TP_fast_assign( cq->timestamp = ktime_get(); cq->interrupt = false; __entry->cq_id = cq->res.id; ), TP_printk("cq.id=%u", __entry->cq_id) ); TRACE_EVENT(cq_process, TP_PROTO( const struct ib_cq *cq ), TP_ARGS(cq), TP_STRUCT__entry( __field(u32, cq_id) __field(bool, interrupt) __field(s64, latency) ), TP_fast_assign( ktime_t latency = ktime_sub(ktime_get(), cq->timestamp); __entry->cq_id = cq->res.id; __entry->latency = ktime_to_us(latency); __entry->interrupt = cq->interrupt; ), TP_printk("cq.id=%u wake-up took %lld [us] from %s", __entry->cq_id, __entry->latency, __entry->interrupt ? "interrupt" : "reschedule" ) ); TRACE_EVENT(cq_poll, TP_PROTO( const struct ib_cq *cq, int requested, int rc ), TP_ARGS(cq, requested, rc), TP_STRUCT__entry( __field(u32, cq_id) __field(int, requested) __field(int, rc) ), TP_fast_assign( __entry->cq_id = cq->res.id; __entry->requested = requested; __entry->rc = rc; ), TP_printk("cq.id=%u requested %d, returned %d", __entry->cq_id, __entry->requested, __entry->rc ) ); TRACE_EVENT(cq_drain_complete, TP_PROTO( const struct ib_cq *cq ), TP_ARGS(cq), TP_STRUCT__entry( __field(u32, cq_id) ), TP_fast_assign( __entry->cq_id = cq->res.id; ), TP_printk("cq.id=%u", __entry->cq_id ) ); TRACE_EVENT(cq_modify, TP_PROTO( const struct ib_cq *cq, u16 comps, u16 usec ), TP_ARGS(cq, comps, usec), TP_STRUCT__entry( __field(u32, cq_id) __field(unsigned int, comps) __field(unsigned int, usec) ), TP_fast_assign( __entry->cq_id = cq->res.id; __entry->comps = comps; __entry->usec = usec; ), TP_printk("cq.id=%u comps=%u usec=%u", __entry->cq_id, __entry->comps, __entry->usec ) ); TRACE_EVENT(cq_alloc, TP_PROTO( const struct ib_cq *cq, int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx ), TP_ARGS(cq, nr_cqe, comp_vector, poll_ctx), TP_STRUCT__entry( __field(u32, cq_id) __field(int, nr_cqe) __field(int, comp_vector) __field(unsigned long, poll_ctx) ), TP_fast_assign( __entry->cq_id = cq->res.id; __entry->nr_cqe = nr_cqe; __entry->comp_vector = comp_vector; __entry->poll_ctx = poll_ctx; ), TP_printk("cq.id=%u nr_cqe=%d comp_vector=%d poll_ctx=%s", __entry->cq_id, __entry->nr_cqe, __entry->comp_vector, rdma_show_ib_poll_ctx(__entry->poll_ctx) ) ); TRACE_EVENT(cq_alloc_error, TP_PROTO( int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx, int rc ), TP_ARGS(nr_cqe, comp_vector, poll_ctx, rc), TP_STRUCT__entry( __field(int, rc) __field(int, nr_cqe) __field(int, comp_vector) __field(unsigned long, poll_ctx) ), TP_fast_assign( __entry->rc = rc; __entry->nr_cqe = nr_cqe; __entry->comp_vector = comp_vector; __entry->poll_ctx = poll_ctx; ), TP_printk("nr_cqe=%d comp_vector=%d poll_ctx=%s rc=%d", __entry->nr_cqe, __entry->comp_vector, rdma_show_ib_poll_ctx(__entry->poll_ctx), __entry->rc ) ); TRACE_EVENT(cq_free, TP_PROTO( const struct ib_cq *cq ), TP_ARGS(cq), TP_STRUCT__entry( __field(u32, cq_id) ), TP_fast_assign( __entry->cq_id = cq->res.id; ), TP_printk("cq.id=%u", __entry->cq_id) ); /** ** Memory Region events **/ /* * enum ib_mr_type, from include/rdma/ib_verbs.h */ #define IB_MR_TYPE_LIST \ ib_mr_type_item(MEM_REG) \ ib_mr_type_item(SG_GAPS) \ ib_mr_type_item(DM) \ ib_mr_type_item(USER) \ ib_mr_type_item(DMA) \ ib_mr_type_end(INTEGRITY) #undef ib_mr_type_item #undef ib_mr_type_end #define ib_mr_type_item(x) TRACE_DEFINE_ENUM(IB_MR_TYPE_##x); #define ib_mr_type_end(x) TRACE_DEFINE_ENUM(IB_MR_TYPE_##x); IB_MR_TYPE_LIST #undef ib_mr_type_item #undef ib_mr_type_end #define ib_mr_type_item(x) { IB_MR_TYPE_##x, #x }, #define ib_mr_type_end(x) { IB_MR_TYPE_##x, #x } #define rdma_show_ib_mr_type(x) \ __print_symbolic(x, IB_MR_TYPE_LIST) TRACE_EVENT(mr_alloc, TP_PROTO( const struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg, const struct ib_mr *mr ), TP_ARGS(pd, mr_type, max_num_sg, mr), TP_STRUCT__entry( __field(u32, pd_id) __field(u32, mr_id) __field(u32, max_num_sg) __field(int, rc) __field(unsigned long, mr_type) ), TP_fast_assign( __entry->pd_id = pd->res.id; if (IS_ERR(mr)) { __entry->mr_id = 0; __entry->rc = PTR_ERR(mr); } else { __entry->mr_id = mr->res.id; __entry->rc = 0; } __entry->max_num_sg = max_num_sg; __entry->mr_type = mr_type; ), TP_printk("pd.id=%u mr.id=%u type=%s max_num_sg=%u rc=%d", __entry->pd_id, __entry->mr_id, rdma_show_ib_mr_type(__entry->mr_type), __entry->max_num_sg, __entry->rc) ); TRACE_EVENT(mr_integ_alloc, TP_PROTO( const struct ib_pd *pd, u32 max_num_data_sg, u32 max_num_meta_sg, const struct ib_mr *mr ), TP_ARGS(pd, max_num_data_sg, max_num_meta_sg, mr), TP_STRUCT__entry( __field(u32, pd_id) __field(u32, mr_id) __field(u32, max_num_data_sg) __field(u32, max_num_meta_sg) __field(int, rc) ), TP_fast_assign( __entry->pd_id = pd->res.id; if (IS_ERR(mr)) { __entry->mr_id = 0; __entry->rc = PTR_ERR(mr); } else { __entry->mr_id = mr->res.id; __entry->rc = 0; } __entry->max_num_data_sg = max_num_data_sg; __entry->max_num_meta_sg = max_num_meta_sg; ), TP_printk("pd.id=%u mr.id=%u max_num_data_sg=%u max_num_meta_sg=%u rc=%d", __entry->pd_id, __entry->mr_id, __entry->max_num_data_sg, __entry->max_num_meta_sg, __entry->rc) ); TRACE_EVENT(mr_dereg, TP_PROTO( const struct ib_mr *mr ), TP_ARGS(mr), TP_STRUCT__entry( __field(u32, id) ), TP_fast_assign( __entry->id = mr->res.id; ), TP_printk("mr.id=%u", __entry->id) ); #endif /* _TRACE_RDMA_CORE_H */ #include <trace/define_trace.h> |
| 4 1 4 5 4 2 2 2 3 3 5 5 5 3 1 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPVS: Weighted Round-Robin Scheduling module * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * * Changes: * Wensong Zhang : changed the ip_vs_wrr_schedule to return dest * Wensong Zhang : changed some comestics things for debugging * Wensong Zhang : changed for the d-linked destination list * Wensong Zhang : added the ip_vs_wrr_update_svc * Julian Anastasov : fixed the bug of returning destination * with weight 0 when all weights are zero */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/module.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/net.h> #include <linux/gcd.h> #include <net/ip_vs.h> /* The WRR algorithm depends on some caclulations: * - mw: maximum weight * - di: weight step, greatest common divisor from all weights * - cw: current required weight * As result, all weights are in the [di..mw] range with a step=di. * * First, we start with cw = mw and select dests with weight >= cw. * Then cw is reduced with di and all dests are checked again. * Last pass should be with cw = di. We have mw/di passes in total: * * pass 1: cw = max weight * pass 2: cw = max weight - di * pass 3: cw = max weight - 2 * di * ... * last pass: cw = di * * Weights are supposed to be >= di but we run in parallel with * weight changes, it is possible some dest weight to be reduced * below di, bad if it is the only available dest. * * So, we modify how mw is calculated, now it is reduced with (di - 1), * so that last cw is 1 to catch such dests with weight below di: * pass 1: cw = max weight - (di - 1) * pass 2: cw = max weight - di - (di - 1) * pass 3: cw = max weight - 2 * di - (di - 1) * ... * last pass: cw = 1 * */ /* * current destination pointer for weighted round-robin scheduling */ struct ip_vs_wrr_mark { struct ip_vs_dest *cl; /* current dest or head */ int cw; /* current weight */ int mw; /* maximum weight */ int di; /* decreasing interval */ struct rcu_head rcu_head; }; static int ip_vs_wrr_gcd_weight(struct ip_vs_service *svc) { struct ip_vs_dest *dest; int weight; int g = 0; list_for_each_entry(dest, &svc->destinations, n_list) { weight = atomic_read(&dest->weight); if (weight > 0) { if (g > 0) g = gcd(weight, g); else g = weight; } } return g ? g : 1; } /* * Get the maximum weight of the service destinations. */ static int ip_vs_wrr_max_weight(struct ip_vs_service *svc) { struct ip_vs_dest *dest; int new_weight, weight = 0; list_for_each_entry(dest, &svc->destinations, n_list) { new_weight = atomic_read(&dest->weight); if (new_weight > weight) weight = new_weight; } return weight; } static int ip_vs_wrr_init_svc(struct ip_vs_service *svc) { struct ip_vs_wrr_mark *mark; /* * Allocate the mark variable for WRR scheduling */ mark = kmalloc(sizeof(struct ip_vs_wrr_mark), GFP_KERNEL); if (mark == NULL) return -ENOMEM; mark->cl = list_entry(&svc->destinations, struct ip_vs_dest, n_list); mark->di = ip_vs_wrr_gcd_weight(svc); mark->mw = ip_vs_wrr_max_weight(svc) - (mark->di - 1); mark->cw = mark->mw; svc->sched_data = mark; return 0; } static void ip_vs_wrr_done_svc(struct ip_vs_service *svc) { struct ip_vs_wrr_mark *mark = svc->sched_data; /* * Release the mark variable */ kfree_rcu(mark, rcu_head); } static int ip_vs_wrr_dest_changed(struct ip_vs_service *svc, struct ip_vs_dest *dest) { struct ip_vs_wrr_mark *mark = svc->sched_data; spin_lock_bh(&svc->sched_lock); mark->cl = list_entry(&svc->destinations, struct ip_vs_dest, n_list); mark->di = ip_vs_wrr_gcd_weight(svc); mark->mw = ip_vs_wrr_max_weight(svc) - (mark->di - 1); if (mark->cw > mark->mw || !mark->cw) mark->cw = mark->mw; else if (mark->di > 1) mark->cw = (mark->cw / mark->di) * mark->di + 1; spin_unlock_bh(&svc->sched_lock); return 0; } /* * Weighted Round-Robin Scheduling */ static struct ip_vs_dest * ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest, *last, *stop = NULL; struct ip_vs_wrr_mark *mark = svc->sched_data; bool last_pass = false, restarted = false; IP_VS_DBG(6, "%s(): Scheduling...\n", __func__); spin_lock_bh(&svc->sched_lock); dest = mark->cl; /* No available dests? */ if (mark->mw == 0) goto err_noavail; last = dest; /* Stop only after all dests were checked for weight >= 1 (last pass) */ while (1) { list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) { if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) && atomic_read(&dest->weight) >= mark->cw) goto found; if (dest == stop) goto err_over; } mark->cw -= mark->di; if (mark->cw <= 0) { mark->cw = mark->mw; /* Stop if we tried last pass from first dest: * 1. last_pass: we started checks when cw > di but * then all dests were checked for w >= 1 * 2. last was head: the first and only traversal * was for weight >= 1, for all dests. */ if (last_pass || &last->n_list == &svc->destinations) goto err_over; restarted = true; } last_pass = mark->cw <= mark->di; if (last_pass && restarted && &last->n_list != &svc->destinations) { /* First traversal was for w >= 1 but only * for dests after 'last', now do the same * for all dests up to 'last'. */ stop = last; } } found: IP_VS_DBG_BUF(6, "WRR: server %s:%u " "activeconns %d refcnt %d weight %d\n", IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), atomic_read(&dest->activeconns), refcount_read(&dest->refcnt), atomic_read(&dest->weight)); mark->cl = dest; out: spin_unlock_bh(&svc->sched_lock); return dest; err_noavail: mark->cl = dest; dest = NULL; ip_vs_scheduler_err(svc, "no destination available"); goto out; err_over: mark->cl = dest; dest = NULL; ip_vs_scheduler_err(svc, "no destination available: " "all destinations are overloaded"); goto out; } static struct ip_vs_scheduler ip_vs_wrr_scheduler = { .name = "wrr", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, .n_list = LIST_HEAD_INIT(ip_vs_wrr_scheduler.n_list), .init_service = ip_vs_wrr_init_svc, .done_service = ip_vs_wrr_done_svc, .add_dest = ip_vs_wrr_dest_changed, .del_dest = ip_vs_wrr_dest_changed, .upd_dest = ip_vs_wrr_dest_changed, .schedule = ip_vs_wrr_schedule, }; static int __init ip_vs_wrr_init(void) { return register_ip_vs_scheduler(&ip_vs_wrr_scheduler) ; } static void __exit ip_vs_wrr_cleanup(void) { unregister_ip_vs_scheduler(&ip_vs_wrr_scheduler); synchronize_rcu(); } module_init(ip_vs_wrr_init); module_exit(ip_vs_wrr_cleanup); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("ipvs weighted round-robin scheduler"); |
| 7 4 1 3 1 3 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IP6 tables REJECT target module * Linux INET6 implementation * * Copyright (C)2003 USAGI/WIDE Project * * Authors: * Yasuyuki Kozakai <yasuyuki.kozakai@toshiba.co.jp> * * Copyright (c) 2005-2007 Patrick McHardy <kaber@trash.net> * * Based on net/ipv4/netfilter/ipt_REJECT.c */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/gfp.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/icmpv6.h> #include <linux/netdevice.h> #include <net/icmp.h> #include <net/flow.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter_ipv6/ip6t_REJECT.h> #include <net/netfilter/ipv6/nf_reject.h> MODULE_AUTHOR("Yasuyuki KOZAKAI <yasuyuki.kozakai@toshiba.co.jp>"); MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv6"); MODULE_LICENSE("GPL"); static unsigned int reject_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct ip6t_reject_info *reject = par->targinfo; struct net *net = xt_net(par); switch (reject->with) { case IP6T_ICMP6_NO_ROUTE: nf_send_unreach6(net, skb, ICMPV6_NOROUTE, xt_hooknum(par)); break; case IP6T_ICMP6_ADM_PROHIBITED: nf_send_unreach6(net, skb, ICMPV6_ADM_PROHIBITED, xt_hooknum(par)); break; case IP6T_ICMP6_NOT_NEIGHBOUR: nf_send_unreach6(net, skb, ICMPV6_NOT_NEIGHBOUR, xt_hooknum(par)); break; case IP6T_ICMP6_ADDR_UNREACH: nf_send_unreach6(net, skb, ICMPV6_ADDR_UNREACH, xt_hooknum(par)); break; case IP6T_ICMP6_PORT_UNREACH: nf_send_unreach6(net, skb, ICMPV6_PORT_UNREACH, xt_hooknum(par)); break; case IP6T_ICMP6_ECHOREPLY: /* Do nothing */ break; case IP6T_TCP_RESET: nf_send_reset6(net, par->state->sk, skb, xt_hooknum(par)); break; case IP6T_ICMP6_POLICY_FAIL: nf_send_unreach6(net, skb, ICMPV6_POLICY_FAIL, xt_hooknum(par)); break; case IP6T_ICMP6_REJECT_ROUTE: nf_send_unreach6(net, skb, ICMPV6_REJECT_ROUTE, xt_hooknum(par)); break; } return NF_DROP; } static int reject_tg6_check(const struct xt_tgchk_param *par) { const struct ip6t_reject_info *rejinfo = par->targinfo; const struct ip6t_entry *e = par->entryinfo; if (rejinfo->with == IP6T_ICMP6_ECHOREPLY) { pr_info_ratelimited("ECHOREPLY is not supported\n"); return -EINVAL; } else if (rejinfo->with == IP6T_TCP_RESET) { /* Must specify that it's a TCP packet */ if (!(e->ipv6.flags & IP6T_F_PROTO) || e->ipv6.proto != IPPROTO_TCP || (e->ipv6.invflags & XT_INV_PROTO)) { pr_info_ratelimited("TCP_RESET illegal for non-tcp\n"); return -EINVAL; } } return 0; } static struct xt_target reject_tg6_reg __read_mostly = { .name = "REJECT", .family = NFPROTO_IPV6, .target = reject_tg6, .targetsize = sizeof(struct ip6t_reject_info), .table = "filter", .hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD) | (1 << NF_INET_LOCAL_OUT), .checkentry = reject_tg6_check, .me = THIS_MODULE }; static int __init reject_tg6_init(void) { return xt_register_target(&reject_tg6_reg); } static void __exit reject_tg6_exit(void) { xt_unregister_target(&reject_tg6_reg); } module_init(reject_tg6_init); module_exit(reject_tg6_exit); |
| 1 1 5 3 1 3 2 3 3 1 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Bridge Multiple Spanning Tree Support * * Authors: * Tobias Waldekranz <tobias@waldekranz.com> */ #include <linux/kernel.h> #include <net/switchdev.h> #include "br_private.h" DEFINE_STATIC_KEY_FALSE(br_mst_used); bool br_mst_enabled(const struct net_device *dev) { if (!netif_is_bridge_master(dev)) return false; return br_opt_get(netdev_priv(dev), BROPT_MST_ENABLED); } EXPORT_SYMBOL_GPL(br_mst_enabled); int br_mst_get_info(const struct net_device *dev, u16 msti, unsigned long *vids) { const struct net_bridge_vlan_group *vg; const struct net_bridge_vlan *v; const struct net_bridge *br; ASSERT_RTNL(); if (!netif_is_bridge_master(dev)) return -EINVAL; br = netdev_priv(dev); if (!br_opt_get(br, BROPT_MST_ENABLED)) return -EINVAL; vg = br_vlan_group(br); list_for_each_entry(v, &vg->vlan_list, vlist) { if (v->msti == msti) __set_bit(v->vid, vids); } return 0; } EXPORT_SYMBOL_GPL(br_mst_get_info); int br_mst_get_state(const struct net_device *dev, u16 msti, u8 *state) { const struct net_bridge_port *p = NULL; const struct net_bridge_vlan_group *vg; const struct net_bridge_vlan *v; ASSERT_RTNL(); p = br_port_get_check_rtnl(dev); if (!p || !br_opt_get(p->br, BROPT_MST_ENABLED)) return -EINVAL; vg = nbp_vlan_group(p); list_for_each_entry(v, &vg->vlan_list, vlist) { if (v->brvlan->msti == msti) { *state = v->state; return 0; } } return -ENOENT; } EXPORT_SYMBOL_GPL(br_mst_get_state); static void br_mst_vlan_set_state(struct net_bridge_vlan_group *vg, struct net_bridge_vlan *v, u8 state) { if (br_vlan_get_state(v) == state) return; br_vlan_set_state(v, state); if (v->vid == vg->pvid) br_vlan_set_pvid_state(vg, state); } int br_mst_set_state(struct net_bridge_port *p, u16 msti, u8 state, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .id = SWITCHDEV_ATTR_ID_PORT_MST_STATE, .orig_dev = p->dev, .u.mst_state = { .msti = msti, .state = state, }, }; struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; int err = 0; rcu_read_lock(); vg = nbp_vlan_group_rcu(p); if (!vg) goto out; /* MSTI 0 (CST) state changes are notified via the regular * SWITCHDEV_ATTR_ID_PORT_STP_STATE. */ if (msti) { err = switchdev_port_attr_set(p->dev, &attr, extack); if (err && err != -EOPNOTSUPP) goto out; } err = 0; list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { if (v->brvlan->msti != msti) continue; br_mst_vlan_set_state(vg, v, state); } out: rcu_read_unlock(); return err; } static void br_mst_vlan_sync_state(struct net_bridge_vlan *pv, u16 msti) { struct net_bridge_vlan_group *vg = nbp_vlan_group(pv->port); struct net_bridge_vlan *v; list_for_each_entry(v, &vg->vlan_list, vlist) { /* If this port already has a defined state in this * MSTI (through some other VLAN membership), inherit * it. */ if (v != pv && v->brvlan->msti == msti) { br_mst_vlan_set_state(vg, pv, v->state); return; } } /* Otherwise, start out in a new MSTI with all ports disabled. */ return br_mst_vlan_set_state(vg, pv, BR_STATE_DISABLED); } int br_mst_vlan_set_msti(struct net_bridge_vlan *mv, u16 msti) { struct switchdev_attr attr = { .id = SWITCHDEV_ATTR_ID_VLAN_MSTI, .orig_dev = mv->br->dev, .u.vlan_msti = { .vid = mv->vid, .msti = msti, }, }; struct net_bridge_vlan_group *vg; struct net_bridge_vlan *pv; struct net_bridge_port *p; int err; if (mv->msti == msti) return 0; err = switchdev_port_attr_set(mv->br->dev, &attr, NULL); if (err && err != -EOPNOTSUPP) return err; mv->msti = msti; list_for_each_entry(p, &mv->br->port_list, list) { vg = nbp_vlan_group(p); pv = br_vlan_find(vg, mv->vid); if (pv) br_mst_vlan_sync_state(pv, msti); } return 0; } void br_mst_vlan_init_state(struct net_bridge_vlan *v) { /* VLANs always start out in MSTI 0 (CST) */ v->msti = 0; if (br_vlan_is_master(v)) v->state = BR_STATE_FORWARDING; else v->state = v->port->state; } int br_mst_set_enabled(struct net_bridge *br, bool on, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .id = SWITCHDEV_ATTR_ID_BRIDGE_MST, .orig_dev = br->dev, .u.mst = on, }; struct net_bridge_vlan_group *vg; struct net_bridge_port *p; int err; list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); if (!vg->num_vlans) continue; NL_SET_ERR_MSG(extack, "MST mode can't be changed while VLANs exist"); return -EBUSY; } if (br_opt_get(br, BROPT_MST_ENABLED) == on) return 0; err = switchdev_port_attr_set(br->dev, &attr, extack); if (err && err != -EOPNOTSUPP) return err; if (on) static_branch_enable(&br_mst_used); else static_branch_disable(&br_mst_used); br_opt_toggle(br, BROPT_MST_ENABLED, on); return 0; } size_t br_mst_info_size(const struct net_bridge_vlan_group *vg) { DECLARE_BITMAP(seen, VLAN_N_VID) = { 0 }; const struct net_bridge_vlan *v; size_t sz; /* IFLA_BRIDGE_MST */ sz = nla_total_size(0); list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { if (test_bit(v->brvlan->msti, seen)) continue; /* IFLA_BRIDGE_MST_ENTRY */ sz += nla_total_size(0) + /* IFLA_BRIDGE_MST_ENTRY_MSTI */ nla_total_size(sizeof(u16)) + /* IFLA_BRIDGE_MST_ENTRY_STATE */ nla_total_size(sizeof(u8)); __set_bit(v->brvlan->msti, seen); } return sz; } int br_mst_fill_info(struct sk_buff *skb, const struct net_bridge_vlan_group *vg) { DECLARE_BITMAP(seen, VLAN_N_VID) = { 0 }; const struct net_bridge_vlan *v; struct nlattr *nest; int err = 0; list_for_each_entry(v, &vg->vlan_list, vlist) { if (test_bit(v->brvlan->msti, seen)) continue; nest = nla_nest_start_noflag(skb, IFLA_BRIDGE_MST_ENTRY); if (!nest || nla_put_u16(skb, IFLA_BRIDGE_MST_ENTRY_MSTI, v->brvlan->msti) || nla_put_u8(skb, IFLA_BRIDGE_MST_ENTRY_STATE, v->state)) { err = -EMSGSIZE; break; } nla_nest_end(skb, nest); __set_bit(v->brvlan->msti, seen); } return err; } static const struct nla_policy br_mst_nl_policy[IFLA_BRIDGE_MST_ENTRY_MAX + 1] = { [IFLA_BRIDGE_MST_ENTRY_MSTI] = NLA_POLICY_RANGE(NLA_U16, 1, /* 0 reserved for CST */ VLAN_N_VID - 1), [IFLA_BRIDGE_MST_ENTRY_STATE] = NLA_POLICY_RANGE(NLA_U8, BR_STATE_DISABLED, BR_STATE_BLOCKING), }; static int br_mst_process_one(struct net_bridge_port *p, const struct nlattr *attr, struct netlink_ext_ack *extack) { struct nlattr *tb[IFLA_BRIDGE_MST_ENTRY_MAX + 1]; u16 msti; u8 state; int err; err = nla_parse_nested(tb, IFLA_BRIDGE_MST_ENTRY_MAX, attr, br_mst_nl_policy, extack); if (err) return err; if (!tb[IFLA_BRIDGE_MST_ENTRY_MSTI]) { NL_SET_ERR_MSG_MOD(extack, "MSTI not specified"); return -EINVAL; } if (!tb[IFLA_BRIDGE_MST_ENTRY_STATE]) { NL_SET_ERR_MSG_MOD(extack, "State not specified"); return -EINVAL; } msti = nla_get_u16(tb[IFLA_BRIDGE_MST_ENTRY_MSTI]); state = nla_get_u8(tb[IFLA_BRIDGE_MST_ENTRY_STATE]); return br_mst_set_state(p, msti, state, extack); } int br_mst_process(struct net_bridge_port *p, const struct nlattr *mst_attr, struct netlink_ext_ack *extack) { struct nlattr *attr; int err, msts = 0; int rem; if (!br_opt_get(p->br, BROPT_MST_ENABLED)) { NL_SET_ERR_MSG_MOD(extack, "Can't modify MST state when MST is disabled"); return -EBUSY; } nla_for_each_nested(attr, mst_attr, rem) { switch (nla_type(attr)) { case IFLA_BRIDGE_MST_ENTRY: err = br_mst_process_one(p, attr, extack); break; default: continue; } msts++; if (err) break; } if (!msts) { NL_SET_ERR_MSG_MOD(extack, "Found no MST entries to process"); err = -EINVAL; } return err; } |
| 11 11 2 9 3 3 3 1 2 2 10 2 1 7 7 896 904 | 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 | /* Copyright (c) 2018, Mellanox Technologies All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include <crypto/aead.h> #include <linux/highmem.h> #include <linux/module.h> #include <linux/netdevice.h> #include <net/dst.h> #include <net/inet_connection_sock.h> #include <net/tcp.h> #include <net/tls.h> #include <linux/skbuff_ref.h> #include "tls.h" #include "trace.h" /* device_offload_lock is used to synchronize tls_dev_add * against NETDEV_DOWN notifications. */ static DECLARE_RWSEM(device_offload_lock); static struct workqueue_struct *destruct_wq __read_mostly; static LIST_HEAD(tls_device_list); static LIST_HEAD(tls_device_down_list); static DEFINE_SPINLOCK(tls_device_lock); static struct page *dummy_page; static void tls_device_free_ctx(struct tls_context *ctx) { if (ctx->tx_conf == TLS_HW) kfree(tls_offload_ctx_tx(ctx)); if (ctx->rx_conf == TLS_HW) kfree(tls_offload_ctx_rx(ctx)); tls_ctx_free(NULL, ctx); } static void tls_device_tx_del_task(struct work_struct *work) { struct tls_offload_context_tx *offload_ctx = container_of(work, struct tls_offload_context_tx, destruct_work); struct tls_context *ctx = offload_ctx->ctx; struct net_device *netdev; /* Safe, because this is the destroy flow, refcount is 0, so * tls_device_down can't store this field in parallel. */ netdev = rcu_dereference_protected(ctx->netdev, !refcount_read(&ctx->refcount)); netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_TX); dev_put(netdev); ctx->netdev = NULL; tls_device_free_ctx(ctx); } static void tls_device_queue_ctx_destruction(struct tls_context *ctx) { struct net_device *netdev; unsigned long flags; bool async_cleanup; spin_lock_irqsave(&tls_device_lock, flags); if (unlikely(!refcount_dec_and_test(&ctx->refcount))) { spin_unlock_irqrestore(&tls_device_lock, flags); return; } list_del(&ctx->list); /* Remove from tls_device_list / tls_device_down_list */ /* Safe, because this is the destroy flow, refcount is 0, so * tls_device_down can't store this field in parallel. */ netdev = rcu_dereference_protected(ctx->netdev, !refcount_read(&ctx->refcount)); async_cleanup = netdev && ctx->tx_conf == TLS_HW; if (async_cleanup) { struct tls_offload_context_tx *offload_ctx = tls_offload_ctx_tx(ctx); /* queue_work inside the spinlock * to make sure tls_device_down waits for that work. */ queue_work(destruct_wq, &offload_ctx->destruct_work); } spin_unlock_irqrestore(&tls_device_lock, flags); if (!async_cleanup) tls_device_free_ctx(ctx); } /* We assume that the socket is already connected */ static struct net_device *get_netdev_for_sock(struct sock *sk) { struct dst_entry *dst = sk_dst_get(sk); struct net_device *netdev = NULL; if (likely(dst)) { netdev = netdev_sk_get_lowest_dev(dst->dev, sk); dev_hold(netdev); } dst_release(dst); return netdev; } static void destroy_record(struct tls_record_info *record) { int i; for (i = 0; i < record->num_frags; i++) __skb_frag_unref(&record->frags[i], false); kfree(record); } static void delete_all_records(struct tls_offload_context_tx *offload_ctx) { struct tls_record_info *info, *temp; list_for_each_entry_safe(info, temp, &offload_ctx->records_list, list) { list_del(&info->list); destroy_record(info); } offload_ctx->retransmit_hint = NULL; } static void tls_icsk_clean_acked(struct sock *sk, u32 acked_seq) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_record_info *info, *temp; struct tls_offload_context_tx *ctx; u64 deleted_records = 0; unsigned long flags; if (!tls_ctx) return; ctx = tls_offload_ctx_tx(tls_ctx); spin_lock_irqsave(&ctx->lock, flags); info = ctx->retransmit_hint; if (info && !before(acked_seq, info->end_seq)) ctx->retransmit_hint = NULL; list_for_each_entry_safe(info, temp, &ctx->records_list, list) { if (before(acked_seq, info->end_seq)) break; list_del(&info->list); destroy_record(info); deleted_records++; } ctx->unacked_record_sn += deleted_records; spin_unlock_irqrestore(&ctx->lock, flags); } /* At this point, there should be no references on this * socket and no in-flight SKBs associated with this * socket, so it is safe to free all the resources. */ void tls_device_sk_destruct(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); tls_ctx->sk_destruct(sk); if (tls_ctx->tx_conf == TLS_HW) { if (ctx->open_record) destroy_record(ctx->open_record); delete_all_records(ctx); crypto_free_aead(ctx->aead_send); clean_acked_data_disable(inet_csk(sk)); } tls_device_queue_ctx_destruction(tls_ctx); } EXPORT_SYMBOL_GPL(tls_device_sk_destruct); void tls_device_free_resources_tx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); tls_free_partial_record(sk, tls_ctx); } void tls_offload_tx_resync_request(struct sock *sk, u32 got_seq, u32 exp_seq) { struct tls_context *tls_ctx = tls_get_ctx(sk); trace_tls_device_tx_resync_req(sk, got_seq, exp_seq); WARN_ON(test_and_set_bit(TLS_TX_SYNC_SCHED, &tls_ctx->flags)); } EXPORT_SYMBOL_GPL(tls_offload_tx_resync_request); static void tls_device_resync_tx(struct sock *sk, struct tls_context *tls_ctx, u32 seq) { struct net_device *netdev; int err = 0; u8 *rcd_sn; tcp_write_collapse_fence(sk); rcd_sn = tls_ctx->tx.rec_seq; trace_tls_device_tx_resync_send(sk, seq, rcd_sn); down_read(&device_offload_lock); netdev = rcu_dereference_protected(tls_ctx->netdev, lockdep_is_held(&device_offload_lock)); if (netdev) err = netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq, rcd_sn, TLS_OFFLOAD_CTX_DIR_TX); up_read(&device_offload_lock); if (err) return; clear_bit_unlock(TLS_TX_SYNC_SCHED, &tls_ctx->flags); } static void tls_append_frag(struct tls_record_info *record, struct page_frag *pfrag, int size) { skb_frag_t *frag; frag = &record->frags[record->num_frags - 1]; if (skb_frag_page(frag) == pfrag->page && skb_frag_off(frag) + skb_frag_size(frag) == pfrag->offset) { skb_frag_size_add(frag, size); } else { ++frag; skb_frag_fill_page_desc(frag, pfrag->page, pfrag->offset, size); ++record->num_frags; get_page(pfrag->page); } pfrag->offset += size; record->len += size; } static int tls_push_record(struct sock *sk, struct tls_context *ctx, struct tls_offload_context_tx *offload_ctx, struct tls_record_info *record, int flags) { struct tls_prot_info *prot = &ctx->prot_info; struct tcp_sock *tp = tcp_sk(sk); skb_frag_t *frag; int i; record->end_seq = tp->write_seq + record->len; list_add_tail_rcu(&record->list, &offload_ctx->records_list); offload_ctx->open_record = NULL; if (test_bit(TLS_TX_SYNC_SCHED, &ctx->flags)) tls_device_resync_tx(sk, ctx, tp->write_seq); tls_advance_record_sn(sk, prot, &ctx->tx); for (i = 0; i < record->num_frags; i++) { frag = &record->frags[i]; sg_unmark_end(&offload_ctx->sg_tx_data[i]); sg_set_page(&offload_ctx->sg_tx_data[i], skb_frag_page(frag), skb_frag_size(frag), skb_frag_off(frag)); sk_mem_charge(sk, skb_frag_size(frag)); get_page(skb_frag_page(frag)); } sg_mark_end(&offload_ctx->sg_tx_data[record->num_frags - 1]); /* all ready, send */ return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags); } static void tls_device_record_close(struct sock *sk, struct tls_context *ctx, struct tls_record_info *record, struct page_frag *pfrag, unsigned char record_type) { struct tls_prot_info *prot = &ctx->prot_info; struct page_frag dummy_tag_frag; /* append tag * device will fill in the tag, we just need to append a placeholder * use socket memory to improve coalescing (re-using a single buffer * increases frag count) * if we can't allocate memory now use the dummy page */ if (unlikely(pfrag->size - pfrag->offset < prot->tag_size) && !skb_page_frag_refill(prot->tag_size, pfrag, sk->sk_allocation)) { dummy_tag_frag.page = dummy_page; dummy_tag_frag.offset = 0; pfrag = &dummy_tag_frag; } tls_append_frag(record, pfrag, prot->tag_size); /* fill prepend */ tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]), record->len - prot->overhead_size, record_type); } static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx, struct page_frag *pfrag, size_t prepend_size) { struct tls_record_info *record; skb_frag_t *frag; record = kmalloc(sizeof(*record), GFP_KERNEL); if (!record) return -ENOMEM; frag = &record->frags[0]; skb_frag_fill_page_desc(frag, pfrag->page, pfrag->offset, prepend_size); get_page(pfrag->page); pfrag->offset += prepend_size; record->num_frags = 1; record->len = prepend_size; offload_ctx->open_record = record; return 0; } static int tls_do_allocation(struct sock *sk, struct tls_offload_context_tx *offload_ctx, struct page_frag *pfrag, size_t prepend_size) { int ret; if (!offload_ctx->open_record) { if (unlikely(!skb_page_frag_refill(prepend_size, pfrag, sk->sk_allocation))) { READ_ONCE(sk->sk_prot)->enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); return -ENOMEM; } ret = tls_create_new_record(offload_ctx, pfrag, prepend_size); if (ret) return ret; if (pfrag->size > pfrag->offset) return 0; } if (!sk_page_frag_refill(sk, pfrag)) return -ENOMEM; return 0; } static int tls_device_copy_data(void *addr, size_t bytes, struct iov_iter *i) { size_t pre_copy, nocache; pre_copy = ~((unsigned long)addr - 1) & (SMP_CACHE_BYTES - 1); if (pre_copy) { pre_copy = min(pre_copy, bytes); if (copy_from_iter(addr, pre_copy, i) != pre_copy) return -EFAULT; bytes -= pre_copy; addr += pre_copy; } nocache = round_down(bytes, SMP_CACHE_BYTES); if (copy_from_iter_nocache(addr, nocache, i) != nocache) return -EFAULT; bytes -= nocache; addr += nocache; if (bytes && copy_from_iter(addr, bytes, i) != bytes) return -EFAULT; return 0; } static int tls_push_data(struct sock *sk, struct iov_iter *iter, size_t size, int flags, unsigned char record_type) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_prot_info *prot = &tls_ctx->prot_info; struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); struct tls_record_info *record; int tls_push_record_flags; struct page_frag *pfrag; size_t orig_size = size; u32 max_open_record_len; bool more = false; bool done = false; int copy, rc = 0; long timeo; if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SPLICE_PAGES | MSG_EOR)) return -EOPNOTSUPP; if ((flags & (MSG_MORE | MSG_EOR)) == (MSG_MORE | MSG_EOR)) return -EINVAL; if (unlikely(sk->sk_err)) return -sk->sk_err; flags |= MSG_SENDPAGE_DECRYPTED; tls_push_record_flags = flags | MSG_MORE; timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); if (tls_is_partially_sent_record(tls_ctx)) { rc = tls_push_partial_record(sk, tls_ctx, flags); if (rc < 0) return rc; } pfrag = sk_page_frag(sk); /* TLS_HEADER_SIZE is not counted as part of the TLS record, and * we need to leave room for an authentication tag. */ max_open_record_len = TLS_MAX_PAYLOAD_SIZE + prot->prepend_size; do { rc = tls_do_allocation(sk, ctx, pfrag, prot->prepend_size); if (unlikely(rc)) { rc = sk_stream_wait_memory(sk, &timeo); if (!rc) continue; record = ctx->open_record; if (!record) break; handle_error: if (record_type != TLS_RECORD_TYPE_DATA) { /* avoid sending partial * record with type != * application_data */ size = orig_size; destroy_record(record); ctx->open_record = NULL; } else if (record->len > prot->prepend_size) { goto last_record; } break; } record = ctx->open_record; copy = min_t(size_t, size, max_open_record_len - record->len); if (copy && (flags & MSG_SPLICE_PAGES)) { struct page_frag zc_pfrag; struct page **pages = &zc_pfrag.page; size_t off; rc = iov_iter_extract_pages(iter, &pages, copy, 1, 0, &off); if (rc <= 0) { if (rc == 0) rc = -EIO; goto handle_error; } copy = rc; if (WARN_ON_ONCE(!sendpage_ok(zc_pfrag.page))) { iov_iter_revert(iter, copy); rc = -EIO; goto handle_error; } zc_pfrag.offset = off; zc_pfrag.size = copy; tls_append_frag(record, &zc_pfrag, copy); } else if (copy) { copy = min_t(size_t, copy, pfrag->size - pfrag->offset); rc = tls_device_copy_data(page_address(pfrag->page) + pfrag->offset, copy, iter); if (rc) goto handle_error; tls_append_frag(record, pfrag, copy); } size -= copy; if (!size) { last_record: tls_push_record_flags = flags; if (flags & MSG_MORE) { more = true; break; } done = true; } if (done || record->len >= max_open_record_len || (record->num_frags >= MAX_SKB_FRAGS - 1)) { tls_device_record_close(sk, tls_ctx, record, pfrag, record_type); rc = tls_push_record(sk, tls_ctx, ctx, record, tls_push_record_flags); if (rc < 0) break; } } while (!done); tls_ctx->pending_open_record_frags = more; if (orig_size - size > 0) rc = orig_size - size; return rc; } int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { unsigned char record_type = TLS_RECORD_TYPE_DATA; struct tls_context *tls_ctx = tls_get_ctx(sk); int rc; if (!tls_ctx->zerocopy_sendfile) msg->msg_flags &= ~MSG_SPLICE_PAGES; mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); if (unlikely(msg->msg_controllen)) { rc = tls_process_cmsg(sk, msg, &record_type); if (rc) goto out; } rc = tls_push_data(sk, &msg->msg_iter, size, msg->msg_flags, record_type); out: release_sock(sk); mutex_unlock(&tls_ctx->tx_lock); return rc; } void tls_device_splice_eof(struct socket *sock) { struct sock *sk = sock->sk; struct tls_context *tls_ctx = tls_get_ctx(sk); struct iov_iter iter = {}; if (!tls_is_partially_sent_record(tls_ctx)) return; mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); if (tls_is_partially_sent_record(tls_ctx)) { iov_iter_bvec(&iter, ITER_SOURCE, NULL, 0, 0); tls_push_data(sk, &iter, 0, 0, TLS_RECORD_TYPE_DATA); } release_sock(sk); mutex_unlock(&tls_ctx->tx_lock); } struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn) { u64 record_sn = context->hint_record_sn; struct tls_record_info *info, *last; info = context->retransmit_hint; if (!info || before(seq, info->end_seq - info->len)) { /* if retransmit_hint is irrelevant start * from the beginning of the list */ info = list_first_entry_or_null(&context->records_list, struct tls_record_info, list); if (!info) return NULL; /* send the start_marker record if seq number is before the * tls offload start marker sequence number. This record is * required to handle TCP packets which are before TLS offload * started. * And if it's not start marker, look if this seq number * belongs to the list. */ if (likely(!tls_record_is_start_marker(info))) { /* we have the first record, get the last record to see * if this seq number belongs to the list. */ last = list_last_entry(&context->records_list, struct tls_record_info, list); if (!between(seq, tls_record_start_seq(info), last->end_seq)) return NULL; } record_sn = context->unacked_record_sn; } /* We just need the _rcu for the READ_ONCE() */ rcu_read_lock(); list_for_each_entry_from_rcu(info, &context->records_list, list) { if (before(seq, info->end_seq)) { if (!context->retransmit_hint || after(info->end_seq, context->retransmit_hint->end_seq)) { context->hint_record_sn = record_sn; context->retransmit_hint = info; } *p_record_sn = record_sn; goto exit_rcu_unlock; } record_sn++; } info = NULL; exit_rcu_unlock: rcu_read_unlock(); return info; } EXPORT_SYMBOL(tls_get_record); static int tls_device_push_pending_record(struct sock *sk, int flags) { struct iov_iter iter; iov_iter_kvec(&iter, ITER_SOURCE, NULL, 0, 0); return tls_push_data(sk, &iter, 0, flags, TLS_RECORD_TYPE_DATA); } void tls_device_write_space(struct sock *sk, struct tls_context *ctx) { if (tls_is_partially_sent_record(ctx)) { gfp_t sk_allocation = sk->sk_allocation; WARN_ON_ONCE(sk->sk_write_pending); sk->sk_allocation = GFP_ATOMIC; tls_push_partial_record(sk, ctx, MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_DECRYPTED); sk->sk_allocation = sk_allocation; } } static void tls_device_resync_rx(struct tls_context *tls_ctx, struct sock *sk, u32 seq, u8 *rcd_sn) { struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx); struct net_device *netdev; trace_tls_device_rx_resync_send(sk, seq, rcd_sn, rx_ctx->resync_type); rcu_read_lock(); netdev = rcu_dereference(tls_ctx->netdev); if (netdev) netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq, rcd_sn, TLS_OFFLOAD_CTX_DIR_RX); rcu_read_unlock(); TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXDEVICERESYNC); } static bool tls_device_rx_resync_async(struct tls_offload_resync_async *resync_async, s64 resync_req, u32 *seq, u16 *rcd_delta) { u32 is_async = resync_req & RESYNC_REQ_ASYNC; u32 req_seq = resync_req >> 32; u32 req_end = req_seq + ((resync_req >> 16) & 0xffff); u16 i; *rcd_delta = 0; if (is_async) { /* shouldn't get to wraparound: * too long in async stage, something bad happened */ if (WARN_ON_ONCE(resync_async->rcd_delta == USHRT_MAX)) return false; /* asynchronous stage: log all headers seq such that * req_seq <= seq <= end_seq, and wait for real resync request */ if (before(*seq, req_seq)) return false; if (!after(*seq, req_end) && resync_async->loglen < TLS_DEVICE_RESYNC_ASYNC_LOGMAX) resync_async->log[resync_async->loglen++] = *seq; resync_async->rcd_delta++; return false; } /* synchronous stage: check against the logged entries and * proceed to check the next entries if no match was found */ for (i = 0; i < resync_async->loglen; i++) if (req_seq == resync_async->log[i] && atomic64_try_cmpxchg(&resync_async->req, &resync_req, 0)) { *rcd_delta = resync_async->rcd_delta - i; *seq = req_seq; resync_async->loglen = 0; resync_async->rcd_delta = 0; return true; } resync_async->loglen = 0; resync_async->rcd_delta = 0; if (req_seq == *seq && atomic64_try_cmpxchg(&resync_async->req, &resync_req, 0)) return true; return false; } void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_offload_context_rx *rx_ctx; u8 rcd_sn[TLS_MAX_REC_SEQ_SIZE]; u32 sock_data, is_req_pending; struct tls_prot_info *prot; s64 resync_req; u16 rcd_delta; u32 req_seq; if (tls_ctx->rx_conf != TLS_HW) return; if (unlikely(test_bit(TLS_RX_DEV_DEGRADED, &tls_ctx->flags))) return; prot = &tls_ctx->prot_info; rx_ctx = tls_offload_ctx_rx(tls_ctx); memcpy(rcd_sn, tls_ctx->rx.rec_seq, prot->rec_seq_size); switch (rx_ctx->resync_type) { case TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ: resync_req = atomic64_read(&rx_ctx->resync_req); req_seq = resync_req >> 32; seq += TLS_HEADER_SIZE - 1; is_req_pending = resync_req; if (likely(!is_req_pending) || req_seq != seq || !atomic64_try_cmpxchg(&rx_ctx->resync_req, &resync_req, 0)) return; break; case TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT: if (likely(!rx_ctx->resync_nh_do_now)) return; /* head of next rec is already in, note that the sock_inq will * include the currently parsed message when called from parser */ sock_data = tcp_inq(sk); if (sock_data > rcd_len) { trace_tls_device_rx_resync_nh_delay(sk, sock_data, rcd_len); return; } rx_ctx->resync_nh_do_now = 0; seq += rcd_len; tls_bigint_increment(rcd_sn, prot->rec_seq_size); break; case TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ_ASYNC: resync_req = atomic64_read(&rx_ctx->resync_async->req); is_req_pending = resync_req; if (likely(!is_req_pending)) return; if (!tls_device_rx_resync_async(rx_ctx->resync_async, resync_req, &seq, &rcd_delta)) return; tls_bigint_subtract(rcd_sn, rcd_delta); break; } tls_device_resync_rx(tls_ctx, sk, seq, rcd_sn); } static void tls_device_core_ctrl_rx_resync(struct tls_context *tls_ctx, struct tls_offload_context_rx *ctx, struct sock *sk, struct sk_buff *skb) { struct strp_msg *rxm; /* device will request resyncs by itself based on stream scan */ if (ctx->resync_type != TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT) return; /* already scheduled */ if (ctx->resync_nh_do_now) return; /* seen decrypted fragments since last fully-failed record */ if (ctx->resync_nh_reset) { ctx->resync_nh_reset = 0; ctx->resync_nh.decrypted_failed = 1; ctx->resync_nh.decrypted_tgt = TLS_DEVICE_RESYNC_NH_START_IVAL; return; } if (++ctx->resync_nh.decrypted_failed <= ctx->resync_nh.decrypted_tgt) return; /* doing resync, bump the next target in case it fails */ if (ctx->resync_nh.decrypted_tgt < TLS_DEVICE_RESYNC_NH_MAX_IVAL) ctx->resync_nh.decrypted_tgt *= 2; else ctx->resync_nh.decrypted_tgt += TLS_DEVICE_RESYNC_NH_MAX_IVAL; rxm = strp_msg(skb); /* head of next rec is already in, parser will sync for us */ if (tcp_inq(sk) > rxm->full_len) { trace_tls_device_rx_resync_nh_schedule(sk); ctx->resync_nh_do_now = 1; } else { struct tls_prot_info *prot = &tls_ctx->prot_info; u8 rcd_sn[TLS_MAX_REC_SEQ_SIZE]; memcpy(rcd_sn, tls_ctx->rx.rec_seq, prot->rec_seq_size); tls_bigint_increment(rcd_sn, prot->rec_seq_size); tls_device_resync_rx(tls_ctx, sk, tcp_sk(sk)->copied_seq, rcd_sn); } } static int tls_device_reencrypt(struct sock *sk, struct tls_context *tls_ctx) { struct tls_sw_context_rx *sw_ctx = tls_sw_ctx_rx(tls_ctx); const struct tls_cipher_desc *cipher_desc; int err, offset, copy, data_len, pos; struct sk_buff *skb, *skb_iter; struct scatterlist sg[1]; struct strp_msg *rxm; char *orig_buf, *buf; cipher_desc = get_cipher_desc(tls_ctx->crypto_recv.info.cipher_type); DEBUG_NET_WARN_ON_ONCE(!cipher_desc || !cipher_desc->offloadable); rxm = strp_msg(tls_strp_msg(sw_ctx)); orig_buf = kmalloc(rxm->full_len + TLS_HEADER_SIZE + cipher_desc->iv, sk->sk_allocation); if (!orig_buf) return -ENOMEM; buf = orig_buf; err = tls_strp_msg_cow(sw_ctx); if (unlikely(err)) goto free_buf; skb = tls_strp_msg(sw_ctx); rxm = strp_msg(skb); offset = rxm->offset; sg_init_table(sg, 1); sg_set_buf(&sg[0], buf, rxm->full_len + TLS_HEADER_SIZE + cipher_desc->iv); err = skb_copy_bits(skb, offset, buf, TLS_HEADER_SIZE + cipher_desc->iv); if (err) goto free_buf; /* We are interested only in the decrypted data not the auth */ err = decrypt_skb(sk, sg); if (err != -EBADMSG) goto free_buf; else err = 0; data_len = rxm->full_len - cipher_desc->tag; if (skb_pagelen(skb) > offset) { copy = min_t(int, skb_pagelen(skb) - offset, data_len); if (skb->decrypted) { err = skb_store_bits(skb, offset, buf, copy); if (err) goto free_buf; } offset += copy; buf += copy; } pos = skb_pagelen(skb); skb_walk_frags(skb, skb_iter) { int frag_pos; /* Practically all frags must belong to msg if reencrypt * is needed with current strparser and coalescing logic, * but strparser may "get optimized", so let's be safe. */ if (pos + skb_iter->len <= offset) goto done_with_frag; if (pos >= data_len + rxm->offset) break; frag_pos = offset - pos; copy = min_t(int, skb_iter->len - frag_pos, data_len + rxm->offset - offset); if (skb_iter->decrypted) { err = skb_store_bits(skb_iter, frag_pos, buf, copy); if (err) goto free_buf; } offset += copy; buf += copy; done_with_frag: pos += skb_iter->len; } free_buf: kfree(orig_buf); return err; } int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx) { struct tls_offload_context_rx *ctx = tls_offload_ctx_rx(tls_ctx); struct tls_sw_context_rx *sw_ctx = tls_sw_ctx_rx(tls_ctx); struct sk_buff *skb = tls_strp_msg(sw_ctx); struct strp_msg *rxm = strp_msg(skb); int is_decrypted, is_encrypted; if (!tls_strp_msg_mixed_decrypted(sw_ctx)) { is_decrypted = skb->decrypted; is_encrypted = !is_decrypted; } else { is_decrypted = 0; is_encrypted = 0; } trace_tls_device_decrypted(sk, tcp_sk(sk)->copied_seq - rxm->full_len, tls_ctx->rx.rec_seq, rxm->full_len, is_encrypted, is_decrypted); if (unlikely(test_bit(TLS_RX_DEV_DEGRADED, &tls_ctx->flags))) { if (likely(is_encrypted || is_decrypted)) return is_decrypted; /* After tls_device_down disables the offload, the next SKB will * likely have initial fragments decrypted, and final ones not * decrypted. We need to reencrypt that single SKB. */ return tls_device_reencrypt(sk, tls_ctx); } /* Return immediately if the record is either entirely plaintext or * entirely ciphertext. Otherwise handle reencrypt partially decrypted * record. */ if (is_decrypted) { ctx->resync_nh_reset = 1; return is_decrypted; } if (is_encrypted) { tls_device_core_ctrl_rx_resync(tls_ctx, ctx, sk, skb); return 0; } ctx->resync_nh_reset = 1; return tls_device_reencrypt(sk, tls_ctx); } static void tls_device_attach(struct tls_context *ctx, struct sock *sk, struct net_device *netdev) { if (sk->sk_destruct != tls_device_sk_destruct) { refcount_set(&ctx->refcount, 1); dev_hold(netdev); RCU_INIT_POINTER(ctx->netdev, netdev); spin_lock_irq(&tls_device_lock); list_add_tail(&ctx->list, &tls_device_list); spin_unlock_irq(&tls_device_lock); ctx->sk_destruct = sk->sk_destruct; smp_store_release(&sk->sk_destruct, tls_device_sk_destruct); } } static struct tls_offload_context_tx *alloc_offload_ctx_tx(struct tls_context *ctx) { struct tls_offload_context_tx *offload_ctx; __be64 rcd_sn; offload_ctx = kzalloc(sizeof(*offload_ctx), GFP_KERNEL); if (!offload_ctx) return NULL; INIT_WORK(&offload_ctx->destruct_work, tls_device_tx_del_task); INIT_LIST_HEAD(&offload_ctx->records_list); spin_lock_init(&offload_ctx->lock); sg_init_table(offload_ctx->sg_tx_data, ARRAY_SIZE(offload_ctx->sg_tx_data)); /* start at rec_seq - 1 to account for the start marker record */ memcpy(&rcd_sn, ctx->tx.rec_seq, sizeof(rcd_sn)); offload_ctx->unacked_record_sn = be64_to_cpu(rcd_sn) - 1; offload_ctx->ctx = ctx; return offload_ctx; } int tls_set_device_offload(struct sock *sk) { struct tls_record_info *start_marker_record; struct tls_offload_context_tx *offload_ctx; const struct tls_cipher_desc *cipher_desc; struct tls_crypto_info *crypto_info; struct tls_prot_info *prot; struct net_device *netdev; struct tls_context *ctx; char *iv, *rec_seq; int rc; ctx = tls_get_ctx(sk); prot = &ctx->prot_info; if (ctx->priv_ctx_tx) return -EEXIST; netdev = get_netdev_for_sock(sk); if (!netdev) { pr_err_ratelimited("%s: netdev not found\n", __func__); return -EINVAL; } if (!(netdev->features & NETIF_F_HW_TLS_TX)) { rc = -EOPNOTSUPP; goto release_netdev; } crypto_info = &ctx->crypto_send.info; if (crypto_info->version != TLS_1_2_VERSION) { rc = -EOPNOTSUPP; goto release_netdev; } cipher_desc = get_cipher_desc(crypto_info->cipher_type); if (!cipher_desc || !cipher_desc->offloadable) { rc = -EINVAL; goto release_netdev; } rc = init_prot_info(prot, crypto_info, cipher_desc); if (rc) goto release_netdev; iv = crypto_info_iv(crypto_info, cipher_desc); rec_seq = crypto_info_rec_seq(crypto_info, cipher_desc); memcpy(ctx->tx.iv + cipher_desc->salt, iv, cipher_desc->iv); memcpy(ctx->tx.rec_seq, rec_seq, cipher_desc->rec_seq); start_marker_record = kmalloc(sizeof(*start_marker_record), GFP_KERNEL); if (!start_marker_record) { rc = -ENOMEM; goto release_netdev; } offload_ctx = alloc_offload_ctx_tx(ctx); if (!offload_ctx) { rc = -ENOMEM; goto free_marker_record; } rc = tls_sw_fallback_init(sk, offload_ctx, crypto_info); if (rc) goto free_offload_ctx; start_marker_record->end_seq = tcp_sk(sk)->write_seq; start_marker_record->len = 0; start_marker_record->num_frags = 0; list_add_tail(&start_marker_record->list, &offload_ctx->records_list); clean_acked_data_enable(inet_csk(sk), &tls_icsk_clean_acked); ctx->push_pending_record = tls_device_push_pending_record; /* TLS offload is greatly simplified if we don't send * SKBs where only part of the payload needs to be encrypted. * So mark the last skb in the write queue as end of record. */ tcp_write_collapse_fence(sk); /* Avoid offloading if the device is down * We don't want to offload new flows after * the NETDEV_DOWN event * * device_offload_lock is taken in tls_devices's NETDEV_DOWN * handler thus protecting from the device going down before * ctx was added to tls_device_list. */ down_read(&device_offload_lock); if (!(netdev->flags & IFF_UP)) { rc = -EINVAL; goto release_lock; } ctx->priv_ctx_tx = offload_ctx; rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_TX, &ctx->crypto_send.info, tcp_sk(sk)->write_seq); trace_tls_device_offload_set(sk, TLS_OFFLOAD_CTX_DIR_TX, tcp_sk(sk)->write_seq, rec_seq, rc); if (rc) goto release_lock; tls_device_attach(ctx, sk, netdev); up_read(&device_offload_lock); /* following this assignment tls_is_skb_tx_device_offloaded * will return true and the context might be accessed * by the netdev's xmit function. */ smp_store_release(&sk->sk_validate_xmit_skb, tls_validate_xmit_skb); dev_put(netdev); return 0; release_lock: up_read(&device_offload_lock); clean_acked_data_disable(inet_csk(sk)); crypto_free_aead(offload_ctx->aead_send); free_offload_ctx: kfree(offload_ctx); ctx->priv_ctx_tx = NULL; free_marker_record: kfree(start_marker_record); release_netdev: dev_put(netdev); return rc; } int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) { struct tls12_crypto_info_aes_gcm_128 *info; struct tls_offload_context_rx *context; struct net_device *netdev; int rc = 0; if (ctx->crypto_recv.info.version != TLS_1_2_VERSION) return -EOPNOTSUPP; netdev = get_netdev_for_sock(sk); if (!netdev) { pr_err_ratelimited("%s: netdev not found\n", __func__); return -EINVAL; } if (!(netdev->features & NETIF_F_HW_TLS_RX)) { rc = -EOPNOTSUPP; goto release_netdev; } /* Avoid offloading if the device is down * We don't want to offload new flows after * the NETDEV_DOWN event * * device_offload_lock is taken in tls_devices's NETDEV_DOWN * handler thus protecting from the device going down before * ctx was added to tls_device_list. */ down_read(&device_offload_lock); if (!(netdev->flags & IFF_UP)) { rc = -EINVAL; goto release_lock; } context = kzalloc(sizeof(*context), GFP_KERNEL); if (!context) { rc = -ENOMEM; goto release_lock; } context->resync_nh_reset = 1; ctx->priv_ctx_rx = context; rc = tls_set_sw_offload(sk, 0); if (rc) goto release_ctx; rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_RX, &ctx->crypto_recv.info, tcp_sk(sk)->copied_seq); info = (void *)&ctx->crypto_recv.info; trace_tls_device_offload_set(sk, TLS_OFFLOAD_CTX_DIR_RX, tcp_sk(sk)->copied_seq, info->rec_seq, rc); if (rc) goto free_sw_resources; tls_device_attach(ctx, sk, netdev); up_read(&device_offload_lock); dev_put(netdev); return 0; free_sw_resources: up_read(&device_offload_lock); tls_sw_free_resources_rx(sk); down_read(&device_offload_lock); release_ctx: ctx->priv_ctx_rx = NULL; release_lock: up_read(&device_offload_lock); release_netdev: dev_put(netdev); return rc; } void tls_device_offload_cleanup_rx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct net_device *netdev; down_read(&device_offload_lock); netdev = rcu_dereference_protected(tls_ctx->netdev, lockdep_is_held(&device_offload_lock)); if (!netdev) goto out; netdev->tlsdev_ops->tls_dev_del(netdev, tls_ctx, TLS_OFFLOAD_CTX_DIR_RX); if (tls_ctx->tx_conf != TLS_HW) { dev_put(netdev); rcu_assign_pointer(tls_ctx->netdev, NULL); } else { set_bit(TLS_RX_DEV_CLOSED, &tls_ctx->flags); } out: up_read(&device_offload_lock); tls_sw_release_resources_rx(sk); } static int tls_device_down(struct net_device *netdev) { struct tls_context *ctx, *tmp; unsigned long flags; LIST_HEAD(list); /* Request a write lock to block new offload attempts */ down_write(&device_offload_lock); spin_lock_irqsave(&tls_device_lock, flags); list_for_each_entry_safe(ctx, tmp, &tls_device_list, list) { struct net_device *ctx_netdev = rcu_dereference_protected(ctx->netdev, lockdep_is_held(&device_offload_lock)); if (ctx_netdev != netdev || !refcount_inc_not_zero(&ctx->refcount)) continue; list_move(&ctx->list, &list); } spin_unlock_irqrestore(&tls_device_lock, flags); list_for_each_entry_safe(ctx, tmp, &list, list) { /* Stop offloaded TX and switch to the fallback. * tls_is_skb_tx_device_offloaded will return false. */ WRITE_ONCE(ctx->sk->sk_validate_xmit_skb, tls_validate_xmit_skb_sw); /* Stop the RX and TX resync. * tls_dev_resync must not be called after tls_dev_del. */ rcu_assign_pointer(ctx->netdev, NULL); /* Start skipping the RX resync logic completely. */ set_bit(TLS_RX_DEV_DEGRADED, &ctx->flags); /* Sync with inflight packets. After this point: * TX: no non-encrypted packets will be passed to the driver. * RX: resync requests from the driver will be ignored. */ synchronize_net(); /* Release the offload context on the driver side. */ if (ctx->tx_conf == TLS_HW) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_TX); if (ctx->rx_conf == TLS_HW && !test_bit(TLS_RX_DEV_CLOSED, &ctx->flags)) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_RX); dev_put(netdev); /* Move the context to a separate list for two reasons: * 1. When the context is deallocated, list_del is called. * 2. It's no longer an offloaded context, so we don't want to * run offload-specific code on this context. */ spin_lock_irqsave(&tls_device_lock, flags); list_move_tail(&ctx->list, &tls_device_down_list); spin_unlock_irqrestore(&tls_device_lock, flags); /* Device contexts for RX and TX will be freed in on sk_destruct * by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW. * Now release the ref taken above. */ if (refcount_dec_and_test(&ctx->refcount)) { /* sk_destruct ran after tls_device_down took a ref, and * it returned early. Complete the destruction here. */ list_del(&ctx->list); tls_device_free_ctx(ctx); } } up_write(&device_offload_lock); flush_workqueue(destruct_wq); return NOTIFY_DONE; } static int tls_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!dev->tlsdev_ops && !(dev->features & (NETIF_F_HW_TLS_RX | NETIF_F_HW_TLS_TX))) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: case NETDEV_FEAT_CHANGE: if (netif_is_bond_master(dev)) return NOTIFY_DONE; if ((dev->features & NETIF_F_HW_TLS_RX) && !dev->tlsdev_ops->tls_dev_resync) return NOTIFY_BAD; if (dev->tlsdev_ops && dev->tlsdev_ops->tls_dev_add && dev->tlsdev_ops->tls_dev_del) return NOTIFY_DONE; else return NOTIFY_BAD; case NETDEV_DOWN: return tls_device_down(dev); } return NOTIFY_DONE; } static struct notifier_block tls_dev_notifier = { .notifier_call = tls_dev_event, }; int __init tls_device_init(void) { int err; dummy_page = alloc_page(GFP_KERNEL); if (!dummy_page) return -ENOMEM; destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); if (!destruct_wq) { err = -ENOMEM; goto err_free_dummy; } err = register_netdevice_notifier(&tls_dev_notifier); if (err) goto err_destroy_wq; return 0; err_destroy_wq: destroy_workqueue(destruct_wq); err_free_dummy: put_page(dummy_page); return err; } void __exit tls_device_cleanup(void) { unregister_netdevice_notifier(&tls_dev_notifier); destroy_workqueue(destruct_wq); clean_acked_data_flush(); put_page(dummy_page); } |
| 2 3 4 3 2 3 2 2 4 1 1 2 6 3 3 3 2 2 1 3 3 11 12 12 4 9 2 1 8 10 13 1 3 9 2 10 1 2 1 3 7 10 4 4 2 2 1 3 5 6 6 1 1 10 1 1 1 1 1 6 1 5 1 4 1 1 1 1 1 5 3 3 3 1 2 1 1 4 1 2 1 7 7 6 4 2 6 1 1 6 1 5 1 4 3 3 13 7 5 5 7 9 1 9 1 2 1 2 3 3 1 1 1 3 21 1 20 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 13 1 1 1 1 1 2 1 1 1 1 1 1 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 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 | /* * af_llc.c - LLC User Interface SAPs * Description: * Functions in this module are implementation of socket based llc * communications for the Linux operating system. Support of llc class * one and class two is provided via SOCK_DGRAM and SOCK_STREAM * respectively. * * An llc2 connection is (mac + sap), only one llc2 sap connection * is allowed per mac. Though one sap may have multiple mac + sap * connections. * * Copyright (c) 2001 by Jay Schulist <jschlst@samba.org> * 2002-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/compiler.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <net/llc.h> #include <net/llc_sap.h> #include <net/llc_pdu.h> #include <net/llc_conn.h> #include <net/tcp_states.h> /* remember: uninitialized global data is zeroed because its in .bss */ static u16 llc_ui_sap_last_autoport = LLC_SAP_DYN_START; static u16 llc_ui_sap_link_no_max[256]; static struct sockaddr_llc llc_ui_addrnull; static const struct proto_ops llc_ui_ops; static bool llc_ui_wait_for_conn(struct sock *sk, long timeout); static int llc_ui_wait_for_disc(struct sock *sk, long timeout); static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout); #if 0 #define dprintk(args...) printk(KERN_DEBUG args) #else #define dprintk(args...) do {} while (0) #endif /* Maybe we'll add some more in the future. */ #define LLC_CMSG_PKTINFO 1 /** * llc_ui_next_link_no - return the next unused link number for a sap * @sap: Address of sap to get link number from. * * Return the next unused link number for a given sap. */ static inline u16 llc_ui_next_link_no(int sap) { return llc_ui_sap_link_no_max[sap]++; } /** * llc_proto_type - return eth protocol for ARP header type * @arphrd: ARP header type. * * Given an ARP header type return the corresponding ethernet protocol. */ static inline __be16 llc_proto_type(u16 arphrd) { return htons(ETH_P_802_2); } /** * llc_ui_addr_null - determines if a address structure is null * @addr: Address to test if null. */ static inline u8 llc_ui_addr_null(struct sockaddr_llc *addr) { return !memcmp(addr, &llc_ui_addrnull, sizeof(*addr)); } /** * llc_ui_header_len - return length of llc header based on operation * @sk: Socket which contains a valid llc socket type. * @addr: Complete sockaddr_llc structure received from the user. * * Provide the length of the llc header depending on what kind of * operation the user would like to perform and the type of socket. * Returns the correct llc header length. */ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr) { u8 rc = LLC_PDU_LEN_U; if (addr->sllc_test) rc = LLC_PDU_LEN_U; else if (addr->sllc_xid) /* We need to expand header to sizeof(struct llc_xid_info) * since llc_pdu_init_as_xid_cmd() sets 4,5,6 bytes of LLC header * as XID PDU. In llc_ui_sendmsg() we reserved header size and then * filled all other space with user data. If we won't reserve this * bytes, llc_pdu_init_as_xid_cmd() will overwrite user data */ rc = LLC_PDU_LEN_U_XID; else if (sk->sk_type == SOCK_STREAM) rc = LLC_PDU_LEN_I; return rc; } /** * llc_ui_send_data - send data via reliable llc2 connection * @sk: Connection the socket is using. * @skb: Data the user wishes to send. * @noblock: can we block waiting for data? * * Send data via reliable llc2 connection. * Returns 0 upon success, non-zero if action did not succeed. * * This function always consumes a reference to the skb. */ static int llc_ui_send_data(struct sock* sk, struct sk_buff *skb, int noblock) { struct llc_sock* llc = llc_sk(sk); if (unlikely(llc_data_accept_state(llc->state) || llc->remote_busy_flag || llc->p_flag)) { long timeout = sock_sndtimeo(sk, noblock); int rc; rc = llc_ui_wait_for_busy_core(sk, timeout); if (rc) { kfree_skb(skb); return rc; } } return llc_build_and_send_pkt(sk, skb); } static void llc_ui_sk_init(struct socket *sock, struct sock *sk) { sock_graft(sk, sock); sk->sk_type = sock->type; sock->ops = &llc_ui_ops; } static struct proto llc_proto = { .name = "LLC", .owner = THIS_MODULE, .obj_size = sizeof(struct llc_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, }; /** * llc_ui_create - alloc and init a new llc_ui socket * @net: network namespace (must be default network) * @sock: Socket to initialize and attach allocated sk to. * @protocol: Unused. * @kern: on behalf of kernel or userspace * * Allocate and initialize a new llc_ui socket, validate the user wants a * socket type we have available. * Returns 0 upon success, negative upon failure. */ static int llc_ui_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; int rc = -ESOCKTNOSUPPORT; if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; if (likely(sock->type == SOCK_DGRAM || sock->type == SOCK_STREAM)) { rc = -ENOMEM; sk = llc_sk_alloc(net, PF_LLC, GFP_KERNEL, &llc_proto, kern); if (sk) { rc = 0; llc_ui_sk_init(sock, sk); } } return rc; } /** * llc_ui_release - shutdown socket * @sock: Socket to release. * * Shutdown and deallocate an existing socket. */ static int llc_ui_release(struct socket *sock) { struct sock *sk = sock->sk; struct llc_sock *llc; if (unlikely(sk == NULL)) goto out; sock_hold(sk); lock_sock(sk); llc = llc_sk(sk); dprintk("%s: closing local(%02X) remote(%02X)\n", __func__, llc->laddr.lsap, llc->daddr.lsap); if (!llc_send_disc(sk)) llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo); if (!sock_flag(sk, SOCK_ZAPPED)) { struct llc_sap *sap = llc->sap; /* Hold this for release_sock(), so that llc_backlog_rcv() * could still use it. */ llc_sap_hold(sap); llc_sap_remove_socket(llc->sap, sk); release_sock(sk); llc_sap_put(sap); } else { release_sock(sk); } netdev_put(llc->dev, &llc->dev_tracker); sock_put(sk); sock_orphan(sk); sock->sk = NULL; llc_sk_free(sk); out: return 0; } /** * llc_ui_autoport - provide dynamically allocate SAP number * * Provide the caller with a dynamically allocated SAP number according * to the rules that are set in this function. Returns: 0, upon failure, * SAP number otherwise. */ static int llc_ui_autoport(void) { struct llc_sap *sap; int i, tries = 0; while (tries < LLC_SAP_DYN_TRIES) { for (i = llc_ui_sap_last_autoport; i < LLC_SAP_DYN_STOP; i += 2) { sap = llc_sap_find(i); if (!sap) { llc_ui_sap_last_autoport = i + 2; goto out; } llc_sap_put(sap); } llc_ui_sap_last_autoport = LLC_SAP_DYN_START; tries++; } i = 0; out: return i; } /** * llc_ui_autobind - automatically bind a socket to a sap * @sock: socket to bind * @addr: address to connect to * * Used by llc_ui_connect and llc_ui_sendmsg when the user hasn't * specifically used llc_ui_bind to bind to an specific address/sap * * Returns: 0 upon success, negative otherwise. */ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); struct net_device *dev = NULL; struct llc_sap *sap; int rc = -EINVAL; if (!sock_flag(sk, SOCK_ZAPPED)) goto out; if (!addr->sllc_arphrd) addr->sllc_arphrd = ARPHRD_ETHER; if (addr->sllc_arphrd != ARPHRD_ETHER) goto out; rc = -ENODEV; if (sk->sk_bound_dev_if) { dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); if (dev && addr->sllc_arphrd != dev->type) { dev_put(dev); dev = NULL; } } else dev = dev_getfirstbyhwtype(&init_net, addr->sllc_arphrd); if (!dev) goto out; rc = -EUSERS; llc->laddr.lsap = llc_ui_autoport(); if (!llc->laddr.lsap) goto out; rc = -EBUSY; /* some other network layer is using the sap */ sap = llc_sap_open(llc->laddr.lsap, NULL); if (!sap) goto out; /* Note: We do not expect errors from this point. */ llc->dev = dev; netdev_tracker_alloc(llc->dev, &llc->dev_tracker, GFP_KERNEL); dev = NULL; memcpy(llc->laddr.mac, llc->dev->dev_addr, IFHWADDRLEN); memcpy(&llc->addr, addr, sizeof(llc->addr)); /* assign new connection to its SAP */ llc_sap_add_socket(sap, sk); sock_reset_flag(sk, SOCK_ZAPPED); rc = 0; out: dev_put(dev); return rc; } /** * llc_ui_bind - bind a socket to a specific address. * @sock: Socket to bind an address to. * @uaddr: Address the user wants the socket bound to. * @addrlen: Length of the uaddr structure. * * Bind a socket to a specific address. For llc a user is able to bind to * a specific sap only or mac + sap. * If the user desires to bind to a specific mac + sap, it is possible to * have multiple sap connections via multiple macs. * Bind and autobind for that matter must enforce the correct sap usage * otherwise all hell will break loose. * Returns: 0 upon success, negative otherwise. */ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) { struct sockaddr_llc *addr = (struct sockaddr_llc *)uaddr; struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); struct net_device *dev = NULL; struct llc_sap *sap; int rc = -EINVAL; lock_sock(sk); if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr))) goto out; rc = -EAFNOSUPPORT; if (!addr->sllc_arphrd) addr->sllc_arphrd = ARPHRD_ETHER; if (unlikely(addr->sllc_family != AF_LLC || addr->sllc_arphrd != ARPHRD_ETHER)) goto out; dprintk("%s: binding %02X\n", __func__, addr->sllc_sap); rc = -ENODEV; rcu_read_lock(); if (sk->sk_bound_dev_if) { dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if); if (dev) { if (is_zero_ether_addr(addr->sllc_mac)) memcpy(addr->sllc_mac, dev->dev_addr, IFHWADDRLEN); if (addr->sllc_arphrd != dev->type || !ether_addr_equal(addr->sllc_mac, dev->dev_addr)) { rc = -EINVAL; dev = NULL; } } } else { dev = dev_getbyhwaddr_rcu(&init_net, addr->sllc_arphrd, addr->sllc_mac); } dev_hold(dev); rcu_read_unlock(); if (!dev) goto out; if (!addr->sllc_sap) { rc = -EUSERS; addr->sllc_sap = llc_ui_autoport(); if (!addr->sllc_sap) goto out; } sap = llc_sap_find(addr->sllc_sap); if (!sap) { sap = llc_sap_open(addr->sllc_sap, NULL); rc = -EBUSY; /* some other network layer is using the sap */ if (!sap) goto out; } else { struct llc_addr laddr, daddr; struct sock *ask; memset(&laddr, 0, sizeof(laddr)); memset(&daddr, 0, sizeof(daddr)); /* * FIXME: check if the address is multicast, * only SOCK_DGRAM can do this. */ memcpy(laddr.mac, addr->sllc_mac, IFHWADDRLEN); laddr.lsap = addr->sllc_sap; rc = -EADDRINUSE; /* mac + sap clash. */ ask = llc_lookup_established(sap, &daddr, &laddr, &init_net); if (ask) { sock_put(ask); goto out_put; } } /* Note: We do not expect errors from this point. */ llc->dev = dev; netdev_tracker_alloc(llc->dev, &llc->dev_tracker, GFP_KERNEL); dev = NULL; llc->laddr.lsap = addr->sllc_sap; memcpy(llc->laddr.mac, addr->sllc_mac, IFHWADDRLEN); memcpy(&llc->addr, addr, sizeof(llc->addr)); /* assign new connection to its SAP */ llc_sap_add_socket(sap, sk); sock_reset_flag(sk, SOCK_ZAPPED); rc = 0; out_put: llc_sap_put(sap); out: dev_put(dev); release_sock(sk); return rc; } /** * llc_ui_shutdown - shutdown a connect llc2 socket. * @sock: Socket to shutdown. * @how: What part of the socket to shutdown. * * Shutdown a connected llc2 socket. Currently this function only supports * shutting down both sends and receives (2), we could probably make this * function such that a user can shutdown only half the connection but not * right now. * Returns: 0 upon success, negative otherwise. */ static int llc_ui_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; int rc = -ENOTCONN; lock_sock(sk); if (unlikely(sk->sk_state != TCP_ESTABLISHED)) goto out; rc = -EINVAL; if (how != 2) goto out; rc = llc_send_disc(sk); if (!rc) rc = llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo); /* Wake up anyone sleeping in poll */ sk->sk_state_change(sk); out: release_sock(sk); return rc; } /** * llc_ui_connect - Connect to a remote llc2 mac + sap. * @sock: Socket which will be connected to the remote destination. * @uaddr: Remote and possibly the local address of the new connection. * @addrlen: Size of uaddr structure. * @flags: Operational flags specified by the user. * * Connect to a remote llc2 mac + sap. The caller must specify the * destination mac and address to connect to. If the user hasn't previously * called bind(2) with a smac the address of the first interface of the * specified arp type will be used. * This function will autobind if user did not previously call bind. * Returns: 0 upon success, negative otherwise. */ static int llc_ui_connect(struct socket *sock, struct sockaddr *uaddr, int addrlen, int flags) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); struct sockaddr_llc *addr = (struct sockaddr_llc *)uaddr; int rc = -EINVAL; lock_sock(sk); if (unlikely(addrlen != sizeof(*addr))) goto out; rc = -EAFNOSUPPORT; if (unlikely(addr->sllc_family != AF_LLC)) goto out; if (unlikely(sk->sk_type != SOCK_STREAM)) goto out; rc = -EALREADY; if (unlikely(sock->state == SS_CONNECTING)) goto out; /* bind connection to sap if user hasn't done it. */ if (sock_flag(sk, SOCK_ZAPPED)) { /* bind to sap with null dev, exclusive */ rc = llc_ui_autobind(sock, addr); if (rc) goto out; } llc->daddr.lsap = addr->sllc_sap; memcpy(llc->daddr.mac, addr->sllc_mac, IFHWADDRLEN); sock->state = SS_CONNECTING; sk->sk_state = TCP_SYN_SENT; llc->link = llc_ui_next_link_no(llc->sap->laddr.lsap); rc = llc_establish_connection(sk, llc->dev->dev_addr, addr->sllc_mac, addr->sllc_sap); if (rc) { dprintk("%s: llc_ui_send_conn failed :-(\n", __func__); sock->state = SS_UNCONNECTED; sk->sk_state = TCP_CLOSE; goto out; } if (sk->sk_state == TCP_SYN_SENT) { const long timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); if (!timeo || !llc_ui_wait_for_conn(sk, timeo)) goto out; rc = sock_intr_errno(timeo); if (signal_pending(current)) goto out; } if (sk->sk_state == TCP_CLOSE) goto sock_error; sock->state = SS_CONNECTED; rc = 0; out: release_sock(sk); return rc; sock_error: rc = sock_error(sk) ? : -ECONNABORTED; sock->state = SS_UNCONNECTED; goto out; } /** * llc_ui_listen - allow a normal socket to accept incoming connections * @sock: Socket to allow incoming connections on. * @backlog: Number of connections to queue. * * Allow a normal socket to accept incoming connections. * Returns 0 upon success, negative otherwise. */ static int llc_ui_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; int rc = -EINVAL; lock_sock(sk); if (unlikely(sock->state != SS_UNCONNECTED)) goto out; rc = -EOPNOTSUPP; if (unlikely(sk->sk_type != SOCK_STREAM)) goto out; rc = -EAGAIN; if (sock_flag(sk, SOCK_ZAPPED)) goto out; rc = 0; if (!(unsigned int)backlog) /* BSDism */ backlog = 1; sk->sk_max_ack_backlog = backlog; if (sk->sk_state != TCP_LISTEN) { sk->sk_ack_backlog = 0; sk->sk_state = TCP_LISTEN; } sk->sk_socket->flags |= __SO_ACCEPTCON; out: release_sock(sk); return rc; } static int llc_ui_wait_for_disc(struct sock *sk, long timeout) { DEFINE_WAIT_FUNC(wait, woken_wake_function); int rc = 0; add_wait_queue(sk_sleep(sk), &wait); while (1) { if (sk_wait_event(sk, &timeout, READ_ONCE(sk->sk_state) == TCP_CLOSE, &wait)) break; rc = -ERESTARTSYS; if (signal_pending(current)) break; rc = -EAGAIN; if (!timeout) break; rc = 0; } remove_wait_queue(sk_sleep(sk), &wait); return rc; } static bool llc_ui_wait_for_conn(struct sock *sk, long timeout) { DEFINE_WAIT_FUNC(wait, woken_wake_function); add_wait_queue(sk_sleep(sk), &wait); while (1) { if (sk_wait_event(sk, &timeout, READ_ONCE(sk->sk_state) != TCP_SYN_SENT, &wait)) break; if (signal_pending(current) || !timeout) break; } remove_wait_queue(sk_sleep(sk), &wait); return timeout; } static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct llc_sock *llc = llc_sk(sk); int rc; add_wait_queue(sk_sleep(sk), &wait); while (1) { rc = 0; if (sk_wait_event(sk, &timeout, (READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN) || (!llc_data_accept_state(llc->state) && !llc->remote_busy_flag && !llc->p_flag), &wait)) break; rc = -ERESTARTSYS; if (signal_pending(current)) break; rc = -EAGAIN; if (!timeout) break; } remove_wait_queue(sk_sleep(sk), &wait); return rc; } static int llc_wait_data(struct sock *sk, long timeo) { int rc; while (1) { /* * POSIX 1003.1g mandates this order. */ rc = sock_error(sk); if (rc) break; rc = 0; if (sk->sk_shutdown & RCV_SHUTDOWN) break; rc = -EAGAIN; if (!timeo) break; rc = sock_intr_errno(timeo); if (signal_pending(current)) break; rc = 0; if (sk_wait_data(sk, &timeo, NULL)) break; } return rc; } static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(skb->sk); if (llc->cmsg_flags & LLC_CMSG_PKTINFO) { struct llc_pktinfo info; memset(&info, 0, sizeof(info)); info.lpi_ifindex = llc_sk(skb->sk)->dev->ifindex; llc_pdu_decode_dsap(skb, &info.lpi_sap); llc_pdu_decode_da(skb, info.lpi_mac); put_cmsg(msg, SOL_LLC, LLC_OPT_PKTINFO, sizeof(info), &info); } } /** * llc_ui_accept - accept a new incoming connection. * @sock: Socket which connections arrive on. * @newsock: Socket to move incoming connection to. * @arg: User specified arguments * * Accept a new incoming connection. * Returns 0 upon success, negative otherwise. */ static int llc_ui_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { struct sock *sk = sock->sk, *newsk; struct llc_sock *llc, *newllc; struct sk_buff *skb; int rc = -EOPNOTSUPP; dprintk("%s: accepting on %02X\n", __func__, llc_sk(sk)->laddr.lsap); lock_sock(sk); if (unlikely(sk->sk_type != SOCK_STREAM)) goto out; rc = -EINVAL; if (unlikely(sock->state != SS_UNCONNECTED || sk->sk_state != TCP_LISTEN)) goto out; /* wait for a connection to arrive. */ if (skb_queue_empty(&sk->sk_receive_queue)) { rc = llc_wait_data(sk, sk->sk_rcvtimeo); if (rc) goto out; } dprintk("%s: got a new connection on %02X\n", __func__, llc_sk(sk)->laddr.lsap); skb = skb_dequeue(&sk->sk_receive_queue); rc = -EINVAL; if (!skb->sk) goto frees; rc = 0; newsk = skb->sk; /* attach connection to a new socket. */ llc_ui_sk_init(newsock, newsk); sock_reset_flag(newsk, SOCK_ZAPPED); newsk->sk_state = TCP_ESTABLISHED; newsock->state = SS_CONNECTED; llc = llc_sk(sk); newllc = llc_sk(newsk); memcpy(&newllc->addr, &llc->addr, sizeof(newllc->addr)); newllc->link = llc_ui_next_link_no(newllc->laddr.lsap); /* put original socket back into a clean listen state. */ sk->sk_state = TCP_LISTEN; sk_acceptq_removed(sk); dprintk("%s: ok success on %02X, client on %02X\n", __func__, llc_sk(sk)->addr.sllc_sap, newllc->daddr.lsap); frees: kfree_skb(skb); out: release_sock(sk); return rc; } /** * llc_ui_recvmsg - copy received data to the socket user. * @sock: Socket to copy data from. * @msg: Various user space related information. * @len: Size of user buffer. * @flags: User specified flags. * * Copy received data to the socket user. * Returns non-negative upon success, negative otherwise. */ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { DECLARE_SOCKADDR(struct sockaddr_llc *, uaddr, msg->msg_name); const int nonblock = flags & MSG_DONTWAIT; struct sk_buff *skb = NULL; struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); size_t copied = 0; u32 peek_seq = 0; u32 *seq, skb_len; unsigned long used; int target; /* Read at least this many bytes */ long timeo; lock_sock(sk); copied = -ENOTCONN; if (unlikely(sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN)) goto out; timeo = sock_rcvtimeo(sk, nonblock); seq = &llc->copied_seq; if (flags & MSG_PEEK) { peek_seq = llc->copied_seq; seq = &peek_seq; } target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); copied = 0; do { u32 offset; /* * We need to check signals first, to get correct SIGURG * handling. FIXME: Need to check this doesn't impact 1003.1g * and move it down to the bottom of the loop */ if (signal_pending(current)) { if (copied) break; copied = timeo ? sock_intr_errno(timeo) : -EAGAIN; break; } /* Next get a buffer. */ skb = skb_peek(&sk->sk_receive_queue); if (skb) { offset = *seq; goto found_ok_skb; } /* Well, if we have backlog, try to process it now yet. */ if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break; if (copied) { if (sk->sk_err || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || !timeo || (flags & MSG_PEEK)) break; } else { if (sock_flag(sk, SOCK_DONE)) break; if (sk->sk_err) { copied = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_CLOSE) { if (!sock_flag(sk, SOCK_DONE)) { /* * This occurs when user tries to read * from never connected socket. */ copied = -ENOTCONN; break; } break; } if (!timeo) { copied = -EAGAIN; break; } } if (copied >= target) { /* Do not sleep, just process backlog. */ release_sock(sk); lock_sock(sk); } else sk_wait_data(sk, &timeo, NULL); if ((flags & MSG_PEEK) && peek_seq != llc->copied_seq) { net_dbg_ratelimited("LLC(%s:%d): Application bug, race in MSG_PEEK\n", current->comm, task_pid_nr(current)); peek_seq = llc->copied_seq; } continue; found_ok_skb: skb_len = skb->len; /* Ok so how much can we use? */ used = skb->len - offset; if (len < used) used = len; if (!(flags & MSG_TRUNC)) { int rc = skb_copy_datagram_msg(skb, offset, msg, used); if (rc) { /* Exception. Bailout! */ if (!copied) copied = -EFAULT; break; } } *seq += used; copied += used; len -= used; /* For non stream protcols we get one packet per recvmsg call */ if (sk->sk_type != SOCK_STREAM) goto copy_uaddr; if (!(flags & MSG_PEEK)) { skb_unlink(skb, &sk->sk_receive_queue); kfree_skb(skb); *seq = 0; } /* Partial read */ if (used + offset < skb_len) continue; } while (len > 0); out: release_sock(sk); return copied; copy_uaddr: if (uaddr != NULL && skb != NULL) { memcpy(uaddr, llc_ui_skb_cb(skb), sizeof(*uaddr)); msg->msg_namelen = sizeof(*uaddr); } if (llc_sk(sk)->cmsg_flags) llc_cmsg_rcv(msg, skb); if (!(flags & MSG_PEEK)) { skb_unlink(skb, &sk->sk_receive_queue); kfree_skb(skb); *seq = 0; } goto out; } /** * llc_ui_sendmsg - Transmit data provided by the socket user. * @sock: Socket to transmit data from. * @msg: Various user related information. * @len: Length of data to transmit. * * Transmit data provided by the socket user. * Returns non-negative upon success, negative otherwise. */ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); int flags = msg->msg_flags; int noblock = flags & MSG_DONTWAIT; int rc = -EINVAL, copied = 0, hdrlen, hh_len; struct sk_buff *skb = NULL; struct net_device *dev; size_t size = 0; dprintk("%s: sending from %02X to %02X\n", __func__, llc->laddr.lsap, llc->daddr.lsap); lock_sock(sk); if (addr) { if (msg->msg_namelen < sizeof(*addr)) goto out; } else { if (llc_ui_addr_null(&llc->addr)) goto out; addr = &llc->addr; } /* must bind connection to sap if user hasn't done it. */ if (sock_flag(sk, SOCK_ZAPPED)) { /* bind to sap with null dev, exclusive. */ rc = llc_ui_autobind(sock, addr); if (rc) goto out; } dev = llc->dev; hh_len = LL_RESERVED_SPACE(dev); hdrlen = llc_ui_header_len(sk, addr); size = hdrlen + len; size = min_t(size_t, size, READ_ONCE(dev->mtu)); copied = size - hdrlen; rc = -EINVAL; if (copied < 0) goto out; release_sock(sk); skb = sock_alloc_send_skb(sk, hh_len + size, noblock, &rc); lock_sock(sk); if (!skb) goto out; if (sock_flag(sk, SOCK_ZAPPED) || llc->dev != dev || hdrlen != llc_ui_header_len(sk, addr) || hh_len != LL_RESERVED_SPACE(dev) || size > READ_ONCE(dev->mtu)) goto out; skb->dev = dev; skb->protocol = llc_proto_type(addr->sllc_arphrd); skb_reserve(skb, hh_len + hdrlen); rc = memcpy_from_msg(skb_put(skb, copied), msg, copied); if (rc) goto out; if (sk->sk_type == SOCK_DGRAM || addr->sllc_ua) { llc_build_and_send_ui_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); skb = NULL; goto out; } if (addr->sllc_test) { llc_build_and_send_test_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); skb = NULL; goto out; } if (addr->sllc_xid) { llc_build_and_send_xid_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); skb = NULL; goto out; } rc = -ENOPROTOOPT; if (!(sk->sk_type == SOCK_STREAM && !addr->sllc_ua)) goto out; rc = llc_ui_send_data(sk, skb, noblock); skb = NULL; out: kfree_skb(skb); if (rc) dprintk("%s: failed sending from %02X to %02X: %d\n", __func__, llc->laddr.lsap, llc->daddr.lsap, rc); release_sock(sk); return rc ? : copied; } /** * llc_ui_getname - return the address info of a socket * @sock: Socket to get address of. * @uaddr: Address structure to return information. * @peer: Does user want local or remote address information. * * Return the address information of a socket. */ static int llc_ui_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sockaddr_llc sllc; struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); int rc = -EBADF; memset(&sllc, 0, sizeof(sllc)); lock_sock(sk); if (sock_flag(sk, SOCK_ZAPPED)) goto out; if (peer) { rc = -ENOTCONN; if (sk->sk_state != TCP_ESTABLISHED) goto out; if(llc->dev) sllc.sllc_arphrd = llc->dev->type; sllc.sllc_sap = llc->daddr.lsap; memcpy(&sllc.sllc_mac, &llc->daddr.mac, IFHWADDRLEN); } else { rc = -EINVAL; if (!llc->sap) goto out; sllc.sllc_sap = llc->sap->laddr.lsap; if (llc->dev) { sllc.sllc_arphrd = llc->dev->type; memcpy(&sllc.sllc_mac, llc->dev->dev_addr, IFHWADDRLEN); } } sllc.sllc_family = AF_LLC; memcpy(uaddr, &sllc, sizeof(sllc)); rc = sizeof(sllc); out: release_sock(sk); return rc; } /** * llc_ui_ioctl - io controls for PF_LLC * @sock: Socket to get/set info * @cmd: command * @arg: optional argument for cmd * * get/set info on llc sockets */ static int llc_ui_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { return -ENOIOCTLCMD; } /** * llc_ui_setsockopt - set various connection specific parameters. * @sock: Socket to set options on. * @level: Socket level user is requesting operations on. * @optname: Operation name. * @optval: User provided operation data. * @optlen: Length of optval. * * Set various connection specific parameters. */ static int llc_ui_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); unsigned int opt; int rc = -EINVAL; lock_sock(sk); if (unlikely(level != SOL_LLC || optlen != sizeof(int))) goto out; rc = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (rc) goto out; rc = -EINVAL; switch (optname) { case LLC_OPT_RETRY: if (opt > LLC_OPT_MAX_RETRY) goto out; llc->n2 = opt; break; case LLC_OPT_SIZE: if (opt > LLC_OPT_MAX_SIZE) goto out; llc->n1 = opt; break; case LLC_OPT_ACK_TMR_EXP: if (opt > LLC_OPT_MAX_ACK_TMR_EXP) goto out; llc->ack_timer.expire = opt * HZ; break; case LLC_OPT_P_TMR_EXP: if (opt > LLC_OPT_MAX_P_TMR_EXP) goto out; llc->pf_cycle_timer.expire = opt * HZ; break; case LLC_OPT_REJ_TMR_EXP: if (opt > LLC_OPT_MAX_REJ_TMR_EXP) goto out; llc->rej_sent_timer.expire = opt * HZ; break; case LLC_OPT_BUSY_TMR_EXP: if (opt > LLC_OPT_MAX_BUSY_TMR_EXP) goto out; llc->busy_state_timer.expire = opt * HZ; break; case LLC_OPT_TX_WIN: if (opt > LLC_OPT_MAX_WIN) goto out; llc->k = opt; break; case LLC_OPT_RX_WIN: if (opt > LLC_OPT_MAX_WIN) goto out; llc->rw = opt; break; case LLC_OPT_PKTINFO: if (opt) llc->cmsg_flags |= LLC_CMSG_PKTINFO; else llc->cmsg_flags &= ~LLC_CMSG_PKTINFO; break; default: rc = -ENOPROTOOPT; goto out; } rc = 0; out: release_sock(sk); return rc; } /** * llc_ui_getsockopt - get connection specific socket info * @sock: Socket to get information from. * @level: Socket level user is requesting operations on. * @optname: Operation name. * @optval: Variable to return operation data in. * @optlen: Length of optval. * * Get connection specific socket information. */ static int llc_ui_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); int val = 0, len = 0, rc = -EINVAL; lock_sock(sk); if (unlikely(level != SOL_LLC)) goto out; rc = get_user(len, optlen); if (rc) goto out; rc = -EINVAL; if (len != sizeof(int)) goto out; switch (optname) { case LLC_OPT_RETRY: val = llc->n2; break; case LLC_OPT_SIZE: val = llc->n1; break; case LLC_OPT_ACK_TMR_EXP: val = llc->ack_timer.expire / HZ; break; case LLC_OPT_P_TMR_EXP: val = llc->pf_cycle_timer.expire / HZ; break; case LLC_OPT_REJ_TMR_EXP: val = llc->rej_sent_timer.expire / HZ; break; case LLC_OPT_BUSY_TMR_EXP: val = llc->busy_state_timer.expire / HZ; break; case LLC_OPT_TX_WIN: val = llc->k; break; case LLC_OPT_RX_WIN: val = llc->rw; break; case LLC_OPT_PKTINFO: val = (llc->cmsg_flags & LLC_CMSG_PKTINFO) != 0; break; default: rc = -ENOPROTOOPT; goto out; } rc = 0; if (put_user(len, optlen) || copy_to_user(optval, &val, len)) rc = -EFAULT; out: release_sock(sk); return rc; } static const struct net_proto_family llc_ui_family_ops = { .family = PF_LLC, .create = llc_ui_create, .owner = THIS_MODULE, }; static const struct proto_ops llc_ui_ops = { .family = PF_LLC, .owner = THIS_MODULE, .release = llc_ui_release, .bind = llc_ui_bind, .connect = llc_ui_connect, .socketpair = sock_no_socketpair, .accept = llc_ui_accept, .getname = llc_ui_getname, .poll = datagram_poll, .ioctl = llc_ui_ioctl, .listen = llc_ui_listen, .shutdown = llc_ui_shutdown, .setsockopt = llc_ui_setsockopt, .getsockopt = llc_ui_getsockopt, .sendmsg = llc_ui_sendmsg, .recvmsg = llc_ui_recvmsg, .mmap = sock_no_mmap, }; static const char llc_proc_err_msg[] __initconst = KERN_CRIT "LLC: Unable to register the proc_fs entries\n"; static const char llc_sysctl_err_msg[] __initconst = KERN_CRIT "LLC: Unable to register the sysctl entries\n"; static const char llc_sock_err_msg[] __initconst = KERN_CRIT "LLC: Unable to register the network family\n"; static int __init llc2_init(void) { int rc = proto_register(&llc_proto, 0); if (rc != 0) goto out; llc_build_offset_table(); llc_station_init(); llc_ui_sap_last_autoport = LLC_SAP_DYN_START; rc = llc_proc_init(); if (rc != 0) { printk(llc_proc_err_msg); goto out_station; } rc = llc_sysctl_init(); if (rc) { printk(llc_sysctl_err_msg); goto out_proc; } rc = sock_register(&llc_ui_family_ops); if (rc) { printk(llc_sock_err_msg); goto out_sysctl; } llc_add_pack(LLC_DEST_SAP, llc_sap_handler); llc_add_pack(LLC_DEST_CONN, llc_conn_handler); out: return rc; out_sysctl: llc_sysctl_exit(); out_proc: llc_proc_exit(); out_station: llc_station_exit(); proto_unregister(&llc_proto); goto out; } static void __exit llc2_exit(void) { llc_station_exit(); llc_remove_pack(LLC_DEST_SAP); llc_remove_pack(LLC_DEST_CONN); sock_unregister(PF_LLC); llc_proc_exit(); llc_sysctl_exit(); proto_unregister(&llc_proto); } module_init(llc2_init); module_exit(llc2_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Procom 1997, Jay Schullist 2001, Arnaldo C. Melo 2001-2003"); MODULE_DESCRIPTION("IEEE 802.2 PF_LLC support"); MODULE_ALIAS_NETPROTO(PF_LLC); |
| 6 6 6 6 6 6 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * This only handles 32bit MTRR on 32bit hosts. This is strictly wrong * because MTRRs can span up to 40 bits (36bits on most modern x86) */ #include <linux/export.h> #include <linux/init.h> #include <linux/io.h> #include <linux/mm.h> #include <linux/cc_platform.h> #include <asm/processor-flags.h> #include <asm/cacheinfo.h> #include <asm/cpufeature.h> #include <asm/hypervisor.h> #include <asm/mshyperv.h> #include <asm/tlbflush.h> #include <asm/mtrr.h> #include <asm/msr.h> #include <asm/memtype.h> #include "mtrr.h" struct fixed_range_block { int base_msr; /* start address of an MTRR block */ int ranges; /* number of MTRRs in this block */ }; static struct fixed_range_block fixed_range_blocks[] = { { MSR_MTRRfix64K_00000, 1 }, /* one 64k MTRR */ { MSR_MTRRfix16K_80000, 2 }, /* two 16k MTRRs */ { MSR_MTRRfix4K_C0000, 8 }, /* eight 4k MTRRs */ {} }; struct cache_map { u64 start; u64 end; u64 flags; u64 type:8; u64 fixed:1; }; bool mtrr_debug; static int __init mtrr_param_setup(char *str) { int rc = 0; if (!str) return -EINVAL; if (!strcmp(str, "debug")) mtrr_debug = true; else rc = -EINVAL; return rc; } early_param("mtrr", mtrr_param_setup); /* * CACHE_MAP_MAX is the maximum number of memory ranges in cache_map, where * no 2 adjacent ranges have the same cache mode (those would be merged). * The number is based on the worst case: * - no two adjacent fixed MTRRs share the same cache mode * - one variable MTRR is spanning a huge area with mode WB * - 255 variable MTRRs with mode UC all overlap with the WB MTRR, creating 2 * additional ranges each (result like "ababababa...aba" with a = WB, b = UC), * accounting for MTRR_MAX_VAR_RANGES * 2 - 1 range entries * - a TOP_MEM2 area (even with overlapping an UC MTRR can't add 2 range entries * to the possible maximum, as it always starts at 4GB, thus it can't be in * the middle of that MTRR, unless that MTRR starts at 0, which would remove * the initial "a" from the "abababa" pattern above) * The map won't contain ranges with no matching MTRR (those fall back to the * default cache mode). */ #define CACHE_MAP_MAX (MTRR_NUM_FIXED_RANGES + MTRR_MAX_VAR_RANGES * 2) static struct cache_map init_cache_map[CACHE_MAP_MAX] __initdata; static struct cache_map *cache_map __refdata = init_cache_map; static unsigned int cache_map_size = CACHE_MAP_MAX; static unsigned int cache_map_n; static unsigned int cache_map_fixed; static unsigned long smp_changes_mask; static int mtrr_state_set; u64 mtrr_tom2; struct mtrr_state_type mtrr_state; EXPORT_SYMBOL_GPL(mtrr_state); /* Reserved bits in the high portion of the MTRRphysBaseN MSR. */ u32 phys_hi_rsvd; /* * BIOS is expected to clear MtrrFixDramModEn bit, see for example * "BIOS and Kernel Developer's Guide for the AMD Athlon 64 and AMD * Opteron Processors" (26094 Rev. 3.30 February 2006), section * "13.2.1.2 SYSCFG Register": "The MtrrFixDramModEn bit should be set * to 1 during BIOS initialization of the fixed MTRRs, then cleared to * 0 for operation." */ static inline void k8_check_syscfg_dram_mod_en(void) { u32 lo, hi; if (!((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0x0f))) return; if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return; rdmsr(MSR_AMD64_SYSCFG, lo, hi); if (lo & K8_MTRRFIXRANGE_DRAM_MODIFY) { pr_err(FW_WARN "MTRR: CPU %u: SYSCFG[MtrrFixDramModEn]" " not cleared by BIOS, clearing this bit\n", smp_processor_id()); lo &= ~K8_MTRRFIXRANGE_DRAM_MODIFY; mtrr_wrmsr(MSR_AMD64_SYSCFG, lo, hi); } } /* Get the size of contiguous MTRR range */ static u64 get_mtrr_size(u64 mask) { u64 size; mask |= (u64)phys_hi_rsvd << 32; size = -mask; return size; } static u8 get_var_mtrr_state(unsigned int reg, u64 *start, u64 *size) { struct mtrr_var_range *mtrr = mtrr_state.var_ranges + reg; if (!(mtrr->mask_lo & MTRR_PHYSMASK_V)) return MTRR_TYPE_INVALID; *start = (((u64)mtrr->base_hi) << 32) + (mtrr->base_lo & PAGE_MASK); *size = get_mtrr_size((((u64)mtrr->mask_hi) << 32) + (mtrr->mask_lo & PAGE_MASK)); return mtrr->base_lo & MTRR_PHYSBASE_TYPE; } static u8 get_effective_type(u8 type1, u8 type2) { if (type1 == MTRR_TYPE_UNCACHABLE || type2 == MTRR_TYPE_UNCACHABLE) return MTRR_TYPE_UNCACHABLE; if ((type1 == MTRR_TYPE_WRBACK && type2 == MTRR_TYPE_WRTHROUGH) || (type1 == MTRR_TYPE_WRTHROUGH && type2 == MTRR_TYPE_WRBACK)) return MTRR_TYPE_WRTHROUGH; if (type1 != type2) return MTRR_TYPE_UNCACHABLE; return type1; } static void rm_map_entry_at(int idx) { cache_map_n--; if (cache_map_n > idx) { memmove(cache_map + idx, cache_map + idx + 1, sizeof(*cache_map) * (cache_map_n - idx)); } } /* * Add an entry into cache_map at a specific index. Merges adjacent entries if * appropriate. Return the number of merges for correcting the scan index * (this is needed as merging will reduce the number of entries, which will * result in skipping entries in future iterations if the scan index isn't * corrected). * Note that the corrected index can never go below -1 (resulting in being 0 in * the next scan iteration), as "2" is returned only if the current index is * larger than zero. */ static int add_map_entry_at(u64 start, u64 end, u8 type, int idx) { bool merge_prev = false, merge_next = false; if (start >= end) return 0; if (idx > 0) { struct cache_map *prev = cache_map + idx - 1; if (!prev->fixed && start == prev->end && type == prev->type) merge_prev = true; } if (idx < cache_map_n) { struct cache_map *next = cache_map + idx; if (!next->fixed && end == next->start && type == next->type) merge_next = true; } if (merge_prev && merge_next) { cache_map[idx - 1].end = cache_map[idx].end; rm_map_entry_at(idx); return 2; } if (merge_prev) { cache_map[idx - 1].end = end; return 1; } if (merge_next) { cache_map[idx].start = start; return 1; } /* Sanity check: the array should NEVER be too small! */ if (cache_map_n == cache_map_size) { WARN(1, "MTRR cache mode memory map exhausted!\n"); cache_map_n = cache_map_fixed; return 0; } if (cache_map_n > idx) { memmove(cache_map + idx + 1, cache_map + idx, sizeof(*cache_map) * (cache_map_n - idx)); } cache_map[idx].start = start; cache_map[idx].end = end; cache_map[idx].type = type; cache_map[idx].fixed = 0; cache_map_n++; return 0; } /* Clear a part of an entry. Return 1 if start of entry is still valid. */ static int clr_map_range_at(u64 start, u64 end, int idx) { int ret = start != cache_map[idx].start; u64 tmp; if (start == cache_map[idx].start && end == cache_map[idx].end) { rm_map_entry_at(idx); } else if (start == cache_map[idx].start) { cache_map[idx].start = end; } else if (end == cache_map[idx].end) { cache_map[idx].end = start; } else { tmp = cache_map[idx].end; cache_map[idx].end = start; add_map_entry_at(end, tmp, cache_map[idx].type, idx + 1); } return ret; } /* * Add MTRR to the map. The current map is scanned and each part of the MTRR * either overlapping with an existing entry or with a hole in the map is * handled separately. */ static void add_map_entry(u64 start, u64 end, u8 type) { u8 new_type, old_type; u64 tmp; int i; for (i = 0; i < cache_map_n && start < end; i++) { if (start >= cache_map[i].end) continue; if (start < cache_map[i].start) { /* Region start has no overlap. */ tmp = min(end, cache_map[i].start); i -= add_map_entry_at(start, tmp, type, i); start = tmp; continue; } new_type = get_effective_type(type, cache_map[i].type); old_type = cache_map[i].type; if (cache_map[i].fixed || new_type == old_type) { /* Cut off start of new entry. */ start = cache_map[i].end; continue; } /* Handle only overlapping part of region. */ tmp = min(end, cache_map[i].end); i += clr_map_range_at(start, tmp, i); i -= add_map_entry_at(start, tmp, new_type, i); start = tmp; } /* Add rest of region after last map entry (rest might be empty). */ add_map_entry_at(start, end, type, i); } /* Add variable MTRRs to cache map. */ static void map_add_var(void) { u64 start, size; unsigned int i; u8 type; /* * Add AMD TOP_MEM2 area. Can't be added in mtrr_build_map(), as it * needs to be added again when rebuilding the map due to potentially * having moved as a result of variable MTRRs for memory below 4GB. */ if (mtrr_tom2) { add_map_entry(BIT_ULL(32), mtrr_tom2, MTRR_TYPE_WRBACK); cache_map[cache_map_n - 1].fixed = 1; } for (i = 0; i < num_var_ranges; i++) { type = get_var_mtrr_state(i, &start, &size); if (type != MTRR_TYPE_INVALID) add_map_entry(start, start + size, type); } } /* * Rebuild map by replacing variable entries. Needs to be called when MTRR * registers are being changed after boot, as such changes could include * removals of registers, which are complicated to handle without rebuild of * the map. */ void generic_rebuild_map(void) { if (mtrr_if != &generic_mtrr_ops) return; cache_map_n = cache_map_fixed; map_add_var(); } static unsigned int __init get_cache_map_size(void) { return cache_map_fixed + 2 * num_var_ranges + (mtrr_tom2 != 0); } /* Build the cache_map containing the cache modes per memory range. */ void __init mtrr_build_map(void) { u64 start, end, size; unsigned int i; u8 type; /* Add fixed MTRRs, optimize for adjacent entries with same type. */ if (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED) { /* * Start with 64k size fixed entries, preset 1st one (hence the * loop below is starting with index 1). */ start = 0; end = size = 0x10000; type = mtrr_state.fixed_ranges[0]; for (i = 1; i < MTRR_NUM_FIXED_RANGES; i++) { /* 8 64k entries, then 16 16k ones, rest 4k. */ if (i == 8 || i == 24) size >>= 2; if (mtrr_state.fixed_ranges[i] != type) { add_map_entry(start, end, type); start = end; type = mtrr_state.fixed_ranges[i]; } end += size; } add_map_entry(start, end, type); } /* Mark fixed, they take precedence. */ for (i = 0; i < cache_map_n; i++) cache_map[i].fixed = 1; cache_map_fixed = cache_map_n; map_add_var(); pr_info("MTRR map: %u entries (%u fixed + %u variable; max %u), built from %u variable MTRRs\n", cache_map_n, cache_map_fixed, cache_map_n - cache_map_fixed, get_cache_map_size(), num_var_ranges + (mtrr_tom2 != 0)); if (mtrr_debug) { for (i = 0; i < cache_map_n; i++) { pr_info("%3u: %016llx-%016llx %s\n", i, cache_map[i].start, cache_map[i].end - 1, mtrr_attrib_to_str(cache_map[i].type)); } } } /* Copy the cache_map from __initdata memory to dynamically allocated one. */ void __init mtrr_copy_map(void) { unsigned int new_size = get_cache_map_size(); if (!mtrr_state.enabled || !new_size) { cache_map = NULL; return; } mutex_lock(&mtrr_mutex); cache_map = kcalloc(new_size, sizeof(*cache_map), GFP_KERNEL); if (cache_map) { memmove(cache_map, init_cache_map, cache_map_n * sizeof(*cache_map)); cache_map_size = new_size; } else { mtrr_state.enabled = 0; pr_err("MTRRs disabled due to allocation failure for lookup map.\n"); } mutex_unlock(&mtrr_mutex); } /** * mtrr_overwrite_state - set static MTRR state * * Used to set MTRR state via different means (e.g. with data obtained from * a hypervisor). * Is allowed only for special cases when running virtualized. Must be called * from the x86_init.hyper.init_platform() hook. It can be called only once. * The MTRR state can't be changed afterwards. To ensure that, X86_FEATURE_MTRR * is cleared. * * @var: MTRR variable range array to use * @num_var: length of the @var array * @def_type: default caching type */ void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var, mtrr_type def_type) { unsigned int i; /* Only allowed to be called once before mtrr_bp_init(). */ if (WARN_ON_ONCE(mtrr_state_set)) return; /* Only allowed when running virtualized. */ if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) return; /* * Only allowed for special virtualization cases: * - when running as Hyper-V, SEV-SNP guest using vTOM * - when running as Xen PV guest * - when running as SEV-SNP or TDX guest to avoid unnecessary * VMM communication/Virtualization exceptions (#VC, #VE) */ if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && !hv_is_isolation_supported() && !cpu_feature_enabled(X86_FEATURE_XENPV) && !cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) return; /* Disable MTRR in order to disable MTRR modifications. */ setup_clear_cpu_cap(X86_FEATURE_MTRR); if (var) { if (num_var > MTRR_MAX_VAR_RANGES) { pr_warn("Trying to overwrite MTRR state with %u variable entries\n", num_var); num_var = MTRR_MAX_VAR_RANGES; } for (i = 0; i < num_var; i++) mtrr_state.var_ranges[i] = var[i]; num_var_ranges = num_var; } mtrr_state.def_type = def_type; mtrr_state.enabled |= MTRR_STATE_MTRR_ENABLED; mtrr_state_set = 1; } static u8 type_merge(u8 type, u8 new_type, u8 *uniform) { u8 effective_type; if (type == MTRR_TYPE_INVALID) return new_type; effective_type = get_effective_type(type, new_type); if (type != effective_type) *uniform = 0; return effective_type; } /** * mtrr_type_lookup - look up memory type in MTRR * * @start: Begin of the physical address range * @end: End of the physical address range * @uniform: output argument: * - 1: the returned MTRR type is valid for the whole region * - 0: otherwise * * Return Values: * MTRR_TYPE_(type) - The effective MTRR type for the region * MTRR_TYPE_INVALID - MTRR is disabled */ u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform) { u8 type = MTRR_TYPE_INVALID; unsigned int i; if (!mtrr_state_set) { /* Uniformity is unknown. */ *uniform = 0; return MTRR_TYPE_UNCACHABLE; } *uniform = 1; if (!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED)) return MTRR_TYPE_UNCACHABLE; for (i = 0; i < cache_map_n && start < end; i++) { /* Region after current map entry? -> continue with next one. */ if (start >= cache_map[i].end) continue; /* Start of region not covered by current map entry? */ if (start < cache_map[i].start) { /* At least some part of region has default type. */ type = type_merge(type, mtrr_state.def_type, uniform); /* End of region not covered, too? -> lookup done. */ if (end <= cache_map[i].start) return type; } /* At least part of region covered by map entry. */ type = type_merge(type, cache_map[i].type, uniform); start = cache_map[i].end; } /* End of region past last entry in map? -> use default type. */ if (start < end) type = type_merge(type, mtrr_state.def_type, uniform); return type; } /* Get the MSR pair relating to a var range */ static void get_mtrr_var_range(unsigned int index, struct mtrr_var_range *vr) { rdmsr(MTRRphysBase_MSR(index), vr->base_lo, vr->base_hi); rdmsr(MTRRphysMask_MSR(index), vr->mask_lo, vr->mask_hi); } /* Fill the MSR pair relating to a var range */ void fill_mtrr_var_range(unsigned int index, u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi) { struct mtrr_var_range *vr; vr = mtrr_state.var_ranges; vr[index].base_lo = base_lo; vr[index].base_hi = base_hi; vr[index].mask_lo = mask_lo; vr[index].mask_hi = mask_hi; } static void get_fixed_ranges(mtrr_type *frs) { unsigned int *p = (unsigned int *)frs; int i; k8_check_syscfg_dram_mod_en(); rdmsr(MSR_MTRRfix64K_00000, p[0], p[1]); for (i = 0; i < 2; i++) rdmsr(MSR_MTRRfix16K_80000 + i, p[2 + i * 2], p[3 + i * 2]); for (i = 0; i < 8; i++) rdmsr(MSR_MTRRfix4K_C0000 + i, p[6 + i * 2], p[7 + i * 2]); } void mtrr_save_fixed_ranges(void *info) { if (boot_cpu_has(X86_FEATURE_MTRR)) get_fixed_ranges(mtrr_state.fixed_ranges); } static unsigned __initdata last_fixed_start; static unsigned __initdata last_fixed_end; static mtrr_type __initdata last_fixed_type; static void __init print_fixed_last(void) { if (!last_fixed_end) return; pr_info(" %05X-%05X %s\n", last_fixed_start, last_fixed_end - 1, mtrr_attrib_to_str(last_fixed_type)); last_fixed_end = 0; } static void __init update_fixed_last(unsigned base, unsigned end, mtrr_type type) { last_fixed_start = base; last_fixed_end = end; last_fixed_type = type; } static void __init print_fixed(unsigned base, unsigned step, const mtrr_type *types) { unsigned i; for (i = 0; i < 8; ++i, ++types, base += step) { if (last_fixed_end == 0) { update_fixed_last(base, base + step, *types); continue; } if (last_fixed_end == base && last_fixed_type == *types) { last_fixed_end = base + step; continue; } /* new segments: gap or different type */ print_fixed_last(); update_fixed_last(base, base + step, *types); } } static void __init print_mtrr_state(void) { unsigned int i; int high_width; pr_info("MTRR default type: %s\n", mtrr_attrib_to_str(mtrr_state.def_type)); if (mtrr_state.have_fixed) { pr_info("MTRR fixed ranges %sabled:\n", ((mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) && (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) ? "en" : "dis"); print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0); for (i = 0; i < 2; ++i) print_fixed(0x80000 + i * 0x20000, 0x04000, mtrr_state.fixed_ranges + (i + 1) * 8); for (i = 0; i < 8; ++i) print_fixed(0xC0000 + i * 0x08000, 0x01000, mtrr_state.fixed_ranges + (i + 3) * 8); /* tail */ print_fixed_last(); } pr_info("MTRR variable ranges %sabled:\n", mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis"); high_width = (boot_cpu_data.x86_phys_bits - (32 - PAGE_SHIFT) + 3) / 4; for (i = 0; i < num_var_ranges; ++i) { if (mtrr_state.var_ranges[i].mask_lo & MTRR_PHYSMASK_V) pr_info(" %u base %0*X%05X000 mask %0*X%05X000 %s\n", i, high_width, mtrr_state.var_ranges[i].base_hi, mtrr_state.var_ranges[i].base_lo >> 12, high_width, mtrr_state.var_ranges[i].mask_hi, mtrr_state.var_ranges[i].mask_lo >> 12, mtrr_attrib_to_str(mtrr_state.var_ranges[i].base_lo & MTRR_PHYSBASE_TYPE)); else pr_info(" %u disabled\n", i); } if (mtrr_tom2) pr_info("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20); } /* Grab all of the MTRR state for this CPU into *state */ bool __init get_mtrr_state(void) { struct mtrr_var_range *vrs; unsigned lo, dummy; unsigned int i; vrs = mtrr_state.var_ranges; rdmsr(MSR_MTRRcap, lo, dummy); mtrr_state.have_fixed = lo & MTRR_CAP_FIX; for (i = 0; i < num_var_ranges; i++) get_mtrr_var_range(i, &vrs[i]); if (mtrr_state.have_fixed) get_fixed_ranges(mtrr_state.fixed_ranges); rdmsr(MSR_MTRRdefType, lo, dummy); mtrr_state.def_type = lo & MTRR_DEF_TYPE_TYPE; mtrr_state.enabled = (lo & MTRR_DEF_TYPE_ENABLE) >> MTRR_STATE_SHIFT; if (amd_special_default_mtrr()) { unsigned low, high; /* TOP_MEM2 */ rdmsr(MSR_K8_TOP_MEM2, low, high); mtrr_tom2 = high; mtrr_tom2 <<= 32; mtrr_tom2 |= low; mtrr_tom2 &= 0xffffff800000ULL; } if (mtrr_debug) print_mtrr_state(); mtrr_state_set = 1; return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED); } /* Some BIOS's are messed up and don't set all MTRRs the same! */ void __init mtrr_state_warn(void) { unsigned long mask = smp_changes_mask; if (!mask) return; if (mask & MTRR_CHANGE_MASK_FIXED) pr_warn("mtrr: your CPUs had inconsistent fixed MTRR settings\n"); if (mask & MTRR_CHANGE_MASK_VARIABLE) pr_warn("mtrr: your CPUs had inconsistent variable MTRR settings\n"); if (mask & MTRR_CHANGE_MASK_DEFTYPE) pr_warn("mtrr: your CPUs had inconsistent MTRRdefType settings\n"); pr_info("mtrr: probably your BIOS does not setup all CPUs.\n"); pr_info("mtrr: corrected configuration.\n"); } /* * Doesn't attempt to pass an error out to MTRR users * because it's quite complicated in some cases and probably not * worth it because the best error handling is to ignore it. */ void mtrr_wrmsr(unsigned msr, unsigned a, unsigned b) { if (wrmsr_safe(msr, a, b) < 0) { pr_err("MTRR: CPU %u: Writing MSR %x to %x:%x failed\n", smp_processor_id(), msr, a, b); } } /** * set_fixed_range - checks & updates a fixed-range MTRR if it * differs from the value it should have * @msr: MSR address of the MTTR which should be checked and updated * @changed: pointer which indicates whether the MTRR needed to be changed * @msrwords: pointer to the MSR values which the MSR should have */ static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords) { unsigned lo, hi; rdmsr(msr, lo, hi); if (lo != msrwords[0] || hi != msrwords[1]) { mtrr_wrmsr(msr, msrwords[0], msrwords[1]); *changed = true; } } /** * generic_get_free_region - Get a free MTRR. * @base: The starting (base) address of the region. * @size: The size (in bytes) of the region. * @replace_reg: mtrr index to be replaced; set to invalid value if none. * * Returns: The index of the region on success, else negative on error. */ int generic_get_free_region(unsigned long base, unsigned long size, int replace_reg) { unsigned long lbase, lsize; mtrr_type ltype; int i, max; max = num_var_ranges; if (replace_reg >= 0 && replace_reg < max) return replace_reg; for (i = 0; i < max; ++i) { mtrr_if->get(i, &lbase, &lsize, <ype); if (lsize == 0) return i; } return -ENOSPC; } static void generic_get_mtrr(unsigned int reg, unsigned long *base, unsigned long *size, mtrr_type *type) { u32 mask_lo, mask_hi, base_lo, base_hi; unsigned int hi; u64 tmp, mask; /* * get_mtrr doesn't need to update mtrr_state, also it could be called * from any cpu, so try to print it out directly. */ get_cpu(); rdmsr(MTRRphysMask_MSR(reg), mask_lo, mask_hi); if (!(mask_lo & MTRR_PHYSMASK_V)) { /* Invalid (i.e. free) range */ *base = 0; *size = 0; *type = 0; goto out_put_cpu; } rdmsr(MTRRphysBase_MSR(reg), base_lo, base_hi); /* Work out the shifted address mask: */ tmp = (u64)mask_hi << 32 | (mask_lo & PAGE_MASK); mask = (u64)phys_hi_rsvd << 32 | tmp; /* Expand tmp with high bits to all 1s: */ hi = fls64(tmp); if (hi > 0) { tmp |= ~((1ULL<<(hi - 1)) - 1); if (tmp != mask) { pr_warn("mtrr: your BIOS has configured an incorrect mask, fixing it.\n"); add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); mask = tmp; } } /* * This works correctly if size is a power of two, i.e. a * contiguous range: */ *size = -mask >> PAGE_SHIFT; *base = (u64)base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT; *type = base_lo & MTRR_PHYSBASE_TYPE; out_put_cpu: put_cpu(); } /** * set_fixed_ranges - checks & updates the fixed-range MTRRs if they * differ from the saved set * @frs: pointer to fixed-range MTRR values, saved by get_fixed_ranges() */ static int set_fixed_ranges(mtrr_type *frs) { unsigned long long *saved = (unsigned long long *)frs; bool changed = false; int block = -1, range; k8_check_syscfg_dram_mod_en(); while (fixed_range_blocks[++block].ranges) { for (range = 0; range < fixed_range_blocks[block].ranges; range++) set_fixed_range(fixed_range_blocks[block].base_msr + range, &changed, (unsigned int *)saved++); } return changed; } /* * Set the MSR pair relating to a var range. * Returns true if changes are made. */ static bool set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr) { unsigned int lo, hi; bool changed = false; rdmsr(MTRRphysBase_MSR(index), lo, hi); if ((vr->base_lo & ~MTRR_PHYSBASE_RSVD) != (lo & ~MTRR_PHYSBASE_RSVD) || (vr->base_hi & ~phys_hi_rsvd) != (hi & ~phys_hi_rsvd)) { mtrr_wrmsr(MTRRphysBase_MSR(index), vr->base_lo, vr->base_hi); changed = true; } rdmsr(MTRRphysMask_MSR(index), lo, hi); if ((vr->mask_lo & ~MTRR_PHYSMASK_RSVD) != (lo & ~MTRR_PHYSMASK_RSVD) || (vr->mask_hi & ~phys_hi_rsvd) != (hi & ~phys_hi_rsvd)) { mtrr_wrmsr(MTRRphysMask_MSR(index), vr->mask_lo, vr->mask_hi); changed = true; } return changed; } static u32 deftype_lo, deftype_hi; /** * set_mtrr_state - Set the MTRR state for this CPU. * * NOTE: The CPU must already be in a safe state for MTRR changes, including * measures that only a single CPU can be active in set_mtrr_state() in * order to not be subject to races for usage of deftype_lo. This is * accomplished by taking cache_disable_lock. * RETURNS: 0 if no changes made, else a mask indicating what was changed. */ static unsigned long set_mtrr_state(void) { unsigned long change_mask = 0; unsigned int i; for (i = 0; i < num_var_ranges; i++) { if (set_mtrr_var_ranges(i, &mtrr_state.var_ranges[i])) change_mask |= MTRR_CHANGE_MASK_VARIABLE; } if (mtrr_state.have_fixed && set_fixed_ranges(mtrr_state.fixed_ranges)) change_mask |= MTRR_CHANGE_MASK_FIXED; /* * Set_mtrr_restore restores the old value of MTRRdefType, * so to set it we fiddle with the saved value: */ if ((deftype_lo & MTRR_DEF_TYPE_TYPE) != mtrr_state.def_type || ((deftype_lo & MTRR_DEF_TYPE_ENABLE) >> MTRR_STATE_SHIFT) != mtrr_state.enabled) { deftype_lo = (deftype_lo & MTRR_DEF_TYPE_DISABLE) | mtrr_state.def_type | (mtrr_state.enabled << MTRR_STATE_SHIFT); change_mask |= MTRR_CHANGE_MASK_DEFTYPE; } return change_mask; } void mtrr_disable(void) { /* Save MTRR state */ rdmsr(MSR_MTRRdefType, deftype_lo, deftype_hi); /* Disable MTRRs, and set the default type to uncached */ mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & MTRR_DEF_TYPE_DISABLE, deftype_hi); } void mtrr_enable(void) { /* Intel (P6) standard MTRRs */ mtrr_wrmsr(MSR_MTRRdefType, deftype_lo, deftype_hi); } void mtrr_generic_set_state(void) { unsigned long mask, count; /* Actually set the state */ mask = set_mtrr_state(); /* Use the atomic bitops to update the global mask */ for (count = 0; count < sizeof(mask) * 8; ++count) { if (mask & 0x01) set_bit(count, &smp_changes_mask); mask >>= 1; } } /** * generic_set_mtrr - set variable MTRR register on the local CPU. * * @reg: The register to set. * @base: The base address of the region. * @size: The size of the region. If this is 0 the region is disabled. * @type: The type of the region. * * Returns nothing. */ static void generic_set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type) { unsigned long flags; struct mtrr_var_range *vr; vr = &mtrr_state.var_ranges[reg]; local_irq_save(flags); cache_disable(); if (size == 0) { /* * The invalid bit is kept in the mask, so we simply * clear the relevant mask register to disable a range. */ mtrr_wrmsr(MTRRphysMask_MSR(reg), 0, 0); memset(vr, 0, sizeof(struct mtrr_var_range)); } else { vr->base_lo = base << PAGE_SHIFT | type; vr->base_hi = (base >> (32 - PAGE_SHIFT)) & ~phys_hi_rsvd; vr->mask_lo = -size << PAGE_SHIFT | MTRR_PHYSMASK_V; vr->mask_hi = (-size >> (32 - PAGE_SHIFT)) & ~phys_hi_rsvd; mtrr_wrmsr(MTRRphysBase_MSR(reg), vr->base_lo, vr->base_hi); mtrr_wrmsr(MTRRphysMask_MSR(reg), vr->mask_lo, vr->mask_hi); } cache_enable(); local_irq_restore(flags); } int generic_validate_add_page(unsigned long base, unsigned long size, unsigned int type) { unsigned long lbase, last; /* * For Intel PPro stepping <= 7 * must be 4 MiB aligned and not touch 0x70000000 -> 0x7003FFFF */ if (mtrr_if == &generic_mtrr_ops && boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && boot_cpu_data.x86_stepping <= 7) { if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) { pr_warn("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base); return -EINVAL; } if (!(base + size < 0x70000 || base > 0x7003F) && (type == MTRR_TYPE_WRCOMB || type == MTRR_TYPE_WRBACK)) { pr_warn("mtrr: writable mtrr between 0x70000000 and 0x7003FFFF may hang the CPU.\n"); return -EINVAL; } } /* * Check upper bits of base and last are equal and lower bits are 0 * for base and 1 for last */ last = base + size - 1; for (lbase = base; !(lbase & 1) && (last & 1); lbase = lbase >> 1, last = last >> 1) ; if (lbase != last) { pr_warn("mtrr: base(0x%lx000) is not aligned on a size(0x%lx000) boundary\n", base, size); return -EINVAL; } return 0; } static int generic_have_wrcomb(void) { unsigned long config, dummy; rdmsr(MSR_MTRRcap, config, dummy); return config & MTRR_CAP_WC; } int positive_have_wrcomb(void) { return 1; } /* * Generic structure... */ const struct mtrr_ops generic_mtrr_ops = { .get = generic_get_mtrr, .get_free_region = generic_get_free_region, .set = generic_set_mtrr, .validate_add_page = generic_validate_add_page, .have_wrcomb = generic_have_wrcomb, }; |
| 9 3 9 1 6 1 1 5 4 15 15 1 2 3 9 4 1 5 3 3 1 20 2 13 4 16 17 2 20 1 27 6 21 2 5 5 20 14 58 3 1 1 9 29 29 25 25 24 24 3 26 18 18 9 14 11 3 14 24 24 1 22 22 5 1 2 3 9 9 7 1 1 2 2 4 4 17 17 1 16 7 7 7 4 1 2 2 6 4 2 20 29 1 28 14 9 1 1 3 9 5 20 1 65 5 63 7 3 35 32 24 51 2 7 1 43 10 51 37 1 36 30 26 1 26 1 1 26 25 59 3 55 3 56 1 53 4 53 5 54 3 55 2 44 13 53 4 56 1 57 55 24 29 4 50 5 2 45 6 3 9 14 1 8 4 3 5 2 4 2 49 55 13 20 13 22 63 4 30 30 1 28 16 15 15 8 8 1 3 3 12 12 11 1 6 82 130 4 1 4 2 1 4 3 2 3 2 1 2 115 43 81 9 35 72 2 9 81 15 21 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: GRE over IP protocol decoder. * * Authors: Alexey Kuznetsov (kuznet@ms2.inr.ac.ru) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/protocol.h> #include <net/ip_tunnels.h> #include <net/arp.h> #include <net/checksum.h> #include <net/dsfield.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/gre.h> #include <net/dst_metadata.h> #include <net/erspan.h> #include <net/inet_dscp.h> /* Problems & solutions -------------------- 1. The most important issue is detecting local dead loops. They would cause complete host lockup in transmit, which would be "resolved" by stack overflow or, if queueing is enabled, with infinite looping in net_bh. We cannot track such dead loops during route installation, it is infeasible task. The most general solutions would be to keep skb->encapsulation counter (sort of local ttl), and silently drop packet when it expires. It is a good solution, but it supposes maintaining new variable in ALL skb, even if no tunneling is used. Current solution: xmit_recursion breaks dead loops. This is a percpu counter, since when we enter the first ndo_xmit(), cpu migration is forbidden. We force an exit if this counter reaches RECURSION_LIMIT 2. Networking dead loops would not kill routers, but would really kill network. IP hop limit plays role of "t->recursion" in this case, if we copy it from packet being encapsulated to upper header. It is very good solution, but it introduces two problems: - Routing protocols, using packets with ttl=1 (OSPF, RIP2), do not work over tunnels. - traceroute does not work. I planned to relay ICMP from tunnel, so that this problem would be solved and traceroute output would even more informative. This idea appeared to be wrong: only Linux complies to rfc1812 now (yes, guys, Linux is the only true router now :-)), all routers (at least, in neighbourhood of mine) return only 8 bytes of payload. It is the end. Hence, if we want that OSPF worked or traceroute said something reasonable, we should search for another solution. One of them is to parse packet trying to detect inner encapsulation made by our node. It is difficult or even impossible, especially, taking into account fragmentation. TO be short, ttl is not solution at all. Current solution: The solution was UNEXPECTEDLY SIMPLE. We force DF flag on tunnels with preconfigured hop limit, that is ALL. :-) Well, it does not remove the problem completely, but exponential growth of network traffic is changed to linear (branches, that exceed pmtu are pruned) and tunnel mtu rapidly degrades to value <68, where looping stops. Yes, it is not good if there exists a router in the loop, which does not force DF, even when encapsulating packets have DF set. But it is not our problem! Nobody could accuse us, we made all that we could make. Even if it is your gated who injected fatal route to network, even if it were you who configured fatal static route: you are innocent. :-) Alexey Kuznetsov. */ static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static struct rtnl_link_ops ipgre_link_ops __read_mostly; static const struct header_ops ipgre_header_ops; static int ipgre_tunnel_init(struct net_device *dev); static void erspan_build_header(struct sk_buff *skb, u32 id, u32 index, bool truncate, bool is_ipv4); static unsigned int ipgre_net_id __read_mostly; static unsigned int gre_tap_net_id __read_mostly; static unsigned int erspan_net_id __read_mostly; static int ipgre_err(struct sk_buff *skb, u32 info, const struct tnl_ptk_info *tpi) { /* All the routers (except for Linux) return only 8 bytes of packet payload. It means, that precise relaying of ICMP in the real Internet is absolutely infeasible. Moreover, Cisco "wise men" put GRE key to the third word in GRE header. It makes impossible maintaining even soft state for keyed GRE tunnels with enabled checksum. Tell them "thank you". Well, I wonder, rfc1812 was written by Cisco employee, what the hell these idiots break standards established by themselves??? */ struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn; const struct iphdr *iph; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; unsigned int data_len = 0; struct ip_tunnel *t; if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); else if (tpi->proto == htons(ETH_P_ERSPAN) || tpi->proto == htons(ETH_P_ERSPAN2)) itn = net_generic(net, erspan_net_id); else itn = net_generic(net, ipgre_net_id); iph = (const struct iphdr *)(icmp_hdr(skb) + 1); t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->daddr, iph->saddr, tpi->key); if (!t) return -ENOENT; switch (type) { default: case ICMP_PARAMETERPROB: return 0; case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: case ICMP_PORT_UNREACH: /* Impossible event. */ return 0; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, I believe they are just ether pollution. --ANK */ break; } break; case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) return 0; data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */ break; case ICMP_REDIRECT: break; } #if IS_ENABLED(CONFIG_IPV6) if (tpi->proto == htons(ETH_P_IPV6) && !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len, type, data_len)) return 0; #endif if (t->parms.iph.daddr == 0 || ipv4_is_multicast(t->parms.iph.daddr)) return 0; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) return 0; if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; return 0; } static void gre_err(struct sk_buff *skb, u32 info) { /* All the routers (except for Linux) return only * 8 bytes of packet payload. It means, that precise relaying of * ICMP in the real Internet is absolutely infeasible. * * Moreover, Cisco "wise men" put GRE key to the third word * in GRE header. It makes impossible maintaining even soft * state for keyed * GRE tunnels with enabled checksum. Tell them "thank you". * * Well, I wonder, rfc1812 was written by Cisco employee, * what the hell these idiots break standards established * by themselves??? */ const struct iphdr *iph = (struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct tnl_ptk_info tpi; if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IP), iph->ihl * 4) < 0) return; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, skb->dev->ifindex, IPPROTO_GRE); return; } if (type == ICMP_REDIRECT) { ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex, IPPROTO_GRE); return; } ipgre_err(skb, info, &tpi); } static bool is_erspan_type1(int gre_hdr_len) { /* Both ERSPAN type I (version 0) and type II (version 1) use * protocol 0x88BE, but the type I has only 4-byte GRE header, * while type II has 8-byte. */ return gre_hdr_len == 4; } static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, int gre_hdr_len) { struct net *net = dev_net(skb->dev); struct metadata_dst *tun_dst = NULL; struct erspan_base_hdr *ershdr; IP_TUNNEL_DECLARE_FLAGS(flags); struct ip_tunnel_net *itn; struct ip_tunnel *tunnel; const struct iphdr *iph; struct erspan_md2 *md2; int ver; int len; ip_tunnel_flags_copy(flags, tpi->flags); itn = net_generic(net, erspan_net_id); iph = ip_hdr(skb); if (is_erspan_type1(gre_hdr_len)) { ver = 0; __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, 0); } else { if (unlikely(!pskb_may_pull(skb, gre_hdr_len + sizeof(*ershdr)))) return PACKET_REJECT; ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; iph = ip_hdr(skb); __set_bit(IP_TUNNEL_KEY_BIT, flags); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, tpi->key); } if (tunnel) { if (is_erspan_type1(gre_hdr_len)) len = gre_hdr_len; else len = gre_hdr_len + erspan_hdr_len(ver); if (unlikely(!pskb_may_pull(skb, len))) return PACKET_REJECT; if (__iptunnel_pull_header(skb, len, htons(ETH_P_TEB), false, false) < 0) goto drop; if (tunnel->collect_md) { struct erspan_metadata *pkt_md, *md; struct ip_tunnel_info *info; unsigned char *gh; __be64 tun_id; __set_bit(IP_TUNNEL_KEY_BIT, tpi->flags); ip_tunnel_flags_copy(flags, tpi->flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, sizeof(*md)); if (!tun_dst) return PACKET_REJECT; /* skb can be uncloned in __iptunnel_pull_header, so * old pkt_md is no longer valid and we need to reset * it */ gh = skb_network_header(skb) + skb_network_header_len(skb); pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len + sizeof(*ershdr)); md = ip_tunnel_info_opts(&tun_dst->u.tun_info); md->version = ver; md2 = &md->u.md2; memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); info = &tun_dst->u.tun_info; __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); info->options_len = sizeof(*md); } skb_reset_mac_header(skb); ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_REJECT; drop: kfree_skb(skb); return PACKET_RCVD; } static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct ip_tunnel_net *itn, int hdr_len, bool raw_proto) { struct metadata_dst *tun_dst = NULL; const struct iphdr *iph; struct ip_tunnel *tunnel; iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->saddr, iph->daddr, tpi->key); if (tunnel) { const struct iphdr *tnl_params; if (__iptunnel_pull_header(skb, hdr_len, tpi->proto, raw_proto, false) < 0) goto drop; /* Special case for ipgre_header_parse(), which expects the * mac_header to point to the outer IP header. */ if (tunnel->dev->header_ops == &ipgre_header_ops) skb_pop_mac_header(skb); else skb_reset_mac_header(skb); tnl_params = &tunnel->parms.iph; if (tunnel->collect_md || tnl_params->daddr == 0) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __be64 tun_id; __set_bit(IP_TUNNEL_CSUM_BIT, flags); __set_bit(IP_TUNNEL_KEY_BIT, flags); ip_tunnel_flags_and(flags, tpi->flags, flags); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0); if (!tun_dst) return PACKET_REJECT; } ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_NEXT; drop: kfree_skb(skb); return PACKET_RCVD; } static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, int hdr_len) { struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn; int res; if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); else itn = net_generic(net, ipgre_net_id); res = __ipgre_rcv(skb, tpi, itn, hdr_len, false); if (res == PACKET_NEXT && tpi->proto == htons(ETH_P_TEB)) { /* ipgre tunnels in collect metadata mode should receive * also ETH_P_TEB traffic. */ itn = net_generic(net, ipgre_net_id); res = __ipgre_rcv(skb, tpi, itn, hdr_len, true); } return res; } static int gre_rcv(struct sk_buff *skb) { struct tnl_ptk_info tpi; bool csum_err = false; int hdr_len; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { /* Looped back packet, drop it! */ if (rt_is_output_route(skb_rtable(skb))) goto drop; } #endif hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP), 0); if (hdr_len < 0) goto drop; if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) || tpi.proto == htons(ETH_P_ERSPAN2))) { if (erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; goto out; } if (ipgre_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; out: icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); IP_TUNNEL_DECLARE_FLAGS(flags); ip_tunnel_flags_copy(flags, tunnel->parms.o_flags); /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, flags, proto, tunnel->parms.o_key, test_bit(IP_TUNNEL_SEQ_BIT, flags) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } static int gre_handle_offloads(struct sk_buff *skb, bool csum) { return iptunnel_handle_offloads(skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; int tunnel_hlen; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto err_free_skb; key = &tun_info->key; tunnel_hlen = gre_calc_hlen(key->tun_flags); if (skb_cow_head(skb, dev->needed_headroom)) goto err_free_skb; /* Push Tunnel header. */ if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags))) goto err_free_skb; __set_bit(IP_TUNNEL_CSUM_BIT, flags); __set_bit(IP_TUNNEL_KEY_BIT, flags); __set_bit(IP_TUNNEL_SEQ_BIT, flags); ip_tunnel_flags_and(flags, tun_info->key.tun_flags, flags); gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), test_bit(IP_TUNNEL_SEQ_BIT, flags) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); return; err_free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); } static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; struct erspan_metadata *md; bool truncate = false; __be16 proto; int tunnel_hlen; int version; int nhoff; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto err_free_skb; key = &tun_info->key; if (!test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_info->key.tun_flags)) goto err_free_skb; if (tun_info->options_len < sizeof(*md)) goto err_free_skb; md = ip_tunnel_info_opts(tun_info); /* ERSPAN has fixed 8 byte GRE header */ version = md->version; tunnel_hlen = 8 + erspan_hdr_len(version); if (skb_cow_head(skb, dev->needed_headroom)) goto err_free_skb; if (gre_handle_offloads(skb, false)) goto err_free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) goto err_free_skb; truncate = true; } nhoff = skb_network_offset(skb); if (skb->protocol == htons(ETH_P_IP) && (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) truncate = true; if (skb->protocol == htons(ETH_P_IPV6)) { int thoff; if (skb_transport_header_was_set(skb)) thoff = skb_transport_offset(skb); else thoff = nhoff + sizeof(struct ipv6hdr); if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff) truncate = true; } if (version == 1) { erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)), ntohl(md->u.index), truncate, true); proto = htons(ETH_P_ERSPAN); } else if (version == 2) { erspan_build_header_v2(skb, ntohl(tunnel_id_to_key32(key->tun_id)), md->u.md2.dir, get_hwid(&md->u.md2), truncate, true); proto = htons(ETH_P_ERSPAN2); } else { goto err_free_skb; } __set_bit(IP_TUNNEL_SEQ_BIT, flags); gre_build_header(skb, 8, flags, proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); return; err_free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); } static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct ip_tunnel_key *key; struct rtable *rt; struct flowi4 fl4; if (ip_tunnel_info_af(info) != AF_INET) return -EINVAL; key = &info->key; ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), key->tos & ~INET_ECN_MASK, dev_net(dev), 0, skb->mark, skb_get_hash(skb), key->flow_flags); rt = ip_route_output_key(dev_net(dev), &fl4); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); info->key.u.ipv4.src = fl4.saddr; return 0; } static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tnl_params; if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { gre_fb_xmit(skb, dev, skb->protocol); return NETDEV_TX_OK; } if (dev->header_ops) { int pull_len = tunnel->hlen + sizeof(struct iphdr); if (skb_cow_head(skb, 0)) goto free_skb; if (!pskb_may_pull(skb, pull_len)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; /* ip_tunnel_xmit() needs skb->data pointing to gre header. */ skb_pull(skb, pull_len); skb_reset_mac_header(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start(skb) < skb->data) goto free_skb; } else { if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; tnl_params = &tunnel->parms.iph; } if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags))) goto free_skb; __gre_xmit(skb, dev, tnl_params, skb->protocol); return NETDEV_TX_OK; free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } static netdev_tx_t erspan_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); bool truncate = false; __be16 proto; if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { erspan_fb_xmit(skb, dev); return NETDEV_TX_OK; } if (gre_handle_offloads(skb, false)) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) goto free_skb; truncate = true; } /* Push ERSPAN header */ if (tunnel->erspan_ver == 0) { proto = htons(ETH_P_ERSPAN); __clear_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags); } else if (tunnel->erspan_ver == 1) { erspan_build_header(skb, ntohl(tunnel->parms.o_key), tunnel->index, truncate, true); proto = htons(ETH_P_ERSPAN); } else if (tunnel->erspan_ver == 2) { erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key), tunnel->dir, tunnel->hwid, truncate, true); proto = htons(ETH_P_ERSPAN2); } else { goto free_skb; } __clear_bit(IP_TUNNEL_KEY_BIT, tunnel->parms.o_flags); __gre_xmit(skb, dev, &tunnel->parms.iph, proto); return NETDEV_TX_OK; free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { gre_fb_xmit(skb, dev, htons(ETH_P_TEB)); return NETDEV_TX_OK; } if (gre_handle_offloads(skb, test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags))) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_TEB)); return NETDEV_TX_OK; free_skb: kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } static void ipgre_link_update(struct net_device *dev, bool set_mtu) { struct ip_tunnel *tunnel = netdev_priv(dev); int len; len = tunnel->tun_hlen; tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); len = tunnel->tun_hlen - len; tunnel->hlen = tunnel->hlen + len; if (dev->header_ops) dev->hard_header_len += len; else dev->needed_headroom += len; if (set_mtu) WRITE_ONCE(dev->mtu, max_t(int, dev->mtu - len, 68)); if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags) || (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && tunnel->encap.type != TUNNEL_ENCAP_NONE)) { dev->features &= ~NETIF_F_GSO_SOFTWARE; dev->hw_features &= ~NETIF_F_GSO_SOFTWARE; } else { dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; } } static int ipgre_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { __be16 i_flags, o_flags; int err; if (!ip_tunnel_flags_is_be16_compat(p->i_flags) || !ip_tunnel_flags_is_be16_compat(p->o_flags)) return -EOVERFLOW; i_flags = ip_tunnel_flags_to_be16(p->i_flags); o_flags = ip_tunnel_flags_to_be16(p->o_flags); if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || p->iph.protocol != IPPROTO_GRE || p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF)) || ((i_flags | o_flags) & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; } gre_flags_to_tnl_flags(p->i_flags, i_flags); gre_flags_to_tnl_flags(p->o_flags, o_flags); err = ip_tunnel_ctl(dev, p, cmd); if (err) return err; if (cmd == SIOCCHGTUNNEL) { struct ip_tunnel *t = netdev_priv(dev); ip_tunnel_flags_copy(t->parms.i_flags, p->i_flags); ip_tunnel_flags_copy(t->parms.o_flags, p->o_flags); if (strcmp(dev->rtnl_link_ops->kind, "erspan")) ipgre_link_update(dev, true); } i_flags = gre_tnl_flags_to_gre_flags(p->i_flags); ip_tunnel_flags_from_be16(p->i_flags, i_flags); o_flags = gre_tnl_flags_to_gre_flags(p->o_flags); ip_tunnel_flags_from_be16(p->o_flags, o_flags); return 0; } /* Nice toy. Unfortunately, useless in real life :-) It allows to construct virtual multiprotocol broadcast "LAN" over the Internet, provided multicast routing is tuned. I have no idea was this bicycle invented before me, so that I had to set ARPHRD_IPGRE to a random value. I have an impression, that Cisco could make something similar, but this feature is apparently missing in IOS<=11.2(8). I set up 10.66.66/24 and fec0:6666:6666::0/96 as virtual networks with broadcast 224.66.66.66. If you have access to mbone, play with me :-) ping -t 255 224.66.66.66 If nobody answers, mbone does not work. ip tunnel add Universe mode gre remote 224.66.66.66 local <Your_real_addr> ttl 255 ip addr add 10.66.66.<somewhat>/24 dev Universe ifconfig Universe up ifconfig Universe add fe80::<Your_real_addr>/10 ifconfig Universe add fec0:6666:6666::<Your_real_addr>/96 ftp 10.66.66.66 ... ftp fec0:6666:6666::193.233.7.65 ... */ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct ip_tunnel *t = netdev_priv(dev); struct iphdr *iph; struct gre_base_hdr *greh; iph = skb_push(skb, t->hlen + sizeof(*iph)); greh = (struct gre_base_hdr *)(iph+1); greh->flags = gre_tnl_flags_to_gre_flags(t->parms.o_flags); greh->protocol = htons(type); memcpy(iph, &t->parms.iph, sizeof(struct iphdr)); /* Set the source hardware address. */ if (saddr) memcpy(&iph->saddr, saddr, 4); if (daddr) memcpy(&iph->daddr, daddr, 4); if (iph->daddr) return t->hlen + sizeof(*iph); return -(t->hlen + sizeof(*iph)); } static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr) { const struct iphdr *iph = (const struct iphdr *) skb_mac_header(skb); memcpy(haddr, &iph->saddr, 4); return 4; } static const struct header_ops ipgre_header_ops = { .create = ipgre_header, .parse = ipgre_header_parse, }; #ifdef CONFIG_NET_IPGRE_BROADCAST static int ipgre_open(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr)) { struct flowi4 fl4; struct rtable *rt; rt = ip_route_output_gre(t->net, &fl4, t->parms.iph.daddr, t->parms.iph.saddr, t->parms.o_key, t->parms.iph.tos & INET_DSCP_MASK, t->parms.link); if (IS_ERR(rt)) return -EADDRNOTAVAIL; dev = rt->dst.dev; ip_rt_put(rt); if (!__in_dev_get_rtnl(dev)) return -EADDRNOTAVAIL; t->mlink = dev->ifindex; ip_mc_inc_group(__in_dev_get_rtnl(dev), t->parms.iph.daddr); } return 0; } static int ipgre_close(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr) && t->mlink) { struct in_device *in_dev; in_dev = inetdev_by_index(t->net, t->mlink); if (in_dev) ip_mc_dec_group(in_dev, t->parms.iph.daddr); } return 0; } #endif static const struct net_device_ops ipgre_netdev_ops = { .ndo_init = ipgre_tunnel_init, .ndo_uninit = ip_tunnel_uninit, #ifdef CONFIG_NET_IPGRE_BROADCAST .ndo_open = ipgre_open, .ndo_stop = ipgre_close, #endif .ndo_start_xmit = ipgre_xmit, .ndo_siocdevprivate = ip_tunnel_siocdevprivate, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = ipgre_tunnel_ctl, }; #define GRE_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_HIGHDMA | \ NETIF_F_HW_CSUM) static void ipgre_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipgre_netdev_ops; dev->type = ARPHRD_IPGRE; ip_tunnel_setup(dev, ipgre_net_id); } static void __gre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel; tunnel = netdev_priv(dev); tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; dev->needed_headroom = tunnel->hlen + sizeof(tunnel->parms.iph); dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; /* TCP offload with GRE SEQ is not supported, nor can we support 2 * levels of outer headers requiring an update. */ if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags)) return; if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.o_flags) && tunnel->encap.type != TUNNEL_ENCAP_NONE) return; dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; dev->lltx = true; } static int ipgre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; __gre_tunnel_init(dev); __dev_addr_set(dev, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); dev->flags = IFF_NOARP; netif_keep_dst(dev); dev->addr_len = 4; if (iph->daddr && !tunnel->collect_md) { #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { if (!iph->saddr) return -EINVAL; dev->flags = IFF_BROADCAST; dev->header_ops = &ipgre_header_ops; dev->hard_header_len = tunnel->hlen + sizeof(*iph); dev->needed_headroom = 0; } #endif } else if (!tunnel->collect_md) { dev->header_ops = &ipgre_header_ops; dev->hard_header_len = tunnel->hlen + sizeof(*iph); dev->needed_headroom = 0; } return ip_tunnel_init(dev); } static const struct gre_protocol ipgre_protocol = { .handler = gre_rcv, .err_handler = gre_err, }; static int __net_init ipgre_init_net(struct net *net) { return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL); } static void __net_exit ipgre_exit_batch_rtnl(struct list_head *list_net, struct list_head *dev_to_kill) { ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops, dev_to_kill); } static struct pernet_operations ipgre_net_ops = { .init = ipgre_init_net, .exit_batch_rtnl = ipgre_exit_batch_rtnl, .id = &ipgre_net_id, .size = sizeof(struct ip_tunnel_net), }; static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be16 flags; if (!data) return 0; flags = 0; if (data[IFLA_GRE_IFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]); if (data[IFLA_GRE_OFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]); if (flags & (GRE_VERSION|GRE_ROUTING)) return -EINVAL; if (data[IFLA_GRE_COLLECT_METADATA] && data[IFLA_GRE_ENCAP_TYPE] && nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]) != TUNNEL_ENCAP_NONE) return -EINVAL; return 0; } static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be32 daddr; if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (!data) goto out; if (data[IFLA_GRE_REMOTE]) { memcpy(&daddr, nla_data(data[IFLA_GRE_REMOTE]), 4); if (!daddr) return -EINVAL; } out: return ipgre_tunnel_validate(tb, data, extack); } static int erspan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be16 flags = 0; int ret; if (!data) return 0; ret = ipgre_tap_validate(tb, data, extack); if (ret) return ret; if (data[IFLA_GRE_ERSPAN_VER] && nla_get_u8(data[IFLA_GRE_ERSPAN_VER]) == 0) return 0; /* ERSPAN type II/III should only have GRE sequence and key flag */ if (data[IFLA_GRE_OFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]); if (data[IFLA_GRE_IFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]); if (!data[IFLA_GRE_COLLECT_METADATA] && flags != (GRE_SEQ | GRE_KEY)) return -EINVAL; /* ERSPAN Session ID only has 10-bit. Since we reuse * 32-bit key field as ID, check it's range. */ if (data[IFLA_GRE_IKEY] && (ntohl(nla_get_be32(data[IFLA_GRE_IKEY])) & ~ID_MASK)) return -EINVAL; if (data[IFLA_GRE_OKEY] && (ntohl(nla_get_be32(data[IFLA_GRE_OKEY])) & ~ID_MASK)) return -EINVAL; return 0; } static int ipgre_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); memset(parms, 0, sizeof(*parms)); parms->iph.protocol = IPPROTO_GRE; if (!data) return 0; if (data[IFLA_GRE_LINK]) parms->link = nla_get_u32(data[IFLA_GRE_LINK]); if (data[IFLA_GRE_IFLAGS]) gre_flags_to_tnl_flags(parms->i_flags, nla_get_be16(data[IFLA_GRE_IFLAGS])); if (data[IFLA_GRE_OFLAGS]) gre_flags_to_tnl_flags(parms->o_flags, nla_get_be16(data[IFLA_GRE_OFLAGS])); if (data[IFLA_GRE_IKEY]) parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]); if (data[IFLA_GRE_OKEY]) parms->o_key = nla_get_be32(data[IFLA_GRE_OKEY]); if (data[IFLA_GRE_LOCAL]) parms->iph.saddr = nla_get_in_addr(data[IFLA_GRE_LOCAL]); if (data[IFLA_GRE_REMOTE]) parms->iph.daddr = nla_get_in_addr(data[IFLA_GRE_REMOTE]); if (data[IFLA_GRE_TTL]) parms->iph.ttl = nla_get_u8(data[IFLA_GRE_TTL]); if (data[IFLA_GRE_TOS]) parms->iph.tos = nla_get_u8(data[IFLA_GRE_TOS]); if (!data[IFLA_GRE_PMTUDISC] || nla_get_u8(data[IFLA_GRE_PMTUDISC])) { if (t->ignore_df) return -EINVAL; parms->iph.frag_off = htons(IP_DF); } if (data[IFLA_GRE_COLLECT_METADATA]) { t->collect_md = true; if (dev->type == ARPHRD_IPGRE) dev->type = ARPHRD_NONE; } if (data[IFLA_GRE_IGNORE_DF]) { if (nla_get_u8(data[IFLA_GRE_IGNORE_DF]) && (parms->iph.frag_off & htons(IP_DF))) return -EINVAL; t->ignore_df = !!nla_get_u8(data[IFLA_GRE_IGNORE_DF]); } if (data[IFLA_GRE_FWMARK]) *fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]); return 0; } static int erspan_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); int err; err = ipgre_netlink_parms(dev, data, tb, parms, fwmark); if (err) return err; if (!data) return 0; if (data[IFLA_GRE_ERSPAN_VER]) { t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); if (t->erspan_ver > 2) return -EINVAL; } if (t->erspan_ver == 1) { if (data[IFLA_GRE_ERSPAN_INDEX]) { t->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); if (t->index & ~INDEX_MASK) return -EINVAL; } } else if (t->erspan_ver == 2) { if (data[IFLA_GRE_ERSPAN_DIR]) { t->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); if (t->dir & ~(DIR_MASK >> DIR_OFFSET)) return -EINVAL; } if (data[IFLA_GRE_ERSPAN_HWID]) { t->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); if (t->hwid & ~(HWID_MASK >> HWID_OFFSET)) return -EINVAL; } } return 0; } /* This function returns true when ENCAP attributes are present in the nl msg */ static bool ipgre_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *ipencap) { bool ret = false; memset(ipencap, 0, sizeof(*ipencap)); if (!data) return ret; if (data[IFLA_GRE_ENCAP_TYPE]) { ret = true; ipencap->type = nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]); } if (data[IFLA_GRE_ENCAP_FLAGS]) { ret = true; ipencap->flags = nla_get_u16(data[IFLA_GRE_ENCAP_FLAGS]); } if (data[IFLA_GRE_ENCAP_SPORT]) { ret = true; ipencap->sport = nla_get_be16(data[IFLA_GRE_ENCAP_SPORT]); } if (data[IFLA_GRE_ENCAP_DPORT]) { ret = true; ipencap->dport = nla_get_be16(data[IFLA_GRE_ENCAP_DPORT]); } return ret; } static int gre_tap_init(struct net_device *dev) { __gre_tunnel_init(dev); dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); return ip_tunnel_init(dev); } static const struct net_device_ops gre_tap_netdev_ops = { .ndo_init = gre_tap_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = gre_tap_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_fill_metadata_dst = gre_fill_metadata_dst, }; static int erspan_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); if (tunnel->erspan_ver == 0) tunnel->tun_hlen = 4; /* 4-byte GRE hdr. */ else tunnel->tun_hlen = 8; /* 8-byte GRE hdr. */ tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + erspan_hdr_len(tunnel->erspan_ver); dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); return ip_tunnel_init(dev); } static const struct net_device_ops erspan_netdev_ops = { .ndo_init = erspan_tunnel_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = erspan_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_fill_metadata_dst = gre_fill_metadata_dst, }; static void ipgre_tap_setup(struct net_device *dev) { ether_setup(dev); dev->max_mtu = 0; dev->netdev_ops = &gre_tap_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, gre_tap_net_id); } static int ipgre_newlink_encap_setup(struct net_device *dev, struct nlattr *data[]) { struct ip_tunnel_encap ipencap; if (ipgre_netlink_encap_parms(data, &ipencap)) { struct ip_tunnel *t = netdev_priv(dev); int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } return 0; } static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; return ip_tunnel_newlink(dev, tb, &p, fwmark); } static int erspan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); if (err) return err; return ip_tunnel_newlink(dev, tb, &p, fwmark); } static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; err = ip_tunnel_changelink(dev, tb, &p, fwmark); if (err < 0) return err; ip_tunnel_flags_copy(t->parms.i_flags, p.i_flags); ip_tunnel_flags_copy(t->parms.o_flags, p.o_flags); ipgre_link_update(dev, !tb[IFLA_MTU]); return 0; } static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; err = ip_tunnel_changelink(dev, tb, &p, fwmark); if (err < 0) return err; ip_tunnel_flags_copy(t->parms.i_flags, p.i_flags); ip_tunnel_flags_copy(t->parms.o_flags, p.o_flags); return 0; } static size_t ipgre_get_size(const struct net_device *dev) { return /* IFLA_GRE_LINK */ nla_total_size(4) + /* IFLA_GRE_IFLAGS */ nla_total_size(2) + /* IFLA_GRE_OFLAGS */ nla_total_size(2) + /* IFLA_GRE_IKEY */ nla_total_size(4) + /* IFLA_GRE_OKEY */ nla_total_size(4) + /* IFLA_GRE_LOCAL */ nla_total_size(4) + /* IFLA_GRE_REMOTE */ nla_total_size(4) + /* IFLA_GRE_TTL */ nla_total_size(1) + /* IFLA_GRE_TOS */ nla_total_size(1) + /* IFLA_GRE_PMTUDISC */ nla_total_size(1) + /* IFLA_GRE_ENCAP_TYPE */ nla_total_size(2) + /* IFLA_GRE_ENCAP_FLAGS */ nla_total_size(2) + /* IFLA_GRE_ENCAP_SPORT */ nla_total_size(2) + /* IFLA_GRE_ENCAP_DPORT */ nla_total_size(2) + /* IFLA_GRE_COLLECT_METADATA */ nla_total_size(0) + /* IFLA_GRE_IGNORE_DF */ nla_total_size(1) + /* IFLA_GRE_FWMARK */ nla_total_size(4) + /* IFLA_GRE_ERSPAN_INDEX */ nla_total_size(4) + /* IFLA_GRE_ERSPAN_VER */ nla_total_size(1) + /* IFLA_GRE_ERSPAN_DIR */ nla_total_size(1) + /* IFLA_GRE_ERSPAN_HWID */ nla_total_size(2) + 0; } static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern *p = &t->parms; IP_TUNNEL_DECLARE_FLAGS(o_flags); ip_tunnel_flags_copy(o_flags, p->o_flags); if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) || nla_put_in_addr(skb, IFLA_GRE_REMOTE, p->iph.daddr) || nla_put_u8(skb, IFLA_GRE_TTL, p->iph.ttl) || nla_put_u8(skb, IFLA_GRE_TOS, p->iph.tos) || nla_put_u8(skb, IFLA_GRE_PMTUDISC, !!(p->iph.frag_off & htons(IP_DF))) || nla_put_u32(skb, IFLA_GRE_FWMARK, t->fwmark)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE, t->encap.type) || nla_put_be16(skb, IFLA_GRE_ENCAP_SPORT, t->encap.sport) || nla_put_be16(skb, IFLA_GRE_ENCAP_DPORT, t->encap.dport) || nla_put_u16(skb, IFLA_GRE_ENCAP_FLAGS, t->encap.flags)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GRE_IGNORE_DF, t->ignore_df)) goto nla_put_failure; if (t->collect_md) { if (nla_put_flag(skb, IFLA_GRE_COLLECT_METADATA)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int erspan_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (t->erspan_ver <= 2) { if (t->erspan_ver != 0 && !t->collect_md) __set_bit(IP_TUNNEL_KEY_BIT, t->parms.o_flags); if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) goto nla_put_failure; if (t->erspan_ver == 1) { if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) goto nla_put_failure; } else if (t->erspan_ver == 2) { if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) goto nla_put_failure; } } return ipgre_fill_info(skb, dev); nla_put_failure: return -EMSGSIZE; } static void erspan_setup(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); ether_setup(dev); dev->max_mtu = 0; dev->netdev_ops = &erspan_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, erspan_net_id); t->erspan_ver = 1; } static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_LINK] = { .type = NLA_U32 }, [IFLA_GRE_IFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, [IFLA_GRE_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, [IFLA_GRE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_TOS] = { .type = NLA_U8 }, [IFLA_GRE_PMTUDISC] = { .type = NLA_U8 }, [IFLA_GRE_ENCAP_TYPE] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_DPORT] = { .type = NLA_U16 }, [IFLA_GRE_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_GRE_IGNORE_DF] = { .type = NLA_U8 }, [IFLA_GRE_FWMARK] = { .type = NLA_U32 }, [IFLA_GRE_ERSPAN_INDEX] = { .type = NLA_U32 }, [IFLA_GRE_ERSPAN_VER] = { .type = NLA_U8 }, [IFLA_GRE_ERSPAN_DIR] = { .type = NLA_U8 }, [IFLA_GRE_ERSPAN_HWID] = { .type = NLA_U16 }, }; static struct rtnl_link_ops ipgre_link_ops __read_mostly = { .kind = "gre", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipgre_tunnel_setup, .validate = ipgre_tunnel_validate, .newlink = ipgre_newlink, .changelink = ipgre_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = ipgre_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static struct rtnl_link_ops ipgre_tap_ops __read_mostly = { .kind = "gretap", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipgre_tap_setup, .validate = ipgre_tap_validate, .newlink = ipgre_newlink, .changelink = ipgre_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = ipgre_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static struct rtnl_link_ops erspan_link_ops __read_mostly = { .kind = "erspan", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = erspan_setup, .validate = erspan_validate, .newlink = erspan_newlink, .changelink = erspan_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = erspan_fill_info, .get_link_net = ip_tunnel_get_link_net, }; struct net_device *gretap_fb_dev_create(struct net *net, const char *name, u8 name_assign_type) { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; LIST_HEAD(list_kill); struct ip_tunnel *t; int err; memset(&tb, 0, sizeof(tb)); dev = rtnl_create_link(net, name, name_assign_type, &ipgre_tap_ops, tb, NULL); if (IS_ERR(dev)) return dev; /* Configure flow based GRE device. */ t = netdev_priv(dev); t->collect_md = true; err = ipgre_newlink(net, dev, tb, NULL, NULL); if (err < 0) { free_netdev(dev); return ERR_PTR(err); } /* openvswitch users expect packet sizes to be unrestricted, * so set the largest MTU we can. */ err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false); if (err) goto out; err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto out; return dev; out: ip_tunnel_dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(gretap_fb_dev_create); static int __net_init ipgre_tap_init_net(struct net *net) { return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0"); } static void __net_exit ipgre_tap_exit_batch_rtnl(struct list_head *list_net, struct list_head *dev_to_kill) { ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops, dev_to_kill); } static struct pernet_operations ipgre_tap_net_ops = { .init = ipgre_tap_init_net, .exit_batch_rtnl = ipgre_tap_exit_batch_rtnl, .id = &gre_tap_net_id, .size = sizeof(struct ip_tunnel_net), }; static int __net_init erspan_init_net(struct net *net) { return ip_tunnel_init_net(net, erspan_net_id, &erspan_link_ops, "erspan0"); } static void __net_exit erspan_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_to_kill) { ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops, dev_to_kill); } static struct pernet_operations erspan_net_ops = { .init = erspan_init_net, .exit_batch_rtnl = erspan_exit_batch_rtnl, .id = &erspan_net_id, .size = sizeof(struct ip_tunnel_net), }; static int __init ipgre_init(void) { int err; pr_info("GRE over IPv4 tunneling driver\n"); err = register_pernet_device(&ipgre_net_ops); if (err < 0) return err; err = register_pernet_device(&ipgre_tap_net_ops); if (err < 0) goto pnet_tap_failed; err = register_pernet_device(&erspan_net_ops); if (err < 0) goto pnet_erspan_failed; err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO); if (err < 0) { pr_info("%s: can't add protocol\n", __func__); goto add_proto_failed; } err = rtnl_link_register(&ipgre_link_ops); if (err < 0) goto rtnl_link_failed; err = rtnl_link_register(&ipgre_tap_ops); if (err < 0) goto tap_ops_failed; err = rtnl_link_register(&erspan_link_ops); if (err < 0) goto erspan_link_failed; return 0; erspan_link_failed: rtnl_link_unregister(&ipgre_tap_ops); tap_ops_failed: rtnl_link_unregister(&ipgre_link_ops); rtnl_link_failed: gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); add_proto_failed: unregister_pernet_device(&erspan_net_ops); pnet_erspan_failed: unregister_pernet_device(&ipgre_tap_net_ops); pnet_tap_failed: unregister_pernet_device(&ipgre_net_ops); return err; } static void __exit ipgre_fini(void) { rtnl_link_unregister(&ipgre_tap_ops); rtnl_link_unregister(&ipgre_link_ops); rtnl_link_unregister(&erspan_link_ops); gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); unregister_pernet_device(&ipgre_tap_net_ops); unregister_pernet_device(&ipgre_net_ops); unregister_pernet_device(&erspan_net_ops); } module_init(ipgre_init); module_exit(ipgre_fini); MODULE_DESCRIPTION("IPv4 GRE tunnels over IP library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("gre"); MODULE_ALIAS_RTNL_LINK("gretap"); MODULE_ALIAS_RTNL_LINK("erspan"); MODULE_ALIAS_NETDEV("gre0"); MODULE_ALIAS_NETDEV("gretap0"); MODULE_ALIAS_NETDEV("erspan0"); |
| 6 6 6 6 6 6 6 6 6 6 6 6 5 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2013 Politecnico di Torino, Italy * TORSEC group -- https://security.polito.it * * Author: Roberto Sassu <roberto.sassu@polito.it> * * File: ima_template_lib.c * Library of supported template fields. */ #include "ima_template_lib.h" #include <linux/xattr.h> #include <linux/evm.h> static bool ima_template_hash_algo_allowed(u8 algo) { if (algo == HASH_ALGO_SHA1 || algo == HASH_ALGO_MD5) return true; return false; } enum data_formats { DATA_FMT_DIGEST = 0, DATA_FMT_DIGEST_WITH_ALGO, DATA_FMT_DIGEST_WITH_TYPE_AND_ALGO, DATA_FMT_STRING, DATA_FMT_HEX, DATA_FMT_UINT }; enum digest_type { DIGEST_TYPE_IMA, DIGEST_TYPE_VERITY, DIGEST_TYPE__LAST }; #define DIGEST_TYPE_NAME_LEN_MAX 7 /* including NUL */ static const char * const digest_type_name[DIGEST_TYPE__LAST] = { [DIGEST_TYPE_IMA] = "ima", [DIGEST_TYPE_VERITY] = "verity" }; static int ima_write_template_field_data(const void *data, const u32 datalen, enum data_formats datafmt, struct ima_field_data *field_data) { u8 *buf, *buf_ptr; u32 buflen = datalen; if (datafmt == DATA_FMT_STRING) buflen = datalen + 1; buf = kzalloc(buflen, GFP_KERNEL); if (!buf) return -ENOMEM; memcpy(buf, data, datalen); /* * Replace all space characters with underscore for event names and * strings. This avoid that, during the parsing of a measurements list, * filenames with spaces or that end with the suffix ' (deleted)' are * split into multiple template fields (the space is the delimitator * character for measurements lists in ASCII format). */ if (datafmt == DATA_FMT_STRING) { for (buf_ptr = buf; buf_ptr - buf < datalen; buf_ptr++) if (*buf_ptr == ' ') *buf_ptr = '_'; } field_data->data = buf; field_data->len = buflen; return 0; } static void ima_show_template_data_ascii(struct seq_file *m, enum ima_show_type show, enum data_formats datafmt, struct ima_field_data *field_data) { u8 *buf_ptr = field_data->data; u32 buflen = field_data->len; switch (datafmt) { case DATA_FMT_DIGEST_WITH_TYPE_AND_ALGO: case DATA_FMT_DIGEST_WITH_ALGO: buf_ptr = strrchr(field_data->data, ':'); if (buf_ptr != field_data->data) seq_printf(m, "%s", field_data->data); /* skip ':' and '\0' */ buf_ptr += 2; buflen -= buf_ptr - field_data->data; fallthrough; case DATA_FMT_DIGEST: case DATA_FMT_HEX: if (!buflen) break; ima_print_digest(m, buf_ptr, buflen); break; case DATA_FMT_STRING: seq_printf(m, "%s", buf_ptr); break; case DATA_FMT_UINT: switch (field_data->len) { case sizeof(u8): seq_printf(m, "%u", *(u8 *)buf_ptr); break; case sizeof(u16): if (ima_canonical_fmt) seq_printf(m, "%u", le16_to_cpu(*(__le16 *)buf_ptr)); else seq_printf(m, "%u", *(u16 *)buf_ptr); break; case sizeof(u32): if (ima_canonical_fmt) seq_printf(m, "%u", le32_to_cpu(*(__le32 *)buf_ptr)); else seq_printf(m, "%u", *(u32 *)buf_ptr); break; case sizeof(u64): if (ima_canonical_fmt) seq_printf(m, "%llu", le64_to_cpu(*(__le64 *)buf_ptr)); else seq_printf(m, "%llu", *(u64 *)buf_ptr); break; default: break; } break; default: break; } } static void ima_show_template_data_binary(struct seq_file *m, enum ima_show_type show, enum data_formats datafmt, struct ima_field_data *field_data) { u32 len = (show == IMA_SHOW_BINARY_OLD_STRING_FMT) ? strlen(field_data->data) : field_data->len; if (show != IMA_SHOW_BINARY_NO_FIELD_LEN) { u32 field_len = !ima_canonical_fmt ? len : (__force u32)cpu_to_le32(len); ima_putc(m, &field_len, sizeof(field_len)); } if (!len) return; ima_putc(m, field_data->data, len); } static void ima_show_template_field_data(struct seq_file *m, enum ima_show_type show, enum data_formats datafmt, struct ima_field_data *field_data) { switch (show) { case IMA_SHOW_ASCII: ima_show_template_data_ascii(m, show, datafmt, field_data); break; case IMA_SHOW_BINARY: case IMA_SHOW_BINARY_NO_FIELD_LEN: case IMA_SHOW_BINARY_OLD_STRING_FMT: ima_show_template_data_binary(m, show, datafmt, field_data); break; default: break; } } void ima_show_template_digest(struct seq_file *m, enum ima_show_type show, struct ima_field_data *field_data) { ima_show_template_field_data(m, show, DATA_FMT_DIGEST, field_data); } void ima_show_template_digest_ng(struct seq_file *m, enum ima_show_type show, struct ima_field_data *field_data) { ima_show_template_field_data(m, show, DATA_FMT_DIGEST_WITH_ALGO, field_data); } void ima_show_template_digest_ngv2(struct seq_file *m, enum ima_show_type show, struct ima_field_data *field_data) { ima_show_template_field_data(m, show, DATA_FMT_DIGEST_WITH_TYPE_AND_ALGO, field_data); } void ima_show_template_string(struct seq_file *m, enum ima_show_type show, struct ima_field_data *field_data) { ima_show_template_field_data(m, show, DATA_FMT_STRING, field_data); } void ima_show_template_sig(struct seq_file *m, enum ima_show_type show, struct ima_field_data *field_data) { ima_show_template_field_data(m, show, DATA_FMT_HEX, field_data); } void ima_show_template_buf(struct seq_file *m, enum ima_show_type show, struct ima_field_data *field_data) { ima_show_template_field_data(m, show, DATA_FMT_HEX, field_data); } void ima_show_template_uint(struct seq_file *m, enum ima_show_type show, struct ima_field_data *field_data) { ima_show_template_field_data(m, show, DATA_FMT_UINT, field_data); } /** * ima_parse_buf() - Parses lengths and data from an input buffer * @bufstartp: Buffer start address. * @bufendp: Buffer end address. * @bufcurp: Pointer to remaining (non-parsed) data. * @maxfields: Length of fields array. * @fields: Array containing lengths and pointers of parsed data. * @curfields: Number of array items containing parsed data. * @len_mask: Bitmap (if bit is set, data length should not be parsed). * @enforce_mask: Check if curfields == maxfields and/or bufcurp == bufendp. * @bufname: String identifier of the input buffer. * * Return: 0 on success, -EINVAL on error. */ int ima_parse_buf(void *bufstartp, void *bufendp, void **bufcurp, int maxfields, struct ima_field_data *fields, int *curfields, unsigned long *len_mask, int enforce_mask, char *bufname) { void *bufp = bufstartp; int i; for (i = 0; i < maxfields; i++) { if (len_mask == NULL || !test_bit(i, len_mask)) { if (bufp > (bufendp - sizeof(u32))) break; if (ima_canonical_fmt) fields[i].len = le32_to_cpu(*(__le32 *)bufp); else fields[i].len = *(u32 *)bufp; bufp += sizeof(u32); } if (bufp > (bufendp - fields[i].len)) break; fields[i].data = bufp; bufp += fields[i].len; } if ((enforce_mask & ENFORCE_FIELDS) && i != maxfields) { pr_err("%s: nr of fields mismatch: expected: %d, current: %d\n", bufname, maxfields, i); return -EINVAL; } if ((enforce_mask & ENFORCE_BUFEND) && bufp != bufendp) { pr_err("%s: buf end mismatch: expected: %p, current: %p\n", bufname, bufendp, bufp); return -EINVAL; } if (curfields) *curfields = i; if (bufcurp) *bufcurp = bufp; return 0; } static int ima_eventdigest_init_common(const u8 *digest, u32 digestsize, u8 digest_type, u8 hash_algo, struct ima_field_data *field_data) { /* * digest formats: * - DATA_FMT_DIGEST: digest * - DATA_FMT_DIGEST_WITH_ALGO: <hash algo> + ':' + '\0' + digest, * - DATA_FMT_DIGEST_WITH_TYPE_AND_ALGO: * <digest type> + ':' + <hash algo> + ':' + '\0' + digest, * * where 'DATA_FMT_DIGEST' is the original digest format ('d') * with a hash size limitation of 20 bytes, * where <digest type> is either "ima" or "verity", * where <hash algo> is the hash_algo_name[] string. */ u8 buffer[DIGEST_TYPE_NAME_LEN_MAX + CRYPTO_MAX_ALG_NAME + 2 + IMA_MAX_DIGEST_SIZE] = { 0 }; enum data_formats fmt = DATA_FMT_DIGEST; u32 offset = 0; if (digest_type < DIGEST_TYPE__LAST && hash_algo < HASH_ALGO__LAST) { fmt = DATA_FMT_DIGEST_WITH_TYPE_AND_ALGO; offset += 1 + sprintf(buffer, "%s:%s:", digest_type_name[digest_type], hash_algo_name[hash_algo]); } else if (hash_algo < HASH_ALGO__LAST) { fmt = DATA_FMT_DIGEST_WITH_ALGO; offset += 1 + sprintf(buffer, "%s:", hash_algo_name[hash_algo]); } if (digest) { memcpy(buffer + offset, digest, digestsize); } else { /* * If digest is NULL, the event being recorded is a violation. * Make room for the digest by increasing the offset by the * hash algorithm digest size. If the hash algorithm is not * specified increase the offset by IMA_DIGEST_SIZE which * fits SHA1 or MD5 */ if (hash_algo < HASH_ALGO__LAST) offset += hash_digest_size[hash_algo]; else offset += IMA_DIGEST_SIZE; } return ima_write_template_field_data(buffer, offset + digestsize, fmt, field_data); } /* * This function writes the digest of an event (with size limit). */ int ima_eventdigest_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { struct ima_max_digest_data hash; struct ima_digest_data *hash_hdr = container_of(&hash.hdr, struct ima_digest_data, hdr); u8 *cur_digest = NULL; u32 cur_digestsize = 0; struct inode *inode; int result; memset(&hash, 0, sizeof(hash)); if (event_data->violation) /* recording a violation. */ goto out; if (ima_template_hash_algo_allowed(event_data->iint->ima_hash->algo)) { cur_digest = event_data->iint->ima_hash->digest; cur_digestsize = event_data->iint->ima_hash->length; goto out; } if ((const char *)event_data->filename == boot_aggregate_name) { if (ima_tpm_chip) { hash.hdr.algo = HASH_ALGO_SHA1; result = ima_calc_boot_aggregate(hash_hdr); /* algo can change depending on available PCR banks */ if (!result && hash.hdr.algo != HASH_ALGO_SHA1) result = -EINVAL; if (result < 0) memset(&hash, 0, sizeof(hash)); } cur_digest = hash_hdr->digest; cur_digestsize = hash_digest_size[HASH_ALGO_SHA1]; goto out; } if (!event_data->file) /* missing info to re-calculate the digest */ return -EINVAL; inode = file_inode(event_data->file); hash.hdr.algo = ima_template_hash_algo_allowed(ima_hash_algo) ? ima_hash_algo : HASH_ALGO_SHA1; result = ima_calc_file_hash(event_data->file, hash_hdr); if (result) { integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, event_data->filename, "collect_data", "failed", result, 0); return result; } cur_digest = hash_hdr->digest; cur_digestsize = hash.hdr.length; out: return ima_eventdigest_init_common(cur_digest, cur_digestsize, DIGEST_TYPE__LAST, HASH_ALGO__LAST, field_data); } /* * This function writes the digest of an event (without size limit). */ int ima_eventdigest_ng_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { u8 *cur_digest = NULL, hash_algo = ima_hash_algo; u32 cur_digestsize = 0; if (event_data->violation) /* recording a violation. */ goto out; cur_digest = event_data->iint->ima_hash->digest; cur_digestsize = event_data->iint->ima_hash->length; hash_algo = event_data->iint->ima_hash->algo; out: return ima_eventdigest_init_common(cur_digest, cur_digestsize, DIGEST_TYPE__LAST, hash_algo, field_data); } /* * This function writes the digest of an event (without size limit), * prefixed with both the digest type and hash algorithm. */ int ima_eventdigest_ngv2_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { u8 *cur_digest = NULL, hash_algo = ima_hash_algo; u32 cur_digestsize = 0; u8 digest_type = DIGEST_TYPE_IMA; if (event_data->violation) /* recording a violation. */ goto out; cur_digest = event_data->iint->ima_hash->digest; cur_digestsize = event_data->iint->ima_hash->length; hash_algo = event_data->iint->ima_hash->algo; if (event_data->iint->flags & IMA_VERITY_REQUIRED) digest_type = DIGEST_TYPE_VERITY; out: return ima_eventdigest_init_common(cur_digest, cur_digestsize, digest_type, hash_algo, field_data); } /* * This function writes the digest of the file which is expected to match the * digest contained in the file's appended signature. */ int ima_eventdigest_modsig_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { enum hash_algo hash_algo; const u8 *cur_digest; u32 cur_digestsize; if (!event_data->modsig) return 0; if (event_data->violation) { /* Recording a violation. */ hash_algo = HASH_ALGO_SHA1; cur_digest = NULL; cur_digestsize = 0; } else { int rc; rc = ima_get_modsig_digest(event_data->modsig, &hash_algo, &cur_digest, &cur_digestsize); if (rc) return rc; else if (hash_algo == HASH_ALGO__LAST || cur_digestsize == 0) /* There was some error collecting the digest. */ return -EINVAL; } return ima_eventdigest_init_common(cur_digest, cur_digestsize, DIGEST_TYPE__LAST, hash_algo, field_data); } static int ima_eventname_init_common(struct ima_event_data *event_data, struct ima_field_data *field_data, bool size_limit) { const char *cur_filename = NULL; struct name_snapshot filename; u32 cur_filename_len = 0; bool snapshot = false; int ret; BUG_ON(event_data->filename == NULL && event_data->file == NULL); if (event_data->filename) { cur_filename = event_data->filename; cur_filename_len = strlen(event_data->filename); if (!size_limit || cur_filename_len <= IMA_EVENT_NAME_LEN_MAX) goto out; } if (event_data->file) { take_dentry_name_snapshot(&filename, event_data->file->f_path.dentry); snapshot = true; cur_filename = filename.name.name; cur_filename_len = strlen(cur_filename); } else /* * Truncate filename if the latter is too long and * the file descriptor is not available. */ cur_filename_len = IMA_EVENT_NAME_LEN_MAX; out: ret = ima_write_template_field_data(cur_filename, cur_filename_len, DATA_FMT_STRING, field_data); if (snapshot) release_dentry_name_snapshot(&filename); return ret; } /* * This function writes the name of an event (with size limit). */ int ima_eventname_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { return ima_eventname_init_common(event_data, field_data, true); } /* * This function writes the name of an event (without size limit). */ int ima_eventname_ng_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { return ima_eventname_init_common(event_data, field_data, false); } /* * ima_eventsig_init - include the file signature as part of the template data */ int ima_eventsig_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { struct evm_ima_xattr_data *xattr_value = event_data->xattr_value; if (!xattr_value || (xattr_value->type != EVM_IMA_XATTR_DIGSIG && xattr_value->type != IMA_VERITY_DIGSIG)) return ima_eventevmsig_init(event_data, field_data); return ima_write_template_field_data(xattr_value, event_data->xattr_len, DATA_FMT_HEX, field_data); } /* * ima_eventbuf_init - include the buffer(kexec-cmldine) as part of the * template data. */ int ima_eventbuf_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { if ((!event_data->buf) || (event_data->buf_len == 0)) return 0; return ima_write_template_field_data(event_data->buf, event_data->buf_len, DATA_FMT_HEX, field_data); } /* * ima_eventmodsig_init - include the appended file signature as part of the * template data */ int ima_eventmodsig_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { const void *data; u32 data_len; int rc; if (!event_data->modsig) return 0; /* * modsig is a runtime structure containing pointers. Get its raw data * instead. */ rc = ima_get_raw_modsig(event_data->modsig, &data, &data_len); if (rc) return rc; return ima_write_template_field_data(data, data_len, DATA_FMT_HEX, field_data); } /* * ima_eventevmsig_init - include the EVM portable signature as part of the * template data */ int ima_eventevmsig_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { struct evm_ima_xattr_data *xattr_data = NULL; int rc = 0; if (!event_data->file) return 0; rc = vfs_getxattr_alloc(&nop_mnt_idmap, file_dentry(event_data->file), XATTR_NAME_EVM, (char **)&xattr_data, 0, GFP_NOFS); if (rc <= 0 || xattr_data->type != EVM_XATTR_PORTABLE_DIGSIG) { rc = 0; goto out; } rc = ima_write_template_field_data((char *)xattr_data, rc, DATA_FMT_HEX, field_data); out: kfree(xattr_data); return rc; } static int ima_eventinodedac_init_common(struct ima_event_data *event_data, struct ima_field_data *field_data, bool get_uid) { unsigned int id; if (!event_data->file) return 0; if (get_uid) id = i_uid_read(file_inode(event_data->file)); else id = i_gid_read(file_inode(event_data->file)); if (ima_canonical_fmt) { if (sizeof(id) == sizeof(u16)) id = (__force u16)cpu_to_le16(id); else id = (__force u32)cpu_to_le32(id); } return ima_write_template_field_data((void *)&id, sizeof(id), DATA_FMT_UINT, field_data); } /* * ima_eventinodeuid_init - include the inode UID as part of the template * data */ int ima_eventinodeuid_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { return ima_eventinodedac_init_common(event_data, field_data, true); } /* * ima_eventinodegid_init - include the inode GID as part of the template * data */ int ima_eventinodegid_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { return ima_eventinodedac_init_common(event_data, field_data, false); } /* * ima_eventinodemode_init - include the inode mode as part of the template * data */ int ima_eventinodemode_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { struct inode *inode; u16 mode; if (!event_data->file) return 0; inode = file_inode(event_data->file); mode = inode->i_mode; if (ima_canonical_fmt) mode = (__force u16)cpu_to_le16(mode); return ima_write_template_field_data((char *)&mode, sizeof(mode), DATA_FMT_UINT, field_data); } static int ima_eventinodexattrs_init_common(struct ima_event_data *event_data, struct ima_field_data *field_data, char type) { u8 *buffer = NULL; int rc; if (!event_data->file) return 0; rc = evm_read_protected_xattrs(file_dentry(event_data->file), NULL, 0, type, ima_canonical_fmt); if (rc < 0) return 0; buffer = kmalloc(rc, GFP_KERNEL); if (!buffer) return 0; rc = evm_read_protected_xattrs(file_dentry(event_data->file), buffer, rc, type, ima_canonical_fmt); if (rc < 0) { rc = 0; goto out; } rc = ima_write_template_field_data((char *)buffer, rc, DATA_FMT_HEX, field_data); out: kfree(buffer); return rc; } /* * ima_eventinodexattrnames_init - include a list of xattr names as part of the * template data */ int ima_eventinodexattrnames_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { return ima_eventinodexattrs_init_common(event_data, field_data, 'n'); } /* * ima_eventinodexattrlengths_init - include a list of xattr lengths as part of * the template data */ int ima_eventinodexattrlengths_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { return ima_eventinodexattrs_init_common(event_data, field_data, 'l'); } /* * ima_eventinodexattrvalues_init - include a list of xattr values as part of * the template data */ int ima_eventinodexattrvalues_init(struct ima_event_data *event_data, struct ima_field_data *field_data) { return ima_eventinodexattrs_init_common(event_data, field_data, 'v'); } |
| 92 92 92 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/ptrace.c * * (C) Copyright 1999 Linus Torvalds * * Common interfaces for "ptrace()" which we do not want * to continually duplicate across every architecture. */ #include <linux/capability.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/task.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/ptrace.h> #include <linux/security.h> #include <linux/signal.h> #include <linux/uio.h> #include <linux/audit.h> #include <linux/pid_namespace.h> #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/regset.h> #include <linux/hw_breakpoint.h> #include <linux/cn_proc.h> #include <linux/compat.h> #include <linux/sched/signal.h> #include <linux/minmax.h> #include <linux/syscall_user_dispatch.h> #include <asm/syscall.h> /* for syscall_get_* */ /* * Access another process' address space via ptrace. * Source/target buffer must be kernel space, * Do not walk the page table directly, use get_user_pages */ int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret; mm = get_task_mm(tsk); if (!mm) return 0; if (!tsk->ptrace || (current != tsk->parent) || ((get_dumpable(mm) != SUID_DUMP_USER) && !ptracer_capable(tsk, mm->user_ns))) { mmput(mm); return 0; } ret = access_remote_vm(mm, addr, buf, len, gup_flags); mmput(mm); return ret; } void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, const struct cred *ptracer_cred) { BUG_ON(!list_empty(&child->ptrace_entry)); list_add(&child->ptrace_entry, &new_parent->ptraced); child->parent = new_parent; child->ptracer_cred = get_cred(ptracer_cred); } /* * ptrace a task: make the debugger its new parent and * move it to the ptrace list. * * Must be called with the tasklist lock write-held. */ static void ptrace_link(struct task_struct *child, struct task_struct *new_parent) { __ptrace_link(child, new_parent, current_cred()); } /** * __ptrace_unlink - unlink ptracee and restore its execution state * @child: ptracee to be unlinked * * Remove @child from the ptrace list, move it back to the original parent, * and restore the execution state so that it conforms to the group stop * state. * * Unlinking can happen via two paths - explicit PTRACE_DETACH or ptracer * exiting. For PTRACE_DETACH, unless the ptracee has been killed between * ptrace_check_attach() and here, it's guaranteed to be in TASK_TRACED. * If the ptracer is exiting, the ptracee can be in any state. * * After detach, the ptracee should be in a state which conforms to the * group stop. If the group is stopped or in the process of stopping, the * ptracee should be put into TASK_STOPPED; otherwise, it should be woken * up from TASK_TRACED. * * If the ptracee is in TASK_TRACED and needs to be moved to TASK_STOPPED, * it goes through TRACED -> RUNNING -> STOPPED transition which is similar * to but in the opposite direction of what happens while attaching to a * stopped task. However, in this direction, the intermediate RUNNING * state is not hidden even from the current ptracer and if it immediately * re-attaches and performs a WNOHANG wait(2), it may fail. * * CONTEXT: * write_lock_irq(tasklist_lock) */ void __ptrace_unlink(struct task_struct *child) { const struct cred *old_cred; BUG_ON(!child->ptrace); clear_task_syscall_work(child, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(child, SYSCALL_EMU); #endif child->parent = child->real_parent; list_del_init(&child->ptrace_entry); old_cred = child->ptracer_cred; child->ptracer_cred = NULL; put_cred(old_cred); spin_lock(&child->sighand->siglock); child->ptrace = 0; /* * Clear all pending traps and TRAPPING. TRAPPING should be * cleared regardless of JOBCTL_STOP_PENDING. Do it explicitly. */ task_clear_jobctl_pending(child, JOBCTL_TRAP_MASK); task_clear_jobctl_trapping(child); /* * Reinstate JOBCTL_STOP_PENDING if group stop is in effect and * @child isn't dead. */ if (!(child->flags & PF_EXITING) && (child->signal->flags & SIGNAL_STOP_STOPPED || child->signal->group_stop_count)) child->jobctl |= JOBCTL_STOP_PENDING; /* * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick * @child in the butt. Note that @resume should be used iff @child * is in TASK_TRACED; otherwise, we might unduly disrupt * TASK_KILLABLE sleeps. */ if (child->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child)) ptrace_signal_wake_up(child, true); spin_unlock(&child->sighand->siglock); } static bool looks_like_a_spurious_pid(struct task_struct *task) { if (task->exit_code != ((PTRACE_EVENT_EXEC << 8) | SIGTRAP)) return false; if (task_pid_vnr(task) == task->ptrace_message) return false; /* * The tracee changed its pid but the PTRACE_EVENT_EXEC event * was not wait()'ed, most probably debugger targets the old * leader which was destroyed in de_thread(). */ return true; } /* * Ensure that nothing can wake it up, even SIGKILL * * A task is switched to this state while a ptrace operation is in progress; * such that the ptrace operation is uninterruptible. */ static bool ptrace_freeze_traced(struct task_struct *task) { bool ret = false; /* Lockless, nobody but us can set this flag */ if (task->jobctl & JOBCTL_LISTENING) return ret; spin_lock_irq(&task->sighand->siglock); if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && !__fatal_signal_pending(task)) { task->jobctl |= JOBCTL_PTRACE_FROZEN; ret = true; } spin_unlock_irq(&task->sighand->siglock); return ret; } static void ptrace_unfreeze_traced(struct task_struct *task) { unsigned long flags; /* * The child may be awake and may have cleared * JOBCTL_PTRACE_FROZEN (see ptrace_resume). The child will * not set JOBCTL_PTRACE_FROZEN or enter __TASK_TRACED anew. */ if (lock_task_sighand(task, &flags)) { task->jobctl &= ~JOBCTL_PTRACE_FROZEN; if (__fatal_signal_pending(task)) { task->jobctl &= ~JOBCTL_TRACED; wake_up_state(task, __TASK_TRACED); } unlock_task_sighand(task, &flags); } } /** * ptrace_check_attach - check whether ptracee is ready for ptrace operation * @child: ptracee to check for * @ignore_state: don't check whether @child is currently %TASK_TRACED * * Check whether @child is being ptraced by %current and ready for further * ptrace operations. If @ignore_state is %false, @child also should be in * %TASK_TRACED state and on return the child is guaranteed to be traced * and not executing. If @ignore_state is %true, @child can be in any * state. * * CONTEXT: * Grabs and releases tasklist_lock and @child->sighand->siglock. * * RETURNS: * 0 on success, -ESRCH if %child is not ready. */ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) { int ret = -ESRCH; /* * We take the read lock around doing both checks to close a * possible race where someone else was tracing our child and * detached between these two checks. After this locked check, * we are sure that this is our traced child and that can only * be changed by us so it's not changing right after this. */ read_lock(&tasklist_lock); if (child->ptrace && child->parent == current) { /* * child->sighand can't be NULL, release_task() * does ptrace_unlink() before __exit_signal(). */ if (ignore_state || ptrace_freeze_traced(child)) ret = 0; } read_unlock(&tasklist_lock); if (!ret && !ignore_state && WARN_ON_ONCE(!wait_task_inactive(child, __TASK_TRACED|TASK_FROZEN))) ret = -ESRCH; return ret; } static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode) { if (mode & PTRACE_MODE_NOAUDIT) return ns_capable_noaudit(ns, CAP_SYS_PTRACE); return ns_capable(ns, CAP_SYS_PTRACE); } /* Returns 0 on success, -errno on denial. */ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) { const struct cred *cred = current_cred(), *tcred; struct mm_struct *mm; kuid_t caller_uid; kgid_t caller_gid; if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) { WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n"); return -EPERM; } /* May we inspect the given task? * This check is used both for attaching with ptrace * and for allowing access to sensitive information in /proc. * * ptrace_attach denies several cases that /proc allows * because setting up the necessary parent/child relationship * or halting the specified task is impossible. */ /* Don't let security modules deny introspection */ if (same_thread_group(task, current)) return 0; rcu_read_lock(); if (mode & PTRACE_MODE_FSCREDS) { caller_uid = cred->fsuid; caller_gid = cred->fsgid; } else { /* * Using the euid would make more sense here, but something * in userland might rely on the old behavior, and this * shouldn't be a security problem since * PTRACE_MODE_REALCREDS implies that the caller explicitly * used a syscall that requests access to another process * (and not a filesystem syscall to procfs). */ caller_uid = cred->uid; caller_gid = cred->gid; } tcred = __task_cred(task); if (uid_eq(caller_uid, tcred->euid) && uid_eq(caller_uid, tcred->suid) && uid_eq(caller_uid, tcred->uid) && gid_eq(caller_gid, tcred->egid) && gid_eq(caller_gid, tcred->sgid) && gid_eq(caller_gid, tcred->gid)) goto ok; if (ptrace_has_cap(tcred->user_ns, mode)) goto ok; rcu_read_unlock(); return -EPERM; ok: rcu_read_unlock(); /* * If a task drops privileges and becomes nondumpable (through a syscall * like setresuid()) while we are trying to access it, we must ensure * that the dumpability is read after the credentials; otherwise, * we may be able to attach to a task that we shouldn't be able to * attach to (as if the task had dropped privileges without becoming * nondumpable). * Pairs with a write barrier in commit_creds(). */ smp_rmb(); mm = task->mm; if (mm && ((get_dumpable(mm) != SUID_DUMP_USER) && !ptrace_has_cap(mm->user_ns, mode))) return -EPERM; return security_ptrace_access_check(task, mode); } bool ptrace_may_access(struct task_struct *task, unsigned int mode) { int err; task_lock(task); err = __ptrace_may_access(task, mode); task_unlock(task); return !err; } static int check_ptrace_options(unsigned long data) { if (data & ~(unsigned long)PTRACE_O_MASK) return -EINVAL; if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) { if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) || !IS_ENABLED(CONFIG_SECCOMP)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (seccomp_mode(¤t->seccomp) != SECCOMP_MODE_DISABLED || current->ptrace & PT_SUSPEND_SECCOMP) return -EPERM; } return 0; } static inline void ptrace_set_stopped(struct task_struct *task, bool seize) { guard(spinlock)(&task->sighand->siglock); /* SEIZE doesn't trap tracee on attach */ if (!seize) send_signal_locked(SIGSTOP, SEND_SIG_PRIV, task, PIDTYPE_PID); /* * If the task is already STOPPED, set JOBCTL_TRAP_STOP and * TRAPPING, and kick it so that it transits to TRACED. TRAPPING * will be cleared if the child completes the transition or any * event which clears the group stop states happens. We'll wait * for the transition to complete before returning from this * function. * * This hides STOPPED -> RUNNING -> TRACED transition from the * attaching thread but a different thread in the same group can * still observe the transient RUNNING state. IOW, if another * thread's WNOHANG wait(2) on the stopped tracee races against * ATTACH, the wait(2) may fail due to the transient RUNNING. * * The following task_is_stopped() test is safe as both transitions * in and out of STOPPED are protected by siglock. */ if (task_is_stopped(task) && task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) { task->jobctl &= ~JOBCTL_STOPPED; signal_wake_up_state(task, __TASK_STOPPED); } } static int ptrace_attach(struct task_struct *task, long request, unsigned long addr, unsigned long flags) { bool seize = (request == PTRACE_SEIZE); int retval; if (seize) { if (addr != 0) return -EIO; /* * This duplicates the check in check_ptrace_options() because * ptrace_attach() and ptrace_setoptions() have historically * used different error codes for unknown ptrace options. */ if (flags & ~(unsigned long)PTRACE_O_MASK) return -EIO; retval = check_ptrace_options(flags); if (retval) return retval; flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT); } else { flags = PT_PTRACED; } audit_ptrace(task); if (unlikely(task->flags & PF_KTHREAD)) return -EPERM; if (same_thread_group(task, current)) return -EPERM; /* * Protect exec's credential calculations against our interference; * SUID, SGID and LSM creds get determined differently * under ptrace. */ scoped_cond_guard (mutex_intr, return -ERESTARTNOINTR, &task->signal->cred_guard_mutex) { scoped_guard (task_lock, task) { retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS); if (retval) return retval; } scoped_guard (write_lock_irq, &tasklist_lock) { if (unlikely(task->exit_state)) return -EPERM; if (task->ptrace) return -EPERM; task->ptrace = flags; ptrace_link(task, current); ptrace_set_stopped(task, seize); } } /* * We do not bother to change retval or clear JOBCTL_TRAPPING * if wait_on_bit() was interrupted by SIGKILL. The tracer will * not return to user-mode, it will exit and clear this bit in * __ptrace_unlink() if it wasn't already cleared by the tracee; * and until then nobody can ptrace this task. */ wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE); proc_ptrace_connector(task, PTRACE_ATTACH); return 0; } /** * ptrace_traceme -- helper for PTRACE_TRACEME * * Performs checks and sets PT_PTRACED. * Should be used by all ptrace implementations for PTRACE_TRACEME. */ static int ptrace_traceme(void) { int ret = -EPERM; write_lock_irq(&tasklist_lock); /* Are we already being traced? */ if (!current->ptrace) { ret = security_ptrace_traceme(current->parent); /* * Check PF_EXITING to ensure ->real_parent has not passed * exit_ptrace(). Otherwise we don't report the error but * pretend ->real_parent untraces us right after return. */ if (!ret && !(current->real_parent->flags & PF_EXITING)) { current->ptrace = PT_PTRACED; ptrace_link(current, current->real_parent); } } write_unlock_irq(&tasklist_lock); return ret; } /* * Called with irqs disabled, returns true if childs should reap themselves. */ static int ignoring_children(struct sighand_struct *sigh) { int ret; spin_lock(&sigh->siglock); ret = (sigh->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) || (sigh->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT); spin_unlock(&sigh->siglock); return ret; } /* * Called with tasklist_lock held for writing. * Unlink a traced task, and clean it up if it was a traced zombie. * Return true if it needs to be reaped with release_task(). * (We can't call release_task() here because we already hold tasklist_lock.) * * If it's a zombie, our attachedness prevented normal parent notification * or self-reaping. Do notification now if it would have happened earlier. * If it should reap itself, return true. * * If it's our own child, there is no notification to do. But if our normal * children self-reap, then this child was prevented by ptrace and we must * reap it now, in that case we must also wake up sub-threads sleeping in * do_wait(). */ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p) { bool dead; __ptrace_unlink(p); if (p->exit_state != EXIT_ZOMBIE) return false; dead = !thread_group_leader(p); if (!dead && thread_group_empty(p)) { if (!same_thread_group(p->real_parent, tracer)) dead = do_notify_parent(p, p->exit_signal); else if (ignoring_children(tracer->sighand)) { __wake_up_parent(p, tracer); dead = true; } } /* Mark it as in the process of being reaped. */ if (dead) p->exit_state = EXIT_DEAD; return dead; } static int ptrace_detach(struct task_struct *child, unsigned int data) { if (!valid_signal(data)) return -EIO; /* Architecture-specific hardware disable .. */ ptrace_disable(child); write_lock_irq(&tasklist_lock); /* * We rely on ptrace_freeze_traced(). It can't be killed and * untraced by another thread, it can't be a zombie. */ WARN_ON(!child->ptrace || child->exit_state); /* * tasklist_lock avoids the race with wait_task_stopped(), see * the comment in ptrace_resume(). */ child->exit_code = data; __ptrace_detach(current, child); write_unlock_irq(&tasklist_lock); proc_ptrace_connector(child, PTRACE_DETACH); return 0; } /* * Detach all tasks we were using ptrace on. Called with tasklist held * for writing. */ void exit_ptrace(struct task_struct *tracer, struct list_head *dead) { struct task_struct *p, *n; list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) { if (unlikely(p->ptrace & PT_EXITKILL)) send_sig_info(SIGKILL, SEND_SIG_PRIV, p); if (__ptrace_detach(tracer, p)) list_add(&p->ptrace_entry, dead); } } int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len) { int copied = 0; while (len > 0) { char buf[128]; int this_len, retval; this_len = (len > sizeof(buf)) ? sizeof(buf) : len; retval = ptrace_access_vm(tsk, src, buf, this_len, FOLL_FORCE); if (!retval) { if (copied) break; return -EIO; } if (copy_to_user(dst, buf, retval)) return -EFAULT; copied += retval; src += retval; dst += retval; len -= retval; } return copied; } int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len) { int copied = 0; while (len > 0) { char buf[128]; int this_len, retval; this_len = (len > sizeof(buf)) ? sizeof(buf) : len; if (copy_from_user(buf, src, this_len)) return -EFAULT; retval = ptrace_access_vm(tsk, dst, buf, this_len, FOLL_FORCE | FOLL_WRITE); if (!retval) { if (copied) break; return -EIO; } copied += retval; src += retval; dst += retval; len -= retval; } return copied; } static int ptrace_setoptions(struct task_struct *child, unsigned long data) { unsigned flags; int ret; ret = check_ptrace_options(data); if (ret) return ret; /* Avoid intermediate state when all opts are cleared */ flags = child->ptrace; flags &= ~(PTRACE_O_MASK << PT_OPT_FLAG_SHIFT); flags |= (data << PT_OPT_FLAG_SHIFT); child->ptrace = flags; return 0; } static int ptrace_getsiginfo(struct task_struct *child, kernel_siginfo_t *info) { unsigned long flags; int error = -ESRCH; if (lock_task_sighand(child, &flags)) { error = -EINVAL; if (likely(child->last_siginfo != NULL)) { copy_siginfo(info, child->last_siginfo); error = 0; } unlock_task_sighand(child, &flags); } return error; } static int ptrace_setsiginfo(struct task_struct *child, const kernel_siginfo_t *info) { unsigned long flags; int error = -ESRCH; if (lock_task_sighand(child, &flags)) { error = -EINVAL; if (likely(child->last_siginfo != NULL)) { copy_siginfo(child->last_siginfo, info); error = 0; } unlock_task_sighand(child, &flags); } return error; } static int ptrace_peek_siginfo(struct task_struct *child, unsigned long addr, unsigned long data) { struct ptrace_peeksiginfo_args arg; struct sigpending *pending; struct sigqueue *q; int ret, i; ret = copy_from_user(&arg, (void __user *) addr, sizeof(struct ptrace_peeksiginfo_args)); if (ret) return -EFAULT; if (arg.flags & ~PTRACE_PEEKSIGINFO_SHARED) return -EINVAL; /* unknown flags */ if (arg.nr < 0) return -EINVAL; /* Ensure arg.off fits in an unsigned long */ if (arg.off > ULONG_MAX) return 0; if (arg.flags & PTRACE_PEEKSIGINFO_SHARED) pending = &child->signal->shared_pending; else pending = &child->pending; for (i = 0; i < arg.nr; ) { kernel_siginfo_t info; unsigned long off = arg.off + i; bool found = false; spin_lock_irq(&child->sighand->siglock); list_for_each_entry(q, &pending->list, list) { if (!off--) { found = true; copy_siginfo(&info, &q->info); break; } } spin_unlock_irq(&child->sighand->siglock); if (!found) /* beyond the end of the list */ break; #ifdef CONFIG_COMPAT if (unlikely(in_compat_syscall())) { compat_siginfo_t __user *uinfo = compat_ptr(data); if (copy_siginfo_to_user32(uinfo, &info)) { ret = -EFAULT; break; } } else #endif { siginfo_t __user *uinfo = (siginfo_t __user *) data; if (copy_siginfo_to_user(uinfo, &info)) { ret = -EFAULT; break; } } data += sizeof(siginfo_t); i++; if (signal_pending(current)) break; cond_resched(); } if (i > 0) return i; return ret; } #ifdef CONFIG_RSEQ static long ptrace_get_rseq_configuration(struct task_struct *task, unsigned long size, void __user *data) { struct ptrace_rseq_configuration conf = { .rseq_abi_pointer = (u64)(uintptr_t)task->rseq, .rseq_abi_size = task->rseq_len, .signature = task->rseq_sig, .flags = 0, }; size = min_t(unsigned long, size, sizeof(conf)); if (copy_to_user(data, &conf, size)) return -EFAULT; return sizeof(conf); } #endif #define is_singlestep(request) ((request) == PTRACE_SINGLESTEP) #ifdef PTRACE_SINGLEBLOCK #define is_singleblock(request) ((request) == PTRACE_SINGLEBLOCK) #else #define is_singleblock(request) 0 #endif #ifdef PTRACE_SYSEMU #define is_sysemu_singlestep(request) ((request) == PTRACE_SYSEMU_SINGLESTEP) #else #define is_sysemu_singlestep(request) 0 #endif static int ptrace_resume(struct task_struct *child, long request, unsigned long data) { if (!valid_signal(data)) return -EIO; if (request == PTRACE_SYSCALL) set_task_syscall_work(child, SYSCALL_TRACE); else clear_task_syscall_work(child, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) if (request == PTRACE_SYSEMU || request == PTRACE_SYSEMU_SINGLESTEP) set_task_syscall_work(child, SYSCALL_EMU); else clear_task_syscall_work(child, SYSCALL_EMU); #endif if (is_singleblock(request)) { if (unlikely(!arch_has_block_step())) return -EIO; user_enable_block_step(child); } else if (is_singlestep(request) || is_sysemu_singlestep(request)) { if (unlikely(!arch_has_single_step())) return -EIO; user_enable_single_step(child); } else { user_disable_single_step(child); } /* * Change ->exit_code and ->state under siglock to avoid the race * with wait_task_stopped() in between; a non-zero ->exit_code will * wrongly look like another report from tracee. * * Note that we need siglock even if ->exit_code == data and/or this * status was not reported yet, the new status must not be cleared by * wait_task_stopped() after resume. */ spin_lock_irq(&child->sighand->siglock); child->exit_code = data; child->jobctl &= ~JOBCTL_TRACED; wake_up_state(child, __TASK_TRACED); spin_unlock_irq(&child->sighand->siglock); return 0; } #ifdef CONFIG_HAVE_ARCH_TRACEHOOK static const struct user_regset * find_regset(const struct user_regset_view *view, unsigned int type) { const struct user_regset *regset; int n; for (n = 0; n < view->n; ++n) { regset = view->regsets + n; if (regset->core_note_type == type) return regset; } return NULL; } static int ptrace_regset(struct task_struct *task, int req, unsigned int type, struct iovec *kiov) { const struct user_regset_view *view = task_user_regset_view(task); const struct user_regset *regset = find_regset(view, type); int regset_no; if (!regset || (kiov->iov_len % regset->size) != 0) return -EINVAL; regset_no = regset - view->regsets; kiov->iov_len = min(kiov->iov_len, (__kernel_size_t) (regset->n * regset->size)); if (req == PTRACE_GETREGSET) return copy_regset_to_user(task, view, regset_no, 0, kiov->iov_len, kiov->iov_base); else return copy_regset_from_user(task, view, regset_no, 0, kiov->iov_len, kiov->iov_base); } /* * This is declared in linux/regset.h and defined in machine-dependent * code. We put the export here, near the primary machine-neutral use, * to ensure no machine forgets it. */ EXPORT_SYMBOL_GPL(task_user_regset_view); static unsigned long ptrace_get_syscall_info_entry(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { unsigned long args[ARRAY_SIZE(info->entry.args)]; int i; info->op = PTRACE_SYSCALL_INFO_ENTRY; info->entry.nr = syscall_get_nr(child, regs); syscall_get_arguments(child, regs, args); for (i = 0; i < ARRAY_SIZE(args); i++) info->entry.args[i] = args[i]; /* args is the last field in struct ptrace_syscall_info.entry */ return offsetofend(struct ptrace_syscall_info, entry.args); } static unsigned long ptrace_get_syscall_info_seccomp(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { /* * As struct ptrace_syscall_info.entry is currently a subset * of struct ptrace_syscall_info.seccomp, it makes sense to * initialize that subset using ptrace_get_syscall_info_entry(). * This can be reconsidered in the future if these structures * diverge significantly enough. */ ptrace_get_syscall_info_entry(child, regs, info); info->op = PTRACE_SYSCALL_INFO_SECCOMP; info->seccomp.ret_data = child->ptrace_message; /* ret_data is the last field in struct ptrace_syscall_info.seccomp */ return offsetofend(struct ptrace_syscall_info, seccomp.ret_data); } static unsigned long ptrace_get_syscall_info_exit(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { info->op = PTRACE_SYSCALL_INFO_EXIT; info->exit.rval = syscall_get_error(child, regs); info->exit.is_error = !!info->exit.rval; if (!info->exit.is_error) info->exit.rval = syscall_get_return_value(child, regs); /* is_error is the last field in struct ptrace_syscall_info.exit */ return offsetofend(struct ptrace_syscall_info, exit.is_error); } static int ptrace_get_syscall_info(struct task_struct *child, unsigned long user_size, void __user *datavp) { struct pt_regs *regs = task_pt_regs(child); struct ptrace_syscall_info info = { .op = PTRACE_SYSCALL_INFO_NONE, .arch = syscall_get_arch(child), .instruction_pointer = instruction_pointer(regs), .stack_pointer = user_stack_pointer(regs), }; unsigned long actual_size = offsetof(struct ptrace_syscall_info, entry); unsigned long write_size; /* * This does not need lock_task_sighand() to access * child->last_siginfo because ptrace_freeze_traced() * called earlier by ptrace_check_attach() ensures that * the tracee cannot go away and clear its last_siginfo. */ switch (child->last_siginfo ? child->last_siginfo->si_code : 0) { case SIGTRAP | 0x80: switch (child->ptrace_message) { case PTRACE_EVENTMSG_SYSCALL_ENTRY: actual_size = ptrace_get_syscall_info_entry(child, regs, &info); break; case PTRACE_EVENTMSG_SYSCALL_EXIT: actual_size = ptrace_get_syscall_info_exit(child, regs, &info); break; } break; case SIGTRAP | (PTRACE_EVENT_SECCOMP << 8): actual_size = ptrace_get_syscall_info_seccomp(child, regs, &info); break; } write_size = min(actual_size, user_size); return copy_to_user(datavp, &info, write_size) ? -EFAULT : actual_size; } #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */ int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data) { bool seized = child->ptrace & PT_SEIZED; int ret = -EIO; kernel_siginfo_t siginfo, *si; void __user *datavp = (void __user *) data; unsigned long __user *datalp = datavp; unsigned long flags; switch (request) { case PTRACE_PEEKTEXT: case PTRACE_PEEKDATA: return generic_ptrace_peekdata(child, addr, data); case PTRACE_POKETEXT: case PTRACE_POKEDATA: return generic_ptrace_pokedata(child, addr, data); #ifdef PTRACE_OLDSETOPTIONS case PTRACE_OLDSETOPTIONS: #endif case PTRACE_SETOPTIONS: ret = ptrace_setoptions(child, data); break; case PTRACE_GETEVENTMSG: ret = put_user(child->ptrace_message, datalp); break; case PTRACE_PEEKSIGINFO: ret = ptrace_peek_siginfo(child, addr, data); break; case PTRACE_GETSIGINFO: ret = ptrace_getsiginfo(child, &siginfo); if (!ret) ret = copy_siginfo_to_user(datavp, &siginfo); break; case PTRACE_SETSIGINFO: ret = copy_siginfo_from_user(&siginfo, datavp); if (!ret) ret = ptrace_setsiginfo(child, &siginfo); break; case PTRACE_GETSIGMASK: { sigset_t *mask; if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } if (test_tsk_restore_sigmask(child)) mask = &child->saved_sigmask; else mask = &child->blocked; if (copy_to_user(datavp, mask, sizeof(sigset_t))) ret = -EFAULT; else ret = 0; break; } case PTRACE_SETSIGMASK: { sigset_t new_set; if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } if (copy_from_user(&new_set, datavp, sizeof(sigset_t))) { ret = -EFAULT; break; } sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP)); /* * Every thread does recalc_sigpending() after resume, so * retarget_shared_pending() and recalc_sigpending() are not * called here. */ spin_lock_irq(&child->sighand->siglock); child->blocked = new_set; spin_unlock_irq(&child->sighand->siglock); clear_tsk_restore_sigmask(child); ret = 0; break; } case PTRACE_INTERRUPT: /* * Stop tracee without any side-effect on signal or job * control. At least one trap is guaranteed to happen * after this request. If @child is already trapped, the * current trap is not disturbed and another trap will * happen after the current trap is ended with PTRACE_CONT. * * The actual trap might not be PTRACE_EVENT_STOP trap but * the pending condition is cleared regardless. */ if (unlikely(!seized || !lock_task_sighand(child, &flags))) break; /* * INTERRUPT doesn't disturb existing trap sans one * exception. If ptracer issued LISTEN for the current * STOP, this INTERRUPT should clear LISTEN and re-trap * tracee into STOP. */ if (likely(task_set_jobctl_pending(child, JOBCTL_TRAP_STOP))) ptrace_signal_wake_up(child, child->jobctl & JOBCTL_LISTENING); unlock_task_sighand(child, &flags); ret = 0; break; case PTRACE_LISTEN: /* * Listen for events. Tracee must be in STOP. It's not * resumed per-se but is not considered to be in TRACED by * wait(2) or ptrace(2). If an async event (e.g. group * stop state change) happens, tracee will enter STOP trap * again. Alternatively, ptracer can issue INTERRUPT to * finish listening and re-trap tracee into STOP. */ if (unlikely(!seized || !lock_task_sighand(child, &flags))) break; si = child->last_siginfo; if (likely(si && (si->si_code >> 8) == PTRACE_EVENT_STOP)) { child->jobctl |= JOBCTL_LISTENING; /* * If NOTIFY is set, it means event happened between * start of this trap and now. Trigger re-trap. */ if (child->jobctl & JOBCTL_TRAP_NOTIFY) ptrace_signal_wake_up(child, true); ret = 0; } unlock_task_sighand(child, &flags); break; case PTRACE_DETACH: /* detach a process that was attached. */ ret = ptrace_detach(child, data); break; #ifdef CONFIG_BINFMT_ELF_FDPIC case PTRACE_GETFDPIC: { struct mm_struct *mm = get_task_mm(child); unsigned long tmp = 0; ret = -ESRCH; if (!mm) break; switch (addr) { case PTRACE_GETFDPIC_EXEC: tmp = mm->context.exec_fdpic_loadmap; break; case PTRACE_GETFDPIC_INTERP: tmp = mm->context.interp_fdpic_loadmap; break; default: break; } mmput(mm); ret = put_user(tmp, datalp); break; } #endif case PTRACE_SINGLESTEP: #ifdef PTRACE_SINGLEBLOCK case PTRACE_SINGLEBLOCK: #endif #ifdef PTRACE_SYSEMU case PTRACE_SYSEMU: case PTRACE_SYSEMU_SINGLESTEP: #endif case PTRACE_SYSCALL: case PTRACE_CONT: return ptrace_resume(child, request, data); case PTRACE_KILL: send_sig_info(SIGKILL, SEND_SIG_NOINFO, child); return 0; #ifdef CONFIG_HAVE_ARCH_TRACEHOOK case PTRACE_GETREGSET: case PTRACE_SETREGSET: { struct iovec kiov; struct iovec __user *uiov = datavp; if (!access_ok(uiov, sizeof(*uiov))) return -EFAULT; if (__get_user(kiov.iov_base, &uiov->iov_base) || __get_user(kiov.iov_len, &uiov->iov_len)) return -EFAULT; ret = ptrace_regset(child, request, addr, &kiov); if (!ret) ret = __put_user(kiov.iov_len, &uiov->iov_len); break; } case PTRACE_GET_SYSCALL_INFO: ret = ptrace_get_syscall_info(child, addr, datavp); break; #endif case PTRACE_SECCOMP_GET_FILTER: ret = seccomp_get_filter(child, addr, datavp); break; case PTRACE_SECCOMP_GET_METADATA: ret = seccomp_get_metadata(child, addr, datavp); break; #ifdef CONFIG_RSEQ case PTRACE_GET_RSEQ_CONFIGURATION: ret = ptrace_get_rseq_configuration(child, addr, datavp); break; #endif case PTRACE_SET_SYSCALL_USER_DISPATCH_CONFIG: ret = syscall_user_dispatch_set_config(child, addr, datavp); break; case PTRACE_GET_SYSCALL_USER_DISPATCH_CONFIG: ret = syscall_user_dispatch_get_config(child, addr, datavp); break; default: break; } return ret; } SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr, unsigned long, data) { struct task_struct *child; long ret; if (request == PTRACE_TRACEME) { ret = ptrace_traceme(); goto out; } child = find_get_task_by_vpid(pid); if (!child) { ret = -ESRCH; goto out; } if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { ret = ptrace_attach(child, request, addr, data); goto out_put_task_struct; } ret = ptrace_check_attach(child, request == PTRACE_KILL || request == PTRACE_INTERRUPT); if (ret < 0) goto out_put_task_struct; ret = arch_ptrace(child, request, addr, data); if (ret || request != PTRACE_DETACH) ptrace_unfreeze_traced(child); out_put_task_struct: put_task_struct(child); out: return ret; } int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr, unsigned long data) { unsigned long tmp; int copied; copied = ptrace_access_vm(tsk, addr, &tmp, sizeof(tmp), FOLL_FORCE); if (copied != sizeof(tmp)) return -EIO; return put_user(tmp, (unsigned long __user *)data); } int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, unsigned long data) { int copied; copied = ptrace_access_vm(tsk, addr, &data, sizeof(data), FOLL_FORCE | FOLL_WRITE); return (copied == sizeof(data)) ? 0 : -EIO; } #if defined CONFIG_COMPAT int compat_ptrace_request(struct task_struct *child, compat_long_t request, compat_ulong_t addr, compat_ulong_t data) { compat_ulong_t __user *datap = compat_ptr(data); compat_ulong_t word; kernel_siginfo_t siginfo; int ret; switch (request) { case PTRACE_PEEKTEXT: case PTRACE_PEEKDATA: ret = ptrace_access_vm(child, addr, &word, sizeof(word), FOLL_FORCE); if (ret != sizeof(word)) ret = -EIO; else ret = put_user(word, datap); break; case PTRACE_POKETEXT: case PTRACE_POKEDATA: ret = ptrace_access_vm(child, addr, &data, sizeof(data), FOLL_FORCE | FOLL_WRITE); ret = (ret != sizeof(data) ? -EIO : 0); break; case PTRACE_GETEVENTMSG: ret = put_user((compat_ulong_t) child->ptrace_message, datap); break; case PTRACE_GETSIGINFO: ret = ptrace_getsiginfo(child, &siginfo); if (!ret) ret = copy_siginfo_to_user32( (struct compat_siginfo __user *) datap, &siginfo); break; case PTRACE_SETSIGINFO: ret = copy_siginfo_from_user32( &siginfo, (struct compat_siginfo __user *) datap); if (!ret) ret = ptrace_setsiginfo(child, &siginfo); break; #ifdef CONFIG_HAVE_ARCH_TRACEHOOK case PTRACE_GETREGSET: case PTRACE_SETREGSET: { struct iovec kiov; struct compat_iovec __user *uiov = (struct compat_iovec __user *) datap; compat_uptr_t ptr; compat_size_t len; if (!access_ok(uiov, sizeof(*uiov))) return -EFAULT; if (__get_user(ptr, &uiov->iov_base) || __get_user(len, &uiov->iov_len)) return -EFAULT; kiov.iov_base = compat_ptr(ptr); kiov.iov_len = len; ret = ptrace_regset(child, request, addr, &kiov); if (!ret) ret = __put_user(kiov.iov_len, &uiov->iov_len); break; } #endif default: ret = ptrace_request(child, request, addr, data); } return ret; } COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid, compat_long_t, addr, compat_long_t, data) { struct task_struct *child; long ret; if (request == PTRACE_TRACEME) { ret = ptrace_traceme(); goto out; } child = find_get_task_by_vpid(pid); if (!child) { ret = -ESRCH; goto out; } if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { ret = ptrace_attach(child, request, addr, data); goto out_put_task_struct; } ret = ptrace_check_attach(child, request == PTRACE_KILL || request == PTRACE_INTERRUPT); if (!ret) { ret = compat_arch_ptrace(child, request, addr, data); if (ret || request != PTRACE_DETACH) ptrace_unfreeze_traced(child); } out_put_task_struct: put_task_struct(child); out: return ret; } #endif /* CONFIG_COMPAT */ |
| 10 41 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Global definitions for the ARP (RFC 826) protocol. * * Version: @(#)if_arp.h 1.0.1 04/16/93 * * Authors: Original taken from Berkeley UNIX 4.3, (c) UCB 1986-1988 * Portions taken from the KA9Q/NOS (v2.00m PA0GRI) source. * Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, * Jonathan Layes <layes@loran.com> * Arnaldo Carvalho de Melo <acme@conectiva.com.br> ARPHRD_HWX25 */ #ifndef _LINUX_IF_ARP_H #define _LINUX_IF_ARP_H #include <linux/skbuff.h> #include <uapi/linux/if_arp.h> static inline struct arphdr *arp_hdr(const struct sk_buff *skb) { return (struct arphdr *)skb_network_header(skb); } static inline unsigned int arp_hdr_len(const struct net_device *dev) { switch (dev->type) { #if IS_ENABLED(CONFIG_FIREWIRE_NET) case ARPHRD_IEEE1394: /* ARP header, device address and 2 IP addresses */ return sizeof(struct arphdr) + dev->addr_len + sizeof(u32) * 2; #endif default: /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ return sizeof(struct arphdr) + (dev->addr_len + sizeof(u32)) * 2; } } static inline bool dev_is_mac_header_xmit(const struct net_device *dev) { switch (dev->type) { case ARPHRD_TUNNEL: case ARPHRD_TUNNEL6: case ARPHRD_SIT: case ARPHRD_IPGRE: case ARPHRD_IP6GRE: case ARPHRD_VOID: case ARPHRD_NONE: case ARPHRD_RAWIP: case ARPHRD_PIMREG: /* PPP adds its l2 header automatically in ppp_start_xmit(). * This makes it look like an l3 device to __bpf_redirect() and tcf_mirred_init(). */ case ARPHRD_PPP: return false; default: return true; } } #endif /* _LINUX_IF_ARP_H */ |
| 3 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * File: pep.h * * Phonet Pipe End Point sockets definitions * * Copyright (C) 2008 Nokia Corporation. */ #ifndef NET_PHONET_PEP_H #define NET_PHONET_PEP_H #include <linux/skbuff.h> #include <net/phonet/phonet.h> struct pep_sock { struct pn_sock pn_sk; /* XXX: union-ify listening vs connected stuff ? */ /* Listening socket stuff: */ struct hlist_head hlist; /* Connected socket stuff: */ struct sock *listener; struct sk_buff_head ctrlreq_queue; #define PNPIPE_CTRLREQ_MAX 10 atomic_t tx_credits; int ifindex; u16 peer_type; /* peer type/subtype */ u8 pipe_handle; u8 rx_credits; u8 rx_fc; /* RX flow control */ u8 tx_fc; /* TX flow control */ u8 init_enable; /* auto-enable at creation */ u8 aligned; }; static inline struct pep_sock *pep_sk(struct sock *sk) { return (struct pep_sock *)sk; } extern const struct proto_ops phonet_stream_ops; /* Pipe protocol definitions */ struct pnpipehdr { u8 utid; /* transaction ID */ u8 message_id; u8 pipe_handle; union { u8 state_after_connect; /* connect request */ u8 state_after_reset; /* reset request */ u8 error_code; /* any response */ u8 pep_type; /* status indication */ u8 data0; /* anything else */ }; u8 data[]; }; #define other_pep_type data[0] static inline struct pnpipehdr *pnp_hdr(struct sk_buff *skb) { return (struct pnpipehdr *)skb_transport_header(skb); } #define MAX_PNPIPE_HEADER (MAX_PHONET_HEADER + 4) enum { PNS_PIPE_CREATE_REQ = 0x00, PNS_PIPE_CREATE_RESP, PNS_PIPE_REMOVE_REQ, PNS_PIPE_REMOVE_RESP, PNS_PIPE_DATA = 0x20, PNS_PIPE_ALIGNED_DATA, PNS_PEP_CONNECT_REQ = 0x40, PNS_PEP_CONNECT_RESP, PNS_PEP_DISCONNECT_REQ, PNS_PEP_DISCONNECT_RESP, PNS_PEP_RESET_REQ, PNS_PEP_RESET_RESP, PNS_PEP_ENABLE_REQ, PNS_PEP_ENABLE_RESP, PNS_PEP_CTRL_REQ, PNS_PEP_CTRL_RESP, PNS_PEP_DISABLE_REQ = 0x4C, PNS_PEP_DISABLE_RESP, PNS_PEP_STATUS_IND = 0x60, PNS_PIPE_CREATED_IND, PNS_PIPE_RESET_IND = 0x63, PNS_PIPE_ENABLED_IND, PNS_PIPE_REDIRECTED_IND, PNS_PIPE_DISABLED_IND = 0x66, }; #define PN_PIPE_INVALID_HANDLE 0xff #define PN_PEP_TYPE_COMMON 0x00 /* Phonet pipe status indication */ enum { PN_PEP_IND_FLOW_CONTROL, PN_PEP_IND_ID_MCFC_GRANT_CREDITS, }; /* Phonet pipe error codes */ enum { PN_PIPE_NO_ERROR, PN_PIPE_ERR_INVALID_PARAM, PN_PIPE_ERR_INVALID_HANDLE, PN_PIPE_ERR_INVALID_CTRL_ID, PN_PIPE_ERR_NOT_ALLOWED, PN_PIPE_ERR_PEP_IN_USE, PN_PIPE_ERR_OVERLOAD, PN_PIPE_ERR_DEV_DISCONNECTED, PN_PIPE_ERR_TIMEOUT, PN_PIPE_ERR_ALL_PIPES_IN_USE, PN_PIPE_ERR_GENERAL, PN_PIPE_ERR_NOT_SUPPORTED, }; /* Phonet pipe states */ enum { PN_PIPE_DISABLE, PN_PIPE_ENABLE, }; /* Phonet pipe sub-block types */ enum { PN_PIPE_SB_CREATE_REQ_PEP_SUB_TYPE, PN_PIPE_SB_CONNECT_REQ_PEP_SUB_TYPE, PN_PIPE_SB_REDIRECT_REQ_PEP_SUB_TYPE, PN_PIPE_SB_NEGOTIATED_FC, PN_PIPE_SB_REQUIRED_FC_TX, PN_PIPE_SB_PREFERRED_FC_RX, PN_PIPE_SB_ALIGNED_DATA, }; /* Phonet pipe flow control models */ enum { PN_NO_FLOW_CONTROL, PN_LEGACY_FLOW_CONTROL, PN_ONE_CREDIT_FLOW_CONTROL, PN_MULTI_CREDIT_FLOW_CONTROL, PN_MAX_FLOW_CONTROL, }; #define pn_flow_safe(fc) ((fc) >> 1) /* Phonet pipe flow control states */ enum { PEP_IND_EMPTY, PEP_IND_BUSY, PEP_IND_READY, }; #endif |
| 2482 2477 2474 | 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 | // SPDX-License-Identifier: GPL-2.0-only // Copyright (C) 2022 Linutronix GmbH, John Ogness // Copyright (C) 2022 Intel, Thomas Gleixner #include <linux/atomic.h> #include <linux/bug.h> #include <linux/console.h> #include <linux/delay.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/init.h> #include <linux/irqflags.h> #include <linux/kthread.h> #include <linux/minmax.h> #include <linux/percpu.h> #include <linux/preempt.h> #include <linux/slab.h> #include <linux/smp.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> #include "internal.h" #include "printk_ringbuffer.h" /* * Printk console printing implementation for consoles which does not depend * on the legacy style console_lock mechanism. * * The state of the console is maintained in the "nbcon_state" atomic * variable. * * The console is locked when: * * - The 'prio' field contains the priority of the context that owns the * console. Only higher priority contexts are allowed to take over the * lock. A value of 0 (NBCON_PRIO_NONE) means the console is not locked. * * - The 'cpu' field denotes on which CPU the console is locked. It is used * to prevent busy waiting on the same CPU. Also it informs the lock owner * that it has lost the lock in a more complex scenario when the lock was * taken over by a higher priority context, released, and taken on another * CPU with the same priority as the interrupted owner. * * The acquire mechanism uses a few more fields: * * - The 'req_prio' field is used by the handover approach to make the * current owner aware that there is a context with a higher priority * waiting for the friendly handover. * * - The 'unsafe' field allows to take over the console in a safe way in the * middle of emitting a message. The field is set only when accessing some * shared resources or when the console device is manipulated. It can be * cleared, for example, after emitting one character when the console * device is in a consistent state. * * - The 'unsafe_takeover' field is set when a hostile takeover took the * console in an unsafe state. The console will stay in the unsafe state * until re-initialized. * * The acquire mechanism uses three approaches: * * 1) Direct acquire when the console is not owned or is owned by a lower * priority context and is in a safe state. * * 2) Friendly handover mechanism uses a request/grant handshake. It is used * when the current owner has lower priority and the console is in an * unsafe state. * * The requesting context: * * a) Sets its priority into the 'req_prio' field. * * b) Waits (with a timeout) for the owning context to unlock the * console. * * c) Takes the lock and clears the 'req_prio' field. * * The owning context: * * a) Observes the 'req_prio' field set on exit from the unsafe * console state. * * b) Gives up console ownership by clearing the 'prio' field. * * 3) Unsafe hostile takeover allows to take over the lock even when the * console is an unsafe state. It is used only in panic() by the final * attempt to flush consoles in a try and hope mode. * * Note that separate record buffers are used in panic(). As a result, * the messages can be read and formatted without any risk even after * using the hostile takeover in unsafe state. * * The release function simply clears the 'prio' field. * * All operations on @console::nbcon_state are atomic cmpxchg based to * handle concurrency. * * The acquire/release functions implement only minimal policies: * * - Preference for higher priority contexts. * - Protection of the panic CPU. * * All other policy decisions must be made at the call sites: * * - What is marked as an unsafe section. * - Whether to spin-wait if there is already an owner and the console is * in an unsafe state. * - Whether to attempt an unsafe hostile takeover. * * The design allows to implement the well known: * * acquire() * output_one_printk_record() * release() * * The output of one printk record might be interrupted with a higher priority * context. The new owner is supposed to reprint the entire interrupted record * from scratch. */ /** * nbcon_state_set - Helper function to set the console state * @con: Console to update * @new: The new state to write * * Only to be used when the console is not yet or no longer visible in the * system. Otherwise use nbcon_state_try_cmpxchg(). */ static inline void nbcon_state_set(struct console *con, struct nbcon_state *new) { atomic_set(&ACCESS_PRIVATE(con, nbcon_state), new->atom); } /** * nbcon_state_read - Helper function to read the console state * @con: Console to read * @state: The state to store the result */ static inline void nbcon_state_read(struct console *con, struct nbcon_state *state) { state->atom = atomic_read(&ACCESS_PRIVATE(con, nbcon_state)); } /** * nbcon_state_try_cmpxchg() - Helper function for atomic_try_cmpxchg() on console state * @con: Console to update * @cur: Old/expected state * @new: New state * * Return: True on success. False on fail and @cur is updated. */ static inline bool nbcon_state_try_cmpxchg(struct console *con, struct nbcon_state *cur, struct nbcon_state *new) { return atomic_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_state), &cur->atom, new->atom); } /** * nbcon_seq_read - Read the current console sequence * @con: Console to read the sequence of * * Return: Sequence number of the next record to print on @con. */ u64 nbcon_seq_read(struct console *con) { unsigned long nbcon_seq = atomic_long_read(&ACCESS_PRIVATE(con, nbcon_seq)); return __ulseq_to_u64seq(prb, nbcon_seq); } /** * nbcon_seq_force - Force console sequence to a specific value * @con: Console to work on * @seq: Sequence number value to set * * Only to be used during init (before registration) or in extreme situations * (such as panic with CONSOLE_REPLAY_ALL). */ void nbcon_seq_force(struct console *con, u64 seq) { /* * If the specified record no longer exists, the oldest available record * is chosen. This is especially important on 32bit systems because only * the lower 32 bits of the sequence number are stored. The upper 32 bits * are derived from the sequence numbers available in the ringbuffer. */ u64 valid_seq = max_t(u64, seq, prb_first_valid_seq(prb)); atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), __u64seq_to_ulseq(valid_seq)); } /** * nbcon_seq_try_update - Try to update the console sequence number * @ctxt: Pointer to an acquire context that contains * all information about the acquire mode * @new_seq: The new sequence number to set * * @ctxt->seq is updated to the new value of @con::nbcon_seq (expanded to * the 64bit value). This could be a different value than @new_seq if * nbcon_seq_force() was used or the current context no longer owns the * console. In the later case, it will stop printing anyway. */ static void nbcon_seq_try_update(struct nbcon_context *ctxt, u64 new_seq) { unsigned long nbcon_seq = __u64seq_to_ulseq(ctxt->seq); struct console *con = ctxt->console; if (atomic_long_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_seq), &nbcon_seq, __u64seq_to_ulseq(new_seq))) { ctxt->seq = new_seq; } else { ctxt->seq = nbcon_seq_read(con); } } /** * nbcon_context_try_acquire_direct - Try to acquire directly * @ctxt: The context of the caller * @cur: The current console state * * Acquire the console when it is released. Also acquire the console when * the current owner has a lower priority and the console is in a safe state. * * Return: 0 on success. Otherwise, an error code on failure. Also @cur * is updated to the latest state when failed to modify it. * * Errors: * * -EPERM: A panic is in progress and this is not the panic CPU. * Or the current owner or waiter has the same or higher * priority. No acquire method can be successful in * this case. * * -EBUSY: The current owner has a lower priority but the console * in an unsafe state. The caller should try using * the handover acquire method. */ static int nbcon_context_try_acquire_direct(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state new; do { /* * Panic does not imply that the console is owned. However, it * is critical that non-panic CPUs during panic are unable to * acquire ownership in order to satisfy the assumptions of * nbcon_waiter_matches(). In particular, the assumption that * lower priorities are ignored during panic. */ if (other_cpu_in_panic()) return -EPERM; if (ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio) return -EPERM; if (cur->unsafe) return -EBUSY; /* * The console should never be safe for a direct acquire * if an unsafe hostile takeover has ever happened. */ WARN_ON_ONCE(cur->unsafe_takeover); new.atom = cur->atom; new.prio = ctxt->prio; new.req_prio = NBCON_PRIO_NONE; new.unsafe = cur->unsafe_takeover; new.cpu = cpu; } while (!nbcon_state_try_cmpxchg(con, cur, &new)); return 0; } static bool nbcon_waiter_matches(struct nbcon_state *cur, int expected_prio) { /* * The request context is well defined by the @req_prio because: * * - Only a context with a priority higher than the owner can become * a waiter. * - Only a context with a priority higher than the waiter can * directly take over the request. * - There are only three priorities. * - Only one CPU is allowed to request PANIC priority. * - Lower priorities are ignored during panic() until reboot. * * As a result, the following scenario is *not* possible: * * 1. This context is currently a waiter. * 2. Another context with a higher priority than this context * directly takes ownership. * 3. The higher priority context releases the ownership. * 4. Another lower priority context takes the ownership. * 5. Another context with the same priority as this context * creates a request and starts waiting. * * Event #1 implies this context is EMERGENCY. * Event #2 implies the new context is PANIC. * Event #3 occurs when panic() has flushed the console. * Events #4 and #5 are not possible due to the other_cpu_in_panic() * check in nbcon_context_try_acquire_direct(). */ return (cur->req_prio == expected_prio); } /** * nbcon_context_try_acquire_requested - Try to acquire after having * requested a handover * @ctxt: The context of the caller * @cur: The current console state * * This is a helper function for nbcon_context_try_acquire_handover(). * It is called when the console is in an unsafe state. The current * owner will release the console on exit from the unsafe region. * * Return: 0 on success and @cur is updated to the new console state. * Otherwise an error code on failure. * * Errors: * * -EPERM: A panic is in progress and this is not the panic CPU * or this context is no longer the waiter. * * -EBUSY: The console is still locked. The caller should * continue waiting. * * Note: The caller must still remove the request when an error has occurred * except when this context is no longer the waiter. */ static int nbcon_context_try_acquire_requested(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state new; /* Note that the caller must still remove the request! */ if (other_cpu_in_panic()) return -EPERM; /* * Note that the waiter will also change if there was an unsafe * hostile takeover. */ if (!nbcon_waiter_matches(cur, ctxt->prio)) return -EPERM; /* If still locked, caller should continue waiting. */ if (cur->prio != NBCON_PRIO_NONE) return -EBUSY; /* * The previous owner should have never released ownership * in an unsafe region. */ WARN_ON_ONCE(cur->unsafe); new.atom = cur->atom; new.prio = ctxt->prio; new.req_prio = NBCON_PRIO_NONE; new.unsafe = cur->unsafe_takeover; new.cpu = cpu; if (!nbcon_state_try_cmpxchg(con, cur, &new)) { /* * The acquire could fail only when it has been taken * over by a higher priority context. */ WARN_ON_ONCE(nbcon_waiter_matches(cur, ctxt->prio)); return -EPERM; } /* Handover success. This context now owns the console. */ return 0; } /** * nbcon_context_try_acquire_handover - Try to acquire via handover * @ctxt: The context of the caller * @cur: The current console state * * The function must be called only when the context has higher priority * than the current owner and the console is in an unsafe state. * It is the case when nbcon_context_try_acquire_direct() returns -EBUSY. * * The function sets "req_prio" field to make the current owner aware of * the request. Then it waits until the current owner releases the console, * or an even higher context takes over the request, or timeout expires. * * The current owner checks the "req_prio" field on exit from the unsafe * region and releases the console. It does not touch the "req_prio" field * so that the console stays reserved for the waiter. * * Return: 0 on success. Otherwise, an error code on failure. Also @cur * is updated to the latest state when failed to modify it. * * Errors: * * -EPERM: A panic is in progress and this is not the panic CPU. * Or a higher priority context has taken over the * console or the handover request. * * -EBUSY: The current owner is on the same CPU so that the hand * shake could not work. Or the current owner is not * willing to wait (zero timeout). Or the console does * not enter the safe state before timeout passed. The * caller might still use the unsafe hostile takeover * when allowed. * * -EAGAIN: @cur has changed when creating the handover request. * The caller should retry with direct acquire. */ static int nbcon_context_try_acquire_handover(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state new; int timeout; int request_err = -EBUSY; /* * Check that the handover is called when the direct acquire failed * with -EBUSY. */ WARN_ON_ONCE(ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio); WARN_ON_ONCE(!cur->unsafe); /* Handover is not possible on the same CPU. */ if (cur->cpu == cpu) return -EBUSY; /* * Console stays unsafe after an unsafe takeover until re-initialized. * Waiting is not going to help in this case. */ if (cur->unsafe_takeover) return -EBUSY; /* Is the caller willing to wait? */ if (ctxt->spinwait_max_us == 0) return -EBUSY; /* * Setup a request for the handover. The caller should try to acquire * the console directly when the current state has been modified. */ new.atom = cur->atom; new.req_prio = ctxt->prio; if (!nbcon_state_try_cmpxchg(con, cur, &new)) return -EAGAIN; cur->atom = new.atom; /* Wait until there is no owner and then acquire the console. */ for (timeout = ctxt->spinwait_max_us; timeout >= 0; timeout--) { /* On successful acquire, this request is cleared. */ request_err = nbcon_context_try_acquire_requested(ctxt, cur); if (!request_err) return 0; /* * If the acquire should be aborted, it must be ensured * that the request is removed before returning to caller. */ if (request_err == -EPERM) break; udelay(1); /* Re-read the state because some time has passed. */ nbcon_state_read(con, cur); } /* Timed out or aborted. Carefully remove handover request. */ do { /* * No need to remove request if there is a new waiter. This * can only happen if a higher priority context has taken over * the console or the handover request. */ if (!nbcon_waiter_matches(cur, ctxt->prio)) return -EPERM; /* Unset request for handover. */ new.atom = cur->atom; new.req_prio = NBCON_PRIO_NONE; if (nbcon_state_try_cmpxchg(con, cur, &new)) { /* * Request successfully unset. Report failure of * acquiring via handover. */ cur->atom = new.atom; return request_err; } /* * Unable to remove request. Try to acquire in case * the owner has released the lock. */ } while (nbcon_context_try_acquire_requested(ctxt, cur)); /* Lucky timing. The acquire succeeded while removing the request. */ return 0; } /** * nbcon_context_try_acquire_hostile - Acquire via unsafe hostile takeover * @ctxt: The context of the caller * @cur: The current console state * * Acquire the console even in the unsafe state. * * It can be permitted by setting the 'allow_unsafe_takeover' field only * by the final attempt to flush messages in panic(). * * Return: 0 on success. -EPERM when not allowed by the context. */ static int nbcon_context_try_acquire_hostile(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state new; if (!ctxt->allow_unsafe_takeover) return -EPERM; /* Ensure caller is allowed to perform unsafe hostile takeovers. */ if (WARN_ON_ONCE(ctxt->prio != NBCON_PRIO_PANIC)) return -EPERM; /* * Check that try_acquire_direct() and try_acquire_handover() returned * -EBUSY in the right situation. */ WARN_ON_ONCE(ctxt->prio <= cur->prio || ctxt->prio <= cur->req_prio); WARN_ON_ONCE(cur->unsafe != true); do { new.atom = cur->atom; new.cpu = cpu; new.prio = ctxt->prio; new.unsafe |= cur->unsafe_takeover; new.unsafe_takeover |= cur->unsafe; } while (!nbcon_state_try_cmpxchg(con, cur, &new)); return 0; } static struct printk_buffers panic_nbcon_pbufs; /** * nbcon_context_try_acquire - Try to acquire nbcon console * @ctxt: The context of the caller * * Context: Under @ctxt->con->device_lock() or local_irq_save(). * Return: True if the console was acquired. False otherwise. * * If the caller allowed an unsafe hostile takeover, on success the * caller should check the current console state to see if it is * in an unsafe state. Otherwise, on success the caller may assume * the console is not in an unsafe state. */ static bool nbcon_context_try_acquire(struct nbcon_context *ctxt) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state cur; int err; nbcon_state_read(con, &cur); try_again: err = nbcon_context_try_acquire_direct(ctxt, &cur); if (err != -EBUSY) goto out; err = nbcon_context_try_acquire_handover(ctxt, &cur); if (err == -EAGAIN) goto try_again; if (err != -EBUSY) goto out; err = nbcon_context_try_acquire_hostile(ctxt, &cur); out: if (err) return false; /* Acquire succeeded. */ /* Assign the appropriate buffer for this context. */ if (atomic_read(&panic_cpu) == cpu) ctxt->pbufs = &panic_nbcon_pbufs; else ctxt->pbufs = con->pbufs; /* Set the record sequence for this context to print. */ ctxt->seq = nbcon_seq_read(ctxt->console); return true; } static bool nbcon_owner_matches(struct nbcon_state *cur, int expected_cpu, int expected_prio) { /* * A similar function, nbcon_waiter_matches(), only deals with * EMERGENCY and PANIC priorities. However, this function must also * deal with the NORMAL priority, which requires additional checks * and constraints. * * For the case where preemption and interrupts are disabled, it is * enough to also verify that the owning CPU has not changed. * * For the case where preemption or interrupts are enabled, an * external synchronization method *must* be used. In particular, * the driver-specific locking mechanism used in device_lock() * (including disabling migration) should be used. It prevents * scenarios such as: * * 1. [Task A] owns a context with NBCON_PRIO_NORMAL on [CPU X] and * is scheduled out. * 2. Another context takes over the lock with NBCON_PRIO_EMERGENCY * and releases it. * 3. [Task B] acquires a context with NBCON_PRIO_NORMAL on [CPU X] * and is scheduled out. * 4. [Task A] gets running on [CPU X] and sees that the console is * still owned by a task on [CPU X] with NBON_PRIO_NORMAL. Thus * [Task A] thinks it is the owner when it is not. */ if (cur->prio != expected_prio) return false; if (cur->cpu != expected_cpu) return false; return true; } /** * nbcon_context_release - Release the console * @ctxt: The nbcon context from nbcon_context_try_acquire() */ static void nbcon_context_release(struct nbcon_context *ctxt) { unsigned int cpu = smp_processor_id(); struct console *con = ctxt->console; struct nbcon_state cur; struct nbcon_state new; nbcon_state_read(con, &cur); do { if (!nbcon_owner_matches(&cur, cpu, ctxt->prio)) break; new.atom = cur.atom; new.prio = NBCON_PRIO_NONE; /* * If @unsafe_takeover is set, it is kept set so that * the state remains permanently unsafe. */ new.unsafe |= cur.unsafe_takeover; } while (!nbcon_state_try_cmpxchg(con, &cur, &new)); ctxt->pbufs = NULL; } /** * nbcon_context_can_proceed - Check whether ownership can proceed * @ctxt: The nbcon context from nbcon_context_try_acquire() * @cur: The current console state * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * Must be invoked when entering the unsafe state to make sure that it still * owns the lock. Also must be invoked when exiting the unsafe context * to eventually free the lock for a higher priority context which asked * for the friendly handover. * * It can be called inside an unsafe section when the console is just * temporary in safe state instead of exiting and entering the unsafe * state. * * Also it can be called in the safe context before doing an expensive * safe operation. It does not make sense to do the operation when * a higher priority context took the lock. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. */ static bool nbcon_context_can_proceed(struct nbcon_context *ctxt, struct nbcon_state *cur) { unsigned int cpu = smp_processor_id(); /* Make sure this context still owns the console. */ if (!nbcon_owner_matches(cur, cpu, ctxt->prio)) return false; /* The console owner can proceed if there is no waiter. */ if (cur->req_prio == NBCON_PRIO_NONE) return true; /* * A console owner within an unsafe region is always allowed to * proceed, even if there are waiters. It can perform a handover * when exiting the unsafe region. Otherwise the waiter will * need to perform an unsafe hostile takeover. */ if (cur->unsafe) return true; /* Waiters always have higher priorities than owners. */ WARN_ON_ONCE(cur->req_prio <= cur->prio); /* * Having a safe point for take over and eventually a few * duplicated characters or a full line is way better than a * hostile takeover. Post processing can take care of the garbage. * Release and hand over. */ nbcon_context_release(ctxt); /* * It is not clear whether the waiter really took over ownership. The * outermost callsite must make the final decision whether console * ownership is needed for it to proceed. If yes, it must reacquire * ownership (possibly hostile) before carefully proceeding. * * The calling context no longer owns the console so go back all the * way instead of trying to implement reacquire heuristics in tons of * places. */ return false; } /** * nbcon_can_proceed - Check whether ownership can proceed * @wctxt: The write context that was handed to the write function * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * It is used in nbcon_enter_unsafe() to make sure that it still owns the * lock. Also it is used in nbcon_exit_unsafe() to eventually free the lock * for a higher priority context which asked for the friendly handover. * * It can be called inside an unsafe section when the console is just * temporary in safe state instead of exiting and entering the unsafe state. * * Also it can be called in the safe context before doing an expensive safe * operation. It does not make sense to do the operation when a higher * priority context took the lock. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. */ bool nbcon_can_proceed(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; struct nbcon_state cur; nbcon_state_read(con, &cur); return nbcon_context_can_proceed(ctxt, &cur); } EXPORT_SYMBOL_GPL(nbcon_can_proceed); #define nbcon_context_enter_unsafe(c) __nbcon_context_update_unsafe(c, true) #define nbcon_context_exit_unsafe(c) __nbcon_context_update_unsafe(c, false) /** * __nbcon_context_update_unsafe - Update the unsafe bit in @con->nbcon_state * @ctxt: The nbcon context from nbcon_context_try_acquire() * @unsafe: The new value for the unsafe bit * * Return: True if the unsafe state was updated and this context still * owns the console. Otherwise false if ownership was handed * over or taken. * * This function allows console owners to modify the unsafe status of the * console. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. * * Internal helper to avoid duplicated code. */ static bool __nbcon_context_update_unsafe(struct nbcon_context *ctxt, bool unsafe) { struct console *con = ctxt->console; struct nbcon_state cur; struct nbcon_state new; nbcon_state_read(con, &cur); do { /* * The unsafe bit must not be cleared if an * unsafe hostile takeover has occurred. */ if (!unsafe && cur.unsafe_takeover) goto out; if (!nbcon_context_can_proceed(ctxt, &cur)) return false; new.atom = cur.atom; new.unsafe = unsafe; } while (!nbcon_state_try_cmpxchg(con, &cur, &new)); cur.atom = new.atom; out: return nbcon_context_can_proceed(ctxt, &cur); } static void nbcon_write_context_set_buf(struct nbcon_write_context *wctxt, char *buf, unsigned int len) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; struct nbcon_state cur; wctxt->outbuf = buf; wctxt->len = len; nbcon_state_read(con, &cur); wctxt->unsafe_takeover = cur.unsafe_takeover; } /** * nbcon_enter_unsafe - Enter an unsafe region in the driver * @wctxt: The write context that was handed to the write function * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. */ bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); bool is_owner; is_owner = nbcon_context_enter_unsafe(ctxt); if (!is_owner) nbcon_write_context_set_buf(wctxt, NULL, 0); return is_owner; } EXPORT_SYMBOL_GPL(nbcon_enter_unsafe); /** * nbcon_exit_unsafe - Exit an unsafe region in the driver * @wctxt: The write context that was handed to the write function * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. */ bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); bool ret; ret = nbcon_context_exit_unsafe(ctxt); if (!ret) nbcon_write_context_set_buf(wctxt, NULL, 0); return ret; } EXPORT_SYMBOL_GPL(nbcon_exit_unsafe); /** * nbcon_reacquire_nobuf - Reacquire a console after losing ownership * while printing * @wctxt: The write context that was handed to the write callback * * Since ownership can be lost at any time due to handover or takeover, a * printing context _must_ be prepared to back out immediately and * carefully. However, there are scenarios where the printing context must * reacquire ownership in order to finalize or revert hardware changes. * * This function allows a printing context to reacquire ownership using the * same priority as its previous ownership. * * Note that after a successful reacquire the printing context will have no * output buffer because that has been lost. This function cannot be used to * resume printing. */ void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); while (!nbcon_context_try_acquire(ctxt)) cpu_relax(); nbcon_write_context_set_buf(wctxt, NULL, 0); } EXPORT_SYMBOL_GPL(nbcon_reacquire_nobuf); /** * nbcon_emit_next_record - Emit a record in the acquired context * @wctxt: The write context that will be handed to the write function * @use_atomic: True if the write_atomic() callback is to be used * * Return: True if this context still owns the console. False if * ownership was handed over or taken. * * When this function returns false then the calling context no longer owns * the console and is no longer allowed to go forward. In this case it must * back out immediately and carefully. The buffer content is also no longer * trusted since it no longer belongs to the calling context. If the caller * wants to do more it must reacquire the console first. * * When true is returned, @wctxt->ctxt.backlog indicates whether there are * still records pending in the ringbuffer, */ static bool nbcon_emit_next_record(struct nbcon_write_context *wctxt, bool use_atomic) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; bool is_extended = console_srcu_read_flags(con) & CON_EXTENDED; struct printk_message pmsg = { .pbufs = ctxt->pbufs, }; unsigned long con_dropped; struct nbcon_state cur; unsigned long dropped; unsigned long ulseq; /* * This function should never be called for consoles that have not * implemented the necessary callback for writing: i.e. legacy * consoles and, when atomic, nbcon consoles with no write_atomic(). * Handle it as if ownership was lost and try to continue. * * Note that for nbcon consoles the write_thread() callback is * mandatory and was already checked in nbcon_alloc(). */ if (WARN_ON_ONCE((use_atomic && !con->write_atomic) || !(console_srcu_read_flags(con) & CON_NBCON))) { nbcon_context_release(ctxt); return false; } /* * The printk buffers are filled within an unsafe section. This * prevents NBCON_PRIO_NORMAL and NBCON_PRIO_EMERGENCY from * clobbering each other. */ if (!nbcon_context_enter_unsafe(ctxt)) return false; ctxt->backlog = printk_get_next_message(&pmsg, ctxt->seq, is_extended, true); if (!ctxt->backlog) return nbcon_context_exit_unsafe(ctxt); /* * @con->dropped is not protected in case of an unsafe hostile * takeover. In that situation the update can be racy so * annotate it accordingly. */ con_dropped = data_race(READ_ONCE(con->dropped)); dropped = con_dropped + pmsg.dropped; if (dropped && !is_extended) console_prepend_dropped(&pmsg, dropped); /* * If the previous owner was assigned the same record, this context * has taken over ownership and is replaying the record. Prepend a * message to let the user know the record is replayed. */ ulseq = atomic_long_read(&ACCESS_PRIVATE(con, nbcon_prev_seq)); if (__ulseq_to_u64seq(prb, ulseq) == pmsg.seq) { console_prepend_replay(&pmsg); } else { /* * Ensure this context is still the owner before trying to * update @nbcon_prev_seq. Otherwise the value in @ulseq may * not be from the previous owner and instead be some later * value from the context that took over ownership. */ nbcon_state_read(con, &cur); if (!nbcon_context_can_proceed(ctxt, &cur)) return false; atomic_long_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_prev_seq), &ulseq, __u64seq_to_ulseq(pmsg.seq)); } if (!nbcon_context_exit_unsafe(ctxt)) return false; /* For skipped records just update seq/dropped in @con. */ if (pmsg.outbuf_len == 0) goto update_con; /* Initialize the write context for driver callbacks. */ nbcon_write_context_set_buf(wctxt, &pmsg.pbufs->outbuf[0], pmsg.outbuf_len); if (use_atomic) con->write_atomic(con, wctxt); else con->write_thread(con, wctxt); if (!wctxt->outbuf) { /* * Ownership was lost and reacquired by the driver. Handle it * as if ownership was lost. */ nbcon_context_release(ctxt); return false; } /* * Ownership may have been lost but _not_ reacquired by the driver. * This case is detected and handled when entering unsafe to update * dropped/seq values. */ /* * Since any dropped message was successfully output, reset the * dropped count for the console. */ dropped = 0; update_con: /* * The dropped count and the sequence number are updated within an * unsafe section. This limits update races to the panic context and * allows the panic context to win. */ if (!nbcon_context_enter_unsafe(ctxt)) return false; if (dropped != con_dropped) { /* Counterpart to the READ_ONCE() above. */ WRITE_ONCE(con->dropped, dropped); } nbcon_seq_try_update(ctxt, pmsg.seq + 1); return nbcon_context_exit_unsafe(ctxt); } /* * nbcon_emit_one - Print one record for an nbcon console using the * specified callback * @wctxt: An initialized write context struct to use for this context * @use_atomic: True if the write_atomic() callback is to be used * * Return: True, when a record has been printed and there are still * pending records. The caller might want to continue flushing. * * False, when there is no pending record, or when the console * context cannot be acquired, or the ownership has been lost. * The caller should give up. Either the job is done, cannot be * done, or will be handled by the owning context. * * This is an internal helper to handle the locking of the console before * calling nbcon_emit_next_record(). */ static bool nbcon_emit_one(struct nbcon_write_context *wctxt, bool use_atomic) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(wctxt, ctxt); struct console *con = ctxt->console; unsigned long flags; bool ret = false; if (!use_atomic) { con->device_lock(con, &flags); /* * Ensure this stays on the CPU to make handover and * takeover possible. */ cant_migrate(); } if (!nbcon_context_try_acquire(ctxt)) goto out; /* * nbcon_emit_next_record() returns false when the console was * handed over or taken over. In both cases the context is no * longer valid. * * The higher priority printing context takes over responsibility * to print the pending records. */ if (!nbcon_emit_next_record(wctxt, use_atomic)) goto out; nbcon_context_release(ctxt); ret = ctxt->backlog; out: if (!use_atomic) con->device_unlock(con, flags); return ret; } /** * nbcon_kthread_should_wakeup - Check whether a printer thread should wakeup * @con: Console to operate on * @ctxt: The nbcon context from nbcon_context_try_acquire() * * Return: True if the thread should shutdown or if the console is * allowed to print and a record is available. False otherwise. * * After the thread wakes up, it must first check if it should shutdown before * attempting any printing. */ static bool nbcon_kthread_should_wakeup(struct console *con, struct nbcon_context *ctxt) { bool ret = false; short flags; int cookie; if (kthread_should_stop()) return true; cookie = console_srcu_read_lock(); flags = console_srcu_read_flags(con); if (console_is_usable(con, flags, false)) { /* Bring the sequence in @ctxt up to date */ ctxt->seq = nbcon_seq_read(con); ret = prb_read_valid(prb, ctxt->seq, NULL); } console_srcu_read_unlock(cookie); return ret; } /** * nbcon_kthread_func - The printer thread function * @__console: Console to operate on * * Return: 0 */ static int nbcon_kthread_func(void *__console) { struct console *con = __console; struct nbcon_write_context wctxt = { .ctxt.console = con, .ctxt.prio = NBCON_PRIO_NORMAL, }; struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); short con_flags; bool backlog; int cookie; wait_for_event: /* * Guarantee this task is visible on the rcuwait before * checking the wake condition. * * The full memory barrier within set_current_state() of * ___rcuwait_wait_event() pairs with the full memory * barrier within rcuwait_has_sleeper(). * * This pairs with rcuwait_has_sleeper:A and nbcon_kthread_wake:A. */ rcuwait_wait_event(&con->rcuwait, nbcon_kthread_should_wakeup(con, ctxt), TASK_INTERRUPTIBLE); /* LMM(nbcon_kthread_func:A) */ do { if (kthread_should_stop()) return 0; backlog = false; /* * Keep the srcu read lock around the entire operation so that * synchronize_srcu() can guarantee that the kthread stopped * or suspended printing. */ cookie = console_srcu_read_lock(); con_flags = console_srcu_read_flags(con); if (console_is_usable(con, con_flags, false)) backlog = nbcon_emit_one(&wctxt, false); console_srcu_read_unlock(cookie); cond_resched(); } while (backlog); goto wait_for_event; } /** * nbcon_irq_work - irq work to wake console printer thread * @irq_work: The irq work to operate on */ static void nbcon_irq_work(struct irq_work *irq_work) { struct console *con = container_of(irq_work, struct console, irq_work); nbcon_kthread_wake(con); } static inline bool rcuwait_has_sleeper(struct rcuwait *w) { /* * Guarantee any new records can be seen by tasks preparing to wait * before this context checks if the rcuwait is empty. * * This full memory barrier pairs with the full memory barrier within * set_current_state() of ___rcuwait_wait_event(), which is called * after prepare_to_rcuwait() adds the waiter but before it has * checked the wait condition. * * This pairs with nbcon_kthread_func:A. */ smp_mb(); /* LMM(rcuwait_has_sleeper:A) */ return rcuwait_active(w); } /** * nbcon_kthreads_wake - Wake up printing threads using irq_work */ void nbcon_kthreads_wake(void) { struct console *con; int cookie; if (!printk_kthreads_running) return; cookie = console_srcu_read_lock(); for_each_console_srcu(con) { if (!(console_srcu_read_flags(con) & CON_NBCON)) continue; /* * Only schedule irq_work if the printing thread is * actively waiting. If not waiting, the thread will * notice by itself that it has work to do. */ if (rcuwait_has_sleeper(&con->rcuwait)) irq_work_queue(&con->irq_work); } console_srcu_read_unlock(cookie); } /* * nbcon_kthread_stop - Stop a console printer thread * @con: Console to operate on */ void nbcon_kthread_stop(struct console *con) { lockdep_assert_console_list_lock_held(); if (!con->kthread) return; kthread_stop(con->kthread); con->kthread = NULL; } /** * nbcon_kthread_create - Create a console printer thread * @con: Console to operate on * * Return: True if the kthread was started or already exists. * Otherwise false and @con must not be registered. * * This function is called when it will be expected that nbcon consoles are * flushed using the kthread. The messages printed with NBCON_PRIO_NORMAL * will be no longer flushed by the legacy loop. This is why failure must * be fatal for console registration. * * If @con was already registered and this function fails, @con must be * unregistered before the global state variable @printk_kthreads_running * can be set. */ bool nbcon_kthread_create(struct console *con) { struct task_struct *kt; lockdep_assert_console_list_lock_held(); if (con->kthread) return true; kt = kthread_run(nbcon_kthread_func, con, "pr/%s%d", con->name, con->index); if (WARN_ON(IS_ERR(kt))) { con_printk(KERN_ERR, con, "failed to start printing thread\n"); return false; } con->kthread = kt; /* * It is important that console printing threads are scheduled * shortly after a printk call and with generous runtime budgets. */ sched_set_normal(con->kthread, -20); return true; } /* Track the nbcon emergency nesting per CPU. */ static DEFINE_PER_CPU(unsigned int, nbcon_pcpu_emergency_nesting); static unsigned int early_nbcon_pcpu_emergency_nesting __initdata; /** * nbcon_get_cpu_emergency_nesting - Get the per CPU emergency nesting pointer * * Context: For reading, any context. For writing, any context which could * not be migrated to another CPU. * Return: Either a pointer to the per CPU emergency nesting counter of * the current CPU or to the init data during early boot. * * The function is safe for reading per-CPU variables in any context because * preemption is disabled if the current CPU is in the emergency state. See * also nbcon_cpu_emergency_enter(). */ static __ref unsigned int *nbcon_get_cpu_emergency_nesting(void) { /* * The value of __printk_percpu_data_ready gets set in normal * context and before SMP initialization. As a result it could * never change while inside an nbcon emergency section. */ if (!printk_percpu_data_ready()) return &early_nbcon_pcpu_emergency_nesting; return raw_cpu_ptr(&nbcon_pcpu_emergency_nesting); } /** * nbcon_get_default_prio - The appropriate nbcon priority to use for nbcon * printing on the current CPU * * Context: Any context. * Return: The nbcon_prio to use for acquiring an nbcon console in this * context for printing. * * The function is safe for reading per-CPU data in any context because * preemption is disabled if the current CPU is in the emergency or panic * state. */ enum nbcon_prio nbcon_get_default_prio(void) { unsigned int *cpu_emergency_nesting; if (this_cpu_in_panic()) return NBCON_PRIO_PANIC; cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); if (*cpu_emergency_nesting) return NBCON_PRIO_EMERGENCY; return NBCON_PRIO_NORMAL; } /** * nbcon_legacy_emit_next_record - Print one record for an nbcon console * in legacy contexts * @con: The console to print on * @handover: Will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding * both the console_lock and the SRCU read lock. Otherwise it * is set to false. * @cookie: The cookie from the SRCU read lock. * @use_atomic: Set true when called in an atomic or unknown context. * It affects which nbcon callback will be used: write_atomic() * or write_thread(). * * When false, the write_thread() callback is used and would be * called in a preemtible context unless disabled by the * device_lock. The legacy handover is not allowed in this mode. * * Context: Any context except NMI. * Return: True, when a record has been printed and there are still * pending records. The caller might want to continue flushing. * * False, when there is no pending record, or when the console * context cannot be acquired, or the ownership has been lost. * The caller should give up. Either the job is done, cannot be * done, or will be handled by the owning context. * * This function is meant to be called by console_flush_all() to print records * on nbcon consoles from legacy context (printing via console unlocking). * Essentially it is the nbcon version of console_emit_next_record(). */ bool nbcon_legacy_emit_next_record(struct console *con, bool *handover, int cookie, bool use_atomic) { struct nbcon_write_context wctxt = { }; struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); unsigned long flags; bool progress; ctxt->console = con; ctxt->prio = nbcon_get_default_prio(); if (use_atomic) { /* * In an atomic or unknown context, use the same procedure as * in console_emit_next_record(). It allows to handover. */ printk_safe_enter_irqsave(flags); console_lock_spinning_enable(); stop_critical_timings(); } progress = nbcon_emit_one(&wctxt, use_atomic); if (use_atomic) { start_critical_timings(); *handover = console_lock_spinning_disable_and_check(cookie); printk_safe_exit_irqrestore(flags); } else { /* Non-atomic does not perform legacy spinning handovers. */ *handover = false; } return progress; } /** * __nbcon_atomic_flush_pending_con - Flush specified nbcon console using its * write_atomic() callback * @con: The nbcon console to flush * @stop_seq: Flush up until this record * @allow_unsafe_takeover: True, to allow unsafe hostile takeovers * * Return: 0 if @con was flushed up to @stop_seq Otherwise, error code on * failure. * * Errors: * * -EPERM: Unable to acquire console ownership. * * -EAGAIN: Another context took over ownership while printing. * * -ENOENT: A record before @stop_seq is not available. * * If flushing up to @stop_seq was not successful, it only makes sense for the * caller to try again when -EAGAIN was returned. When -EPERM is returned, * this context is not allowed to acquire the console. When -ENOENT is * returned, it cannot be expected that the unfinalized record will become * available. */ static int __nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq, bool allow_unsafe_takeover) { struct nbcon_write_context wctxt = { }; struct nbcon_context *ctxt = &ACCESS_PRIVATE(&wctxt, ctxt); int err = 0; ctxt->console = con; ctxt->spinwait_max_us = 2000; ctxt->prio = nbcon_get_default_prio(); ctxt->allow_unsafe_takeover = allow_unsafe_takeover; if (!nbcon_context_try_acquire(ctxt)) return -EPERM; while (nbcon_seq_read(con) < stop_seq) { /* * nbcon_emit_next_record() returns false when the console was * handed over or taken over. In both cases the context is no * longer valid. */ if (!nbcon_emit_next_record(&wctxt, true)) return -EAGAIN; if (!ctxt->backlog) { /* Are there reserved but not yet finalized records? */ if (nbcon_seq_read(con) < stop_seq) err = -ENOENT; break; } } nbcon_context_release(ctxt); return err; } /** * nbcon_atomic_flush_pending_con - Flush specified nbcon console using its * write_atomic() callback * @con: The nbcon console to flush * @stop_seq: Flush up until this record * @allow_unsafe_takeover: True, to allow unsafe hostile takeovers * * This will stop flushing before @stop_seq if another context has ownership. * That context is then responsible for the flushing. Likewise, if new records * are added while this context was flushing and there is no other context * to handle the printing, this context must also flush those records. */ static void nbcon_atomic_flush_pending_con(struct console *con, u64 stop_seq, bool allow_unsafe_takeover) { struct console_flush_type ft; unsigned long flags; int err; again: /* * Atomic flushing does not use console driver synchronization (i.e. * it does not hold the port lock for uart consoles). Therefore IRQs * must be disabled to avoid being interrupted and then calling into * a driver that will deadlock trying to acquire console ownership. */ local_irq_save(flags); err = __nbcon_atomic_flush_pending_con(con, stop_seq, allow_unsafe_takeover); local_irq_restore(flags); /* * If there was a new owner (-EPERM, -EAGAIN), that context is * responsible for completing. * * Do not wait for records not yet finalized (-ENOENT) to avoid a * possible deadlock. They will either get flushed by the writer or * eventually skipped on panic CPU. */ if (err) return; /* * If flushing was successful but more records are available, this * context must flush those remaining records if the printer thread * is not available do it. */ printk_get_console_flush_type(&ft); if (!ft.nbcon_offload && prb_read_valid(prb, nbcon_seq_read(con), NULL)) { stop_seq = prb_next_reserve_seq(prb); goto again; } } /** * __nbcon_atomic_flush_pending - Flush all nbcon consoles using their * write_atomic() callback * @stop_seq: Flush up until this record * @allow_unsafe_takeover: True, to allow unsafe hostile takeovers */ static void __nbcon_atomic_flush_pending(u64 stop_seq, bool allow_unsafe_takeover) { struct console *con; int cookie; cookie = console_srcu_read_lock(); for_each_console_srcu(con) { short flags = console_srcu_read_flags(con); if (!(flags & CON_NBCON)) continue; if (!console_is_usable(con, flags, true)) continue; if (nbcon_seq_read(con) >= stop_seq) continue; nbcon_atomic_flush_pending_con(con, stop_seq, allow_unsafe_takeover); } console_srcu_read_unlock(cookie); } /** * nbcon_atomic_flush_pending - Flush all nbcon consoles using their * write_atomic() callback * * Flush the backlog up through the currently newest record. Any new * records added while flushing will not be flushed if there is another * context available to handle the flushing. This is to avoid one CPU * printing unbounded because other CPUs continue to add records. */ void nbcon_atomic_flush_pending(void) { __nbcon_atomic_flush_pending(prb_next_reserve_seq(prb), false); } /** * nbcon_atomic_flush_unsafe - Flush all nbcon consoles using their * write_atomic() callback and allowing unsafe hostile takeovers * * Flush the backlog up through the currently newest record. Unsafe hostile * takeovers will be performed, if necessary. */ void nbcon_atomic_flush_unsafe(void) { __nbcon_atomic_flush_pending(prb_next_reserve_seq(prb), true); } /** * nbcon_cpu_emergency_enter - Enter an emergency section where printk() * messages for that CPU are flushed directly * * Context: Any context. Disables preemption. * * When within an emergency section, printk() calls will attempt to flush any * pending messages in the ringbuffer. */ void nbcon_cpu_emergency_enter(void) { unsigned int *cpu_emergency_nesting; preempt_disable(); cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); (*cpu_emergency_nesting)++; } /** * nbcon_cpu_emergency_exit - Exit an emergency section * * Context: Within an emergency section. Enables preemption. */ void nbcon_cpu_emergency_exit(void) { unsigned int *cpu_emergency_nesting; cpu_emergency_nesting = nbcon_get_cpu_emergency_nesting(); if (!WARN_ON_ONCE(*cpu_emergency_nesting == 0)) (*cpu_emergency_nesting)--; preempt_enable(); } /** * nbcon_alloc - Allocate and init the nbcon console specific data * @con: Console to initialize * * Return: True if the console was fully allocated and initialized. * Otherwise @con must not be registered. * * When allocation and init was successful, the console must be properly * freed using nbcon_free() once it is no longer needed. */ bool nbcon_alloc(struct console *con) { struct nbcon_state state = { }; /* The write_thread() callback is mandatory. */ if (WARN_ON(!con->write_thread)) return false; rcuwait_init(&con->rcuwait); init_irq_work(&con->irq_work, nbcon_irq_work); atomic_long_set(&ACCESS_PRIVATE(con, nbcon_prev_seq), -1UL); nbcon_state_set(con, &state); /* * Initialize @nbcon_seq to the highest possible sequence number so * that practically speaking it will have nothing to print until a * desired initial sequence number has been set via nbcon_seq_force(). */ atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), ULSEQ_MAX(prb)); if (con->flags & CON_BOOT) { /* * Boot console printing is synchronized with legacy console * printing, so boot consoles can share the same global printk * buffers. */ con->pbufs = &printk_shared_pbufs; } else { con->pbufs = kmalloc(sizeof(*con->pbufs), GFP_KERNEL); if (!con->pbufs) { con_printk(KERN_ERR, con, "failed to allocate printing buffer\n"); return false; } if (printk_kthreads_running) { if (!nbcon_kthread_create(con)) { kfree(con->pbufs); con->pbufs = NULL; return false; } } } return true; } /** * nbcon_free - Free and cleanup the nbcon console specific data * @con: Console to free/cleanup nbcon data */ void nbcon_free(struct console *con) { struct nbcon_state state = { }; if (printk_kthreads_running) nbcon_kthread_stop(con); nbcon_state_set(con, &state); /* Boot consoles share global printk buffers. */ if (!(con->flags & CON_BOOT)) kfree(con->pbufs); con->pbufs = NULL; } /** * nbcon_device_try_acquire - Try to acquire nbcon console and enter unsafe * section * @con: The nbcon console to acquire * * Context: Under the locking mechanism implemented in * @con->device_lock() including disabling migration. * Return: True if the console was acquired. False otherwise. * * Console drivers will usually use their own internal synchronization * mechasism to synchronize between console printing and non-printing * activities (such as setting baud rates). However, nbcon console drivers * supporting atomic consoles may also want to mark unsafe sections when * performing non-printing activities in order to synchronize against their * atomic_write() callback. * * This function acquires the nbcon console using priority NBCON_PRIO_NORMAL * and marks it unsafe for handover/takeover. */ bool nbcon_device_try_acquire(struct console *con) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(con, nbcon_device_ctxt); cant_migrate(); memset(ctxt, 0, sizeof(*ctxt)); ctxt->console = con; ctxt->prio = NBCON_PRIO_NORMAL; if (!nbcon_context_try_acquire(ctxt)) return false; if (!nbcon_context_enter_unsafe(ctxt)) return false; return true; } EXPORT_SYMBOL_GPL(nbcon_device_try_acquire); /** * nbcon_device_release - Exit unsafe section and release the nbcon console * @con: The nbcon console acquired in nbcon_device_try_acquire() */ void nbcon_device_release(struct console *con) { struct nbcon_context *ctxt = &ACCESS_PRIVATE(con, nbcon_device_ctxt); struct console_flush_type ft; int cookie; if (!nbcon_context_exit_unsafe(ctxt)) return; nbcon_context_release(ctxt); /* * This context must flush any new records added while the console * was locked if the printer thread is not available to do it. The * console_srcu_read_lock must be taken to ensure the console is * usable throughout flushing. */ cookie = console_srcu_read_lock(); printk_get_console_flush_type(&ft); if (console_is_usable(con, console_srcu_read_flags(con), true) && !ft.nbcon_offload && prb_read_valid(prb, nbcon_seq_read(con), NULL)) { /* * If nbcon_atomic flushing is not available, fallback to * using the legacy loop. */ if (ft.nbcon_atomic) { __nbcon_atomic_flush_pending_con(con, prb_next_reserve_seq(prb), false); } else if (ft.legacy_direct) { if (console_trylock()) console_unlock(); } else if (ft.legacy_offload) { printk_trigger_flush(); } } console_srcu_read_unlock(cookie); } EXPORT_SYMBOL_GPL(nbcon_device_release); |
| 7 2 11 4 2 1 13 13 11 2 13 12 1 13 5 14 9 19 14 11 22 1 6 1 3 28 28 1 12 24 24 18 6 26 27 27 25 24 13 11 10 13 13 12 1 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2014 Fraunhofer ITWM * * Written by: * Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de> */ #include <linux/ieee802154.h> #include <net/mac802154.h> #include <net/ieee802154_netdev.h> static int ieee802154_hdr_push_addr(u8 *buf, const struct ieee802154_addr *addr, bool omit_pan) { int pos = 0; if (addr->mode == IEEE802154_ADDR_NONE) return 0; if (!omit_pan) { memcpy(buf + pos, &addr->pan_id, 2); pos += 2; } switch (addr->mode) { case IEEE802154_ADDR_SHORT: memcpy(buf + pos, &addr->short_addr, 2); pos += 2; break; case IEEE802154_ADDR_LONG: memcpy(buf + pos, &addr->extended_addr, IEEE802154_ADDR_LEN); pos += IEEE802154_ADDR_LEN; break; default: return -EINVAL; } return pos; } static int ieee802154_hdr_push_sechdr(u8 *buf, const struct ieee802154_sechdr *hdr) { int pos = 5; memcpy(buf, hdr, 1); memcpy(buf + 1, &hdr->frame_counter, 4); switch (hdr->key_id_mode) { case IEEE802154_SCF_KEY_IMPLICIT: return pos; case IEEE802154_SCF_KEY_INDEX: break; case IEEE802154_SCF_KEY_SHORT_INDEX: memcpy(buf + pos, &hdr->short_src, 4); pos += 4; break; case IEEE802154_SCF_KEY_HW_INDEX: memcpy(buf + pos, &hdr->extended_src, IEEE802154_ADDR_LEN); pos += IEEE802154_ADDR_LEN; break; } buf[pos++] = hdr->key_id; return pos; } int ieee802154_hdr_push(struct sk_buff *skb, struct ieee802154_hdr *hdr) { u8 buf[IEEE802154_MAX_HEADER_LEN]; int pos = 2; int rc; struct ieee802154_hdr_fc *fc = &hdr->fc; buf[pos++] = hdr->seq; fc->dest_addr_mode = hdr->dest.mode; rc = ieee802154_hdr_push_addr(buf + pos, &hdr->dest, false); if (rc < 0) return -EINVAL; pos += rc; fc->source_addr_mode = hdr->source.mode; if (hdr->source.pan_id == hdr->dest.pan_id && hdr->dest.mode != IEEE802154_ADDR_NONE) fc->intra_pan = true; rc = ieee802154_hdr_push_addr(buf + pos, &hdr->source, fc->intra_pan); if (rc < 0) return -EINVAL; pos += rc; if (fc->security_enabled) { fc->version = 1; rc = ieee802154_hdr_push_sechdr(buf + pos, &hdr->sec); if (rc < 0) return -EINVAL; pos += rc; } memcpy(buf, fc, 2); memcpy(skb_push(skb, pos), buf, pos); return pos; } EXPORT_SYMBOL_GPL(ieee802154_hdr_push); int ieee802154_mac_cmd_push(struct sk_buff *skb, void *f, const void *pl, unsigned int pl_len) { struct ieee802154_mac_cmd_frame *frame = f; struct ieee802154_mac_cmd_pl *mac_pl = &frame->mac_pl; struct ieee802154_hdr *mhr = &frame->mhr; int ret; skb_reserve(skb, sizeof(*mhr)); ret = ieee802154_hdr_push(skb, mhr); if (ret < 0) return ret; skb_reset_mac_header(skb); skb->mac_len = ret; skb_put_data(skb, mac_pl, sizeof(*mac_pl)); skb_put_data(skb, pl, pl_len); return 0; } EXPORT_SYMBOL_GPL(ieee802154_mac_cmd_push); int ieee802154_beacon_push(struct sk_buff *skb, struct ieee802154_beacon_frame *beacon) { struct ieee802154_beacon_hdr *mac_pl = &beacon->mac_pl; struct ieee802154_hdr *mhr = &beacon->mhr; int ret; skb_reserve(skb, sizeof(*mhr)); ret = ieee802154_hdr_push(skb, mhr); if (ret < 0) return ret; skb_reset_mac_header(skb); skb->mac_len = ret; skb_put_data(skb, mac_pl, sizeof(*mac_pl)); if (mac_pl->pend_short_addr_count || mac_pl->pend_ext_addr_count) return -EOPNOTSUPP; return 0; } EXPORT_SYMBOL_GPL(ieee802154_beacon_push); static int ieee802154_hdr_get_addr(const u8 *buf, int mode, bool omit_pan, struct ieee802154_addr *addr) { int pos = 0; addr->mode = mode; if (mode == IEEE802154_ADDR_NONE) return 0; if (!omit_pan) { memcpy(&addr->pan_id, buf + pos, 2); pos += 2; } if (mode == IEEE802154_ADDR_SHORT) { memcpy(&addr->short_addr, buf + pos, 2); return pos + 2; } else { memcpy(&addr->extended_addr, buf + pos, IEEE802154_ADDR_LEN); return pos + IEEE802154_ADDR_LEN; } } static int ieee802154_hdr_addr_len(int mode, bool omit_pan) { int pan_len = omit_pan ? 0 : 2; switch (mode) { case IEEE802154_ADDR_NONE: return 0; case IEEE802154_ADDR_SHORT: return 2 + pan_len; case IEEE802154_ADDR_LONG: return IEEE802154_ADDR_LEN + pan_len; default: return -EINVAL; } } static int ieee802154_hdr_get_sechdr(const u8 *buf, struct ieee802154_sechdr *hdr) { int pos = 5; memcpy(hdr, buf, 1); memcpy(&hdr->frame_counter, buf + 1, 4); switch (hdr->key_id_mode) { case IEEE802154_SCF_KEY_IMPLICIT: return pos; case IEEE802154_SCF_KEY_INDEX: break; case IEEE802154_SCF_KEY_SHORT_INDEX: memcpy(&hdr->short_src, buf + pos, 4); pos += 4; break; case IEEE802154_SCF_KEY_HW_INDEX: memcpy(&hdr->extended_src, buf + pos, IEEE802154_ADDR_LEN); pos += IEEE802154_ADDR_LEN; break; } hdr->key_id = buf[pos++]; return pos; } static int ieee802154_sechdr_lengths[4] = { [IEEE802154_SCF_KEY_IMPLICIT] = 5, [IEEE802154_SCF_KEY_INDEX] = 6, [IEEE802154_SCF_KEY_SHORT_INDEX] = 10, [IEEE802154_SCF_KEY_HW_INDEX] = 14, }; static int ieee802154_hdr_sechdr_len(u8 sc) { return ieee802154_sechdr_lengths[IEEE802154_SCF_KEY_ID_MODE(sc)]; } static int ieee802154_hdr_minlen(const struct ieee802154_hdr *hdr) { int dlen, slen; dlen = ieee802154_hdr_addr_len(hdr->fc.dest_addr_mode, false); slen = ieee802154_hdr_addr_len(hdr->fc.source_addr_mode, hdr->fc.intra_pan); if (slen < 0 || dlen < 0) return -EINVAL; return 3 + dlen + slen + hdr->fc.security_enabled; } static int ieee802154_hdr_get_addrs(const u8 *buf, struct ieee802154_hdr *hdr) { int pos = 0; pos += ieee802154_hdr_get_addr(buf + pos, hdr->fc.dest_addr_mode, false, &hdr->dest); pos += ieee802154_hdr_get_addr(buf + pos, hdr->fc.source_addr_mode, hdr->fc.intra_pan, &hdr->source); if (hdr->fc.intra_pan) hdr->source.pan_id = hdr->dest.pan_id; return pos; } int ieee802154_hdr_pull(struct sk_buff *skb, struct ieee802154_hdr *hdr) { int pos = 3, rc; if (!pskb_may_pull(skb, 3)) return -EINVAL; memcpy(hdr, skb->data, 3); rc = ieee802154_hdr_minlen(hdr); if (rc < 0 || !pskb_may_pull(skb, rc)) return -EINVAL; pos += ieee802154_hdr_get_addrs(skb->data + pos, hdr); if (hdr->fc.security_enabled) { int want = pos + ieee802154_hdr_sechdr_len(skb->data[pos]); if (!pskb_may_pull(skb, want)) return -EINVAL; pos += ieee802154_hdr_get_sechdr(skb->data + pos, &hdr->sec); } skb_pull(skb, pos); return pos; } EXPORT_SYMBOL_GPL(ieee802154_hdr_pull); int ieee802154_mac_cmd_pl_pull(struct sk_buff *skb, struct ieee802154_mac_cmd_pl *mac_pl) { if (!pskb_may_pull(skb, sizeof(*mac_pl))) return -EINVAL; memcpy(mac_pl, skb->data, sizeof(*mac_pl)); skb_pull(skb, sizeof(*mac_pl)); return 0; } EXPORT_SYMBOL_GPL(ieee802154_mac_cmd_pl_pull); int ieee802154_hdr_peek_addrs(const struct sk_buff *skb, struct ieee802154_hdr *hdr) { const u8 *buf = skb_mac_header(skb); int pos = 3, rc; if (buf + 3 > skb_tail_pointer(skb)) return -EINVAL; memcpy(hdr, buf, 3); rc = ieee802154_hdr_minlen(hdr); if (rc < 0 || buf + rc > skb_tail_pointer(skb)) return -EINVAL; pos += ieee802154_hdr_get_addrs(buf + pos, hdr); return pos; } EXPORT_SYMBOL_GPL(ieee802154_hdr_peek_addrs); int ieee802154_hdr_peek(const struct sk_buff *skb, struct ieee802154_hdr *hdr) { const u8 *buf = skb_mac_header(skb); int pos; pos = ieee802154_hdr_peek_addrs(skb, hdr); if (pos < 0) return -EINVAL; if (hdr->fc.security_enabled) { u8 key_id_mode = IEEE802154_SCF_KEY_ID_MODE(*(buf + pos)); int want = pos + ieee802154_sechdr_lengths[key_id_mode]; if (buf + want > skb_tail_pointer(skb)) return -EINVAL; pos += ieee802154_hdr_get_sechdr(buf + pos, &hdr->sec); } return pos; } EXPORT_SYMBOL_GPL(ieee802154_hdr_peek); int ieee802154_max_payload(const struct ieee802154_hdr *hdr) { int hlen = ieee802154_hdr_minlen(hdr); if (hdr->fc.security_enabled) { hlen += ieee802154_sechdr_lengths[hdr->sec.key_id_mode] - 1; hlen += ieee802154_sechdr_authtag_len(&hdr->sec); } return IEEE802154_MTU - hlen - IEEE802154_MFR_SIZE; } EXPORT_SYMBOL_GPL(ieee802154_max_payload); |
| 2 2 2 2 2 1 1 28 28 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/if_bridge.h> #include <linux/in.h> #include <linux/list.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/rhashtable.h> #include <linux/rhashtable-types.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <linux/types.h> #include <net/netlink.h> #include <net/vxlan.h> #include "vxlan_private.h" struct vxlan_mdb_entry_key { union vxlan_addr src; union vxlan_addr dst; __be32 vni; }; struct vxlan_mdb_entry { struct rhash_head rhnode; struct list_head remotes; struct vxlan_mdb_entry_key key; struct hlist_node mdb_node; struct rcu_head rcu; }; #define VXLAN_MDB_REMOTE_F_BLOCKED BIT(0) struct vxlan_mdb_remote { struct list_head list; struct vxlan_rdst __rcu *rd; u8 flags; u8 filter_mode; u8 rt_protocol; struct hlist_head src_list; struct rcu_head rcu; }; #define VXLAN_SGRP_F_DELETE BIT(0) struct vxlan_mdb_src_entry { struct hlist_node node; union vxlan_addr addr; u8 flags; }; struct vxlan_mdb_dump_ctx { long reserved; long entry_idx; long remote_idx; }; struct vxlan_mdb_config_src_entry { union vxlan_addr addr; struct list_head node; }; struct vxlan_mdb_config { struct vxlan_dev *vxlan; struct vxlan_mdb_entry_key group; struct list_head src_list; union vxlan_addr remote_ip; u32 remote_ifindex; __be32 remote_vni; __be16 remote_port; u16 nlflags; u8 flags; u8 filter_mode; u8 rt_protocol; }; struct vxlan_mdb_flush_desc { union vxlan_addr remote_ip; __be32 src_vni; __be32 remote_vni; __be16 remote_port; u8 rt_protocol; }; static const struct rhashtable_params vxlan_mdb_rht_params = { .head_offset = offsetof(struct vxlan_mdb_entry, rhnode), .key_offset = offsetof(struct vxlan_mdb_entry, key), .key_len = sizeof(struct vxlan_mdb_entry_key), .automatic_shrinking = true, }; static int __vxlan_mdb_add(const struct vxlan_mdb_config *cfg, struct netlink_ext_ack *extack); static int __vxlan_mdb_del(const struct vxlan_mdb_config *cfg, struct netlink_ext_ack *extack); static void vxlan_br_mdb_entry_fill(const struct vxlan_dev *vxlan, const struct vxlan_mdb_entry *mdb_entry, const struct vxlan_mdb_remote *remote, struct br_mdb_entry *e) { const union vxlan_addr *dst = &mdb_entry->key.dst; memset(e, 0, sizeof(*e)); e->ifindex = vxlan->dev->ifindex; e->state = MDB_PERMANENT; if (remote->flags & VXLAN_MDB_REMOTE_F_BLOCKED) e->flags |= MDB_FLAGS_BLOCKED; switch (dst->sa.sa_family) { case AF_INET: e->addr.u.ip4 = dst->sin.sin_addr.s_addr; e->addr.proto = htons(ETH_P_IP); break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: e->addr.u.ip6 = dst->sin6.sin6_addr; e->addr.proto = htons(ETH_P_IPV6); break; #endif } } static int vxlan_mdb_entry_info_fill_srcs(struct sk_buff *skb, const struct vxlan_mdb_remote *remote) { struct vxlan_mdb_src_entry *ent; struct nlattr *nest; if (hlist_empty(&remote->src_list)) return 0; nest = nla_nest_start(skb, MDBA_MDB_EATTR_SRC_LIST); if (!nest) return -EMSGSIZE; hlist_for_each_entry(ent, &remote->src_list, node) { struct nlattr *nest_ent; nest_ent = nla_nest_start(skb, MDBA_MDB_SRCLIST_ENTRY); if (!nest_ent) goto out_cancel_err; if (vxlan_nla_put_addr(skb, MDBA_MDB_SRCATTR_ADDRESS, &ent->addr) || nla_put_u32(skb, MDBA_MDB_SRCATTR_TIMER, 0)) goto out_cancel_err; nla_nest_end(skb, nest_ent); } nla_nest_end(skb, nest); return 0; out_cancel_err: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int vxlan_mdb_entry_info_fill(const struct vxlan_dev *vxlan, struct sk_buff *skb, const struct vxlan_mdb_entry *mdb_entry, const struct vxlan_mdb_remote *remote) { struct vxlan_rdst *rd = rtnl_dereference(remote->rd); struct br_mdb_entry e; struct nlattr *nest; nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY_INFO); if (!nest) return -EMSGSIZE; vxlan_br_mdb_entry_fill(vxlan, mdb_entry, remote, &e); if (nla_put_nohdr(skb, sizeof(e), &e) || nla_put_u32(skb, MDBA_MDB_EATTR_TIMER, 0)) goto nest_err; if (!vxlan_addr_any(&mdb_entry->key.src) && vxlan_nla_put_addr(skb, MDBA_MDB_EATTR_SOURCE, &mdb_entry->key.src)) goto nest_err; if (nla_put_u8(skb, MDBA_MDB_EATTR_RTPROT, remote->rt_protocol) || nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE, remote->filter_mode) || vxlan_mdb_entry_info_fill_srcs(skb, remote) || vxlan_nla_put_addr(skb, MDBA_MDB_EATTR_DST, &rd->remote_ip)) goto nest_err; if (rd->remote_port && rd->remote_port != vxlan->cfg.dst_port && nla_put_u16(skb, MDBA_MDB_EATTR_DST_PORT, be16_to_cpu(rd->remote_port))) goto nest_err; if (rd->remote_vni != vxlan->default_dst.remote_vni && nla_put_u32(skb, MDBA_MDB_EATTR_VNI, be32_to_cpu(rd->remote_vni))) goto nest_err; if (rd->remote_ifindex && nla_put_u32(skb, MDBA_MDB_EATTR_IFINDEX, rd->remote_ifindex)) goto nest_err; if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && mdb_entry->key.vni && nla_put_u32(skb, MDBA_MDB_EATTR_SRC_VNI, be32_to_cpu(mdb_entry->key.vni))) goto nest_err; nla_nest_end(skb, nest); return 0; nest_err: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int vxlan_mdb_entry_fill(const struct vxlan_dev *vxlan, struct sk_buff *skb, struct vxlan_mdb_dump_ctx *ctx, const struct vxlan_mdb_entry *mdb_entry) { int remote_idx = 0, s_remote_idx = ctx->remote_idx; struct vxlan_mdb_remote *remote; struct nlattr *nest; int err = 0; nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY); if (!nest) return -EMSGSIZE; list_for_each_entry(remote, &mdb_entry->remotes, list) { if (remote_idx < s_remote_idx) goto skip; err = vxlan_mdb_entry_info_fill(vxlan, skb, mdb_entry, remote); if (err) break; skip: remote_idx++; } ctx->remote_idx = err ? remote_idx : 0; nla_nest_end(skb, nest); return err; } static int vxlan_mdb_fill(const struct vxlan_dev *vxlan, struct sk_buff *skb, struct vxlan_mdb_dump_ctx *ctx) { int entry_idx = 0, s_entry_idx = ctx->entry_idx; struct vxlan_mdb_entry *mdb_entry; struct nlattr *nest; int err = 0; nest = nla_nest_start_noflag(skb, MDBA_MDB); if (!nest) return -EMSGSIZE; hlist_for_each_entry(mdb_entry, &vxlan->mdb_list, mdb_node) { if (entry_idx < s_entry_idx) goto skip; err = vxlan_mdb_entry_fill(vxlan, skb, ctx, mdb_entry); if (err) break; skip: entry_idx++; } ctx->entry_idx = err ? entry_idx : 0; nla_nest_end(skb, nest); return err; } int vxlan_mdb_dump(struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb) { struct vxlan_mdb_dump_ctx *ctx = (void *)cb->ctx; struct vxlan_dev *vxlan = netdev_priv(dev); struct br_port_msg *bpm; struct nlmsghdr *nlh; int err; ASSERT_RTNL(); NL_ASSERT_CTX_FITS(struct vxlan_mdb_dump_ctx); nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWMDB, sizeof(*bpm), NLM_F_MULTI); if (!nlh) return -EMSGSIZE; bpm = nlmsg_data(nlh); memset(bpm, 0, sizeof(*bpm)); bpm->family = AF_BRIDGE; bpm->ifindex = dev->ifindex; err = vxlan_mdb_fill(vxlan, skb, ctx); nlmsg_end(skb, nlh); cb->seq = vxlan->mdb_seq; nl_dump_check_consistent(cb, nlh); return err; } static const struct nla_policy vxlan_mdbe_src_list_entry_pol[MDBE_SRCATTR_MAX + 1] = { [MDBE_SRCATTR_ADDRESS] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), }; static const struct nla_policy vxlan_mdbe_src_list_pol[MDBE_SRC_LIST_MAX + 1] = { [MDBE_SRC_LIST_ENTRY] = NLA_POLICY_NESTED(vxlan_mdbe_src_list_entry_pol), }; static const struct netlink_range_validation vni_range = { .max = VXLAN_N_VID - 1, }; static const struct nla_policy vxlan_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), [MDBE_ATTR_GROUP_MODE] = NLA_POLICY_RANGE(NLA_U8, MCAST_EXCLUDE, MCAST_INCLUDE), [MDBE_ATTR_SRC_LIST] = NLA_POLICY_NESTED(vxlan_mdbe_src_list_pol), [MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC), [MDBE_ATTR_DST] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), [MDBE_ATTR_DST_PORT] = { .type = NLA_U16 }, [MDBE_ATTR_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range), [MDBE_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1), [MDBE_ATTR_SRC_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range), }; static bool vxlan_mdb_is_valid_source(const struct nlattr *attr, __be16 proto, struct netlink_ext_ack *extack) { switch (proto) { case htons(ETH_P_IP): if (nla_len(attr) != sizeof(struct in_addr)) { NL_SET_ERR_MSG_MOD(extack, "IPv4 invalid source address length"); return false; } if (ipv4_is_multicast(nla_get_in_addr(attr))) { NL_SET_ERR_MSG_MOD(extack, "IPv4 multicast source address is not allowed"); return false; } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): { struct in6_addr src; if (nla_len(attr) != sizeof(struct in6_addr)) { NL_SET_ERR_MSG_MOD(extack, "IPv6 invalid source address length"); return false; } src = nla_get_in6_addr(attr); if (ipv6_addr_is_multicast(&src)) { NL_SET_ERR_MSG_MOD(extack, "IPv6 multicast source address is not allowed"); return false; } break; } #endif default: NL_SET_ERR_MSG_MOD(extack, "Invalid protocol used with source address"); return false; } return true; } static void vxlan_mdb_group_set(struct vxlan_mdb_entry_key *group, const struct br_mdb_entry *entry, const struct nlattr *source_attr) { switch (entry->addr.proto) { case htons(ETH_P_IP): group->dst.sa.sa_family = AF_INET; group->dst.sin.sin_addr.s_addr = entry->addr.u.ip4; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): group->dst.sa.sa_family = AF_INET6; group->dst.sin6.sin6_addr = entry->addr.u.ip6; break; #endif } if (source_attr) vxlan_nla_get_addr(&group->src, source_attr); } static bool vxlan_mdb_is_star_g(const struct vxlan_mdb_entry_key *group) { return !vxlan_addr_any(&group->dst) && vxlan_addr_any(&group->src); } static bool vxlan_mdb_is_sg(const struct vxlan_mdb_entry_key *group) { return !vxlan_addr_any(&group->dst) && !vxlan_addr_any(&group->src); } static int vxlan_mdb_config_src_entry_init(struct vxlan_mdb_config *cfg, __be16 proto, const struct nlattr *src_entry, struct netlink_ext_ack *extack) { struct nlattr *tb[MDBE_SRCATTR_MAX + 1]; struct vxlan_mdb_config_src_entry *src; int err; err = nla_parse_nested(tb, MDBE_SRCATTR_MAX, src_entry, vxlan_mdbe_src_list_entry_pol, extack); if (err) return err; if (NL_REQ_ATTR_CHECK(extack, src_entry, tb, MDBE_SRCATTR_ADDRESS)) return -EINVAL; if (!vxlan_mdb_is_valid_source(tb[MDBE_SRCATTR_ADDRESS], proto, extack)) return -EINVAL; src = kzalloc(sizeof(*src), GFP_KERNEL); if (!src) return -ENOMEM; err = vxlan_nla_get_addr(&src->addr, tb[MDBE_SRCATTR_ADDRESS]); if (err) goto err_free_src; list_add_tail(&src->node, &cfg->src_list); return 0; err_free_src: kfree(src); return err; } static void vxlan_mdb_config_src_entry_fini(struct vxlan_mdb_config_src_entry *src) { list_del(&src->node); kfree(src); } static int vxlan_mdb_config_src_list_init(struct vxlan_mdb_config *cfg, __be16 proto, const struct nlattr *src_list, struct netlink_ext_ack *extack) { struct vxlan_mdb_config_src_entry *src, *tmp; struct nlattr *src_entry; int rem, err; nla_for_each_nested(src_entry, src_list, rem) { err = vxlan_mdb_config_src_entry_init(cfg, proto, src_entry, extack); if (err) goto err_src_entry_init; } return 0; err_src_entry_init: list_for_each_entry_safe_reverse(src, tmp, &cfg->src_list, node) vxlan_mdb_config_src_entry_fini(src); return err; } static void vxlan_mdb_config_src_list_fini(struct vxlan_mdb_config *cfg) { struct vxlan_mdb_config_src_entry *src, *tmp; list_for_each_entry_safe_reverse(src, tmp, &cfg->src_list, node) vxlan_mdb_config_src_entry_fini(src); } static int vxlan_mdb_config_attrs_init(struct vxlan_mdb_config *cfg, const struct br_mdb_entry *entry, const struct nlattr *set_attrs, struct netlink_ext_ack *extack) { struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1]; int err; err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX, set_attrs, vxlan_mdbe_attrs_pol, extack); if (err) return err; if (NL_REQ_ATTR_CHECK(extack, set_attrs, mdbe_attrs, MDBE_ATTR_DST)) { NL_SET_ERR_MSG_MOD(extack, "Missing remote destination IP address"); return -EINVAL; } if (mdbe_attrs[MDBE_ATTR_SOURCE] && !vxlan_mdb_is_valid_source(mdbe_attrs[MDBE_ATTR_SOURCE], entry->addr.proto, extack)) return -EINVAL; vxlan_mdb_group_set(&cfg->group, entry, mdbe_attrs[MDBE_ATTR_SOURCE]); /* rtnetlink code only validates that IPv4 group address is * multicast. */ if (!vxlan_addr_is_multicast(&cfg->group.dst) && !vxlan_addr_any(&cfg->group.dst)) { NL_SET_ERR_MSG_MOD(extack, "Group address is not multicast"); return -EINVAL; } if (vxlan_addr_any(&cfg->group.dst) && mdbe_attrs[MDBE_ATTR_SOURCE]) { NL_SET_ERR_MSG_MOD(extack, "Source cannot be specified for the all-zeros entry"); return -EINVAL; } if (vxlan_mdb_is_sg(&cfg->group)) cfg->filter_mode = MCAST_INCLUDE; if (mdbe_attrs[MDBE_ATTR_GROUP_MODE]) { if (!vxlan_mdb_is_star_g(&cfg->group)) { NL_SET_ERR_MSG_MOD(extack, "Filter mode can only be set for (*, G) entries"); return -EINVAL; } cfg->filter_mode = nla_get_u8(mdbe_attrs[MDBE_ATTR_GROUP_MODE]); } if (mdbe_attrs[MDBE_ATTR_SRC_LIST]) { if (!vxlan_mdb_is_star_g(&cfg->group)) { NL_SET_ERR_MSG_MOD(extack, "Source list can only be set for (*, G) entries"); return -EINVAL; } if (!mdbe_attrs[MDBE_ATTR_GROUP_MODE]) { NL_SET_ERR_MSG_MOD(extack, "Source list cannot be set without filter mode"); return -EINVAL; } err = vxlan_mdb_config_src_list_init(cfg, entry->addr.proto, mdbe_attrs[MDBE_ATTR_SRC_LIST], extack); if (err) return err; } if (vxlan_mdb_is_star_g(&cfg->group) && list_empty(&cfg->src_list) && cfg->filter_mode == MCAST_INCLUDE) { NL_SET_ERR_MSG_MOD(extack, "Cannot add (*, G) INCLUDE with an empty source list"); return -EINVAL; } if (mdbe_attrs[MDBE_ATTR_RTPROT]) cfg->rt_protocol = nla_get_u8(mdbe_attrs[MDBE_ATTR_RTPROT]); err = vxlan_nla_get_addr(&cfg->remote_ip, mdbe_attrs[MDBE_ATTR_DST]); if (err) { NL_SET_ERR_MSG_MOD(extack, "Invalid remote destination address"); goto err_src_list_fini; } if (mdbe_attrs[MDBE_ATTR_DST_PORT]) cfg->remote_port = cpu_to_be16(nla_get_u16(mdbe_attrs[MDBE_ATTR_DST_PORT])); if (mdbe_attrs[MDBE_ATTR_VNI]) cfg->remote_vni = cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_VNI])); if (mdbe_attrs[MDBE_ATTR_IFINDEX]) { cfg->remote_ifindex = nla_get_s32(mdbe_attrs[MDBE_ATTR_IFINDEX]); if (!__dev_get_by_index(cfg->vxlan->net, cfg->remote_ifindex)) { NL_SET_ERR_MSG_MOD(extack, "Outgoing interface not found"); err = -EINVAL; goto err_src_list_fini; } } if (mdbe_attrs[MDBE_ATTR_SRC_VNI]) cfg->group.vni = cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_SRC_VNI])); return 0; err_src_list_fini: vxlan_mdb_config_src_list_fini(cfg); return err; } static int vxlan_mdb_config_init(struct vxlan_mdb_config *cfg, struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags, struct netlink_ext_ack *extack) { struct br_mdb_entry *entry = nla_data(tb[MDBA_SET_ENTRY]); struct vxlan_dev *vxlan = netdev_priv(dev); memset(cfg, 0, sizeof(*cfg)); cfg->vxlan = vxlan; cfg->group.vni = vxlan->default_dst.remote_vni; INIT_LIST_HEAD(&cfg->src_list); cfg->nlflags = nlmsg_flags; cfg->filter_mode = MCAST_EXCLUDE; cfg->rt_protocol = RTPROT_STATIC; cfg->remote_vni = vxlan->default_dst.remote_vni; cfg->remote_port = vxlan->cfg.dst_port; if (entry->ifindex != dev->ifindex) { NL_SET_ERR_MSG_MOD(extack, "Port net device must be the VXLAN net device"); return -EINVAL; } /* State is not part of the entry key and can be ignored on deletion * requests. */ if ((nlmsg_flags & (NLM_F_CREATE | NLM_F_REPLACE)) && entry->state != MDB_PERMANENT) { NL_SET_ERR_MSG_MOD(extack, "MDB entry must be permanent"); return -EINVAL; } if (entry->flags) { NL_SET_ERR_MSG_MOD(extack, "Invalid MDB entry flags"); return -EINVAL; } if (entry->vid) { NL_SET_ERR_MSG_MOD(extack, "VID must not be specified"); return -EINVAL; } if (entry->addr.proto != htons(ETH_P_IP) && entry->addr.proto != htons(ETH_P_IPV6)) { NL_SET_ERR_MSG_MOD(extack, "Group address must be an IPv4 / IPv6 address"); return -EINVAL; } if (NL_REQ_ATTR_CHECK(extack, NULL, tb, MDBA_SET_ENTRY_ATTRS)) { NL_SET_ERR_MSG_MOD(extack, "Missing MDBA_SET_ENTRY_ATTRS attribute"); return -EINVAL; } return vxlan_mdb_config_attrs_init(cfg, entry, tb[MDBA_SET_ENTRY_ATTRS], extack); } static void vxlan_mdb_config_fini(struct vxlan_mdb_config *cfg) { vxlan_mdb_config_src_list_fini(cfg); } static struct vxlan_mdb_entry * vxlan_mdb_entry_lookup(struct vxlan_dev *vxlan, const struct vxlan_mdb_entry_key *group) { return rhashtable_lookup_fast(&vxlan->mdb_tbl, group, vxlan_mdb_rht_params); } static struct vxlan_mdb_remote * vxlan_mdb_remote_lookup(const struct vxlan_mdb_entry *mdb_entry, const union vxlan_addr *addr) { struct vxlan_mdb_remote *remote; list_for_each_entry(remote, &mdb_entry->remotes, list) { struct vxlan_rdst *rd = rtnl_dereference(remote->rd); if (vxlan_addr_equal(addr, &rd->remote_ip)) return remote; } return NULL; } static void vxlan_mdb_rdst_free(struct rcu_head *head) { struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu); dst_cache_destroy(&rd->dst_cache); kfree(rd); } static int vxlan_mdb_remote_rdst_init(const struct vxlan_mdb_config *cfg, struct vxlan_mdb_remote *remote) { struct vxlan_rdst *rd; int err; rd = kzalloc(sizeof(*rd), GFP_KERNEL); if (!rd) return -ENOMEM; err = dst_cache_init(&rd->dst_cache, GFP_KERNEL); if (err) goto err_free_rdst; rd->remote_ip = cfg->remote_ip; rd->remote_port = cfg->remote_port; rd->remote_vni = cfg->remote_vni; rd->remote_ifindex = cfg->remote_ifindex; rcu_assign_pointer(remote->rd, rd); return 0; err_free_rdst: kfree(rd); return err; } static void vxlan_mdb_remote_rdst_fini(struct vxlan_rdst *rd) { call_rcu(&rd->rcu, vxlan_mdb_rdst_free); } static int vxlan_mdb_remote_init(const struct vxlan_mdb_config *cfg, struct vxlan_mdb_remote *remote) { int err; err = vxlan_mdb_remote_rdst_init(cfg, remote); if (err) return err; remote->flags = cfg->flags; remote->filter_mode = cfg->filter_mode; remote->rt_protocol = cfg->rt_protocol; INIT_HLIST_HEAD(&remote->src_list); return 0; } static void vxlan_mdb_remote_fini(struct vxlan_dev *vxlan, struct vxlan_mdb_remote *remote) { WARN_ON_ONCE(!hlist_empty(&remote->src_list)); vxlan_mdb_remote_rdst_fini(rtnl_dereference(remote->rd)); } static struct vxlan_mdb_src_entry * vxlan_mdb_remote_src_entry_lookup(const struct vxlan_mdb_remote *remote, const union vxlan_addr *addr) { struct vxlan_mdb_src_entry *ent; hlist_for_each_entry(ent, &remote->src_list, node) { if (vxlan_addr_equal(&ent->addr, addr)) return ent; } return NULL; } static struct vxlan_mdb_src_entry * vxlan_mdb_remote_src_entry_add(struct vxlan_mdb_remote *remote, const union vxlan_addr *addr) { struct vxlan_mdb_src_entry *ent; ent = kzalloc(sizeof(*ent), GFP_KERNEL); if (!ent) return NULL; ent->addr = *addr; hlist_add_head(&ent->node, &remote->src_list); return ent; } static void vxlan_mdb_remote_src_entry_del(struct vxlan_mdb_src_entry *ent) { hlist_del(&ent->node); kfree(ent); } static int vxlan_mdb_remote_src_fwd_add(const struct vxlan_mdb_config *cfg, const union vxlan_addr *addr, struct netlink_ext_ack *extack) { struct vxlan_mdb_config sg_cfg; memset(&sg_cfg, 0, sizeof(sg_cfg)); sg_cfg.vxlan = cfg->vxlan; sg_cfg.group.src = *addr; sg_cfg.group.dst = cfg->group.dst; sg_cfg.group.vni = cfg->group.vni; INIT_LIST_HEAD(&sg_cfg.src_list); sg_cfg.remote_ip = cfg->remote_ip; sg_cfg.remote_ifindex = cfg->remote_ifindex; sg_cfg.remote_vni = cfg->remote_vni; sg_cfg.remote_port = cfg->remote_port; sg_cfg.nlflags = cfg->nlflags; sg_cfg.filter_mode = MCAST_INCLUDE; if (cfg->filter_mode == MCAST_EXCLUDE) sg_cfg.flags = VXLAN_MDB_REMOTE_F_BLOCKED; sg_cfg.rt_protocol = cfg->rt_protocol; return __vxlan_mdb_add(&sg_cfg, extack); } static void vxlan_mdb_remote_src_fwd_del(struct vxlan_dev *vxlan, const struct vxlan_mdb_entry_key *group, const struct vxlan_mdb_remote *remote, const union vxlan_addr *addr) { struct vxlan_rdst *rd = rtnl_dereference(remote->rd); struct vxlan_mdb_config sg_cfg; memset(&sg_cfg, 0, sizeof(sg_cfg)); sg_cfg.vxlan = vxlan; sg_cfg.group.src = *addr; sg_cfg.group.dst = group->dst; sg_cfg.group.vni = group->vni; INIT_LIST_HEAD(&sg_cfg.src_list); sg_cfg.remote_ip = rd->remote_ip; __vxlan_mdb_del(&sg_cfg, NULL); } static int vxlan_mdb_remote_src_add(const struct vxlan_mdb_config *cfg, struct vxlan_mdb_remote *remote, const struct vxlan_mdb_config_src_entry *src, struct netlink_ext_ack *extack) { struct vxlan_mdb_src_entry *ent; int err; ent = vxlan_mdb_remote_src_entry_lookup(remote, &src->addr); if (!ent) { ent = vxlan_mdb_remote_src_entry_add(remote, &src->addr); if (!ent) return -ENOMEM; } else if (!(cfg->nlflags & NLM_F_REPLACE)) { NL_SET_ERR_MSG_MOD(extack, "Source entry already exists"); return -EEXIST; } err = vxlan_mdb_remote_src_fwd_add(cfg, &ent->addr, extack); if (err) goto err_src_del; /* Clear flags in case source entry was marked for deletion as part of * replace flow. */ ent->flags = 0; return 0; err_src_del: vxlan_mdb_remote_src_entry_del(ent); return err; } static void vxlan_mdb_remote_src_del(struct vxlan_dev *vxlan, const struct vxlan_mdb_entry_key *group, const struct vxlan_mdb_remote *remote, struct vxlan_mdb_src_entry *ent) { vxlan_mdb_remote_src_fwd_del(vxlan, group, remote, &ent->addr); vxlan_mdb_remote_src_entry_del(ent); } static int vxlan_mdb_remote_srcs_add(const struct vxlan_mdb_config *cfg, struct vxlan_mdb_remote *remote, struct netlink_ext_ack *extack) { struct vxlan_mdb_config_src_entry *src; struct vxlan_mdb_src_entry *ent; struct hlist_node *tmp; int err; list_for_each_entry(src, &cfg->src_list, node) { err = vxlan_mdb_remote_src_add(cfg, remote, src, extack); if (err) goto err_src_del; } return 0; err_src_del: hlist_for_each_entry_safe(ent, tmp, &remote->src_list, node) vxlan_mdb_remote_src_del(cfg->vxlan, &cfg->group, remote, ent); return err; } static void vxlan_mdb_remote_srcs_del(struct vxlan_dev *vxlan, const struct vxlan_mdb_entry_key *group, struct vxlan_mdb_remote *remote) { struct vxlan_mdb_src_entry *ent; struct hlist_node *tmp; hlist_for_each_entry_safe(ent, tmp, &remote->src_list, node) vxlan_mdb_remote_src_del(vxlan, group, remote, ent); } static size_t vxlan_mdb_nlmsg_src_list_size(const struct vxlan_mdb_entry_key *group, const struct vxlan_mdb_remote *remote) { struct vxlan_mdb_src_entry *ent; size_t nlmsg_size; if (hlist_empty(&remote->src_list)) return 0; /* MDBA_MDB_EATTR_SRC_LIST */ nlmsg_size = nla_total_size(0); hlist_for_each_entry(ent, &remote->src_list, node) { /* MDBA_MDB_SRCLIST_ENTRY */ nlmsg_size += nla_total_size(0) + /* MDBA_MDB_SRCATTR_ADDRESS */ nla_total_size(vxlan_addr_size(&group->dst)) + /* MDBA_MDB_SRCATTR_TIMER */ nla_total_size(sizeof(u8)); } return nlmsg_size; } static size_t vxlan_mdb_nlmsg_remote_size(const struct vxlan_dev *vxlan, const struct vxlan_mdb_entry *mdb_entry, const struct vxlan_mdb_remote *remote) { const struct vxlan_mdb_entry_key *group = &mdb_entry->key; struct vxlan_rdst *rd = rtnl_dereference(remote->rd); size_t nlmsg_size; /* MDBA_MDB_ENTRY_INFO */ nlmsg_size = nla_total_size(sizeof(struct br_mdb_entry)) + /* MDBA_MDB_EATTR_TIMER */ nla_total_size(sizeof(u32)); /* MDBA_MDB_EATTR_SOURCE */ if (vxlan_mdb_is_sg(group)) nlmsg_size += nla_total_size(vxlan_addr_size(&group->dst)); /* MDBA_MDB_EATTR_RTPROT */ nlmsg_size += nla_total_size(sizeof(u8)); /* MDBA_MDB_EATTR_SRC_LIST */ nlmsg_size += vxlan_mdb_nlmsg_src_list_size(group, remote); /* MDBA_MDB_EATTR_GROUP_MODE */ nlmsg_size += nla_total_size(sizeof(u8)); /* MDBA_MDB_EATTR_DST */ nlmsg_size += nla_total_size(vxlan_addr_size(&rd->remote_ip)); /* MDBA_MDB_EATTR_DST_PORT */ if (rd->remote_port && rd->remote_port != vxlan->cfg.dst_port) nlmsg_size += nla_total_size(sizeof(u16)); /* MDBA_MDB_EATTR_VNI */ if (rd->remote_vni != vxlan->default_dst.remote_vni) nlmsg_size += nla_total_size(sizeof(u32)); /* MDBA_MDB_EATTR_IFINDEX */ if (rd->remote_ifindex) nlmsg_size += nla_total_size(sizeof(u32)); /* MDBA_MDB_EATTR_SRC_VNI */ if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && group->vni) nlmsg_size += nla_total_size(sizeof(u32)); return nlmsg_size; } static size_t vxlan_mdb_nlmsg_size(const struct vxlan_dev *vxlan, const struct vxlan_mdb_entry *mdb_entry, const struct vxlan_mdb_remote *remote) { return NLMSG_ALIGN(sizeof(struct br_port_msg)) + /* MDBA_MDB */ nla_total_size(0) + /* MDBA_MDB_ENTRY */ nla_total_size(0) + /* Remote entry */ vxlan_mdb_nlmsg_remote_size(vxlan, mdb_entry, remote); } static int vxlan_mdb_nlmsg_fill(const struct vxlan_dev *vxlan, struct sk_buff *skb, const struct vxlan_mdb_entry *mdb_entry, const struct vxlan_mdb_remote *remote, int type) { struct nlattr *mdb_nest, *mdb_entry_nest; struct br_port_msg *bpm; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, 0, 0, type, sizeof(*bpm), 0); if (!nlh) return -EMSGSIZE; bpm = nlmsg_data(nlh); memset(bpm, 0, sizeof(*bpm)); bpm->family = AF_BRIDGE; bpm->ifindex = vxlan->dev->ifindex; mdb_nest = nla_nest_start_noflag(skb, MDBA_MDB); if (!mdb_nest) goto cancel; mdb_entry_nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY); if (!mdb_entry_nest) goto cancel; if (vxlan_mdb_entry_info_fill(vxlan, skb, mdb_entry, remote)) goto cancel; nla_nest_end(skb, mdb_entry_nest); nla_nest_end(skb, mdb_nest); nlmsg_end(skb, nlh); return 0; cancel: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static void vxlan_mdb_remote_notify(const struct vxlan_dev *vxlan, const struct vxlan_mdb_entry *mdb_entry, const struct vxlan_mdb_remote *remote, int type) { struct net *net = dev_net(vxlan->dev); struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(vxlan_mdb_nlmsg_size(vxlan, mdb_entry, remote), GFP_KERNEL); if (!skb) goto errout; err = vxlan_mdb_nlmsg_fill(vxlan, skb, mdb_entry, remote, type); if (err) { kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_MDB, err); } static int vxlan_mdb_remote_srcs_replace(const struct vxlan_mdb_config *cfg, const struct vxlan_mdb_entry *mdb_entry, struct vxlan_mdb_remote *remote, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = cfg->vxlan; struct vxlan_mdb_src_entry *ent; struct hlist_node *tmp; int err; hlist_for_each_entry(ent, &remote->src_list, node) ent->flags |= VXLAN_SGRP_F_DELETE; err = vxlan_mdb_remote_srcs_add(cfg, remote, extack); if (err) goto err_clear_delete; hlist_for_each_entry_safe(ent, tmp, &remote->src_list, node) { if (ent->flags & VXLAN_SGRP_F_DELETE) vxlan_mdb_remote_src_del(vxlan, &mdb_entry->key, remote, ent); } return 0; err_clear_delete: hlist_for_each_entry(ent, &remote->src_list, node) ent->flags &= ~VXLAN_SGRP_F_DELETE; return err; } static int vxlan_mdb_remote_replace(const struct vxlan_mdb_config *cfg, const struct vxlan_mdb_entry *mdb_entry, struct vxlan_mdb_remote *remote, struct netlink_ext_ack *extack) { struct vxlan_rdst *new_rd, *old_rd = rtnl_dereference(remote->rd); struct vxlan_dev *vxlan = cfg->vxlan; int err; err = vxlan_mdb_remote_rdst_init(cfg, remote); if (err) return err; new_rd = rtnl_dereference(remote->rd); err = vxlan_mdb_remote_srcs_replace(cfg, mdb_entry, remote, extack); if (err) goto err_rdst_reset; WRITE_ONCE(remote->flags, cfg->flags); WRITE_ONCE(remote->filter_mode, cfg->filter_mode); remote->rt_protocol = cfg->rt_protocol; vxlan_mdb_remote_notify(vxlan, mdb_entry, remote, RTM_NEWMDB); vxlan_mdb_remote_rdst_fini(old_rd); return 0; err_rdst_reset: rcu_assign_pointer(remote->rd, old_rd); vxlan_mdb_remote_rdst_fini(new_rd); return err; } static int vxlan_mdb_remote_add(const struct vxlan_mdb_config *cfg, struct vxlan_mdb_entry *mdb_entry, struct netlink_ext_ack *extack) { struct vxlan_mdb_remote *remote; int err; remote = vxlan_mdb_remote_lookup(mdb_entry, &cfg->remote_ip); if (remote) { if (!(cfg->nlflags & NLM_F_REPLACE)) { NL_SET_ERR_MSG_MOD(extack, "Replace not specified and MDB remote entry already exists"); return -EEXIST; } return vxlan_mdb_remote_replace(cfg, mdb_entry, remote, extack); } if (!(cfg->nlflags & NLM_F_CREATE)) { NL_SET_ERR_MSG_MOD(extack, "Create not specified and entry does not exist"); return -ENOENT; } remote = kzalloc(sizeof(*remote), GFP_KERNEL); if (!remote) return -ENOMEM; err = vxlan_mdb_remote_init(cfg, remote); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed to initialize remote MDB entry"); goto err_free_remote; } err = vxlan_mdb_remote_srcs_add(cfg, remote, extack); if (err) goto err_remote_fini; list_add_rcu(&remote->list, &mdb_entry->remotes); vxlan_mdb_remote_notify(cfg->vxlan, mdb_entry, remote, RTM_NEWMDB); return 0; err_remote_fini: vxlan_mdb_remote_fini(cfg->vxlan, remote); err_free_remote: kfree(remote); return err; } static void vxlan_mdb_remote_del(struct vxlan_dev *vxlan, struct vxlan_mdb_entry *mdb_entry, struct vxlan_mdb_remote *remote) { vxlan_mdb_remote_notify(vxlan, mdb_entry, remote, RTM_DELMDB); list_del_rcu(&remote->list); vxlan_mdb_remote_srcs_del(vxlan, &mdb_entry->key, remote); vxlan_mdb_remote_fini(vxlan, remote); kfree_rcu(remote, rcu); } static struct vxlan_mdb_entry * vxlan_mdb_entry_get(struct vxlan_dev *vxlan, const struct vxlan_mdb_entry_key *group) { struct vxlan_mdb_entry *mdb_entry; int err; mdb_entry = vxlan_mdb_entry_lookup(vxlan, group); if (mdb_entry) return mdb_entry; mdb_entry = kzalloc(sizeof(*mdb_entry), GFP_KERNEL); if (!mdb_entry) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&mdb_entry->remotes); memcpy(&mdb_entry->key, group, sizeof(mdb_entry->key)); hlist_add_head(&mdb_entry->mdb_node, &vxlan->mdb_list); err = rhashtable_lookup_insert_fast(&vxlan->mdb_tbl, &mdb_entry->rhnode, vxlan_mdb_rht_params); if (err) goto err_free_entry; if (hlist_is_singular_node(&mdb_entry->mdb_node, &vxlan->mdb_list)) vxlan->cfg.flags |= VXLAN_F_MDB; return mdb_entry; err_free_entry: hlist_del(&mdb_entry->mdb_node); kfree(mdb_entry); return ERR_PTR(err); } static void vxlan_mdb_entry_put(struct vxlan_dev *vxlan, struct vxlan_mdb_entry *mdb_entry) { if (!list_empty(&mdb_entry->remotes)) return; if (hlist_is_singular_node(&mdb_entry->mdb_node, &vxlan->mdb_list)) vxlan->cfg.flags &= ~VXLAN_F_MDB; rhashtable_remove_fast(&vxlan->mdb_tbl, &mdb_entry->rhnode, vxlan_mdb_rht_params); hlist_del(&mdb_entry->mdb_node); kfree_rcu(mdb_entry, rcu); } static int __vxlan_mdb_add(const struct vxlan_mdb_config *cfg, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = cfg->vxlan; struct vxlan_mdb_entry *mdb_entry; int err; mdb_entry = vxlan_mdb_entry_get(vxlan, &cfg->group); if (IS_ERR(mdb_entry)) return PTR_ERR(mdb_entry); err = vxlan_mdb_remote_add(cfg, mdb_entry, extack); if (err) goto err_entry_put; vxlan->mdb_seq++; return 0; err_entry_put: vxlan_mdb_entry_put(vxlan, mdb_entry); return err; } static int __vxlan_mdb_del(const struct vxlan_mdb_config *cfg, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = cfg->vxlan; struct vxlan_mdb_entry *mdb_entry; struct vxlan_mdb_remote *remote; mdb_entry = vxlan_mdb_entry_lookup(vxlan, &cfg->group); if (!mdb_entry) { NL_SET_ERR_MSG_MOD(extack, "Did not find MDB entry"); return -ENOENT; } remote = vxlan_mdb_remote_lookup(mdb_entry, &cfg->remote_ip); if (!remote) { NL_SET_ERR_MSG_MOD(extack, "Did not find MDB remote entry"); return -ENOENT; } vxlan_mdb_remote_del(vxlan, mdb_entry, remote); vxlan_mdb_entry_put(vxlan, mdb_entry); vxlan->mdb_seq++; return 0; } int vxlan_mdb_add(struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags, struct netlink_ext_ack *extack) { struct vxlan_mdb_config cfg; int err; ASSERT_RTNL(); err = vxlan_mdb_config_init(&cfg, dev, tb, nlmsg_flags, extack); if (err) return err; err = __vxlan_mdb_add(&cfg, extack); vxlan_mdb_config_fini(&cfg); return err; } int vxlan_mdb_del(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct vxlan_mdb_config cfg; int err; ASSERT_RTNL(); err = vxlan_mdb_config_init(&cfg, dev, tb, 0, extack); if (err) return err; err = __vxlan_mdb_del(&cfg, extack); vxlan_mdb_config_fini(&cfg); return err; } static const struct nla_policy vxlan_mdbe_attrs_del_bulk_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC), [MDBE_ATTR_DST] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), [MDBE_ATTR_DST_PORT] = { .type = NLA_U16 }, [MDBE_ATTR_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range), [MDBE_ATTR_SRC_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range), [MDBE_ATTR_STATE_MASK] = NLA_POLICY_MASK(NLA_U8, MDB_PERMANENT), }; static int vxlan_mdb_flush_desc_init(struct vxlan_dev *vxlan, struct vxlan_mdb_flush_desc *desc, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct br_mdb_entry *entry = nla_data(tb[MDBA_SET_ENTRY]); struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1]; int err; if (entry->ifindex && entry->ifindex != vxlan->dev->ifindex) { NL_SET_ERR_MSG_MOD(extack, "Invalid port net device"); return -EINVAL; } if (entry->vid) { NL_SET_ERR_MSG_MOD(extack, "VID must not be specified"); return -EINVAL; } if (!tb[MDBA_SET_ENTRY_ATTRS]) return 0; err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX, tb[MDBA_SET_ENTRY_ATTRS], vxlan_mdbe_attrs_del_bulk_pol, extack); if (err) return err; if (mdbe_attrs[MDBE_ATTR_STATE_MASK]) { u8 state_mask = nla_get_u8(mdbe_attrs[MDBE_ATTR_STATE_MASK]); if ((state_mask & MDB_PERMANENT) && !(entry->state & MDB_PERMANENT)) { NL_SET_ERR_MSG_MOD(extack, "Only permanent MDB entries are supported"); return -EINVAL; } } if (mdbe_attrs[MDBE_ATTR_RTPROT]) desc->rt_protocol = nla_get_u8(mdbe_attrs[MDBE_ATTR_RTPROT]); if (mdbe_attrs[MDBE_ATTR_DST]) vxlan_nla_get_addr(&desc->remote_ip, mdbe_attrs[MDBE_ATTR_DST]); if (mdbe_attrs[MDBE_ATTR_DST_PORT]) desc->remote_port = cpu_to_be16(nla_get_u16(mdbe_attrs[MDBE_ATTR_DST_PORT])); if (mdbe_attrs[MDBE_ATTR_VNI]) desc->remote_vni = cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_VNI])); if (mdbe_attrs[MDBE_ATTR_SRC_VNI]) desc->src_vni = cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_SRC_VNI])); return 0; } static void vxlan_mdb_remotes_flush(struct vxlan_dev *vxlan, struct vxlan_mdb_entry *mdb_entry, const struct vxlan_mdb_flush_desc *desc) { struct vxlan_mdb_remote *remote, *tmp; list_for_each_entry_safe(remote, tmp, &mdb_entry->remotes, list) { struct vxlan_rdst *rd = rtnl_dereference(remote->rd); __be32 remote_vni; if (desc->remote_ip.sa.sa_family && !vxlan_addr_equal(&desc->remote_ip, &rd->remote_ip)) continue; /* Encapsulation is performed with source VNI if remote VNI * is not set. */ remote_vni = rd->remote_vni ? : mdb_entry->key.vni; if (desc->remote_vni && desc->remote_vni != remote_vni) continue; if (desc->remote_port && desc->remote_port != rd->remote_port) continue; if (desc->rt_protocol && desc->rt_protocol != remote->rt_protocol) continue; vxlan_mdb_remote_del(vxlan, mdb_entry, remote); } } static void vxlan_mdb_flush(struct vxlan_dev *vxlan, const struct vxlan_mdb_flush_desc *desc) { struct vxlan_mdb_entry *mdb_entry; struct hlist_node *tmp; /* The removal of an entry cannot trigger the removal of another entry * since entries are always added to the head of the list. */ hlist_for_each_entry_safe(mdb_entry, tmp, &vxlan->mdb_list, mdb_node) { if (desc->src_vni && desc->src_vni != mdb_entry->key.vni) continue; vxlan_mdb_remotes_flush(vxlan, mdb_entry, desc); /* Entry will only be removed if its remotes list is empty. */ vxlan_mdb_entry_put(vxlan, mdb_entry); } } int vxlan_mdb_del_bulk(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_mdb_flush_desc desc = {}; int err; ASSERT_RTNL(); err = vxlan_mdb_flush_desc_init(vxlan, &desc, tb, extack); if (err) return err; vxlan_mdb_flush(vxlan, &desc); return 0; } static const struct nla_policy vxlan_mdbe_attrs_get_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), [MDBE_ATTR_SRC_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range), }; static int vxlan_mdb_get_parse(struct net_device *dev, struct nlattr *tb[], struct vxlan_mdb_entry_key *group, struct netlink_ext_ack *extack) { struct br_mdb_entry *entry = nla_data(tb[MDBA_GET_ENTRY]); struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1]; struct vxlan_dev *vxlan = netdev_priv(dev); int err; memset(group, 0, sizeof(*group)); group->vni = vxlan->default_dst.remote_vni; if (!tb[MDBA_GET_ENTRY_ATTRS]) { vxlan_mdb_group_set(group, entry, NULL); return 0; } err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX, tb[MDBA_GET_ENTRY_ATTRS], vxlan_mdbe_attrs_get_pol, extack); if (err) return err; if (mdbe_attrs[MDBE_ATTR_SOURCE] && !vxlan_mdb_is_valid_source(mdbe_attrs[MDBE_ATTR_SOURCE], entry->addr.proto, extack)) return -EINVAL; vxlan_mdb_group_set(group, entry, mdbe_attrs[MDBE_ATTR_SOURCE]); if (mdbe_attrs[MDBE_ATTR_SRC_VNI]) group->vni = cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_SRC_VNI])); return 0; } static struct sk_buff * vxlan_mdb_get_reply_alloc(const struct vxlan_dev *vxlan, const struct vxlan_mdb_entry *mdb_entry) { struct vxlan_mdb_remote *remote; size_t nlmsg_size; nlmsg_size = NLMSG_ALIGN(sizeof(struct br_port_msg)) + /* MDBA_MDB */ nla_total_size(0) + /* MDBA_MDB_ENTRY */ nla_total_size(0); list_for_each_entry(remote, &mdb_entry->remotes, list) nlmsg_size += vxlan_mdb_nlmsg_remote_size(vxlan, mdb_entry, remote); return nlmsg_new(nlmsg_size, GFP_KERNEL); } static int vxlan_mdb_get_reply_fill(const struct vxlan_dev *vxlan, struct sk_buff *skb, const struct vxlan_mdb_entry *mdb_entry, u32 portid, u32 seq) { struct nlattr *mdb_nest, *mdb_entry_nest; struct vxlan_mdb_remote *remote; struct br_port_msg *bpm; struct nlmsghdr *nlh; int err; nlh = nlmsg_put(skb, portid, seq, RTM_NEWMDB, sizeof(*bpm), 0); if (!nlh) return -EMSGSIZE; bpm = nlmsg_data(nlh); memset(bpm, 0, sizeof(*bpm)); bpm->family = AF_BRIDGE; bpm->ifindex = vxlan->dev->ifindex; mdb_nest = nla_nest_start_noflag(skb, MDBA_MDB); if (!mdb_nest) { err = -EMSGSIZE; goto cancel; } mdb_entry_nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY); if (!mdb_entry_nest) { err = -EMSGSIZE; goto cancel; } list_for_each_entry(remote, &mdb_entry->remotes, list) { err = vxlan_mdb_entry_info_fill(vxlan, skb, mdb_entry, remote); if (err) goto cancel; } nla_nest_end(skb, mdb_entry_nest); nla_nest_end(skb, mdb_nest); nlmsg_end(skb, nlh); return 0; cancel: nlmsg_cancel(skb, nlh); return err; } int vxlan_mdb_get(struct net_device *dev, struct nlattr *tb[], u32 portid, u32 seq, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_mdb_entry *mdb_entry; struct vxlan_mdb_entry_key group; struct sk_buff *skb; int err; ASSERT_RTNL(); err = vxlan_mdb_get_parse(dev, tb, &group, extack); if (err) return err; mdb_entry = vxlan_mdb_entry_lookup(vxlan, &group); if (!mdb_entry) { NL_SET_ERR_MSG_MOD(extack, "MDB entry not found"); return -ENOENT; } skb = vxlan_mdb_get_reply_alloc(vxlan, mdb_entry); if (!skb) return -ENOMEM; err = vxlan_mdb_get_reply_fill(vxlan, skb, mdb_entry, portid, seq); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed to fill MDB get reply"); goto free; } return rtnl_unicast(skb, dev_net(dev), portid); free: kfree_skb(skb); return err; } struct vxlan_mdb_entry *vxlan_mdb_entry_skb_get(struct vxlan_dev *vxlan, struct sk_buff *skb, __be32 src_vni) { struct vxlan_mdb_entry *mdb_entry; struct vxlan_mdb_entry_key group; if (!is_multicast_ether_addr(eth_hdr(skb)->h_dest) || is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) return NULL; /* When not in collect metadata mode, 'src_vni' is zero, but MDB * entries are stored with the VNI of the VXLAN device. */ if (!(vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA)) src_vni = vxlan->default_dst.remote_vni; memset(&group, 0, sizeof(group)); group.vni = src_vni; switch (skb->protocol) { case htons(ETH_P_IP): if (!pskb_may_pull(skb, sizeof(struct iphdr))) return NULL; group.dst.sa.sa_family = AF_INET; group.dst.sin.sin_addr.s_addr = ip_hdr(skb)->daddr; group.src.sa.sa_family = AF_INET; group.src.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) return NULL; group.dst.sa.sa_family = AF_INET6; group.dst.sin6.sin6_addr = ipv6_hdr(skb)->daddr; group.src.sa.sa_family = AF_INET6; group.src.sin6.sin6_addr = ipv6_hdr(skb)->saddr; break; #endif default: return NULL; } mdb_entry = vxlan_mdb_entry_lookup(vxlan, &group); if (mdb_entry) return mdb_entry; memset(&group.src, 0, sizeof(group.src)); mdb_entry = vxlan_mdb_entry_lookup(vxlan, &group); if (mdb_entry) return mdb_entry; /* No (S, G) or (*, G) found. Look up the all-zeros entry, but only if * the destination IP address is not link-local multicast since we want * to transmit such traffic together with broadcast and unknown unicast * traffic. */ switch (skb->protocol) { case htons(ETH_P_IP): if (ipv4_is_local_multicast(group.dst.sin.sin_addr.s_addr)) return NULL; group.dst.sin.sin_addr.s_addr = 0; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): if (ipv6_addr_type(&group.dst.sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL) return NULL; memset(&group.dst.sin6.sin6_addr, 0, sizeof(group.dst.sin6.sin6_addr)); break; #endif default: return NULL; } return vxlan_mdb_entry_lookup(vxlan, &group); } netdev_tx_t vxlan_mdb_xmit(struct vxlan_dev *vxlan, const struct vxlan_mdb_entry *mdb_entry, struct sk_buff *skb) { struct vxlan_mdb_remote *remote, *fremote = NULL; __be32 src_vni = mdb_entry->key.vni; list_for_each_entry_rcu(remote, &mdb_entry->remotes, list) { struct sk_buff *skb1; if ((vxlan_mdb_is_star_g(&mdb_entry->key) && READ_ONCE(remote->filter_mode) == MCAST_INCLUDE) || (READ_ONCE(remote->flags) & VXLAN_MDB_REMOTE_F_BLOCKED)) continue; if (!fremote) { fremote = remote; continue; } skb1 = skb_clone(skb, GFP_ATOMIC); if (skb1) vxlan_xmit_one(skb1, vxlan->dev, src_vni, rcu_dereference(remote->rd), false); } if (fremote) vxlan_xmit_one(skb, vxlan->dev, src_vni, rcu_dereference(fremote->rd), false); else kfree_skb_reason(skb, SKB_DROP_REASON_VXLAN_NO_REMOTE); return NETDEV_TX_OK; } static void vxlan_mdb_check_empty(void *ptr, void *arg) { WARN_ON_ONCE(1); } int vxlan_mdb_init(struct vxlan_dev *vxlan) { int err; err = rhashtable_init(&vxlan->mdb_tbl, &vxlan_mdb_rht_params); if (err) return err; INIT_HLIST_HEAD(&vxlan->mdb_list); return 0; } void vxlan_mdb_fini(struct vxlan_dev *vxlan) { struct vxlan_mdb_flush_desc desc = {}; vxlan_mdb_flush(vxlan, &desc); WARN_ON_ONCE(vxlan->cfg.flags & VXLAN_F_MDB); rhashtable_free_and_destroy(&vxlan->mdb_tbl, vxlan_mdb_check_empty, NULL); } |
| 11 11 11 11 11 11 11 11 6 6 6 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/net/sunrpc/stats.c * * procfs-based user access to generic RPC statistics. The stats files * reside in /proc/net/rpc. * * The read routines assume that the buffer passed in is just big enough. * If you implement an RPC service that has its own stats routine which * appends the generic RPC stats, make sure you don't exceed the PAGE_SIZE * limit. * * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> */ #include <linux/module.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/metrics.h> #include <linux/rcupdate.h> #include <trace/events/sunrpc.h> #include "netns.h" #define RPCDBG_FACILITY RPCDBG_MISC /* * Get RPC client stats */ static int rpc_proc_show(struct seq_file *seq, void *v) { const struct rpc_stat *statp = seq->private; const struct rpc_program *prog = statp->program; unsigned int i, j; seq_printf(seq, "net %u %u %u %u\n", statp->netcnt, statp->netudpcnt, statp->nettcpcnt, statp->nettcpconn); seq_printf(seq, "rpc %u %u %u\n", statp->rpccnt, statp->rpcretrans, statp->rpcauthrefresh); for (i = 0; i < prog->nrvers; i++) { const struct rpc_version *vers = prog->version[i]; if (!vers) continue; seq_printf(seq, "proc%u %u", vers->number, vers->nrprocs); for (j = 0; j < vers->nrprocs; j++) seq_printf(seq, " %u", vers->counts[j]); seq_putc(seq, '\n'); } return 0; } static int rpc_proc_open(struct inode *inode, struct file *file) { return single_open(file, rpc_proc_show, pde_data(inode)); } static const struct proc_ops rpc_proc_ops = { .proc_open = rpc_proc_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = single_release, }; /* * Get RPC server stats */ void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) { const struct svc_program *prog = statp->program; const struct svc_version *vers; unsigned int i, j, k; unsigned long count; seq_printf(seq, "net %u %u %u %u\n", statp->netcnt, statp->netudpcnt, statp->nettcpcnt, statp->nettcpconn); seq_printf(seq, "rpc %u %u %u %u %u\n", statp->rpccnt, statp->rpcbadfmt+statp->rpcbadauth+statp->rpcbadclnt, statp->rpcbadfmt, statp->rpcbadauth, statp->rpcbadclnt); for (i = 0; i < prog->pg_nvers; i++) { vers = prog->pg_vers[i]; if (!vers) continue; seq_printf(seq, "proc%d %u", i, vers->vs_nproc); for (j = 0; j < vers->vs_nproc; j++) { count = 0; for_each_possible_cpu(k) count += per_cpu(vers->vs_count[j], k); seq_printf(seq, " %lu", count); } seq_putc(seq, '\n'); } } EXPORT_SYMBOL_GPL(svc_seq_show); /** * rpc_alloc_iostats - allocate an rpc_iostats structure * @clnt: RPC program, version, and xprt * */ struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt) { struct rpc_iostats *stats; int i; stats = kcalloc(clnt->cl_maxproc, sizeof(*stats), GFP_KERNEL); if (stats) { for (i = 0; i < clnt->cl_maxproc; i++) spin_lock_init(&stats[i].om_lock); } return stats; } EXPORT_SYMBOL_GPL(rpc_alloc_iostats); /** * rpc_free_iostats - release an rpc_iostats structure * @stats: doomed rpc_iostats structure * */ void rpc_free_iostats(struct rpc_iostats *stats) { kfree(stats); } EXPORT_SYMBOL_GPL(rpc_free_iostats); /** * rpc_count_iostats_metrics - tally up per-task stats * @task: completed rpc_task * @op_metrics: stat structure for OP that will accumulate stats from @task */ void rpc_count_iostats_metrics(const struct rpc_task *task, struct rpc_iostats *op_metrics) { struct rpc_rqst *req = task->tk_rqstp; ktime_t backlog, execute, now; if (!op_metrics || !req) return; now = ktime_get(); spin_lock(&op_metrics->om_lock); op_metrics->om_ops++; /* kernel API: om_ops must never become larger than om_ntrans */ op_metrics->om_ntrans += max(req->rq_ntrans, 1); op_metrics->om_timeouts += task->tk_timeouts; op_metrics->om_bytes_sent += req->rq_xmit_bytes_sent; op_metrics->om_bytes_recv += req->rq_reply_bytes_recvd; backlog = 0; if (ktime_to_ns(req->rq_xtime)) { backlog = ktime_sub(req->rq_xtime, task->tk_start); op_metrics->om_queue = ktime_add(op_metrics->om_queue, backlog); } op_metrics->om_rtt = ktime_add(op_metrics->om_rtt, req->rq_rtt); execute = ktime_sub(now, task->tk_start); op_metrics->om_execute = ktime_add(op_metrics->om_execute, execute); if (task->tk_status < 0) op_metrics->om_error_status++; spin_unlock(&op_metrics->om_lock); trace_rpc_stats_latency(req->rq_task, backlog, req->rq_rtt, execute); } EXPORT_SYMBOL_GPL(rpc_count_iostats_metrics); /** * rpc_count_iostats - tally up per-task stats * @task: completed rpc_task * @stats: array of stat structures * * Uses the statidx from @task */ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) { rpc_count_iostats_metrics(task, &stats[task->tk_msg.rpc_proc->p_statidx]); } EXPORT_SYMBOL_GPL(rpc_count_iostats); static void _print_name(struct seq_file *seq, unsigned int op, const struct rpc_procinfo *procs) { if (procs[op].p_name) seq_printf(seq, "\t%12s: ", procs[op].p_name); else if (op == 0) seq_printf(seq, "\t NULL: "); else seq_printf(seq, "\t%12u: ", op); } static void _add_rpc_iostats(struct rpc_iostats *a, struct rpc_iostats *b) { a->om_ops += b->om_ops; a->om_ntrans += b->om_ntrans; a->om_timeouts += b->om_timeouts; a->om_bytes_sent += b->om_bytes_sent; a->om_bytes_recv += b->om_bytes_recv; a->om_queue = ktime_add(a->om_queue, b->om_queue); a->om_rtt = ktime_add(a->om_rtt, b->om_rtt); a->om_execute = ktime_add(a->om_execute, b->om_execute); a->om_error_status += b->om_error_status; } static void _print_rpc_iostats(struct seq_file *seq, struct rpc_iostats *stats, int op, const struct rpc_procinfo *procs) { _print_name(seq, op, procs); seq_printf(seq, "%lu %lu %lu %llu %llu %llu %llu %llu %lu\n", stats->om_ops, stats->om_ntrans, stats->om_timeouts, stats->om_bytes_sent, stats->om_bytes_recv, ktime_to_ms(stats->om_queue), ktime_to_ms(stats->om_rtt), ktime_to_ms(stats->om_execute), stats->om_error_status); } static int do_print_stats(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *seqv) { struct seq_file *seq = seqv; xprt->ops->print_stats(xprt, seq); return 0; } void rpc_clnt_show_stats(struct seq_file *seq, struct rpc_clnt *clnt) { unsigned int op, maxproc = clnt->cl_maxproc; if (!clnt->cl_metrics) return; seq_printf(seq, "\tRPC iostats version: %s ", RPC_IOSTATS_VERS); seq_printf(seq, "p/v: %u/%u (%s)\n", clnt->cl_prog, clnt->cl_vers, clnt->cl_program->name); rpc_clnt_iterate_for_each_xprt(clnt, do_print_stats, seq); seq_printf(seq, "\tper-op statistics\n"); for (op = 0; op < maxproc; op++) { struct rpc_iostats stats = {}; struct rpc_clnt *next = clnt; do { _add_rpc_iostats(&stats, &next->cl_metrics[op]); if (next == next->cl_parent) break; next = next->cl_parent; } while (next); _print_rpc_iostats(seq, &stats, op, clnt->cl_procinfo); } } EXPORT_SYMBOL_GPL(rpc_clnt_show_stats); /* * Register/unregister RPC proc files */ static inline struct proc_dir_entry * do_register(struct net *net, const char *name, void *data, const struct proc_ops *proc_ops) { struct sunrpc_net *sn; dprintk("RPC: registering /proc/net/rpc/%s\n", name); sn = net_generic(net, sunrpc_net_id); return proc_create_data(name, 0, sn->proc_net_rpc, proc_ops, data); } struct proc_dir_entry * rpc_proc_register(struct net *net, struct rpc_stat *statp) { return do_register(net, statp->program->name, statp, &rpc_proc_ops); } EXPORT_SYMBOL_GPL(rpc_proc_register); void rpc_proc_unregister(struct net *net, const char *name) { struct sunrpc_net *sn; sn = net_generic(net, sunrpc_net_id); remove_proc_entry(name, sn->proc_net_rpc); } EXPORT_SYMBOL_GPL(rpc_proc_unregister); struct proc_dir_entry * svc_proc_register(struct net *net, struct svc_stat *statp, const struct proc_ops *proc_ops) { return do_register(net, statp->program->pg_name, net, proc_ops); } EXPORT_SYMBOL_GPL(svc_proc_register); void svc_proc_unregister(struct net *net, const char *name) { struct sunrpc_net *sn; sn = net_generic(net, sunrpc_net_id); remove_proc_entry(name, sn->proc_net_rpc); } EXPORT_SYMBOL_GPL(svc_proc_unregister); int rpc_proc_init(struct net *net) { struct sunrpc_net *sn; dprintk("RPC: registering /proc/net/rpc\n"); sn = net_generic(net, sunrpc_net_id); sn->proc_net_rpc = proc_mkdir("rpc", net->proc_net); if (sn->proc_net_rpc == NULL) return -ENOMEM; return 0; } void rpc_proc_exit(struct net *net) { dprintk("RPC: unregistering /proc/net/rpc\n"); remove_proc_entry("rpc", net->proc_net); } |
| 169 5 1 27 5 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * NET Generic infrastructure for INET connection oriented protocols. * * Definitions for inet_connection_sock * * Authors: Many people, see the TCP sources * * From code originally in TCP */ #ifndef _INET_CONNECTION_SOCK_H #define _INET_CONNECTION_SOCK_H #include <linux/compiler.h> #include <linux/string.h> #include <linux/timer.h> #include <linux/poll.h> #include <linux/kernel.h> #include <linux/sockptr.h> #include <net/inet_sock.h> #include <net/request_sock.h> /* Cancel timers, when they are not required. */ #undef INET_CSK_CLEAR_TIMERS struct inet_bind_bucket; struct inet_bind2_bucket; struct tcp_congestion_ops; /* * Pointers to address related TCP functions * (i.e. things that depend on the address family) */ struct inet_connection_sock_af_ops { int (*queue_xmit)(struct sock *sk, struct sk_buff *skb, struct flowi *fl); void (*send_check)(struct sock *sk, struct sk_buff *skb); int (*rebuild_header)(struct sock *sk); void (*sk_rx_dst_set)(struct sock *sk, const struct sk_buff *skb); int (*conn_request)(struct sock *sk, struct sk_buff *skb); struct sock *(*syn_recv_sock)(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req); u16 net_header_len; u16 sockaddr_len; int (*setsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); void (*addr2sockaddr)(struct sock *sk, struct sockaddr *); void (*mtu_reduced)(struct sock *sk); }; /** inet_connection_sock - INET connection oriented sock * * @icsk_accept_queue: FIFO of established children * @icsk_bind_hash: Bind node * @icsk_bind2_hash: Bind node in the bhash2 table * @icsk_timeout: Timeout * @icsk_retransmit_timer: Resend (no ack) * @icsk_rto: Retransmit timeout * @icsk_pmtu_cookie Last pmtu seen by socket * @icsk_ca_ops Pluggable congestion control hook * @icsk_af_ops Operations which are AF_INET{4,6} specific * @icsk_ulp_ops Pluggable ULP control hook * @icsk_ulp_data ULP private data * @icsk_clean_acked Clean acked data hook * @icsk_ca_state: Congestion control state * @icsk_retransmits: Number of unrecovered [RTO] timeouts * @icsk_pending: Scheduled timer event * @icsk_backoff: Backoff * @icsk_syn_retries: Number of allowed SYN (or equivalent) retries * @icsk_probes_out: unanswered 0 window probes * @icsk_ext_hdr_len: Network protocol overhead (IP/IPv6 options) * @icsk_ack: Delayed ACK control data * @icsk_mtup; MTU probing control data * @icsk_probes_tstamp: Probe timestamp (cleared by non-zero window ack) * @icsk_user_timeout: TCP_USER_TIMEOUT value */ struct inet_connection_sock { /* inet_sock has to be the first member! */ struct inet_sock icsk_inet; struct request_sock_queue icsk_accept_queue; struct inet_bind_bucket *icsk_bind_hash; struct inet_bind2_bucket *icsk_bind2_hash; unsigned long icsk_timeout; struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; __u32 icsk_rto; __u32 icsk_rto_min; __u32 icsk_delack_max; __u32 icsk_pmtu_cookie; const struct tcp_congestion_ops *icsk_ca_ops; const struct inet_connection_sock_af_ops *icsk_af_ops; const struct tcp_ulp_ops *icsk_ulp_ops; void __rcu *icsk_ulp_data; void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq); unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); __u8 icsk_ca_state:5, icsk_ca_initialized:1, icsk_ca_setsockopt:1, icsk_ca_dst_locked:1; __u8 icsk_retransmits; __u8 icsk_pending; __u8 icsk_backoff; __u8 icsk_syn_retries; __u8 icsk_probes_out; __u16 icsk_ext_hdr_len; struct { __u8 pending; /* ACK is pending */ __u8 quick; /* Scheduled number of quick acks */ __u8 pingpong; /* The session is interactive */ __u8 retry; /* Number of attempts */ #define ATO_BITS 8 __u32 ato:ATO_BITS, /* Predicted tick of soft clock */ lrcv_flowlabel:20, /* last received ipv6 flowlabel */ unused:4; unsigned long timeout; /* Currently scheduled timeout */ __u32 lrcvtime; /* timestamp of last received data packet */ __u16 last_seg_size; /* Size of last incoming segment */ __u16 rcv_mss; /* MSS used for delayed ACK decisions */ } icsk_ack; struct { /* Range of MTUs to search */ int search_high; int search_low; /* Information on the current probe. */ u32 probe_size:31, /* Is the MTUP feature enabled for this connection? */ enabled:1; u32 probe_timestamp; } icsk_mtup; u32 icsk_probes_tstamp; u32 icsk_user_timeout; u64 icsk_ca_priv[104 / sizeof(u64)]; #define ICSK_CA_PRIV_SIZE sizeof_field(struct inet_connection_sock, icsk_ca_priv) }; #define ICSK_TIME_RETRANS 1 /* Retransmit timer */ #define ICSK_TIME_DACK 2 /* Delayed ack timer */ #define ICSK_TIME_PROBE0 3 /* Zero window probe timer */ #define ICSK_TIME_LOSS_PROBE 5 /* Tail loss probe timer */ #define ICSK_TIME_REO_TIMEOUT 6 /* Reordering timer */ #define inet_csk(ptr) container_of_const(ptr, struct inet_connection_sock, icsk_inet.sk) static inline void *inet_csk_ca(const struct sock *sk) { return (void *)inet_csk(sk)->icsk_ca_priv; } struct sock *inet_csk_clone_lock(const struct sock *sk, const struct request_sock *req, const gfp_t priority); enum inet_csk_ack_state_t { ICSK_ACK_SCHED = 1, ICSK_ACK_TIMER = 2, ICSK_ACK_PUSHED = 4, ICSK_ACK_PUSHED2 = 8, ICSK_ACK_NOW = 16, /* Send the next ACK immediately (once) */ ICSK_ACK_NOMEM = 32, }; void inet_csk_init_xmit_timers(struct sock *sk, void (*retransmit_handler)(struct timer_list *), void (*delack_handler)(struct timer_list *), void (*keepalive_handler)(struct timer_list *)); void inet_csk_clear_xmit_timers(struct sock *sk); void inet_csk_clear_xmit_timers_sync(struct sock *sk); static inline void inet_csk_schedule_ack(struct sock *sk) { inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_SCHED; } static inline int inet_csk_ack_scheduled(const struct sock *sk) { return inet_csk(sk)->icsk_ack.pending & ICSK_ACK_SCHED; } static inline void inet_csk_delack_init(struct sock *sk) { memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack)); } void inet_csk_delete_keepalive_timer(struct sock *sk); void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout); static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what) { struct inet_connection_sock *icsk = inet_csk(sk); if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) { smp_store_release(&icsk->icsk_pending, 0); #ifdef INET_CSK_CLEAR_TIMERS sk_stop_timer(sk, &icsk->icsk_retransmit_timer); #endif } else if (what == ICSK_TIME_DACK) { smp_store_release(&icsk->icsk_ack.pending, 0); icsk->icsk_ack.retry = 0; #ifdef INET_CSK_CLEAR_TIMERS sk_stop_timer(sk, &icsk->icsk_delack_timer); #endif } else { pr_debug("inet_csk BUG: unknown timer value\n"); } } /* * Reset the retransmission timer */ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, unsigned long when, const unsigned long max_when) { struct inet_connection_sock *icsk = inet_csk(sk); if (when > max_when) { pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n", sk, what, when, (void *)_THIS_IP_); when = max_when; } if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 || what == ICSK_TIME_LOSS_PROBE || what == ICSK_TIME_REO_TIMEOUT) { smp_store_release(&icsk->icsk_pending, what); icsk->icsk_timeout = jiffies + when; sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout); } else if (what == ICSK_TIME_DACK) { smp_store_release(&icsk->icsk_ack.pending, icsk->icsk_ack.pending | ICSK_ACK_TIMER); icsk->icsk_ack.timeout = jiffies + when; sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout); } else { pr_debug("inet_csk BUG: unknown timer value\n"); } } static inline unsigned long inet_csk_rto_backoff(const struct inet_connection_sock *icsk, unsigned long max_when) { u64 when = (u64)icsk->icsk_rto << icsk->icsk_backoff; return (unsigned long)min_t(u64, when, max_when); } struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg); int inet_csk_get_port(struct sock *sk, unsigned short snum); struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, const struct request_sock *req); struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *newsk, const struct request_sock *req); struct sock *inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, struct sock *child); bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, struct request_sock *req, bool own_req); static inline void inet_csk_reqsk_queue_added(struct sock *sk) { reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue); } static inline int inet_csk_reqsk_queue_len(const struct sock *sk) { return reqsk_queue_len(&inet_csk(sk)->icsk_accept_queue); } static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) { return inet_csk_reqsk_queue_len(sk) > READ_ONCE(sk->sk_max_ack_backlog); } bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req); static inline unsigned long reqsk_timeout(struct request_sock *req, unsigned long max_timeout) { u64 timeout = (u64)req->timeout << req->num_timeout; return (unsigned long)min_t(u64, timeout, max_timeout); } static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk) { /* The below has to be done to allow calling inet_csk_destroy_sock */ sock_set_flag(sk, SOCK_DEAD); this_cpu_inc(*sk->sk_prot->orphan_count); } void inet_csk_destroy_sock(struct sock *sk); void inet_csk_prepare_forced_close(struct sock *sk); /* * LISTEN is a special case for poll.. */ static inline __poll_t inet_csk_listen_poll(const struct sock *sk) { return !reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue) ? (EPOLLIN | EPOLLRDNORM) : 0; } int inet_csk_listen_start(struct sock *sk); void inet_csk_listen_stop(struct sock *sk); void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr); /* update the fast reuse flag when adding a socket */ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, struct sock *sk); struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu); static inline void inet_csk_enter_pingpong_mode(struct sock *sk) { inet_csk(sk)->icsk_ack.pingpong = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pingpong_thresh); } static inline void inet_csk_exit_pingpong_mode(struct sock *sk) { inet_csk(sk)->icsk_ack.pingpong = 0; } static inline bool inet_csk_in_pingpong_mode(struct sock *sk) { return inet_csk(sk)->icsk_ack.pingpong >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pingpong_thresh); } static inline void inet_csk_inc_pingpong_cnt(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ack.pingpong < U8_MAX) icsk->icsk_ack.pingpong++; } static inline bool inet_csk_has_ulp(const struct sock *sk) { return inet_test_bit(IS_ICSK, sk) && !!inet_csk(sk)->icsk_ulp_ops; } static inline void inet_init_csk_locks(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); spin_lock_init(&icsk->icsk_accept_queue.rskq_lock); spin_lock_init(&icsk->icsk_accept_queue.fastopenq.lock); } #endif /* _INET_CONNECTION_SOCK_H */ |
| 137 138 112 20 95 3 131 1 6 1 1 1 2 139 135 133 131 136 2 139 139 139 3 5 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * XFRM compat layer * Author: Dmitry Safonov <dima@arista.com> * Based on code and translator idea by: Florian Westphal <fw@strlen.de> */ #include <linux/compat.h> #include <linux/nospec.h> #include <linux/xfrm.h> #include <net/xfrm.h> struct compat_xfrm_lifetime_cfg { compat_u64 soft_byte_limit, hard_byte_limit; compat_u64 soft_packet_limit, hard_packet_limit; compat_u64 soft_add_expires_seconds, hard_add_expires_seconds; compat_u64 soft_use_expires_seconds, hard_use_expires_seconds; }; /* same size on 32bit, but only 4 byte alignment required */ struct compat_xfrm_lifetime_cur { compat_u64 bytes, packets, add_time, use_time; }; /* same size on 32bit, but only 4 byte alignment required */ struct compat_xfrm_userpolicy_info { struct xfrm_selector sel; struct compat_xfrm_lifetime_cfg lft; struct compat_xfrm_lifetime_cur curlft; __u32 priority, index; u8 dir, action, flags, share; /* 4 bytes additional padding on 64bit */ }; struct compat_xfrm_usersa_info { struct xfrm_selector sel; struct xfrm_id id; xfrm_address_t saddr; struct compat_xfrm_lifetime_cfg lft; struct compat_xfrm_lifetime_cur curlft; struct xfrm_stats stats; __u32 seq, reqid; u16 family; u8 mode, replay_window, flags; /* 4 bytes additional padding on 64bit */ }; struct compat_xfrm_user_acquire { struct xfrm_id id; xfrm_address_t saddr; struct xfrm_selector sel; struct compat_xfrm_userpolicy_info policy; /* 4 bytes additional padding on 64bit */ __u32 aalgos, ealgos, calgos, seq; }; struct compat_xfrm_userspi_info { struct compat_xfrm_usersa_info info; /* 4 bytes additional padding on 64bit */ __u32 min, max; }; struct compat_xfrm_user_expire { struct compat_xfrm_usersa_info state; /* 8 bytes additional padding on 64bit */ u8 hard; }; struct compat_xfrm_user_polexpire { struct compat_xfrm_userpolicy_info pol; /* 8 bytes additional padding on 64bit */ u8 hard; }; #define XMSGSIZE(type) sizeof(struct type) static const int compat_msg_min[XFRM_NR_MSGTYPES] = { [XFRM_MSG_NEWSA - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info), [XFRM_MSG_DELSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), [XFRM_MSG_GETSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), [XFRM_MSG_NEWPOLICY - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info), [XFRM_MSG_DELPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), [XFRM_MSG_GETPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), [XFRM_MSG_ALLOCSPI - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userspi_info), [XFRM_MSG_ACQUIRE - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_acquire), [XFRM_MSG_EXPIRE - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_expire), [XFRM_MSG_UPDPOLICY - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info), [XFRM_MSG_UPDSA - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info), [XFRM_MSG_POLEXPIRE - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_polexpire), [XFRM_MSG_FLUSHSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush), [XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = 0, [XFRM_MSG_NEWAE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id), [XFRM_MSG_GETAE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id), [XFRM_MSG_REPORT - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_report), [XFRM_MSG_MIGRATE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id), [XFRM_MSG_NEWSADINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_GETSADINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_NEWSPDINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_GETSPDINFO - XFRM_MSG_BASE] = sizeof(u32), [XFRM_MSG_MAPPING - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_mapping) }; static const struct nla_policy compat_policy[XFRMA_MAX+1] = { [XFRMA_UNSPEC] = { .strict_start_type = XFRMA_SA_DIR }, [XFRMA_SA] = { .len = XMSGSIZE(compat_xfrm_usersa_info)}, [XFRMA_POLICY] = { .len = XMSGSIZE(compat_xfrm_userpolicy_info)}, [XFRMA_LASTUSED] = { .type = NLA_U64}, [XFRMA_ALG_AUTH_TRUNC] = { .len = sizeof(struct xfrm_algo_auth)}, [XFRMA_ALG_AEAD] = { .len = sizeof(struct xfrm_algo_aead) }, [XFRMA_ALG_AUTH] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ALG_CRYPT] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) }, [XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) }, [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_user_sec_ctx) }, [XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) }, [XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) }, [XFRMA_REPLAY_THRESH] = { .type = NLA_U32 }, [XFRMA_ETIMER_THRESH] = { .type = NLA_U32 }, [XFRMA_SRCADDR] = { .len = sizeof(xfrm_address_t) }, [XFRMA_COADDR] = { .len = sizeof(xfrm_address_t) }, [XFRMA_POLICY_TYPE] = { .len = sizeof(struct xfrm_userpolicy_type)}, [XFRMA_MIGRATE] = { .len = sizeof(struct xfrm_user_migrate) }, [XFRMA_KMADDRESS] = { .len = sizeof(struct xfrm_user_kmaddress) }, [XFRMA_MARK] = { .len = sizeof(struct xfrm_mark) }, [XFRMA_TFCPAD] = { .type = NLA_U32 }, [XFRMA_REPLAY_ESN_VAL] = { .len = sizeof(struct xfrm_replay_state_esn) }, [XFRMA_SA_EXTRA_FLAGS] = { .type = NLA_U32 }, [XFRMA_PROTO] = { .type = NLA_U8 }, [XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) }, [XFRMA_OFFLOAD_DEV] = { .len = sizeof(struct xfrm_user_offload) }, [XFRMA_SET_MARK] = { .type = NLA_U32 }, [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, [XFRMA_IF_ID] = { .type = NLA_U32 }, [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, [XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT), [XFRMA_NAT_KEEPALIVE_INTERVAL] = { .type = NLA_U32 }, [XFRMA_SA_PCPU] = { .type = NLA_U32 }, }; static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src, u16 type) { int payload = compat_msg_min[type]; int src_len = xfrm_msg_min[type]; struct nlmsghdr *nlh_dst; /* Compat messages are shorter or equal to native (+padding) */ if (WARN_ON_ONCE(src_len < payload)) return ERR_PTR(-EMSGSIZE); nlh_dst = nlmsg_put(skb, nlh_src->nlmsg_pid, nlh_src->nlmsg_seq, nlh_src->nlmsg_type, payload, nlh_src->nlmsg_flags); if (!nlh_dst) return ERR_PTR(-EMSGSIZE); memset(nlmsg_data(nlh_dst), 0, payload); switch (nlh_src->nlmsg_type) { /* Compat message has the same layout as native */ case XFRM_MSG_DELSA: case XFRM_MSG_DELPOLICY: case XFRM_MSG_FLUSHSA: case XFRM_MSG_FLUSHPOLICY: case XFRM_MSG_NEWAE: case XFRM_MSG_REPORT: case XFRM_MSG_MIGRATE: case XFRM_MSG_NEWSADINFO: case XFRM_MSG_NEWSPDINFO: case XFRM_MSG_MAPPING: WARN_ON_ONCE(src_len != payload); memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), src_len); break; /* 4 byte alignment for trailing u64 on native, but not on compat */ case XFRM_MSG_NEWSA: case XFRM_MSG_NEWPOLICY: case XFRM_MSG_UPDSA: case XFRM_MSG_UPDPOLICY: WARN_ON_ONCE(src_len != payload + 4); memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), payload); break; case XFRM_MSG_EXPIRE: { const struct xfrm_user_expire *src_ue = nlmsg_data(nlh_src); struct compat_xfrm_user_expire *dst_ue = nlmsg_data(nlh_dst); /* compat_xfrm_user_expire has 4-byte smaller state */ memcpy(dst_ue, src_ue, sizeof(dst_ue->state)); dst_ue->hard = src_ue->hard; break; } case XFRM_MSG_ACQUIRE: { const struct xfrm_user_acquire *src_ua = nlmsg_data(nlh_src); struct compat_xfrm_user_acquire *dst_ua = nlmsg_data(nlh_dst); memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos)); dst_ua->aalgos = src_ua->aalgos; dst_ua->ealgos = src_ua->ealgos; dst_ua->calgos = src_ua->calgos; dst_ua->seq = src_ua->seq; break; } case XFRM_MSG_POLEXPIRE: { const struct xfrm_user_polexpire *src_upe = nlmsg_data(nlh_src); struct compat_xfrm_user_polexpire *dst_upe = nlmsg_data(nlh_dst); /* compat_xfrm_user_polexpire has 4-byte smaller state */ memcpy(dst_upe, src_upe, sizeof(dst_upe->pol)); dst_upe->hard = src_upe->hard; break; } case XFRM_MSG_ALLOCSPI: { const struct xfrm_userspi_info *src_usi = nlmsg_data(nlh_src); struct compat_xfrm_userspi_info *dst_usi = nlmsg_data(nlh_dst); /* compat_xfrm_user_polexpire has 4-byte smaller state */ memcpy(dst_usi, src_usi, sizeof(src_usi->info)); dst_usi->min = src_usi->min; dst_usi->max = src_usi->max; break; } /* Not being sent by kernel */ case XFRM_MSG_GETSA: case XFRM_MSG_GETPOLICY: case XFRM_MSG_GETAE: case XFRM_MSG_GETSADINFO: case XFRM_MSG_GETSPDINFO: default: pr_warn_once("unsupported nlmsg_type %d\n", nlh_src->nlmsg_type); return ERR_PTR(-EOPNOTSUPP); } return nlh_dst; } static int xfrm_nla_cpy(struct sk_buff *dst, const struct nlattr *src, int len) { return nla_put(dst, src->nla_type, len, nla_data(src)); } static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) { switch (src->nla_type) { case XFRMA_PAD: /* Ignore */ return 0; case XFRMA_UNSPEC: case XFRMA_ALG_AUTH: case XFRMA_ALG_CRYPT: case XFRMA_ALG_COMP: case XFRMA_ENCAP: case XFRMA_TMPL: return xfrm_nla_cpy(dst, src, nla_len(src)); case XFRMA_SA: return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_usersa_info)); case XFRMA_POLICY: return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_userpolicy_info)); case XFRMA_SEC_CTX: return xfrm_nla_cpy(dst, src, nla_len(src)); case XFRMA_LTIME_VAL: return nla_put_64bit(dst, src->nla_type, nla_len(src), nla_data(src), XFRMA_PAD); case XFRMA_REPLAY_VAL: case XFRMA_REPLAY_THRESH: case XFRMA_ETIMER_THRESH: case XFRMA_SRCADDR: case XFRMA_COADDR: return xfrm_nla_cpy(dst, src, nla_len(src)); case XFRMA_LASTUSED: return nla_put_64bit(dst, src->nla_type, nla_len(src), nla_data(src), XFRMA_PAD); case XFRMA_POLICY_TYPE: case XFRMA_MIGRATE: case XFRMA_ALG_AEAD: case XFRMA_KMADDRESS: case XFRMA_ALG_AUTH_TRUNC: case XFRMA_MARK: case XFRMA_TFCPAD: case XFRMA_REPLAY_ESN_VAL: case XFRMA_SA_EXTRA_FLAGS: case XFRMA_PROTO: case XFRMA_ADDRESS_FILTER: case XFRMA_OFFLOAD_DEV: case XFRMA_SET_MARK: case XFRMA_SET_MARK_MASK: case XFRMA_IF_ID: case XFRMA_MTIMER_THRESH: case XFRMA_SA_DIR: case XFRMA_NAT_KEEPALIVE_INTERVAL: case XFRMA_SA_PCPU: return xfrm_nla_cpy(dst, src, nla_len(src)); default: BUILD_BUG_ON(XFRMA_MAX != XFRMA_SA_PCPU); pr_warn_once("unsupported nla_type %d\n", src->nla_type); return -EOPNOTSUPP; } } /* Take kernel-built (64bit layout) and create 32bit layout for userspace */ static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src) { u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE; const struct nlattr *nla, *attrs; struct nlmsghdr *nlh_dst; int len, remaining; nlh_dst = xfrm_nlmsg_put_compat(dst, nlh_src, type); if (IS_ERR(nlh_dst)) return PTR_ERR(nlh_dst); attrs = nlmsg_attrdata(nlh_src, xfrm_msg_min[type]); len = nlmsg_attrlen(nlh_src, xfrm_msg_min[type]); nla_for_each_attr(nla, attrs, len, remaining) { int err; switch (nlh_src->nlmsg_type) { case XFRM_MSG_NEWSPDINFO: err = xfrm_nla_cpy(dst, nla, nla_len(nla)); break; default: err = xfrm_xlate64_attr(dst, nla); break; } if (err) return err; } nlmsg_end(dst, nlh_dst); return 0; } static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src) { u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE; struct sk_buff *new = NULL; int err; if (type >= ARRAY_SIZE(xfrm_msg_min)) { pr_warn_once("unsupported nlmsg_type %d\n", nlh_src->nlmsg_type); return -EOPNOTSUPP; } if (skb_shinfo(skb)->frag_list == NULL) { new = alloc_skb(skb->len + skb_tailroom(skb), GFP_ATOMIC); if (!new) return -ENOMEM; skb_shinfo(skb)->frag_list = new; } err = xfrm_xlate64(skb_shinfo(skb)->frag_list, nlh_src); if (err) { if (new) { kfree_skb(new); skb_shinfo(skb)->frag_list = NULL; } return err; } return 0; } /* Calculates len of translated 64-bit message. */ static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src, struct nlattr *attrs[XFRMA_MAX + 1], int maxtype) { size_t len = nlmsg_len(src); switch (src->nlmsg_type) { case XFRM_MSG_NEWSA: case XFRM_MSG_NEWPOLICY: case XFRM_MSG_ALLOCSPI: case XFRM_MSG_ACQUIRE: case XFRM_MSG_UPDPOLICY: case XFRM_MSG_UPDSA: len += 4; break; case XFRM_MSG_EXPIRE: case XFRM_MSG_POLEXPIRE: len += 8; break; case XFRM_MSG_NEWSPDINFO: /* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */ return len; default: break; } /* Unexpected for anything, but XFRM_MSG_NEWSPDINFO, please * correct both 64=>32-bit and 32=>64-bit translators to copy * new attributes. */ if (WARN_ON_ONCE(maxtype)) return len; if (attrs[XFRMA_SA]) len += 4; if (attrs[XFRMA_POLICY]) len += 4; /* XXX: some attrs may need to be realigned * if !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */ return len; } static int xfrm_attr_cpy32(void *dst, size_t *pos, const struct nlattr *src, size_t size, int copy_len, int payload) { struct nlmsghdr *nlmsg = dst; struct nlattr *nla; /* xfrm_user_rcv_msg_compat() relies on fact that 32-bit messages * have the same len or shorted than 64-bit ones. * 32-bit translation that is bigger than 64-bit original is unexpected. */ if (WARN_ON_ONCE(copy_len > payload)) copy_len = payload; if (size - *pos < nla_attr_size(payload)) return -ENOBUFS; nla = dst + *pos; memcpy(nla, src, nla_attr_size(copy_len)); nla->nla_len = nla_attr_size(payload); *pos += nla_attr_size(copy_len); nlmsg->nlmsg_len += nla->nla_len; memset(dst + *pos, 0, payload - copy_len); *pos += payload - copy_len; return 0; } static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, size_t *pos, size_t size, struct netlink_ext_ack *extack) { int type = nla_type(nla); u16 pol_len32, pol_len64; int err; if (type > XFRMA_MAX) { BUILD_BUG_ON(XFRMA_MAX != XFRMA_SA_PCPU); NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } type = array_index_nospec(type, XFRMA_MAX + 1); if (nla_len(nla) < compat_policy[type].len) { NL_SET_ERR_MSG(extack, "Attribute bad length"); return -EOPNOTSUPP; } pol_len32 = compat_policy[type].len; pol_len64 = xfrma_policy[type].len; /* XFRMA_SA and XFRMA_POLICY - need to know how-to translate */ if (pol_len32 != pol_len64) { if (nla_len(nla) != compat_policy[type].len) { NL_SET_ERR_MSG(extack, "Attribute bad length"); return -EOPNOTSUPP; } err = xfrm_attr_cpy32(dst, pos, nla, size, pol_len32, pol_len64); if (err) return err; } return xfrm_attr_cpy32(dst, pos, nla, size, nla_len(nla), nla_len(nla)); } static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src, struct nlattr *attrs[XFRMA_MAX+1], size_t size, u8 type, int maxtype, struct netlink_ext_ack *extack) { size_t pos; int i; memcpy(dst, src, NLMSG_HDRLEN); dst->nlmsg_len = NLMSG_HDRLEN + xfrm_msg_min[type]; memset(nlmsg_data(dst), 0, xfrm_msg_min[type]); switch (src->nlmsg_type) { /* Compat message has the same layout as native */ case XFRM_MSG_DELSA: case XFRM_MSG_GETSA: case XFRM_MSG_DELPOLICY: case XFRM_MSG_GETPOLICY: case XFRM_MSG_FLUSHSA: case XFRM_MSG_FLUSHPOLICY: case XFRM_MSG_NEWAE: case XFRM_MSG_GETAE: case XFRM_MSG_REPORT: case XFRM_MSG_MIGRATE: case XFRM_MSG_NEWSADINFO: case XFRM_MSG_GETSADINFO: case XFRM_MSG_NEWSPDINFO: case XFRM_MSG_GETSPDINFO: case XFRM_MSG_MAPPING: memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]); break; /* 4 byte alignment for trailing u64 on native, but not on compat */ case XFRM_MSG_NEWSA: case XFRM_MSG_NEWPOLICY: case XFRM_MSG_UPDSA: case XFRM_MSG_UPDPOLICY: memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]); break; case XFRM_MSG_EXPIRE: { const struct compat_xfrm_user_expire *src_ue = nlmsg_data(src); struct xfrm_user_expire *dst_ue = nlmsg_data(dst); /* compat_xfrm_user_expire has 4-byte smaller state */ memcpy(dst_ue, src_ue, sizeof(src_ue->state)); dst_ue->hard = src_ue->hard; break; } case XFRM_MSG_ACQUIRE: { const struct compat_xfrm_user_acquire *src_ua = nlmsg_data(src); struct xfrm_user_acquire *dst_ua = nlmsg_data(dst); memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos)); dst_ua->aalgos = src_ua->aalgos; dst_ua->ealgos = src_ua->ealgos; dst_ua->calgos = src_ua->calgos; dst_ua->seq = src_ua->seq; break; } case XFRM_MSG_POLEXPIRE: { const struct compat_xfrm_user_polexpire *src_upe = nlmsg_data(src); struct xfrm_user_polexpire *dst_upe = nlmsg_data(dst); /* compat_xfrm_user_polexpire has 4-byte smaller state */ memcpy(dst_upe, src_upe, sizeof(src_upe->pol)); dst_upe->hard = src_upe->hard; break; } case XFRM_MSG_ALLOCSPI: { const struct compat_xfrm_userspi_info *src_usi = nlmsg_data(src); struct xfrm_userspi_info *dst_usi = nlmsg_data(dst); /* compat_xfrm_user_polexpire has 4-byte smaller state */ memcpy(dst_usi, src_usi, sizeof(src_usi->info)); dst_usi->min = src_usi->min; dst_usi->max = src_usi->max; break; } default: NL_SET_ERR_MSG(extack, "Unsupported message type"); return -EOPNOTSUPP; } pos = dst->nlmsg_len; if (maxtype) { /* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */ WARN_ON_ONCE(src->nlmsg_type != XFRM_MSG_NEWSPDINFO); for (i = 1; i <= maxtype; i++) { int err; if (!attrs[i]) continue; /* just copy - no need for translation */ err = xfrm_attr_cpy32(dst, &pos, attrs[i], size, nla_len(attrs[i]), nla_len(attrs[i])); if (err) return err; } return 0; } for (i = 1; i < XFRMA_MAX + 1; i++) { int err; if (i == XFRMA_PAD) continue; if (!attrs[i]) continue; err = xfrm_xlate32_attr(dst, attrs[i], &pos, size, extack); if (err) return err; } return 0; } static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { /* netlink_rcv_skb() checks if a message has full (struct nlmsghdr) */ u16 type = h32->nlmsg_type - XFRM_MSG_BASE; struct nlattr *attrs[XFRMA_MAX+1]; struct nlmsghdr *h64; size_t len; int err; BUILD_BUG_ON(ARRAY_SIZE(xfrm_msg_min) != ARRAY_SIZE(compat_msg_min)); if (type >= ARRAY_SIZE(xfrm_msg_min)) return ERR_PTR(-EINVAL); /* Don't call parse: the message might have only nlmsg header */ if ((h32->nlmsg_type == XFRM_MSG_GETSA || h32->nlmsg_type == XFRM_MSG_GETPOLICY) && (h32->nlmsg_flags & NLM_F_DUMP)) return NULL; err = nlmsg_parse_deprecated(h32, compat_msg_min[type], attrs, maxtype ? : XFRMA_MAX, policy ? : compat_policy, extack); if (err < 0) return ERR_PTR(err); len = xfrm_user_rcv_calculate_len64(h32, attrs, maxtype); /* The message doesn't need translation */ if (len == nlmsg_len(h32)) return NULL; len += NLMSG_HDRLEN; h64 = kvmalloc(len, GFP_KERNEL); if (!h64) return ERR_PTR(-ENOMEM); err = xfrm_xlate32(h64, h32, attrs, len, type, maxtype, extack); if (err < 0) { kvfree(h64); return ERR_PTR(err); } return h64; } static int xfrm_user_policy_compat(u8 **pdata32, int optlen) { struct compat_xfrm_userpolicy_info *p = (void *)*pdata32; u8 *src_templates, *dst_templates; u8 *data64; if (optlen < sizeof(*p)) return -EINVAL; data64 = kmalloc_track_caller(optlen + 4, GFP_USER | __GFP_NOWARN); if (!data64) return -ENOMEM; memcpy(data64, *pdata32, sizeof(*p)); memset(data64 + sizeof(*p), 0, 4); src_templates = *pdata32 + sizeof(*p); dst_templates = data64 + sizeof(*p) + 4; memcpy(dst_templates, src_templates, optlen - sizeof(*p)); kfree(*pdata32); *pdata32 = data64; return 0; } static struct xfrm_translator xfrm_translator = { .owner = THIS_MODULE, .alloc_compat = xfrm_alloc_compat, .rcv_msg_compat = xfrm_user_rcv_msg_compat, .xlate_user_policy_sockptr = xfrm_user_policy_compat, }; static int __init xfrm_compat_init(void) { return xfrm_register_translator(&xfrm_translator); } static void __exit xfrm_compat_exit(void) { xfrm_unregister_translator(&xfrm_translator); } module_init(xfrm_compat_init); module_exit(xfrm_compat_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Dmitry Safonov"); MODULE_DESCRIPTION("XFRM 32-bit compatibility layer"); |
| 4 4 4 4 4 4 3 4 3 4 4 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 | // SPDX-License-Identifier: GPL-2.0-only /* * spectrum management * * Copyright 2003, Jouni Malinen <jkmaline@cc.hut.fi> * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2005-2006, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2008, Intel Corporation * Copyright 2008, Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2018, 2020, 2022-2024 Intel Corporation */ #include <linux/ieee80211.h> #include <net/cfg80211.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "sta_info.h" #include "wme.h" static bool wbcs_elem_to_chandef(const struct ieee80211_wide_bw_chansw_ie *wbcs_elem, struct cfg80211_chan_def *chandef) { u8 ccfs0 = wbcs_elem->new_center_freq_seg0; u8 ccfs1 = wbcs_elem->new_center_freq_seg1; u32 cf0 = ieee80211_channel_to_frequency(ccfs0, chandef->chan->band); u32 cf1 = ieee80211_channel_to_frequency(ccfs1, chandef->chan->band); switch (wbcs_elem->new_channel_width) { case IEEE80211_VHT_CHANWIDTH_160MHZ: /* deprecated encoding */ chandef->width = NL80211_CHAN_WIDTH_160; chandef->center_freq1 = cf0; break; case IEEE80211_VHT_CHANWIDTH_80P80MHZ: /* deprecated encoding */ chandef->width = NL80211_CHAN_WIDTH_80P80; chandef->center_freq1 = cf0; chandef->center_freq2 = cf1; break; case IEEE80211_VHT_CHANWIDTH_80MHZ: chandef->width = NL80211_CHAN_WIDTH_80; chandef->center_freq1 = cf0; if (ccfs1) { u8 diff = abs(ccfs0 - ccfs1); if (diff == 8) { chandef->width = NL80211_CHAN_WIDTH_160; chandef->center_freq1 = cf1; } else if (diff > 8) { chandef->width = NL80211_CHAN_WIDTH_80P80; chandef->center_freq2 = cf1; } } break; case IEEE80211_VHT_CHANWIDTH_USE_HT: default: /* If the WBCS Element is present, new channel bandwidth is * at least 40 MHz. */ chandef->width = NL80211_CHAN_WIDTH_40; chandef->center_freq1 = cf0; break; } return cfg80211_chandef_valid(chandef); } static void validate_chandef_by_ht_vht_oper(struct ieee80211_sub_if_data *sdata, struct ieee80211_conn_settings *conn, u32 vht_cap_info, struct cfg80211_chan_def *chandef) { u32 control_freq, center_freq1, center_freq2; enum nl80211_chan_width chan_width; struct ieee80211_ht_operation ht_oper; struct ieee80211_vht_operation vht_oper; if (conn->mode < IEEE80211_CONN_MODE_HT || conn->bw_limit < IEEE80211_CONN_BW_LIMIT_40) { chandef->chan = NULL; return; } control_freq = chandef->chan->center_freq; center_freq1 = chandef->center_freq1; center_freq2 = chandef->center_freq2; chan_width = chandef->width; ht_oper.primary_chan = ieee80211_frequency_to_channel(control_freq); if (control_freq != center_freq1) ht_oper.ht_param = control_freq > center_freq1 ? IEEE80211_HT_PARAM_CHA_SEC_BELOW : IEEE80211_HT_PARAM_CHA_SEC_ABOVE; else ht_oper.ht_param = IEEE80211_HT_PARAM_CHA_SEC_NONE; ieee80211_chandef_ht_oper(&ht_oper, chandef); if (conn->mode < IEEE80211_CONN_MODE_VHT) return; vht_oper.center_freq_seg0_idx = ieee80211_frequency_to_channel(center_freq1); vht_oper.center_freq_seg1_idx = center_freq2 ? ieee80211_frequency_to_channel(center_freq2) : 0; switch (chan_width) { case NL80211_CHAN_WIDTH_320: WARN_ON(1); break; case NL80211_CHAN_WIDTH_160: vht_oper.chan_width = IEEE80211_VHT_CHANWIDTH_80MHZ; vht_oper.center_freq_seg1_idx = vht_oper.center_freq_seg0_idx; vht_oper.center_freq_seg0_idx += control_freq < center_freq1 ? -8 : 8; break; case NL80211_CHAN_WIDTH_80P80: vht_oper.chan_width = IEEE80211_VHT_CHANWIDTH_80MHZ; break; case NL80211_CHAN_WIDTH_80: vht_oper.chan_width = IEEE80211_VHT_CHANWIDTH_80MHZ; break; default: vht_oper.chan_width = IEEE80211_VHT_CHANWIDTH_USE_HT; break; } ht_oper.operation_mode = le16_encode_bits(vht_oper.center_freq_seg1_idx, IEEE80211_HT_OP_MODE_CCFS2_MASK); if (!ieee80211_chandef_vht_oper(&sdata->local->hw, vht_cap_info, &vht_oper, &ht_oper, chandef)) chandef->chan = NULL; } static void validate_chandef_by_6ghz_he_eht_oper(struct ieee80211_sub_if_data *sdata, struct ieee80211_conn_settings *conn, struct cfg80211_chan_def *chandef) { struct ieee80211_local *local = sdata->local; u32 control_freq, center_freq1, center_freq2; enum nl80211_chan_width chan_width; struct { struct ieee80211_he_operation _oper; struct ieee80211_he_6ghz_oper _6ghz_oper; } __packed he; struct { struct ieee80211_eht_operation _oper; struct ieee80211_eht_operation_info _oper_info; } __packed eht; const struct ieee80211_eht_operation *eht_oper; if (conn->mode < IEEE80211_CONN_MODE_HE) { chandef->chan = NULL; return; } control_freq = chandef->chan->center_freq; center_freq1 = chandef->center_freq1; center_freq2 = chandef->center_freq2; chan_width = chandef->width; he._oper.he_oper_params = le32_encode_bits(1, IEEE80211_HE_OPERATION_6GHZ_OP_INFO); he._6ghz_oper.primary = ieee80211_frequency_to_channel(control_freq); he._6ghz_oper.ccfs0 = ieee80211_frequency_to_channel(center_freq1); he._6ghz_oper.ccfs1 = center_freq2 ? ieee80211_frequency_to_channel(center_freq2) : 0; switch (chan_width) { case NL80211_CHAN_WIDTH_320: he._6ghz_oper.ccfs1 = he._6ghz_oper.ccfs0; he._6ghz_oper.ccfs0 += control_freq < center_freq1 ? -16 : 16; he._6ghz_oper.control = IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ; break; case NL80211_CHAN_WIDTH_160: he._6ghz_oper.ccfs1 = he._6ghz_oper.ccfs0; he._6ghz_oper.ccfs0 += control_freq < center_freq1 ? -8 : 8; fallthrough; case NL80211_CHAN_WIDTH_80P80: he._6ghz_oper.control = IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ; break; case NL80211_CHAN_WIDTH_80: he._6ghz_oper.control = IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ; break; case NL80211_CHAN_WIDTH_40: he._6ghz_oper.control = IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_40MHZ; break; default: he._6ghz_oper.control = IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_20MHZ; break; } if (conn->mode < IEEE80211_CONN_MODE_EHT) { eht_oper = NULL; } else { eht._oper.params = IEEE80211_EHT_OPER_INFO_PRESENT; eht._oper_info.control = he._6ghz_oper.control; eht._oper_info.ccfs0 = he._6ghz_oper.ccfs0; eht._oper_info.ccfs1 = he._6ghz_oper.ccfs1; eht_oper = &eht._oper; } if (!ieee80211_chandef_he_6ghz_oper(local, &he._oper, eht_oper, chandef)) chandef->chan = NULL; } int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems, enum nl80211_band current_band, u32 vht_cap_info, struct ieee80211_conn_settings *conn, u8 *bssid, bool unprot_action, struct ieee80211_csa_ie *csa_ie) { enum nl80211_band new_band = current_band; int new_freq; u8 new_chan_no = 0, new_op_class = 0; struct ieee80211_channel *new_chan; struct cfg80211_chan_def new_chandef = {}; const struct ieee80211_sec_chan_offs_ie *sec_chan_offs; const struct ieee80211_wide_bw_chansw_ie *wide_bw_chansw_ie; const struct ieee80211_bandwidth_indication *bwi; const struct ieee80211_ext_chansw_ie *ext_chansw_elem; int secondary_channel_offset = -1; memset(csa_ie, 0, sizeof(*csa_ie)); sec_chan_offs = elems->sec_chan_offs; wide_bw_chansw_ie = elems->wide_bw_chansw_ie; bwi = elems->bandwidth_indication; ext_chansw_elem = elems->ext_chansw_ie; if (conn->mode < IEEE80211_CONN_MODE_HT || conn->bw_limit < IEEE80211_CONN_BW_LIMIT_40) { sec_chan_offs = NULL; wide_bw_chansw_ie = NULL; } if (conn->mode < IEEE80211_CONN_MODE_VHT) wide_bw_chansw_ie = NULL; if (ext_chansw_elem) { new_op_class = ext_chansw_elem->new_operating_class; if (!ieee80211_operating_class_to_band(new_op_class, &new_band)) { new_op_class = 0; if (!unprot_action) sdata_info(sdata, "cannot understand ECSA IE operating class, %d, ignoring\n", ext_chansw_elem->new_operating_class); } else { new_chan_no = ext_chansw_elem->new_ch_num; csa_ie->count = ext_chansw_elem->count; csa_ie->mode = ext_chansw_elem->mode; } } if (!new_op_class && elems->ch_switch_ie) { new_chan_no = elems->ch_switch_ie->new_ch_num; csa_ie->count = elems->ch_switch_ie->count; csa_ie->mode = elems->ch_switch_ie->mode; } /* nothing here we understand */ if (!new_chan_no) return 1; /* Mesh Channel Switch Parameters Element */ if (elems->mesh_chansw_params_ie) { csa_ie->ttl = elems->mesh_chansw_params_ie->mesh_ttl; csa_ie->mode = elems->mesh_chansw_params_ie->mesh_flags; csa_ie->pre_value = le16_to_cpu( elems->mesh_chansw_params_ie->mesh_pre_value); if (elems->mesh_chansw_params_ie->mesh_flags & WLAN_EID_CHAN_SWITCH_PARAM_REASON) csa_ie->reason_code = le16_to_cpu( elems->mesh_chansw_params_ie->mesh_reason); } new_freq = ieee80211_channel_to_frequency(new_chan_no, new_band); new_chan = ieee80211_get_channel(sdata->local->hw.wiphy, new_freq); if (!new_chan || new_chan->flags & IEEE80211_CHAN_DISABLED) { if (!unprot_action) sdata_info(sdata, "BSS %pM switches to unsupported channel (%d MHz), disconnecting\n", bssid, new_freq); return -EINVAL; } if (sec_chan_offs) { secondary_channel_offset = sec_chan_offs->sec_chan_offs; } else if (conn->mode >= IEEE80211_CONN_MODE_HT) { /* If the secondary channel offset IE is not present, * we can't know what's the post-CSA offset, so the * best we can do is use 20MHz. */ secondary_channel_offset = IEEE80211_HT_PARAM_CHA_SEC_NONE; } switch (secondary_channel_offset) { default: /* secondary_channel_offset was present but is invalid */ case IEEE80211_HT_PARAM_CHA_SEC_NONE: cfg80211_chandef_create(&csa_ie->chanreq.oper, new_chan, NL80211_CHAN_HT20); break; case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: cfg80211_chandef_create(&csa_ie->chanreq.oper, new_chan, NL80211_CHAN_HT40PLUS); break; case IEEE80211_HT_PARAM_CHA_SEC_BELOW: cfg80211_chandef_create(&csa_ie->chanreq.oper, new_chan, NL80211_CHAN_HT40MINUS); break; case -1: cfg80211_chandef_create(&csa_ie->chanreq.oper, new_chan, NL80211_CHAN_NO_HT); /* keep width for 5/10 MHz channels */ switch (sdata->vif.bss_conf.chanreq.oper.width) { case NL80211_CHAN_WIDTH_5: case NL80211_CHAN_WIDTH_10: csa_ie->chanreq.oper.width = sdata->vif.bss_conf.chanreq.oper.width; break; default: break; } break; } /* capture the AP configuration */ csa_ie->chanreq.ap = csa_ie->chanreq.oper; /* parse one of the Elements to build a new chandef */ memset(&new_chandef, 0, sizeof(new_chandef)); new_chandef.chan = new_chan; if (bwi) { /* start with the CSA one */ new_chandef = csa_ie->chanreq.oper; /* and update the width accordingly */ ieee80211_chandef_eht_oper(&bwi->info, &new_chandef); if (bwi->params & IEEE80211_BW_IND_DIS_SUBCH_PRESENT) new_chandef.punctured = get_unaligned_le16(bwi->info.optional); } else if (!wide_bw_chansw_ie || !wbcs_elem_to_chandef(wide_bw_chansw_ie, &new_chandef)) { if (!ieee80211_operating_class_to_chandef(new_op_class, new_chan, &new_chandef)) new_chandef = csa_ie->chanreq.oper; } /* check if the new chandef fits the capabilities */ if (new_band == NL80211_BAND_6GHZ) validate_chandef_by_6ghz_he_eht_oper(sdata, conn, &new_chandef); else validate_chandef_by_ht_vht_oper(sdata, conn, vht_cap_info, &new_chandef); /* if data is there validate the bandwidth & use it */ if (new_chandef.chan) { /* capture the AP chandef before (potential) downgrading */ csa_ie->chanreq.ap = new_chandef; while (conn->bw_limit < ieee80211_min_bw_limit_from_chandef(&new_chandef)) ieee80211_chandef_downgrade(&new_chandef, NULL); if (!cfg80211_chandef_compatible(&new_chandef, &csa_ie->chanreq.oper)) { sdata_info(sdata, "BSS %pM: CSA has inconsistent channel data, disconnecting\n", bssid); return -EINVAL; } csa_ie->chanreq.oper = new_chandef; } if (elems->max_channel_switch_time) csa_ie->max_switch_time = (elems->max_channel_switch_time[0] << 0) | (elems->max_channel_switch_time[1] << 8) | (elems->max_channel_switch_time[2] << 16); return 0; } static void ieee80211_send_refuse_measurement_request(struct ieee80211_sub_if_data *sdata, struct ieee80211_msrment_ie *request_ie, const u8 *da, const u8 *bssid, u8 dialog_token) { struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ieee80211_mgmt *msr_report; skb = dev_alloc_skb(sizeof(*msr_report) + local->hw.extra_tx_headroom + sizeof(struct ieee80211_msrment_ie)); if (!skb) return; skb_reserve(skb, local->hw.extra_tx_headroom); msr_report = skb_put_zero(skb, 24); memcpy(msr_report->da, da, ETH_ALEN); memcpy(msr_report->sa, sdata->vif.addr, ETH_ALEN); memcpy(msr_report->bssid, bssid, ETH_ALEN); msr_report->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); skb_put(skb, 1 + sizeof(msr_report->u.action.u.measurement)); msr_report->u.action.category = WLAN_CATEGORY_SPECTRUM_MGMT; msr_report->u.action.u.measurement.action_code = WLAN_ACTION_SPCT_MSR_RPRT; msr_report->u.action.u.measurement.dialog_token = dialog_token; msr_report->u.action.u.measurement.element_id = WLAN_EID_MEASURE_REPORT; msr_report->u.action.u.measurement.length = sizeof(struct ieee80211_msrment_ie); memset(&msr_report->u.action.u.measurement.msr_elem, 0, sizeof(struct ieee80211_msrment_ie)); msr_report->u.action.u.measurement.msr_elem.token = request_ie->token; msr_report->u.action.u.measurement.msr_elem.mode |= IEEE80211_SPCT_MSR_RPRT_MODE_REFUSED; msr_report->u.action.u.measurement.msr_elem.type = request_ie->type; ieee80211_tx_skb(sdata, skb); } void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len) { /* * Ignoring measurement request is spec violation. * Mandatory measurements must be reported optional * measurements might be refused or reported incapable * For now just refuse * TODO: Answer basic measurement as unmeasured */ ieee80211_send_refuse_measurement_request(sdata, &mgmt->u.action.u.measurement.msr_elem, mgmt->sa, mgmt->bssid, mgmt->u.action.u.measurement.dialog_token); } |
| 25 13 13 8 8 7 12 20 15 8 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * sha1_base.h - core logic for SHA-1 implementations * * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org> */ #ifndef _CRYPTO_SHA1_BASE_H #define _CRYPTO_SHA1_BASE_H #include <crypto/internal/hash.h> #include <crypto/sha1.h> #include <linux/crypto.h> #include <linux/module.h> #include <linux/string.h> #include <linux/unaligned.h> typedef void (sha1_block_fn)(struct sha1_state *sst, u8 const *src, int blocks); static inline int sha1_base_init(struct shash_desc *desc) { struct sha1_state *sctx = shash_desc_ctx(desc); sctx->state[0] = SHA1_H0; sctx->state[1] = SHA1_H1; sctx->state[2] = SHA1_H2; sctx->state[3] = SHA1_H3; sctx->state[4] = SHA1_H4; sctx->count = 0; return 0; } static inline int sha1_base_do_update(struct shash_desc *desc, const u8 *data, unsigned int len, sha1_block_fn *block_fn) { struct sha1_state *sctx = shash_desc_ctx(desc); unsigned int partial = sctx->count % SHA1_BLOCK_SIZE; sctx->count += len; if (unlikely((partial + len) >= SHA1_BLOCK_SIZE)) { int blocks; if (partial) { int p = SHA1_BLOCK_SIZE - partial; memcpy(sctx->buffer + partial, data, p); data += p; len -= p; block_fn(sctx, sctx->buffer, 1); } blocks = len / SHA1_BLOCK_SIZE; len %= SHA1_BLOCK_SIZE; if (blocks) { block_fn(sctx, data, blocks); data += blocks * SHA1_BLOCK_SIZE; } partial = 0; } if (len) memcpy(sctx->buffer + partial, data, len); return 0; } static inline int sha1_base_do_finalize(struct shash_desc *desc, sha1_block_fn *block_fn) { const int bit_offset = SHA1_BLOCK_SIZE - sizeof(__be64); struct sha1_state *sctx = shash_desc_ctx(desc); __be64 *bits = (__be64 *)(sctx->buffer + bit_offset); unsigned int partial = sctx->count % SHA1_BLOCK_SIZE; sctx->buffer[partial++] = 0x80; if (partial > bit_offset) { memset(sctx->buffer + partial, 0x0, SHA1_BLOCK_SIZE - partial); partial = 0; block_fn(sctx, sctx->buffer, 1); } memset(sctx->buffer + partial, 0x0, bit_offset - partial); *bits = cpu_to_be64(sctx->count << 3); block_fn(sctx, sctx->buffer, 1); return 0; } static inline int sha1_base_finish(struct shash_desc *desc, u8 *out) { struct sha1_state *sctx = shash_desc_ctx(desc); __be32 *digest = (__be32 *)out; int i; for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++) put_unaligned_be32(sctx->state[i], digest++); memzero_explicit(sctx, sizeof(*sctx)); return 0; } #endif /* _CRYPTO_SHA1_BASE_H */ |
| 29 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_TEXT_PATCHING_H #define _ASM_X86_TEXT_PATCHING_H #include <linux/types.h> #include <linux/stddef.h> #include <asm/ptrace.h> /* * Currently, the max observed size in the kernel code is * JUMP_LABEL_NOP_SIZE/RELATIVEJUMP_SIZE, which are 5. * Raise it if needed. */ #define POKE_MAX_OPCODE_SIZE 5 extern void text_poke_early(void *addr, const void *opcode, size_t len); extern void apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len); /* * Clear and restore the kernel write-protection flag on the local CPU. * Allows the kernel to edit read-only pages. * Side-effect: any interrupt handler running between save and restore will have * the ability to write to read-only pages. * * Warning: * Code patching in the UP case is safe if NMIs and MCE handlers are stopped and * no thread can be preempted in the instructions being modified (no iret to an * invalid instruction possible) or if the instructions are changed from a * consistent state to another consistent state atomically. * On the local CPU you need to be protected against NMI or MCE handlers seeing * an inconsistent instruction while you patch. */ extern void *text_poke(void *addr, const void *opcode, size_t len); extern void text_poke_sync(void); extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len); extern void *text_poke_copy(void *addr, const void *opcode, size_t len); #define text_poke_copy text_poke_copy extern void *text_poke_copy_locked(void *addr, const void *opcode, size_t len, bool core_ok); extern void *text_poke_set(void *addr, int c, size_t len); extern int poke_int3_handler(struct pt_regs *regs); extern void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate); extern void text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate); extern void text_poke_finish(void); #define INT3_INSN_SIZE 1 #define INT3_INSN_OPCODE 0xCC #define RET_INSN_SIZE 1 #define RET_INSN_OPCODE 0xC3 #define CALL_INSN_SIZE 5 #define CALL_INSN_OPCODE 0xE8 #define JMP32_INSN_SIZE 5 #define JMP32_INSN_OPCODE 0xE9 #define JMP8_INSN_SIZE 2 #define JMP8_INSN_OPCODE 0xEB #define DISP32_SIZE 4 static __always_inline int text_opcode_size(u8 opcode) { int size = 0; #define __CASE(insn) \ case insn##_INSN_OPCODE: size = insn##_INSN_SIZE; break switch(opcode) { __CASE(INT3); __CASE(RET); __CASE(CALL); __CASE(JMP32); __CASE(JMP8); } #undef __CASE return size; } union text_poke_insn { u8 text[POKE_MAX_OPCODE_SIZE]; struct { u8 opcode; s32 disp; } __attribute__((packed)); }; static __always_inline void __text_gen_insn(void *buf, u8 opcode, const void *addr, const void *dest, int size) { union text_poke_insn *insn = buf; BUG_ON(size < text_opcode_size(opcode)); /* * Hide the addresses to avoid the compiler folding in constants when * referencing code, these can mess up annotations like * ANNOTATE_NOENDBR. */ OPTIMIZER_HIDE_VAR(insn); OPTIMIZER_HIDE_VAR(addr); OPTIMIZER_HIDE_VAR(dest); insn->opcode = opcode; if (size > 1) { insn->disp = (long)dest - (long)(addr + size); if (size == 2) { /* * Ensure that for JMP8 the displacement * actually fits the signed byte. */ BUG_ON((insn->disp >> 31) != (insn->disp >> 7)); } } } static __always_inline void *text_gen_insn(u8 opcode, const void *addr, const void *dest) { static union text_poke_insn insn; /* per instance */ __text_gen_insn(&insn, opcode, addr, dest, text_opcode_size(opcode)); return &insn.text; } extern int after_bootmem; extern __ro_after_init struct mm_struct *poking_mm; extern __ro_after_init unsigned long poking_addr; #ifndef CONFIG_UML_X86 static __always_inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip) { regs->ip = ip; } static __always_inline void int3_emulate_push(struct pt_regs *regs, unsigned long val) { /* * The int3 handler in entry_64.S adds a gap between the * stack where the break point happened, and the saving of * pt_regs. We can extend the original stack because of * this gap. See the idtentry macro's create_gap option. * * Similarly entry_32.S will have a gap on the stack for (any) hardware * exception and pt_regs; see FIXUP_FRAME. */ regs->sp -= sizeof(unsigned long); *(unsigned long *)regs->sp = val; } static __always_inline unsigned long int3_emulate_pop(struct pt_regs *regs) { unsigned long val = *(unsigned long *)regs->sp; regs->sp += sizeof(unsigned long); return val; } static __always_inline void int3_emulate_call(struct pt_regs *regs, unsigned long func) { int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + CALL_INSN_SIZE); int3_emulate_jmp(regs, func); } static __always_inline void int3_emulate_ret(struct pt_regs *regs) { unsigned long ip = int3_emulate_pop(regs); int3_emulate_jmp(regs, ip); } static __always_inline void int3_emulate_jcc(struct pt_regs *regs, u8 cc, unsigned long ip, unsigned long disp) { static const unsigned long jcc_mask[6] = { [0] = X86_EFLAGS_OF, [1] = X86_EFLAGS_CF, [2] = X86_EFLAGS_ZF, [3] = X86_EFLAGS_CF | X86_EFLAGS_ZF, [4] = X86_EFLAGS_SF, [5] = X86_EFLAGS_PF, }; bool invert = cc & 1; bool match; if (cc < 0xc) { match = regs->flags & jcc_mask[cc >> 1]; } else { match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^ ((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT); if (cc >= 0xe) match = match || (regs->flags & X86_EFLAGS_ZF); } if ((match && !invert) || (!match && invert)) ip += disp; int3_emulate_jmp(regs, ip); } #endif /* !CONFIG_UML_X86 */ #endif /* _ASM_X86_TEXT_PATCHING_H */ |
| 77 77 84 83 2 81 85 76 77 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/errno.h> #include <linux/unistd.h> #include <linux/uaccess.h> #include <linux/syscalls.h> #include <asm/ucontext.h> #include <asm/fpu/signal.h> #include <asm/sighandling.h> #include <asm/syscall.h> #include <asm/sigframe.h> #include <asm/signal.h> /* * If regs->ss will cause an IRET fault, change it. Otherwise leave it * alone. Using this generally makes no sense unless * user_64bit_mode(regs) would return true. */ static void force_valid_ss(struct pt_regs *regs) { u32 ar; asm volatile ("lar %[old_ss], %[ar]\n\t" "jz 1f\n\t" /* If invalid: */ "xorl %[ar], %[ar]\n\t" /* set ar = 0 */ "1:" : [ar] "=r" (ar) : [old_ss] "rm" ((u16)regs->ss)); /* * For a valid 64-bit user context, we need DPL 3, type * read-write data or read-write exp-down data, and S and P * set. We can't use VERW because VERW doesn't check the * P bit. */ ar &= AR_DPL_MASK | AR_S | AR_P | AR_TYPE_MASK; if (ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA) && ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA_EXPDOWN)) regs->ss = __USER_DS; } static bool restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *usc, unsigned long uc_flags) { struct sigcontext sc; /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; if (copy_from_user(&sc, usc, offsetof(struct sigcontext, reserved1))) return false; regs->bx = sc.bx; regs->cx = sc.cx; regs->dx = sc.dx; regs->si = sc.si; regs->di = sc.di; regs->bp = sc.bp; regs->ax = sc.ax; regs->sp = sc.sp; regs->ip = sc.ip; regs->r8 = sc.r8; regs->r9 = sc.r9; regs->r10 = sc.r10; regs->r11 = sc.r11; regs->r12 = sc.r12; regs->r13 = sc.r13; regs->r14 = sc.r14; regs->r15 = sc.r15; /* Get CS/SS and force CPL3 */ regs->cs = sc.cs | 0x03; regs->ss = sc.ss | 0x03; regs->flags = (regs->flags & ~FIX_EFLAGS) | (sc.flags & FIX_EFLAGS); /* disable syscall checks */ regs->orig_ax = -1; /* * Fix up SS if needed for the benefit of old DOSEMU and * CRIU. */ if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && user_64bit_mode(regs))) force_valid_ss(regs); return fpu__restore_sig((void __user *)sc.fpstate, 0); } static __always_inline int __unsafe_setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, struct pt_regs *regs, unsigned long mask) { unsafe_put_user(regs->di, &sc->di, Efault); unsafe_put_user(regs->si, &sc->si, Efault); unsafe_put_user(regs->bp, &sc->bp, Efault); unsafe_put_user(regs->sp, &sc->sp, Efault); unsafe_put_user(regs->bx, &sc->bx, Efault); unsafe_put_user(regs->dx, &sc->dx, Efault); unsafe_put_user(regs->cx, &sc->cx, Efault); unsafe_put_user(regs->ax, &sc->ax, Efault); unsafe_put_user(regs->r8, &sc->r8, Efault); unsafe_put_user(regs->r9, &sc->r9, Efault); unsafe_put_user(regs->r10, &sc->r10, Efault); unsafe_put_user(regs->r11, &sc->r11, Efault); unsafe_put_user(regs->r12, &sc->r12, Efault); unsafe_put_user(regs->r13, &sc->r13, Efault); unsafe_put_user(regs->r14, &sc->r14, Efault); unsafe_put_user(regs->r15, &sc->r15, Efault); unsafe_put_user(current->thread.trap_nr, &sc->trapno, Efault); unsafe_put_user(current->thread.error_code, &sc->err, Efault); unsafe_put_user(regs->ip, &sc->ip, Efault); unsafe_put_user(regs->flags, &sc->flags, Efault); unsafe_put_user(regs->cs, &sc->cs, Efault); unsafe_put_user(0, &sc->gs, Efault); unsafe_put_user(0, &sc->fs, Efault); unsafe_put_user(regs->ss, &sc->ss, Efault); unsafe_put_user(fpstate, (unsigned long __user *)&sc->fpstate, Efault); /* non-iBCS2 extensions.. */ unsafe_put_user(mask, &sc->oldmask, Efault); unsafe_put_user(current->thread.cr2, &sc->cr2, Efault); return 0; Efault: return -EFAULT; } #define unsafe_put_sigcontext(sc, fp, regs, set, label) \ do { \ if (__unsafe_setup_sigcontext(sc, fp, regs, set->sig[0])) \ goto label; \ } while(0); #define unsafe_put_sigmask(set, frame, label) \ unsafe_put_user(*(__u64 *)(set), \ (__u64 __user *)&(frame)->uc.uc_sigmask, \ label) static unsigned long frame_uc_flags(struct pt_regs *regs) { unsigned long flags; if (boot_cpu_has(X86_FEATURE_XSAVE)) flags = UC_FP_XSTATE | UC_SIGCONTEXT_SS; else flags = UC_SIGCONTEXT_SS; if (likely(user_64bit_mode(regs))) flags |= UC_STRICT_RESTORE_SS; return flags; } int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) { sigset_t *set = sigmask_to_save(); struct rt_sigframe __user *frame; void __user *fp = NULL; unsigned long uc_flags; /* x86-64 should always use SA_RESTORER. */ if (!(ksig->ka.sa.sa_flags & SA_RESTORER)) return -EFAULT; frame = get_sigframe(ksig, regs, sizeof(struct rt_sigframe), &fp); uc_flags = frame_uc_flags(regs); if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; /* Create the ucontext. */ unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault); unsafe_put_user(0, &frame->uc.uc_link, Efault); unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); /* Set up to return from userspace. If provided, use a stub already in userspace. */ unsafe_put_user(ksig->ka.sa.sa_restorer, &frame->pretcode, Efault); unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); unsafe_put_sigmask(set, frame, Efault); user_access_end(); if (ksig->ka.sa.sa_flags & SA_SIGINFO) { if (copy_siginfo_to_user(&frame->info, &ksig->info)) return -EFAULT; } if (setup_signal_shadow_stack(ksig)) return -EFAULT; /* Set up registers for signal handler */ regs->di = ksig->sig; /* In case the signal handler was declared without prototypes */ regs->ax = 0; /* This also works for non SA_SIGINFO handlers because they expect the next argument after the signal number on the stack. */ regs->si = (unsigned long)&frame->info; regs->dx = (unsigned long)&frame->uc; regs->ip = (unsigned long) ksig->ka.sa.sa_handler; regs->sp = (unsigned long)frame; /* * Set up the CS and SS registers to run signal handlers in * 64-bit mode, even if the handler happens to be interrupting * 32-bit or 16-bit code. * * SS is subtle. In 64-bit mode, we don't need any particular * SS descriptor, but we do need SS to be valid. It's possible * that the old SS is entirely bogus -- this can happen if the * signal we're trying to deliver is #GP or #SS caused by a bad * SS value. We also have a compatibility issue here: DOSEMU * relies on the contents of the SS register indicating the * SS value at the time of the signal, even though that code in * DOSEMU predates sigreturn's ability to restore SS. (DOSEMU * avoids relying on sigreturn to restore SS; instead it uses * a trampoline.) So we do our best: if the old SS was valid, * we keep it. Otherwise we replace it. */ regs->cs = __USER_CS; if (unlikely(regs->ss != __USER_DS)) force_valid_ss(regs); return 0; Efault: user_access_end(); return -EFAULT; } /* * Do a signal return; undo the signal stack. */ SYSCALL_DEFINE0(rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe __user *frame; sigset_t set; unsigned long uc_flags; frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long)); if (!access_ok(frame, sizeof(*frame))) goto badframe; if (__get_user(*(__u64 *)&set, (__u64 __user *)&frame->uc.uc_sigmask)) goto badframe; if (__get_user(uc_flags, &frame->uc.uc_flags)) goto badframe; set_current_blocked(&set); if (restore_altstack(&frame->uc.uc_stack)) goto badframe; if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) goto badframe; if (restore_signal_shadow_stack()) goto badframe; return regs->ax; badframe: signal_fault(regs, frame, "rt_sigreturn"); return 0; } #ifdef CONFIG_X86_X32_ABI static int x32_copy_siginfo_to_user(struct compat_siginfo __user *to, const struct kernel_siginfo *from) { struct compat_siginfo new; copy_siginfo_to_external32(&new, from); if (from->si_signo == SIGCHLD) { new._sifields._sigchld_x32._utime = from->si_utime; new._sifields._sigchld_x32._stime = from->si_stime; } if (copy_to_user(to, &new, sizeof(struct compat_siginfo))) return -EFAULT; return 0; } int copy_siginfo_to_user32(struct compat_siginfo __user *to, const struct kernel_siginfo *from) { if (in_x32_syscall()) return x32_copy_siginfo_to_user(to, from); return __copy_siginfo_to_user32(to, from); } int x32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) { compat_sigset_t *set = (compat_sigset_t *) sigmask_to_save(); struct rt_sigframe_x32 __user *frame; unsigned long uc_flags; void __user *restorer; void __user *fp = NULL; if (!(ksig->ka.sa.sa_flags & SA_RESTORER)) return -EFAULT; frame = get_sigframe(ksig, regs, sizeof(*frame), &fp); uc_flags = frame_uc_flags(regs); if (setup_signal_shadow_stack(ksig)) return -EFAULT; if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; /* Create the ucontext. */ unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault); unsafe_put_user(0, &frame->uc.uc_link, Efault); unsafe_compat_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); unsafe_put_user(0, &frame->uc.uc__pad0, Efault); restorer = ksig->ka.sa.sa_restorer; unsafe_put_user(restorer, (unsigned long __user *)&frame->pretcode, Efault); unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); unsafe_put_sigmask(set, frame, Efault); user_access_end(); if (ksig->ka.sa.sa_flags & SA_SIGINFO) { if (x32_copy_siginfo_to_user(&frame->info, &ksig->info)) return -EFAULT; } /* Set up registers for signal handler */ regs->sp = (unsigned long) frame; regs->ip = (unsigned long) ksig->ka.sa.sa_handler; /* We use the x32 calling convention here... */ regs->di = ksig->sig; regs->si = (unsigned long) &frame->info; regs->dx = (unsigned long) &frame->uc; loadsegment(ds, __USER_DS); loadsegment(es, __USER_DS); regs->cs = __USER_CS; regs->ss = __USER_DS; return 0; Efault: user_access_end(); return -EFAULT; } COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe_x32 __user *frame; sigset_t set; unsigned long uc_flags; frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8); if (!access_ok(frame, sizeof(*frame))) goto badframe; if (__get_user(set.sig[0], (__u64 __user *)&frame->uc.uc_sigmask)) goto badframe; if (__get_user(uc_flags, &frame->uc.uc_flags)) goto badframe; set_current_blocked(&set); if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) goto badframe; if (restore_signal_shadow_stack()) goto badframe; if (compat_restore_altstack(&frame->uc.uc_stack)) goto badframe; return regs->ax; badframe: signal_fault(regs, frame, "x32 rt_sigreturn"); return 0; } #endif /* CONFIG_X86_X32_ABI */ #ifdef CONFIG_COMPAT void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact) { if (!act) return; if (in_ia32_syscall()) act->sa.sa_flags |= SA_IA32_ABI; if (in_x32_syscall()) act->sa.sa_flags |= SA_X32_ABI; } #endif /* CONFIG_COMPAT */ /* * If adding a new si_code, there is probably new data in * the siginfo. Make sure folks bumping the si_code * limits also have to look at this code. Make sure any * new fields are handled in copy_siginfo_to_user32()! */ static_assert(NSIGILL == 11); static_assert(NSIGFPE == 15); static_assert(NSIGSEGV == 10); static_assert(NSIGBUS == 5); static_assert(NSIGTRAP == 6); static_assert(NSIGCHLD == 6); static_assert(NSIGSYS == 2); /* This is part of the ABI and can never change in size: */ static_assert(sizeof(siginfo_t) == 128); /* This is a part of the ABI and can never change in alignment */ static_assert(__alignof__(siginfo_t) == 8); /* * The offsets of all the (unioned) si_fields are fixed * in the ABI, of course. Make sure none of them ever * move and are always at the beginning: */ static_assert(offsetof(siginfo_t, si_signo) == 0); static_assert(offsetof(siginfo_t, si_errno) == 4); static_assert(offsetof(siginfo_t, si_code) == 8); /* * Ensure that the size of each si_field never changes. * If it does, it is a sign that the * copy_siginfo_to_user32() code below needs to updated * along with the size in the CHECK_SI_SIZE(). * * We repeat this check for both the generic and compat * siginfos. * * Note: it is OK for these to grow as long as the whole * structure stays within the padding size (checked * above). */ #define CHECK_SI_OFFSET(name) \ static_assert(offsetof(siginfo_t, _sifields) == \ offsetof(siginfo_t, _sifields.name)) #define CHECK_SI_SIZE(name, size) \ static_assert(sizeof_field(siginfo_t, _sifields.name) == size) CHECK_SI_OFFSET(_kill); CHECK_SI_SIZE (_kill, 2*sizeof(int)); static_assert(offsetof(siginfo_t, si_pid) == 0x10); static_assert(offsetof(siginfo_t, si_uid) == 0x14); CHECK_SI_OFFSET(_timer); CHECK_SI_SIZE (_timer, 6*sizeof(int)); static_assert(offsetof(siginfo_t, si_tid) == 0x10); static_assert(offsetof(siginfo_t, si_overrun) == 0x14); static_assert(offsetof(siginfo_t, si_value) == 0x18); CHECK_SI_OFFSET(_rt); CHECK_SI_SIZE (_rt, 4*sizeof(int)); static_assert(offsetof(siginfo_t, si_pid) == 0x10); static_assert(offsetof(siginfo_t, si_uid) == 0x14); static_assert(offsetof(siginfo_t, si_value) == 0x18); CHECK_SI_OFFSET(_sigchld); CHECK_SI_SIZE (_sigchld, 8*sizeof(int)); static_assert(offsetof(siginfo_t, si_pid) == 0x10); static_assert(offsetof(siginfo_t, si_uid) == 0x14); static_assert(offsetof(siginfo_t, si_status) == 0x18); static_assert(offsetof(siginfo_t, si_utime) == 0x20); static_assert(offsetof(siginfo_t, si_stime) == 0x28); #ifdef CONFIG_X86_X32_ABI /* no _sigchld_x32 in the generic siginfo_t */ static_assert(sizeof_field(compat_siginfo_t, _sifields._sigchld_x32) == 7*sizeof(int)); static_assert(offsetof(compat_siginfo_t, _sifields) == offsetof(compat_siginfo_t, _sifields._sigchld_x32)); static_assert(offsetof(compat_siginfo_t, _sifields._sigchld_x32._utime) == 0x18); static_assert(offsetof(compat_siginfo_t, _sifields._sigchld_x32._stime) == 0x20); #endif CHECK_SI_OFFSET(_sigfault); CHECK_SI_SIZE (_sigfault, 8*sizeof(int)); static_assert(offsetof(siginfo_t, si_addr) == 0x10); static_assert(offsetof(siginfo_t, si_trapno) == 0x18); static_assert(offsetof(siginfo_t, si_addr_lsb) == 0x18); static_assert(offsetof(siginfo_t, si_lower) == 0x20); static_assert(offsetof(siginfo_t, si_upper) == 0x28); static_assert(offsetof(siginfo_t, si_pkey) == 0x20); static_assert(offsetof(siginfo_t, si_perf_data) == 0x18); static_assert(offsetof(siginfo_t, si_perf_type) == 0x20); static_assert(offsetof(siginfo_t, si_perf_flags) == 0x24); CHECK_SI_OFFSET(_sigpoll); CHECK_SI_SIZE (_sigpoll, 4*sizeof(int)); static_assert(offsetof(siginfo_t, si_band) == 0x10); static_assert(offsetof(siginfo_t, si_fd) == 0x18); CHECK_SI_OFFSET(_sigsys); CHECK_SI_SIZE (_sigsys, 4*sizeof(int)); static_assert(offsetof(siginfo_t, si_call_addr) == 0x10); static_assert(offsetof(siginfo_t, si_syscall) == 0x18); static_assert(offsetof(siginfo_t, si_arch) == 0x1C); /* any new si_fields should be added here */ |
| 7 24 29 22 19 23 8 19 26 24 6 29 28 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * sha512_base.h - core logic for SHA-512 implementations * * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org> */ #ifndef _CRYPTO_SHA512_BASE_H #define _CRYPTO_SHA512_BASE_H #include <crypto/internal/hash.h> #include <crypto/sha2.h> #include <linux/crypto.h> #include <linux/module.h> #include <linux/string.h> #include <linux/unaligned.h> typedef void (sha512_block_fn)(struct sha512_state *sst, u8 const *src, int blocks); static inline int sha384_base_init(struct shash_desc *desc) { struct sha512_state *sctx = shash_desc_ctx(desc); sctx->state[0] = SHA384_H0; sctx->state[1] = SHA384_H1; sctx->state[2] = SHA384_H2; sctx->state[3] = SHA384_H3; sctx->state[4] = SHA384_H4; sctx->state[5] = SHA384_H5; sctx->state[6] = SHA384_H6; sctx->state[7] = SHA384_H7; sctx->count[0] = sctx->count[1] = 0; return 0; } static inline int sha512_base_init(struct shash_desc *desc) { struct sha512_state *sctx = shash_desc_ctx(desc); sctx->state[0] = SHA512_H0; sctx->state[1] = SHA512_H1; sctx->state[2] = SHA512_H2; sctx->state[3] = SHA512_H3; sctx->state[4] = SHA512_H4; sctx->state[5] = SHA512_H5; sctx->state[6] = SHA512_H6; sctx->state[7] = SHA512_H7; sctx->count[0] = sctx->count[1] = 0; return 0; } static inline int sha512_base_do_update(struct shash_desc *desc, const u8 *data, unsigned int len, sha512_block_fn *block_fn) { struct sha512_state *sctx = shash_desc_ctx(desc); unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE; sctx->count[0] += len; if (sctx->count[0] < len) sctx->count[1]++; if (unlikely((partial + len) >= SHA512_BLOCK_SIZE)) { int blocks; if (partial) { int p = SHA512_BLOCK_SIZE - partial; memcpy(sctx->buf + partial, data, p); data += p; len -= p; block_fn(sctx, sctx->buf, 1); } blocks = len / SHA512_BLOCK_SIZE; len %= SHA512_BLOCK_SIZE; if (blocks) { block_fn(sctx, data, blocks); data += blocks * SHA512_BLOCK_SIZE; } partial = 0; } if (len) memcpy(sctx->buf + partial, data, len); return 0; } static inline int sha512_base_do_finalize(struct shash_desc *desc, sha512_block_fn *block_fn) { const int bit_offset = SHA512_BLOCK_SIZE - sizeof(__be64[2]); struct sha512_state *sctx = shash_desc_ctx(desc); __be64 *bits = (__be64 *)(sctx->buf + bit_offset); unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE; sctx->buf[partial++] = 0x80; if (partial > bit_offset) { memset(sctx->buf + partial, 0x0, SHA512_BLOCK_SIZE - partial); partial = 0; block_fn(sctx, sctx->buf, 1); } memset(sctx->buf + partial, 0x0, bit_offset - partial); bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61); bits[1] = cpu_to_be64(sctx->count[0] << 3); block_fn(sctx, sctx->buf, 1); return 0; } static inline int sha512_base_finish(struct shash_desc *desc, u8 *out) { unsigned int digest_size = crypto_shash_digestsize(desc->tfm); struct sha512_state *sctx = shash_desc_ctx(desc); __be64 *digest = (__be64 *)out; int i; for (i = 0; digest_size > 0; i++, digest_size -= sizeof(__be64)) put_unaligned_be64(sctx->state[i], digest++); memzero_explicit(sctx, sizeof(*sctx)); return 0; } #endif /* _CRYPTO_SHA512_BASE_H */ |
| 1 1 79 1 3 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/ns_common.h> #include <linux/fs_pin.h> struct mnt_namespace { struct ns_common ns; struct mount * root; struct rb_root mounts; /* Protected by namespace_sem */ struct user_namespace *user_ns; struct ucounts *ucounts; u64 seq; /* Sequence number to prevent loops */ wait_queue_head_t poll; u64 event; unsigned int nr_mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; struct rb_node mnt_ns_tree_node; /* node in the mnt_ns_tree */ refcount_t passive; /* number references not pinning @mounts */ } __randomize_layout; struct mnt_pcp { int mnt_count; int mnt_writers; }; struct mountpoint { struct hlist_node m_hash; struct dentry *m_dentry; struct hlist_head m_list; int m_count; }; struct mount { struct hlist_node mnt_hash; struct mount *mnt_parent; struct dentry *mnt_mountpoint; struct vfsmount mnt; union { struct rb_node mnt_node; /* node in the ns->mounts rbtree */ struct rcu_head mnt_rcu; struct llist_node mnt_llist; }; #ifdef CONFIG_SMP struct mnt_pcp __percpu *mnt_pcp; #else int mnt_count; int mnt_writers; #endif struct list_head mnt_mounts; /* list of children, anchored here */ struct list_head mnt_child; /* and going through their mnt_child */ struct list_head mnt_instance; /* mount instance on sb->s_mounts */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct list_head mnt_slave_list;/* list of slave mounts */ struct list_head mnt_slave; /* slave list entry */ struct mount *mnt_master; /* slave is on master->mnt_slave_list */ struct mnt_namespace *mnt_ns; /* containing namespace */ struct mountpoint *mnt_mp; /* where is it mounted */ union { struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ struct hlist_node mnt_umount; }; struct list_head mnt_umounting; /* list entry for umount propagation */ #ifdef CONFIG_FSNOTIFY struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; #endif int mnt_id; /* mount identifier, reused */ u64 mnt_id_unique; /* mount ID unique until reboot */ int mnt_group_id; /* peer group identifier */ int mnt_expiry_mark; /* true if marked for expiry */ struct hlist_head mnt_pins; struct hlist_head mnt_stuck_children; } __randomize_layout; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ static inline struct mount *real_mount(struct vfsmount *mnt) { return container_of(mnt, struct mount, mnt); } static inline int mnt_has_parent(struct mount *mnt) { return mnt != mnt->mnt_parent; } static inline int is_mounted(struct vfsmount *mnt) { /* neither detached nor internal? */ return !IS_ERR_OR_NULL(real_mount(mnt)->mnt_ns); } extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *); extern int __legitimize_mnt(struct vfsmount *, unsigned); static inline bool __path_is_mountpoint(const struct path *path) { struct mount *m = __lookup_mnt(path->mnt, path->dentry); return m && likely(!(m->mnt.mnt_flags & MNT_SYNC_UMOUNT)); } extern void __detach_mounts(struct dentry *dentry); static inline void detach_mounts(struct dentry *dentry) { if (!d_mountpoint(dentry)) return; __detach_mounts(dentry); } static inline void get_mnt_ns(struct mnt_namespace *ns) { refcount_inc(&ns->ns.count); } extern seqlock_t mount_lock; struct proc_mounts { struct mnt_namespace *ns; struct path root; int (*show)(struct seq_file *, struct vfsmount *); }; extern const struct seq_operations mounts_op; extern bool __is_local_mountpoint(struct dentry *dentry); static inline bool is_local_mountpoint(struct dentry *dentry) { if (!d_mountpoint(dentry)) return false; return __is_local_mountpoint(dentry); } static inline bool is_anon_ns(struct mnt_namespace *ns) { return ns->seq == 0; } static inline bool mnt_ns_attached(const struct mount *mnt) { return !RB_EMPTY_NODE(&mnt->mnt_node); } static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list) { WARN_ON(!mnt_ns_attached(mnt)); rb_erase(&mnt->mnt_node, &mnt->mnt_ns->mounts); RB_CLEAR_NODE(&mnt->mnt_node); list_add_tail(&mnt->mnt_list, dt_list); } bool has_locked_children(struct mount *mnt, struct dentry *dentry); struct mnt_namespace *__lookup_next_mnt_ns(struct mnt_namespace *mnt_ns, bool previous); static inline struct mnt_namespace *lookup_next_mnt_ns(struct mnt_namespace *mntns) { return __lookup_next_mnt_ns(mntns, false); } static inline struct mnt_namespace *lookup_prev_mnt_ns(struct mnt_namespace *mntns) { return __lookup_next_mnt_ns(mntns, true); } static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } |
| 8 6 8 8 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/syscalls.h> #include <linux/time_namespace.h> #include "futex.h" /* * Support for robust futexes: the kernel cleans up held futexes at * thread exit time. * * Implementation: user-space maintains a per-thread list of locks it * is holding. Upon do_exit(), the kernel carefully walks this list, * and marks all locks that are owned by this thread with the * FUTEX_OWNER_DIED bit, and wakes up a waiter (if any). The list is * always manipulated with the lock held, so the list is private and * per-thread. Userspace also maintains a per-thread 'list_op_pending' * field, to allow the kernel to clean up if the thread dies after * acquiring the lock, but just before it could have added itself to * the list. There can only be one such pending lock. */ /** * sys_set_robust_list() - Set the robust-futex list head of a task * @head: pointer to the list-head * @len: length of the list-head, as userspace expects */ SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, size_t, len) { /* * The kernel knows only one size for now: */ if (unlikely(len != sizeof(*head))) return -EINVAL; current->robust_list = head; return 0; } /** * sys_get_robust_list() - Get the robust-futex list head of a task * @pid: pid of the process [zero for current task] * @head_ptr: pointer to a list-head pointer, the kernel fills it in * @len_ptr: pointer to a length field, the kernel fills in the header size */ SYSCALL_DEFINE3(get_robust_list, int, pid, struct robust_list_head __user * __user *, head_ptr, size_t __user *, len_ptr) { struct robust_list_head __user *head; unsigned long ret; struct task_struct *p; rcu_read_lock(); ret = -ESRCH; if (!pid) p = current; else { p = find_task_by_vpid(pid); if (!p) goto err_unlock; } ret = -EPERM; if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) goto err_unlock; head = p->robust_list; rcu_read_unlock(); if (put_user(sizeof(*head), len_ptr)) return -EFAULT; return put_user(head, head_ptr); err_unlock: rcu_read_unlock(); return ret; } long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) { unsigned int flags = futex_to_flags(op); int cmd = op & FUTEX_CMD_MASK; if (flags & FLAGS_CLOCKRT) { if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI && cmd != FUTEX_LOCK_PI2) return -ENOSYS; } switch (cmd) { case FUTEX_WAIT: val3 = FUTEX_BITSET_MATCH_ANY; fallthrough; case FUTEX_WAIT_BITSET: return futex_wait(uaddr, flags, val, timeout, val3); case FUTEX_WAKE: val3 = FUTEX_BITSET_MATCH_ANY; fallthrough; case FUTEX_WAKE_BITSET: return futex_wake(uaddr, flags, val, val3); case FUTEX_REQUEUE: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, NULL, 0); case FUTEX_CMP_REQUEUE: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 0); case FUTEX_WAKE_OP: return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); case FUTEX_LOCK_PI: flags |= FLAGS_CLOCKRT; fallthrough; case FUTEX_LOCK_PI2: return futex_lock_pi(uaddr, flags, timeout, 0); case FUTEX_UNLOCK_PI: return futex_unlock_pi(uaddr, flags); case FUTEX_TRYLOCK_PI: return futex_lock_pi(uaddr, flags, NULL, 1); case FUTEX_WAIT_REQUEUE_PI: val3 = FUTEX_BITSET_MATCH_ANY; return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3, uaddr2); case FUTEX_CMP_REQUEUE_PI: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 1); } return -ENOSYS; } static __always_inline bool futex_cmd_has_timeout(u32 cmd) { switch (cmd) { case FUTEX_WAIT: case FUTEX_LOCK_PI: case FUTEX_LOCK_PI2: case FUTEX_WAIT_BITSET: case FUTEX_WAIT_REQUEUE_PI: return true; } return false; } static __always_inline int futex_init_timeout(u32 cmd, u32 op, struct timespec64 *ts, ktime_t *t) { if (!timespec64_valid(ts)) return -EINVAL; *t = timespec64_to_ktime(*ts); if (cmd == FUTEX_WAIT) *t = ktime_add_safe(ktime_get(), *t); else if (cmd != FUTEX_LOCK_PI && !(op & FUTEX_CLOCK_REALTIME)) *t = timens_ktime_to_host(CLOCK_MONOTONIC, *t); return 0; } SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, const struct __kernel_timespec __user *, utime, u32 __user *, uaddr2, u32, val3) { int ret, cmd = op & FUTEX_CMD_MASK; ktime_t t, *tp = NULL; struct timespec64 ts; if (utime && futex_cmd_has_timeout(cmd)) { if (unlikely(should_fail_futex(!(op & FUTEX_PRIVATE_FLAG)))) return -EFAULT; if (get_timespec64(&ts, utime)) return -EFAULT; ret = futex_init_timeout(cmd, op, &ts, &t); if (ret) return ret; tp = &t; } return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } /** * futex_parse_waitv - Parse a waitv array from userspace * @futexv: Kernel side list of waiters to be filled * @uwaitv: Userspace list to be parsed * @nr_futexes: Length of futexv * @wake: Wake to call when futex is woken * @wake_data: Data for the wake handler * * Return: Error code on failure, 0 on success */ int futex_parse_waitv(struct futex_vector *futexv, struct futex_waitv __user *uwaitv, unsigned int nr_futexes, futex_wake_fn *wake, void *wake_data) { struct futex_waitv aux; unsigned int i; for (i = 0; i < nr_futexes; i++) { unsigned int flags; if (copy_from_user(&aux, &uwaitv[i], sizeof(aux))) return -EFAULT; if ((aux.flags & ~FUTEX2_VALID_MASK) || aux.__reserved) return -EINVAL; flags = futex2_to_flags(aux.flags); if (!futex_flags_valid(flags)) return -EINVAL; if (!futex_validate_input(flags, aux.val)) return -EINVAL; futexv[i].w.flags = flags; futexv[i].w.val = aux.val; futexv[i].w.uaddr = aux.uaddr; futexv[i].q = futex_q_init; futexv[i].q.wake = wake; futexv[i].q.wake_data = wake_data; } return 0; } static int futex2_setup_timeout(struct __kernel_timespec __user *timeout, clockid_t clockid, struct hrtimer_sleeper *to) { int flag_clkid = 0, flag_init = 0; struct timespec64 ts; ktime_t time; int ret; if (!timeout) return 0; if (clockid == CLOCK_REALTIME) { flag_clkid = FLAGS_CLOCKRT; flag_init = FUTEX_CLOCK_REALTIME; } if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC) return -EINVAL; if (get_timespec64(&ts, timeout)) return -EFAULT; /* * Since there's no opcode for futex_waitv, use * FUTEX_WAIT_BITSET that uses absolute timeout as well */ ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time); if (ret) return ret; futex_setup_timer(&time, to, flag_clkid, 0); return 0; } static inline void futex2_destroy_timeout(struct hrtimer_sleeper *to) { hrtimer_cancel(&to->timer); destroy_hrtimer_on_stack(&to->timer); } /** * sys_futex_waitv - Wait on a list of futexes * @waiters: List of futexes to wait on * @nr_futexes: Length of futexv * @flags: Flag for timeout (monotonic/realtime) * @timeout: Optional absolute timeout. * @clockid: Clock to be used for the timeout, realtime or monotonic. * * Given an array of `struct futex_waitv`, wait on each uaddr. The thread wakes * if a futex_wake() is performed at any uaddr. The syscall returns immediately * if any waiter has *uaddr != val. *timeout is an optional timeout value for * the operation. Each waiter has individual flags. The `flags` argument for * the syscall should be used solely for specifying the timeout as realtime, if * needed. Flags for private futexes, sizes, etc. should be used on the * individual flags of each waiter. * * Returns the array index of one of the woken futexes. No further information * is provided: any number of other futexes may also have been woken by the * same event, and if more than one futex was woken, the retrned index may * refer to any one of them. (It is not necessaryily the futex with the * smallest index, nor the one most recently woken, nor...) */ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, unsigned int, nr_futexes, unsigned int, flags, struct __kernel_timespec __user *, timeout, clockid_t, clockid) { struct hrtimer_sleeper to; struct futex_vector *futexv; int ret; /* This syscall supports no flags for now */ if (flags) return -EINVAL; if (!nr_futexes || nr_futexes > FUTEX_WAITV_MAX || !waiters) return -EINVAL; if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to))) return ret; futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL); if (!futexv) { ret = -ENOMEM; goto destroy_timer; } ret = futex_parse_waitv(futexv, waiters, nr_futexes, futex_wake_mark, NULL); if (!ret) ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL); kfree(futexv); destroy_timer: if (timeout) futex2_destroy_timeout(&to); return ret; } /* * sys_futex_wake - Wake a number of futexes * @uaddr: Address of the futex(es) to wake * @mask: bitmask * @nr: Number of the futexes to wake * @flags: FUTEX2 flags * * Identical to the traditional FUTEX_WAKE_BITSET op, except it is part of the * futex2 family of calls. */ SYSCALL_DEFINE4(futex_wake, void __user *, uaddr, unsigned long, mask, int, nr, unsigned int, flags) { if (flags & ~FUTEX2_VALID_MASK) return -EINVAL; flags = futex2_to_flags(flags); if (!futex_flags_valid(flags)) return -EINVAL; if (!futex_validate_input(flags, mask)) return -EINVAL; return futex_wake(uaddr, FLAGS_STRICT | flags, nr, mask); } /* * sys_futex_wait - Wait on a futex * @uaddr: Address of the futex to wait on * @val: Value of @uaddr * @mask: bitmask * @flags: FUTEX2 flags * @timeout: Optional absolute timeout * @clockid: Clock to be used for the timeout, realtime or monotonic * * Identical to the traditional FUTEX_WAIT_BITSET op, except it is part of the * futex2 familiy of calls. */ SYSCALL_DEFINE6(futex_wait, void __user *, uaddr, unsigned long, val, unsigned long, mask, unsigned int, flags, struct __kernel_timespec __user *, timeout, clockid_t, clockid) { struct hrtimer_sleeper to; int ret; if (flags & ~FUTEX2_VALID_MASK) return -EINVAL; flags = futex2_to_flags(flags); if (!futex_flags_valid(flags)) return -EINVAL; if (!futex_validate_input(flags, val) || !futex_validate_input(flags, mask)) return -EINVAL; if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to))) return ret; ret = __futex_wait(uaddr, flags, val, timeout ? &to : NULL, mask); if (timeout) futex2_destroy_timeout(&to); return ret; } /* * sys_futex_requeue - Requeue a waiter from one futex to another * @waiters: array describing the source and destination futex * @flags: unused * @nr_wake: number of futexes to wake * @nr_requeue: number of futexes to requeue * * Identical to the traditional FUTEX_CMP_REQUEUE op, except it is part of the * futex2 family of calls. */ SYSCALL_DEFINE4(futex_requeue, struct futex_waitv __user *, waiters, unsigned int, flags, int, nr_wake, int, nr_requeue) { struct futex_vector futexes[2]; u32 cmpval; int ret; if (flags) return -EINVAL; if (!waiters) return -EINVAL; ret = futex_parse_waitv(futexes, waiters, 2, futex_wake_mark, NULL); if (ret) return ret; cmpval = futexes[0].w.val; return futex_requeue(u64_to_user_ptr(futexes[0].w.uaddr), futexes[0].w.flags, u64_to_user_ptr(futexes[1].w.uaddr), futexes[1].w.flags, nr_wake, nr_requeue, &cmpval, 0); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(set_robust_list, struct compat_robust_list_head __user *, head, compat_size_t, len) { if (unlikely(len != sizeof(*head))) return -EINVAL; current->compat_robust_list = head; return 0; } COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, compat_uptr_t __user *, head_ptr, compat_size_t __user *, len_ptr) { struct compat_robust_list_head __user *head; unsigned long ret; struct task_struct *p; rcu_read_lock(); ret = -ESRCH; if (!pid) p = current; else { p = find_task_by_vpid(pid); if (!p) goto err_unlock; } ret = -EPERM; if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) goto err_unlock; head = p->compat_robust_list; rcu_read_unlock(); if (put_user(sizeof(*head), len_ptr)) return -EFAULT; return put_user(ptr_to_compat(head), head_ptr); err_unlock: rcu_read_unlock(); return ret; } #endif /* CONFIG_COMPAT */ #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val, const struct old_timespec32 __user *, utime, u32 __user *, uaddr2, u32, val3) { int ret, cmd = op & FUTEX_CMD_MASK; ktime_t t, *tp = NULL; struct timespec64 ts; if (utime && futex_cmd_has_timeout(cmd)) { if (get_old_timespec32(&ts, utime)) return -EFAULT; ret = futex_init_timeout(cmd, op, &ts, &t); if (ret) return ret; tp = &t; } return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } #endif /* CONFIG_COMPAT_32BIT_TIME */ |
| 213 213 212 223 29 1 5 5 4 1 1 1 34 49 4 1 21 21 60 60 59 60 2 1 1 2 1 3 1 2 1 4 1 3 3 3 3 13 1 2 1 1 9 8 8 1 1 6 6 6 7 6 1 1 1 5 9 9 9 3 7 6 1 2 5 2 5 8 27 27 27 27 26 24 7 13 5 1 4 4 69 144 74 152 26 26 25 26 22 6 212 208 11 207 4 2 8 11 11 205 205 10 10 10 206 206 7 206 213 210 213 207 30 30 4 27 26 1 211 192 209 192 36 36 8 29 211 1 212 1 210 210 1 1 213 211 214 2 1 215 5 213 213 211 213 211 11 2 24 2 21 1 1 18 2 2 3 2 1 1 3 10 2 3 1 11 11 11 12 12 1 10 24 24 6 12 10 307 308 195 304 26 2 213 213 17 195 29 29 29 29 29 29 299 300 301 287 25 301 1 469 468 191 191 192 202 202 200 4 199 54 30 23 2 1 24 9 1 2 9 9 9 7 3 3 4 4 19 2 17 17 2 15 15 2 14 12 14 4 9 2 2 13 12 3 12 13 12 24 4 8 3 6 22 23 5 7 13 3 11 1 1 8 1 2 20 20 19 2 18 18 11 14 18 13 3 3 3 12 9 213 214 27 29 2 2 27 7 23 17 12 8 8 3 5 9 10 10 6 9 1 5 2 1 5 24 1 23 2 22 1 1 9 9 4 19 2 2 2 12 2 1 11 1 2 10 1 1 9 1 8 8 1 4 6 3 3 6 6 1 1 5 2 2 1 1 2 2 7 7 1 1 5 3 4 4 4 60 33 28 28 1 7 22 7 1 4 3 3 3 27 158 155 2 1 1 2 188 188 2 2 186 124 24 27 1 1 75 6 6 905 908 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: Internet Group Management Protocol [IGMP] * * This code implements the IGMP protocol as defined in RFC1112. There has * been a further revision of this protocol since which is now supported. * * If you have trouble with this module be careful what gcc you have used, * the older version didn't come out right using gcc 2.5.8, the newer one * seems to fall out with gcc 2.6.2. * * Authors: * Alan Cox <alan@lxorguk.ukuu.org.uk> * * Fixes: * * Alan Cox : Added lots of __inline__ to optimise * the memory usage of all the tiny little * functions. * Alan Cox : Dumped the header building experiment. * Alan Cox : Minor tweaks ready for multicast routing * and extended IGMP protocol. * Alan Cox : Removed a load of inline directives. Gcc 2.5.8 * writes utterly bogus code otherwise (sigh) * fixed IGMP loopback to behave in the manner * desired by mrouted, fixed the fact it has been * broken since 1.3.6 and cleaned up a few minor * points. * * Chih-Jen Chang : Tried to revise IGMP to Version 2 * Tsu-Sheng Tsao E-mail: chihjenc@scf.usc.edu and tsusheng@scf.usc.edu * The enhancements are mainly based on Steve Deering's * ipmulti-3.5 source code. * Chih-Jen Chang : Added the igmp_get_mrouter_info and * Tsu-Sheng Tsao igmp_set_mrouter_info to keep track of * the mrouted version on that device. * Chih-Jen Chang : Added the max_resp_time parameter to * Tsu-Sheng Tsao igmp_heard_query(). Using this parameter * to identify the multicast router version * and do what the IGMP version 2 specified. * Chih-Jen Chang : Added a timer to revert to IGMP V2 router * Tsu-Sheng Tsao if the specified time expired. * Alan Cox : Stop IGMP from 0.0.0.0 being accepted. * Alan Cox : Use GFP_ATOMIC in the right places. * Christian Daudt : igmp timer wasn't set for local group * memberships but was being deleted, * which caused a "del_timer() called * from %p with timer not initialized\n" * message (960131). * Christian Daudt : removed del_timer from * igmp_timer_expire function (960205). * Christian Daudt : igmp_heard_report now only calls * igmp_timer_expire if tm->running is * true (960216). * Malcolm Beattie : ttl comparison wrong in igmp_rcv made * igmp_heard_query never trigger. Expiry * miscalculation fixed in igmp_heard_query * and random() made to return unsigned to * prevent negative expiry times. * Alexey Kuznetsov: Wrong group leaving behaviour, backport * fix from pending 2.1.x patches. * Alan Cox: Forget to enable FDDI support earlier. * Alexey Kuznetsov: Fixed leaving groups on device down. * Alexey Kuznetsov: Accordance to igmp-v2-06 draft. * David L Stevens: IGMPv3 support, with help from * Vinay Kulkarni */ #include <linux/module.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/times.h> #include <linux/pkt_sched.h> #include <linux/byteorder/generic.h> #include <net/net_namespace.h> #include <net/arp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/sock.h> #include <net/checksum.h> #include <net/inet_common.h> #include <linux/netfilter_ipv4.h> #ifdef CONFIG_IP_MROUTE #include <linux/mroute.h> #endif #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> #endif #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ #define IGMP_QUERY_INTERVAL (125*HZ) #define IGMP_QUERY_RESPONSE_INTERVAL (10*HZ) #define IGMP_INITIAL_REPORT_DELAY (1) /* IGMP_INITIAL_REPORT_DELAY is not from IGMP specs! * IGMP specs require to report membership immediately after * joining a group, but we delay the first report by a * small interval. It seems more natural and still does not * contradict to specs provided this delay is small enough. */ #define IGMP_V1_SEEN(in_dev) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 1 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 1 || \ ((in_dev)->mr_v1_seen && \ time_before(jiffies, (in_dev)->mr_v1_seen))) #define IGMP_V2_SEEN(in_dev) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 2 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 2 || \ ((in_dev)->mr_v2_seen && \ time_before(jiffies, (in_dev)->mr_v2_seen))) static int unsolicited_report_interval(struct in_device *in_dev) { int interval_ms, interval_jiffies; if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) interval_ms = IN_DEV_CONF_GET( in_dev, IGMPV2_UNSOLICITED_REPORT_INTERVAL); else /* v3 */ interval_ms = IN_DEV_CONF_GET( in_dev, IGMPV3_UNSOLICITED_REPORT_INTERVAL); interval_jiffies = msecs_to_jiffies(interval_ms); /* _timer functions can't handle a delay of 0 jiffies so ensure * we always return a positive value. */ if (interval_jiffies <= 0) interval_jiffies = 1; return interval_jiffies; } static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, gfp_t gfp); static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im); static void igmpv3_clear_delrec(struct in_device *in_dev); static int sf_setstate(struct ip_mc_list *pmc); static void sf_markstate(struct ip_mc_list *pmc); #endif static void ip_mc_clear_src(struct ip_mc_list *pmc); static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta); static void ip_ma_put(struct ip_mc_list *im) { if (refcount_dec_and_test(&im->refcnt)) { in_dev_put(im->interface); kfree_rcu(im, rcu); } } #define for_each_pmc_rcu(in_dev, pmc) \ for (pmc = rcu_dereference(in_dev->mc_list); \ pmc != NULL; \ pmc = rcu_dereference(pmc->next_rcu)) #define for_each_pmc_rtnl(in_dev, pmc) \ for (pmc = rtnl_dereference(in_dev->mc_list); \ pmc != NULL; \ pmc = rtnl_dereference(pmc->next_rcu)) static void ip_sf_list_clear_all(struct ip_sf_list *psf) { struct ip_sf_list *next; while (psf) { next = psf->sf_next; kfree(psf); psf = next; } } #ifdef CONFIG_IP_MULTICAST /* * Timer management */ static void igmp_stop_timer(struct ip_mc_list *im) { spin_lock_bh(&im->lock); if (del_timer(&im->timer)) refcount_dec(&im->refcnt); im->tm_running = 0; im->reporter = 0; im->unsolicit_count = 0; spin_unlock_bh(&im->lock); } /* It must be called with locked im->lock */ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) { int tv = get_random_u32_below(max_delay); im->tm_running = 1; if (refcount_inc_not_zero(&im->refcnt)) { if (mod_timer(&im->timer, jiffies + tv + 2)) ip_ma_put(im); } } static void igmp_gq_start_timer(struct in_device *in_dev) { int tv = get_random_u32_below(in_dev->mr_maxdelay); unsigned long exp = jiffies + tv + 2; if (in_dev->mr_gq_running && time_after_eq(exp, (in_dev->mr_gq_timer).expires)) return; in_dev->mr_gq_running = 1; if (!mod_timer(&in_dev->mr_gq_timer, exp)) in_dev_hold(in_dev); } static void igmp_ifc_start_timer(struct in_device *in_dev, int delay) { int tv = get_random_u32_below(delay); if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2)) in_dev_hold(in_dev); } static void igmp_mod_timer(struct ip_mc_list *im, int max_delay) { spin_lock_bh(&im->lock); im->unsolicit_count = 0; if (del_timer(&im->timer)) { if ((long)(im->timer.expires-jiffies) < max_delay) { add_timer(&im->timer); im->tm_running = 1; spin_unlock_bh(&im->lock); return; } refcount_dec(&im->refcnt); } igmp_start_timer(im, max_delay); spin_unlock_bh(&im->lock); } /* * Send an IGMP report. */ #define IGMP_SIZE (sizeof(struct igmphdr)+sizeof(struct iphdr)+4) static int is_in(struct ip_mc_list *pmc, struct ip_sf_list *psf, int type, int gdeleted, int sdeleted) { switch (type) { case IGMPV3_MODE_IS_INCLUDE: case IGMPV3_MODE_IS_EXCLUDE: if (gdeleted || sdeleted) return 0; if (!(pmc->gsquery && !psf->sf_gsresp)) { if (pmc->sfmode == MCAST_INCLUDE) return 1; /* don't include if this source is excluded * in all filters */ if (psf->sf_count[MCAST_INCLUDE]) return type == IGMPV3_MODE_IS_INCLUDE; return pmc->sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; } return 0; case IGMPV3_CHANGE_TO_INCLUDE: if (gdeleted || sdeleted) return 0; return psf->sf_count[MCAST_INCLUDE] != 0; case IGMPV3_CHANGE_TO_EXCLUDE: if (gdeleted || sdeleted) return 0; if (pmc->sfcount[MCAST_EXCLUDE] == 0 || psf->sf_count[MCAST_INCLUDE]) return 0; return pmc->sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; case IGMPV3_ALLOW_NEW_SOURCES: if (gdeleted || !psf->sf_crcount) return 0; return (pmc->sfmode == MCAST_INCLUDE) ^ sdeleted; case IGMPV3_BLOCK_OLD_SOURCES: if (pmc->sfmode == MCAST_INCLUDE) return gdeleted || (psf->sf_crcount && sdeleted); return psf->sf_crcount && !gdeleted && !sdeleted; } return 0; } static int igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) { struct ip_sf_list *psf; int scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; } return scount; } /* source address selection per RFC 3376 section 4.2.13 */ static __be32 igmpv3_get_srcaddr(struct net_device *dev, const struct flowi4 *fl4) { struct in_device *in_dev = __in_dev_get_rcu(dev); const struct in_ifaddr *ifa; if (!in_dev) return htonl(INADDR_ANY); in_dev_for_each_ifa_rcu(ifa, in_dev) { if (fl4->saddr == ifa->ifa_local) return fl4->saddr; } return htonl(INADDR_ANY); } static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) { struct sk_buff *skb; struct rtable *rt; struct iphdr *pip; struct igmpv3_report *pig; struct net *net = dev_net(dev); struct flowi4 fl4; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; unsigned int size; size = min(mtu, IP_MAX_MTU); while (1) { skb = alloc_skb(size + hlen + tlen, GFP_ATOMIC | __GFP_NOWARN); if (skb) break; size >>= 1; if (size < 256) return NULL; } skb->priority = TC_PRIO_CONTROL; rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0, 0, 0, IPPROTO_IGMP, 0, dev->ifindex); if (IS_ERR(rt)) { kfree_skb(skb); return NULL; } skb_dst_set(skb, &rt->dst); skb->dev = dev; skb_reserve(skb, hlen); skb_tailroom_reserve(skb, mtu, tlen); skb_reset_network_header(skb); pip = ip_hdr(skb); skb_put(skb, sizeof(struct iphdr) + 4); pip->version = 4; pip->ihl = (sizeof(struct iphdr)+4)>>2; pip->tos = 0xc0; pip->frag_off = htons(IP_DF); pip->ttl = 1; pip->daddr = fl4.daddr; rcu_read_lock(); pip->saddr = igmpv3_get_srcaddr(dev, &fl4); rcu_read_unlock(); pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(net, skb, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; ((u8 *)&pip[1])[3] = 0; skb->transport_header = skb->network_header + sizeof(struct iphdr) + 4; skb_put(skb, sizeof(*pig)); pig = igmpv3_report_hdr(skb); pig->type = IGMPV3_HOST_MEMBERSHIP_REPORT; pig->resv1 = 0; pig->csum = 0; pig->resv2 = 0; pig->ngrec = 0; return skb; } static int igmpv3_sendpack(struct sk_buff *skb) { struct igmphdr *pig = igmp_hdr(skb); const int igmplen = skb_tail_pointer(skb) - skb_transport_header(skb); pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen); return ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); } static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) { return sizeof(struct igmpv3_grec) + 4*igmp_scount(pmc, type, gdel, sdel); } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc, int type, struct igmpv3_grec **ppgr, unsigned int mtu) { struct net_device *dev = pmc->interface->dev; struct igmpv3_report *pih; struct igmpv3_grec *pgr; if (!skb) { skb = igmpv3_newpack(dev, mtu); if (!skb) return NULL; } pgr = skb_put(skb, sizeof(struct igmpv3_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; pgr->grec_mca = pmc->multiaddr; pih = igmpv3_report_hdr(skb); pih->ngrec = htons(ntohs(pih->ngrec)+1); *ppgr = pgr; return skb; } #define AVAILABLE(skb) ((skb) ? skb_availroom(skb) : 0) static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) { struct net_device *dev = pmc->interface->dev; struct net *net = dev_net(dev); struct igmpv3_report *pih; struct igmpv3_grec *pgr = NULL; struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; int scount, stotal, first, isquery, truncate; unsigned int mtu; if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; if (ipv4_is_local_multicast(pmc->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return skb; mtu = READ_ONCE(dev->mtu); if (mtu < IPV4_MIN_MTU) return skb; isquery = type == IGMPV3_MODE_IS_INCLUDE || type == IGMPV3_MODE_IS_EXCLUDE; truncate = type == IGMPV3_MODE_IS_EXCLUDE || type == IGMPV3_CHANGE_TO_EXCLUDE; stotal = scount = 0; psf_list = sdeleted ? &pmc->tomb : &pmc->sources; if (!*psf_list) goto empty_source; pih = skb ? igmpv3_report_hdr(skb) : NULL; /* EX and TO_EX get a fresh packet, if needed */ if (truncate) { if (pih && pih->ngrec && AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) igmpv3_sendpack(skb); skb = igmpv3_newpack(dev, mtu); } } first = 1; psf_prev = NULL; for (psf = *psf_list; psf; psf = psf_next) { __be32 *psrc; psf_next = psf->sf_next; if (!is_in(pmc, psf, type, gdeleted, sdeleted)) { psf_prev = psf; continue; } /* Based on RFC3376 5.1. Should not send source-list change * records when there is a filter mode change. */ if (((gdeleted && pmc->sfmode == MCAST_EXCLUDE) || (!gdeleted && pmc->crcount)) && (type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) && psf->sf_crcount) goto decrease_sf_crcount; /* clear marks on query responses */ if (isquery) psf->sf_gsresp = 0; if (AVAILABLE(skb) < sizeof(__be32) + first*sizeof(struct igmpv3_grec)) { if (truncate && !first) break; /* truncate these */ if (pgr) pgr->grec_nsrcs = htons(scount); if (skb) igmpv3_sendpack(skb); skb = igmpv3_newpack(dev, mtu); first = 1; scount = 0; } if (first) { skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) return NULL; psrc = skb_put(skb, sizeof(__be32)); *psrc = psf->sf_inaddr; scount++; stotal++; if ((type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) && psf->sf_crcount) { decrease_sf_crcount: psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) psf_prev->sf_next = psf->sf_next; else *psf_list = psf->sf_next; kfree(psf); continue; } } psf_prev = psf; } empty_source: if (!stotal) { if (type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) return skb; if (pmc->crcount || isquery) { /* make sure we have room for group header */ if (skb && AVAILABLE(skb) < sizeof(struct igmpv3_grec)) { igmpv3_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) pgr->grec_nsrcs = htons(scount); if (isquery) pmc->gsquery = 0; /* clear query state on report */ return skb; } static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) { struct sk_buff *skb = NULL; struct net *net = dev_net(in_dev->dev); int type; if (!pmc) { rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(pmc->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; else type = IGMPV3_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } rcu_read_unlock(); } else { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; else type = IGMPV3_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } if (!skb) return 0; return igmpv3_sendpack(skb); } /* * remove zero-count source records from a source filter list */ static void igmpv3_clear_zeros(struct ip_sf_list **ppsf) { struct ip_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; for (psf = *ppsf; psf; psf = psf_next) { psf_next = psf->sf_next; if (psf->sf_crcount == 0) { if (psf_prev) psf_prev->sf_next = psf->sf_next; else *ppsf = psf->sf_next; kfree(psf); } else psf_prev = psf; } } static void kfree_pmc(struct ip_mc_list *pmc) { ip_sf_list_clear_all(pmc->sources); ip_sf_list_clear_all(pmc->tomb); kfree(pmc); } static void igmpv3_send_cr(struct in_device *in_dev) { struct ip_mc_list *pmc, *pmc_prev, *pmc_next; struct sk_buff *skb = NULL; int type, dtype; rcu_read_lock(); spin_lock_bh(&in_dev->mc_tomb_lock); /* deleted MCA's */ pmc_prev = NULL; for (pmc = in_dev->mc_tomb; pmc; pmc = pmc_next) { pmc_next = pmc->next; if (pmc->sfmode == MCAST_INCLUDE) { type = IGMPV3_BLOCK_OLD_SOURCES; dtype = IGMPV3_BLOCK_OLD_SOURCES; skb = add_grec(skb, pmc, type, 1, 0); skb = add_grec(skb, pmc, dtype, 1, 1); } if (pmc->crcount) { if (pmc->sfmode == MCAST_EXCLUDE) { type = IGMPV3_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 1, 0); } pmc->crcount--; if (pmc->crcount == 0) { igmpv3_clear_zeros(&pmc->tomb); igmpv3_clear_zeros(&pmc->sources); } } if (pmc->crcount == 0 && !pmc->tomb && !pmc->sources) { if (pmc_prev) pmc_prev->next = pmc_next; else in_dev->mc_tomb = pmc_next; in_dev_put(pmc->interface); kfree_pmc(pmc); } else pmc_prev = pmc; } spin_unlock_bh(&in_dev->mc_tomb_lock); /* change recs */ for_each_pmc_rcu(in_dev, pmc) { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) { type = IGMPV3_BLOCK_OLD_SOURCES; dtype = IGMPV3_ALLOW_NEW_SOURCES; } else { type = IGMPV3_ALLOW_NEW_SOURCES; dtype = IGMPV3_BLOCK_OLD_SOURCES; } skb = add_grec(skb, pmc, type, 0, 0); skb = add_grec(skb, pmc, dtype, 0, 1); /* deleted sources */ /* filter mode changes */ if (pmc->crcount) { if (pmc->sfmode == MCAST_EXCLUDE) type = IGMPV3_CHANGE_TO_EXCLUDE; else type = IGMPV3_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); pmc->crcount--; } spin_unlock_bh(&pmc->lock); } rcu_read_unlock(); if (!skb) return; (void) igmpv3_sendpack(skb); } static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, int type) { struct sk_buff *skb; struct iphdr *iph; struct igmphdr *ih; struct rtable *rt; struct net_device *dev = in_dev->dev; struct net *net = dev_net(dev); __be32 group = pmc ? pmc->multiaddr : 0; struct flowi4 fl4; __be32 dst; int hlen, tlen; if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); if (ipv4_is_local_multicast(group) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return 0; if (type == IGMP_HOST_LEAVE_MESSAGE) dst = IGMP_ALL_ROUTER; else dst = group; rt = ip_route_output_ports(net, &fl4, NULL, dst, 0, 0, 0, IPPROTO_IGMP, 0, dev->ifindex); if (IS_ERR(rt)) return -1; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC); if (!skb) { ip_rt_put(rt); return -1; } skb->priority = TC_PRIO_CONTROL; skb_dst_set(skb, &rt->dst); skb_reserve(skb, hlen); skb_reset_network_header(skb); iph = ip_hdr(skb); skb_put(skb, sizeof(struct iphdr) + 4); iph->version = 4; iph->ihl = (sizeof(struct iphdr)+4)>>2; iph->tos = 0xc0; iph->frag_off = htons(IP_DF); iph->ttl = 1; iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; ip_select_ident(net, skb, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; ((u8 *)&iph[1])[3] = 0; ih = skb_put(skb, sizeof(struct igmphdr)); ih->type = type; ih->code = 0; ih->csum = 0; ih->group = group; ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr)); return ip_local_out(net, skb->sk, skb); } static void igmp_gq_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_gq_timer); in_dev->mr_gq_running = 0; igmpv3_send_report(in_dev, NULL); in_dev_put(in_dev); } static void igmp_ifc_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer); u32 mr_ifc_count; igmpv3_send_cr(in_dev); restart: mr_ifc_count = READ_ONCE(in_dev->mr_ifc_count); if (mr_ifc_count) { if (cmpxchg(&in_dev->mr_ifc_count, mr_ifc_count, mr_ifc_count - 1) != mr_ifc_count) goto restart; igmp_ifc_start_timer(in_dev, unsolicited_report_interval(in_dev)); } in_dev_put(in_dev); } static void igmp_ifc_event(struct in_device *in_dev) { struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv)); igmp_ifc_start_timer(in_dev, 1); } static void igmp_timer_expire(struct timer_list *t) { struct ip_mc_list *im = from_timer(im, t, timer); struct in_device *in_dev = im->interface; spin_lock(&im->lock); im->tm_running = 0; if (im->unsolicit_count && --im->unsolicit_count) igmp_start_timer(im, unsolicited_report_interval(in_dev)); im->reporter = 1; spin_unlock(&im->lock); if (IGMP_V1_SEEN(in_dev)) igmp_send_report(in_dev, im, IGMP_HOST_MEMBERSHIP_REPORT); else if (IGMP_V2_SEEN(in_dev)) igmp_send_report(in_dev, im, IGMPV2_HOST_MEMBERSHIP_REPORT); else igmp_send_report(in_dev, im, IGMPV3_HOST_MEMBERSHIP_REPORT); ip_ma_put(im); } /* mark EXCLUDE-mode sources */ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) { struct ip_sf_list *psf; int i, scount; scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { /* skip inactive filters */ if (psf->sf_count[MCAST_INCLUDE] || pmc->sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) break; if (srcs[i] == psf->sf_inaddr) { scount++; break; } } } pmc->gsquery = 0; if (scount == nsrcs) /* all sources excluded */ return 0; return 1; } static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) { struct ip_sf_list *psf; int i, scount; if (pmc->sfmode == MCAST_EXCLUDE) return igmp_xmarksources(pmc, nsrcs, srcs); /* mark INCLUDE-mode sources */ scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) if (srcs[i] == psf->sf_inaddr) { psf->sf_gsresp = 1; scount++; break; } } if (!scount) { pmc->gsquery = 0; return 0; } pmc->gsquery = 1; return 1; } /* return true if packet was dropped */ static bool igmp_heard_report(struct in_device *in_dev, __be32 group) { struct ip_mc_list *im; struct net *net = dev_net(in_dev->dev); /* Timers are only set for non-local groups */ if (group == IGMP_ALL_HOSTS) return false; if (ipv4_is_local_multicast(group) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return false; rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == group) { igmp_stop_timer(im); break; } } rcu_read_unlock(); return false; } /* return true if packet was dropped */ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, int len) { struct igmphdr *ih = igmp_hdr(skb); struct igmpv3_query *ih3 = igmpv3_query_hdr(skb); struct ip_mc_list *im; __be32 group = ih->group; int max_delay; int mark = 0; struct net *net = dev_net(in_dev->dev); if (len == 8) { if (ih->code == 0) { /* Alas, old v1 router presents here. */ max_delay = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_v1_seen = jiffies + (in_dev->mr_qrv * in_dev->mr_qi) + in_dev->mr_qri; group = 0; } else { /* v2 router present */ max_delay = ih->code*(HZ/IGMP_TIMER_SCALE); in_dev->mr_v2_seen = jiffies + (in_dev->mr_qrv * in_dev->mr_qi) + in_dev->mr_qri; } /* cancel the interface change timer */ WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); /* clear deleted report items */ igmpv3_clear_delrec(in_dev); } else if (len < 12) { return true; /* ignore bogus packet; freed by caller */ } else if (IGMP_V1_SEEN(in_dev)) { /* This is a v3 query with v1 queriers present */ max_delay = IGMP_QUERY_RESPONSE_INTERVAL; group = 0; } else if (IGMP_V2_SEEN(in_dev)) { /* this is a v3 query with v2 queriers present; * Interpretation of the max_delay code is problematic here. * A real v2 host would use ih_code directly, while v3 has a * different encoding. We use the v3 encoding as more likely * to be intended in a v3 query. */ max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ } else { /* v3 */ if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) return true; ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs) { if (!pskb_may_pull(skb, sizeof(struct igmpv3_query) + ntohs(ih3->nsrcs)*sizeof(__be32))) return true; ih3 = igmpv3_query_hdr(skb); } max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ in_dev->mr_maxdelay = max_delay; /* RFC3376, 4.1.6. QRV and 4.1.7. QQIC, when the most recently * received value was zero, use the default or statically * configured value. */ in_dev->mr_qrv = ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL; /* RFC3376, 8.3. Query Response Interval: * The number of seconds represented by the [Query Response * Interval] must be less than the [Query Interval]. */ if (in_dev->mr_qri >= in_dev->mr_qi) in_dev->mr_qri = (in_dev->mr_qi/HZ - 1)*HZ; if (!group) { /* general query */ if (ih3->nsrcs) return true; /* no sources allowed */ igmp_gq_start_timer(in_dev); return false; } /* mark sources to include, if group & source-specific */ mark = ih3->nsrcs != 0; } /* * - Start the timers in all of our membership records * that the query applies to for the interface on * which the query arrived excl. those that belong * to a "local" group (224.0.0.X) * - For timers already running check if they need to * be reset. * - Use the igmp->igmp_code field as the maximum * delay possible */ rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { int changed; if (group && group != im->multiaddr) continue; if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&im->lock); if (im->tm_running) im->gsquery = im->gsquery && mark; else im->gsquery = mark; changed = !im->gsquery || igmp_marksources(im, ntohs(ih3->nsrcs), ih3->srcs); spin_unlock_bh(&im->lock); if (changed) igmp_mod_timer(im, max_delay); } rcu_read_unlock(); return false; } /* called in rcu_read_lock() section */ int igmp_rcv(struct sk_buff *skb) { /* This basically follows the spec line by line -- see RFC1112 */ struct igmphdr *ih; struct net_device *dev = skb->dev; struct in_device *in_dev; int len = skb->len; bool dropped = true; if (netif_is_l3_master(dev)) { dev = dev_get_by_index_rcu(dev_net(dev), IPCB(skb)->iif); if (!dev) goto drop; } in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto drop; if (!pskb_may_pull(skb, sizeof(struct igmphdr))) goto drop; if (skb_checksum_simple_validate(skb)) goto drop; ih = igmp_hdr(skb); switch (ih->type) { case IGMP_HOST_MEMBERSHIP_QUERY: dropped = igmp_heard_query(in_dev, skb, len); break; case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: /* Is it our report looped back? */ if (rt_is_output_route(skb_rtable(skb))) break; /* don't rely on MC router hearing unicast reports */ if (skb->pkt_type == PACKET_MULTICAST || skb->pkt_type == PACKET_BROADCAST) dropped = igmp_heard_report(in_dev, ih->group); break; case IGMP_PIM: #ifdef CONFIG_IP_PIMSM_V1 return pim_rcv_v1(skb); #endif case IGMPV3_HOST_MEMBERSHIP_REPORT: case IGMP_DVMRP: case IGMP_TRACE: case IGMP_HOST_LEAVE_MESSAGE: case IGMP_MTRACE: case IGMP_MTRACE_RESP: break; default: break; } drop: if (dropped) kfree_skb(skb); else consume_skb(skb); return 0; } #endif /* * Add a filter to a device */ static void ip_mc_filter_add(struct in_device *in_dev, __be32 addr) { char buf[MAX_ADDR_LEN]; struct net_device *dev = in_dev->dev; /* Checking for IFF_MULTICAST here is WRONG-WRONG-WRONG. We will get multicast token leakage, when IFF_MULTICAST is changed. This check should be done in ndo_set_rx_mode routine. Something sort of: if (dev->mc_list && dev->flags&IFF_MULTICAST) { do it; } --ANK */ if (arp_mc_map(addr, buf, dev, 0) == 0) dev_mc_add(dev, buf); } /* * Remove a filter from a device */ static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr) { char buf[MAX_ADDR_LEN]; struct net_device *dev = in_dev->dev; if (arp_mc_map(addr, buf, dev, 0) == 0) dev_mc_del(dev, buf); } #ifdef CONFIG_IP_MULTICAST /* * deleted ip_mc_list manipulation */ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, gfp_t gfp) { struct ip_mc_list *pmc; struct net *net = dev_net(in_dev->dev); /* this is an "ip_mc_list" for convenience; only the fields below * are actually used. In particular, the refcnt and users are not * used for management of the delete list. Using the same structure * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ pmc = kzalloc(sizeof(*pmc), gfp); if (!pmc) return; spin_lock_init(&pmc->lock); spin_lock_bh(&im->lock); pmc->interface = im->interface; in_dev_hold(in_dev); pmc->multiaddr = im->multiaddr; pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); pmc->sfmode = im->sfmode; if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; pmc->tomb = im->tomb; pmc->sources = im->sources; im->tomb = im->sources = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = pmc->crcount; } spin_unlock_bh(&im->lock); spin_lock_bh(&in_dev->mc_tomb_lock); pmc->next = in_dev->mc_tomb; in_dev->mc_tomb = pmc; spin_unlock_bh(&in_dev->mc_tomb_lock); } /* * restore ip_mc_list deleted records */ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list *pmc, *pmc_prev; struct ip_sf_list *psf; struct net *net = dev_net(in_dev->dev); __be32 multiaddr = im->multiaddr; spin_lock_bh(&in_dev->mc_tomb_lock); pmc_prev = NULL; for (pmc = in_dev->mc_tomb; pmc; pmc = pmc->next) { if (pmc->multiaddr == multiaddr) break; pmc_prev = pmc; } if (pmc) { if (pmc_prev) pmc_prev->next = pmc->next; else in_dev->mc_tomb = pmc->next; } spin_unlock_bh(&in_dev->mc_tomb_lock); spin_lock_bh(&im->lock); if (pmc) { im->interface = pmc->interface; if (im->sfmode == MCAST_INCLUDE) { swap(im->tomb, pmc->tomb); swap(im->sources, pmc->sources); for (psf = im->sources; psf; psf = psf->sf_next) psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } else { im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } in_dev_put(pmc->interface); kfree_pmc(pmc); } spin_unlock_bh(&im->lock); } /* * flush ip_mc_list deleted records */ static void igmpv3_clear_delrec(struct in_device *in_dev) { struct ip_mc_list *pmc, *nextpmc; spin_lock_bh(&in_dev->mc_tomb_lock); pmc = in_dev->mc_tomb; in_dev->mc_tomb = NULL; spin_unlock_bh(&in_dev->mc_tomb_lock); for (; pmc; pmc = nextpmc) { nextpmc = pmc->next; ip_mc_clear_src(pmc); in_dev_put(pmc->interface); kfree_pmc(pmc); } /* clear dead sources, too */ rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { struct ip_sf_list *psf; spin_lock_bh(&pmc->lock); psf = pmc->tomb; pmc->tomb = NULL; spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(psf); } rcu_read_unlock(); } #endif static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST struct net *net = dev_net(in_dev->dev); int reporter; #endif if (im->loaded) { im->loaded = 0; ip_mc_filter_del(in_dev, im->multiaddr); } #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; reporter = im->reporter; igmp_stop_timer(im); if (!in_dev->dead) { if (IGMP_V1_SEEN(in_dev)) return; if (IGMP_V2_SEEN(in_dev)) { if (reporter) igmp_send_report(in_dev, im, IGMP_HOST_LEAVE_MESSAGE); return; } /* IGMPv3 */ igmpv3_add_delrec(in_dev, im, gfp); igmp_ifc_event(in_dev); } #endif } static void igmp_group_dropped(struct ip_mc_list *im) { __igmp_group_dropped(im, GFP_KERNEL); } static void igmp_group_added(struct ip_mc_list *im) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST struct net *net = dev_net(in_dev->dev); #endif if (im->loaded == 0) { im->loaded = 1; ip_mc_filter_add(in_dev, im->multiaddr); } #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; if (in_dev->dead) return; im->unsolicit_count = READ_ONCE(net->ipv4.sysctl_igmp_qrv); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) { spin_lock_bh(&im->lock); igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY); spin_unlock_bh(&im->lock); return; } /* else, v3 */ /* Based on RFC3376 5.1, for newly added INCLUDE SSM, we should * not send filter-mode change record as the mode should be from * IN() to IN(A). */ if (im->sfmode == MCAST_EXCLUDE) im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); igmp_ifc_event(in_dev); #endif } /* * Multicast list managers */ static u32 ip_mc_hash(const struct ip_mc_list *im) { return hash_32((__force u32)im->multiaddr, MC_HASH_SZ_LOG); } static void ip_mc_hash_add(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list __rcu **mc_hash; u32 hash; mc_hash = rtnl_dereference(in_dev->mc_hash); if (mc_hash) { hash = ip_mc_hash(im); im->next_hash = mc_hash[hash]; rcu_assign_pointer(mc_hash[hash], im); return; } /* do not use a hash table for small number of items */ if (in_dev->mc_count < 4) return; mc_hash = kzalloc(sizeof(struct ip_mc_list *) << MC_HASH_SZ_LOG, GFP_KERNEL); if (!mc_hash) return; for_each_pmc_rtnl(in_dev, im) { hash = ip_mc_hash(im); im->next_hash = mc_hash[hash]; RCU_INIT_POINTER(mc_hash[hash], im); } rcu_assign_pointer(in_dev->mc_hash, mc_hash); } static void ip_mc_hash_remove(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list __rcu **mc_hash = rtnl_dereference(in_dev->mc_hash); struct ip_mc_list *aux; if (!mc_hash) return; mc_hash += ip_mc_hash(im); while ((aux = rtnl_dereference(*mc_hash)) != im) mc_hash = &aux->next_hash; *mc_hash = im->next_hash; } /* * A socket has joined a multicast group on device dev. */ static void ____ip_mc_inc_group(struct in_device *in_dev, __be32 addr, unsigned int mode, gfp_t gfp) { struct ip_mc_list __rcu **mc_hash; struct ip_mc_list *im; ASSERT_RTNL(); mc_hash = rtnl_dereference(in_dev->mc_hash); if (mc_hash) { u32 hash = hash_32((__force u32)addr, MC_HASH_SZ_LOG); for (im = rtnl_dereference(mc_hash[hash]); im; im = rtnl_dereference(im->next_hash)) { if (im->multiaddr == addr) break; } } else { for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == addr) break; } } if (im) { im->users++; ip_mc_add_src(in_dev, &addr, mode, 0, NULL, 0); goto out; } im = kzalloc(sizeof(*im), gfp); if (!im) goto out; im->users = 1; im->interface = in_dev; in_dev_hold(in_dev); im->multiaddr = addr; /* initial mode is (EX, empty) */ im->sfmode = mode; im->sfcount[mode] = 1; refcount_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST timer_setup(&im->timer, igmp_timer_expire, 0); #endif im->next_rcu = in_dev->mc_list; in_dev->mc_count++; rcu_assign_pointer(in_dev->mc_list, im); ip_mc_hash_add(in_dev, im); #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im); #endif igmp_group_added(im); if (!in_dev->dead) ip_rt_multicast_event(in_dev); out: return; } void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { ____ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE, gfp); } EXPORT_SYMBOL(__ip_mc_inc_group); void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) { __ip_mc_inc_group(in_dev, addr, GFP_KERNEL); } EXPORT_SYMBOL(ip_mc_inc_group); static int ip_mc_check_iphdr(struct sk_buff *skb) { const struct iphdr *iph; unsigned int len; unsigned int offset = skb_network_offset(skb) + sizeof(*iph); if (!pskb_may_pull(skb, offset)) return -EINVAL; iph = ip_hdr(skb); if (iph->version != 4 || ip_hdrlen(skb) < sizeof(*iph)) return -EINVAL; offset += ip_hdrlen(skb) - sizeof(*iph); if (!pskb_may_pull(skb, offset)) return -EINVAL; iph = ip_hdr(skb); if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) return -EINVAL; len = skb_network_offset(skb) + ntohs(iph->tot_len); if (skb->len < len || len < offset) return -EINVAL; skb_set_transport_header(skb, offset); return 0; } static int ip_mc_check_igmp_reportv3(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb); len += sizeof(struct igmpv3_report); return ip_mc_may_pull(skb, len) ? 0 : -EINVAL; } static int ip_mc_check_igmp_query(struct sk_buff *skb) { unsigned int transport_len = ip_transport_len(skb); unsigned int len; /* IGMPv{1,2}? */ if (transport_len != sizeof(struct igmphdr)) { /* or IGMPv3? */ if (transport_len < sizeof(struct igmpv3_query)) return -EINVAL; len = skb_transport_offset(skb) + sizeof(struct igmpv3_query); if (!ip_mc_may_pull(skb, len)) return -EINVAL; } /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer * all-systems destination addresses (224.0.0.1) for general queries */ if (!igmp_hdr(skb)->group && ip_hdr(skb)->daddr != htonl(INADDR_ALLHOSTS_GROUP)) return -EINVAL; return 0; } static int ip_mc_check_igmp_msg(struct sk_buff *skb) { switch (igmp_hdr(skb)->type) { case IGMP_HOST_LEAVE_MESSAGE: case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: return 0; case IGMPV3_HOST_MEMBERSHIP_REPORT: return ip_mc_check_igmp_reportv3(skb); case IGMP_HOST_MEMBERSHIP_QUERY: return ip_mc_check_igmp_query(skb); default: return -ENOMSG; } } static __sum16 ip_mc_validate_checksum(struct sk_buff *skb) { return skb_checksum_simple_validate(skb); } static int ip_mc_check_igmp_csum(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb) + sizeof(struct igmphdr); unsigned int transport_len = ip_transport_len(skb); struct sk_buff *skb_chk; if (!ip_mc_may_pull(skb, len)) return -EINVAL; skb_chk = skb_checksum_trimmed(skb, transport_len, ip_mc_validate_checksum); if (!skb_chk) return -EINVAL; if (skb_chk != skb) kfree_skb(skb_chk); return 0; } /** * ip_mc_check_igmp - checks whether this is a sane IGMP packet * @skb: the skb to validate * * Checks whether an IPv4 packet is a valid IGMP packet. If so sets * skb transport header accordingly and returns zero. * * -EINVAL: A broken packet was detected, i.e. it violates some internet * standard * -ENOMSG: IP header validation succeeded but it is not an IGMP packet. * -ENOMEM: A memory allocation failure happened. * * Caller needs to set the skb network header and free any returned skb if it * differs from the provided skb. */ int ip_mc_check_igmp(struct sk_buff *skb) { int ret = ip_mc_check_iphdr(skb); if (ret < 0) return ret; if (ip_hdr(skb)->protocol != IPPROTO_IGMP) return -ENOMSG; ret = ip_mc_check_igmp_csum(skb); if (ret < 0) return ret; return ip_mc_check_igmp_msg(skb); } EXPORT_SYMBOL(ip_mc_check_igmp); /* * Resend IGMP JOIN report; used by netdev notifier. */ static void ip_mc_rejoin_groups(struct in_device *in_dev) { #ifdef CONFIG_IP_MULTICAST struct ip_mc_list *im; int type; struct net *net = dev_net(in_dev->dev); ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; /* a failover is happening and switches * must be notified immediately */ if (IGMP_V1_SEEN(in_dev)) type = IGMP_HOST_MEMBERSHIP_REPORT; else if (IGMP_V2_SEEN(in_dev)) type = IGMPV2_HOST_MEMBERSHIP_REPORT; else type = IGMPV3_HOST_MEMBERSHIP_REPORT; igmp_send_report(in_dev, im, type); } #endif } /* * A socket has left a multicast group on device dev */ void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { struct ip_mc_list *i; struct ip_mc_list __rcu **ip; ASSERT_RTNL(); for (ip = &in_dev->mc_list; (i = rtnl_dereference(*ip)) != NULL; ip = &i->next_rcu) { if (i->multiaddr == addr) { if (--i->users == 0) { ip_mc_hash_remove(in_dev, i); *ip = i->next_rcu; in_dev->mc_count--; __igmp_group_dropped(i, gfp); ip_mc_clear_src(i); if (!in_dev->dead) ip_rt_multicast_event(in_dev); ip_ma_put(i); return; } break; } } } EXPORT_SYMBOL(__ip_mc_dec_group); /* Device changing type */ void ip_mc_unmap(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) igmp_group_dropped(pmc); } void ip_mc_remap(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) { #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif igmp_group_added(pmc); } } /* Device going down */ void ip_mc_down(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); in_dev->mr_gq_running = 0; if (del_timer(&in_dev->mr_gq_timer)) __in_dev_put(in_dev); #endif ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS); } #ifdef CONFIG_IP_MULTICAST static void ip_mc_reset(struct in_device *in_dev) { struct net *net = dev_net(in_dev->dev); in_dev->mr_qi = IGMP_QUERY_INTERVAL; in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_qrv = READ_ONCE(net->ipv4.sysctl_igmp_qrv); } #else static void ip_mc_reset(struct in_device *in_dev) { } #endif void ip_mc_init_dev(struct in_device *in_dev) { ASSERT_RTNL(); #ifdef CONFIG_IP_MULTICAST timer_setup(&in_dev->mr_gq_timer, igmp_gq_timer_expire, 0); timer_setup(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, 0); #endif ip_mc_reset(in_dev); spin_lock_init(&in_dev->mc_tomb_lock); } /* Device going up */ void ip_mc_up(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); ip_mc_reset(in_dev); ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); for_each_pmc_rtnl(in_dev, pmc) { #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif igmp_group_added(pmc); } } /* * Device is about to be destroyed: clean up. */ void ip_mc_destroy_dev(struct in_device *in_dev) { struct ip_mc_list *i; ASSERT_RTNL(); /* Deactivate timers */ ip_mc_down(in_dev); #ifdef CONFIG_IP_MULTICAST igmpv3_clear_delrec(in_dev); #endif while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { in_dev->mc_list = i->next_rcu; in_dev->mc_count--; ip_mc_clear_src(i); ip_ma_put(i); } } /* RTNL is locked */ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) { struct net_device *dev = NULL; struct in_device *idev = NULL; if (imr->imr_ifindex) { idev = inetdev_by_index(net, imr->imr_ifindex); return idev; } if (imr->imr_address.s_addr) { dev = __ip_dev_find(net, imr->imr_address.s_addr, false); if (!dev) return NULL; } if (!dev) { struct rtable *rt = ip_route_output(net, imr->imr_multiaddr.s_addr, 0, 0, 0, RT_SCOPE_UNIVERSE); if (!IS_ERR(rt)) { dev = rt->dst.dev; ip_rt_put(rt); } } if (dev) { imr->imr_ifindex = dev->ifindex; idev = __in_dev_get_rtnl(dev); } return idev; } /* * Join a socket to a group */ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) { struct ip_sf_list *psf, *psf_prev; int rv = 0; psf_prev = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; } if (!psf || psf->sf_count[sfmode] == 0) { /* source filter not found, or count wrong => bug */ return -ESRCH; } psf->sf_count[sfmode]--; if (psf->sf_count[sfmode] == 0) { ip_rt_multicast_event(pmc->interface); } if (!psf->sf_count[MCAST_INCLUDE] && !psf->sf_count[MCAST_EXCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct in_device *in_dev = pmc->interface; struct net *net = dev_net(in_dev->dev); #endif /* no more filters for this source */ if (psf_prev) psf_prev->sf_next = psf->sf_next; else pmc->sources = psf->sf_next; #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); psf->sf_next = pmc->tomb; pmc->tomb = psf; rv = 1; } else #endif kfree(psf); } return rv; } #ifndef CONFIG_IP_MULTICAST #define igmp_ifc_event(x) do { } while (0) #endif static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta) { struct ip_mc_list *pmc; int changerec = 0; int i, err; if (!in_dev) return -ENODEV; rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif if (!delta) { err = -EINVAL; if (!pmc->sfcount[sfmode]) goto out_unlock; pmc->sfcount[sfmode]--; } err = 0; for (i = 0; i < sfcount; i++) { int rv = ip_mc_del1_src(pmc, sfmode, &psfsrc[i]); changerec |= rv > 0; if (!err && rv < 0) err = rv; } if (pmc->sfmode == MCAST_EXCLUDE && pmc->sfcount[MCAST_EXCLUDE] == 0 && pmc->sfcount[MCAST_INCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; struct net *net = dev_net(in_dev->dev); #endif /* filter mode change */ pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); } else if (sf_setstate(pmc) || changerec) { igmp_ifc_event(pmc->interface); #endif } out_unlock: spin_unlock_bh(&pmc->lock); return err; } /* * Add multicast single-source filter to the interface list */ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) { struct ip_sf_list *psf, *psf_prev; psf_prev = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; } if (!psf) { psf = kzalloc(sizeof(*psf), GFP_ATOMIC); if (!psf) return -ENOBUFS; psf->sf_inaddr = *psfsrc; if (psf_prev) { psf_prev->sf_next = psf; } else pmc->sources = psf; } psf->sf_count[sfmode]++; if (psf->sf_count[sfmode] == 1) { ip_rt_multicast_event(pmc->interface); } return 0; } #ifdef CONFIG_IP_MULTICAST static void sf_markstate(struct ip_mc_list *pmc) { struct ip_sf_list *psf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; for (psf = pmc->sources; psf; psf = psf->sf_next) if (pmc->sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; } static int sf_setstate(struct ip_mc_list *pmc) { struct ip_sf_list *psf, *dpsf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; int qrv = pmc->interface->mr_qrv; int new_in, rv; rv = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (pmc->sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else new_in = psf->sf_count[MCAST_INCLUDE] != 0; if (new_in) { if (!psf->sf_oldin) { struct ip_sf_list *prev = NULL; for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; prev = dpsf; } if (dpsf) { if (prev) prev->sf_next = dpsf->sf_next; else pmc->tomb = dpsf->sf_next; kfree(dpsf); } psf->sf_crcount = qrv; rv++; } } else if (psf->sf_oldin) { psf->sf_crcount = 0; /* * add or update "delete" records if an active filter * is now inactive */ for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) if (dpsf->sf_inaddr == psf->sf_inaddr) break; if (!dpsf) { dpsf = kmalloc(sizeof(*dpsf), GFP_ATOMIC); if (!dpsf) continue; *dpsf = *psf; /* pmc->lock held by callers */ dpsf->sf_next = pmc->tomb; pmc->tomb = dpsf; } dpsf->sf_crcount = qrv; rv++; } } return rv; } #endif /* * Add multicast source filter list to the interface list */ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta) { struct ip_mc_list *pmc; int isexclude; int i, err; if (!in_dev) return -ENODEV; rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif isexclude = pmc->sfmode == MCAST_EXCLUDE; if (!delta) pmc->sfcount[sfmode]++; err = 0; for (i = 0; i < sfcount; i++) { err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]); if (err) break; } if (err) { int j; if (!delta) pmc->sfcount[sfmode]--; for (j = 0; j < i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; struct net *net = dev_net(pmc->interface->dev); in_dev = pmc->interface; #endif /* filter mode change */ if (pmc->sfcount[MCAST_EXCLUDE]) pmc->sfmode = MCAST_EXCLUDE; else if (pmc->sfcount[MCAST_INCLUDE]) pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST /* else no filters; keep old mode for reports */ pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(in_dev); } else if (sf_setstate(pmc)) { igmp_ifc_event(in_dev); #endif } spin_unlock_bh(&pmc->lock); return err; } static void ip_mc_clear_src(struct ip_mc_list *pmc) { struct ip_sf_list *tomb, *sources; spin_lock_bh(&pmc->lock); tomb = pmc->tomb; pmc->tomb = NULL; sources = pmc->sources; pmc->sources = NULL; pmc->sfmode = MCAST_EXCLUDE; pmc->sfcount[MCAST_INCLUDE] = 0; pmc->sfcount[MCAST_EXCLUDE] = 1; spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(tomb); ip_sf_list_clear_all(sources); } /* Join a multicast group */ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, unsigned int mode) { __be32 addr = imr->imr_multiaddr.s_addr; struct ip_mc_socklist *iml, *i; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); int ifindex; int count = 0; int err; ASSERT_RTNL(); if (!ipv4_is_multicast(addr)) return -EINVAL; in_dev = ip_mc_find_dev(net, imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRINUSE; ifindex = imr->imr_ifindex; for_each_pmc_rtnl(inet, i) { if (i->multi.imr_multiaddr.s_addr == addr && i->multi.imr_ifindex == ifindex) goto done; count++; } err = -ENOBUFS; if (count >= READ_ONCE(net->ipv4.sysctl_igmp_max_memberships)) goto done; iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); if (!iml) goto done; memcpy(&iml->multi, imr, sizeof(*imr)); iml->next_rcu = inet->mc_list; iml->sflist = NULL; iml->sfmode = mode; rcu_assign_pointer(inet->mc_list, iml); ____ip_mc_inc_group(in_dev, addr, mode, GFP_KERNEL); err = 0; done: return err; } /* Join ASM (Any-Source Multicast) group */ int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) { return __ip_mc_join_group(sk, imr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ip_mc_join_group); /* Join SSM (Source-Specific Multicast) group */ int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, unsigned int mode) { return __ip_mc_join_group(sk, imr, mode); } static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct in_device *in_dev) { struct ip_sf_socklist *psf = rtnl_dereference(iml->sflist); int err; if (!psf) { /* any-source empty exclude case */ return ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, 0, NULL, 0); } err = ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, psf->sl_count, psf->sl_addr, 0); RCU_INIT_POINTER(iml->sflist, NULL); /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psf, sl_addr, psf->sl_max), &sk->sk_omem_alloc); kfree_rcu(psf, rcu); return err; } int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; struct ip_mc_socklist __rcu **imlp; struct in_device *in_dev; struct net *net = sock_net(sk); __be32 group = imr->imr_multiaddr.s_addr; u32 ifindex; int ret = -EADDRNOTAVAIL; ASSERT_RTNL(); in_dev = ip_mc_find_dev(net, imr); if (!imr->imr_ifindex && !imr->imr_address.s_addr && !in_dev) { ret = -ENODEV; goto out; } ifindex = imr->imr_ifindex; for (imlp = &inet->mc_list; (iml = rtnl_dereference(*imlp)) != NULL; imlp = &iml->next_rcu) { if (iml->multi.imr_multiaddr.s_addr != group) continue; if (ifindex) { if (iml->multi.imr_ifindex != ifindex) continue; } else if (imr->imr_address.s_addr && imr->imr_address.s_addr != iml->multi.imr_address.s_addr) continue; (void) ip_mc_leave_src(sk, iml, in_dev); *imlp = iml->next_rcu; if (in_dev) ip_mc_dec_group(in_dev, group); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); return 0; } out: return ret; } EXPORT_SYMBOL(ip_mc_leave_group); int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mreq_source *mreqs, int ifindex) { int err; struct ip_mreqn imr; __be32 addr = mreqs->imr_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev = NULL; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; struct net *net = sock_net(sk); int leavegroup = 0; int i, j, rv; if (!ipv4_is_multicast(addr)) return -EINVAL; ASSERT_RTNL(); imr.imr_multiaddr.s_addr = mreqs->imr_multiaddr; imr.imr_address.s_addr = mreqs->imr_interface; imr.imr_ifindex = ifindex; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRNOTAVAIL; for_each_pmc_rtnl(inet, pmc) { if ((pmc->multi.imr_multiaddr.s_addr == imr.imr_multiaddr.s_addr) && (pmc->multi.imr_ifindex == imr.imr_ifindex)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } /* if a source filter was set, must be the same mode as before */ if (pmc->sflist) { if (pmc->sfmode != omode) { err = -EINVAL; goto done; } } else if (pmc->sfmode != omode) { /* allow mode switches for empty-set filters */ ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 0, NULL, 0); ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, pmc->sfmode, 0, NULL, 0); pmc->sfmode = omode; } psl = rtnl_dereference(pmc->sflist); if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ rv = !0; for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) break; } if (rv) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (psl->sl_count == 1 && omode == MCAST_INCLUDE) { leavegroup = 1; goto done; } /* update the interface filter */ ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); for (j = i+1; j < psl->sl_count; j++) psl->sl_addr[j-1] = psl->sl_addr[j]; psl->sl_count--; err = 0; goto done; } /* else, add a new source to the filter */ if (psl && psl->sl_count >= READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) { err = -ENOBUFS; goto done; } if (!psl || psl->sl_count == psl->sl_max) { struct ip_sf_socklist *newpsl; int count = IP_SFBLOCK; if (psl) count += psl->sl_max; newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = count; newpsl->sl_count = count - IP_SFBLOCK; if (psl) { for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } rcu_assign_pointer(pmc->sflist, newpsl); if (psl) kfree_rcu(psl, rcu); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) break; } if (rv == 0) /* address already there is an error */ goto done; for (j = psl->sl_count-1; j >= i; j--) psl->sl_addr[j+1] = psl->sl_addr[j]; psl->sl_addr[i] = mreqs->imr_sourceaddr; psl->sl_count++; err = 0; /* update the interface list */ ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); done: if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; } int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) { int err = 0; struct ip_mreqn imr; __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); int leavegroup = 0; if (!ipv4_is_multicast(addr)) return -EINVAL; if (msf->imsf_fmode != MCAST_INCLUDE && msf->imsf_fmode != MCAST_EXCLUDE) return -EINVAL; ASSERT_RTNL(); imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = ifindex; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (msf->imsf_fmode == MCAST_INCLUDE && msf->imsf_numsrc == 0) { leavegroup = 1; goto done; } for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } if (msf->imsf_numsrc) { newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, msf->imsf_numsrc), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = newpsl->sl_count = msf->imsf_numsrc; memcpy(newpsl->sl_addr, msf->imsf_slist_flex, flex_array_size(msf, imsf_slist_flex, msf->imsf_numsrc)); err = ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { sock_kfree_s(sk, newpsl, struct_size(newpsl, sl_addr, newpsl->sl_max)); goto done; } } else { newpsl = NULL; (void) ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, 0, NULL, 0); } psl = rtnl_dereference(pmc->sflist); if (psl) { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } else { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, 0, NULL, 0); } rcu_assign_pointer(pmc->sflist, newpsl); if (psl) kfree_rcu(psl, rcu); pmc->sfmode = msf->imsf_fmode; err = 0; done: if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; } int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, sockptr_t optval, sockptr_t optlen) { int err, len, count, copycount, msf_size; struct ip_mreqn imr; __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; struct net *net = sock_net(sk); ASSERT_RTNL(); if (!ipv4_is_multicast(addr)) return -EINVAL; imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = 0; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRNOTAVAIL; for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; } if (!pmc) /* must have a prior join */ goto done; msf->imsf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); if (!psl) { count = 0; } else { count = psl->sl_count; } copycount = count < msf->imsf_numsrc ? count : msf->imsf_numsrc; len = flex_array_size(psl, sl_addr, copycount); msf->imsf_numsrc = count; msf_size = IP_MSFILTER_SIZE(copycount); if (copy_to_sockptr(optlen, &msf_size, sizeof(int)) || copy_to_sockptr(optval, msf, IP_MSFILTER_SIZE(0))) { return -EFAULT; } if (len && copy_to_sockptr_offset(optval, offsetof(struct ip_msfilter, imsf_slist_flex), psl->sl_addr, len)) return -EFAULT; return 0; done: return err; } int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t ss_offset) { int i, count, copycount; struct sockaddr_in *psin; __be32 addr; struct ip_mc_socklist *pmc; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; ASSERT_RTNL(); psin = (struct sockaddr_in *)&gsf->gf_group; if (psin->sin_family != AF_INET) return -EINVAL; addr = psin->sin_addr.s_addr; if (!ipv4_is_multicast(addr)) return -EINVAL; for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == addr && pmc->multi.imr_ifindex == gsf->gf_interface) break; } if (!pmc) /* must have a prior join */ return -EADDRNOTAVAIL; gsf->gf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; gsf->gf_numsrc = count; for (i = 0; i < copycount; i++) { struct sockaddr_storage ss; psin = (struct sockaddr_in *)&ss; memset(&ss, 0, sizeof(ss)); psin->sin_family = AF_INET; psin->sin_addr.s_addr = psl->sl_addr[i]; if (copy_to_sockptr_offset(optval, ss_offset, &ss, sizeof(ss))) return -EFAULT; ss_offset += sizeof(ss); } return 0; } /* * check if a multicast source filter allows delivery for a given <src,dst,intf> */ int ip_mc_sf_allow(const struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif, int sdif) { const struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *pmc; struct ip_sf_socklist *psl; int i; int ret; ret = 1; if (!ipv4_is_multicast(loc_addr)) goto out; rcu_read_lock(); for_each_pmc_rcu(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == loc_addr && (pmc->multi.imr_ifindex == dif || (sdif && pmc->multi.imr_ifindex == sdif))) break; } ret = inet_test_bit(MC_ALL, sk); if (!pmc) goto unlock; psl = rcu_dereference(pmc->sflist); ret = (pmc->sfmode == MCAST_EXCLUDE); if (!psl) goto unlock; for (i = 0; i < psl->sl_count; i++) { if (psl->sl_addr[i] == rmt_addr) break; } ret = 0; if (pmc->sfmode == MCAST_INCLUDE && i >= psl->sl_count) goto unlock; if (pmc->sfmode == MCAST_EXCLUDE && i < psl->sl_count) goto unlock; ret = 1; unlock: rcu_read_unlock(); out: return ret; } /* * A socket is closing. */ void ip_mc_drop_socket(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; struct net *net = sock_net(sk); if (!inet->mc_list) return; rtnl_lock(); while ((iml = rtnl_dereference(inet->mc_list)) != NULL) { struct in_device *in_dev; inet->mc_list = iml->next_rcu; in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); if (in_dev) ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); } rtnl_unlock(); } /* called with rcu_read_lock() */ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u8 proto) { struct ip_mc_list *im; struct ip_mc_list __rcu **mc_hash; struct ip_sf_list *psf; int rv = 0; mc_hash = rcu_dereference(in_dev->mc_hash); if (mc_hash) { u32 hash = hash_32((__force u32)mc_addr, MC_HASH_SZ_LOG); for (im = rcu_dereference(mc_hash[hash]); im != NULL; im = rcu_dereference(im->next_hash)) { if (im->multiaddr == mc_addr) break; } } else { for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == mc_addr) break; } } if (im && proto == IPPROTO_IGMP) { rv = 1; } else if (im) { if (src_addr) { spin_lock_bh(&im->lock); for (psf = im->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == src_addr) break; } if (psf) rv = psf->sf_count[MCAST_INCLUDE] || psf->sf_count[MCAST_EXCLUDE] != im->sfcount[MCAST_EXCLUDE]; else rv = im->sfcount[MCAST_EXCLUDE] != 0; spin_unlock_bh(&im->lock); } else rv = 1; /* unspecified source; tentatively allow */ } return rv; } #if defined(CONFIG_PROC_FS) struct igmp_mc_iter_state { struct seq_net_private p; struct net_device *dev; struct in_device *in_dev; }; #define igmp_mc_seq_private(seq) ((struct igmp_mc_iter_state *)(seq)->private) static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ip_mc_list *im = NULL; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; for_each_netdev_rcu(net, state->dev) { struct in_device *in_dev; in_dev = __in_dev_get_rcu(state->dev); if (!in_dev) continue; im = rcu_dereference(in_dev->mc_list); if (im) { state->in_dev = in_dev; break; } } return im; } static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_list *im) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); im = rcu_dereference(im->next_rcu); while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->in_dev = NULL; break; } state->in_dev = __in_dev_get_rcu(state->dev); if (!state->in_dev) continue; im = rcu_dereference(state->in_dev->mc_list); } return im; } static struct ip_mc_list *igmp_mc_get_idx(struct seq_file *seq, loff_t pos) { struct ip_mc_list *im = igmp_mc_get_first(seq); if (im) while (pos && (im = igmp_mc_get_next(seq, im)) != NULL) --pos; return pos ? NULL : im; } static void *igmp_mc_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return *pos ? igmp_mc_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_mc_list *im; if (v == SEQ_START_TOKEN) im = igmp_mc_get_first(seq); else im = igmp_mc_get_next(seq, v); ++*pos; return im; } static void igmp_mc_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp_mc_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_puts(seq, "Idx\tDevice : Count Querier\tGroup Users Timer\tReporter\n"); else { struct ip_mc_list *im = v; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); char *querier; long delta; #ifdef CONFIG_IP_MULTICAST querier = IGMP_V1_SEEN(state->in_dev) ? "V1" : IGMP_V2_SEEN(state->in_dev) ? "V2" : "V3"; #else querier = "NONE"; #endif if (rcu_access_pointer(state->in_dev->mc_list) == im) { seq_printf(seq, "%d\t%-10s: %5d %7s\n", state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier); } delta = im->timer.expires - jiffies; seq_printf(seq, "\t\t\t\t%08X %5d %d:%08lX\t\t%d\n", im->multiaddr, im->users, im->tm_running, im->tm_running ? jiffies_delta_to_clock_t(delta) : 0, im->reporter); } return 0; } static const struct seq_operations igmp_mc_seq_ops = { .start = igmp_mc_seq_start, .next = igmp_mc_seq_next, .stop = igmp_mc_seq_stop, .show = igmp_mc_seq_show, }; struct igmp_mcf_iter_state { struct seq_net_private p; struct net_device *dev; struct in_device *idev; struct ip_mc_list *im; }; #define igmp_mcf_seq_private(seq) ((struct igmp_mcf_iter_state *)(seq)->private) static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ip_sf_list *psf = NULL; struct ip_mc_list *im = NULL; struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); state->idev = NULL; state->im = NULL; for_each_netdev_rcu(net, state->dev) { struct in_device *idev; idev = __in_dev_get_rcu(state->dev); if (unlikely(!idev)) continue; im = rcu_dereference(idev->mc_list); if (likely(im)) { spin_lock_bh(&im->lock); psf = im->sources; if (likely(psf)) { state->im = im; state->idev = idev; break; } spin_unlock_bh(&im->lock); } } return psf; } static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_list *psf) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); psf = psf->sf_next; while (!psf) { spin_unlock_bh(&state->im->lock); state->im = state->im->next; while (!state->im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } state->idev = __in_dev_get_rcu(state->dev); if (!state->idev) continue; state->im = rcu_dereference(state->idev->mc_list); } spin_lock_bh(&state->im->lock); psf = state->im->sources; } out: return psf; } static struct ip_sf_list *igmp_mcf_get_idx(struct seq_file *seq, loff_t pos) { struct ip_sf_list *psf = igmp_mcf_get_first(seq); if (psf) while (pos && (psf = igmp_mcf_get_next(seq, psf)) != NULL) --pos; return pos ? NULL : psf; } static void *igmp_mcf_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return *pos ? igmp_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_sf_list *psf; if (v == SEQ_START_TOKEN) psf = igmp_mcf_get_first(seq); else psf = igmp_mcf_get_next(seq, v); ++*pos; return psf; } static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (likely(state->im)) { spin_unlock_bh(&state->im->lock); state->im = NULL; } state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp_mcf_seq_show(struct seq_file *seq, void *v) { struct ip_sf_list *psf = v; struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, "Idx Device MCA SRC INC EXC\n"); } else { seq_printf(seq, "%3d %6.6s 0x%08x " "0x%08x %6lu %6lu\n", state->dev->ifindex, state->dev->name, ntohl(state->im->multiaddr), ntohl(psf->sf_inaddr), psf->sf_count[MCAST_INCLUDE], psf->sf_count[MCAST_EXCLUDE]); } return 0; } static const struct seq_operations igmp_mcf_seq_ops = { .start = igmp_mcf_seq_start, .next = igmp_mcf_seq_next, .stop = igmp_mcf_seq_stop, .show = igmp_mcf_seq_show, }; static int __net_init igmp_net_init(struct net *net) { struct proc_dir_entry *pde; int err; pde = proc_create_net("igmp", 0444, net->proc_net, &igmp_mc_seq_ops, sizeof(struct igmp_mc_iter_state)); if (!pde) goto out_igmp; pde = proc_create_net("mcfilter", 0444, net->proc_net, &igmp_mcf_seq_ops, sizeof(struct igmp_mcf_iter_state)); if (!pde) goto out_mcfilter; err = inet_ctl_sock_create(&net->ipv4.mc_autojoin_sk, AF_INET, SOCK_DGRAM, 0, net); if (err < 0) { pr_err("Failed to initialize the IGMP autojoin socket (err %d)\n", err); goto out_sock; } return 0; out_sock: remove_proc_entry("mcfilter", net->proc_net); out_mcfilter: remove_proc_entry("igmp", net->proc_net); out_igmp: return -ENOMEM; } static void __net_exit igmp_net_exit(struct net *net) { remove_proc_entry("mcfilter", net->proc_net); remove_proc_entry("igmp", net->proc_net); inet_ctl_sock_destroy(net->ipv4.mc_autojoin_sk); } static struct pernet_operations igmp_net_ops = { .init = igmp_net_init, .exit = igmp_net_exit, }; #endif static int igmp_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct in_device *in_dev; switch (event) { case NETDEV_RESEND_IGMP: in_dev = __in_dev_get_rtnl(dev); if (in_dev) ip_mc_rejoin_groups(in_dev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block igmp_notifier = { .notifier_call = igmp_netdev_event, }; int __init igmp_mc_init(void) { #if defined(CONFIG_PROC_FS) int err; err = register_pernet_subsys(&igmp_net_ops); if (err) return err; err = register_netdevice_notifier(&igmp_notifier); if (err) goto reg_notif_fail; return 0; reg_notif_fail: unregister_pernet_subsys(&igmp_net_ops); return err; #else return register_netdevice_notifier(&igmp_notifier); #endif } |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Public Key Encryption * * Copyright (c) 2015, Intel Corporation * Authors: Tadeusz Struk <tadeusz.struk@intel.com> */ #include <crypto/internal/akcipher.h> #include <linux/cryptouser.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/scatterlist.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/string.h> #include <net/netlink.h> #include "internal.h" #define CRYPTO_ALG_TYPE_AHASH_MASK 0x0000000e struct crypto_akcipher_sync_data { struct crypto_akcipher *tfm; const void *src; void *dst; unsigned int slen; unsigned int dlen; struct akcipher_request *req; struct crypto_wait cwait; struct scatterlist sg; u8 *buf; }; static int __maybe_unused crypto_akcipher_report( struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_akcipher rakcipher; memset(&rakcipher, 0, sizeof(rakcipher)); strscpy(rakcipher.type, "akcipher", sizeof(rakcipher.type)); return nla_put(skb, CRYPTOCFGA_REPORT_AKCIPHER, sizeof(rakcipher), &rakcipher); } static void crypto_akcipher_show(struct seq_file *m, struct crypto_alg *alg) __maybe_unused; static void crypto_akcipher_show(struct seq_file *m, struct crypto_alg *alg) { seq_puts(m, "type : akcipher\n"); } static void crypto_akcipher_exit_tfm(struct crypto_tfm *tfm) { struct crypto_akcipher *akcipher = __crypto_akcipher_tfm(tfm); struct akcipher_alg *alg = crypto_akcipher_alg(akcipher); alg->exit(akcipher); } static int crypto_akcipher_init_tfm(struct crypto_tfm *tfm) { struct crypto_akcipher *akcipher = __crypto_akcipher_tfm(tfm); struct akcipher_alg *alg = crypto_akcipher_alg(akcipher); if (alg->exit) akcipher->base.exit = crypto_akcipher_exit_tfm; if (alg->init) return alg->init(akcipher); return 0; } static void crypto_akcipher_free_instance(struct crypto_instance *inst) { struct akcipher_instance *akcipher = akcipher_instance(inst); akcipher->free(akcipher); } static const struct crypto_type crypto_akcipher_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_akcipher_init_tfm, .free = crypto_akcipher_free_instance, #ifdef CONFIG_PROC_FS .show = crypto_akcipher_show, #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_akcipher_report, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_AHASH_MASK, .type = CRYPTO_ALG_TYPE_AKCIPHER, .tfmsize = offsetof(struct crypto_akcipher, base), }; int crypto_grab_akcipher(struct crypto_akcipher_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask) { spawn->base.frontend = &crypto_akcipher_type; return crypto_grab_spawn(&spawn->base, inst, name, type, mask); } EXPORT_SYMBOL_GPL(crypto_grab_akcipher); struct crypto_akcipher *crypto_alloc_akcipher(const char *alg_name, u32 type, u32 mask) { return crypto_alloc_tfm(alg_name, &crypto_akcipher_type, type, mask); } EXPORT_SYMBOL_GPL(crypto_alloc_akcipher); static void akcipher_prepare_alg(struct akcipher_alg *alg) { struct crypto_alg *base = &alg->base; base->cra_type = &crypto_akcipher_type; base->cra_flags &= ~CRYPTO_ALG_TYPE_MASK; base->cra_flags |= CRYPTO_ALG_TYPE_AKCIPHER; } static int akcipher_default_op(struct akcipher_request *req) { return -ENOSYS; } static int akcipher_default_set_key(struct crypto_akcipher *tfm, const void *key, unsigned int keylen) { return -ENOSYS; } int crypto_register_akcipher(struct akcipher_alg *alg) { struct crypto_alg *base = &alg->base; if (!alg->encrypt) alg->encrypt = akcipher_default_op; if (!alg->decrypt) alg->decrypt = akcipher_default_op; if (!alg->set_priv_key) alg->set_priv_key = akcipher_default_set_key; akcipher_prepare_alg(alg); return crypto_register_alg(base); } EXPORT_SYMBOL_GPL(crypto_register_akcipher); void crypto_unregister_akcipher(struct akcipher_alg *alg) { crypto_unregister_alg(&alg->base); } EXPORT_SYMBOL_GPL(crypto_unregister_akcipher); int akcipher_register_instance(struct crypto_template *tmpl, struct akcipher_instance *inst) { if (WARN_ON(!inst->free)) return -EINVAL; akcipher_prepare_alg(&inst->alg); return crypto_register_instance(tmpl, akcipher_crypto_instance(inst)); } EXPORT_SYMBOL_GPL(akcipher_register_instance); static int crypto_akcipher_sync_prep(struct crypto_akcipher_sync_data *data) { unsigned int reqsize = crypto_akcipher_reqsize(data->tfm); struct akcipher_request *req; struct scatterlist *sg; unsigned int mlen; unsigned int len; u8 *buf; mlen = max(data->slen, data->dlen); len = sizeof(*req) + reqsize + mlen; if (len < mlen) return -EOVERFLOW; req = kzalloc(len, GFP_KERNEL); if (!req) return -ENOMEM; data->req = req; akcipher_request_set_tfm(req, data->tfm); buf = (u8 *)(req + 1) + reqsize; data->buf = buf; memcpy(buf, data->src, data->slen); sg = &data->sg; sg_init_one(sg, buf, mlen); akcipher_request_set_crypt(req, sg, sg, data->slen, data->dlen); crypto_init_wait(&data->cwait); akcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, &data->cwait); return 0; } static int crypto_akcipher_sync_post(struct crypto_akcipher_sync_data *data, int err) { err = crypto_wait_req(err, &data->cwait); memcpy(data->dst, data->buf, data->dlen); data->dlen = data->req->dst_len; kfree_sensitive(data->req); return err; } int crypto_akcipher_sync_encrypt(struct crypto_akcipher *tfm, const void *src, unsigned int slen, void *dst, unsigned int dlen) { struct crypto_akcipher_sync_data data = { .tfm = tfm, .src = src, .dst = dst, .slen = slen, .dlen = dlen, }; return crypto_akcipher_sync_prep(&data) ?: crypto_akcipher_sync_post(&data, crypto_akcipher_encrypt(data.req)); } EXPORT_SYMBOL_GPL(crypto_akcipher_sync_encrypt); int crypto_akcipher_sync_decrypt(struct crypto_akcipher *tfm, const void *src, unsigned int slen, void *dst, unsigned int dlen) { struct crypto_akcipher_sync_data data = { .tfm = tfm, .src = src, .dst = dst, .slen = slen, .dlen = dlen, }; return crypto_akcipher_sync_prep(&data) ?: crypto_akcipher_sync_post(&data, crypto_akcipher_decrypt(data.req)) ?: data.dlen; } EXPORT_SYMBOL_GPL(crypto_akcipher_sync_decrypt); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Generic public key cipher type"); |
| 950 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM fib6 #if !defined(_TRACE_FIB6_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FIB6_H #include <linux/in6.h> #include <net/flow.h> #include <net/ip6_fib.h> #include <linux/tracepoint.h> TRACE_EVENT(fib6_table_lookup, TP_PROTO(const struct net *net, const struct fib6_result *res, struct fib6_table *table, const struct flowi6 *flp), TP_ARGS(net, res, table, flp), TP_STRUCT__entry( __field( u32, tb_id ) __field( int, err ) __field( int, oif ) __field( int, iif ) __field( __u8, tos ) __field( __u8, scope ) __field( __u8, flags ) __array( __u8, src, 16 ) __array( __u8, dst, 16 ) __field( u16, sport ) __field( u16, dport ) __field( u8, proto ) __field( u8, rt_type ) __array( char, name, IFNAMSIZ ) __array( __u8, gw, 16 ) ), TP_fast_assign( struct in6_addr *in6; __entry->tb_id = table->tb6_id; __entry->err = ip6_rt_type_to_error(res->fib6_type); __entry->oif = flp->flowi6_oif; __entry->iif = flp->flowi6_iif; __entry->tos = ip6_tclass(flp->flowlabel); __entry->scope = flp->flowi6_scope; __entry->flags = flp->flowi6_flags; in6 = (struct in6_addr *)__entry->src; *in6 = flp->saddr; in6 = (struct in6_addr *)__entry->dst; *in6 = flp->daddr; __entry->proto = flp->flowi6_proto; if (__entry->proto == IPPROTO_TCP || __entry->proto == IPPROTO_UDP) { __entry->sport = ntohs(flp->fl6_sport); __entry->dport = ntohs(flp->fl6_dport); } else { __entry->sport = 0; __entry->dport = 0; } if (res->nh && res->nh->fib_nh_dev) { strscpy(__entry->name, res->nh->fib_nh_dev->name, IFNAMSIZ); } else { strcpy(__entry->name, "-"); } if (res->f6i == net->ipv6.fib6_null_entry) { in6 = (struct in6_addr *)__entry->gw; *in6 = in6addr_any; } else if (res->nh) { in6 = (struct in6_addr *)__entry->gw; *in6 = res->nh->fib_nh_gw6; } ), TP_printk("table %3u oif %d iif %d proto %u %pI6c/%u -> %pI6c/%u tos %d scope %d flags %x ==> dev %s gw %pI6c err %d", __entry->tb_id, __entry->oif, __entry->iif, __entry->proto, __entry->src, __entry->sport, __entry->dst, __entry->dport, __entry->tos, __entry->scope, __entry->flags, __entry->name, __entry->gw, __entry->err) ); #endif /* _TRACE_FIB6_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 18 18 17 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * ksyms_common.c: A split of kernel/kallsyms.c * Contains a few generic function definations independent of config KALLSYMS. */ #include <linux/kallsyms.h> #include <linux/security.h> static inline int kallsyms_for_perf(void) { #ifdef CONFIG_PERF_EVENTS extern int sysctl_perf_event_paranoid; if (sysctl_perf_event_paranoid <= 1) return 1; #endif return 0; } /* * We show kallsyms information even to normal users if we've enabled * kernel profiling and are explicitly not paranoid (so kptr_restrict * is clear, and sysctl_perf_event_paranoid isn't set). * * Otherwise, require CAP_SYSLOG (assuming kptr_restrict isn't set to * block even that). */ bool kallsyms_show_value(const struct cred *cred) { switch (kptr_restrict) { case 0: if (kallsyms_for_perf()) return true; fallthrough; case 1: if (security_capable(cred, &init_user_ns, CAP_SYSLOG, CAP_OPT_NOAUDIT) == 0) return true; fallthrough; default: return false; } } |
| 3 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ /* * Basic idea behind the notification queue: An fsnotify group (like inotify) * sends the userspace notification about events asynchronously some time after * the event happened. When inotify gets an event it will need to add that * event to the group notify queue. Since a single event might need to be on * multiple group's notification queues we can't add the event directly to each * queue and instead add a small "event_holder" to each queue. This event_holder * has a pointer back to the original event. Since the majority of events are * going to end up on one, and only one, notification queue we embed one * event_holder into each event. This means we have a single allocation instead * of always needing two. If the embedded event_holder is already in use by * another group a new event_holder (from fsnotify_event_holder_cachep) will be * allocated and used. */ #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/mutex.h> #include <linux/namei.h> #include <linux/path.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" static atomic_t fsnotify_sync_cookie = ATOMIC_INIT(0); /** * fsnotify_get_cookie - return a unique cookie for use in synchronizing events. * Called from fsnotify_move, which is inlined into filesystem modules. */ u32 fsnotify_get_cookie(void) { return atomic_inc_return(&fsnotify_sync_cookie); } EXPORT_SYMBOL_GPL(fsnotify_get_cookie); void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event) { /* Overflow events are per-group and we don't want to free them */ if (!event || event == group->overflow_event) return; /* * If the event is still queued, we have a problem... Do an unreliable * lockless check first to avoid locking in the common case. The * locking may be necessary for permission events which got removed * from the list by a different CPU than the one freeing the event. */ if (!list_empty(&event->list)) { spin_lock(&group->notification_lock); WARN_ON(!list_empty(&event->list)); spin_unlock(&group->notification_lock); } group->ops->free_event(group, event); } /* * Try to add an event to the notification queue. * The group can later pull this event off the queue to deal with. * The group can use the @merge hook to merge the event with a queued event. * The group can use the @insert hook to insert the event into hash table. * The function returns: * 0 if the event was added to a queue * 1 if the event was merged with some other queued event * 2 if the event was not queued - either the queue of events has overflown * or the group is shutting down. */ int fsnotify_insert_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct fsnotify_group *, struct fsnotify_event *), void (*insert)(struct fsnotify_group *, struct fsnotify_event *)) { int ret = 0; struct list_head *list = &group->notification_list; pr_debug("%s: group=%p event=%p\n", __func__, group, event); spin_lock(&group->notification_lock); if (group->shutdown) { spin_unlock(&group->notification_lock); return 2; } if (event == group->overflow_event || group->q_len >= group->max_events) { ret = 2; /* Queue overflow event only if it isn't already queued */ if (!list_empty(&group->overflow_event->list)) { spin_unlock(&group->notification_lock); return ret; } event = group->overflow_event; goto queue; } if (!list_empty(list) && merge) { ret = merge(group, event); if (ret) { spin_unlock(&group->notification_lock); return ret; } } queue: group->q_len++; list_add_tail(&event->list, list); if (insert) insert(group, event); spin_unlock(&group->notification_lock); wake_up(&group->notification_waitq); kill_fasync(&group->fsn_fa, SIGIO, POLL_IN); return ret; } void fsnotify_remove_queued_event(struct fsnotify_group *group, struct fsnotify_event *event) { assert_spin_locked(&group->notification_lock); /* * We need to init list head for the case of overflow event so that * check in fsnotify_add_event() works */ list_del_init(&event->list); group->q_len--; } /* * Return the first event on the notification list without removing it. * Returns NULL if the list is empty. */ struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group) { assert_spin_locked(&group->notification_lock); if (fsnotify_notify_queue_is_empty(group)) return NULL; return list_first_entry(&group->notification_list, struct fsnotify_event, list); } /* * Remove and return the first event from the notification list. It is the * responsibility of the caller to destroy the obtained event */ struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group) { struct fsnotify_event *event = fsnotify_peek_first_event(group); if (!event) return NULL; pr_debug("%s: group=%p event=%p\n", __func__, group, event); fsnotify_remove_queued_event(group, event); return event; } /* * Called when a group is being torn down to clean up any outstanding * event notifications. */ void fsnotify_flush_notify(struct fsnotify_group *group) { struct fsnotify_event *event; spin_lock(&group->notification_lock); while (!fsnotify_notify_queue_is_empty(group)) { event = fsnotify_remove_first_event(group); spin_unlock(&group->notification_lock); fsnotify_destroy_event(group, event); spin_lock(&group->notification_lock); } spin_unlock(&group->notification_lock); } |
| 26 112 114 114 114 115 113 231 62 62 59 1 3 4 3 1 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_GRE_H #define __LINUX_GRE_H #include <linux/skbuff.h> #include <net/ip_tunnels.h> struct gre_base_hdr { __be16 flags; __be16 protocol; } __packed; struct gre_full_hdr { struct gre_base_hdr fixed_header; __be16 csum; __be16 reserved1; __be32 key; __be32 seq; } __packed; #define GRE_HEADER_SECTION 4 #define GREPROTO_CISCO 0 #define GREPROTO_PPTP 1 #define GREPROTO_MAX 2 #define GRE_IP_PROTO_MAX 2 struct gre_protocol { int (*handler)(struct sk_buff *skb); void (*err_handler)(struct sk_buff *skb, u32 info); }; int gre_add_protocol(const struct gre_protocol *proto, u8 version); int gre_del_protocol(const struct gre_protocol *proto, u8 version); struct net_device *gretap_fb_dev_create(struct net *net, const char *name, u8 name_assign_type); int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err, __be16 proto, int nhs); static inline bool netif_is_gretap(const struct net_device *dev) { return dev->rtnl_link_ops && !strcmp(dev->rtnl_link_ops->kind, "gretap"); } static inline bool netif_is_ip6gretap(const struct net_device *dev) { return dev->rtnl_link_ops && !strcmp(dev->rtnl_link_ops->kind, "ip6gretap"); } static inline int gre_calc_hlen(const unsigned long *o_flags) { int addend = 4; if (test_bit(IP_TUNNEL_CSUM_BIT, o_flags)) addend += 4; if (test_bit(IP_TUNNEL_KEY_BIT, o_flags)) addend += 4; if (test_bit(IP_TUNNEL_SEQ_BIT, o_flags)) addend += 4; return addend; } static inline void gre_flags_to_tnl_flags(unsigned long *dst, __be16 flags) { IP_TUNNEL_DECLARE_FLAGS(res) = { }; __assign_bit(IP_TUNNEL_CSUM_BIT, res, flags & GRE_CSUM); __assign_bit(IP_TUNNEL_ROUTING_BIT, res, flags & GRE_ROUTING); __assign_bit(IP_TUNNEL_KEY_BIT, res, flags & GRE_KEY); __assign_bit(IP_TUNNEL_SEQ_BIT, res, flags & GRE_SEQ); __assign_bit(IP_TUNNEL_STRICT_BIT, res, flags & GRE_STRICT); __assign_bit(IP_TUNNEL_REC_BIT, res, flags & GRE_REC); __assign_bit(IP_TUNNEL_VERSION_BIT, res, flags & GRE_VERSION); ip_tunnel_flags_copy(dst, res); } static inline __be16 gre_tnl_flags_to_gre_flags(const unsigned long *tflags) { __be16 flags = 0; if (test_bit(IP_TUNNEL_CSUM_BIT, tflags)) flags |= GRE_CSUM; if (test_bit(IP_TUNNEL_ROUTING_BIT, tflags)) flags |= GRE_ROUTING; if (test_bit(IP_TUNNEL_KEY_BIT, tflags)) flags |= GRE_KEY; if (test_bit(IP_TUNNEL_SEQ_BIT, tflags)) flags |= GRE_SEQ; if (test_bit(IP_TUNNEL_STRICT_BIT, tflags)) flags |= GRE_STRICT; if (test_bit(IP_TUNNEL_REC_BIT, tflags)) flags |= GRE_REC; if (test_bit(IP_TUNNEL_VERSION_BIT, tflags)) flags |= GRE_VERSION; return flags; } static inline void gre_build_header(struct sk_buff *skb, int hdr_len, const unsigned long *flags, __be16 proto, __be32 key, __be32 seq) { IP_TUNNEL_DECLARE_FLAGS(cond) = { }; struct gre_base_hdr *greh; skb_push(skb, hdr_len); skb_set_inner_protocol(skb, proto); skb_reset_transport_header(skb); greh = (struct gre_base_hdr *)skb->data; greh->flags = gre_tnl_flags_to_gre_flags(flags); greh->protocol = proto; __set_bit(IP_TUNNEL_KEY_BIT, cond); __set_bit(IP_TUNNEL_CSUM_BIT, cond); __set_bit(IP_TUNNEL_SEQ_BIT, cond); if (ip_tunnel_flags_intersect(flags, cond)) { __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); if (test_bit(IP_TUNNEL_SEQ_BIT, flags)) { *ptr = seq; ptr--; } if (test_bit(IP_TUNNEL_KEY_BIT, flags)) { *ptr = key; ptr--; } if (test_bit(IP_TUNNEL_CSUM_BIT, flags) && !(skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) { *ptr = 0; if (skb->ip_summed == CHECKSUM_PARTIAL) { *(__sum16 *)ptr = csum_fold(lco_csum(skb)); } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = sizeof(*greh); } } } } #endif |
| 26 26 89 89 408 410 168 26 21 15 408 3 410 237 233 264 10 24 145 143 144 145 145 467 469 468 461 466 202 202 74 201 202 89 88 89 88 74 15 2 1 89 89 84 4 28 28 28 27 1 10 9 1 2 9 1 26 14 3 1 14 7 3 4 96 95 2 94 95 2 2 2 2 3 3 2 1 11 1 1 1 8 8 7 5 1 3 1 4 1 12 12 1 7 20 1 1 1 1 15 3 2 2 14 2 14 4 10 14 14 11 3 1 13 10 4 13 1 14 9 2 22 22 1 15 14 10 8 1 1 1 1 2 3 10 4 7 1 1 2 42 41 1 27 15 21 5 38 39 1 37 1 2 2 18 38 20 6 6 14 14 9 4 1 4 2 4 1 7 7 1 1 1 1 1 4 3 1 3 3 1 3 1 1 1 1 16 16 13 14 112 112 111 113 112 14 95 12 105 16 13 16 5 16 111 44 12 17 11 1 3 1 2 1 906 908 901 570 462 6 1 4 666 1 187 6 219 1 190 28 29 101 203 17 17 120 121 120 118 1 5 120 121 111 11 1 120 119 1 1 116 4 121 3 1 3 3 4 11 1 13 1 10 5 5 3 5 22 22 3 19 1 1 1 1 1 4 4 1 4 22 22 116 116 116 874 872 923 928 194 37 8 8 1 1 5 1 1 5 5 1 1 3 2 581 582 582 581 580 594 1 1 220 506 499 499 503 499 501 9 580 582 581 1 9 7 14 10 4 1 1 1 1 1 1 3 2 1 3 12 10 1 1 11 11 11 7 11 1 3 1 3 11 484 487 218 483 485 218 6 6 6 6 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NET3 IP device support routines. * * Derived from the IP parts of dev.c 1.0.19 * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * * Additional Authors: * Alan Cox, <gw4pts@gw4pts.ampr.org> * Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Changes: * Alexey Kuznetsov: pa_* fields are replaced with ifaddr * lists. * Cyrus Durgin: updated for kmod * Matthias Andree: in devinet_ioctl, compare label and * address (4.4BSD alias style support), * fall back to comparing just the label * if no match found. */ #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/if_addr.h> #include <linux/if_ether.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/notifier.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/slab.h> #include <linux/hash.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/kmod.h> #include <linux/netconf.h> #include <net/arp.h> #include <net/ip.h> #include <net/route.h> #include <net/ip_fib.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/addrconf.h> #define IPV6ONLY_FLAGS \ (IFA_F_NODAD | IFA_F_OPTIMISTIC | IFA_F_DADFAILED | \ IFA_F_HOMEADDRESS | IFA_F_TENTATIVE | \ IFA_F_MANAGETEMPADDR | IFA_F_STABLE_PRIVACY) static struct ipv4_devconf ipv4_devconf = { .data = { [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1, [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, [IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1, }, }; static struct ipv4_devconf ipv4_devconf_dflt = { .data = { [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1, [IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE - 1] = 1, [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, [IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1, }, }; #define IPV4_DEVCONF_DFLT(net, attr) \ IPV4_DEVCONF((*net->ipv4.devconf_dflt), attr) static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_LOCAL] = { .type = NLA_U32 }, [IFA_ADDRESS] = { .type = NLA_U32 }, [IFA_BROADCAST] = { .type = NLA_U32 }, [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, [IFA_FLAGS] = { .type = NLA_U32 }, [IFA_RT_PRIORITY] = { .type = NLA_U32 }, [IFA_TARGET_NETNSID] = { .type = NLA_S32 }, [IFA_PROTO] = { .type = NLA_U8 }, }; struct inet_fill_args { u32 portid; u32 seq; int event; unsigned int flags; int netnsid; int ifindex; }; #define IN4_ADDR_HSIZE_SHIFT 8 #define IN4_ADDR_HSIZE (1U << IN4_ADDR_HSIZE_SHIFT) static u32 inet_addr_hash(const struct net *net, __be32 addr) { u32 val = __ipv4_addr_hash(addr, net_hash_mix(net)); return hash_32(val, IN4_ADDR_HSIZE_SHIFT); } static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa) { u32 hash = inet_addr_hash(net, ifa->ifa_local); ASSERT_RTNL(); hlist_add_head_rcu(&ifa->addr_lst, &net->ipv4.inet_addr_lst[hash]); } static void inet_hash_remove(struct in_ifaddr *ifa) { ASSERT_RTNL(); hlist_del_init_rcu(&ifa->addr_lst); } /** * __ip_dev_find - find the first device with a given source address. * @net: the net namespace * @addr: the source address * @devref: if true, take a reference on the found device * * If a caller uses devref=false, it should be protected by RCU, or RTNL */ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) { struct net_device *result = NULL; struct in_ifaddr *ifa; rcu_read_lock(); ifa = inet_lookup_ifaddr_rcu(net, addr); if (!ifa) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res = { 0 }; struct fib_table *local; /* Fallback to FIB local table so that communication * over loopback subnets work. */ local = fib_get_table(net, RT_TABLE_LOCAL); if (local && !fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) && res.type == RTN_LOCAL) result = FIB_RES_DEV(res); } else { result = ifa->ifa_dev->dev; } if (result && devref) dev_hold(result); rcu_read_unlock(); return result; } EXPORT_SYMBOL(__ip_dev_find); /* called under RCU lock */ struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr) { u32 hash = inet_addr_hash(net, addr); struct in_ifaddr *ifa; hlist_for_each_entry_rcu(ifa, &net->ipv4.inet_addr_lst[hash], addr_lst) if (ifa->ifa_local == addr) return ifa; return NULL; } static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32); static BLOCKING_NOTIFIER_HEAD(inetaddr_chain); static BLOCKING_NOTIFIER_HEAD(inetaddr_validator_chain); static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr __rcu **ifap, int destroy); #ifdef CONFIG_SYSCTL static int devinet_sysctl_register(struct in_device *idev); static void devinet_sysctl_unregister(struct in_device *idev); #else static int devinet_sysctl_register(struct in_device *idev) { return 0; } static void devinet_sysctl_unregister(struct in_device *idev) { } #endif /* Locks all the inet devices. */ static struct in_ifaddr *inet_alloc_ifa(struct in_device *in_dev) { struct in_ifaddr *ifa; ifa = kzalloc(sizeof(*ifa), GFP_KERNEL_ACCOUNT); if (!ifa) return NULL; in_dev_hold(in_dev); ifa->ifa_dev = in_dev; INIT_HLIST_NODE(&ifa->addr_lst); return ifa; } static void inet_rcu_free_ifa(struct rcu_head *head) { struct in_ifaddr *ifa = container_of(head, struct in_ifaddr, rcu_head); in_dev_put(ifa->ifa_dev); kfree(ifa); } static void inet_free_ifa(struct in_ifaddr *ifa) { /* Our reference to ifa->ifa_dev must be freed ASAP * to release the reference to the netdev the same way. * in_dev_put() -> in_dev_finish_destroy() -> netdev_put() */ call_rcu_hurry(&ifa->rcu_head, inet_rcu_free_ifa); } static void in_dev_free_rcu(struct rcu_head *head) { struct in_device *idev = container_of(head, struct in_device, rcu_head); kfree(rcu_dereference_protected(idev->mc_hash, 1)); kfree(idev); } void in_dev_finish_destroy(struct in_device *idev) { struct net_device *dev = idev->dev; WARN_ON(idev->ifa_list); WARN_ON(idev->mc_list); #ifdef NET_REFCNT_DEBUG pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL"); #endif netdev_put(dev, &idev->dev_tracker); if (!idev->dead) pr_err("Freeing alive in_device %p\n", idev); else call_rcu(&idev->rcu_head, in_dev_free_rcu); } EXPORT_SYMBOL(in_dev_finish_destroy); static struct in_device *inetdev_init(struct net_device *dev) { struct in_device *in_dev; int err = -ENOMEM; ASSERT_RTNL(); in_dev = kzalloc(sizeof(*in_dev), GFP_KERNEL); if (!in_dev) goto out; memcpy(&in_dev->cnf, dev_net(dev)->ipv4.devconf_dflt, sizeof(in_dev->cnf)); in_dev->cnf.sysctl = NULL; in_dev->dev = dev; in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl); if (!in_dev->arp_parms) goto out_kfree; if (IPV4_DEVCONF(in_dev->cnf, FORWARDING)) dev_disable_lro(dev); /* Reference in_dev->dev */ netdev_hold(dev, &in_dev->dev_tracker, GFP_KERNEL); /* Account for reference dev->ip_ptr (below) */ refcount_set(&in_dev->refcnt, 1); if (dev != blackhole_netdev) { err = devinet_sysctl_register(in_dev); if (err) { in_dev->dead = 1; neigh_parms_release(&arp_tbl, in_dev->arp_parms); in_dev_put(in_dev); in_dev = NULL; goto out; } ip_mc_init_dev(in_dev); if (dev->flags & IFF_UP) ip_mc_up(in_dev); } /* we can receive as soon as ip_ptr is set -- do this last */ rcu_assign_pointer(dev->ip_ptr, in_dev); out: return in_dev ?: ERR_PTR(err); out_kfree: kfree(in_dev); in_dev = NULL; goto out; } static void inetdev_destroy(struct in_device *in_dev) { struct net_device *dev; struct in_ifaddr *ifa; ASSERT_RTNL(); dev = in_dev->dev; in_dev->dead = 1; ip_mc_destroy_dev(in_dev); while ((ifa = rtnl_dereference(in_dev->ifa_list)) != NULL) { inet_del_ifa(in_dev, &in_dev->ifa_list, 0); inet_free_ifa(ifa); } RCU_INIT_POINTER(dev->ip_ptr, NULL); devinet_sysctl_unregister(in_dev); neigh_parms_release(&arp_tbl, in_dev->arp_parms); arp_ifdown(dev); in_dev_put(in_dev); } static int __init inet_blackhole_dev_init(void) { int err = 0; rtnl_lock(); if (!inetdev_init(blackhole_netdev)) err = -ENOMEM; rtnl_unlock(); return err; } late_initcall(inet_blackhole_dev_init); int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b) { const struct in_ifaddr *ifa; rcu_read_lock(); in_dev_for_each_ifa_rcu(ifa, in_dev) { if (inet_ifa_match(a, ifa)) { if (!b || inet_ifa_match(b, ifa)) { rcu_read_unlock(); return 1; } } } rcu_read_unlock(); return 0; } static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr __rcu **ifap, int destroy, struct nlmsghdr *nlh, u32 portid) { struct in_ifaddr *promote = NULL; struct in_ifaddr *ifa, *ifa1; struct in_ifaddr __rcu **last_prim; struct in_ifaddr *prev_prom = NULL; int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev); ASSERT_RTNL(); ifa1 = rtnl_dereference(*ifap); last_prim = ifap; if (in_dev->dead) goto no_promotions; /* 1. Deleting primary ifaddr forces deletion all secondaries * unless alias promotion is set **/ if (!(ifa1->ifa_flags & IFA_F_SECONDARY)) { struct in_ifaddr __rcu **ifap1 = &ifa1->ifa_next; while ((ifa = rtnl_dereference(*ifap1)) != NULL) { if (!(ifa->ifa_flags & IFA_F_SECONDARY) && ifa1->ifa_scope <= ifa->ifa_scope) last_prim = &ifa->ifa_next; if (!(ifa->ifa_flags & IFA_F_SECONDARY) || ifa1->ifa_mask != ifa->ifa_mask || !inet_ifa_match(ifa1->ifa_address, ifa)) { ifap1 = &ifa->ifa_next; prev_prom = ifa; continue; } if (!do_promote) { inet_hash_remove(ifa); *ifap1 = ifa->ifa_next; rtmsg_ifa(RTM_DELADDR, ifa, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa); inet_free_ifa(ifa); } else { promote = ifa; break; } } } /* On promotion all secondaries from subnet are changing * the primary IP, we must remove all their routes silently * and later to add them back with new prefsrc. Do this * while all addresses are on the device list. */ for (ifa = promote; ifa; ifa = rtnl_dereference(ifa->ifa_next)) { if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa)) fib_del_ifaddr(ifa, ifa1); } no_promotions: /* 2. Unlink it */ *ifap = ifa1->ifa_next; inet_hash_remove(ifa1); /* 3. Announce address deletion */ /* Send message first, then call notifier. At first sight, FIB update triggered by notifier will refer to already deleted ifaddr, that could confuse netlink listeners. It is not true: look, gated sees that route deleted and if it still thinks that ifaddr is valid, it will try to restore deleted routes... Grr. So that, this order is correct. */ rtmsg_ifa(RTM_DELADDR, ifa1, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1); if (promote) { struct in_ifaddr *next_sec; next_sec = rtnl_dereference(promote->ifa_next); if (prev_prom) { struct in_ifaddr *last_sec; rcu_assign_pointer(prev_prom->ifa_next, next_sec); last_sec = rtnl_dereference(*last_prim); rcu_assign_pointer(promote->ifa_next, last_sec); rcu_assign_pointer(*last_prim, promote); } promote->ifa_flags &= ~IFA_F_SECONDARY; rtmsg_ifa(RTM_NEWADDR, promote, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, promote); for (ifa = next_sec; ifa; ifa = rtnl_dereference(ifa->ifa_next)) { if (ifa1->ifa_mask != ifa->ifa_mask || !inet_ifa_match(ifa1->ifa_address, ifa)) continue; fib_add_ifaddr(ifa); } } if (destroy) inet_free_ifa(ifa1); } static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr __rcu **ifap, int destroy) { __inet_del_ifa(in_dev, ifap, destroy, NULL, 0); } static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid, struct netlink_ext_ack *extack) { struct in_ifaddr __rcu **last_primary, **ifap; struct in_device *in_dev = ifa->ifa_dev; struct net *net = dev_net(in_dev->dev); struct in_validator_info ivi; struct in_ifaddr *ifa1; int ret; ASSERT_RTNL(); ifa->ifa_flags &= ~IFA_F_SECONDARY; last_primary = &in_dev->ifa_list; /* Don't set IPv6 only flags to IPv4 addresses */ ifa->ifa_flags &= ~IPV6ONLY_FLAGS; ifap = &in_dev->ifa_list; ifa1 = rtnl_dereference(*ifap); while (ifa1) { if (!(ifa1->ifa_flags & IFA_F_SECONDARY) && ifa->ifa_scope <= ifa1->ifa_scope) last_primary = &ifa1->ifa_next; if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa)) { if (ifa1->ifa_local == ifa->ifa_local) { inet_free_ifa(ifa); return -EEXIST; } if (ifa1->ifa_scope != ifa->ifa_scope) { NL_SET_ERR_MSG(extack, "ipv4: Invalid scope value"); inet_free_ifa(ifa); return -EINVAL; } ifa->ifa_flags |= IFA_F_SECONDARY; } ifap = &ifa1->ifa_next; ifa1 = rtnl_dereference(*ifap); } /* Allow any devices that wish to register ifaddr validtors to weigh * in now, before changes are committed. The rntl lock is serializing * access here, so the state should not change between a validator call * and a final notify on commit. This isn't invoked on promotion under * the assumption that validators are checking the address itself, and * not the flags. */ ivi.ivi_addr = ifa->ifa_address; ivi.ivi_dev = ifa->ifa_dev; ivi.extack = extack; ret = blocking_notifier_call_chain(&inetaddr_validator_chain, NETDEV_UP, &ivi); ret = notifier_to_errno(ret); if (ret) { inet_free_ifa(ifa); return ret; } if (!(ifa->ifa_flags & IFA_F_SECONDARY)) ifap = last_primary; rcu_assign_pointer(ifa->ifa_next, *ifap); rcu_assign_pointer(*ifap, ifa); inet_hash_insert(dev_net(in_dev->dev), ifa); cancel_delayed_work(&net->ipv4.addr_chk_work); queue_delayed_work(system_power_efficient_wq, &net->ipv4.addr_chk_work, 0); /* Send message first, then call notifier. Notifier will trigger FIB update, so that listeners of netlink will know about new ifaddr */ rtmsg_ifa(RTM_NEWADDR, ifa, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa); return 0; } static int inet_insert_ifa(struct in_ifaddr *ifa) { if (!ifa->ifa_local) { inet_free_ifa(ifa); return 0; } return __inet_insert_ifa(ifa, NULL, 0, NULL); } static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) { struct in_device *in_dev = __in_dev_get_rtnl_net(dev); ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); if (ipv4_is_loopback(ifa->ifa_local)) ifa->ifa_scope = RT_SCOPE_HOST; return inet_insert_ifa(ifa); } /* Caller must hold RCU or RTNL : * We dont take a reference on found in_device */ struct in_device *inetdev_by_index(struct net *net, int ifindex) { struct net_device *dev; struct in_device *in_dev = NULL; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) in_dev = rcu_dereference_rtnl(dev->ip_ptr); rcu_read_unlock(); return in_dev; } EXPORT_SYMBOL(inetdev_by_index); /* Called only from RTNL semaphored context. No locks. */ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask) { struct in_ifaddr *ifa; ASSERT_RTNL(); in_dev_for_each_ifa_rtnl(ifa, in_dev) { if (ifa->ifa_mask == mask && inet_ifa_match(prefix, ifa)) return ifa; } return NULL; } static int ip_mc_autojoin_config(struct net *net, bool join, const struct in_ifaddr *ifa) { #if defined(CONFIG_IP_MULTICAST) struct ip_mreqn mreq = { .imr_multiaddr.s_addr = ifa->ifa_address, .imr_ifindex = ifa->ifa_dev->dev->ifindex, }; struct sock *sk = net->ipv4.mc_autojoin_sk; int ret; ASSERT_RTNL_NET(net); lock_sock(sk); if (join) ret = ip_mc_join_group(sk, &mreq); else ret = ip_mc_leave_group(sk, &mreq); release_sock(sk); return ret; #else return -EOPNOTSUPP; #endif } static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct in_ifaddr __rcu **ifap; struct nlattr *tb[IFA_MAX+1]; struct in_device *in_dev; struct ifaddrmsg *ifm; struct in_ifaddr *ifa; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy, extack); if (err < 0) goto out; ifm = nlmsg_data(nlh); rtnl_net_lock(net); in_dev = inetdev_by_index(net, ifm->ifa_index); if (!in_dev) { NL_SET_ERR_MSG(extack, "ipv4: Device not found"); err = -ENODEV; goto unlock; } for (ifap = &in_dev->ifa_list; (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) { if (tb[IFA_LOCAL] && ifa->ifa_local != nla_get_in_addr(tb[IFA_LOCAL])) continue; if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label)) continue; if (tb[IFA_ADDRESS] && (ifm->ifa_prefixlen != ifa->ifa_prefixlen || !inet_ifa_match(nla_get_in_addr(tb[IFA_ADDRESS]), ifa))) continue; if (ipv4_is_multicast(ifa->ifa_address)) ip_mc_autojoin_config(net, false, ifa); __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid); goto unlock; } NL_SET_ERR_MSG(extack, "ipv4: Address not found"); err = -EADDRNOTAVAIL; unlock: rtnl_net_unlock(net); out: return err; } static void check_lifetime(struct work_struct *work) { unsigned long now, next, next_sec, next_sched; struct in_ifaddr *ifa; struct hlist_node *n; struct net *net; int i; net = container_of(to_delayed_work(work), struct net, ipv4.addr_chk_work); now = jiffies; next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); for (i = 0; i < IN4_ADDR_HSIZE; i++) { struct hlist_head *head = &net->ipv4.inet_addr_lst[i]; bool change_needed = false; rcu_read_lock(); hlist_for_each_entry_rcu(ifa, head, addr_lst) { unsigned long age, tstamp; u32 preferred_lft; u32 valid_lft; u32 flags; flags = READ_ONCE(ifa->ifa_flags); if (flags & IFA_F_PERMANENT) continue; preferred_lft = READ_ONCE(ifa->ifa_preferred_lft); valid_lft = READ_ONCE(ifa->ifa_valid_lft); tstamp = READ_ONCE(ifa->ifa_tstamp); /* We try to batch several events at once. */ age = (now - tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if (valid_lft != INFINITY_LIFE_TIME && age >= valid_lft) { change_needed = true; } else if (preferred_lft == INFINITY_LIFE_TIME) { continue; } else if (age >= preferred_lft) { if (time_before(tstamp + valid_lft * HZ, next)) next = tstamp + valid_lft * HZ; if (!(flags & IFA_F_DEPRECATED)) change_needed = true; } else if (time_before(tstamp + preferred_lft * HZ, next)) { next = tstamp + preferred_lft * HZ; } } rcu_read_unlock(); if (!change_needed) continue; rtnl_net_lock(net); hlist_for_each_entry_safe(ifa, n, head, addr_lst) { unsigned long age; if (ifa->ifa_flags & IFA_F_PERMANENT) continue; /* We try to batch several events at once. */ age = (now - ifa->ifa_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_valid_lft) { struct in_ifaddr __rcu **ifap; struct in_ifaddr *tmp; ifap = &ifa->ifa_dev->ifa_list; tmp = rtnl_net_dereference(net, *ifap); while (tmp) { if (tmp == ifa) { inet_del_ifa(ifa->ifa_dev, ifap, 1); break; } ifap = &tmp->ifa_next; tmp = rtnl_net_dereference(net, *ifap); } } else if (ifa->ifa_preferred_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_preferred_lft && !(ifa->ifa_flags & IFA_F_DEPRECATED)) { ifa->ifa_flags |= IFA_F_DEPRECATED; rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); } } rtnl_net_unlock(net); } next_sec = round_jiffies_up(next); next_sched = next; /* If rounded timeout is accurate enough, accept it. */ if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ)) next_sched = next_sec; now = jiffies; /* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */ if (time_before(next_sched, now + ADDRCONF_TIMER_FUZZ_MAX)) next_sched = now + ADDRCONF_TIMER_FUZZ_MAX; queue_delayed_work(system_power_efficient_wq, &net->ipv4.addr_chk_work, next_sched - now); } static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft, __u32 prefered_lft) { unsigned long timeout; u32 flags; flags = ifa->ifa_flags & ~(IFA_F_PERMANENT | IFA_F_DEPRECATED); timeout = addrconf_timeout_fixup(valid_lft, HZ); if (addrconf_finite_timeout(timeout)) WRITE_ONCE(ifa->ifa_valid_lft, timeout); else flags |= IFA_F_PERMANENT; timeout = addrconf_timeout_fixup(prefered_lft, HZ); if (addrconf_finite_timeout(timeout)) { if (timeout == 0) flags |= IFA_F_DEPRECATED; WRITE_ONCE(ifa->ifa_preferred_lft, timeout); } WRITE_ONCE(ifa->ifa_flags, flags); WRITE_ONCE(ifa->ifa_tstamp, jiffies); if (!ifa->ifa_cstamp) WRITE_ONCE(ifa->ifa_cstamp, ifa->ifa_tstamp); } static int inet_validate_rtm(struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack, __u32 *valid_lft, __u32 *prefered_lft) { struct ifaddrmsg *ifm = nlmsg_data(nlh); int err; err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy, extack); if (err < 0) return err; if (ifm->ifa_prefixlen > 32) { NL_SET_ERR_MSG(extack, "ipv4: Invalid prefix length"); return -EINVAL; } if (!tb[IFA_LOCAL]) { NL_SET_ERR_MSG(extack, "ipv4: Local address is not supplied"); return -EINVAL; } if (tb[IFA_CACHEINFO]) { struct ifa_cacheinfo *ci; ci = nla_data(tb[IFA_CACHEINFO]); if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) { NL_SET_ERR_MSG(extack, "ipv4: address lifetime invalid"); return -EINVAL; } *valid_lft = ci->ifa_valid; *prefered_lft = ci->ifa_prefered; } return 0; } static struct in_ifaddr *inet_rtm_to_ifa(struct net *net, struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct ifaddrmsg *ifm = nlmsg_data(nlh); struct in_device *in_dev; struct net_device *dev; struct in_ifaddr *ifa; int err; dev = __dev_get_by_index(net, ifm->ifa_index); err = -ENODEV; if (!dev) { NL_SET_ERR_MSG(extack, "ipv4: Device not found"); goto errout; } in_dev = __in_dev_get_rtnl_net(dev); err = -ENOBUFS; if (!in_dev) goto errout; ifa = inet_alloc_ifa(in_dev); if (!ifa) /* * A potential indev allocation can be left alive, it stays * assigned to its device and is destroy with it. */ goto errout; ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); if (!tb[IFA_ADDRESS]) tb[IFA_ADDRESS] = tb[IFA_LOCAL]; ifa->ifa_prefixlen = ifm->ifa_prefixlen; ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen); ifa->ifa_flags = nla_get_u32_default(tb[IFA_FLAGS], ifm->ifa_flags); ifa->ifa_scope = ifm->ifa_scope; ifa->ifa_local = nla_get_in_addr(tb[IFA_LOCAL]); ifa->ifa_address = nla_get_in_addr(tb[IFA_ADDRESS]); if (tb[IFA_BROADCAST]) ifa->ifa_broadcast = nla_get_in_addr(tb[IFA_BROADCAST]); if (tb[IFA_LABEL]) nla_strscpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); if (tb[IFA_RT_PRIORITY]) ifa->ifa_rt_priority = nla_get_u32(tb[IFA_RT_PRIORITY]); if (tb[IFA_PROTO]) ifa->ifa_proto = nla_get_u8(tb[IFA_PROTO]); return ifa; errout: return ERR_PTR(err); } static struct in_ifaddr *find_matching_ifa(struct net *net, struct in_ifaddr *ifa) { struct in_device *in_dev = ifa->ifa_dev; struct in_ifaddr *ifa1; in_dev_for_each_ifa_rtnl_net(net, ifa1, in_dev) { if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa) && ifa1->ifa_local == ifa->ifa_local) return ifa1; } return NULL; } static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { __u32 prefered_lft = INFINITY_LIFE_TIME; __u32 valid_lft = INFINITY_LIFE_TIME; struct net *net = sock_net(skb->sk); struct in_ifaddr *ifa_existing; struct nlattr *tb[IFA_MAX + 1]; struct in_ifaddr *ifa; int ret; ret = inet_validate_rtm(nlh, tb, extack, &valid_lft, &prefered_lft); if (ret < 0) return ret; if (!nla_get_in_addr(tb[IFA_LOCAL])) return 0; rtnl_net_lock(net); ifa = inet_rtm_to_ifa(net, nlh, tb, extack); if (IS_ERR(ifa)) { ret = PTR_ERR(ifa); goto unlock; } ifa_existing = find_matching_ifa(net, ifa); if (!ifa_existing) { /* It would be best to check for !NLM_F_CREATE here but * userspace already relies on not having to provide this. */ set_ifa_lifetime(ifa, valid_lft, prefered_lft); if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) { ret = ip_mc_autojoin_config(net, true, ifa); if (ret < 0) { NL_SET_ERR_MSG(extack, "ipv4: Multicast auto join failed"); inet_free_ifa(ifa); goto unlock; } } ret = __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid, extack); } else { u32 new_metric = ifa->ifa_rt_priority; u8 new_proto = ifa->ifa_proto; inet_free_ifa(ifa); if (nlh->nlmsg_flags & NLM_F_EXCL || !(nlh->nlmsg_flags & NLM_F_REPLACE)) { NL_SET_ERR_MSG(extack, "ipv4: Address already assigned"); ret = -EEXIST; goto unlock; } ifa = ifa_existing; if (ifa->ifa_rt_priority != new_metric) { fib_modify_prefix_metric(ifa, new_metric); ifa->ifa_rt_priority = new_metric; } ifa->ifa_proto = new_proto; set_ifa_lifetime(ifa, valid_lft, prefered_lft); cancel_delayed_work(&net->ipv4.addr_chk_work); queue_delayed_work(system_power_efficient_wq, &net->ipv4.addr_chk_work, 0); rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid); } unlock: rtnl_net_unlock(net); return ret; } /* * Determine a default network mask, based on the IP address. */ static int inet_abc_len(__be32 addr) { int rc = -1; /* Something else, probably a multicast. */ if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) rc = 0; else { __u32 haddr = ntohl(addr); if (IN_CLASSA(haddr)) rc = 8; else if (IN_CLASSB(haddr)) rc = 16; else if (IN_CLASSC(haddr)) rc = 24; else if (IN_CLASSE(haddr)) rc = 32; } return rc; } int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) { struct sockaddr_in sin_orig; struct sockaddr_in *sin = (struct sockaddr_in *)&ifr->ifr_addr; struct in_ifaddr __rcu **ifap = NULL; struct in_device *in_dev; struct in_ifaddr *ifa = NULL; struct net_device *dev; char *colon; int ret = -EFAULT; int tryaddrmatch = 0; ifr->ifr_name[IFNAMSIZ - 1] = 0; /* save original address for comparison */ memcpy(&sin_orig, sin, sizeof(*sin)); colon = strchr(ifr->ifr_name, ':'); if (colon) *colon = 0; dev_load(net, ifr->ifr_name); switch (cmd) { case SIOCGIFADDR: /* Get interface address */ case SIOCGIFBRDADDR: /* Get the broadcast address */ case SIOCGIFDSTADDR: /* Get the destination address */ case SIOCGIFNETMASK: /* Get the netmask for the interface */ /* Note that these ioctls will not sleep, so that we do not impose a lock. One day we will be forced to put shlock here (I mean SMP) */ tryaddrmatch = (sin_orig.sin_family == AF_INET); memset(sin, 0, sizeof(*sin)); sin->sin_family = AF_INET; break; case SIOCSIFFLAGS: ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto out; break; case SIOCSIFADDR: /* Set interface address (and family) */ case SIOCSIFBRDADDR: /* Set the broadcast address */ case SIOCSIFDSTADDR: /* Set the destination address */ case SIOCSIFNETMASK: /* Set the netmask for the interface */ ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto out; ret = -EINVAL; if (sin->sin_family != AF_INET) goto out; break; default: ret = -EINVAL; goto out; } rtnl_net_lock(net); ret = -ENODEV; dev = __dev_get_by_name(net, ifr->ifr_name); if (!dev) goto done; if (colon) *colon = ':'; in_dev = __in_dev_get_rtnl_net(dev); if (in_dev) { if (tryaddrmatch) { /* Matthias Andree */ /* compare label and address (4.4BSD style) */ /* note: we only do this for a limited set of ioctls and only if the original address family was AF_INET. This is checked above. */ for (ifap = &in_dev->ifa_list; (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) { if (!strcmp(ifr->ifr_name, ifa->ifa_label) && sin_orig.sin_addr.s_addr == ifa->ifa_local) { break; /* found */ } } } /* we didn't get a match, maybe the application is 4.3BSD-style and passed in junk so we fall back to comparing just the label */ if (!ifa) { for (ifap = &in_dev->ifa_list; (ifa = rtnl_net_dereference(net, *ifap)) != NULL; ifap = &ifa->ifa_next) if (!strcmp(ifr->ifr_name, ifa->ifa_label)) break; } } ret = -EADDRNOTAVAIL; if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS) goto done; switch (cmd) { case SIOCGIFADDR: /* Get interface address */ ret = 0; sin->sin_addr.s_addr = ifa->ifa_local; break; case SIOCGIFBRDADDR: /* Get the broadcast address */ ret = 0; sin->sin_addr.s_addr = ifa->ifa_broadcast; break; case SIOCGIFDSTADDR: /* Get the destination address */ ret = 0; sin->sin_addr.s_addr = ifa->ifa_address; break; case SIOCGIFNETMASK: /* Get the netmask for the interface */ ret = 0; sin->sin_addr.s_addr = ifa->ifa_mask; break; case SIOCSIFFLAGS: if (colon) { ret = -EADDRNOTAVAIL; if (!ifa) break; ret = 0; if (!(ifr->ifr_flags & IFF_UP)) inet_del_ifa(in_dev, ifap, 1); break; } /* NETDEV_UP/DOWN/CHANGE could touch a peer dev */ ASSERT_RTNL(); ret = dev_change_flags(dev, ifr->ifr_flags, NULL); break; case SIOCSIFADDR: /* Set interface address (and family) */ ret = -EINVAL; if (inet_abc_len(sin->sin_addr.s_addr) < 0) break; if (!ifa) { ret = -ENOBUFS; if (!in_dev) break; ifa = inet_alloc_ifa(in_dev); if (!ifa) break; if (colon) memcpy(ifa->ifa_label, ifr->ifr_name, IFNAMSIZ); else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); } else { ret = 0; if (ifa->ifa_local == sin->sin_addr.s_addr) break; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_broadcast = 0; ifa->ifa_scope = 0; } ifa->ifa_address = ifa->ifa_local = sin->sin_addr.s_addr; if (!(dev->flags & IFF_POINTOPOINT)) { ifa->ifa_prefixlen = inet_abc_len(ifa->ifa_address); ifa->ifa_mask = inet_make_mask(ifa->ifa_prefixlen); if ((dev->flags & IFF_BROADCAST) && ifa->ifa_prefixlen < 31) ifa->ifa_broadcast = ifa->ifa_address | ~ifa->ifa_mask; } else { ifa->ifa_prefixlen = 32; ifa->ifa_mask = inet_make_mask(32); } set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); ret = inet_set_ifa(dev, ifa); break; case SIOCSIFBRDADDR: /* Set the broadcast address */ ret = 0; if (ifa->ifa_broadcast != sin->sin_addr.s_addr) { inet_del_ifa(in_dev, ifap, 0); ifa->ifa_broadcast = sin->sin_addr.s_addr; inet_insert_ifa(ifa); } break; case SIOCSIFDSTADDR: /* Set the destination address */ ret = 0; if (ifa->ifa_address == sin->sin_addr.s_addr) break; ret = -EINVAL; if (inet_abc_len(sin->sin_addr.s_addr) < 0) break; ret = 0; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_address = sin->sin_addr.s_addr; inet_insert_ifa(ifa); break; case SIOCSIFNETMASK: /* Set the netmask for the interface */ /* * The mask we set must be legal. */ ret = -EINVAL; if (bad_mask(sin->sin_addr.s_addr, 0)) break; ret = 0; if (ifa->ifa_mask != sin->sin_addr.s_addr) { __be32 old_mask = ifa->ifa_mask; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_mask = sin->sin_addr.s_addr; ifa->ifa_prefixlen = inet_mask_len(ifa->ifa_mask); /* See if current broadcast address matches * with current netmask, then recalculate * the broadcast address. Otherwise it's a * funny address, so don't touch it since * the user seems to know what (s)he's doing... */ if ((dev->flags & IFF_BROADCAST) && (ifa->ifa_prefixlen < 31) && (ifa->ifa_broadcast == (ifa->ifa_local|~old_mask))) { ifa->ifa_broadcast = (ifa->ifa_local | ~sin->sin_addr.s_addr); } inet_insert_ifa(ifa); } break; } done: rtnl_net_unlock(net); out: return ret; } int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { struct in_device *in_dev = __in_dev_get_rtnl_net(dev); const struct in_ifaddr *ifa; struct ifreq ifr; int done = 0; if (WARN_ON(size > sizeof(struct ifreq))) goto out; if (!in_dev) goto out; in_dev_for_each_ifa_rtnl_net(dev_net(dev), ifa, in_dev) { if (!buf) { done += size; continue; } if (len < size) break; memset(&ifr, 0, sizeof(struct ifreq)); strcpy(ifr.ifr_name, ifa->ifa_label); (*(struct sockaddr_in *)&ifr.ifr_addr).sin_family = AF_INET; (*(struct sockaddr_in *)&ifr.ifr_addr).sin_addr.s_addr = ifa->ifa_local; if (copy_to_user(buf + done, &ifr, size)) { done = -EFAULT; break; } len -= size; done += size; } out: return done; } static __be32 in_dev_select_addr(const struct in_device *in_dev, int scope) { const struct in_ifaddr *ifa; in_dev_for_each_ifa_rcu(ifa, in_dev) { if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) continue; if (ifa->ifa_scope != RT_SCOPE_LINK && ifa->ifa_scope <= scope) return ifa->ifa_local; } return 0; } __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) { const struct in_ifaddr *ifa; __be32 addr = 0; unsigned char localnet_scope = RT_SCOPE_HOST; struct in_device *in_dev; struct net *net = dev_net(dev); int master_idx; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto no_in_dev; if (unlikely(IN_DEV_ROUTE_LOCALNET(in_dev))) localnet_scope = RT_SCOPE_LINK; in_dev_for_each_ifa_rcu(ifa, in_dev) { if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) continue; if (min(ifa->ifa_scope, localnet_scope) > scope) continue; if (!dst || inet_ifa_match(dst, ifa)) { addr = ifa->ifa_local; break; } if (!addr) addr = ifa->ifa_local; } if (addr) goto out_unlock; no_in_dev: master_idx = l3mdev_master_ifindex_rcu(dev); /* For VRFs, the VRF device takes the place of the loopback device, * with addresses on it being preferred. Note in such cases the * loopback device will be among the devices that fail the master_idx * equality check in the loop below. */ if (master_idx && (dev = dev_get_by_index_rcu(net, master_idx)) && (in_dev = __in_dev_get_rcu(dev))) { addr = in_dev_select_addr(in_dev, scope); if (addr) goto out_unlock; } /* Not loopback addresses on loopback should be preferred in this case. It is important that lo is the first interface in dev_base list. */ for_each_netdev_rcu(net, dev) { if (l3mdev_master_ifindex_rcu(dev) != master_idx) continue; in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; addr = in_dev_select_addr(in_dev, scope); if (addr) goto out_unlock; } out_unlock: rcu_read_unlock(); return addr; } EXPORT_SYMBOL(inet_select_addr); static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, __be32 local, int scope) { unsigned char localnet_scope = RT_SCOPE_HOST; const struct in_ifaddr *ifa; __be32 addr = 0; int same = 0; if (unlikely(IN_DEV_ROUTE_LOCALNET(in_dev))) localnet_scope = RT_SCOPE_LINK; in_dev_for_each_ifa_rcu(ifa, in_dev) { unsigned char min_scope = min(ifa->ifa_scope, localnet_scope); if (!addr && (local == ifa->ifa_local || !local) && min_scope <= scope) { addr = ifa->ifa_local; if (same) break; } if (!same) { same = (!local || inet_ifa_match(local, ifa)) && (!dst || inet_ifa_match(dst, ifa)); if (same && addr) { if (local || !dst) break; /* Is the selected addr into dst subnet? */ if (inet_ifa_match(addr, ifa)) break; /* No, then can we use new local src? */ if (min_scope <= scope) { addr = ifa->ifa_local; break; } /* search for large dst subnet for addr */ same = 0; } } } return same ? addr : 0; } /* * Confirm that local IP address exists using wildcards: * - net: netns to check, cannot be NULL * - in_dev: only on this interface, NULL=any interface * - dst: only in the same subnet as dst, 0=any dst * - local: address, 0=autoselect the local address * - scope: maximum allowed scope value for the local address */ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope) { __be32 addr = 0; struct net_device *dev; if (in_dev) return confirm_addr_indev(in_dev, dst, local, scope); rcu_read_lock(); for_each_netdev_rcu(net, dev) { in_dev = __in_dev_get_rcu(dev); if (in_dev) { addr = confirm_addr_indev(in_dev, dst, local, scope); if (addr) break; } } rcu_read_unlock(); return addr; } EXPORT_SYMBOL(inet_confirm_addr); /* * Device notifier */ int register_inetaddr_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&inetaddr_chain, nb); } EXPORT_SYMBOL(register_inetaddr_notifier); int unregister_inetaddr_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&inetaddr_chain, nb); } EXPORT_SYMBOL(unregister_inetaddr_notifier); int register_inetaddr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&inetaddr_validator_chain, nb); } EXPORT_SYMBOL(register_inetaddr_validator_notifier); int unregister_inetaddr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&inetaddr_validator_chain, nb); } EXPORT_SYMBOL(unregister_inetaddr_validator_notifier); /* Rename ifa_labels for a device name change. Make some effort to preserve * existing alias numbering and to create unique labels if possible. */ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev) { struct in_ifaddr *ifa; int named = 0; in_dev_for_each_ifa_rtnl(ifa, in_dev) { char old[IFNAMSIZ], *dot; memcpy(old, ifa->ifa_label, IFNAMSIZ); memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); if (named++ == 0) goto skip; dot = strchr(old, ':'); if (!dot) { sprintf(old, ":%d", named); dot = old; } if (strlen(dot) + strlen(dev->name) < IFNAMSIZ) strcat(ifa->ifa_label, dot); else strcpy(ifa->ifa_label + (IFNAMSIZ - strlen(dot) - 1), dot); skip: rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); } } static void inetdev_send_gratuitous_arp(struct net_device *dev, struct in_device *in_dev) { const struct in_ifaddr *ifa; in_dev_for_each_ifa_rtnl(ifa, in_dev) { arp_send(ARPOP_REQUEST, ETH_P_ARP, ifa->ifa_local, dev, ifa->ifa_local, NULL, dev->dev_addr, NULL); } } /* Called only under RTNL semaphore */ static int inetdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct in_device *in_dev = __in_dev_get_rtnl(dev); ASSERT_RTNL(); if (!in_dev) { if (event == NETDEV_REGISTER) { in_dev = inetdev_init(dev); if (IS_ERR(in_dev)) return notifier_from_errno(PTR_ERR(in_dev)); if (dev->flags & IFF_LOOPBACK) { IN_DEV_CONF_SET(in_dev, NOXFRM, 1); IN_DEV_CONF_SET(in_dev, NOPOLICY, 1); } } else if (event == NETDEV_CHANGEMTU) { /* Re-enabling IP */ if (inetdev_valid_mtu(dev->mtu)) in_dev = inetdev_init(dev); } goto out; } switch (event) { case NETDEV_REGISTER: pr_debug("%s: bug\n", __func__); RCU_INIT_POINTER(dev->ip_ptr, NULL); break; case NETDEV_UP: if (!inetdev_valid_mtu(dev->mtu)) break; if (dev->flags & IFF_LOOPBACK) { struct in_ifaddr *ifa = inet_alloc_ifa(in_dev); if (ifa) { ifa->ifa_local = ifa->ifa_address = htonl(INADDR_LOOPBACK); ifa->ifa_prefixlen = 8; ifa->ifa_mask = inet_make_mask(8); ifa->ifa_scope = RT_SCOPE_HOST; memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); inet_insert_ifa(ifa); } } ip_mc_up(in_dev); fallthrough; case NETDEV_CHANGEADDR: if (!IN_DEV_ARP_NOTIFY(in_dev)) break; fallthrough; case NETDEV_NOTIFY_PEERS: /* Send gratuitous ARP to notify of link change */ inetdev_send_gratuitous_arp(dev, in_dev); break; case NETDEV_DOWN: ip_mc_down(in_dev); break; case NETDEV_PRE_TYPE_CHANGE: ip_mc_unmap(in_dev); break; case NETDEV_POST_TYPE_CHANGE: ip_mc_remap(in_dev); break; case NETDEV_CHANGEMTU: if (inetdev_valid_mtu(dev->mtu)) break; /* disable IP when MTU is not enough */ fallthrough; case NETDEV_UNREGISTER: inetdev_destroy(in_dev); break; case NETDEV_CHANGENAME: /* Do not notify about label change, this event is * not interesting to applications using netlink. */ inetdev_changename(dev, in_dev); devinet_sysctl_unregister(in_dev); devinet_sysctl_register(in_dev); break; } out: return NOTIFY_DONE; } static struct notifier_block ip_netdev_notifier = { .notifier_call = inetdev_event, }; static size_t inet_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(4) /* IFA_ADDRESS */ + nla_total_size(4) /* IFA_LOCAL */ + nla_total_size(4) /* IFA_BROADCAST */ + nla_total_size(IFNAMSIZ) /* IFA_LABEL */ + nla_total_size(4) /* IFA_FLAGS */ + nla_total_size(1) /* IFA_PROTO */ + nla_total_size(4) /* IFA_RT_PRIORITY */ + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */ } static inline u32 cstamp_delta(unsigned long cstamp) { return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; } static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, unsigned long tstamp, u32 preferred, u32 valid) { struct ifa_cacheinfo ci; ci.cstamp = cstamp_delta(cstamp); ci.tstamp = cstamp_delta(tstamp); ci.ifa_prefered = preferred; ci.ifa_valid = valid; return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci); } static int inet_fill_ifaddr(struct sk_buff *skb, const struct in_ifaddr *ifa, struct inet_fill_args *args) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; unsigned long tstamp; u32 preferred, valid; u32 flags; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(*ifm), args->flags); if (!nlh) return -EMSGSIZE; ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = ifa->ifa_prefixlen; flags = READ_ONCE(ifa->ifa_flags); /* Warning : ifm->ifa_flags is an __u8, it holds only 8 bits. * The 32bit value is given in IFA_FLAGS attribute. */ ifm->ifa_flags = (__u8)flags; ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; if (args->netnsid >= 0 && nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) goto nla_put_failure; tstamp = READ_ONCE(ifa->ifa_tstamp); if (!(flags & IFA_F_PERMANENT)) { preferred = READ_ONCE(ifa->ifa_preferred_lft); valid = READ_ONCE(ifa->ifa_valid_lft); if (preferred != INFINITY_LIFE_TIME) { long tval = (jiffies - tstamp) / HZ; if (preferred > tval) preferred -= tval; else preferred = 0; if (valid != INFINITY_LIFE_TIME) { if (valid > tval) valid -= tval; else valid = 0; } } } else { preferred = INFINITY_LIFE_TIME; valid = INFINITY_LIFE_TIME; } if ((ifa->ifa_address && nla_put_in_addr(skb, IFA_ADDRESS, ifa->ifa_address)) || (ifa->ifa_local && nla_put_in_addr(skb, IFA_LOCAL, ifa->ifa_local)) || (ifa->ifa_broadcast && nla_put_in_addr(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || (ifa->ifa_label[0] && nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || (ifa->ifa_proto && nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) || nla_put_u32(skb, IFA_FLAGS, flags) || (ifa->ifa_rt_priority && nla_put_u32(skb, IFA_RT_PRIORITY, ifa->ifa_rt_priority)) || put_cacheinfo(skb, READ_ONCE(ifa->ifa_cstamp), tstamp, preferred, valid)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int inet_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, struct inet_fill_args *fillargs, struct net **tgt_net, struct sock *sk, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[IFA_MAX+1]; struct ifaddrmsg *ifm; int err, i; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for address dump request"); return -EINVAL; } ifm = nlmsg_data(nlh); if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for address dump request"); return -EINVAL; } fillargs->ifindex = ifm->ifa_index; if (fillargs->ifindex) { cb->answer_flags |= NLM_F_DUMP_FILTERED; fillargs->flags |= NLM_F_DUMP_FILTERED; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy, extack); if (err < 0) return err; for (i = 0; i <= IFA_MAX; ++i) { if (!tb[i]) continue; if (i == IFA_TARGET_NETNSID) { struct net *net; fillargs->netnsid = nla_get_s32(tb[i]); net = rtnl_get_net_ns_capable(sk, fillargs->netnsid); if (IS_ERR(net)) { fillargs->netnsid = -1; NL_SET_ERR_MSG(extack, "ipv4: Invalid target network namespace id"); return PTR_ERR(net); } *tgt_net = net; } else { NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in dump request"); return -EINVAL; } } return 0; } static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, struct netlink_callback *cb, int *s_ip_idx, struct inet_fill_args *fillargs) { struct in_ifaddr *ifa; int ip_idx = 0; int err; in_dev_for_each_ifa_rcu(ifa, in_dev) { if (ip_idx < *s_ip_idx) { ip_idx++; continue; } err = inet_fill_ifaddr(skb, ifa, fillargs); if (err < 0) goto done; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); ip_idx++; } err = 0; ip_idx = 0; done: *s_ip_idx = ip_idx; return err; } /* Combine dev_addr_genid and dev_base_seq to detect changes. */ static u32 inet_base_seq(const struct net *net) { u32 res = atomic_read(&net->ipv4.dev_addr_genid) + READ_ONCE(net->dev_base_seq); /* Must not return 0 (see nl_dump_check_consistent()). * Chose a value far away from 0. */ if (!res) res = 0x80000000; return res; } static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct inet_fill_args fillargs = { .portid = NETLINK_CB(cb->skb).portid, .seq = nlh->nlmsg_seq, .event = RTM_NEWADDR, .flags = NLM_F_MULTI, .netnsid = -1, }; struct net *net = sock_net(skb->sk); struct net *tgt_net = net; struct { unsigned long ifindex; int ip_idx; } *ctx = (void *)cb->ctx; struct in_device *in_dev; struct net_device *dev; int err = 0; rcu_read_lock(); if (cb->strict_check) { err = inet_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net, skb->sk, cb); if (err < 0) goto done; if (fillargs.ifindex) { dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); if (!dev) { err = -ENODEV; goto done; } in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto done; err = in_dev_dump_addr(in_dev, skb, cb, &ctx->ip_idx, &fillargs); goto done; } } cb->seq = inet_base_seq(tgt_net); for_each_netdev_dump(tgt_net, dev, ctx->ifindex) { in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; err = in_dev_dump_addr(in_dev, skb, cb, &ctx->ip_idx, &fillargs); if (err < 0) goto done; } done: if (fillargs.netnsid >= 0) put_net(tgt_net); rcu_read_unlock(); return err; } static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid) { struct inet_fill_args fillargs = { .portid = portid, .seq = nlh ? nlh->nlmsg_seq : 0, .event = event, .flags = 0, .netnsid = -1, }; struct sk_buff *skb; int err = -ENOBUFS; struct net *net; net = dev_net(ifa->ifa_dev->dev); skb = nlmsg_new(inet_nlmsg_size(), GFP_KERNEL); if (!skb) goto errout; err = inet_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, portid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); } static size_t inet_get_link_af_size(const struct net_device *dev, u32 ext_filter_mask) { struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); if (!in_dev) return 0; return nla_total_size(IPV4_DEVCONF_MAX * 4); /* IFLA_INET_CONF */ } static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev, u32 ext_filter_mask) { struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); struct nlattr *nla; int i; if (!in_dev) return -ENODATA; nla = nla_reserve(skb, IFLA_INET_CONF, IPV4_DEVCONF_MAX * 4); if (!nla) return -EMSGSIZE; for (i = 0; i < IPV4_DEVCONF_MAX; i++) ((u32 *) nla_data(nla))[i] = READ_ONCE(in_dev->cnf.data[i]); return 0; } static const struct nla_policy inet_af_policy[IFLA_INET_MAX+1] = { [IFLA_INET_CONF] = { .type = NLA_NESTED }, }; static int inet_validate_link_af(const struct net_device *dev, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct nlattr *a, *tb[IFLA_INET_MAX+1]; int err, rem; if (dev && !__in_dev_get_rtnl(dev)) return -EAFNOSUPPORT; err = nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, inet_af_policy, extack); if (err < 0) return err; if (tb[IFLA_INET_CONF]) { nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) { int cfgid = nla_type(a); if (nla_len(a) < 4) return -EINVAL; if (cfgid <= 0 || cfgid > IPV4_DEVCONF_MAX) return -EINVAL; } } return 0; } static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct in_device *in_dev = __in_dev_get_rtnl(dev); struct nlattr *a, *tb[IFLA_INET_MAX+1]; int rem; if (!in_dev) return -EAFNOSUPPORT; if (nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0) return -EINVAL; if (tb[IFLA_INET_CONF]) { nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) ipv4_devconf_set(in_dev, nla_type(a), nla_get_u32(a)); } return 0; } static int inet_netconf_msgsize_devconf(int type) { int size = NLMSG_ALIGN(sizeof(struct netconfmsg)) + nla_total_size(4); /* NETCONFA_IFINDEX */ bool all = false; if (type == NETCONFA_ALL) all = true; if (all || type == NETCONFA_FORWARDING) size += nla_total_size(4); if (all || type == NETCONFA_RP_FILTER) size += nla_total_size(4); if (all || type == NETCONFA_MC_FORWARDING) size += nla_total_size(4); if (all || type == NETCONFA_BC_FORWARDING) size += nla_total_size(4); if (all || type == NETCONFA_PROXY_NEIGH) size += nla_total_size(4); if (all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) size += nla_total_size(4); return size; } static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, const struct ipv4_devconf *devconf, u32 portid, u32 seq, int event, unsigned int flags, int type) { struct nlmsghdr *nlh; struct netconfmsg *ncm; bool all = false; nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), flags); if (!nlh) return -EMSGSIZE; if (type == NETCONFA_ALL) all = true; ncm = nlmsg_data(nlh); ncm->ncm_family = AF_INET; if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0) goto nla_put_failure; if (!devconf) goto out; if ((all || type == NETCONFA_FORWARDING) && nla_put_s32(skb, NETCONFA_FORWARDING, IPV4_DEVCONF_RO(*devconf, FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_RP_FILTER) && nla_put_s32(skb, NETCONFA_RP_FILTER, IPV4_DEVCONF_RO(*devconf, RP_FILTER)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_MC_FORWARDING) && nla_put_s32(skb, NETCONFA_MC_FORWARDING, IPV4_DEVCONF_RO(*devconf, MC_FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_BC_FORWARDING) && nla_put_s32(skb, NETCONFA_BC_FORWARDING, IPV4_DEVCONF_RO(*devconf, BC_FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_PROXY_NEIGH) && nla_put_s32(skb, NETCONFA_PROXY_NEIGH, IPV4_DEVCONF_RO(*devconf, PROXY_ARP)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, IPV4_DEVCONF_RO(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0) goto nla_put_failure; out: nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf) { struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(inet_netconf_msgsize_devconf(type), GFP_KERNEL); if (!skb) goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, event, 0, type); if (err < 0) { /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV4_NETCONF, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err); } static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = { [NETCONFA_IFINDEX] = { .len = sizeof(int) }, [NETCONFA_FORWARDING] = { .len = sizeof(int) }, [NETCONFA_RP_FILTER] = { .len = sizeof(int) }, [NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) }, [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) }, }; static int inet_netconf_valid_get_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct netconfmsg))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for netconf get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_ipv4_policy, extack); err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_ipv4_policy, extack); if (err) return err; for (i = 0; i <= NETCONFA_MAX; i++) { if (!tb[i]) continue; switch (i) { case NETCONFA_IFINDEX: break; default: NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in netconf get request"); return -EINVAL; } } return 0; } static int inet_netconf_get_devconf(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX + 1]; const struct ipv4_devconf *devconf; struct in_device *in_dev = NULL; struct net_device *dev = NULL; struct sk_buff *skb; int ifindex; int err; err = inet_netconf_valid_get_req(in_skb, nlh, tb, extack); if (err) return err; if (!tb[NETCONFA_IFINDEX]) return -EINVAL; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); switch (ifindex) { case NETCONFA_IFINDEX_ALL: devconf = net->ipv4.devconf_all; break; case NETCONFA_IFINDEX_DEFAULT: devconf = net->ipv4.devconf_dflt; break; default: err = -ENODEV; dev = dev_get_by_index(net, ifindex); if (dev) in_dev = in_dev_get(dev); if (!in_dev) goto errout; devconf = &in_dev->cnf; break; } err = -ENOBUFS; skb = nlmsg_new(inet_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); if (!skb) goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, 0, NETCONFA_ALL); if (err < 0) { /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: if (in_dev) in_dev_put(in_dev); dev_put(dev); return err; } static int inet_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct { unsigned long ifindex; unsigned int all_default; } *ctx = (void *)cb->ctx; const struct in_device *in_dev; struct net_device *dev; int err = 0; if (cb->strict_check) { struct netlink_ext_ack *extack = cb->extack; struct netconfmsg *ncm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ncm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for netconf dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ncm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid data after header in netconf dump request"); return -EINVAL; } } rcu_read_lock(); for_each_netdev_dump(net, dev, ctx->ifindex) { in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; err = inet_netconf_fill_devconf(skb, dev->ifindex, &in_dev->cnf, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) goto done; } if (ctx->all_default == 0) { err = inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) goto done; ctx->all_default++; } if (ctx->all_default == 1) { err = inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) goto done; ctx->all_default++; } done: rcu_read_unlock(); return err; } #ifdef CONFIG_SYSCTL static void devinet_copy_dflt_conf(struct net *net, int i) { struct net_device *dev; rcu_read_lock(); for_each_netdev_rcu(net, dev) { struct in_device *in_dev; in_dev = __in_dev_get_rcu(dev); if (in_dev && !test_bit(i, in_dev->cnf.state)) in_dev->cnf.data[i] = net->ipv4.devconf_dflt->data[i]; } rcu_read_unlock(); } /* called with RTNL locked */ static void inet_forward_change(struct net *net) { struct net_device *dev; int on = IPV4_DEVCONF_ALL(net, FORWARDING); IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on; IPV4_DEVCONF_DFLT(net, FORWARDING) = on; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt); for_each_netdev(net, dev) { struct in_device *in_dev; if (on) dev_disable_lro(dev); in_dev = __in_dev_get_rtnl_net(dev); if (in_dev) { IN_DEV_CONF_SET(in_dev, FORWARDING, on); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, dev->ifindex, &in_dev->cnf); } } } static int devinet_conf_ifindex(struct net *net, struct ipv4_devconf *cnf) { if (cnf == net->ipv4.devconf_dflt) return NETCONFA_IFINDEX_DEFAULT; else if (cnf == net->ipv4.devconf_all) return NETCONFA_IFINDEX_ALL; else { struct in_device *idev = container_of(cnf, struct in_device, cnf); return idev->dev->ifindex; } } static int devinet_conf_proc(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_value = *(int *)ctl->data; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); int new_value = *(int *)ctl->data; if (write) { struct ipv4_devconf *cnf = ctl->extra1; struct net *net = ctl->extra2; int i = (int *)ctl->data - cnf->data; int ifindex; set_bit(i, cnf->state); if (cnf == net->ipv4.devconf_dflt) devinet_copy_dflt_conf(net, i); if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1 || i == IPV4_DEVCONF_ROUTE_LOCALNET - 1) if ((new_value == 0) && (old_value != 0)) rt_cache_flush(net); if (i == IPV4_DEVCONF_BC_FORWARDING - 1 && new_value != old_value) rt_cache_flush(net); if (i == IPV4_DEVCONF_RP_FILTER - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_RP_FILTER, ifindex, cnf); } if (i == IPV4_DEVCONF_PROXY_ARP - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_PROXY_NEIGH, ifindex, cnf); } if (i == IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, ifindex, cnf); } } return ret; } static int devinet_sysctl_forward(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; struct net *net = ctl->extra2; int ret; if (write && !ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write && *valp != val) { if (valp != &IPV4_DEVCONF_DFLT(net, FORWARDING)) { if (!rtnl_net_trylock(net)) { /* Restore the original values before restarting */ *valp = val; *ppos = pos; return restart_syscall(); } if (valp == &IPV4_DEVCONF_ALL(net, FORWARDING)) { inet_forward_change(net); } else { struct ipv4_devconf *cnf = ctl->extra1; struct in_device *idev = container_of(cnf, struct in_device, cnf); if (*valp) dev_disable_lro(idev->dev); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, idev->dev->ifindex, cnf); } rtnl_net_unlock(net); rt_cache_flush(net); } else inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt); } return ret; } static int ipv4_doint_and_flush(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); struct net *net = ctl->extra2; if (write && *valp != val) rt_cache_flush(net); return ret; } #define DEVINET_SYSCTL_ENTRY(attr, name, mval, proc) \ { \ .procname = name, \ .data = ipv4_devconf.data + \ IPV4_DEVCONF_ ## attr - 1, \ .maxlen = sizeof(int), \ .mode = mval, \ .proc_handler = proc, \ .extra1 = &ipv4_devconf, \ } #define DEVINET_SYSCTL_RW_ENTRY(attr, name) \ DEVINET_SYSCTL_ENTRY(attr, name, 0644, devinet_conf_proc) #define DEVINET_SYSCTL_RO_ENTRY(attr, name) \ DEVINET_SYSCTL_ENTRY(attr, name, 0444, devinet_conf_proc) #define DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, proc) \ DEVINET_SYSCTL_ENTRY(attr, name, 0644, proc) #define DEVINET_SYSCTL_FLUSHING_ENTRY(attr, name) \ DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, ipv4_doint_and_flush) static struct devinet_sysctl_table { struct ctl_table_header *sysctl_header; struct ctl_table devinet_vars[IPV4_DEVCONF_MAX]; } devinet_sysctl = { .devinet_vars = { DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding", devinet_sysctl_forward), DEVINET_SYSCTL_RO_ENTRY(MC_FORWARDING, "mc_forwarding"), DEVINET_SYSCTL_RW_ENTRY(BC_FORWARDING, "bc_forwarding"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_REDIRECTS, "accept_redirects"), DEVINET_SYSCTL_RW_ENTRY(SECURE_REDIRECTS, "secure_redirects"), DEVINET_SYSCTL_RW_ENTRY(SHARED_MEDIA, "shared_media"), DEVINET_SYSCTL_RW_ENTRY(RP_FILTER, "rp_filter"), DEVINET_SYSCTL_RW_ENTRY(SEND_REDIRECTS, "send_redirects"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_SOURCE_ROUTE, "accept_source_route"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_LOCAL, "accept_local"), DEVINET_SYSCTL_RW_ENTRY(SRC_VMARK, "src_valid_mark"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP, "proxy_arp"), DEVINET_SYSCTL_RW_ENTRY(MEDIUM_ID, "medium_id"), DEVINET_SYSCTL_RW_ENTRY(BOOTP_RELAY, "bootp_relay"), DEVINET_SYSCTL_RW_ENTRY(LOG_MARTIANS, "log_martians"), DEVINET_SYSCTL_RW_ENTRY(TAG, "tag"), DEVINET_SYSCTL_RW_ENTRY(ARPFILTER, "arp_filter"), DEVINET_SYSCTL_RW_ENTRY(ARP_ANNOUNCE, "arp_announce"), DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"), DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"), DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"), DEVINET_SYSCTL_RW_ENTRY(ARP_EVICT_NOCARRIER, "arp_evict_nocarrier"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"), DEVINET_SYSCTL_RW_ENTRY(FORCE_IGMP_VERSION, "force_igmp_version"), DEVINET_SYSCTL_RW_ENTRY(IGMPV2_UNSOLICITED_REPORT_INTERVAL, "igmpv2_unsolicited_report_interval"), DEVINET_SYSCTL_RW_ENTRY(IGMPV3_UNSOLICITED_REPORT_INTERVAL, "igmpv3_unsolicited_report_interval"), DEVINET_SYSCTL_RW_ENTRY(IGNORE_ROUTES_WITH_LINKDOWN, "ignore_routes_with_linkdown"), DEVINET_SYSCTL_RW_ENTRY(DROP_GRATUITOUS_ARP, "drop_gratuitous_arp"), DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"), DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"), DEVINET_SYSCTL_FLUSHING_ENTRY(PROMOTE_SECONDARIES, "promote_secondaries"), DEVINET_SYSCTL_FLUSHING_ENTRY(ROUTE_LOCALNET, "route_localnet"), DEVINET_SYSCTL_FLUSHING_ENTRY(DROP_UNICAST_IN_L2_MULTICAST, "drop_unicast_in_l2_multicast"), }, }; static int __devinet_sysctl_register(struct net *net, char *dev_name, int ifindex, struct ipv4_devconf *p) { int i; struct devinet_sysctl_table *t; char path[sizeof("net/ipv4/conf/") + IFNAMSIZ]; t = kmemdup(&devinet_sysctl, sizeof(*t), GFP_KERNEL_ACCOUNT); if (!t) goto out; for (i = 0; i < ARRAY_SIZE(t->devinet_vars); i++) { t->devinet_vars[i].data += (char *)p - (char *)&ipv4_devconf; t->devinet_vars[i].extra1 = p; t->devinet_vars[i].extra2 = net; } snprintf(path, sizeof(path), "net/ipv4/conf/%s", dev_name); t->sysctl_header = register_net_sysctl(net, path, t->devinet_vars); if (!t->sysctl_header) goto free; p->sysctl = t; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, ifindex, p); return 0; free: kfree(t); out: return -ENOMEM; } static void __devinet_sysctl_unregister(struct net *net, struct ipv4_devconf *cnf, int ifindex) { struct devinet_sysctl_table *t = cnf->sysctl; if (t) { cnf->sysctl = NULL; unregister_net_sysctl_table(t->sysctl_header); kfree(t); } inet_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL); } static int devinet_sysctl_register(struct in_device *idev) { int err; if (!sysctl_dev_name_is_allowed(idev->dev->name)) return -EINVAL; err = neigh_sysctl_register(idev->dev, idev->arp_parms, NULL); if (err) return err; err = __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name, idev->dev->ifindex, &idev->cnf); if (err) neigh_sysctl_unregister(idev->arp_parms); return err; } static void devinet_sysctl_unregister(struct in_device *idev) { struct net *net = dev_net(idev->dev); __devinet_sysctl_unregister(net, &idev->cnf, idev->dev->ifindex); neigh_sysctl_unregister(idev->arp_parms); } static struct ctl_table ctl_forward_entry[] = { { .procname = "ip_forward", .data = &ipv4_devconf.data[ IPV4_DEVCONF_FORWARDING - 1], .maxlen = sizeof(int), .mode = 0644, .proc_handler = devinet_sysctl_forward, .extra1 = &ipv4_devconf, .extra2 = &init_net, }, }; #endif static __net_init int devinet_init_net(struct net *net) { #ifdef CONFIG_SYSCTL struct ctl_table_header *forw_hdr; struct ctl_table *tbl; #endif struct ipv4_devconf *all, *dflt; int err; int i; err = -ENOMEM; net->ipv4.inet_addr_lst = kmalloc_array(IN4_ADDR_HSIZE, sizeof(struct hlist_head), GFP_KERNEL); if (!net->ipv4.inet_addr_lst) goto err_alloc_hash; all = kmemdup(&ipv4_devconf, sizeof(ipv4_devconf), GFP_KERNEL); if (!all) goto err_alloc_all; dflt = kmemdup(&ipv4_devconf_dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL); if (!dflt) goto err_alloc_dflt; #ifdef CONFIG_SYSCTL tbl = kmemdup(ctl_forward_entry, sizeof(ctl_forward_entry), GFP_KERNEL); if (!tbl) goto err_alloc_ctl; tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1]; tbl[0].extra1 = all; tbl[0].extra2 = net; #endif if (!net_eq(net, &init_net)) { switch (net_inherit_devconf()) { case 3: /* copy from the current netns */ memcpy(all, current->nsproxy->net_ns->ipv4.devconf_all, sizeof(ipv4_devconf)); memcpy(dflt, current->nsproxy->net_ns->ipv4.devconf_dflt, sizeof(ipv4_devconf_dflt)); break; case 0: case 1: /* copy from init_net */ memcpy(all, init_net.ipv4.devconf_all, sizeof(ipv4_devconf)); memcpy(dflt, init_net.ipv4.devconf_dflt, sizeof(ipv4_devconf_dflt)); break; case 2: /* use compiled values */ break; } } #ifdef CONFIG_SYSCTL err = __devinet_sysctl_register(net, "all", NETCONFA_IFINDEX_ALL, all); if (err < 0) goto err_reg_all; err = __devinet_sysctl_register(net, "default", NETCONFA_IFINDEX_DEFAULT, dflt); if (err < 0) goto err_reg_dflt; err = -ENOMEM; forw_hdr = register_net_sysctl_sz(net, "net/ipv4", tbl, ARRAY_SIZE(ctl_forward_entry)); if (!forw_hdr) goto err_reg_ctl; net->ipv4.forw_hdr = forw_hdr; #endif for (i = 0; i < IN4_ADDR_HSIZE; i++) INIT_HLIST_HEAD(&net->ipv4.inet_addr_lst[i]); INIT_DEFERRABLE_WORK(&net->ipv4.addr_chk_work, check_lifetime); net->ipv4.devconf_all = all; net->ipv4.devconf_dflt = dflt; return 0; #ifdef CONFIG_SYSCTL err_reg_ctl: __devinet_sysctl_unregister(net, dflt, NETCONFA_IFINDEX_DEFAULT); err_reg_dflt: __devinet_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL); err_reg_all: kfree(tbl); err_alloc_ctl: #endif kfree(dflt); err_alloc_dflt: kfree(all); err_alloc_all: kfree(net->ipv4.inet_addr_lst); err_alloc_hash: return err; } static __net_exit void devinet_exit_net(struct net *net) { #ifdef CONFIG_SYSCTL const struct ctl_table *tbl; #endif cancel_delayed_work_sync(&net->ipv4.addr_chk_work); #ifdef CONFIG_SYSCTL tbl = net->ipv4.forw_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.forw_hdr); __devinet_sysctl_unregister(net, net->ipv4.devconf_dflt, NETCONFA_IFINDEX_DEFAULT); __devinet_sysctl_unregister(net, net->ipv4.devconf_all, NETCONFA_IFINDEX_ALL); kfree(tbl); #endif kfree(net->ipv4.devconf_dflt); kfree(net->ipv4.devconf_all); kfree(net->ipv4.inet_addr_lst); } static __net_initdata struct pernet_operations devinet_ops = { .init = devinet_init_net, .exit = devinet_exit_net, }; static struct rtnl_af_ops inet_af_ops __read_mostly = { .family = AF_INET, .fill_link_af = inet_fill_link_af, .get_link_af_size = inet_get_link_af_size, .validate_link_af = inet_validate_link_af, .set_link_af = inet_set_link_af, }; static const struct rtnl_msg_handler devinet_rtnl_msg_handlers[] __initconst = { {.protocol = PF_INET, .msgtype = RTM_NEWADDR, .doit = inet_rtm_newaddr, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_DELADDR, .doit = inet_rtm_deladdr, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_GETADDR, .dumpit = inet_dump_ifaddr, .flags = RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE}, {.protocol = PF_INET, .msgtype = RTM_GETNETCONF, .doit = inet_netconf_get_devconf, .dumpit = inet_netconf_dump_devconf, .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, }; void __init devinet_init(void) { register_pernet_subsys(&devinet_ops); register_netdevice_notifier(&ip_netdev_notifier); if (rtnl_af_register(&inet_af_ops)) panic("Unable to register inet_af_ops\n"); rtnl_register_many(devinet_rtnl_msg_handlers); } |
| 15 61 36 3 3 1 1 4 4 74 37 9 12 4 5 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_UDP_TUNNEL_H #define __NET_UDP_TUNNEL_H #include <net/ip_tunnels.h> #include <net/udp.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/ipv6_stubs.h> #endif struct udp_port_cfg { u8 family; /* Used only for kernel-created sockets */ union { struct in_addr local_ip; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr local_ip6; #endif }; union { struct in_addr peer_ip; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr peer_ip6; #endif }; __be16 local_udp_port; __be16 peer_udp_port; int bind_ifindex; unsigned int use_udp_checksums:1, use_udp6_tx_checksums:1, use_udp6_rx_checksums:1, ipv6_v6only:1; }; int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp); #if IS_ENABLED(CONFIG_IPV6) int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp); #else static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { return 0; } #endif static inline int udp_sock_create(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { if (cfg->family == AF_INET) return udp_sock_create4(net, cfg, sockp); if (cfg->family == AF_INET6) return udp_sock_create6(net, cfg, sockp); return -EPFNOSUPPORT; } typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb); typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk, struct sk_buff *skb); typedef void (*udp_tunnel_encap_err_rcv_t)(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk); typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk, struct list_head *head, struct sk_buff *skb); typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb, int nhoff); struct udp_tunnel_sock_cfg { void *sk_user_data; /* user data used by encap_rcv call back */ /* Used for setting up udp_sock fields, see udp.h for details */ __u8 encap_type; udp_tunnel_encap_rcv_t encap_rcv; udp_tunnel_encap_err_lookup_t encap_err_lookup; udp_tunnel_encap_err_rcv_t encap_err_rcv; udp_tunnel_encap_destroy_t encap_destroy; udp_tunnel_gro_receive_t gro_receive; udp_tunnel_gro_complete_t gro_complete; }; /* Setup the given (UDP) sock to receive UDP encapsulated packets */ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct udp_tunnel_sock_cfg *sock_cfg); /* -- List of parsable UDP tunnel types -- * * Adding to this list will result in serious debate. The main issue is * that this list is essentially a list of workarounds for either poorly * designed tunnels, or poorly designed device offloads. * * The parsing supported via these types should really be used for Rx * traffic only as the network stack will have already inserted offsets for * the location of the headers in the skb. In addition any ports that are * pushed should be kept within the namespace without leaking to other * devices such as VFs or other ports on the same device. * * It is strongly encouraged to use CHECKSUM_COMPLETE for Rx to avoid the * need to use this for Rx checksum offload. It should not be necessary to * call this function to perform Tx offloads on outgoing traffic. */ enum udp_parsable_tunnel_type { UDP_TUNNEL_TYPE_VXLAN = BIT(0), /* RFC 7348 */ UDP_TUNNEL_TYPE_GENEVE = BIT(1), /* draft-ietf-nvo3-geneve */ UDP_TUNNEL_TYPE_VXLAN_GPE = BIT(2), /* draft-ietf-nvo3-vxlan-gpe */ }; struct udp_tunnel_info { unsigned short type; sa_family_t sa_family; __be16 port; u8 hw_priv; }; /* Notify network devices of offloadable types */ void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock, unsigned short type); void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock, unsigned short type); void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type); void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type); static inline void udp_tunnel_get_rx_info(struct net_device *dev) { ASSERT_RTNL(); if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev); } static inline void udp_tunnel_drop_rx_info(struct net_device *dev) { ASSERT_RTNL(); if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; call_netdevice_notifiers(NETDEV_UDP_TUNNEL_DROP_INFO, dev); } /* Transmit the skb using UDP encapsulation. */ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, bool xnet, bool nocheck); int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr, __u8 prio, __u8 ttl, __be32 label, __be16 src_port, __be16 dst_port, bool nocheck); void udp_tunnel_sock_release(struct socket *sock); struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb, struct net_device *dev, struct net *net, int oif, __be32 *saddr, const struct ip_tunnel_key *key, __be16 sport, __be16 dport, u8 tos, struct dst_cache *dst_cache); struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, struct net_device *dev, struct net *net, struct socket *sock, int oif, struct in6_addr *saddr, const struct ip_tunnel_key *key, __be16 sport, __be16 dport, u8 dsfield, struct dst_cache *dst_cache); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, const unsigned long *flags, __be64 tunnel_id, int md_size); #ifdef CONFIG_INET static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) { int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; return iptunnel_handle_offloads(skb, type); } #endif static inline void udp_tunnel_encap_enable(struct sock *sk) { if (udp_test_and_set_bit(ENCAP_ENABLED, sk)) return; #if IS_ENABLED(CONFIG_IPV6) if (READ_ONCE(sk->sk_family) == PF_INET6) ipv6_stub->udpv6_encap_enable(); #endif udp_encap_enable(); } #define UDP_TUNNEL_NIC_MAX_TABLES 4 enum udp_tunnel_nic_info_flags { /* Device callbacks may sleep */ UDP_TUNNEL_NIC_INFO_MAY_SLEEP = BIT(0), /* Device only supports offloads when it's open, all ports * will be removed before close and re-added after open. */ UDP_TUNNEL_NIC_INFO_OPEN_ONLY = BIT(1), /* Device supports only IPv4 tunnels */ UDP_TUNNEL_NIC_INFO_IPV4_ONLY = BIT(2), /* Device has hard-coded the IANA VXLAN port (4789) as VXLAN. * This port must not be counted towards n_entries of any table. * Driver will not receive any callback associated with port 4789. */ UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN = BIT(3), }; struct udp_tunnel_nic; #define UDP_TUNNEL_NIC_MAX_SHARING_DEVICES (U16_MAX / 2) struct udp_tunnel_nic_shared { struct udp_tunnel_nic *udp_tunnel_nic_info; struct list_head devices; }; struct udp_tunnel_nic_shared_node { struct net_device *dev; struct list_head list; }; /** * struct udp_tunnel_nic_info - driver UDP tunnel offload information * @set_port: callback for adding a new port * @unset_port: callback for removing a port * @sync_table: callback for syncing the entire port table at once * @shared: reference to device global state (optional) * @flags: device flags from enum udp_tunnel_nic_info_flags * @tables: UDP port tables this device has * @tables.n_entries: number of entries in this table * @tables.tunnel_types: types of tunnels this table accepts * * Drivers are expected to provide either @set_port and @unset_port callbacks * or the @sync_table callback. Callbacks are invoked with rtnl lock held. * * Devices which (misguidedly) share the UDP tunnel port table across multiple * netdevs should allocate an instance of struct udp_tunnel_nic_shared and * point @shared at it. * There must never be more than %UDP_TUNNEL_NIC_MAX_SHARING_DEVICES devices * sharing a table. * * Known limitations: * - UDP tunnel port notifications are fundamentally best-effort - * it is likely the driver will both see skbs which use a UDP tunnel port, * while not being a tunneled skb, and tunnel skbs from other ports - * drivers should only use these ports for non-critical RX-side offloads, * e.g. the checksum offload; * - none of the devices care about the socket family at present, so we don't * track it. Please extend this code if you care. */ struct udp_tunnel_nic_info { /* one-by-one */ int (*set_port)(struct net_device *dev, unsigned int table, unsigned int entry, struct udp_tunnel_info *ti); int (*unset_port)(struct net_device *dev, unsigned int table, unsigned int entry, struct udp_tunnel_info *ti); /* all at once */ int (*sync_table)(struct net_device *dev, unsigned int table); struct udp_tunnel_nic_shared *shared; unsigned int flags; struct udp_tunnel_nic_table_info { unsigned int n_entries; unsigned int tunnel_types; } tables[UDP_TUNNEL_NIC_MAX_TABLES]; }; /* UDP tunnel module dependencies * * Tunnel drivers are expected to have a hard dependency on the udp_tunnel * module. NIC drivers are not, they just attach their * struct udp_tunnel_nic_info to the netdev and wait for callbacks to come. * Loading a tunnel driver will cause the udp_tunnel module to be loaded * and only then will all the required state structures be allocated. * Since we want a weak dependency from the drivers and the core to udp_tunnel * we call things through the following stubs. */ struct udp_tunnel_nic_ops { void (*get_port)(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti); void (*set_port_priv)(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv); void (*add_port)(struct net_device *dev, struct udp_tunnel_info *ti); void (*del_port)(struct net_device *dev, struct udp_tunnel_info *ti); void (*reset_ntf)(struct net_device *dev); size_t (*dump_size)(struct net_device *dev, unsigned int table); int (*dump_write)(struct net_device *dev, unsigned int table, struct sk_buff *skb); }; #ifdef CONFIG_INET extern const struct udp_tunnel_nic_ops *udp_tunnel_nic_ops; #else #define udp_tunnel_nic_ops ((struct udp_tunnel_nic_ops *)NULL) #endif static inline void udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { /* This helper is used from .sync_table, we indicate empty entries * by zero'ed @ti. Drivers which need to know the details of a port * when it gets deleted should use the .set_port / .unset_port * callbacks. * Zero out here, otherwise !CONFIG_INET causes uninitilized warnings. */ memset(ti, 0, sizeof(*ti)); if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->get_port(dev, table, idx, ti); } static inline void udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->set_port_priv(dev, table, idx, priv); } static inline void udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) { if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->add_port(dev, ti); } static inline void udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti) { if (!(dev->features & NETIF_F_RX_UDP_TUNNEL_PORT)) return; if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->del_port(dev, ti); } /** * udp_tunnel_nic_reset_ntf() - device-originating reset notification * @dev: network interface device structure * * Called by the driver to inform the core that the entire UDP tunnel port * state has been lost, usually due to device reset. Core will assume device * forgot all the ports and issue .set_port and .sync_table callbacks as * necessary. * * This function must be called with rtnl lock held, and will issue all * the callbacks before returning. */ static inline void udp_tunnel_nic_reset_ntf(struct net_device *dev) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->reset_ntf(dev); } static inline size_t udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table) { if (!udp_tunnel_nic_ops) return 0; return udp_tunnel_nic_ops->dump_size(dev, table); } static inline int udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, struct sk_buff *skb) { if (!udp_tunnel_nic_ops) return 0; return udp_tunnel_nic_ops->dump_write(dev, table, skb); } #endif |
| 5 11 5 6 7 11 5 5 5 5 1 1 1 1 1 1 1 1 1 1 1 10 5 2 15 15 15 8 15 1 1 1 1 1 1 1 4 4 4 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Copyright (c) 2004 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2004 Infinicon Corporation. All rights reserved. * Copyright (c) 2004 Intel Corporation. All rights reserved. * Copyright (c) 2004 Topspin Corporation. All rights reserved. * Copyright (c) 2004 Voltaire Corporation. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2005, 2006 Cisco Systems. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include <linux/errno.h> #include <linux/err.h> #include <linux/export.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/in.h> #include <linux/in6.h> #include <net/addrconf.h> #include <linux/security.h> #include <rdma/ib_verbs.h> #include <rdma/ib_cache.h> #include <rdma/ib_addr.h> #include <rdma/rw.h> #include <rdma/lag.h> #include "core_priv.h" #include <trace/events/rdma_core.h> static int ib_resolve_eth_dmac(struct ib_device *device, struct rdma_ah_attr *ah_attr); static const char * const ib_events[] = { [IB_EVENT_CQ_ERR] = "CQ error", [IB_EVENT_QP_FATAL] = "QP fatal error", [IB_EVENT_QP_REQ_ERR] = "QP request error", [IB_EVENT_QP_ACCESS_ERR] = "QP access error", [IB_EVENT_COMM_EST] = "communication established", [IB_EVENT_SQ_DRAINED] = "send queue drained", [IB_EVENT_PATH_MIG] = "path migration successful", [IB_EVENT_PATH_MIG_ERR] = "path migration error", [IB_EVENT_DEVICE_FATAL] = "device fatal error", [IB_EVENT_PORT_ACTIVE] = "port active", [IB_EVENT_PORT_ERR] = "port error", [IB_EVENT_LID_CHANGE] = "LID change", [IB_EVENT_PKEY_CHANGE] = "P_key change", [IB_EVENT_SM_CHANGE] = "SM change", [IB_EVENT_SRQ_ERR] = "SRQ error", [IB_EVENT_SRQ_LIMIT_REACHED] = "SRQ limit reached", [IB_EVENT_QP_LAST_WQE_REACHED] = "last WQE reached", [IB_EVENT_CLIENT_REREGISTER] = "client reregister", [IB_EVENT_GID_CHANGE] = "GID changed", }; const char *__attribute_const__ ib_event_msg(enum ib_event_type event) { size_t index = event; return (index < ARRAY_SIZE(ib_events) && ib_events[index]) ? ib_events[index] : "unrecognized event"; } EXPORT_SYMBOL(ib_event_msg); static const char * const wc_statuses[] = { [IB_WC_SUCCESS] = "success", [IB_WC_LOC_LEN_ERR] = "local length error", [IB_WC_LOC_QP_OP_ERR] = "local QP operation error", [IB_WC_LOC_EEC_OP_ERR] = "local EE context operation error", [IB_WC_LOC_PROT_ERR] = "local protection error", [IB_WC_WR_FLUSH_ERR] = "WR flushed", [IB_WC_MW_BIND_ERR] = "memory bind operation error", [IB_WC_BAD_RESP_ERR] = "bad response error", [IB_WC_LOC_ACCESS_ERR] = "local access error", [IB_WC_REM_INV_REQ_ERR] = "remote invalid request error", [IB_WC_REM_ACCESS_ERR] = "remote access error", [IB_WC_REM_OP_ERR] = "remote operation error", [IB_WC_RETRY_EXC_ERR] = "transport retry counter exceeded", [IB_WC_RNR_RETRY_EXC_ERR] = "RNR retry counter exceeded", [IB_WC_LOC_RDD_VIOL_ERR] = "local RDD violation error", [IB_WC_REM_INV_RD_REQ_ERR] = "remote invalid RD request", [IB_WC_REM_ABORT_ERR] = "operation aborted", [IB_WC_INV_EECN_ERR] = "invalid EE context number", [IB_WC_INV_EEC_STATE_ERR] = "invalid EE context state", [IB_WC_FATAL_ERR] = "fatal error", [IB_WC_RESP_TIMEOUT_ERR] = "response timeout error", [IB_WC_GENERAL_ERR] = "general error", }; const char *__attribute_const__ ib_wc_status_msg(enum ib_wc_status status) { size_t index = status; return (index < ARRAY_SIZE(wc_statuses) && wc_statuses[index]) ? wc_statuses[index] : "unrecognized status"; } EXPORT_SYMBOL(ib_wc_status_msg); __attribute_const__ int ib_rate_to_mult(enum ib_rate rate) { switch (rate) { case IB_RATE_2_5_GBPS: return 1; case IB_RATE_5_GBPS: return 2; case IB_RATE_10_GBPS: return 4; case IB_RATE_20_GBPS: return 8; case IB_RATE_30_GBPS: return 12; case IB_RATE_40_GBPS: return 16; case IB_RATE_60_GBPS: return 24; case IB_RATE_80_GBPS: return 32; case IB_RATE_120_GBPS: return 48; case IB_RATE_14_GBPS: return 6; case IB_RATE_56_GBPS: return 22; case IB_RATE_112_GBPS: return 45; case IB_RATE_168_GBPS: return 67; case IB_RATE_25_GBPS: return 10; case IB_RATE_100_GBPS: return 40; case IB_RATE_200_GBPS: return 80; case IB_RATE_300_GBPS: return 120; case IB_RATE_28_GBPS: return 11; case IB_RATE_50_GBPS: return 20; case IB_RATE_400_GBPS: return 160; case IB_RATE_600_GBPS: return 240; case IB_RATE_800_GBPS: return 320; default: return -1; } } EXPORT_SYMBOL(ib_rate_to_mult); __attribute_const__ enum ib_rate mult_to_ib_rate(int mult) { switch (mult) { case 1: return IB_RATE_2_5_GBPS; case 2: return IB_RATE_5_GBPS; case 4: return IB_RATE_10_GBPS; case 8: return IB_RATE_20_GBPS; case 12: return IB_RATE_30_GBPS; case 16: return IB_RATE_40_GBPS; case 24: return IB_RATE_60_GBPS; case 32: return IB_RATE_80_GBPS; case 48: return IB_RATE_120_GBPS; case 6: return IB_RATE_14_GBPS; case 22: return IB_RATE_56_GBPS; case 45: return IB_RATE_112_GBPS; case 67: return IB_RATE_168_GBPS; case 10: return IB_RATE_25_GBPS; case 40: return IB_RATE_100_GBPS; case 80: return IB_RATE_200_GBPS; case 120: return IB_RATE_300_GBPS; case 11: return IB_RATE_28_GBPS; case 20: return IB_RATE_50_GBPS; case 160: return IB_RATE_400_GBPS; case 240: return IB_RATE_600_GBPS; case 320: return IB_RATE_800_GBPS; default: return IB_RATE_PORT_CURRENT; } } EXPORT_SYMBOL(mult_to_ib_rate); __attribute_const__ int ib_rate_to_mbps(enum ib_rate rate) { switch (rate) { case IB_RATE_2_5_GBPS: return 2500; case IB_RATE_5_GBPS: return 5000; case IB_RATE_10_GBPS: return 10000; case IB_RATE_20_GBPS: return 20000; case IB_RATE_30_GBPS: return 30000; case IB_RATE_40_GBPS: return 40000; case IB_RATE_60_GBPS: return 60000; case IB_RATE_80_GBPS: return 80000; case IB_RATE_120_GBPS: return 120000; case IB_RATE_14_GBPS: return 14062; case IB_RATE_56_GBPS: return 56250; case IB_RATE_112_GBPS: return 112500; case IB_RATE_168_GBPS: return 168750; case IB_RATE_25_GBPS: return 25781; case IB_RATE_100_GBPS: return 103125; case IB_RATE_200_GBPS: return 206250; case IB_RATE_300_GBPS: return 309375; case IB_RATE_28_GBPS: return 28125; case IB_RATE_50_GBPS: return 53125; case IB_RATE_400_GBPS: return 425000; case IB_RATE_600_GBPS: return 637500; case IB_RATE_800_GBPS: return 850000; default: return -1; } } EXPORT_SYMBOL(ib_rate_to_mbps); __attribute_const__ enum rdma_transport_type rdma_node_get_transport(unsigned int node_type) { if (node_type == RDMA_NODE_USNIC) return RDMA_TRANSPORT_USNIC; if (node_type == RDMA_NODE_USNIC_UDP) return RDMA_TRANSPORT_USNIC_UDP; if (node_type == RDMA_NODE_RNIC) return RDMA_TRANSPORT_IWARP; if (node_type == RDMA_NODE_UNSPECIFIED) return RDMA_TRANSPORT_UNSPECIFIED; return RDMA_TRANSPORT_IB; } EXPORT_SYMBOL(rdma_node_get_transport); enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u32 port_num) { enum rdma_transport_type lt; if (device->ops.get_link_layer) return device->ops.get_link_layer(device, port_num); lt = rdma_node_get_transport(device->node_type); if (lt == RDMA_TRANSPORT_IB) return IB_LINK_LAYER_INFINIBAND; return IB_LINK_LAYER_ETHERNET; } EXPORT_SYMBOL(rdma_port_get_link_layer); /* Protection domains */ /** * __ib_alloc_pd - Allocates an unused protection domain. * @device: The device on which to allocate the protection domain. * @flags: protection domain flags * @caller: caller's build-time module name * * A protection domain object provides an association between QPs, shared * receive queues, address handles, memory regions, and memory windows. * * Every PD has a local_dma_lkey which can be used as the lkey value for local * memory operations. */ struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags, const char *caller) { struct ib_pd *pd; int mr_access_flags = 0; int ret; pd = rdma_zalloc_drv_obj(device, ib_pd); if (!pd) return ERR_PTR(-ENOMEM); pd->device = device; pd->flags = flags; rdma_restrack_new(&pd->res, RDMA_RESTRACK_PD); rdma_restrack_set_name(&pd->res, caller); ret = device->ops.alloc_pd(pd, NULL); if (ret) { rdma_restrack_put(&pd->res); kfree(pd); return ERR_PTR(ret); } rdma_restrack_add(&pd->res); if (device->attrs.kernel_cap_flags & IBK_LOCAL_DMA_LKEY) pd->local_dma_lkey = device->local_dma_lkey; else mr_access_flags |= IB_ACCESS_LOCAL_WRITE; if (flags & IB_PD_UNSAFE_GLOBAL_RKEY) { pr_warn("%s: enabling unsafe global rkey\n", caller); mr_access_flags |= IB_ACCESS_REMOTE_READ | IB_ACCESS_REMOTE_WRITE; } if (mr_access_flags) { struct ib_mr *mr; mr = pd->device->ops.get_dma_mr(pd, mr_access_flags); if (IS_ERR(mr)) { ib_dealloc_pd(pd); return ERR_CAST(mr); } mr->device = pd->device; mr->pd = pd; mr->type = IB_MR_TYPE_DMA; mr->uobject = NULL; mr->need_inval = false; pd->__internal_mr = mr; if (!(device->attrs.kernel_cap_flags & IBK_LOCAL_DMA_LKEY)) pd->local_dma_lkey = pd->__internal_mr->lkey; if (flags & IB_PD_UNSAFE_GLOBAL_RKEY) pd->unsafe_global_rkey = pd->__internal_mr->rkey; } return pd; } EXPORT_SYMBOL(__ib_alloc_pd); /** * ib_dealloc_pd_user - Deallocates a protection domain. * @pd: The protection domain to deallocate. * @udata: Valid user data or NULL for kernel object * * It is an error to call this function while any resources in the pd still * exist. The caller is responsible to synchronously destroy them and * guarantee no new allocations will happen. */ int ib_dealloc_pd_user(struct ib_pd *pd, struct ib_udata *udata) { int ret; if (pd->__internal_mr) { ret = pd->device->ops.dereg_mr(pd->__internal_mr, NULL); WARN_ON(ret); pd->__internal_mr = NULL; } ret = pd->device->ops.dealloc_pd(pd, udata); if (ret) return ret; rdma_restrack_del(&pd->res); kfree(pd); return ret; } EXPORT_SYMBOL(ib_dealloc_pd_user); /* Address handles */ /** * rdma_copy_ah_attr - Copy rdma ah attribute from source to destination. * @dest: Pointer to destination ah_attr. Contents of the destination * pointer is assumed to be invalid and attribute are overwritten. * @src: Pointer to source ah_attr. */ void rdma_copy_ah_attr(struct rdma_ah_attr *dest, const struct rdma_ah_attr *src) { *dest = *src; if (dest->grh.sgid_attr) rdma_hold_gid_attr(dest->grh.sgid_attr); } EXPORT_SYMBOL(rdma_copy_ah_attr); /** * rdma_replace_ah_attr - Replace valid ah_attr with new one. * @old: Pointer to existing ah_attr which needs to be replaced. * old is assumed to be valid or zero'd * @new: Pointer to the new ah_attr. * * rdma_replace_ah_attr() first releases any reference in the old ah_attr if * old the ah_attr is valid; after that it copies the new attribute and holds * the reference to the replaced ah_attr. */ void rdma_replace_ah_attr(struct rdma_ah_attr *old, const struct rdma_ah_attr *new) { rdma_destroy_ah_attr(old); *old = *new; if (old->grh.sgid_attr) rdma_hold_gid_attr(old->grh.sgid_attr); } EXPORT_SYMBOL(rdma_replace_ah_attr); /** * rdma_move_ah_attr - Move ah_attr pointed by source to destination. * @dest: Pointer to destination ah_attr to copy to. * dest is assumed to be valid or zero'd * @src: Pointer to the new ah_attr. * * rdma_move_ah_attr() first releases any reference in the destination ah_attr * if it is valid. This also transfers ownership of internal references from * src to dest, making src invalid in the process. No new reference of the src * ah_attr is taken. */ void rdma_move_ah_attr(struct rdma_ah_attr *dest, struct rdma_ah_attr *src) { rdma_destroy_ah_attr(dest); *dest = *src; src->grh.sgid_attr = NULL; } EXPORT_SYMBOL(rdma_move_ah_attr); /* * Validate that the rdma_ah_attr is valid for the device before passing it * off to the driver. */ static int rdma_check_ah_attr(struct ib_device *device, struct rdma_ah_attr *ah_attr) { if (!rdma_is_port_valid(device, ah_attr->port_num)) return -EINVAL; if ((rdma_is_grh_required(device, ah_attr->port_num) || ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE) && !(ah_attr->ah_flags & IB_AH_GRH)) return -EINVAL; if (ah_attr->grh.sgid_attr) { /* * Make sure the passed sgid_attr is consistent with the * parameters */ if (ah_attr->grh.sgid_attr->index != ah_attr->grh.sgid_index || ah_attr->grh.sgid_attr->port_num != ah_attr->port_num) return -EINVAL; } return 0; } /* * If the ah requires a GRH then ensure that sgid_attr pointer is filled in. * On success the caller is responsible to call rdma_unfill_sgid_attr(). */ static int rdma_fill_sgid_attr(struct ib_device *device, struct rdma_ah_attr *ah_attr, const struct ib_gid_attr **old_sgid_attr) { const struct ib_gid_attr *sgid_attr; struct ib_global_route *grh; int ret; *old_sgid_attr = ah_attr->grh.sgid_attr; ret = rdma_check_ah_attr(device, ah_attr); if (ret) return ret; if (!(ah_attr->ah_flags & IB_AH_GRH)) return 0; grh = rdma_ah_retrieve_grh(ah_attr); if (grh->sgid_attr) return 0; sgid_attr = rdma_get_gid_attr(device, ah_attr->port_num, grh->sgid_index); if (IS_ERR(sgid_attr)) return PTR_ERR(sgid_attr); /* Move ownerhip of the kref into the ah_attr */ grh->sgid_attr = sgid_attr; return 0; } static void rdma_unfill_sgid_attr(struct rdma_ah_attr *ah_attr, const struct ib_gid_attr *old_sgid_attr) { /* * Fill didn't change anything, the caller retains ownership of * whatever it passed */ if (ah_attr->grh.sgid_attr == old_sgid_attr) return; /* * Otherwise, we need to undo what rdma_fill_sgid_attr so the caller * doesn't see any change in the rdma_ah_attr. If we get here * old_sgid_attr is NULL. */ rdma_destroy_ah_attr(ah_attr); } static const struct ib_gid_attr * rdma_update_sgid_attr(struct rdma_ah_attr *ah_attr, const struct ib_gid_attr *old_attr) { if (old_attr) rdma_put_gid_attr(old_attr); if (ah_attr->ah_flags & IB_AH_GRH) { rdma_hold_gid_attr(ah_attr->grh.sgid_attr); return ah_attr->grh.sgid_attr; } return NULL; } static struct ib_ah *_rdma_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, u32 flags, struct ib_udata *udata, struct net_device *xmit_slave) { struct rdma_ah_init_attr init_attr = {}; struct ib_device *device = pd->device; struct ib_ah *ah; int ret; might_sleep_if(flags & RDMA_CREATE_AH_SLEEPABLE); if (!udata && !device->ops.create_ah) return ERR_PTR(-EOPNOTSUPP); ah = rdma_zalloc_drv_obj_gfp( device, ib_ah, (flags & RDMA_CREATE_AH_SLEEPABLE) ? GFP_KERNEL : GFP_ATOMIC); if (!ah) return ERR_PTR(-ENOMEM); ah->device = device; ah->pd = pd; ah->type = ah_attr->type; ah->sgid_attr = rdma_update_sgid_attr(ah_attr, NULL); init_attr.ah_attr = ah_attr; init_attr.flags = flags; init_attr.xmit_slave = xmit_slave; if (udata) ret = device->ops.create_user_ah(ah, &init_attr, udata); else ret = device->ops.create_ah(ah, &init_attr, NULL); if (ret) { if (ah->sgid_attr) rdma_put_gid_attr(ah->sgid_attr); kfree(ah); return ERR_PTR(ret); } atomic_inc(&pd->usecnt); return ah; } /** * rdma_create_ah - Creates an address handle for the * given address vector. * @pd: The protection domain associated with the address handle. * @ah_attr: The attributes of the address vector. * @flags: Create address handle flags (see enum rdma_create_ah_flags). * * It returns 0 on success and returns appropriate error code on error. * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *rdma_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, u32 flags) { const struct ib_gid_attr *old_sgid_attr; struct net_device *slave; struct ib_ah *ah; int ret; ret = rdma_fill_sgid_attr(pd->device, ah_attr, &old_sgid_attr); if (ret) return ERR_PTR(ret); slave = rdma_lag_get_ah_roce_slave(pd->device, ah_attr, (flags & RDMA_CREATE_AH_SLEEPABLE) ? GFP_KERNEL : GFP_ATOMIC); if (IS_ERR(slave)) { rdma_unfill_sgid_attr(ah_attr, old_sgid_attr); return (void *)slave; } ah = _rdma_create_ah(pd, ah_attr, flags, NULL, slave); rdma_lag_put_ah_roce_slave(slave); rdma_unfill_sgid_attr(ah_attr, old_sgid_attr); return ah; } EXPORT_SYMBOL(rdma_create_ah); /** * rdma_create_user_ah - Creates an address handle for the * given address vector. * It resolves destination mac address for ah attribute of RoCE type. * @pd: The protection domain associated with the address handle. * @ah_attr: The attributes of the address vector. * @udata: pointer to user's input output buffer information need by * provider driver. * * It returns 0 on success and returns appropriate error code on error. * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *rdma_create_user_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, struct ib_udata *udata) { const struct ib_gid_attr *old_sgid_attr; struct ib_ah *ah; int err; err = rdma_fill_sgid_attr(pd->device, ah_attr, &old_sgid_attr); if (err) return ERR_PTR(err); if (ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE) { err = ib_resolve_eth_dmac(pd->device, ah_attr); if (err) { ah = ERR_PTR(err); goto out; } } ah = _rdma_create_ah(pd, ah_attr, RDMA_CREATE_AH_SLEEPABLE, udata, NULL); out: rdma_unfill_sgid_attr(ah_attr, old_sgid_attr); return ah; } EXPORT_SYMBOL(rdma_create_user_ah); int ib_get_rdma_header_version(const union rdma_network_hdr *hdr) { const struct iphdr *ip4h = (struct iphdr *)&hdr->roce4grh; struct iphdr ip4h_checked; const struct ipv6hdr *ip6h = (struct ipv6hdr *)&hdr->ibgrh; /* If it's IPv6, the version must be 6, otherwise, the first * 20 bytes (before the IPv4 header) are garbled. */ if (ip6h->version != 6) return (ip4h->version == 4) ? 4 : 0; /* version may be 6 or 4 because the first 20 bytes could be garbled */ /* RoCE v2 requires no options, thus header length * must be 5 words */ if (ip4h->ihl != 5) return 6; /* Verify checksum. * We can't write on scattered buffers so we need to copy to * temp buffer. */ memcpy(&ip4h_checked, ip4h, sizeof(ip4h_checked)); ip4h_checked.check = 0; ip4h_checked.check = ip_fast_csum((u8 *)&ip4h_checked, 5); /* if IPv4 header checksum is OK, believe it */ if (ip4h->check == ip4h_checked.check) return 4; return 6; } EXPORT_SYMBOL(ib_get_rdma_header_version); static enum rdma_network_type ib_get_net_type_by_grh(struct ib_device *device, u32 port_num, const struct ib_grh *grh) { int grh_version; if (rdma_protocol_ib(device, port_num)) return RDMA_NETWORK_IB; grh_version = ib_get_rdma_header_version((union rdma_network_hdr *)grh); if (grh_version == 4) return RDMA_NETWORK_IPV4; if (grh->next_hdr == IPPROTO_UDP) return RDMA_NETWORK_IPV6; return RDMA_NETWORK_ROCE_V1; } struct find_gid_index_context { u16 vlan_id; enum ib_gid_type gid_type; }; static bool find_gid_index(const union ib_gid *gid, const struct ib_gid_attr *gid_attr, void *context) { struct find_gid_index_context *ctx = context; u16 vlan_id = 0xffff; int ret; if (ctx->gid_type != gid_attr->gid_type) return false; ret = rdma_read_gid_l2_fields(gid_attr, &vlan_id, NULL); if (ret) return false; return ctx->vlan_id == vlan_id; } static const struct ib_gid_attr * get_sgid_attr_from_eth(struct ib_device *device, u32 port_num, u16 vlan_id, const union ib_gid *sgid, enum ib_gid_type gid_type) { struct find_gid_index_context context = {.vlan_id = vlan_id, .gid_type = gid_type}; return rdma_find_gid_by_filter(device, sgid, port_num, find_gid_index, &context); } int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr, enum rdma_network_type net_type, union ib_gid *sgid, union ib_gid *dgid) { struct sockaddr_in src_in; struct sockaddr_in dst_in; __be32 src_saddr, dst_saddr; if (!sgid || !dgid) return -EINVAL; if (net_type == RDMA_NETWORK_IPV4) { memcpy(&src_in.sin_addr.s_addr, &hdr->roce4grh.saddr, 4); memcpy(&dst_in.sin_addr.s_addr, &hdr->roce4grh.daddr, 4); src_saddr = src_in.sin_addr.s_addr; dst_saddr = dst_in.sin_addr.s_addr; ipv6_addr_set_v4mapped(src_saddr, (struct in6_addr *)sgid); ipv6_addr_set_v4mapped(dst_saddr, (struct in6_addr *)dgid); return 0; } else if (net_type == RDMA_NETWORK_IPV6 || net_type == RDMA_NETWORK_IB || RDMA_NETWORK_ROCE_V1) { *dgid = hdr->ibgrh.dgid; *sgid = hdr->ibgrh.sgid; return 0; } else { return -EINVAL; } } EXPORT_SYMBOL(ib_get_gids_from_rdma_hdr); /* Resolve destination mac address and hop limit for unicast destination * GID entry, considering the source GID entry as well. * ah_attribute must have valid port_num, sgid_index. */ static int ib_resolve_unicast_gid_dmac(struct ib_device *device, struct rdma_ah_attr *ah_attr) { struct ib_global_route *grh = rdma_ah_retrieve_grh(ah_attr); const struct ib_gid_attr *sgid_attr = grh->sgid_attr; int hop_limit = 0xff; int ret = 0; /* If destination is link local and source GID is RoCEv1, * IP stack is not used. */ if (rdma_link_local_addr((struct in6_addr *)grh->dgid.raw) && sgid_attr->gid_type == IB_GID_TYPE_ROCE) { rdma_get_ll_mac((struct in6_addr *)grh->dgid.raw, ah_attr->roce.dmac); return ret; } ret = rdma_addr_find_l2_eth_by_grh(&sgid_attr->gid, &grh->dgid, ah_attr->roce.dmac, sgid_attr, &hop_limit); grh->hop_limit = hop_limit; return ret; } /* * This function initializes address handle attributes from the incoming packet. * Incoming packet has dgid of the receiver node on which this code is * getting executed and, sgid contains the GID of the sender. * * When resolving mac address of destination, the arrived dgid is used * as sgid and, sgid is used as dgid because sgid contains destinations * GID whom to respond to. * * On success the caller is responsible to call rdma_destroy_ah_attr on the * attr. */ int ib_init_ah_attr_from_wc(struct ib_device *device, u32 port_num, const struct ib_wc *wc, const struct ib_grh *grh, struct rdma_ah_attr *ah_attr) { u32 flow_class; int ret; enum rdma_network_type net_type = RDMA_NETWORK_IB; enum ib_gid_type gid_type = IB_GID_TYPE_IB; const struct ib_gid_attr *sgid_attr; int hoplimit = 0xff; union ib_gid dgid; union ib_gid sgid; might_sleep(); memset(ah_attr, 0, sizeof *ah_attr); ah_attr->type = rdma_ah_find_type(device, port_num); if (rdma_cap_eth_ah(device, port_num)) { if (wc->wc_flags & IB_WC_WITH_NETWORK_HDR_TYPE) net_type = wc->network_hdr_type; else net_type = ib_get_net_type_by_grh(device, port_num, grh); gid_type = ib_network_to_gid_type(net_type); } ret = ib_get_gids_from_rdma_hdr((union rdma_network_hdr *)grh, net_type, &sgid, &dgid); if (ret) return ret; rdma_ah_set_sl(ah_attr, wc->sl); rdma_ah_set_port_num(ah_attr, port_num); if (rdma_protocol_roce(device, port_num)) { u16 vlan_id = wc->wc_flags & IB_WC_WITH_VLAN ? wc->vlan_id : 0xffff; if (!(wc->wc_flags & IB_WC_GRH)) return -EPROTOTYPE; sgid_attr = get_sgid_attr_from_eth(device, port_num, vlan_id, &dgid, gid_type); if (IS_ERR(sgid_attr)) return PTR_ERR(sgid_attr); flow_class = be32_to_cpu(grh->version_tclass_flow); rdma_move_grh_sgid_attr(ah_attr, &sgid, flow_class & 0xFFFFF, hoplimit, (flow_class >> 20) & 0xFF, sgid_attr); ret = ib_resolve_unicast_gid_dmac(device, ah_attr); if (ret) rdma_destroy_ah_attr(ah_attr); return ret; } else { rdma_ah_set_dlid(ah_attr, wc->slid); rdma_ah_set_path_bits(ah_attr, wc->dlid_path_bits); if ((wc->wc_flags & IB_WC_GRH) == 0) return 0; if (dgid.global.interface_id != cpu_to_be64(IB_SA_WELL_KNOWN_GUID)) { sgid_attr = rdma_find_gid_by_port( device, &dgid, IB_GID_TYPE_IB, port_num, NULL); } else sgid_attr = rdma_get_gid_attr(device, port_num, 0); if (IS_ERR(sgid_attr)) return PTR_ERR(sgid_attr); flow_class = be32_to_cpu(grh->version_tclass_flow); rdma_move_grh_sgid_attr(ah_attr, &sgid, flow_class & 0xFFFFF, hoplimit, (flow_class >> 20) & 0xFF, sgid_attr); return 0; } } EXPORT_SYMBOL(ib_init_ah_attr_from_wc); /** * rdma_move_grh_sgid_attr - Sets the sgid attribute of GRH, taking ownership * of the reference * * @attr: Pointer to AH attribute structure * @dgid: Destination GID * @flow_label: Flow label * @hop_limit: Hop limit * @traffic_class: traffic class * @sgid_attr: Pointer to SGID attribute * * This takes ownership of the sgid_attr reference. The caller must ensure * rdma_destroy_ah_attr() is called before destroying the rdma_ah_attr after * calling this function. */ void rdma_move_grh_sgid_attr(struct rdma_ah_attr *attr, union ib_gid *dgid, u32 flow_label, u8 hop_limit, u8 traffic_class, const struct ib_gid_attr *sgid_attr) { rdma_ah_set_grh(attr, dgid, flow_label, sgid_attr->index, hop_limit, traffic_class); attr->grh.sgid_attr = sgid_attr; } EXPORT_SYMBOL(rdma_move_grh_sgid_attr); /** * rdma_destroy_ah_attr - Release reference to SGID attribute of * ah attribute. * @ah_attr: Pointer to ah attribute * * Release reference to the SGID attribute of the ah attribute if it is * non NULL. It is safe to call this multiple times, and safe to call it on * a zero initialized ah_attr. */ void rdma_destroy_ah_attr(struct rdma_ah_attr *ah_attr) { if (ah_attr->grh.sgid_attr) { rdma_put_gid_attr(ah_attr->grh.sgid_attr); ah_attr->grh.sgid_attr = NULL; } } EXPORT_SYMBOL(rdma_destroy_ah_attr); struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, const struct ib_wc *wc, const struct ib_grh *grh, u32 port_num) { struct rdma_ah_attr ah_attr; struct ib_ah *ah; int ret; ret = ib_init_ah_attr_from_wc(pd->device, port_num, wc, grh, &ah_attr); if (ret) return ERR_PTR(ret); ah = rdma_create_ah(pd, &ah_attr, RDMA_CREATE_AH_SLEEPABLE); rdma_destroy_ah_attr(&ah_attr); return ah; } EXPORT_SYMBOL(ib_create_ah_from_wc); int rdma_modify_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr) { const struct ib_gid_attr *old_sgid_attr; int ret; if (ah->type != ah_attr->type) return -EINVAL; ret = rdma_fill_sgid_attr(ah->device, ah_attr, &old_sgid_attr); if (ret) return ret; ret = ah->device->ops.modify_ah ? ah->device->ops.modify_ah(ah, ah_attr) : -EOPNOTSUPP; ah->sgid_attr = rdma_update_sgid_attr(ah_attr, ah->sgid_attr); rdma_unfill_sgid_attr(ah_attr, old_sgid_attr); return ret; } EXPORT_SYMBOL(rdma_modify_ah); int rdma_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr) { ah_attr->grh.sgid_attr = NULL; return ah->device->ops.query_ah ? ah->device->ops.query_ah(ah, ah_attr) : -EOPNOTSUPP; } EXPORT_SYMBOL(rdma_query_ah); int rdma_destroy_ah_user(struct ib_ah *ah, u32 flags, struct ib_udata *udata) { const struct ib_gid_attr *sgid_attr = ah->sgid_attr; struct ib_pd *pd; int ret; might_sleep_if(flags & RDMA_DESTROY_AH_SLEEPABLE); pd = ah->pd; ret = ah->device->ops.destroy_ah(ah, flags); if (ret) return ret; atomic_dec(&pd->usecnt); if (sgid_attr) rdma_put_gid_attr(sgid_attr); kfree(ah); return ret; } EXPORT_SYMBOL(rdma_destroy_ah_user); /* Shared receive queues */ /** * ib_create_srq_user - Creates a SRQ associated with the specified protection * domain. * @pd: The protection domain associated with the SRQ. * @srq_init_attr: A list of initial attributes required to create the * SRQ. If SRQ creation succeeds, then the attributes are updated to * the actual capabilities of the created SRQ. * @uobject: uobject pointer if this is not a kernel SRQ * @udata: udata pointer if this is not a kernel SRQ * * srq_attr->max_wr and srq_attr->max_sge are read the determine the * requested size of the SRQ, and set to the actual values allocated * on return. If ib_create_srq() succeeds, then max_wr and max_sge * will always be at least as large as the requested values. */ struct ib_srq *ib_create_srq_user(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr, struct ib_usrq_object *uobject, struct ib_udata *udata) { struct ib_srq *srq; int ret; srq = rdma_zalloc_drv_obj(pd->device, ib_srq); if (!srq) return ERR_PTR(-ENOMEM); srq->device = pd->device; srq->pd = pd; srq->event_handler = srq_init_attr->event_handler; srq->srq_context = srq_init_attr->srq_context; srq->srq_type = srq_init_attr->srq_type; srq->uobject = uobject; if (ib_srq_has_cq(srq->srq_type)) { srq->ext.cq = srq_init_attr->ext.cq; atomic_inc(&srq->ext.cq->usecnt); } if (srq->srq_type == IB_SRQT_XRC) { srq->ext.xrc.xrcd = srq_init_attr->ext.xrc.xrcd; if (srq->ext.xrc.xrcd) atomic_inc(&srq->ext.xrc.xrcd->usecnt); } atomic_inc(&pd->usecnt); rdma_restrack_new(&srq->res, RDMA_RESTRACK_SRQ); rdma_restrack_parent_name(&srq->res, &pd->res); ret = pd->device->ops.create_srq(srq, srq_init_attr, udata); if (ret) { rdma_restrack_put(&srq->res); atomic_dec(&pd->usecnt); if (srq->srq_type == IB_SRQT_XRC && srq->ext.xrc.xrcd) atomic_dec(&srq->ext.xrc.xrcd->usecnt); if (ib_srq_has_cq(srq->srq_type)) atomic_dec(&srq->ext.cq->usecnt); kfree(srq); return ERR_PTR(ret); } rdma_restrack_add(&srq->res); return srq; } EXPORT_SYMBOL(ib_create_srq_user); int ib_modify_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr, enum ib_srq_attr_mask srq_attr_mask) { return srq->device->ops.modify_srq ? srq->device->ops.modify_srq(srq, srq_attr, srq_attr_mask, NULL) : -EOPNOTSUPP; } EXPORT_SYMBOL(ib_modify_srq); int ib_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr) { return srq->device->ops.query_srq ? srq->device->ops.query_srq(srq, srq_attr) : -EOPNOTSUPP; } EXPORT_SYMBOL(ib_query_srq); int ib_destroy_srq_user(struct ib_srq *srq, struct ib_udata *udata) { int ret; if (atomic_read(&srq->usecnt)) return -EBUSY; ret = srq->device->ops.destroy_srq(srq, udata); if (ret) return ret; atomic_dec(&srq->pd->usecnt); if (srq->srq_type == IB_SRQT_XRC && srq->ext.xrc.xrcd) atomic_dec(&srq->ext.xrc.xrcd->usecnt); if (ib_srq_has_cq(srq->srq_type)) atomic_dec(&srq->ext.cq->usecnt); rdma_restrack_del(&srq->res); kfree(srq); return ret; } EXPORT_SYMBOL(ib_destroy_srq_user); /* Queue pairs */ static void __ib_qp_event_handler(struct ib_event *event, void *context) { struct ib_qp *qp = event->element.qp; if (event->event == IB_EVENT_QP_LAST_WQE_REACHED) complete(&qp->srq_completion); if (qp->registered_event_handler) qp->registered_event_handler(event, qp->qp_context); } static void __ib_shared_qp_event_handler(struct ib_event *event, void *context) { struct ib_qp *qp = context; unsigned long flags; spin_lock_irqsave(&qp->device->qp_open_list_lock, flags); list_for_each_entry(event->element.qp, &qp->open_list, open_list) if (event->element.qp->event_handler) event->element.qp->event_handler(event, event->element.qp->qp_context); spin_unlock_irqrestore(&qp->device->qp_open_list_lock, flags); } static struct ib_qp *__ib_open_qp(struct ib_qp *real_qp, void (*event_handler)(struct ib_event *, void *), void *qp_context) { struct ib_qp *qp; unsigned long flags; int err; qp = kzalloc(sizeof *qp, GFP_KERNEL); if (!qp) return ERR_PTR(-ENOMEM); qp->real_qp = real_qp; err = ib_open_shared_qp_security(qp, real_qp->device); if (err) { kfree(qp); return ERR_PTR(err); } qp->real_qp = real_qp; atomic_inc(&real_qp->usecnt); qp->device = real_qp->device; qp->event_handler = event_handler; qp->qp_context = qp_context; qp->qp_num = real_qp->qp_num; qp->qp_type = real_qp->qp_type; spin_lock_irqsave(&real_qp->device->qp_open_list_lock, flags); list_add(&qp->open_list, &real_qp->open_list); spin_unlock_irqrestore(&real_qp->device->qp_open_list_lock, flags); return qp; } struct ib_qp *ib_open_qp(struct ib_xrcd *xrcd, struct ib_qp_open_attr *qp_open_attr) { struct ib_qp *qp, *real_qp; if (qp_open_attr->qp_type != IB_QPT_XRC_TGT) return ERR_PTR(-EINVAL); down_read(&xrcd->tgt_qps_rwsem); real_qp = xa_load(&xrcd->tgt_qps, qp_open_attr->qp_num); if (!real_qp) { up_read(&xrcd->tgt_qps_rwsem); return ERR_PTR(-EINVAL); } qp = __ib_open_qp(real_qp, qp_open_attr->event_handler, qp_open_attr->qp_context); up_read(&xrcd->tgt_qps_rwsem); return qp; } EXPORT_SYMBOL(ib_open_qp); static struct ib_qp *create_xrc_qp_user(struct ib_qp *qp, struct ib_qp_init_attr *qp_init_attr) { struct ib_qp *real_qp = qp; int err; qp->event_handler = __ib_shared_qp_event_handler; qp->qp_context = qp; qp->pd = NULL; qp->send_cq = qp->recv_cq = NULL; qp->srq = NULL; qp->xrcd = qp_init_attr->xrcd; atomic_inc(&qp_init_attr->xrcd->usecnt); INIT_LIST_HEAD(&qp->open_list); qp = __ib_open_qp(real_qp, qp_init_attr->event_handler, qp_init_attr->qp_context); if (IS_ERR(qp)) return qp; err = xa_err(xa_store(&qp_init_attr->xrcd->tgt_qps, real_qp->qp_num, real_qp, GFP_KERNEL)); if (err) { ib_close_qp(qp); return ERR_PTR(err); } return qp; } static struct ib_qp *create_qp(struct ib_device *dev, struct ib_pd *pd, struct ib_qp_init_attr *attr, struct ib_udata *udata, struct ib_uqp_object *uobj, const char *caller) { struct ib_udata dummy = {}; struct ib_qp *qp; int ret; if (!dev->ops.create_qp) return ERR_PTR(-EOPNOTSUPP); qp = rdma_zalloc_drv_obj_numa(dev, ib_qp); if (!qp) return ERR_PTR(-ENOMEM); qp->device = dev; qp->pd = pd; qp->uobject = uobj; qp->real_qp = qp; qp->qp_type = attr->qp_type; qp->rwq_ind_tbl = attr->rwq_ind_tbl; qp->srq = attr->srq; qp->event_handler = __ib_qp_event_handler; qp->registered_event_handler = attr->event_handler; qp->port = attr->port_num; qp->qp_context = attr->qp_context; spin_lock_init(&qp->mr_lock); INIT_LIST_HEAD(&qp->rdma_mrs); INIT_LIST_HEAD(&qp->sig_mrs); init_completion(&qp->srq_completion); qp->send_cq = attr->send_cq; qp->recv_cq = attr->recv_cq; rdma_restrack_new(&qp->res, RDMA_RESTRACK_QP); WARN_ONCE(!udata && !caller, "Missing kernel QP owner"); rdma_restrack_set_name(&qp->res, udata ? NULL : caller); ret = dev->ops.create_qp(qp, attr, udata); if (ret) goto err_create; /* * TODO: The mlx4 internally overwrites send_cq and recv_cq. * Unfortunately, it is not an easy task to fix that driver. */ qp->send_cq = attr->send_cq; qp->recv_cq = attr->recv_cq; ret = ib_create_qp_security(qp, dev); if (ret) goto err_security; rdma_restrack_add(&qp->res); return qp; err_security: qp->device->ops.destroy_qp(qp, udata ? &dummy : NULL); err_create: rdma_restrack_put(&qp->res); kfree(qp); return ERR_PTR(ret); } /** * ib_create_qp_user - Creates a QP associated with the specified protection * domain. * @dev: IB device * @pd: The protection domain associated with the QP. * @attr: A list of initial attributes required to create the * QP. If QP creation succeeds, then the attributes are updated to * the actual capabilities of the created QP. * @udata: User data * @uobj: uverbs obect * @caller: caller's build-time module name */ struct ib_qp *ib_create_qp_user(struct ib_device *dev, struct ib_pd *pd, struct ib_qp_init_attr *attr, struct ib_udata *udata, struct ib_uqp_object *uobj, const char *caller) { struct ib_qp *qp, *xrc_qp; if (attr->qp_type == IB_QPT_XRC_TGT) qp = create_qp(dev, pd, attr, NULL, NULL, caller); else qp = create_qp(dev, pd, attr, udata, uobj, NULL); if (attr->qp_type != IB_QPT_XRC_TGT || IS_ERR(qp)) return qp; xrc_qp = create_xrc_qp_user(qp, attr); if (IS_ERR(xrc_qp)) { ib_destroy_qp(qp); return xrc_qp; } xrc_qp->uobject = uobj; return xrc_qp; } EXPORT_SYMBOL(ib_create_qp_user); void ib_qp_usecnt_inc(struct ib_qp *qp) { if (qp->pd) atomic_inc(&qp->pd->usecnt); if (qp->send_cq) atomic_inc(&qp->send_cq->usecnt); if (qp->recv_cq) atomic_inc(&qp->recv_cq->usecnt); if (qp->srq) atomic_inc(&qp->srq->usecnt); if (qp->rwq_ind_tbl) atomic_inc(&qp->rwq_ind_tbl->usecnt); } EXPORT_SYMBOL(ib_qp_usecnt_inc); void ib_qp_usecnt_dec(struct ib_qp *qp) { if (qp->rwq_ind_tbl) atomic_dec(&qp->rwq_ind_tbl->usecnt); if (qp->srq) atomic_dec(&qp->srq->usecnt); if (qp->recv_cq) atomic_dec(&qp->recv_cq->usecnt); if (qp->send_cq) atomic_dec(&qp->send_cq->usecnt); if (qp->pd) atomic_dec(&qp->pd->usecnt); } EXPORT_SYMBOL(ib_qp_usecnt_dec); struct ib_qp *ib_create_qp_kernel(struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr, const char *caller) { struct ib_device *device = pd->device; struct ib_qp *qp; int ret; /* * If the callers is using the RDMA API calculate the resources * needed for the RDMA READ/WRITE operations. * * Note that these callers need to pass in a port number. */ if (qp_init_attr->cap.max_rdma_ctxs) rdma_rw_init_qp(device, qp_init_attr); qp = create_qp(device, pd, qp_init_attr, NULL, NULL, caller); if (IS_ERR(qp)) return qp; ib_qp_usecnt_inc(qp); if (qp_init_attr->cap.max_rdma_ctxs) { ret = rdma_rw_init_mrs(qp, qp_init_attr); if (ret) goto err; } /* * Note: all hw drivers guarantee that max_send_sge is lower than * the device RDMA WRITE SGE limit but not all hw drivers ensure that * max_send_sge <= max_sge_rd. */ qp->max_write_sge = qp_init_attr->cap.max_send_sge; qp->max_read_sge = min_t(u32, qp_init_attr->cap.max_send_sge, device->attrs.max_sge_rd); if (qp_init_attr->create_flags & IB_QP_CREATE_INTEGRITY_EN) qp->integrity_en = true; return qp; err: ib_destroy_qp(qp); return ERR_PTR(ret); } EXPORT_SYMBOL(ib_create_qp_kernel); static const struct { int valid; enum ib_qp_attr_mask req_param[IB_QPT_MAX]; enum ib_qp_attr_mask opt_param[IB_QPT_MAX]; } qp_state_table[IB_QPS_ERR + 1][IB_QPS_ERR + 1] = { [IB_QPS_RESET] = { [IB_QPS_RESET] = { .valid = 1 }, [IB_QPS_INIT] = { .valid = 1, .req_param = { [IB_QPT_UD] = (IB_QP_PKEY_INDEX | IB_QP_PORT | IB_QP_QKEY), [IB_QPT_RAW_PACKET] = IB_QP_PORT, [IB_QPT_UC] = (IB_QP_PKEY_INDEX | IB_QP_PORT | IB_QP_ACCESS_FLAGS), [IB_QPT_RC] = (IB_QP_PKEY_INDEX | IB_QP_PORT | IB_QP_ACCESS_FLAGS), [IB_QPT_XRC_INI] = (IB_QP_PKEY_INDEX | IB_QP_PORT | IB_QP_ACCESS_FLAGS), [IB_QPT_XRC_TGT] = (IB_QP_PKEY_INDEX | IB_QP_PORT | IB_QP_ACCESS_FLAGS), [IB_QPT_SMI] = (IB_QP_PKEY_INDEX | IB_QP_QKEY), [IB_QPT_GSI] = (IB_QP_PKEY_INDEX | IB_QP_QKEY), } }, }, [IB_QPS_INIT] = { [IB_QPS_RESET] = { .valid = 1 }, [IB_QPS_ERR] = { .valid = 1 }, [IB_QPS_INIT] = { .valid = 1, .opt_param = { [IB_QPT_UD] = (IB_QP_PKEY_INDEX | IB_QP_PORT | IB_QP_QKEY), [IB_QPT_UC] = (IB_QP_PKEY_INDEX | IB_QP_PORT | IB_QP_ACCESS_FLAGS), [IB_QPT_RC] = (IB_QP_PKEY_INDEX | IB_QP_PORT | IB_QP_ACCESS_FLAGS), [IB_QPT_XRC_INI] = (IB_QP_PKEY_INDEX | IB_QP_PORT | IB_QP_ACCESS_FLAGS), [IB_QPT_XRC_TGT] = (IB_QP_PKEY_INDEX | IB_QP_PORT | IB_QP_ACCESS_FLAGS), [IB_QPT_SMI] = (IB_QP_PKEY_INDEX | IB_QP_QKEY), [IB_QPT_GSI] = (IB_QP_PKEY_INDEX | IB_QP_QKEY), } }, [IB_QPS_RTR] = { .valid = 1, .req_param = { [IB_QPT_UC] = (IB_QP_AV | IB_QP_PATH_MTU | IB_QP_DEST_QPN | IB_QP_RQ_PSN), [IB_QPT_RC] = (IB_QP_AV | IB_QP_PATH_MTU | IB_QP_DEST_QPN | IB_QP_RQ_PSN | IB_QP_MAX_DEST_RD_ATOMIC | IB_QP_MIN_RNR_TIMER), [IB_QPT_XRC_INI] = (IB_QP_AV | IB_QP_PATH_MTU | IB_QP_DEST_QPN | IB_QP_RQ_PSN), [IB_QPT_XRC_TGT] = (IB_QP_AV | IB_QP_PATH_MTU | IB_QP_DEST_QPN | IB_QP_RQ_PSN | IB_QP_MAX_DEST_RD_ATOMIC | IB_QP_MIN_RNR_TIMER), }, .opt_param = { [IB_QPT_UD] = (IB_QP_PKEY_INDEX | IB_QP_QKEY), [IB_QPT_UC] = (IB_QP_ALT_PATH | IB_QP_ACCESS_FLAGS | IB_QP_PKEY_INDEX), [IB_QPT_RC] = (IB_QP_ALT_PATH | IB_QP_ACCESS_FLAGS | IB_QP_PKEY_INDEX), [IB_QPT_XRC_INI] = (IB_QP_ALT_PATH | IB_QP_ACCESS_FLAGS | IB_QP_PKEY_INDEX), [IB_QPT_XRC_TGT] = (IB_QP_ALT_PATH | IB_QP_ACCESS_FLAGS | IB_QP_PKEY_INDEX), [IB_QPT_SMI] = (IB_QP_PKEY_INDEX | IB_QP_QKEY), [IB_QPT_GSI] = (IB_QP_PKEY_INDEX | IB_QP_QKEY), }, }, }, [IB_QPS_RTR] = { [IB_QPS_RESET] = { .valid = 1 }, [IB_QPS_ERR] = { .valid = 1 }, [IB_QPS_RTS] = { .valid = 1, .req_param = { [IB_QPT_UD] = IB_QP_SQ_PSN, [IB_QPT_UC] = IB_QP_SQ_PSN, [IB_QPT_RC] = (IB_QP_TIMEOUT | IB_QP_RETRY_CNT | IB_QP_RNR_RETRY | IB_QP_SQ_PSN | IB_QP_MAX_QP_RD_ATOMIC), [IB_QPT_XRC_INI] = (IB_QP_TIMEOUT | IB_QP_RETRY_CNT | IB_QP_RNR_RETRY | IB_QP_SQ_PSN | IB_QP_MAX_QP_RD_ATOMIC), [IB_QPT_XRC_TGT] = (IB_QP_TIMEOUT | IB_QP_SQ_PSN), [IB_QPT_SMI] = IB_QP_SQ_PSN, [IB_QPT_GSI] = IB_QP_SQ_PSN, }, .opt_param = { [IB_QPT_UD] = (IB_QP_CUR_STATE | IB_QP_QKEY), [IB_QPT_UC] = (IB_QP_CUR_STATE | IB_QP_ALT_PATH | IB_QP_ACCESS_FLAGS | IB_QP_PATH_MIG_STATE), [IB_QPT_RC] = (IB_QP_CUR_STATE | IB_QP_ALT_PATH | IB_QP_ACCESS_FLAGS | IB_QP_MIN_RNR_TIMER | IB_QP_PATH_MIG_STATE), [IB_QPT_XRC_INI] = (IB_QP_CUR_STATE | IB_QP_ALT_PATH | IB_QP_ACCESS_FLAGS | IB_QP_PATH_MIG_STATE), [IB_QPT_XRC_TGT] = (IB_QP_CUR_STATE | IB_QP_ALT_PATH | IB_QP_ACCESS_FLAGS | IB_QP_MIN_RNR_TIMER | IB_QP_PATH_MIG_STATE), [IB_QPT_SMI] = (IB_QP_CUR_STATE | IB_QP_QKEY), [IB_QPT_GSI] = (IB_QP_CUR_STATE | IB_QP_QKEY), [IB_QPT_RAW_PACKET] = IB_QP_RATE_LIMIT, } } }, [IB_QPS_RTS] = { [IB_QPS_RESET] = { .valid = 1 }, [IB_QPS_ERR] = { .valid = 1 }, [IB_QPS_RTS] = { .valid = 1, .opt_param = { [IB_QPT_UD] = (IB_QP_CUR_STATE | IB_QP_QKEY), [IB_QPT_UC] = (IB_QP_CUR_STATE | IB_QP_ACCESS_FLAGS | IB_QP_ALT_PATH | IB_QP_PATH_MIG_STATE), [IB_QPT_RC] = (IB_QP_CUR_STATE | IB_QP_ACCESS_FLAGS | IB_QP_ALT_PATH | IB_QP_PATH_MIG_STATE | IB_QP_MIN_RNR_TIMER), [IB_QPT_XRC_INI] = (IB_QP_CUR_STATE | IB_QP_ACCESS_FLAGS | IB_QP_ALT_PATH | IB_QP_PATH_MIG_STATE), [IB_QPT_XRC_TGT] = (IB_QP_CUR_STATE | IB_QP_ACCESS_FLAGS | IB_QP_ALT_PATH | IB_QP_PATH_MIG_STATE | IB_QP_MIN_RNR_TIMER), [IB_QPT_SMI] = (IB_QP_CUR_STATE | IB_QP_QKEY), [IB_QPT_GSI] = (IB_QP_CUR_STATE | IB_QP_QKEY), [IB_QPT_RAW_PACKET] = IB_QP_RATE_LIMIT, } }, [IB_QPS_SQD] = { .valid = 1, .opt_param = { [IB_QPT_UD] = IB_QP_EN_SQD_ASYNC_NOTIFY, [IB_QPT_UC] = IB_QP_EN_SQD_ASYNC_NOTIFY, [IB_QPT_RC] = IB_QP_EN_SQD_ASYNC_NOTIFY, [IB_QPT_XRC_INI] = IB_QP_EN_SQD_ASYNC_NOTIFY, [IB_QPT_XRC_TGT] = IB_QP_EN_SQD_ASYNC_NOTIFY, /* ??? */ [IB_QPT_SMI] = IB_QP_EN_SQD_ASYNC_NOTIFY, [IB_QPT_GSI] = IB_QP_EN_SQD_ASYNC_NOTIFY } }, }, [IB_QPS_SQD] = { [IB_QPS_RESET] = { .valid = 1 }, [IB_QPS_ERR] = { .valid = 1 }, [IB_QPS_RTS] = { .valid = 1, .opt_param = { [IB_QPT_UD] = (IB_QP_CUR_STATE | IB_QP_QKEY), [IB_QPT_UC] = (IB_QP_CUR_STATE | IB_QP_ALT_PATH | IB_QP_ACCESS_FLAGS | IB_QP_PATH_MIG_STATE), [IB_QPT_RC] = (IB_QP_CUR_STATE | IB_QP_ALT_PATH | IB_QP_ACCESS_FLAGS | IB_QP_MIN_RNR_TIMER | IB_QP_PATH_MIG_STATE), [IB_QPT_XRC_INI] = (IB_QP_CUR_STATE | IB_QP_ALT_PATH | IB_QP_ACCESS_FLAGS | IB_QP_PATH_MIG_STATE), [IB_QPT_XRC_TGT] = (IB_QP_CUR_STATE | IB_QP_ALT_PATH | IB_QP_ACCESS_FLAGS | IB_QP_MIN_RNR_TIMER | IB_QP_PATH_MIG_STATE), [IB_QPT_SMI] = (IB_QP_CUR_STATE | IB_QP_QKEY), [IB_QPT_GSI] = (IB_QP_CUR_STATE | IB_QP_QKEY), } }, [IB_QPS_SQD] = { .valid = 1, .opt_param = { [IB_QPT_UD] = (IB_QP_PKEY_INDEX | IB_QP_QKEY), [IB_QPT_UC] = (IB_QP_AV | IB_QP_ALT_PATH | IB_QP_ACCESS_FLAGS | IB_QP_PKEY_INDEX | IB_QP_PATH_MIG_STATE), [IB_QPT_RC] = (IB_QP_PORT | IB_QP_AV | IB_QP_TIMEOUT | IB_QP_RETRY_CNT | IB_QP_RNR_RETRY | IB_QP_MAX_QP_RD_ATOMIC | IB_QP_MAX_DEST_RD_ATOMIC | IB_QP_ALT_PATH | IB_QP_ACCESS_FLAGS | IB_QP_PKEY_INDEX | IB_QP_MIN_RNR_TIMER | IB_QP_PATH_MIG_STATE), [IB_QPT_XRC_INI] = (IB_QP_PORT | IB_QP_AV | IB_QP_TIMEOUT | IB_QP_RETRY_CNT | IB_QP_RNR_RETRY | IB_QP_MAX_QP_RD_ATOMIC | IB_QP_ALT_PATH | IB_QP_ACCESS_FLAGS | IB_QP_PKEY_INDEX | IB_QP_PATH_MIG_STATE), [IB_QPT_XRC_TGT] = (IB_QP_PORT | IB_QP_AV | IB_QP_TIMEOUT | IB_QP_MAX_DEST_RD_ATOMIC | IB_QP_ALT_PATH | IB_QP_ACCESS_FLAGS | IB_QP_PKEY_INDEX | IB_QP_MIN_RNR_TIMER | IB_QP_PATH_MIG_STATE), [IB_QPT_SMI] = (IB_QP_PKEY_INDEX | IB_QP_QKEY), [IB_QPT_GSI] = (IB_QP_PKEY_INDEX | IB_QP_QKEY), } } }, [IB_QPS_SQE] = { [IB_QPS_RESET] = { .valid = 1 }, [IB_QPS_ERR] = { .valid = 1 }, [IB_QPS_RTS] = { .valid = 1, .opt_param = { [IB_QPT_UD] = (IB_QP_CUR_STATE | IB_QP_QKEY), [IB_QPT_UC] = (IB_QP_CUR_STATE | IB_QP_ACCESS_FLAGS), [IB_QPT_SMI] = (IB_QP_CUR_STATE | IB_QP_QKEY), [IB_QPT_GSI] = (IB_QP_CUR_STATE | IB_QP_QKEY), } } }, [IB_QPS_ERR] = { [IB_QPS_RESET] = { .valid = 1 }, [IB_QPS_ERR] = { .valid = 1 } } }; bool ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state, enum ib_qp_type type, enum ib_qp_attr_mask mask) { enum ib_qp_attr_mask req_param, opt_param; if (mask & IB_QP_CUR_STATE && cur_state != IB_QPS_RTR && cur_state != IB_QPS_RTS && cur_state != IB_QPS_SQD && cur_state != IB_QPS_SQE) return false; if (!qp_state_table[cur_state][next_state].valid) return false; req_param = qp_state_table[cur_state][next_state].req_param[type]; opt_param = qp_state_table[cur_state][next_state].opt_param[type]; if ((mask & req_param) != req_param) return false; if (mask & ~(req_param | opt_param | IB_QP_STATE)) return false; return true; } EXPORT_SYMBOL(ib_modify_qp_is_ok); /** * ib_resolve_eth_dmac - Resolve destination mac address * @device: Device to consider * @ah_attr: address handle attribute which describes the * source and destination parameters * ib_resolve_eth_dmac() resolves destination mac address and L3 hop limit It * returns 0 on success or appropriate error code. It initializes the * necessary ah_attr fields when call is successful. */ static int ib_resolve_eth_dmac(struct ib_device *device, struct rdma_ah_attr *ah_attr) { int ret = 0; if (rdma_is_multicast_addr((struct in6_addr *)ah_attr->grh.dgid.raw)) { if (ipv6_addr_v4mapped((struct in6_addr *)ah_attr->grh.dgid.raw)) { __be32 addr = 0; memcpy(&addr, ah_attr->grh.dgid.raw + 12, 4); ip_eth_mc_map(addr, (char *)ah_attr->roce.dmac); } else { ipv6_eth_mc_map((struct in6_addr *)ah_attr->grh.dgid.raw, (char *)ah_attr->roce.dmac); } } else { ret = ib_resolve_unicast_gid_dmac(device, ah_attr); } return ret; } static bool is_qp_type_connected(const struct ib_qp *qp) { return (qp->qp_type == IB_QPT_UC || qp->qp_type == IB_QPT_RC || qp->qp_type == IB_QPT_XRC_INI || qp->qp_type == IB_QPT_XRC_TGT); } /* * IB core internal function to perform QP attributes modification. */ static int _ib_modify_qp(struct ib_qp *qp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata) { u32 port = attr_mask & IB_QP_PORT ? attr->port_num : qp->port; const struct ib_gid_attr *old_sgid_attr_av; const struct ib_gid_attr *old_sgid_attr_alt_av; int ret; attr->xmit_slave = NULL; if (attr_mask & IB_QP_AV) { ret = rdma_fill_sgid_attr(qp->device, &attr->ah_attr, &old_sgid_attr_av); if (ret) return ret; if (attr->ah_attr.type == RDMA_AH_ATTR_TYPE_ROCE && is_qp_type_connected(qp)) { struct net_device *slave; /* * If the user provided the qp_attr then we have to * resolve it. Kerne users have to provide already * resolved rdma_ah_attr's. */ if (udata) { ret = ib_resolve_eth_dmac(qp->device, &attr->ah_attr); if (ret) goto out_av; } slave = rdma_lag_get_ah_roce_slave(qp->device, &attr->ah_attr, GFP_KERNEL); if (IS_ERR(slave)) { ret = PTR_ERR(slave); goto out_av; } attr->xmit_slave = slave; } } if (attr_mask & IB_QP_ALT_PATH) { /* * FIXME: This does not track the migration state, so if the * user loads a new alternate path after the HW has migrated * from primary->alternate we will keep the wrong * references. This is OK for IB because the reference * counting does not serve any functional purpose. */ ret = rdma_fill_sgid_attr(qp->device, &attr->alt_ah_attr, &old_sgid_attr_alt_av); if (ret) goto out_av; /* * Today the core code can only handle alternate paths and APM * for IB. Ban them in roce mode. */ if (!(rdma_protocol_ib(qp->device, attr->alt_ah_attr.port_num) && rdma_protocol_ib(qp->device, port))) { ret = -EINVAL; goto out; } } if (rdma_ib_or_roce(qp->device, port)) { if (attr_mask & IB_QP_RQ_PSN && attr->rq_psn & ~0xffffff) { dev_warn(&qp->device->dev, "%s rq_psn overflow, masking to 24 bits\n", __func__); attr->rq_psn &= 0xffffff; } if (attr_mask & IB_QP_SQ_PSN && attr->sq_psn & ~0xffffff) { dev_warn(&qp->device->dev, " %s sq_psn overflow, masking to 24 bits\n", __func__); attr->sq_psn &= 0xffffff; } } /* * Bind this qp to a counter automatically based on the rdma counter * rules. This only set in RST2INIT with port specified */ if (!qp->counter && (attr_mask & IB_QP_PORT) && ((attr_mask & IB_QP_STATE) && attr->qp_state == IB_QPS_INIT)) rdma_counter_bind_qp_auto(qp, attr->port_num); ret = ib_security_modify_qp(qp, attr, attr_mask, udata); if (ret) goto out; if (attr_mask & IB_QP_PORT) qp->port = attr->port_num; if (attr_mask & IB_QP_AV) qp->av_sgid_attr = rdma_update_sgid_attr(&attr->ah_attr, qp->av_sgid_attr); if (attr_mask & IB_QP_ALT_PATH) qp->alt_path_sgid_attr = rdma_update_sgid_attr( &attr->alt_ah_attr, qp->alt_path_sgid_attr); out: if (attr_mask & IB_QP_ALT_PATH) rdma_unfill_sgid_attr(&attr->alt_ah_attr, old_sgid_attr_alt_av); out_av: if (attr_mask & IB_QP_AV) { rdma_lag_put_ah_roce_slave(attr->xmit_slave); rdma_unfill_sgid_attr(&attr->ah_attr, old_sgid_attr_av); } return ret; } /** * ib_modify_qp_with_udata - Modifies the attributes for the specified QP. * @ib_qp: The QP to modify. * @attr: On input, specifies the QP attributes to modify. On output, * the current values of selected QP attributes are returned. * @attr_mask: A bit-mask used to specify which attributes of the QP * are being modified. * @udata: pointer to user's input output buffer information * are being modified. * It returns 0 on success and returns appropriate error code on error. */ int ib_modify_qp_with_udata(struct ib_qp *ib_qp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata) { return _ib_modify_qp(ib_qp->real_qp, attr, attr_mask, udata); } EXPORT_SYMBOL(ib_modify_qp_with_udata); static void ib_get_width_and_speed(u32 netdev_speed, u32 lanes, u16 *speed, u8 *width) { if (!lanes) { if (netdev_speed <= SPEED_1000) { *width = IB_WIDTH_1X; *speed = IB_SPEED_SDR; } else if (netdev_speed <= SPEED_10000) { *width = IB_WIDTH_1X; *speed = IB_SPEED_FDR10; } else if (netdev_speed <= SPEED_20000) { *width = IB_WIDTH_4X; *speed = IB_SPEED_DDR; } else if (netdev_speed <= SPEED_25000) { *width = IB_WIDTH_1X; *speed = IB_SPEED_EDR; } else if (netdev_speed <= SPEED_40000) { *width = IB_WIDTH_4X; *speed = IB_SPEED_FDR10; } else if (netdev_speed <= SPEED_50000) { *width = IB_WIDTH_2X; *speed = IB_SPEED_EDR; } else if (netdev_speed <= SPEED_100000) { *width = IB_WIDTH_4X; *speed = IB_SPEED_EDR; } else if (netdev_speed <= SPEED_200000) { *width = IB_WIDTH_4X; *speed = IB_SPEED_HDR; } else { *width = IB_WIDTH_4X; *speed = IB_SPEED_NDR; } return; } switch (lanes) { case 1: *width = IB_WIDTH_1X; break; case 2: *width = IB_WIDTH_2X; break; case 4: *width = IB_WIDTH_4X; break; case 8: *width = IB_WIDTH_8X; break; case 12: *width = IB_WIDTH_12X; break; default: *width = IB_WIDTH_1X; } switch (netdev_speed / lanes) { case SPEED_2500: *speed = IB_SPEED_SDR; break; case SPEED_5000: *speed = IB_SPEED_DDR; break; case SPEED_10000: *speed = IB_SPEED_FDR10; break; case SPEED_14000: *speed = IB_SPEED_FDR; break; case SPEED_25000: *speed = IB_SPEED_EDR; break; case SPEED_50000: *speed = IB_SPEED_HDR; break; case SPEED_100000: *speed = IB_SPEED_NDR; break; default: *speed = IB_SPEED_SDR; } } int ib_get_eth_speed(struct ib_device *dev, u32 port_num, u16 *speed, u8 *width) { int rc; u32 netdev_speed; struct net_device *netdev; struct ethtool_link_ksettings lksettings = {}; if (rdma_port_get_link_layer(dev, port_num) != IB_LINK_LAYER_ETHERNET) return -EINVAL; netdev = ib_device_get_netdev(dev, port_num); if (!netdev) return -ENODEV; rtnl_lock(); rc = __ethtool_get_link_ksettings(netdev, &lksettings); rtnl_unlock(); dev_put(netdev); if (!rc && lksettings.base.speed != (u32)SPEED_UNKNOWN) { netdev_speed = lksettings.base.speed; } else { netdev_speed = SPEED_1000; if (rc) pr_warn("%s speed is unknown, defaulting to %u\n", netdev->name, netdev_speed); } ib_get_width_and_speed(netdev_speed, lksettings.lanes, speed, width); return 0; } EXPORT_SYMBOL(ib_get_eth_speed); int ib_modify_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask) { return _ib_modify_qp(qp->real_qp, qp_attr, qp_attr_mask, NULL); } EXPORT_SYMBOL(ib_modify_qp); int ib_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr) { qp_attr->ah_attr.grh.sgid_attr = NULL; qp_attr->alt_ah_attr.grh.sgid_attr = NULL; return qp->device->ops.query_qp ? qp->device->ops.query_qp(qp->real_qp, qp_attr, qp_attr_mask, qp_init_attr) : -EOPNOTSUPP; } EXPORT_SYMBOL(ib_query_qp); int ib_close_qp(struct ib_qp *qp) { struct ib_qp *real_qp; unsigned long flags; real_qp = qp->real_qp; if (real_qp == qp) return -EINVAL; spin_lock_irqsave(&real_qp->device->qp_open_list_lock, flags); list_del(&qp->open_list); spin_unlock_irqrestore(&real_qp->device->qp_open_list_lock, flags); atomic_dec(&real_qp->usecnt); if (qp->qp_sec) ib_close_shared_qp_security(qp->qp_sec); kfree(qp); return 0; } EXPORT_SYMBOL(ib_close_qp); static int __ib_destroy_shared_qp(struct ib_qp *qp) { struct ib_xrcd *xrcd; struct ib_qp *real_qp; int ret; real_qp = qp->real_qp; xrcd = real_qp->xrcd; down_write(&xrcd->tgt_qps_rwsem); ib_close_qp(qp); if (atomic_read(&real_qp->usecnt) == 0) xa_erase(&xrcd->tgt_qps, real_qp->qp_num); else real_qp = NULL; up_write(&xrcd->tgt_qps_rwsem); if (real_qp) { ret = ib_destroy_qp(real_qp); if (!ret) atomic_dec(&xrcd->usecnt); } return 0; } int ib_destroy_qp_user(struct ib_qp *qp, struct ib_udata *udata) { const struct ib_gid_attr *alt_path_sgid_attr = qp->alt_path_sgid_attr; const struct ib_gid_attr *av_sgid_attr = qp->av_sgid_attr; struct ib_qp_security *sec; int ret; WARN_ON_ONCE(qp->mrs_used > 0); if (atomic_read(&qp->usecnt)) return -EBUSY; if (qp->real_qp != qp) return __ib_destroy_shared_qp(qp); sec = qp->qp_sec; if (sec) ib_destroy_qp_security_begin(sec); if (!qp->uobject) rdma_rw_cleanup_mrs(qp); rdma_counter_unbind_qp(qp, true); ret = qp->device->ops.destroy_qp(qp, udata); if (ret) { if (sec) ib_destroy_qp_security_abort(sec); return ret; } if (alt_path_sgid_attr) rdma_put_gid_attr(alt_path_sgid_attr); if (av_sgid_attr) rdma_put_gid_attr(av_sgid_attr); ib_qp_usecnt_dec(qp); if (sec) ib_destroy_qp_security_end(sec); rdma_restrack_del(&qp->res); kfree(qp); return ret; } EXPORT_SYMBOL(ib_destroy_qp_user); /* Completion queues */ struct ib_cq *__ib_create_cq(struct ib_device *device, ib_comp_handler comp_handler, void (*event_handler)(struct ib_event *, void *), void *cq_context, const struct ib_cq_init_attr *cq_attr, const char *caller) { struct ib_cq *cq; int ret; cq = rdma_zalloc_drv_obj(device, ib_cq); if (!cq) return ERR_PTR(-ENOMEM); cq->device = device; cq->uobject = NULL; cq->comp_handler = comp_handler; cq->event_handler = event_handler; cq->cq_context = cq_context; atomic_set(&cq->usecnt, 0); rdma_restrack_new(&cq->res, RDMA_RESTRACK_CQ); rdma_restrack_set_name(&cq->res, caller); ret = device->ops.create_cq(cq, cq_attr, NULL); if (ret) { rdma_restrack_put(&cq->res); kfree(cq); return ERR_PTR(ret); } rdma_restrack_add(&cq->res); return cq; } EXPORT_SYMBOL(__ib_create_cq); int rdma_set_cq_moderation(struct ib_cq *cq, u16 cq_count, u16 cq_period) { if (cq->shared) return -EOPNOTSUPP; return cq->device->ops.modify_cq ? cq->device->ops.modify_cq(cq, cq_count, cq_period) : -EOPNOTSUPP; } EXPORT_SYMBOL(rdma_set_cq_moderation); int ib_destroy_cq_user(struct ib_cq *cq, struct ib_udata *udata) { int ret; if (WARN_ON_ONCE(cq->shared)) return -EOPNOTSUPP; if (atomic_read(&cq->usecnt)) return -EBUSY; ret = cq->device->ops.destroy_cq(cq, udata); if (ret) return ret; rdma_restrack_del(&cq->res); kfree(cq); return ret; } EXPORT_SYMBOL(ib_destroy_cq_user); int ib_resize_cq(struct ib_cq *cq, int cqe) { if (cq->shared) return -EOPNOTSUPP; return cq->device->ops.resize_cq ? cq->device->ops.resize_cq(cq, cqe, NULL) : -EOPNOTSUPP; } EXPORT_SYMBOL(ib_resize_cq); /* Memory regions */ struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int access_flags) { struct ib_mr *mr; if (access_flags & IB_ACCESS_ON_DEMAND) { if (!(pd->device->attrs.kernel_cap_flags & IBK_ON_DEMAND_PAGING)) { pr_debug("ODP support not available\n"); return ERR_PTR(-EINVAL); } } mr = pd->device->ops.reg_user_mr(pd, start, length, virt_addr, access_flags, NULL); if (IS_ERR(mr)) return mr; mr->device = pd->device; mr->type = IB_MR_TYPE_USER; mr->pd = pd; mr->dm = NULL; atomic_inc(&pd->usecnt); mr->iova = virt_addr; mr->length = length; rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR); rdma_restrack_parent_name(&mr->res, &pd->res); rdma_restrack_add(&mr->res); return mr; } EXPORT_SYMBOL(ib_reg_user_mr); int ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice, u32 flags, struct ib_sge *sg_list, u32 num_sge) { if (!pd->device->ops.advise_mr) return -EOPNOTSUPP; if (!num_sge) return 0; return pd->device->ops.advise_mr(pd, advice, flags, sg_list, num_sge, NULL); } EXPORT_SYMBOL(ib_advise_mr); int ib_dereg_mr_user(struct ib_mr *mr, struct ib_udata *udata) { struct ib_pd *pd = mr->pd; struct ib_dm *dm = mr->dm; struct ib_sig_attrs *sig_attrs = mr->sig_attrs; int ret; trace_mr_dereg(mr); rdma_restrack_del(&mr->res); ret = mr->device->ops.dereg_mr(mr, udata); if (!ret) { atomic_dec(&pd->usecnt); if (dm) atomic_dec(&dm->usecnt); kfree(sig_attrs); } return ret; } EXPORT_SYMBOL(ib_dereg_mr_user); /** * ib_alloc_mr() - Allocates a memory region * @pd: protection domain associated with the region * @mr_type: memory region type * @max_num_sg: maximum sg entries available for registration. * * Notes: * Memory registeration page/sg lists must not exceed max_num_sg. * For mr_type IB_MR_TYPE_MEM_REG, the total length cannot exceed * max_num_sg * used_page_size. * */ struct ib_mr *ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg) { struct ib_mr *mr; if (!pd->device->ops.alloc_mr) { mr = ERR_PTR(-EOPNOTSUPP); goto out; } if (mr_type == IB_MR_TYPE_INTEGRITY) { WARN_ON_ONCE(1); mr = ERR_PTR(-EINVAL); goto out; } mr = pd->device->ops.alloc_mr(pd, mr_type, max_num_sg); if (IS_ERR(mr)) goto out; mr->device = pd->device; mr->pd = pd; mr->dm = NULL; mr->uobject = NULL; atomic_inc(&pd->usecnt); mr->need_inval = false; mr->type = mr_type; mr->sig_attrs = NULL; rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR); rdma_restrack_parent_name(&mr->res, &pd->res); rdma_restrack_add(&mr->res); out: trace_mr_alloc(pd, mr_type, max_num_sg, mr); return mr; } EXPORT_SYMBOL(ib_alloc_mr); /** * ib_alloc_mr_integrity() - Allocates an integrity memory region * @pd: protection domain associated with the region * @max_num_data_sg: maximum data sg entries available for registration * @max_num_meta_sg: maximum metadata sg entries available for * registration * * Notes: * Memory registration page/sg lists must not exceed max_num_sg, * also the integrity page/sg lists must not exceed max_num_meta_sg. * */ struct ib_mr *ib_alloc_mr_integrity(struct ib_pd *pd, u32 max_num_data_sg, u32 max_num_meta_sg) { struct ib_mr *mr; struct ib_sig_attrs *sig_attrs; if (!pd->device->ops.alloc_mr_integrity || !pd->device->ops.map_mr_sg_pi) { mr = ERR_PTR(-EOPNOTSUPP); goto out; } if (!max_num_meta_sg) { mr = ERR_PTR(-EINVAL); goto out; } sig_attrs = kzalloc(sizeof(struct ib_sig_attrs), GFP_KERNEL); if (!sig_attrs) { mr = ERR_PTR(-ENOMEM); goto out; } mr = pd->device->ops.alloc_mr_integrity(pd, max_num_data_sg, max_num_meta_sg); if (IS_ERR(mr)) { kfree(sig_attrs); goto out; } mr->device = pd->device; mr->pd = pd; mr->dm = NULL; mr->uobject = NULL; atomic_inc(&pd->usecnt); mr->need_inval = false; mr->type = IB_MR_TYPE_INTEGRITY; mr->sig_attrs = sig_attrs; rdma_restrack_new(&mr->res, RDMA_RESTRACK_MR); rdma_restrack_parent_name(&mr->res, &pd->res); rdma_restrack_add(&mr->res); out: trace_mr_integ_alloc(pd, max_num_data_sg, max_num_meta_sg, mr); return mr; } EXPORT_SYMBOL(ib_alloc_mr_integrity); /* Multicast groups */ static bool is_valid_mcast_lid(struct ib_qp *qp, u16 lid) { struct ib_qp_init_attr init_attr = {}; struct ib_qp_attr attr = {}; int num_eth_ports = 0; unsigned int port; /* If QP state >= init, it is assigned to a port and we can check this * port only. */ if (!ib_query_qp(qp, &attr, IB_QP_STATE | IB_QP_PORT, &init_attr)) { if (attr.qp_state >= IB_QPS_INIT) { if (rdma_port_get_link_layer(qp->device, attr.port_num) != IB_LINK_LAYER_INFINIBAND) return true; goto lid_check; } } /* Can't get a quick answer, iterate over all ports */ rdma_for_each_port(qp->device, port) if (rdma_port_get_link_layer(qp->device, port) != IB_LINK_LAYER_INFINIBAND) num_eth_ports++; /* If we have at lease one Ethernet port, RoCE annex declares that * multicast LID should be ignored. We can't tell at this step if the * QP belongs to an IB or Ethernet port. */ if (num_eth_ports) return true; /* If all the ports are IB, we can check according to IB spec. */ lid_check: return !(lid < be16_to_cpu(IB_MULTICAST_LID_BASE) || lid == be16_to_cpu(IB_LID_PERMISSIVE)); } int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid) { int ret; if (!qp->device->ops.attach_mcast) return -EOPNOTSUPP; if (!rdma_is_multicast_addr((struct in6_addr *)gid->raw) || qp->qp_type != IB_QPT_UD || !is_valid_mcast_lid(qp, lid)) return -EINVAL; ret = qp->device->ops.attach_mcast(qp, gid, lid); if (!ret) atomic_inc(&qp->usecnt); return ret; } EXPORT_SYMBOL(ib_attach_mcast); int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid) { int ret; if (!qp->device->ops.detach_mcast) return -EOPNOTSUPP; if (!rdma_is_multicast_addr((struct in6_addr *)gid->raw) || qp->qp_type != IB_QPT_UD || !is_valid_mcast_lid(qp, lid)) return -EINVAL; ret = qp->device->ops.detach_mcast(qp, gid, lid); if (!ret) atomic_dec(&qp->usecnt); return ret; } EXPORT_SYMBOL(ib_detach_mcast); /** * ib_alloc_xrcd_user - Allocates an XRC domain. * @device: The device on which to allocate the XRC domain. * @inode: inode to connect XRCD * @udata: Valid user data or NULL for kernel object */ struct ib_xrcd *ib_alloc_xrcd_user(struct ib_device *device, struct inode *inode, struct ib_udata *udata) { struct ib_xrcd *xrcd; int ret; if (!device->ops.alloc_xrcd) return ERR_PTR(-EOPNOTSUPP); xrcd = rdma_zalloc_drv_obj(device, ib_xrcd); if (!xrcd) return ERR_PTR(-ENOMEM); xrcd->device = device; xrcd->inode = inode; atomic_set(&xrcd->usecnt, 0); init_rwsem(&xrcd->tgt_qps_rwsem); xa_init(&xrcd->tgt_qps); ret = device->ops.alloc_xrcd(xrcd, udata); if (ret) goto err; return xrcd; err: kfree(xrcd); return ERR_PTR(ret); } EXPORT_SYMBOL(ib_alloc_xrcd_user); /** * ib_dealloc_xrcd_user - Deallocates an XRC domain. * @xrcd: The XRC domain to deallocate. * @udata: Valid user data or NULL for kernel object */ int ib_dealloc_xrcd_user(struct ib_xrcd *xrcd, struct ib_udata *udata) { int ret; if (atomic_read(&xrcd->usecnt)) return -EBUSY; WARN_ON(!xa_empty(&xrcd->tgt_qps)); ret = xrcd->device->ops.dealloc_xrcd(xrcd, udata); if (ret) return ret; kfree(xrcd); return ret; } EXPORT_SYMBOL(ib_dealloc_xrcd_user); /** * ib_create_wq - Creates a WQ associated with the specified protection * domain. * @pd: The protection domain associated with the WQ. * @wq_attr: A list of initial attributes required to create the * WQ. If WQ creation succeeds, then the attributes are updated to * the actual capabilities of the created WQ. * * wq_attr->max_wr and wq_attr->max_sge determine * the requested size of the WQ, and set to the actual values allocated * on return. * If ib_create_wq() succeeds, then max_wr and max_sge will always be * at least as large as the requested values. */ struct ib_wq *ib_create_wq(struct ib_pd *pd, struct ib_wq_init_attr *wq_attr) { struct ib_wq *wq; if (!pd->device->ops.create_wq) return ERR_PTR(-EOPNOTSUPP); wq = pd->device->ops.create_wq(pd, wq_attr, NULL); if (!IS_ERR(wq)) { wq->event_handler = wq_attr->event_handler; wq->wq_context = wq_attr->wq_context; wq->wq_type = wq_attr->wq_type; wq->cq = wq_attr->cq; wq->device = pd->device; wq->pd = pd; wq->uobject = NULL; atomic_inc(&pd->usecnt); atomic_inc(&wq_attr->cq->usecnt); atomic_set(&wq->usecnt, 0); } return wq; } EXPORT_SYMBOL(ib_create_wq); /** * ib_destroy_wq_user - Destroys the specified user WQ. * @wq: The WQ to destroy. * @udata: Valid user data */ int ib_destroy_wq_user(struct ib_wq *wq, struct ib_udata *udata) { struct ib_cq *cq = wq->cq; struct ib_pd *pd = wq->pd; int ret; if (atomic_read(&wq->usecnt)) return -EBUSY; ret = wq->device->ops.destroy_wq(wq, udata); if (ret) return ret; atomic_dec(&pd->usecnt); atomic_dec(&cq->usecnt); return ret; } EXPORT_SYMBOL(ib_destroy_wq_user); int ib_check_mr_status(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status) { if (!mr->device->ops.check_mr_status) return -EOPNOTSUPP; return mr->device->ops.check_mr_status(mr, check_mask, mr_status); } EXPORT_SYMBOL(ib_check_mr_status); int ib_set_vf_link_state(struct ib_device *device, int vf, u32 port, int state) { if (!device->ops.set_vf_link_state) return -EOPNOTSUPP; return device->ops.set_vf_link_state(device, vf, port, state); } EXPORT_SYMBOL(ib_set_vf_link_state); int ib_get_vf_config(struct ib_device *device, int vf, u32 port, struct ifla_vf_info *info) { if (!device->ops.get_vf_config) return -EOPNOTSUPP; return device->ops.get_vf_config(device, vf, port, info); } EXPORT_SYMBOL(ib_get_vf_config); int ib_get_vf_stats(struct ib_device *device, int vf, u32 port, struct ifla_vf_stats *stats) { if (!device->ops.get_vf_stats) return -EOPNOTSUPP; return device->ops.get_vf_stats(device, vf, port, stats); } EXPORT_SYMBOL(ib_get_vf_stats); int ib_set_vf_guid(struct ib_device *device, int vf, u32 port, u64 guid, int type) { if (!device->ops.set_vf_guid) return -EOPNOTSUPP; return device->ops.set_vf_guid(device, vf, port, guid, type); } EXPORT_SYMBOL(ib_set_vf_guid); int ib_get_vf_guid(struct ib_device *device, int vf, u32 port, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid) { if (!device->ops.get_vf_guid) return -EOPNOTSUPP; return device->ops.get_vf_guid(device, vf, port, node_guid, port_guid); } EXPORT_SYMBOL(ib_get_vf_guid); /** * ib_map_mr_sg_pi() - Map the dma mapped SG lists for PI (protection * information) and set an appropriate memory region for registration. * @mr: memory region * @data_sg: dma mapped scatterlist for data * @data_sg_nents: number of entries in data_sg * @data_sg_offset: offset in bytes into data_sg * @meta_sg: dma mapped scatterlist for metadata * @meta_sg_nents: number of entries in meta_sg * @meta_sg_offset: offset in bytes into meta_sg * @page_size: page vector desired page size * * Constraints: * - The MR must be allocated with type IB_MR_TYPE_INTEGRITY. * * Return: 0 on success. * * After this completes successfully, the memory region * is ready for registration. */ int ib_map_mr_sg_pi(struct ib_mr *mr, struct scatterlist *data_sg, int data_sg_nents, unsigned int *data_sg_offset, struct scatterlist *meta_sg, int meta_sg_nents, unsigned int *meta_sg_offset, unsigned int page_size) { if (unlikely(!mr->device->ops.map_mr_sg_pi || WARN_ON_ONCE(mr->type != IB_MR_TYPE_INTEGRITY))) return -EOPNOTSUPP; mr->page_size = page_size; return mr->device->ops.map_mr_sg_pi(mr, data_sg, data_sg_nents, data_sg_offset, meta_sg, meta_sg_nents, meta_sg_offset); } EXPORT_SYMBOL(ib_map_mr_sg_pi); /** * ib_map_mr_sg() - Map the largest prefix of a dma mapped SG list * and set it the memory region. * @mr: memory region * @sg: dma mapped scatterlist * @sg_nents: number of entries in sg * @sg_offset: offset in bytes into sg * @page_size: page vector desired page size * * Constraints: * * - The first sg element is allowed to have an offset. * - Each sg element must either be aligned to page_size or virtually * contiguous to the previous element. In case an sg element has a * non-contiguous offset, the mapping prefix will not include it. * - The last sg element is allowed to have length less than page_size. * - If sg_nents total byte length exceeds the mr max_num_sge * page_size * then only max_num_sg entries will be mapped. * - If the MR was allocated with type IB_MR_TYPE_SG_GAPS, none of these * constraints holds and the page_size argument is ignored. * * Returns the number of sg elements that were mapped to the memory region. * * After this completes successfully, the memory region * is ready for registration. */ int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size) { if (unlikely(!mr->device->ops.map_mr_sg)) return -EOPNOTSUPP; mr->page_size = page_size; return mr->device->ops.map_mr_sg(mr, sg, sg_nents, sg_offset); } EXPORT_SYMBOL(ib_map_mr_sg); /** * ib_sg_to_pages() - Convert the largest prefix of a sg list * to a page vector * @mr: memory region * @sgl: dma mapped scatterlist * @sg_nents: number of entries in sg * @sg_offset_p: ==== ======================================================= * IN start offset in bytes into sg * OUT offset in bytes for element n of the sg of the first * byte that has not been processed where n is the return * value of this function. * ==== ======================================================= * @set_page: driver page assignment function pointer * * Core service helper for drivers to convert the largest * prefix of given sg list to a page vector. The sg list * prefix converted is the prefix that meet the requirements * of ib_map_mr_sg. * * Returns the number of sg elements that were assigned to * a page vector. */ int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents, unsigned int *sg_offset_p, int (*set_page)(struct ib_mr *, u64)) { struct scatterlist *sg; u64 last_end_dma_addr = 0; unsigned int sg_offset = sg_offset_p ? *sg_offset_p : 0; unsigned int last_page_off = 0; u64 page_mask = ~((u64)mr->page_size - 1); int i, ret; if (unlikely(sg_nents <= 0 || sg_offset > sg_dma_len(&sgl[0]))) return -EINVAL; mr->iova = sg_dma_address(&sgl[0]) + sg_offset; mr->length = 0; for_each_sg(sgl, sg, sg_nents, i) { u64 dma_addr = sg_dma_address(sg) + sg_offset; u64 prev_addr = dma_addr; unsigned int dma_len = sg_dma_len(sg) - sg_offset; u64 end_dma_addr = dma_addr + dma_len; u64 page_addr = dma_addr & page_mask; /* * For the second and later elements, check whether either the * end of element i-1 or the start of element i is not aligned * on a page boundary. */ if (i && (last_page_off != 0 || page_addr != dma_addr)) { /* Stop mapping if there is a gap. */ if (last_end_dma_addr != dma_addr) break; /* * Coalesce this element with the last. If it is small * enough just update mr->length. Otherwise start * mapping from the next page. */ goto next_page; } do { ret = set_page(mr, page_addr); if (unlikely(ret < 0)) { sg_offset = prev_addr - sg_dma_address(sg); mr->length += prev_addr - dma_addr; if (sg_offset_p) *sg_offset_p = sg_offset; return i || sg_offset ? i : ret; } prev_addr = page_addr; next_page: page_addr += mr->page_size; } while (page_addr < end_dma_addr); mr->length += dma_len; last_end_dma_addr = end_dma_addr; last_page_off = end_dma_addr & ~page_mask; sg_offset = 0; } if (sg_offset_p) *sg_offset_p = 0; return i; } EXPORT_SYMBOL(ib_sg_to_pages); struct ib_drain_cqe { struct ib_cqe cqe; struct completion done; }; static void ib_drain_qp_done(struct ib_cq *cq, struct ib_wc *wc) { struct ib_drain_cqe *cqe = container_of(wc->wr_cqe, struct ib_drain_cqe, cqe); complete(&cqe->done); } /* * Post a WR and block until its completion is reaped for the SQ. */ static void __ib_drain_sq(struct ib_qp *qp) { struct ib_cq *cq = qp->send_cq; struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR }; struct ib_drain_cqe sdrain; struct ib_rdma_wr swr = { .wr = { .next = NULL, { .wr_cqe = &sdrain.cqe, }, .opcode = IB_WR_RDMA_WRITE, }, }; int ret; ret = ib_modify_qp(qp, &attr, IB_QP_STATE); if (ret) { WARN_ONCE(ret, "failed to drain send queue: %d\n", ret); return; } sdrain.cqe.done = ib_drain_qp_done; init_completion(&sdrain.done); ret = ib_post_send(qp, &swr.wr, NULL); if (ret) { WARN_ONCE(ret, "failed to drain send queue: %d\n", ret); return; } if (cq->poll_ctx == IB_POLL_DIRECT) while (wait_for_completion_timeout(&sdrain.done, HZ / 10) <= 0) ib_process_cq_direct(cq, -1); else wait_for_completion(&sdrain.done); } /* * Post a WR and block until its completion is reaped for the RQ. */ static void __ib_drain_rq(struct ib_qp *qp) { struct ib_cq *cq = qp->recv_cq; struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR }; struct ib_drain_cqe rdrain; struct ib_recv_wr rwr = {}; int ret; ret = ib_modify_qp(qp, &attr, IB_QP_STATE); if (ret) { WARN_ONCE(ret, "failed to drain recv queue: %d\n", ret); return; } rwr.wr_cqe = &rdrain.cqe; rdrain.cqe.done = ib_drain_qp_done; init_completion(&rdrain.done); ret = ib_post_recv(qp, &rwr, NULL); if (ret) { WARN_ONCE(ret, "failed to drain recv queue: %d\n", ret); return; } if (cq->poll_ctx == IB_POLL_DIRECT) while (wait_for_completion_timeout(&rdrain.done, HZ / 10) <= 0) ib_process_cq_direct(cq, -1); else wait_for_completion(&rdrain.done); } /* * __ib_drain_srq() - Block until Last WQE Reached event arrives, or timeout * expires. * @qp: queue pair associated with SRQ to drain * * Quoting 10.3.1 Queue Pair and EE Context States: * * Note, for QPs that are associated with an SRQ, the Consumer should take the * QP through the Error State before invoking a Destroy QP or a Modify QP to the * Reset State. The Consumer may invoke the Destroy QP without first performing * a Modify QP to the Error State and waiting for the Affiliated Asynchronous * Last WQE Reached Event. However, if the Consumer does not wait for the * Affiliated Asynchronous Last WQE Reached Event, then WQE and Data Segment * leakage may occur. Therefore, it is good programming practice to tear down a * QP that is associated with an SRQ by using the following process: * * - Put the QP in the Error State * - Wait for the Affiliated Asynchronous Last WQE Reached Event; * - either: * drain the CQ by invoking the Poll CQ verb and either wait for CQ * to be empty or the number of Poll CQ operations has exceeded * CQ capacity size; * - or * post another WR that completes on the same CQ and wait for this * WR to return as a WC; * - and then invoke a Destroy QP or Reset QP. * * We use the first option. */ static void __ib_drain_srq(struct ib_qp *qp) { struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR }; struct ib_cq *cq; int n, polled = 0; int ret; if (!qp->srq) { WARN_ONCE(1, "QP 0x%p is not associated with SRQ\n", qp); return; } ret = ib_modify_qp(qp, &attr, IB_QP_STATE); if (ret) { WARN_ONCE(ret, "failed to drain shared recv queue: %d\n", ret); return; } if (ib_srq_has_cq(qp->srq->srq_type)) { cq = qp->srq->ext.cq; } else if (qp->recv_cq) { cq = qp->recv_cq; } else { WARN_ONCE(1, "QP 0x%p has no CQ associated with SRQ\n", qp); return; } if (wait_for_completion_timeout(&qp->srq_completion, 60 * HZ) > 0) { while (polled != cq->cqe) { n = ib_process_cq_direct(cq, cq->cqe - polled); if (!n) return; polled += n; } } } /** * ib_drain_sq() - Block until all SQ CQEs have been consumed by the * application. * @qp: queue pair to drain * * If the device has a provider-specific drain function, then * call that. Otherwise call the generic drain function * __ib_drain_sq(). * * The caller must: * * ensure there is room in the CQ and SQ for the drain work request and * completion. * * allocate the CQ using ib_alloc_cq(). * * ensure that there are no other contexts that are posting WRs concurrently. * Otherwise the drain is not guaranteed. */ void ib_drain_sq(struct ib_qp *qp) { if (qp->device->ops.drain_sq) qp->device->ops.drain_sq(qp); else __ib_drain_sq(qp); trace_cq_drain_complete(qp->send_cq); } EXPORT_SYMBOL(ib_drain_sq); /** * ib_drain_rq() - Block until all RQ CQEs have been consumed by the * application. * @qp: queue pair to drain * * If the device has a provider-specific drain function, then * call that. Otherwise call the generic drain function * __ib_drain_rq(). * * The caller must: * * ensure there is room in the CQ and RQ for the drain work request and * completion. * * allocate the CQ using ib_alloc_cq(). * * ensure that there are no other contexts that are posting WRs concurrently. * Otherwise the drain is not guaranteed. */ void ib_drain_rq(struct ib_qp *qp) { if (qp->device->ops.drain_rq) qp->device->ops.drain_rq(qp); else __ib_drain_rq(qp); trace_cq_drain_complete(qp->recv_cq); } EXPORT_SYMBOL(ib_drain_rq); /** * ib_drain_qp() - Block until all CQEs have been consumed by the * application on both the RQ and SQ. * @qp: queue pair to drain * * The caller must: * * ensure there is room in the CQ(s), SQ, and RQ for drain work requests * and completions. * * allocate the CQs using ib_alloc_cq(). * * ensure that there are no other contexts that are posting WRs concurrently. * Otherwise the drain is not guaranteed. */ void ib_drain_qp(struct ib_qp *qp) { ib_drain_sq(qp); if (!qp->srq) ib_drain_rq(qp); else __ib_drain_srq(qp); } EXPORT_SYMBOL(ib_drain_qp); struct net_device *rdma_alloc_netdev(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *)) { struct rdma_netdev_alloc_params params; struct net_device *netdev; int rc; if (!device->ops.rdma_netdev_get_params) return ERR_PTR(-EOPNOTSUPP); rc = device->ops.rdma_netdev_get_params(device, port_num, type, ¶ms); if (rc) return ERR_PTR(rc); netdev = alloc_netdev_mqs(params.sizeof_priv, name, name_assign_type, setup, params.txqs, params.rxqs); if (!netdev) return ERR_PTR(-ENOMEM); return netdev; } EXPORT_SYMBOL(rdma_alloc_netdev); int rdma_init_netdev(struct ib_device *device, u32 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), struct net_device *netdev) { struct rdma_netdev_alloc_params params; int rc; if (!device->ops.rdma_netdev_get_params) return -EOPNOTSUPP; rc = device->ops.rdma_netdev_get_params(device, port_num, type, ¶ms); if (rc) return rc; return params.initialize_rdma_netdev(device, port_num, netdev, params.param); } EXPORT_SYMBOL(rdma_init_netdev); void __rdma_block_iter_start(struct ib_block_iter *biter, struct scatterlist *sglist, unsigned int nents, unsigned long pgsz) { memset(biter, 0, sizeof(struct ib_block_iter)); biter->__sg = sglist; biter->__sg_nents = nents; /* Driver provides best block size to use */ biter->__pg_bit = __fls(pgsz); } EXPORT_SYMBOL(__rdma_block_iter_start); bool __rdma_block_iter_next(struct ib_block_iter *biter) { unsigned int block_offset; unsigned int sg_delta; if (!biter->__sg_nents || !biter->__sg) return false; biter->__dma_addr = sg_dma_address(biter->__sg) + biter->__sg_advance; block_offset = biter->__dma_addr & (BIT_ULL(biter->__pg_bit) - 1); sg_delta = BIT_ULL(biter->__pg_bit) - block_offset; if (sg_dma_len(biter->__sg) - biter->__sg_advance > sg_delta) { biter->__sg_advance += sg_delta; } else { biter->__sg_advance = 0; biter->__sg = sg_next(biter->__sg); biter->__sg_nents--; } return true; } EXPORT_SYMBOL(__rdma_block_iter_next); /** * rdma_alloc_hw_stats_struct - Helper function to allocate dynamic struct * for the drivers. * @descs: array of static descriptors * @num_counters: number of elements in array * @lifespan: milliseconds between updates */ struct rdma_hw_stats *rdma_alloc_hw_stats_struct( const struct rdma_stat_desc *descs, int num_counters, unsigned long lifespan) { struct rdma_hw_stats *stats; stats = kzalloc(struct_size(stats, value, num_counters), GFP_KERNEL); if (!stats) return NULL; stats->is_disabled = kcalloc(BITS_TO_LONGS(num_counters), sizeof(*stats->is_disabled), GFP_KERNEL); if (!stats->is_disabled) goto err; stats->descs = descs; stats->num_counters = num_counters; stats->lifespan = msecs_to_jiffies(lifespan); mutex_init(&stats->lock); return stats; err: kfree(stats); return NULL; } EXPORT_SYMBOL(rdma_alloc_hw_stats_struct); /** * rdma_free_hw_stats_struct - Helper function to release rdma_hw_stats * @stats: statistics to release */ void rdma_free_hw_stats_struct(struct rdma_hw_stats *stats) { if (!stats) return; kfree(stats->is_disabled); kfree(stats); } EXPORT_SYMBOL(rdma_free_hw_stats_struct); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Definitions for the IPPROTO_SMC (socket related) * * Copyright IBM Corp. 2016, 2018 * Copyright (c) 2024, Alibaba Inc. * * Author: D. Wythe <alibuda@linux.alibaba.com> */ #include <net/protocol.h> #include <net/sock.h> #include "smc_inet.h" #include "smc.h" static int smc_inet_init_sock(struct sock *sk); static struct proto smc_inet_prot = { .name = "INET_SMC", .owner = THIS_MODULE, .init = smc_inet_init_sock, .hash = smc_hash_sk, .unhash = smc_unhash_sk, .release_cb = smc_release_cb, .obj_size = sizeof(struct smc_sock), .h.smc_hash = &smc_v4_hashinfo, .slab_flags = SLAB_TYPESAFE_BY_RCU, }; static const struct proto_ops smc_inet_stream_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = smc_release, .bind = smc_bind, .connect = smc_connect, .socketpair = sock_no_socketpair, .accept = smc_accept, .getname = smc_getname, .poll = smc_poll, .ioctl = smc_ioctl, .listen = smc_listen, .shutdown = smc_shutdown, .setsockopt = smc_setsockopt, .getsockopt = smc_getsockopt, .sendmsg = smc_sendmsg, .recvmsg = smc_recvmsg, .mmap = sock_no_mmap, .splice_read = smc_splice_read, }; static struct inet_protosw smc_inet_protosw = { .type = SOCK_STREAM, .protocol = IPPROTO_SMC, .prot = &smc_inet_prot, .ops = &smc_inet_stream_ops, .flags = INET_PROTOSW_ICSK, }; #if IS_ENABLED(CONFIG_IPV6) struct smc6_sock { struct smc_sock smc; struct ipv6_pinfo inet6; }; static struct proto smc_inet6_prot = { .name = "INET6_SMC", .owner = THIS_MODULE, .init = smc_inet_init_sock, .hash = smc_hash_sk, .unhash = smc_unhash_sk, .release_cb = smc_release_cb, .obj_size = sizeof(struct smc6_sock), .h.smc_hash = &smc_v6_hashinfo, .slab_flags = SLAB_TYPESAFE_BY_RCU, .ipv6_pinfo_offset = offsetof(struct smc6_sock, inet6), }; static const struct proto_ops smc_inet6_stream_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = smc_release, .bind = smc_bind, .connect = smc_connect, .socketpair = sock_no_socketpair, .accept = smc_accept, .getname = smc_getname, .poll = smc_poll, .ioctl = smc_ioctl, .listen = smc_listen, .shutdown = smc_shutdown, .setsockopt = smc_setsockopt, .getsockopt = smc_getsockopt, .sendmsg = smc_sendmsg, .recvmsg = smc_recvmsg, .mmap = sock_no_mmap, .splice_read = smc_splice_read, }; static struct inet_protosw smc_inet6_protosw = { .type = SOCK_STREAM, .protocol = IPPROTO_SMC, .prot = &smc_inet6_prot, .ops = &smc_inet6_stream_ops, .flags = INET_PROTOSW_ICSK, }; #endif /* CONFIG_IPV6 */ static unsigned int smc_sync_mss(struct sock *sk, u32 pmtu) { /* No need pass it through to clcsock, mss can always be set by * sock_create_kern or smc_setsockopt. */ return 0; } static int smc_inet_init_sock(struct sock *sk) { struct net *net = sock_net(sk); /* init common smc sock */ smc_sk_init(net, sk, IPPROTO_SMC); inet_csk(sk)->icsk_sync_mss = smc_sync_mss; /* create clcsock */ return smc_create_clcsk(net, sk, sk->sk_family); } int __init smc_inet_init(void) { int rc; rc = proto_register(&smc_inet_prot, 1); if (rc) { pr_err("%s: proto_register smc_inet_prot fails with %d\n", __func__, rc); return rc; } /* no return value */ inet_register_protosw(&smc_inet_protosw); #if IS_ENABLED(CONFIG_IPV6) rc = proto_register(&smc_inet6_prot, 1); if (rc) { pr_err("%s: proto_register smc_inet6_prot fails with %d\n", __func__, rc); goto out_inet6_prot; } rc = inet6_register_protosw(&smc_inet6_protosw); if (rc) { pr_err("%s: inet6_register_protosw smc_inet6_protosw fails with %d\n", __func__, rc); goto out_inet6_protosw; } return rc; out_inet6_protosw: proto_unregister(&smc_inet6_prot); out_inet6_prot: inet_unregister_protosw(&smc_inet_protosw); proto_unregister(&smc_inet_prot); #endif /* CONFIG_IPV6 */ return rc; } void smc_inet_exit(void) { #if IS_ENABLED(CONFIG_IPV6) inet6_unregister_protosw(&smc_inet6_protosw); proto_unregister(&smc_inet6_prot); #endif /* CONFIG_IPV6 */ inet_unregister_protosw(&smc_inet_protosw); proto_unregister(&smc_inet_prot); } |
| 2 1 2 10 10 1 1 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ #include "main.h" #include <linux/errno.h> #include <linux/list.h> #include <linux/moduleparam.h> #include <linux/netlink.h> #include <linux/printk.h> #include <linux/skbuff.h> #include <linux/stddef.h> #include <linux/string.h> #include <net/genetlink.h> #include <net/netlink.h> #include <uapi/linux/batman_adv.h> #include "bat_algo.h" #include "netlink.h" char batadv_routing_algo[20] = "BATMAN_IV"; static struct hlist_head batadv_algo_list; /** * batadv_algo_init() - Initialize batman-adv algorithm management data * structures */ void batadv_algo_init(void) { INIT_HLIST_HEAD(&batadv_algo_list); } /** * batadv_algo_get() - Search for algorithm with specific name * @name: algorithm name to find * * Return: Pointer to batadv_algo_ops on success, NULL otherwise */ struct batadv_algo_ops *batadv_algo_get(const char *name) { struct batadv_algo_ops *bat_algo_ops = NULL, *bat_algo_ops_tmp; hlist_for_each_entry(bat_algo_ops_tmp, &batadv_algo_list, list) { if (strcmp(bat_algo_ops_tmp->name, name) != 0) continue; bat_algo_ops = bat_algo_ops_tmp; break; } return bat_algo_ops; } /** * batadv_algo_register() - Register callbacks for a mesh algorithm * @bat_algo_ops: mesh algorithm callbacks to add * * Return: 0 on success or negative error number in case of failure */ int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops) { struct batadv_algo_ops *bat_algo_ops_tmp; bat_algo_ops_tmp = batadv_algo_get(bat_algo_ops->name); if (bat_algo_ops_tmp) { pr_info("Trying to register already registered routing algorithm: %s\n", bat_algo_ops->name); return -EEXIST; } /* all algorithms must implement all ops (for now) */ if (!bat_algo_ops->iface.enable || !bat_algo_ops->iface.disable || !bat_algo_ops->iface.update_mac || !bat_algo_ops->iface.primary_set || !bat_algo_ops->neigh.cmp || !bat_algo_ops->neigh.is_similar_or_better) { pr_info("Routing algo '%s' does not implement required ops\n", bat_algo_ops->name); return -EINVAL; } INIT_HLIST_NODE(&bat_algo_ops->list); hlist_add_head(&bat_algo_ops->list, &batadv_algo_list); return 0; } /** * batadv_algo_select() - Select algorithm of soft interface * @bat_priv: the bat priv with all the soft interface information * @name: name of the algorithm to select * * The algorithm callbacks for the soft interface will be set when the algorithm * with the correct name was found. Any previous selected algorithm will not be * deinitialized and the new selected algorithm will also not be initialized. * It is therefore not allowed to call batadv_algo_select outside the creation * function of the soft interface. * * Return: 0 on success or negative error number in case of failure */ int batadv_algo_select(struct batadv_priv *bat_priv, const char *name) { struct batadv_algo_ops *bat_algo_ops; bat_algo_ops = batadv_algo_get(name); if (!bat_algo_ops) return -EINVAL; bat_priv->algo_ops = bat_algo_ops; return 0; } static int batadv_param_set_ra(const char *val, const struct kernel_param *kp) { struct batadv_algo_ops *bat_algo_ops; char *algo_name = (char *)val; size_t name_len = strlen(algo_name); if (name_len > 0 && algo_name[name_len - 1] == '\n') algo_name[name_len - 1] = '\0'; bat_algo_ops = batadv_algo_get(algo_name); if (!bat_algo_ops) { pr_err("Routing algorithm '%s' is not supported\n", algo_name); return -EINVAL; } return param_set_copystring(algo_name, kp); } static const struct kernel_param_ops batadv_param_ops_ra = { .set = batadv_param_set_ra, .get = param_get_string, }; static struct kparam_string batadv_param_string_ra = { .maxlen = sizeof(batadv_routing_algo), .string = batadv_routing_algo, }; module_param_cb(routing_algo, &batadv_param_ops_ra, &batadv_param_string_ra, 0644); /** * batadv_algo_dump_entry() - fill in information about one supported routing * algorithm * @msg: netlink message to be sent back * @portid: Port to reply to * @seq: Sequence number of message * @bat_algo_ops: Algorithm to be dumped * * Return: Error number, or 0 on success */ static int batadv_algo_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, struct batadv_algo_ops *bat_algo_ops) { void *hdr; hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, NLM_F_MULTI, BATADV_CMD_GET_ROUTING_ALGOS); if (!hdr) return -EMSGSIZE; if (nla_put_string(msg, BATADV_ATTR_ALGO_NAME, bat_algo_ops->name)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } /** * batadv_algo_dump() - fill in information about supported routing * algorithms * @msg: netlink message to be sent back * @cb: Parameters to the netlink request * * Return: Length of reply message. */ int batadv_algo_dump(struct sk_buff *msg, struct netlink_callback *cb) { int portid = NETLINK_CB(cb->skb).portid; struct batadv_algo_ops *bat_algo_ops; int skip = cb->args[0]; int i = 0; hlist_for_each_entry(bat_algo_ops, &batadv_algo_list, list) { if (i++ < skip) continue; if (batadv_algo_dump_entry(msg, portid, cb->nlh->nlmsg_seq, bat_algo_ops)) { i--; break; } } cb->args[0] = i; return msg->len; } |
| 2 2 2 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _SOCK_REUSEPORT_H #define _SOCK_REUSEPORT_H #include <linux/filter.h> #include <linux/skbuff.h> #include <linux/types.h> #include <linux/spinlock.h> #include <net/sock.h> extern spinlock_t reuseport_lock; struct sock_reuseport { struct rcu_head rcu; u16 max_socks; /* length of socks */ u16 num_socks; /* elements in socks */ u16 num_closed_socks; /* closed elements in socks */ u16 incoming_cpu; /* The last synq overflow event timestamp of this * reuse->socks[] group. */ unsigned int synq_overflow_ts; /* ID stays the same even after the size of socks[] grows. */ unsigned int reuseport_id; unsigned int bind_inany:1; unsigned int has_conns:1; struct bpf_prog __rcu *prog; /* optional BPF sock selector */ struct sock *socks[] __counted_by(max_socks); }; extern int reuseport_alloc(struct sock *sk, bool bind_inany); extern int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany); extern void reuseport_detach_sock(struct sock *sk); void reuseport_stop_listen_sock(struct sock *sk); extern struct sock *reuseport_select_sock(struct sock *sk, u32 hash, struct sk_buff *skb, int hdr_len); struct sock *reuseport_migrate_sock(struct sock *sk, struct sock *migrating_sk, struct sk_buff *skb); extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog); extern int reuseport_detach_prog(struct sock *sk); static inline bool reuseport_has_conns(struct sock *sk) { struct sock_reuseport *reuse; bool ret = false; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); if (reuse && reuse->has_conns) ret = true; rcu_read_unlock(); return ret; } void reuseport_has_conns_set(struct sock *sk); void reuseport_update_incoming_cpu(struct sock *sk, int val); #endif /* _SOCK_REUSEPORT_H */ |
| 35 85 85 2 1 1 616 513 106 3 140 20 118 119 6 120 120 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 118 118 141 42 84 21 83 21 3 3 119 2 2 4 4 299 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Integrity Measurement Architecture * * Copyright (C) 2005,2006,2007,2008 IBM Corporation * * Authors: * Reiner Sailer <sailer@watson.ibm.com> * Serge Hallyn <serue@us.ibm.com> * Kylene Hall <kylene@us.ibm.com> * Mimi Zohar <zohar@us.ibm.com> * * File: ima_main.c * implements the IMA hooks: ima_bprm_check, ima_file_mmap, * and ima_file_check. */ #include <linux/module.h> #include <linux/file.h> #include <linux/binfmts.h> #include <linux/kernel_read_file.h> #include <linux/mount.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/xattr.h> #include <linux/ima.h> #include <linux/fs.h> #include <linux/iversion.h> #include <linux/evm.h> #include "ima.h" #ifdef CONFIG_IMA_APPRAISE int ima_appraise = IMA_APPRAISE_ENFORCE; #else int ima_appraise; #endif int __ro_after_init ima_hash_algo = HASH_ALGO_SHA1; static int hash_setup_done; static struct notifier_block ima_lsm_policy_notifier = { .notifier_call = ima_lsm_policy_change, }; static int __init hash_setup(char *str) { struct ima_template_desc *template_desc = ima_template_desc_current(); int i; if (hash_setup_done) return 1; if (strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0) { if (strncmp(str, "sha1", 4) == 0) { ima_hash_algo = HASH_ALGO_SHA1; } else if (strncmp(str, "md5", 3) == 0) { ima_hash_algo = HASH_ALGO_MD5; } else { pr_err("invalid hash algorithm \"%s\" for template \"%s\"", str, IMA_TEMPLATE_IMA_NAME); return 1; } goto out; } i = match_string(hash_algo_name, HASH_ALGO__LAST, str); if (i < 0) { pr_err("invalid hash algorithm \"%s\"", str); return 1; } ima_hash_algo = i; out: hash_setup_done = 1; return 1; } __setup("ima_hash=", hash_setup); enum hash_algo ima_get_current_hash_algo(void) { return ima_hash_algo; } /* Prevent mmap'ing a file execute that is already mmap'ed write */ static int mmap_violation_check(enum ima_hooks func, struct file *file, char **pathbuf, const char **pathname, char *filename) { struct inode *inode; int rc = 0; if ((func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) && mapping_writably_mapped(file->f_mapping)) { rc = -ETXTBSY; inode = file_inode(file); if (!*pathbuf) /* ima_rdwr_violation possibly pre-fetched */ *pathname = ima_d_path(&file->f_path, pathbuf, filename); integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, *pathname, "mmap_file", "mmapped_writers", rc, 0); } return rc; } /* * ima_rdwr_violation_check * * Only invalidate the PCR for measured files: * - Opening a file for write when already open for read, * results in a time of measure, time of use (ToMToU) error. * - Opening a file for read when already open for write, * could result in a file measurement error. * */ static void ima_rdwr_violation_check(struct file *file, struct ima_iint_cache *iint, int must_measure, char **pathbuf, const char **pathname, char *filename) { struct inode *inode = file_inode(file); fmode_t mode = file->f_mode; bool send_tomtou = false, send_writers = false; if (mode & FMODE_WRITE) { if (atomic_read(&inode->i_readcount) && IS_IMA(inode)) { if (!iint) iint = ima_iint_find(inode); /* IMA_MEASURE is set from reader side */ if (iint && test_bit(IMA_MUST_MEASURE, &iint->atomic_flags)) send_tomtou = true; } } else { if (must_measure) set_bit(IMA_MUST_MEASURE, &iint->atomic_flags); if (inode_is_open_for_write(inode) && must_measure) send_writers = true; } if (!send_tomtou && !send_writers) return; *pathname = ima_d_path(&file->f_path, pathbuf, filename); if (send_tomtou) ima_add_violation(file, *pathname, iint, "invalid_pcr", "ToMToU"); if (send_writers) ima_add_violation(file, *pathname, iint, "invalid_pcr", "open_writers"); } static void ima_check_last_writer(struct ima_iint_cache *iint, struct inode *inode, struct file *file) { fmode_t mode = file->f_mode; bool update; if (!(mode & FMODE_WRITE)) return; mutex_lock(&iint->mutex); if (atomic_read(&inode->i_writecount) == 1) { struct kstat stat; update = test_and_clear_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); if ((iint->flags & IMA_NEW_FILE) || vfs_getattr_nosec(&file->f_path, &stat, STATX_CHANGE_COOKIE, AT_STATX_SYNC_AS_STAT) || !(stat.result_mask & STATX_CHANGE_COOKIE) || stat.change_cookie != iint->real_inode.version) { iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE); iint->measured_pcrs = 0; if (update) ima_update_xattr(iint, file); } } mutex_unlock(&iint->mutex); } /** * ima_file_free - called on __fput() * @file: pointer to file structure being freed * * Flag files that changed, based on i_version */ static void ima_file_free(struct file *file) { struct inode *inode = file_inode(file); struct ima_iint_cache *iint; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; iint = ima_iint_find(inode); if (!iint) return; ima_check_last_writer(iint, inode, file); } static int process_measurement(struct file *file, const struct cred *cred, struct lsm_prop *prop, char *buf, loff_t size, int mask, enum ima_hooks func) { struct inode *real_inode, *inode = file_inode(file); struct ima_iint_cache *iint = NULL; struct ima_template_desc *template_desc = NULL; struct inode *metadata_inode; char *pathbuf = NULL; char filename[NAME_MAX]; const char *pathname = NULL; int rc = 0, action, must_appraise = 0; int pcr = CONFIG_IMA_MEASURE_PCR_IDX; struct evm_ima_xattr_data *xattr_value = NULL; struct modsig *modsig = NULL; int xattr_len = 0; bool violation_check; enum hash_algo hash_algo; unsigned int allowed_algos = 0; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return 0; /* Return an IMA_MEASURE, IMA_APPRAISE, IMA_AUDIT action * bitmask based on the appraise/audit/measurement policy. * Included is the appraise submask. */ action = ima_get_action(file_mnt_idmap(file), inode, cred, prop, mask, func, &pcr, &template_desc, NULL, &allowed_algos); violation_check = ((func == FILE_CHECK || func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) && (ima_policy_flag & IMA_MEASURE)); if (!action && !violation_check) return 0; must_appraise = action & IMA_APPRAISE; /* Is the appraise rule hook specific? */ if (action & IMA_FILE_APPRAISE) func = FILE_CHECK; inode_lock(inode); if (action) { iint = ima_inode_get(inode); if (!iint) rc = -ENOMEM; } if (!rc && violation_check) ima_rdwr_violation_check(file, iint, action & IMA_MEASURE, &pathbuf, &pathname, filename); inode_unlock(inode); if (rc) goto out; if (!action) goto out; mutex_lock(&iint->mutex); if (test_and_clear_bit(IMA_CHANGE_ATTR, &iint->atomic_flags)) /* reset appraisal flags if ima_inode_post_setattr was called */ iint->flags &= ~(IMA_APPRAISE | IMA_APPRAISED | IMA_APPRAISE_SUBMASK | IMA_APPRAISED_SUBMASK | IMA_NONACTION_FLAGS); /* * Re-evaulate the file if either the xattr has changed or the * kernel has no way of detecting file change on the filesystem. * (Limited to privileged mounted filesystems.) */ if (test_and_clear_bit(IMA_CHANGE_XATTR, &iint->atomic_flags) || ((inode->i_sb->s_iflags & SB_I_IMA_UNVERIFIABLE_SIGNATURE) && !(inode->i_sb->s_iflags & SB_I_UNTRUSTED_MOUNTER) && !(action & IMA_FAIL_UNVERIFIABLE_SIGS))) { iint->flags &= ~IMA_DONE_MASK; iint->measured_pcrs = 0; } /* * On stacked filesystems, detect and re-evaluate file data and * metadata changes. */ real_inode = d_real_inode(file_dentry(file)); if (real_inode != inode && (action & IMA_DO_MASK) && (iint->flags & IMA_DONE_MASK)) { if (!IS_I_VERSION(real_inode) || integrity_inode_attrs_changed(&iint->real_inode, real_inode)) { iint->flags &= ~IMA_DONE_MASK; iint->measured_pcrs = 0; } /* * Reset the EVM status when metadata changed. */ metadata_inode = d_inode(d_real(file_dentry(file), D_REAL_METADATA)); if (evm_metadata_changed(inode, metadata_inode)) iint->flags &= ~(IMA_APPRAISED | IMA_APPRAISED_SUBMASK); } /* Determine if already appraised/measured based on bitmask * (IMA_MEASURE, IMA_MEASURED, IMA_XXXX_APPRAISE, IMA_XXXX_APPRAISED, * IMA_AUDIT, IMA_AUDITED) */ iint->flags |= action; action &= IMA_DO_MASK; action &= ~((iint->flags & (IMA_DONE_MASK ^ IMA_MEASURED)) >> 1); /* If target pcr is already measured, unset IMA_MEASURE action */ if ((action & IMA_MEASURE) && (iint->measured_pcrs & (0x1 << pcr))) action ^= IMA_MEASURE; /* HASH sets the digital signature and update flags, nothing else */ if ((action & IMA_HASH) && !(test_bit(IMA_DIGSIG, &iint->atomic_flags))) { xattr_len = ima_read_xattr(file_dentry(file), &xattr_value, xattr_len); if ((xattr_value && xattr_len > 2) && (xattr_value->type == EVM_IMA_XATTR_DIGSIG)) set_bit(IMA_DIGSIG, &iint->atomic_flags); iint->flags |= IMA_HASHED; action ^= IMA_HASH; set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } /* Nothing to do, just return existing appraised status */ if (!action) { if (must_appraise) { rc = mmap_violation_check(func, file, &pathbuf, &pathname, filename); if (!rc) rc = ima_get_cache_status(iint, func); } goto out_locked; } if ((action & IMA_APPRAISE_SUBMASK) || strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0) { /* read 'security.ima' */ xattr_len = ima_read_xattr(file_dentry(file), &xattr_value, xattr_len); /* * Read the appended modsig if allowed by the policy, and allow * an additional measurement list entry, if needed, based on the * template format and whether the file was already measured. */ if (iint->flags & IMA_MODSIG_ALLOWED) { rc = ima_read_modsig(func, buf, size, &modsig); if (!rc && ima_template_has_modsig(template_desc) && iint->flags & IMA_MEASURED) action |= IMA_MEASURE; } } hash_algo = ima_get_hash_algo(xattr_value, xattr_len); rc = ima_collect_measurement(iint, file, buf, size, hash_algo, modsig); if (rc != 0 && rc != -EBADF && rc != -EINVAL) goto out_locked; if (!pathbuf) /* ima_rdwr_violation possibly pre-fetched */ pathname = ima_d_path(&file->f_path, &pathbuf, filename); if (action & IMA_MEASURE) ima_store_measurement(iint, file, pathname, xattr_value, xattr_len, modsig, pcr, template_desc); if (rc == 0 && (action & IMA_APPRAISE_SUBMASK)) { rc = ima_check_blacklist(iint, modsig, pcr); if (rc != -EPERM) { inode_lock(inode); rc = ima_appraise_measurement(func, iint, file, pathname, xattr_value, xattr_len, modsig); inode_unlock(inode); } if (!rc) rc = mmap_violation_check(func, file, &pathbuf, &pathname, filename); } if (action & IMA_AUDIT) ima_audit_measurement(iint, pathname); if ((file->f_flags & O_DIRECT) && (iint->flags & IMA_PERMIT_DIRECTIO)) rc = 0; /* Ensure the digest was generated using an allowed algorithm */ if (rc == 0 && must_appraise && allowed_algos != 0 && (allowed_algos & (1U << hash_algo)) == 0) { rc = -EACCES; integrity_audit_msg(AUDIT_INTEGRITY_DATA, file_inode(file), pathname, "collect_data", "denied-hash-algorithm", rc, 0); } out_locked: if ((mask & MAY_WRITE) && test_bit(IMA_DIGSIG, &iint->atomic_flags) && !(iint->flags & IMA_NEW_FILE)) rc = -EACCES; mutex_unlock(&iint->mutex); kfree(xattr_value); ima_free_modsig(modsig); out: if (pathbuf) __putname(pathbuf); if (must_appraise) { if (rc && (ima_appraise & IMA_APPRAISE_ENFORCE)) return -EACCES; if (file->f_mode & FMODE_WRITE) set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } return 0; } /** * ima_file_mmap - based on policy, collect/store measurement. * @file: pointer to the file to be measured (May be NULL) * @reqprot: protection requested by the application * @prot: protection that will be applied by the kernel * @flags: operational flags * * Measure files being mmapped executable based on the ima_must_measure() * policy decision. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_file_mmap(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { struct lsm_prop prop; int ret; if (!file) return 0; security_current_getlsmprop_subj(&prop); if (reqprot & PROT_EXEC) { ret = process_measurement(file, current_cred(), &prop, NULL, 0, MAY_EXEC, MMAP_CHECK_REQPROT); if (ret) return ret; } if (prot & PROT_EXEC) return process_measurement(file, current_cred(), &prop, NULL, 0, MAY_EXEC, MMAP_CHECK); return 0; } /** * ima_file_mprotect - based on policy, limit mprotect change * @vma: vm_area_struct protection is set to * @reqprot: protection requested by the application * @prot: protection that will be applied by the kernel * * Files can be mmap'ed read/write and later changed to execute to circumvent * IMA's mmap appraisal policy rules. Due to locking issues (mmap semaphore * would be taken before i_mutex), files can not be measured or appraised at * this point. Eliminate this integrity gap by denying the mprotect * PROT_EXECUTE change, if an mmap appraise policy rule exists. * * On mprotect change success, return 0. On failure, return -EACESS. */ static int ima_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { struct ima_template_desc *template = NULL; struct file *file; char filename[NAME_MAX]; char *pathbuf = NULL; const char *pathname = NULL; struct inode *inode; struct lsm_prop prop; int result = 0; int action; int pcr; /* Is mprotect making an mmap'ed file executable? */ if (!(ima_policy_flag & IMA_APPRAISE) || !vma->vm_file || !(prot & PROT_EXEC) || (vma->vm_flags & VM_EXEC)) return 0; security_current_getlsmprop_subj(&prop); inode = file_inode(vma->vm_file); action = ima_get_action(file_mnt_idmap(vma->vm_file), inode, current_cred(), &prop, MAY_EXEC, MMAP_CHECK, &pcr, &template, NULL, NULL); action |= ima_get_action(file_mnt_idmap(vma->vm_file), inode, current_cred(), &prop, MAY_EXEC, MMAP_CHECK_REQPROT, &pcr, &template, NULL, NULL); /* Is the mmap'ed file in policy? */ if (!(action & (IMA_MEASURE | IMA_APPRAISE_SUBMASK))) return 0; if (action & IMA_APPRAISE_SUBMASK) result = -EPERM; file = vma->vm_file; pathname = ima_d_path(&file->f_path, &pathbuf, filename); integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, pathname, "collect_data", "failed-mprotect", result, 0); if (pathbuf) __putname(pathbuf); return result; } /** * ima_bprm_check - based on policy, collect/store measurement. * @bprm: contains the linux_binprm structure * * The OS protects against an executable file, already open for write, * from being executed in deny_write_access() and an executable file, * already open for execute, from being modified in get_write_access(). * So we can be certain that what we verify and measure here is actually * what is being executed. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_bprm_check(struct linux_binprm *bprm) { int ret; struct lsm_prop prop; security_current_getlsmprop_subj(&prop); ret = process_measurement(bprm->file, current_cred(), &prop, NULL, 0, MAY_EXEC, BPRM_CHECK); if (ret) return ret; security_cred_getlsmprop(bprm->cred, &prop); return process_measurement(bprm->file, bprm->cred, &prop, NULL, 0, MAY_EXEC, CREDS_CHECK); } /** * ima_file_check - based on policy, collect/store measurement. * @file: pointer to the file to be measured * @mask: contains MAY_READ, MAY_WRITE, MAY_EXEC or MAY_APPEND * * Measure files based on the ima_must_measure() policy decision. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_file_check(struct file *file, int mask) { struct lsm_prop prop; security_current_getlsmprop_subj(&prop); return process_measurement(file, current_cred(), &prop, NULL, 0, mask & (MAY_READ | MAY_WRITE | MAY_EXEC | MAY_APPEND), FILE_CHECK); } static int __ima_inode_hash(struct inode *inode, struct file *file, char *buf, size_t buf_size) { struct ima_iint_cache *iint = NULL, tmp_iint; int rc, hash_algo; if (ima_policy_flag) { iint = ima_iint_find(inode); if (iint) mutex_lock(&iint->mutex); } if ((!iint || !(iint->flags & IMA_COLLECTED)) && file) { if (iint) mutex_unlock(&iint->mutex); memset(&tmp_iint, 0, sizeof(tmp_iint)); mutex_init(&tmp_iint.mutex); rc = ima_collect_measurement(&tmp_iint, file, NULL, 0, ima_hash_algo, NULL); if (rc < 0) { /* ima_hash could be allocated in case of failure. */ if (rc != -ENOMEM) kfree(tmp_iint.ima_hash); return -EOPNOTSUPP; } iint = &tmp_iint; mutex_lock(&iint->mutex); } if (!iint) return -EOPNOTSUPP; /* * ima_file_hash can be called when ima_collect_measurement has still * not been called, we might not always have a hash. */ if (!iint->ima_hash || !(iint->flags & IMA_COLLECTED)) { mutex_unlock(&iint->mutex); return -EOPNOTSUPP; } if (buf) { size_t copied_size; copied_size = min_t(size_t, iint->ima_hash->length, buf_size); memcpy(buf, iint->ima_hash->digest, copied_size); } hash_algo = iint->ima_hash->algo; mutex_unlock(&iint->mutex); if (iint == &tmp_iint) kfree(iint->ima_hash); return hash_algo; } /** * ima_file_hash - return a measurement of the file * @file: pointer to the file * @buf: buffer in which to store the hash * @buf_size: length of the buffer * * On success, return the hash algorithm (as defined in the enum hash_algo). * If buf is not NULL, this function also outputs the hash into buf. * If the hash is larger than buf_size, then only buf_size bytes will be copied. * It generally just makes sense to pass a buffer capable of holding the largest * possible hash: IMA_MAX_DIGEST_SIZE. * The file hash returned is based on the entire file, including the appended * signature. * * If the measurement cannot be performed, return -EOPNOTSUPP. * If the parameters are incorrect, return -EINVAL. */ int ima_file_hash(struct file *file, char *buf, size_t buf_size) { if (!file) return -EINVAL; return __ima_inode_hash(file_inode(file), file, buf, buf_size); } EXPORT_SYMBOL_GPL(ima_file_hash); /** * ima_inode_hash - return the stored measurement if the inode has been hashed * and is in the iint cache. * @inode: pointer to the inode * @buf: buffer in which to store the hash * @buf_size: length of the buffer * * On success, return the hash algorithm (as defined in the enum hash_algo). * If buf is not NULL, this function also outputs the hash into buf. * If the hash is larger than buf_size, then only buf_size bytes will be copied. * It generally just makes sense to pass a buffer capable of holding the largest * possible hash: IMA_MAX_DIGEST_SIZE. * The hash returned is based on the entire contents, including the appended * signature. * * If IMA is disabled or if no measurement is available, return -EOPNOTSUPP. * If the parameters are incorrect, return -EINVAL. */ int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size) { if (!inode) return -EINVAL; return __ima_inode_hash(inode, NULL, buf, buf_size); } EXPORT_SYMBOL_GPL(ima_inode_hash); /** * ima_post_create_tmpfile - mark newly created tmpfile as new * @idmap: idmap of the mount the inode was found from * @inode: inode of the newly created tmpfile * * No measuring, appraising or auditing of newly created tmpfiles is needed. * Skip calling process_measurement(), but indicate which newly, created * tmpfiles are in policy. */ static void ima_post_create_tmpfile(struct mnt_idmap *idmap, struct inode *inode) { struct ima_iint_cache *iint; int must_appraise; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS, FILE_CHECK); if (!must_appraise) return; /* Nothing to do if we can't allocate memory */ iint = ima_inode_get(inode); if (!iint) return; /* needed for writing the security xattrs */ set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); iint->ima_file_status = INTEGRITY_PASS; } /** * ima_post_path_mknod - mark as a new inode * @idmap: idmap of the mount the inode was found from * @dentry: newly created dentry * * Mark files created via the mknodat syscall as new, so that the * file data can be written later. */ static void ima_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { struct ima_iint_cache *iint; struct inode *inode = dentry->d_inode; int must_appraise; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS, FILE_CHECK); if (!must_appraise) return; /* Nothing to do if we can't allocate memory */ iint = ima_inode_get(inode); if (!iint) return; /* needed for re-opening empty files */ iint->flags |= IMA_NEW_FILE; } /** * ima_read_file - pre-measure/appraise hook decision based on policy * @file: pointer to the file to be measured/appraised/audit * @read_id: caller identifier * @contents: whether a subsequent call will be made to ima_post_read_file() * * Permit reading a file based on policy. The policy rules are written * in terms of the policy identifier. Appraising the integrity of * a file requires a file descriptor. * * For permission return 0, otherwise return -EACCES. */ static int ima_read_file(struct file *file, enum kernel_read_file_id read_id, bool contents) { enum ima_hooks func; struct lsm_prop prop; /* * Do devices using pre-allocated memory run the risk of the * firmware being accessible to the device prior to the completion * of IMA's signature verification any more than when using two * buffers? It may be desirable to include the buffer address * in this API and walk all the dma_map_single() mappings to check. */ /* * There will be a call made to ima_post_read_file() with * a filled buffer, so we don't need to perform an extra * read early here. */ if (contents) return 0; /* Read entire file for all partial reads. */ func = read_idmap[read_id] ?: FILE_CHECK; security_current_getlsmprop_subj(&prop); return process_measurement(file, current_cred(), &prop, NULL, 0, MAY_READ, func); } const int read_idmap[READING_MAX_ID] = { [READING_FIRMWARE] = FIRMWARE_CHECK, [READING_MODULE] = MODULE_CHECK, [READING_KEXEC_IMAGE] = KEXEC_KERNEL_CHECK, [READING_KEXEC_INITRAMFS] = KEXEC_INITRAMFS_CHECK, [READING_POLICY] = POLICY_CHECK }; /** * ima_post_read_file - in memory collect/appraise/audit measurement * @file: pointer to the file to be measured/appraised/audit * @buf: pointer to in memory file contents * @size: size of in memory file contents * @read_id: caller identifier * * Measure/appraise/audit in memory file based on policy. Policy rules * are written in terms of a policy identifier. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id read_id) { enum ima_hooks func; struct lsm_prop prop; /* permit signed certs */ if (!file && read_id == READING_X509_CERTIFICATE) return 0; if (!file || !buf || size == 0) { /* should never happen */ if (ima_appraise & IMA_APPRAISE_ENFORCE) return -EACCES; return 0; } func = read_idmap[read_id] ?: FILE_CHECK; security_current_getlsmprop_subj(&prop); return process_measurement(file, current_cred(), &prop, buf, size, MAY_READ, func); } /** * ima_load_data - appraise decision based on policy * @id: kernel load data caller identifier * @contents: whether the full contents will be available in a later * call to ima_post_load_data(). * * Callers of this LSM hook can not measure, appraise, or audit the * data provided by userspace. Enforce policy rules requiring a file * signature (eg. kexec'ed kernel image). * * For permission return 0, otherwise return -EACCES. */ static int ima_load_data(enum kernel_load_data_id id, bool contents) { bool ima_enforce, sig_enforce; ima_enforce = (ima_appraise & IMA_APPRAISE_ENFORCE) == IMA_APPRAISE_ENFORCE; switch (id) { case LOADING_KEXEC_IMAGE: if (IS_ENABLED(CONFIG_KEXEC_SIG) && arch_ima_get_secureboot()) { pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); return -EACCES; } if (ima_enforce && (ima_appraise & IMA_APPRAISE_KEXEC)) { pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; case LOADING_FIRMWARE: if (ima_enforce && (ima_appraise & IMA_APPRAISE_FIRMWARE) && !contents) { pr_err("Prevent firmware sysfs fallback loading.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; case LOADING_MODULE: sig_enforce = is_module_sig_enforced(); if (ima_enforce && (!sig_enforce && (ima_appraise & IMA_APPRAISE_MODULES))) { pr_err("impossible to appraise a module without a file descriptor. sig_enforce kernel parameter might help\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; default: break; } return 0; } /** * ima_post_load_data - appraise decision based on policy * @buf: pointer to in memory file contents * @size: size of in memory file contents * @load_id: kernel load data caller identifier * @description: @load_id-specific description of contents * * Measure/appraise/audit in memory buffer based on policy. Policy rules * are written in terms of a policy identifier. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_post_load_data(char *buf, loff_t size, enum kernel_load_data_id load_id, char *description) { if (load_id == LOADING_FIRMWARE) { if ((ima_appraise & IMA_APPRAISE_FIRMWARE) && (ima_appraise & IMA_APPRAISE_ENFORCE)) { pr_err("Prevent firmware loading_store.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } return 0; } /* * Measure the init_module syscall buffer containing the ELF image. */ if (load_id == LOADING_MODULE) ima_measure_critical_data("modules", "init_module", buf, size, true, NULL, 0); return 0; } /** * process_buffer_measurement - Measure the buffer or the buffer data hash * @idmap: idmap of the mount the inode was found from * @inode: inode associated with the object being measured (NULL for KEY_CHECK) * @buf: pointer to the buffer that needs to be added to the log. * @size: size of buffer(in bytes). * @eventname: event name to be used for the buffer entry. * @func: IMA hook * @pcr: pcr to extend the measurement * @func_data: func specific data, may be NULL * @buf_hash: measure buffer data hash * @digest: buffer digest will be written to * @digest_len: buffer length * * Based on policy, either the buffer data or buffer data hash is measured * * Return: 0 if the buffer has been successfully measured, 1 if the digest * has been written to the passed location but not added to a measurement entry, * a negative value otherwise. */ int process_buffer_measurement(struct mnt_idmap *idmap, struct inode *inode, const void *buf, int size, const char *eventname, enum ima_hooks func, int pcr, const char *func_data, bool buf_hash, u8 *digest, size_t digest_len) { int ret = 0; const char *audit_cause = "ENOMEM"; struct ima_template_entry *entry = NULL; struct ima_iint_cache iint = {}; struct ima_event_data event_data = {.iint = &iint, .filename = eventname, .buf = buf, .buf_len = size}; struct ima_template_desc *template; struct ima_max_digest_data hash; struct ima_digest_data *hash_hdr = container_of(&hash.hdr, struct ima_digest_data, hdr); char digest_hash[IMA_MAX_DIGEST_SIZE]; int digest_hash_len = hash_digest_size[ima_hash_algo]; int violation = 0; int action = 0; struct lsm_prop prop; if (digest && digest_len < digest_hash_len) return -EINVAL; if (!ima_policy_flag && !digest) return -ENOENT; template = ima_template_desc_buf(); if (!template) { ret = -EINVAL; audit_cause = "ima_template_desc_buf"; goto out; } /* * Both LSM hooks and auxilary based buffer measurements are * based on policy. To avoid code duplication, differentiate * between the LSM hooks and auxilary buffer measurements, * retrieving the policy rule information only for the LSM hook * buffer measurements. */ if (func) { security_current_getlsmprop_subj(&prop); action = ima_get_action(idmap, inode, current_cred(), &prop, 0, func, &pcr, &template, func_data, NULL); if (!(action & IMA_MEASURE) && !digest) return -ENOENT; } if (!pcr) pcr = CONFIG_IMA_MEASURE_PCR_IDX; iint.ima_hash = hash_hdr; iint.ima_hash->algo = ima_hash_algo; iint.ima_hash->length = hash_digest_size[ima_hash_algo]; ret = ima_calc_buffer_hash(buf, size, iint.ima_hash); if (ret < 0) { audit_cause = "hashing_error"; goto out; } if (buf_hash) { memcpy(digest_hash, hash_hdr->digest, digest_hash_len); ret = ima_calc_buffer_hash(digest_hash, digest_hash_len, iint.ima_hash); if (ret < 0) { audit_cause = "hashing_error"; goto out; } event_data.buf = digest_hash; event_data.buf_len = digest_hash_len; } if (digest) memcpy(digest, iint.ima_hash->digest, digest_hash_len); if (!ima_policy_flag || (func && !(action & IMA_MEASURE))) return 1; ret = ima_alloc_init_template(&event_data, &entry, template); if (ret < 0) { audit_cause = "alloc_entry"; goto out; } ret = ima_store_template(entry, violation, NULL, event_data.buf, pcr); if (ret < 0) { audit_cause = "store_entry"; ima_free_template_entry(entry); } out: if (ret < 0) integrity_audit_message(AUDIT_INTEGRITY_PCR, NULL, eventname, func_measure_str(func), audit_cause, ret, 0, ret); return ret; } /** * ima_kexec_cmdline - measure kexec cmdline boot args * @kernel_fd: file descriptor of the kexec kernel being loaded * @buf: pointer to buffer * @size: size of buffer * * Buffers can only be measured, not appraised. */ void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) { if (!buf || !size) return; CLASS(fd, f)(kernel_fd); if (fd_empty(f)) return; process_buffer_measurement(file_mnt_idmap(fd_file(f)), file_inode(fd_file(f)), buf, size, "kexec-cmdline", KEXEC_CMDLINE, 0, NULL, false, NULL, 0); } /** * ima_measure_critical_data - measure kernel integrity critical data * @event_label: unique event label for grouping and limiting critical data * @event_name: event name for the record in the IMA measurement list * @buf: pointer to buffer data * @buf_len: length of buffer data (in bytes) * @hash: measure buffer data hash * @digest: buffer digest will be written to * @digest_len: buffer length * * Measure data critical to the integrity of the kernel into the IMA log * and extend the pcr. Examples of critical data could be various data * structures, policies, and states stored in kernel memory that can * impact the integrity of the system. * * Return: 0 if the buffer has been successfully measured, 1 if the digest * has been written to the passed location but not added to a measurement entry, * a negative value otherwise. */ int ima_measure_critical_data(const char *event_label, const char *event_name, const void *buf, size_t buf_len, bool hash, u8 *digest, size_t digest_len) { if (!event_name || !event_label || !buf || !buf_len) return -ENOPARAM; return process_buffer_measurement(&nop_mnt_idmap, NULL, buf, buf_len, event_name, CRITICAL_DATA, 0, event_label, hash, digest, digest_len); } EXPORT_SYMBOL_GPL(ima_measure_critical_data); #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS /** * ima_kernel_module_request - Prevent crypto-pkcs1(rsa,*) requests * @kmod_name: kernel module name * * Avoid a verification loop where verifying the signature of the modprobe * binary requires executing modprobe itself. Since the modprobe iint->mutex * is already held when the signature verification is performed, a deadlock * occurs as soon as modprobe is executed within the critical region, since * the same lock cannot be taken again. * * This happens when public_key_verify_signature(), in case of RSA algorithm, * use alg_name to store internal information in order to construct an * algorithm on the fly, but crypto_larval_lookup() will try to use alg_name * in order to load a kernel module with same name. * * Since we don't have any real "crypto-pkcs1(rsa,*)" kernel modules, * we are safe to fail such module request from crypto_larval_lookup(), and * avoid the verification loop. * * Return: Zero if it is safe to load the kernel module, -EINVAL otherwise. */ static int ima_kernel_module_request(char *kmod_name) { if (strncmp(kmod_name, "crypto-pkcs1(rsa,", 17) == 0) return -EINVAL; return 0; } #endif /* CONFIG_INTEGRITY_ASYMMETRIC_KEYS */ static int __init init_ima(void) { int error; ima_appraise_parse_cmdline(); ima_init_template_list(); hash_setup(CONFIG_IMA_DEFAULT_HASH); error = ima_init(); if (error && strcmp(hash_algo_name[ima_hash_algo], CONFIG_IMA_DEFAULT_HASH) != 0) { pr_info("Allocating %s failed, going to use default hash algorithm %s\n", hash_algo_name[ima_hash_algo], CONFIG_IMA_DEFAULT_HASH); hash_setup_done = 0; hash_setup(CONFIG_IMA_DEFAULT_HASH); error = ima_init(); } if (error) return error; error = register_blocking_lsm_notifier(&ima_lsm_policy_notifier); if (error) pr_warn("Couldn't register LSM notifier, error %d\n", error); if (!error) ima_update_policy_flags(); return error; } static struct security_hook_list ima_hooks[] __ro_after_init = { LSM_HOOK_INIT(bprm_check_security, ima_bprm_check), LSM_HOOK_INIT(file_post_open, ima_file_check), LSM_HOOK_INIT(inode_post_create_tmpfile, ima_post_create_tmpfile), LSM_HOOK_INIT(file_release, ima_file_free), LSM_HOOK_INIT(mmap_file, ima_file_mmap), LSM_HOOK_INIT(file_mprotect, ima_file_mprotect), LSM_HOOK_INIT(kernel_load_data, ima_load_data), LSM_HOOK_INIT(kernel_post_load_data, ima_post_load_data), LSM_HOOK_INIT(kernel_read_file, ima_read_file), LSM_HOOK_INIT(kernel_post_read_file, ima_post_read_file), LSM_HOOK_INIT(path_post_mknod, ima_post_path_mknod), #ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS LSM_HOOK_INIT(key_post_create_or_update, ima_post_key_create_or_update), #endif #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS LSM_HOOK_INIT(kernel_module_request, ima_kernel_module_request), #endif LSM_HOOK_INIT(inode_free_security_rcu, ima_inode_free_rcu), }; static const struct lsm_id ima_lsmid = { .name = "ima", .id = LSM_ID_IMA, }; static int __init init_ima_lsm(void) { ima_iintcache_init(); security_add_hooks(ima_hooks, ARRAY_SIZE(ima_hooks), &ima_lsmid); init_ima_appraise_lsm(&ima_lsmid); return 0; } struct lsm_blob_sizes ima_blob_sizes __ro_after_init = { .lbs_inode = sizeof(struct ima_iint_cache *), }; DEFINE_LSM(ima) = { .name = "ima", .init = init_ima_lsm, .order = LSM_ORDER_LAST, .blobs = &ima_blob_sizes, }; late_initcall(init_ima); /* Start IMA after the TPM is available */ |
| 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* AFS client file system * * Copyright (C) 2002,5 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/init.h> #include <linux/completion.h> #include <linux/sched.h> #include <linux/random.h> #include <linux/proc_fs.h> #define CREATE_TRACE_POINTS #include "internal.h" MODULE_DESCRIPTION("AFS Client File System"); MODULE_AUTHOR("Red Hat, Inc."); MODULE_LICENSE("GPL"); unsigned afs_debug; module_param_named(debug, afs_debug, uint, S_IWUSR | S_IRUGO); MODULE_PARM_DESC(debug, "AFS debugging mask"); static char *rootcell; module_param(rootcell, charp, 0); MODULE_PARM_DESC(rootcell, "root AFS cell name and VL server IP addr list"); struct workqueue_struct *afs_wq; static struct proc_dir_entry *afs_proc_symlink; #if defined(CONFIG_ALPHA) const char afs_init_sysname[] = "alpha_linux26"; #elif defined(CONFIG_X86_64) const char afs_init_sysname[] = "amd64_linux26"; #elif defined(CONFIG_ARM) const char afs_init_sysname[] = "arm_linux26"; #elif defined(CONFIG_ARM64) const char afs_init_sysname[] = "aarch64_linux26"; #elif defined(CONFIG_X86_32) const char afs_init_sysname[] = "i386_linux26"; #elif defined(CONFIG_PPC64) const char afs_init_sysname[] = "ppc64_linux26"; #elif defined(CONFIG_PPC32) const char afs_init_sysname[] = "ppc_linux26"; #elif defined(CONFIG_S390) #ifdef CONFIG_64BIT const char afs_init_sysname[] = "s390x_linux26"; #else const char afs_init_sysname[] = "s390_linux26"; #endif #elif defined(CONFIG_SPARC64) const char afs_init_sysname[] = "sparc64_linux26"; #elif defined(CONFIG_SPARC32) const char afs_init_sysname[] = "sparc_linux26"; #else const char afs_init_sysname[] = "unknown_linux26"; #endif /* * Initialise an AFS network namespace record. */ static int __net_init afs_net_init(struct net *net_ns) { struct afs_sysnames *sysnames; struct afs_net *net = afs_net(net_ns); int ret; net->net = net_ns; net->live = true; generate_random_uuid((unsigned char *)&net->uuid); INIT_WORK(&net->charge_preallocation_work, afs_charge_preallocation); mutex_init(&net->socket_mutex); net->cells = RB_ROOT; init_rwsem(&net->cells_lock); INIT_WORK(&net->cells_manager, afs_manage_cells); timer_setup(&net->cells_timer, afs_cells_timer, 0); mutex_init(&net->cells_alias_lock); mutex_init(&net->proc_cells_lock); INIT_HLIST_HEAD(&net->proc_cells); seqlock_init(&net->fs_lock); net->fs_servers = RB_ROOT; INIT_LIST_HEAD(&net->fs_probe_fast); INIT_LIST_HEAD(&net->fs_probe_slow); INIT_HLIST_HEAD(&net->fs_proc); INIT_HLIST_HEAD(&net->fs_addresses); seqlock_init(&net->fs_addr_lock); INIT_WORK(&net->fs_manager, afs_manage_servers); timer_setup(&net->fs_timer, afs_servers_timer, 0); INIT_WORK(&net->fs_prober, afs_fs_probe_dispatcher); timer_setup(&net->fs_probe_timer, afs_fs_probe_timer, 0); atomic_set(&net->servers_outstanding, 1); ret = -ENOMEM; sysnames = kzalloc(sizeof(*sysnames), GFP_KERNEL); if (!sysnames) goto error_sysnames; sysnames->subs[0] = (char *)&afs_init_sysname; sysnames->nr = 1; refcount_set(&sysnames->usage, 1); net->sysnames = sysnames; rwlock_init(&net->sysnames_lock); /* Register the /proc stuff */ ret = afs_proc_init(net); if (ret < 0) goto error_proc; /* Initialise the cell DB */ ret = afs_cell_init(net, rootcell); if (ret < 0) goto error_cell_init; /* Create the RxRPC transport */ ret = afs_open_socket(net); if (ret < 0) goto error_open_socket; return 0; error_open_socket: net->live = false; afs_fs_probe_cleanup(net); afs_cell_purge(net); afs_purge_servers(net); error_cell_init: net->live = false; afs_proc_cleanup(net); error_proc: afs_put_sysnames(net->sysnames); error_sysnames: net->live = false; return ret; } /* * Clean up and destroy an AFS network namespace record. */ static void __net_exit afs_net_exit(struct net *net_ns) { struct afs_net *net = afs_net(net_ns); net->live = false; afs_fs_probe_cleanup(net); afs_cell_purge(net); afs_purge_servers(net); afs_close_socket(net); afs_proc_cleanup(net); afs_put_sysnames(net->sysnames); kfree_rcu(rcu_access_pointer(net->address_prefs), rcu); } static struct pernet_operations afs_net_ops = { .init = afs_net_init, .exit = afs_net_exit, .id = &afs_net_id, .size = sizeof(struct afs_net), }; /* * initialise the AFS client FS module */ static int __init afs_init(void) { int ret = -ENOMEM; printk(KERN_INFO "kAFS: Red Hat AFS client v0.1 registering.\n"); afs_wq = alloc_workqueue("afs", 0, 0); if (!afs_wq) goto error_afs_wq; afs_async_calls = alloc_workqueue("kafsd", WQ_MEM_RECLAIM, 0); if (!afs_async_calls) goto error_async; afs_lock_manager = alloc_workqueue("kafs_lockd", WQ_MEM_RECLAIM, 0); if (!afs_lock_manager) goto error_lockmgr; ret = register_pernet_device(&afs_net_ops); if (ret < 0) goto error_net; /* register the filesystems */ ret = afs_fs_init(); if (ret < 0) goto error_fs; afs_proc_symlink = proc_symlink("fs/afs", NULL, "../self/net/afs"); if (!afs_proc_symlink) { ret = -ENOMEM; goto error_proc; } return ret; error_proc: afs_fs_exit(); error_fs: unregister_pernet_device(&afs_net_ops); error_net: destroy_workqueue(afs_lock_manager); error_lockmgr: destroy_workqueue(afs_async_calls); error_async: destroy_workqueue(afs_wq); error_afs_wq: rcu_barrier(); printk(KERN_ERR "kAFS: failed to register: %d\n", ret); return ret; } /* XXX late_initcall is kludgy, but the only alternative seems to create * a transport upon the first mount, which is worse. Or is it? */ late_initcall(afs_init); /* must be called after net/ to create socket */ /* * clean up on module removal */ static void __exit afs_exit(void) { printk(KERN_INFO "kAFS: Red Hat AFS client v0.1 unregistering.\n"); proc_remove(afs_proc_symlink); afs_fs_exit(); unregister_pernet_device(&afs_net_ops); destroy_workqueue(afs_lock_manager); destroy_workqueue(afs_async_calls); destroy_workqueue(afs_wq); afs_clean_up_permit_cache(); rcu_barrier(); } module_exit(afs_exit); |
| 2 2 6 2 1 2 2 1 1 1 2 2 2 2 1 1 1 1 1 2 1 1 11 12 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NetLabel CALIPSO/IPv6 Support * * This file defines the CALIPSO/IPv6 functions for the NetLabel system. The * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and CALIPSO. * * Authors: Paul Moore <paul@paul-moore.com> * Huw Davies <huw@codeweavers.com> */ /* (c) Copyright Hewlett-Packard Development Company, L.P., 2006 * (c) Copyright Huw Davies <huw@codeweavers.com>, 2015 */ #include <linux/types.h> #include <linux/socket.h> #include <linux/string.h> #include <linux/skbuff.h> #include <linux/audit.h> #include <linux/slab.h> #include <net/sock.h> #include <net/netlink.h> #include <net/genetlink.h> #include <net/netlabel.h> #include <net/calipso.h> #include <linux/atomic.h> #include "netlabel_user.h" #include "netlabel_calipso.h" #include "netlabel_mgmt.h" #include "netlabel_domainhash.h" /* Argument struct for calipso_doi_walk() */ struct netlbl_calipso_doiwalk_arg { struct netlink_callback *nl_cb; struct sk_buff *skb; u32 seq; }; /* Argument struct for netlbl_domhsh_walk() */ struct netlbl_domhsh_walk_arg { struct netlbl_audit *audit_info; u32 doi; }; /* NetLabel Generic NETLINK CALIPSO family */ static struct genl_family netlbl_calipso_gnl_family; /* NetLabel Netlink attribute policy */ static const struct nla_policy calipso_genl_policy[NLBL_CALIPSO_A_MAX + 1] = { [NLBL_CALIPSO_A_DOI] = { .type = NLA_U32 }, [NLBL_CALIPSO_A_MTYPE] = { .type = NLA_U32 }, }; static const struct netlbl_calipso_ops *calipso_ops; /** * netlbl_calipso_ops_register - Register the CALIPSO operations * @ops: ops to register * * Description: * Register the CALIPSO packet engine operations. * */ const struct netlbl_calipso_ops * netlbl_calipso_ops_register(const struct netlbl_calipso_ops *ops) { return xchg(&calipso_ops, ops); } EXPORT_SYMBOL(netlbl_calipso_ops_register); static const struct netlbl_calipso_ops *netlbl_calipso_ops_get(void) { return READ_ONCE(calipso_ops); } /* NetLabel Command Handlers */ /** * netlbl_calipso_add_pass - Adds a CALIPSO pass DOI definition * @info: the Generic NETLINK info block * @audit_info: NetLabel audit information * * Description: * Create a new CALIPSO_MAP_PASS DOI definition based on the given ADD message * and add it to the CALIPSO engine. Return zero on success and non-zero on * error. * */ static int netlbl_calipso_add_pass(struct genl_info *info, struct netlbl_audit *audit_info) { int ret_val; struct calipso_doi *doi_def = NULL; doi_def = kmalloc(sizeof(*doi_def), GFP_KERNEL); if (!doi_def) return -ENOMEM; doi_def->type = CALIPSO_MAP_PASS; doi_def->doi = nla_get_u32(info->attrs[NLBL_CALIPSO_A_DOI]); ret_val = calipso_doi_add(doi_def, audit_info); if (ret_val != 0) calipso_doi_free(doi_def); return ret_val; } /** * netlbl_calipso_add - Handle an ADD message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Create a new DOI definition based on the given ADD message and add it to the * CALIPSO engine. Returns zero on success, negative values on failure. * */ static int netlbl_calipso_add(struct sk_buff *skb, struct genl_info *info) { int ret_val = -EINVAL; struct netlbl_audit audit_info; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (!info->attrs[NLBL_CALIPSO_A_DOI] || !info->attrs[NLBL_CALIPSO_A_MTYPE]) return -EINVAL; if (!ops) return -EOPNOTSUPP; netlbl_netlink_auditinfo(&audit_info); switch (nla_get_u32(info->attrs[NLBL_CALIPSO_A_MTYPE])) { case CALIPSO_MAP_PASS: ret_val = netlbl_calipso_add_pass(info, &audit_info); break; } if (ret_val == 0) atomic_inc(&netlabel_mgmt_protocount); return ret_val; } /** * netlbl_calipso_list - Handle a LIST message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated LIST message and respond accordingly. * Returns zero on success and negative values on error. * */ static int netlbl_calipso_list(struct sk_buff *skb, struct genl_info *info) { int ret_val; struct sk_buff *ans_skb = NULL; void *data; u32 doi; struct calipso_doi *doi_def; if (!info->attrs[NLBL_CALIPSO_A_DOI]) { ret_val = -EINVAL; goto list_failure; } doi = nla_get_u32(info->attrs[NLBL_CALIPSO_A_DOI]); doi_def = calipso_doi_getdef(doi); if (!doi_def) { ret_val = -EINVAL; goto list_failure; } ans_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!ans_skb) { ret_val = -ENOMEM; goto list_failure_put; } data = genlmsg_put_reply(ans_skb, info, &netlbl_calipso_gnl_family, 0, NLBL_CALIPSO_C_LIST); if (!data) { ret_val = -ENOMEM; goto list_failure_put; } ret_val = nla_put_u32(ans_skb, NLBL_CALIPSO_A_MTYPE, doi_def->type); if (ret_val != 0) goto list_failure_put; calipso_doi_putdef(doi_def); genlmsg_end(ans_skb, data); return genlmsg_reply(ans_skb, info); list_failure_put: calipso_doi_putdef(doi_def); list_failure: kfree_skb(ans_skb); return ret_val; } /** * netlbl_calipso_listall_cb - calipso_doi_walk() callback for LISTALL * @doi_def: the CALIPSO DOI definition * @arg: the netlbl_calipso_doiwalk_arg structure * * Description: * This function is designed to be used as a callback to the * calipso_doi_walk() function for use in generating a response for a LISTALL * message. Returns the size of the message on success, negative values on * failure. * */ static int netlbl_calipso_listall_cb(struct calipso_doi *doi_def, void *arg) { int ret_val = -ENOMEM; struct netlbl_calipso_doiwalk_arg *cb_arg = arg; void *data; data = genlmsg_put(cb_arg->skb, NETLINK_CB(cb_arg->nl_cb->skb).portid, cb_arg->seq, &netlbl_calipso_gnl_family, NLM_F_MULTI, NLBL_CALIPSO_C_LISTALL); if (!data) goto listall_cb_failure; ret_val = nla_put_u32(cb_arg->skb, NLBL_CALIPSO_A_DOI, doi_def->doi); if (ret_val != 0) goto listall_cb_failure; ret_val = nla_put_u32(cb_arg->skb, NLBL_CALIPSO_A_MTYPE, doi_def->type); if (ret_val != 0) goto listall_cb_failure; genlmsg_end(cb_arg->skb, data); return 0; listall_cb_failure: genlmsg_cancel(cb_arg->skb, data); return ret_val; } /** * netlbl_calipso_listall - Handle a LISTALL message * @skb: the NETLINK buffer * @cb: the NETLINK callback * * Description: * Process a user generated LISTALL message and respond accordingly. Returns * zero on success and negative values on error. * */ static int netlbl_calipso_listall(struct sk_buff *skb, struct netlink_callback *cb) { struct netlbl_calipso_doiwalk_arg cb_arg; u32 doi_skip = cb->args[0]; cb_arg.nl_cb = cb; cb_arg.skb = skb; cb_arg.seq = cb->nlh->nlmsg_seq; calipso_doi_walk(&doi_skip, netlbl_calipso_listall_cb, &cb_arg); cb->args[0] = doi_skip; return skb->len; } /** * netlbl_calipso_remove_cb - netlbl_calipso_remove() callback for REMOVE * @entry: LSM domain mapping entry * @arg: the netlbl_domhsh_walk_arg structure * * Description: * This function is intended for use by netlbl_calipso_remove() as the callback * for the netlbl_domhsh_walk() function; it removes LSM domain map entries * which are associated with the CALIPSO DOI specified in @arg. Returns zero on * success, negative values on failure. * */ static int netlbl_calipso_remove_cb(struct netlbl_dom_map *entry, void *arg) { struct netlbl_domhsh_walk_arg *cb_arg = arg; if (entry->def.type == NETLBL_NLTYPE_CALIPSO && entry->def.calipso->doi == cb_arg->doi) return netlbl_domhsh_remove_entry(entry, cb_arg->audit_info); return 0; } /** * netlbl_calipso_remove - Handle a REMOVE message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated REMOVE message and respond accordingly. Returns * zero on success, negative values on failure. * */ static int netlbl_calipso_remove(struct sk_buff *skb, struct genl_info *info) { int ret_val = -EINVAL; struct netlbl_domhsh_walk_arg cb_arg; struct netlbl_audit audit_info; u32 skip_bkt = 0; u32 skip_chain = 0; if (!info->attrs[NLBL_CALIPSO_A_DOI]) return -EINVAL; netlbl_netlink_auditinfo(&audit_info); cb_arg.doi = nla_get_u32(info->attrs[NLBL_CALIPSO_A_DOI]); cb_arg.audit_info = &audit_info; ret_val = netlbl_domhsh_walk(&skip_bkt, &skip_chain, netlbl_calipso_remove_cb, &cb_arg); if (ret_val == 0 || ret_val == -ENOENT) { ret_val = calipso_doi_remove(cb_arg.doi, &audit_info); if (ret_val == 0) atomic_dec(&netlabel_mgmt_protocount); } return ret_val; } /* NetLabel Generic NETLINK Command Definitions */ static const struct genl_small_ops netlbl_calipso_ops[] = { { .cmd = NLBL_CALIPSO_C_ADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = netlbl_calipso_add, .dumpit = NULL, }, { .cmd = NLBL_CALIPSO_C_REMOVE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = netlbl_calipso_remove, .dumpit = NULL, }, { .cmd = NLBL_CALIPSO_C_LIST, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, .doit = netlbl_calipso_list, .dumpit = NULL, }, { .cmd = NLBL_CALIPSO_C_LISTALL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, .doit = NULL, .dumpit = netlbl_calipso_listall, }, }; static struct genl_family netlbl_calipso_gnl_family __ro_after_init = { .hdrsize = 0, .name = NETLBL_NLTYPE_CALIPSO_NAME, .version = NETLBL_PROTO_VERSION, .maxattr = NLBL_CALIPSO_A_MAX, .policy = calipso_genl_policy, .module = THIS_MODULE, .small_ops = netlbl_calipso_ops, .n_small_ops = ARRAY_SIZE(netlbl_calipso_ops), .resv_start_op = NLBL_CALIPSO_C_LISTALL + 1, }; /* NetLabel Generic NETLINK Protocol Functions */ /** * netlbl_calipso_genl_init - Register the CALIPSO NetLabel component * * Description: * Register the CALIPSO packet NetLabel component with the Generic NETLINK * mechanism. Returns zero on success, negative values on failure. * */ int __init netlbl_calipso_genl_init(void) { return genl_register_family(&netlbl_calipso_gnl_family); } /** * calipso_doi_add - Add a new DOI to the CALIPSO protocol engine * @doi_def: the DOI structure * @audit_info: NetLabel audit information * * Description: * The caller defines a new DOI for use by the CALIPSO engine and calls this * function to add it to the list of acceptable domains. The caller must * ensure that the mapping table specified in @doi_def->map meets all of the * requirements of the mapping type (see calipso.h for details). Returns * zero on success and non-zero on failure. * */ int calipso_doi_add(struct calipso_doi *doi_def, struct netlbl_audit *audit_info) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->doi_add(doi_def, audit_info); return ret_val; } /** * calipso_doi_free - Frees a DOI definition * @doi_def: the DOI definition * * Description: * This function frees all of the memory associated with a DOI definition. * */ void calipso_doi_free(struct calipso_doi *doi_def) { const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ops->doi_free(doi_def); } /** * calipso_doi_remove - Remove an existing DOI from the CALIPSO protocol engine * @doi: the DOI value * @audit_info: NetLabel audit information * * Description: * Removes a DOI definition from the CALIPSO engine. The NetLabel routines will * be called to release their own LSM domain mappings as well as our own * domain list. Returns zero on success and negative values on failure. * */ int calipso_doi_remove(u32 doi, struct netlbl_audit *audit_info) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->doi_remove(doi, audit_info); return ret_val; } /** * calipso_doi_getdef - Returns a reference to a valid DOI definition * @doi: the DOI value * * Description: * Searches for a valid DOI definition and if one is found it is returned to * the caller. Otherwise NULL is returned. The caller must ensure that * calipso_doi_putdef() is called when the caller is done. * */ struct calipso_doi *calipso_doi_getdef(u32 doi) { struct calipso_doi *ret_val = NULL; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->doi_getdef(doi); return ret_val; } /** * calipso_doi_putdef - Releases a reference for the given DOI definition * @doi_def: the DOI definition * * Description: * Releases a DOI definition reference obtained from calipso_doi_getdef(). * */ void calipso_doi_putdef(struct calipso_doi *doi_def) { const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ops->doi_putdef(doi_def); } /** * calipso_doi_walk - Iterate through the DOI definitions * @skip_cnt: skip past this number of DOI definitions, updated * @callback: callback for each DOI definition * @cb_arg: argument for the callback function * * Description: * Iterate over the DOI definition list, skipping the first @skip_cnt entries. * For each entry call @callback, if @callback returns a negative value stop * 'walking' through the list and return. Updates the value in @skip_cnt upon * return. Returns zero on success, negative values on failure. * */ int calipso_doi_walk(u32 *skip_cnt, int (*callback)(struct calipso_doi *doi_def, void *arg), void *cb_arg) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->doi_walk(skip_cnt, callback, cb_arg); return ret_val; } /** * calipso_sock_getattr - Get the security attributes from a sock * @sk: the sock * @secattr: the security attributes * * Description: * Query @sk to see if there is a CALIPSO option attached to the sock and if * there is return the CALIPSO security attributes in @secattr. This function * requires that @sk be locked, or privately held, but it does not do any * locking itself. Returns zero on success and negative values on failure. * */ int calipso_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->sock_getattr(sk, secattr); return ret_val; } /** * calipso_sock_setattr - Add a CALIPSO option to a socket * @sk: the socket * @doi_def: the CALIPSO DOI to use * @secattr: the specific security attributes of the socket * * Description: * Set the CALIPSO option on the given socket using the DOI definition and * security attributes passed to the function. This function requires * exclusive access to @sk, which means it either needs to be in the * process of being created or locked. Returns zero on success and negative * values on failure. * */ int calipso_sock_setattr(struct sock *sk, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->sock_setattr(sk, doi_def, secattr); return ret_val; } /** * calipso_sock_delattr - Delete the CALIPSO option from a socket * @sk: the socket * * Description: * Removes the CALIPSO option from a socket, if present. * */ void calipso_sock_delattr(struct sock *sk) { const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ops->sock_delattr(sk); } /** * calipso_req_setattr - Add a CALIPSO option to a connection request socket * @req: the connection request socket * @doi_def: the CALIPSO DOI to use * @secattr: the specific security attributes of the socket * * Description: * Set the CALIPSO option on the given socket using the DOI definition and * security attributes passed to the function. Returns zero on success and * negative values on failure. * */ int calipso_req_setattr(struct request_sock *req, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->req_setattr(req, doi_def, secattr); return ret_val; } /** * calipso_req_delattr - Delete the CALIPSO option from a request socket * @req: the request socket * * Description: * Removes the CALIPSO option from a request socket, if present. * */ void calipso_req_delattr(struct request_sock *req) { const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ops->req_delattr(req); } /** * calipso_optptr - Find the CALIPSO option in the packet * @skb: the packet * * Description: * Parse the packet's IP header looking for a CALIPSO option. Returns a pointer * to the start of the CALIPSO option on success, NULL if one if not found. * */ unsigned char *calipso_optptr(const struct sk_buff *skb) { unsigned char *ret_val = NULL; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->skbuff_optptr(skb); return ret_val; } /** * calipso_getattr - Get the security attributes from a memory block. * @calipso: the CALIPSO option * @secattr: the security attributes * * Description: * Inspect @calipso and return the security attributes in @secattr. * Returns zero on success and negative values on failure. * */ int calipso_getattr(const unsigned char *calipso, struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->opt_getattr(calipso, secattr); return ret_val; } /** * calipso_skbuff_setattr - Set the CALIPSO option on a packet * @skb: the packet * @doi_def: the CALIPSO DOI to use * @secattr: the security attributes * * Description: * Set the CALIPSO option on the given packet based on the security attributes. * Returns a pointer to the IP header on success and NULL on failure. * */ int calipso_skbuff_setattr(struct sk_buff *skb, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->skbuff_setattr(skb, doi_def, secattr); return ret_val; } /** * calipso_skbuff_delattr - Delete any CALIPSO options from a packet * @skb: the packet * * Description: * Removes any and all CALIPSO options from the given packet. Returns zero on * success, negative values on failure. * */ int calipso_skbuff_delattr(struct sk_buff *skb) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->skbuff_delattr(skb); return ret_val; } /** * calipso_cache_invalidate - Invalidates the current CALIPSO cache * * Description: * Invalidates and frees any entries in the CALIPSO cache. Returns zero on * success and negative values on failure. * */ void calipso_cache_invalidate(void) { const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ops->cache_invalidate(); } /** * calipso_cache_add - Add an entry to the CALIPSO cache * @calipso_ptr: the CALIPSO option * @secattr: the packet's security attributes * * Description: * Add a new entry into the CALIPSO label mapping cache. * Returns zero on success, negative values on failure. * */ int calipso_cache_add(const unsigned char *calipso_ptr, const struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->cache_add(calipso_ptr, secattr); return ret_val; } |
| 78 78 78 96 96 34 78 8 7 5 2 1 2 2 3 3 3 3 3 3 1 5 5 4 5 4 5 6 6 6 6 6 41 1 28 21 21 21 9 9 1 1 1 1 1 1 16 11 11 7 5 2 5 8 8 12 12 12 12 8 5 9 9 9 9 9 8 6 6 3 3 5 11 11 11 24 17 14 1 6 16 16 11 15 9 9 8 9 9 9 9 10 12 4 13 13 11 11 9 4 8 7 7 7 7 20 20 20 2 7 20 1 1 20 2 19 8 2 21 21 20 21 7 1 8 8 8 8 8 8 8 8 8 5 5 8 8 8 8 1 8 8 8 8 8 5 8 8 8 8 8 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 8 8 3 4 1 8 8 8 8 8 8 8 1 1 8 8 8 8 1 8 4 8 8 1 2 8 4 8 3 8 19 19 2 17 3 3 4 1 11 9 9 1 9 9 30 28 29 14 15 11 11 10 9 9 4 9 9 9 8 8 4 8 8 2 7 1 24 10 2 1 4 5 1 1 2 10 10 10 5 5 3 2 281 278 2 5 5 12 11 5 5 5 11 4 3 13 12 1 1 12 11 10 9 10 10 10 5 1 1 7 2 3 3 2 9 1 5 4 2 13 9 9 3 7 30 29 2 37 37 37 1 10 29 12 18 24 37 30 12 13 2 11 37 13 30 2 30 29 3 9 8 4 9 4 2 2 2 2 8 8 32 8 8 8 8 7 8 35 35 1 12 12 11 7 7 7 5 5 2 2 24 10 65 9 4 4 4 10 10 10 8 2 2 2 2 2 12 12 12 12 12 12 12 12 1 4 32 26 6 6 6 11 11 11 9 1 1 2 10 10 1 10 10 11 11 11 1 11 1 11 11 40 40 40 19 20 25 25 1 25 25 25 25 10 10 35 35 35 35 35 13 13 14 14 14 16 16 1 1 279 283 285 1 1 1 1 278 13 283 17 10 11 16 24 3 286 3 3 3 3 3 3 3 1 1 1 1 4 3 3 3 3 3 2 2 2 15 14 3 1 2 2 11 11 5 1 2 2 1 38 38 38 38 38 38 14 25 38 15 30 14 25 16 30 10 10 1 5 4 6 4 7 7 7 1 6 6 1 6 2 2 2 1 1 1 3 6 6 6 6 1 4 1 3 1 | 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 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 | // SPDX-License-Identifier: GPL-2.0 /* Multipath TCP * * Copyright (c) 2017 - 2019, Intel Corporation. */ #define pr_fmt(fmt) "MPTCP: " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/sched/signal.h> #include <linux/atomic.h> #include <net/sock.h> #include <net/inet_common.h> #include <net/inet_hashtables.h> #include <net/protocol.h> #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/transp_v6.h> #endif #include <net/mptcp.h> #include <net/hotdata.h> #include <net/xfrm.h> #include <asm/ioctls.h> #include "protocol.h" #include "mib.h" #define CREATE_TRACE_POINTS #include <trace/events/mptcp.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) struct mptcp6_sock { struct mptcp_sock msk; struct ipv6_pinfo np; }; #endif enum { MPTCP_CMSG_TS = BIT(0), MPTCP_CMSG_INQ = BIT(1), }; static struct percpu_counter mptcp_sockets_allocated ____cacheline_aligned_in_smp; static void __mptcp_destroy_sock(struct sock *sk); static void mptcp_check_send_data_fin(struct sock *sk); DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); static struct net_device mptcp_napi_dev; /* Returns end sequence number of the receiver's advertised window */ static u64 mptcp_wnd_end(const struct mptcp_sock *msk) { return READ_ONCE(msk->wnd_end); } static const struct proto_ops *mptcp_fallback_tcp_ops(const struct sock *sk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (sk->sk_prot == &tcpv6_prot) return &inet6_stream_ops; #endif WARN_ON_ONCE(sk->sk_prot != &tcp_prot); return &inet_stream_ops; } static int __mptcp_socket_create(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; struct socket *ssock; int err; err = mptcp_subflow_create_socket(sk, sk->sk_family, &ssock); if (err) return err; msk->scaling_ratio = tcp_sk(ssock->sk)->scaling_ratio; WRITE_ONCE(msk->first, ssock->sk); subflow = mptcp_subflow_ctx(ssock->sk); list_add(&subflow->node, &msk->conn_list); sock_hold(ssock->sk); subflow->request_mptcp = 1; subflow->subflow_id = msk->subflow_id++; /* This is the first subflow, always with id 0 */ WRITE_ONCE(subflow->local_id, 0); mptcp_sock_graft(msk->first, sk->sk_socket); iput(SOCK_INODE(ssock)); return 0; } /* If the MPC handshake is not started, returns the first subflow, * eventually allocating it. */ struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; int ret; if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) return ERR_PTR(-EINVAL); if (!msk->first) { ret = __mptcp_socket_create(msk); if (ret) return ERR_PTR(ret); } return msk->first; } static void mptcp_drop(struct sock *sk, struct sk_buff *skb) { sk_drops_add(sk, skb); __kfree_skb(skb); } static void mptcp_rmem_fwd_alloc_add(struct sock *sk, int size) { WRITE_ONCE(mptcp_sk(sk)->rmem_fwd_alloc, mptcp_sk(sk)->rmem_fwd_alloc + size); } static void mptcp_rmem_charge(struct sock *sk, int size) { mptcp_rmem_fwd_alloc_add(sk, -size); } static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, struct sk_buff *from) { bool fragstolen; int delta; if (MPTCP_SKB_CB(from)->offset || ((to->len + from->len) > (sk->sk_rcvbuf >> 3)) || !skb_try_coalesce(to, from, &fragstolen, &delta)) return false; pr_debug("colesced seq %llx into %llx new len %d new end seq %llx\n", MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq, to->len, MPTCP_SKB_CB(from)->end_seq); MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq; /* note the fwd memory can reach a negative value after accounting * for the delta, but the later skb free will restore a non * negative one */ atomic_add(delta, &sk->sk_rmem_alloc); mptcp_rmem_charge(sk, delta); kfree_skb_partial(from, fragstolen); return true; } static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to, struct sk_buff *from) { if (MPTCP_SKB_CB(from)->map_seq != MPTCP_SKB_CB(to)->end_seq) return false; return mptcp_try_coalesce((struct sock *)msk, to, from); } static void __mptcp_rmem_reclaim(struct sock *sk, int amount) { amount >>= PAGE_SHIFT; mptcp_rmem_charge(sk, amount << PAGE_SHIFT); __sk_mem_reduce_allocated(sk, amount); } static void mptcp_rmem_uncharge(struct sock *sk, int size) { struct mptcp_sock *msk = mptcp_sk(sk); int reclaimable; mptcp_rmem_fwd_alloc_add(sk, size); reclaimable = msk->rmem_fwd_alloc - sk_unused_reserved_mem(sk); /* see sk_mem_uncharge() for the rationale behind the following schema */ if (unlikely(reclaimable >= PAGE_SIZE)) __mptcp_rmem_reclaim(sk, reclaimable); } static void mptcp_rfree(struct sk_buff *skb) { unsigned int len = skb->truesize; struct sock *sk = skb->sk; atomic_sub(len, &sk->sk_rmem_alloc); mptcp_rmem_uncharge(sk, len); } void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk) { skb_orphan(skb); skb->sk = sk; skb->destructor = mptcp_rfree; atomic_add(skb->truesize, &sk->sk_rmem_alloc); mptcp_rmem_charge(sk, skb->truesize); } /* "inspired" by tcp_data_queue_ofo(), main differences: * - use mptcp seqs * - don't cope with sacks */ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb) { struct sock *sk = (struct sock *)msk; struct rb_node **p, *parent; u64 seq, end_seq, max_seq; struct sk_buff *skb1; seq = MPTCP_SKB_CB(skb)->map_seq; end_seq = MPTCP_SKB_CB(skb)->end_seq; max_seq = atomic64_read(&msk->rcv_wnd_sent); pr_debug("msk=%p seq=%llx limit=%llx empty=%d\n", msk, seq, max_seq, RB_EMPTY_ROOT(&msk->out_of_order_queue)); if (after64(end_seq, max_seq)) { /* out of window */ mptcp_drop(sk, skb); pr_debug("oow by %lld, rcv_wnd_sent %llu\n", (unsigned long long)end_seq - (unsigned long)max_seq, (unsigned long long)atomic64_read(&msk->rcv_wnd_sent)); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_NODSSWINDOW); return; } p = &msk->out_of_order_queue.rb_node; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUE); if (RB_EMPTY_ROOT(&msk->out_of_order_queue)) { rb_link_node(&skb->rbnode, NULL, p); rb_insert_color(&skb->rbnode, &msk->out_of_order_queue); msk->ooo_last_skb = skb; goto end; } /* with 2 subflows, adding at end of ooo queue is quite likely * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. */ if (mptcp_ooo_try_coalesce(msk, msk->ooo_last_skb, skb)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL); return; } /* Can avoid an rbtree lookup if we are adding skb after ooo_last_skb */ if (!before64(seq, MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL); parent = &msk->ooo_last_skb->rbnode; p = &parent->rb_right; goto insert; } /* Find place to insert this segment. Handle overlaps on the way. */ parent = NULL; while (*p) { parent = *p; skb1 = rb_to_skb(parent); if (before64(seq, MPTCP_SKB_CB(skb1)->map_seq)) { p = &parent->rb_left; continue; } if (before64(seq, MPTCP_SKB_CB(skb1)->end_seq)) { if (!after64(end_seq, MPTCP_SKB_CB(skb1)->end_seq)) { /* All the bits are present. Drop. */ mptcp_drop(sk, skb); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); return; } if (after64(seq, MPTCP_SKB_CB(skb1)->map_seq)) { /* partial overlap: * | skb | * | skb1 | * continue traversing */ } else { /* skb's seq == skb1's seq and skb covers skb1. * Replace skb1 with skb. */ rb_replace_node(&skb1->rbnode, &skb->rbnode, &msk->out_of_order_queue); mptcp_drop(sk, skb1); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); goto merge_right; } } else if (mptcp_ooo_try_coalesce(msk, skb1, skb)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE); return; } p = &parent->rb_right; } insert: /* Insert segment into RB tree. */ rb_link_node(&skb->rbnode, parent, p); rb_insert_color(&skb->rbnode, &msk->out_of_order_queue); merge_right: /* Remove other segments covered by skb. */ while ((skb1 = skb_rb_next(skb)) != NULL) { if (before64(end_seq, MPTCP_SKB_CB(skb1)->end_seq)) break; rb_erase(&skb1->rbnode, &msk->out_of_order_queue); mptcp_drop(sk, skb1); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); } /* If there is no skb after us, we are the last_skb ! */ if (!skb1) msk->ooo_last_skb = skb; end: skb_condense(skb); mptcp_set_owner_r(skb, sk); } static bool mptcp_rmem_schedule(struct sock *sk, struct sock *ssk, int size) { struct mptcp_sock *msk = mptcp_sk(sk); int amt, amount; if (size <= msk->rmem_fwd_alloc) return true; size -= msk->rmem_fwd_alloc; amt = sk_mem_pages(size); amount = amt << PAGE_SHIFT; if (!__sk_mem_raise_allocated(sk, size, amt, SK_MEM_RECV)) return false; mptcp_rmem_fwd_alloc_add(sk, amount); return true; } static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, struct sk_buff *skb, unsigned int offset, size_t copy_len) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = (struct sock *)msk; struct sk_buff *tail; bool has_rxtstamp; __skb_unlink(skb, &ssk->sk_receive_queue); skb_ext_reset(skb); skb_orphan(skb); /* try to fetch required memory from subflow */ if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); goto drop; } has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; /* the skb map_seq accounts for the skb offset: * mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq * value */ MPTCP_SKB_CB(skb)->map_seq = mptcp_subflow_get_mapped_dsn(subflow); MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + copy_len; MPTCP_SKB_CB(skb)->offset = offset; MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp; if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) { /* in sequence */ msk->bytes_received += copy_len; WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len); tail = skb_peek_tail(&sk->sk_receive_queue); if (tail && mptcp_try_coalesce(sk, tail, skb)) return true; mptcp_set_owner_r(skb, sk); __skb_queue_tail(&sk->sk_receive_queue, skb); return true; } else if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) { mptcp_data_queue_ofo(msk, skb); return false; } /* old data, keep it simple and drop the whole pkt, sender * will retransmit as needed, if needed. */ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); drop: mptcp_drop(sk, skb); return false; } static void mptcp_stop_rtx_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); sk_stop_timer(sk, &icsk->icsk_retransmit_timer); mptcp_sk(sk)->timer_ival = 0; } static void mptcp_close_wake_up(struct sock *sk) { if (sock_flag(sk, SOCK_DEAD)) return; sk->sk_state_change(sk); if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == TCP_CLOSE) sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP); else sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); } /* called under the msk socket lock */ static bool mptcp_pending_data_fin_ack(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); return ((1 << sk->sk_state) & (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) && msk->write_seq == READ_ONCE(msk->snd_una); } static void mptcp_check_data_fin_ack(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); /* Look for an acknowledged DATA_FIN */ if (mptcp_pending_data_fin_ack(sk)) { WRITE_ONCE(msk->snd_data_fin_enable, 0); switch (sk->sk_state) { case TCP_FIN_WAIT1: mptcp_set_state(sk, TCP_FIN_WAIT2); break; case TCP_CLOSING: case TCP_LAST_ACK: mptcp_set_state(sk, TCP_CLOSE); break; } mptcp_close_wake_up(sk); } } /* can be called with no lock acquired */ static bool mptcp_pending_data_fin(struct sock *sk, u64 *seq) { struct mptcp_sock *msk = mptcp_sk(sk); if (READ_ONCE(msk->rcv_data_fin) && ((1 << inet_sk_state_load(sk)) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2))) { u64 rcv_data_fin_seq = READ_ONCE(msk->rcv_data_fin_seq); if (READ_ONCE(msk->ack_seq) == rcv_data_fin_seq) { if (seq) *seq = rcv_data_fin_seq; return true; } } return false; } static void mptcp_set_datafin_timeout(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); u32 retransmits; retransmits = min_t(u32, icsk->icsk_retransmits, ilog2(TCP_RTO_MAX / TCP_RTO_MIN)); mptcp_sk(sk)->timer_ival = TCP_RTO_MIN << retransmits; } static void __mptcp_set_timeout(struct sock *sk, long tout) { mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN; } static long mptcp_timeout_from_subflow(const struct mptcp_subflow_context *subflow) { const struct sock *ssk = mptcp_subflow_tcp_sock(subflow); return inet_csk(ssk)->icsk_pending && !subflow->stale_count ? inet_csk(ssk)->icsk_timeout - jiffies : 0; } static void mptcp_set_timeout(struct sock *sk) { struct mptcp_subflow_context *subflow; long tout = 0; mptcp_for_each_subflow(mptcp_sk(sk), subflow) tout = max(tout, mptcp_timeout_from_subflow(subflow)); __mptcp_set_timeout(sk, tout); } static inline bool tcp_can_send_ack(const struct sock *ssk) { return !((1 << inet_sk_state_load(ssk)) & (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN)); } void __mptcp_subflow_send_ack(struct sock *ssk) { if (tcp_can_send_ack(ssk)) tcp_send_ack(ssk); } static void mptcp_subflow_send_ack(struct sock *ssk) { bool slow; slow = lock_sock_fast(ssk); __mptcp_subflow_send_ack(ssk); unlock_sock_fast(ssk, slow); } static void mptcp_send_ack(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; mptcp_for_each_subflow(msk, subflow) mptcp_subflow_send_ack(mptcp_subflow_tcp_sock(subflow)); } static void mptcp_subflow_cleanup_rbuf(struct sock *ssk, int copied) { bool slow; slow = lock_sock_fast(ssk); if (tcp_can_send_ack(ssk)) tcp_cleanup_rbuf(ssk, copied); unlock_sock_fast(ssk, slow); } static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty) { const struct inet_connection_sock *icsk = inet_csk(ssk); u8 ack_pending = READ_ONCE(icsk->icsk_ack.pending); const struct tcp_sock *tp = tcp_sk(ssk); return (ack_pending & ICSK_ACK_SCHED) && ((READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->rcv_wup) > READ_ONCE(icsk->icsk_ack.rcv_mss)) || (rx_empty && ack_pending & (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED))); } static void mptcp_cleanup_rbuf(struct mptcp_sock *msk, int copied) { int old_space = READ_ONCE(msk->old_wspace); struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; int space = __mptcp_space(sk); bool cleanup, rx_empty; cleanup = (space > 0) && (space >= (old_space << 1)) && copied; rx_empty = !__mptcp_rmem(sk) && copied; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty)) mptcp_subflow_cleanup_rbuf(ssk, copied); } } static bool mptcp_check_data_fin(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); u64 rcv_data_fin_seq; bool ret = false; /* Need to ack a DATA_FIN received from a peer while this side * of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2. * msk->rcv_data_fin was set when parsing the incoming options * at the subflow level and the msk lock was not held, so this * is the first opportunity to act on the DATA_FIN and change * the msk state. * * If we are caught up to the sequence number of the incoming * DATA_FIN, send the DATA_ACK now and do state transition. If * not caught up, do nothing and let the recv code send DATA_ACK * when catching up. */ if (mptcp_pending_data_fin(sk, &rcv_data_fin_seq)) { WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1); WRITE_ONCE(msk->rcv_data_fin, 0); WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ switch (sk->sk_state) { case TCP_ESTABLISHED: mptcp_set_state(sk, TCP_CLOSE_WAIT); break; case TCP_FIN_WAIT1: mptcp_set_state(sk, TCP_CLOSING); break; case TCP_FIN_WAIT2: mptcp_set_state(sk, TCP_CLOSE); break; default: /* Other states not expected */ WARN_ON_ONCE(1); break; } ret = true; if (!__mptcp_check_fallback(msk)) mptcp_send_ack(msk); mptcp_close_wake_up(sk); } return ret; } static void mptcp_dss_corruption(struct mptcp_sock *msk, struct sock *ssk) { if (READ_ONCE(msk->allow_infinite_fallback)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSCORRUPTIONFALLBACK); mptcp_do_fallback(ssk); } else { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSCORRUPTIONRESET); mptcp_subflow_reset(ssk); } } static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, struct sock *ssk, unsigned int *bytes) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = (struct sock *)msk; unsigned int moved = 0; bool more_data_avail; struct tcp_sock *tp; bool done = false; int sk_rbuf; sk_rbuf = READ_ONCE(sk->sk_rcvbuf); if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { int ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf); if (unlikely(ssk_rbuf > sk_rbuf)) { WRITE_ONCE(sk->sk_rcvbuf, ssk_rbuf); sk_rbuf = ssk_rbuf; } } pr_debug("msk=%p ssk=%p\n", msk, ssk); tp = tcp_sk(ssk); do { u32 map_remaining, offset; u32 seq = tp->copied_seq; struct sk_buff *skb; bool fin; /* try to move as much data as available */ map_remaining = subflow->map_data_len - mptcp_subflow_get_map_offset(subflow); skb = skb_peek(&ssk->sk_receive_queue); if (!skb) { /* With racing move_skbs_to_msk() and __mptcp_move_skbs(), * a different CPU can have already processed the pending * data, stop here or we can enter an infinite loop */ if (!moved) done = true; break; } if (__mptcp_check_fallback(msk)) { /* Under fallback skbs have no MPTCP extension and TCP could * collapse them between the dummy map creation and the * current dequeue. Be sure to adjust the map size. */ map_remaining = skb->len; subflow->map_data_len = skb->len; } offset = seq - TCP_SKB_CB(skb)->seq; fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; if (fin) { done = true; seq++; } if (offset < skb->len) { size_t len = skb->len - offset; if (tp->urg_data) done = true; if (__mptcp_move_skb(msk, ssk, skb, offset, len)) moved += len; seq += len; if (unlikely(map_remaining < len)) { DEBUG_NET_WARN_ON_ONCE(1); mptcp_dss_corruption(msk, ssk); } } else { if (unlikely(!fin)) { DEBUG_NET_WARN_ON_ONCE(1); mptcp_dss_corruption(msk, ssk); } sk_eat_skb(ssk, skb); done = true; } WRITE_ONCE(tp->copied_seq, seq); more_data_avail = mptcp_subflow_data_available(ssk); if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) { done = true; break; } } while (more_data_avail); if (moved > 0) msk->last_data_recv = tcp_jiffies32; *bytes += moved; return done; } static bool __mptcp_ofo_queue(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; struct sk_buff *skb, *tail; bool moved = false; struct rb_node *p; u64 end_seq; p = rb_first(&msk->out_of_order_queue); pr_debug("msk=%p empty=%d\n", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue)); while (p) { skb = rb_to_skb(p); if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) break; p = rb_next(p); rb_erase(&skb->rbnode, &msk->out_of_order_queue); if (unlikely(!after64(MPTCP_SKB_CB(skb)->end_seq, msk->ack_seq))) { mptcp_drop(sk, skb); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); continue; } end_seq = MPTCP_SKB_CB(skb)->end_seq; tail = skb_peek_tail(&sk->sk_receive_queue); if (!tail || !mptcp_ooo_try_coalesce(msk, tail, skb)) { int delta = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq; /* skip overlapping data, if any */ pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d\n", MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq, delta); MPTCP_SKB_CB(skb)->offset += delta; MPTCP_SKB_CB(skb)->map_seq += delta; __skb_queue_tail(&sk->sk_receive_queue, skb); } msk->bytes_received += end_seq - msk->ack_seq; WRITE_ONCE(msk->ack_seq, end_seq); moved = true; } return moved; } static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk) { int err = sock_error(ssk); int ssk_state; if (!err) return false; /* only propagate errors on fallen-back sockets or * on MPC connect */ if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(mptcp_sk(sk))) return false; /* We need to propagate only transition to CLOSE state. * Orphaned socket will see such state change via * subflow_sched_work_if_closed() and that path will properly * destroy the msk as needed. */ ssk_state = inet_sk_state_load(ssk); if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) mptcp_set_state(sk, ssk_state); WRITE_ONCE(sk->sk_err, -err); /* This barrier is coupled with smp_rmb() in mptcp_poll() */ smp_wmb(); sk_error_report(sk); return true; } void __mptcp_error_report(struct sock *sk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); mptcp_for_each_subflow(msk, subflow) if (__mptcp_subflow_error_report(sk, mptcp_subflow_tcp_sock(subflow))) break; } /* In most cases we will be able to lock the mptcp socket. If its already * owned, we need to defer to the work queue to avoid ABBA deadlock. */ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; unsigned int moved = 0; __mptcp_move_skbs_from_subflow(msk, ssk, &moved); __mptcp_ofo_queue(msk); if (unlikely(ssk->sk_err)) { if (!sock_owned_by_user(sk)) __mptcp_error_report(sk); else __set_bit(MPTCP_ERROR_REPORT, &msk->cb_flags); } /* If the moves have caught up with the DATA_FIN sequence number * it's time to ack the DATA_FIN and change socket state, but * this is not a good place to change state. Let the workqueue * do it. */ if (mptcp_pending_data_fin(sk, NULL)) mptcp_schedule_work(sk); return moved > 0; } void mptcp_data_ready(struct sock *sk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(sk); int sk_rbuf, ssk_rbuf; /* The peer can send data while we are shutting down this * subflow at msk destruction time, but we must avoid enqueuing * more data to the msk receive queue */ if (unlikely(subflow->disposable)) return; ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf); sk_rbuf = READ_ONCE(sk->sk_rcvbuf); if (unlikely(ssk_rbuf > sk_rbuf)) sk_rbuf = ssk_rbuf; /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ if (__mptcp_rmem(sk) > sk_rbuf) return; /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk)) sk->sk_data_ready(sk); mptcp_data_unlock(sk); } static void mptcp_subflow_joined(struct mptcp_sock *msk, struct sock *ssk) { mptcp_subflow_ctx(ssk)->map_seq = READ_ONCE(msk->ack_seq); WRITE_ONCE(msk->allow_infinite_fallback, false); mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC); } static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; if (sk->sk_state != TCP_ESTABLISHED) return false; /* attach to msk socket only after we are sure we will deal with it * at close time */ if (sk->sk_socket && !ssk->sk_socket) mptcp_sock_graft(ssk, sk->sk_socket); mptcp_subflow_ctx(ssk)->subflow_id = msk->subflow_id++; mptcp_sockopt_sync_locked(msk, ssk); mptcp_subflow_joined(msk, ssk); mptcp_stop_tout_timer(sk); __mptcp_propagate_sndbuf(sk, ssk); return true; } static void __mptcp_flush_join_list(struct sock *sk, struct list_head *join_list) { struct mptcp_subflow_context *tmp, *subflow; struct mptcp_sock *msk = mptcp_sk(sk); list_for_each_entry_safe(subflow, tmp, join_list, node) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast(ssk); list_move_tail(&subflow->node, &msk->conn_list); if (!__mptcp_finish_join(msk, ssk)) mptcp_subflow_reset(ssk); unlock_sock_fast(ssk, slow); } } static bool mptcp_rtx_timer_pending(struct sock *sk) { return timer_pending(&inet_csk(sk)->icsk_retransmit_timer); } static void mptcp_reset_rtx_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); unsigned long tout; /* prevent rescheduling on close */ if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE)) return; tout = mptcp_sk(sk)->timer_ival; sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + tout); } bool mptcp_schedule_work(struct sock *sk) { if (inet_sk_state_load(sk) != TCP_CLOSE && schedule_work(&mptcp_sk(sk)->work)) { /* each subflow already holds a reference to the sk, and the * workqueue is invoked by a subflow, so sk can't go away here. */ sock_hold(sk); return true; } return false; } static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; msk_owned_by_me(msk); mptcp_for_each_subflow(msk, subflow) { if (READ_ONCE(subflow->data_avail)) return mptcp_subflow_tcp_sock(subflow); } return NULL; } static bool mptcp_skb_can_collapse_to(u64 write_seq, const struct sk_buff *skb, const struct mptcp_ext *mpext) { if (!tcp_skb_can_collapse_to(skb)) return false; /* can collapse only if MPTCP level sequence is in order and this * mapping has not been xmitted yet */ return mpext && mpext->data_seq + mpext->data_len == write_seq && !mpext->frozen; } /* we can append data to the given data frag if: * - there is space available in the backing page_frag * - the data frag tail matches the current page_frag free offset * - the data frag end sequence number matches the current write seq */ static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk, const struct page_frag *pfrag, const struct mptcp_data_frag *df) { return df && pfrag->page == df->page && pfrag->size - pfrag->offset > 0 && pfrag->offset == (df->offset + df->data_len) && df->data_seq + df->data_len == msk->write_seq; } static void dfrag_uncharge(struct sock *sk, int len) { sk_mem_uncharge(sk, len); sk_wmem_queued_add(sk, -len); } static void dfrag_clear(struct sock *sk, struct mptcp_data_frag *dfrag) { int len = dfrag->data_len + dfrag->overhead; list_del(&dfrag->list); dfrag_uncharge(sk, len); put_page(dfrag->page); } /* called under both the msk socket lock and the data lock */ static void __mptcp_clean_una(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_data_frag *dtmp, *dfrag; u64 snd_una; snd_una = msk->snd_una; list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) { if (after64(dfrag->data_seq + dfrag->data_len, snd_una)) break; if (unlikely(dfrag == msk->first_pending)) { /* in recovery mode can see ack after the current snd head */ if (WARN_ON_ONCE(!msk->recovery)) break; WRITE_ONCE(msk->first_pending, mptcp_send_next(sk)); } dfrag_clear(sk, dfrag); } dfrag = mptcp_rtx_head(sk); if (dfrag && after64(snd_una, dfrag->data_seq)) { u64 delta = snd_una - dfrag->data_seq; /* prevent wrap around in recovery mode */ if (unlikely(delta > dfrag->already_sent)) { if (WARN_ON_ONCE(!msk->recovery)) goto out; if (WARN_ON_ONCE(delta > dfrag->data_len)) goto out; dfrag->already_sent += delta - dfrag->already_sent; } dfrag->data_seq += delta; dfrag->offset += delta; dfrag->data_len -= delta; dfrag->already_sent -= delta; dfrag_uncharge(sk, delta); } /* all retransmitted data acked, recovery completed */ if (unlikely(msk->recovery) && after64(msk->snd_una, msk->recovery_snd_nxt)) msk->recovery = false; out: if (snd_una == msk->snd_nxt && snd_una == msk->write_seq) { if (mptcp_rtx_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) mptcp_stop_rtx_timer(sk); } else { mptcp_reset_rtx_timer(sk); } if (mptcp_pending_data_fin_ack(sk)) mptcp_schedule_work(sk); } static void __mptcp_clean_una_wakeup(struct sock *sk) { lockdep_assert_held_once(&sk->sk_lock.slock); __mptcp_clean_una(sk); mptcp_write_space(sk); } static void mptcp_clean_una_wakeup(struct sock *sk) { mptcp_data_lock(sk); __mptcp_clean_una_wakeup(sk); mptcp_data_unlock(sk); } static void mptcp_enter_memory_pressure(struct sock *sk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); bool first = true; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (first) tcp_enter_memory_pressure(ssk); sk_stream_moderate_sndbuf(ssk); first = false; } __mptcp_sync_sndbuf(sk); } /* ensure we get enough memory for the frag hdr, beyond some minimal amount of * data */ static bool mptcp_page_frag_refill(struct sock *sk, struct page_frag *pfrag) { if (likely(skb_page_frag_refill(32U + sizeof(struct mptcp_data_frag), pfrag, sk->sk_allocation))) return true; mptcp_enter_memory_pressure(sk); return false; } static struct mptcp_data_frag * mptcp_carve_data_frag(const struct mptcp_sock *msk, struct page_frag *pfrag, int orig_offset) { int offset = ALIGN(orig_offset, sizeof(long)); struct mptcp_data_frag *dfrag; dfrag = (struct mptcp_data_frag *)(page_to_virt(pfrag->page) + offset); dfrag->data_len = 0; dfrag->data_seq = msk->write_seq; dfrag->overhead = offset - orig_offset + sizeof(struct mptcp_data_frag); dfrag->offset = offset + sizeof(struct mptcp_data_frag); dfrag->already_sent = 0; dfrag->page = pfrag->page; return dfrag; } struct mptcp_sendmsg_info { int mss_now; int size_goal; u16 limit; u16 sent; unsigned int flags; bool data_lock_held; }; static int mptcp_check_allowed_size(const struct mptcp_sock *msk, struct sock *ssk, u64 data_seq, int avail_size) { u64 window_end = mptcp_wnd_end(msk); u64 mptcp_snd_wnd; if (__mptcp_check_fallback(msk)) return avail_size; mptcp_snd_wnd = window_end - data_seq; avail_size = min_t(unsigned int, mptcp_snd_wnd, avail_size); if (unlikely(tcp_sk(ssk)->snd_wnd < mptcp_snd_wnd)) { tcp_sk(ssk)->snd_wnd = min_t(u64, U32_MAX, mptcp_snd_wnd); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_SNDWNDSHARED); } return avail_size; } static bool __mptcp_add_ext(struct sk_buff *skb, gfp_t gfp) { struct skb_ext *mpext = __skb_ext_alloc(gfp); if (!mpext) return false; __skb_ext_set(skb, SKB_EXT_MPTCP, mpext); return true; } static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp) { struct sk_buff *skb; skb = alloc_skb_fclone(MAX_TCP_HEADER, gfp); if (likely(skb)) { if (likely(__mptcp_add_ext(skb, gfp))) { skb_reserve(skb, MAX_TCP_HEADER); skb->ip_summed = CHECKSUM_PARTIAL; INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); return skb; } __kfree_skb(skb); } else { mptcp_enter_memory_pressure(sk); } return NULL; } static struct sk_buff *__mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp) { struct sk_buff *skb; skb = __mptcp_do_alloc_tx_skb(sk, gfp); if (!skb) return NULL; if (likely(sk_wmem_schedule(ssk, skb->truesize))) { tcp_skb_entail(ssk, skb); return skb; } tcp_skb_tsorted_anchor_cleanup(skb); kfree_skb(skb); return NULL; } static struct sk_buff *mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, bool data_lock_held) { gfp_t gfp = data_lock_held ? GFP_ATOMIC : sk->sk_allocation; return __mptcp_alloc_tx_skb(sk, ssk, gfp); } /* note: this always recompute the csum on the whole skb, even * if we just appended a single frag. More status info needed */ static void mptcp_update_data_checksum(struct sk_buff *skb, int added) { struct mptcp_ext *mpext = mptcp_get_ext(skb); __wsum csum = ~csum_unfold(mpext->csum); int offset = skb->len - added; mpext->csum = csum_fold(csum_block_add(csum, skb_checksum(skb, offset, added, 0), offset)); } static void mptcp_update_infinite_map(struct mptcp_sock *msk, struct sock *ssk, struct mptcp_ext *mpext) { if (!mpext) return; mpext->infinite_map = 1; mpext->data_len = 0; MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPTX); mptcp_subflow_ctx(ssk)->send_infinite_map = 0; pr_fallback(msk); mptcp_do_fallback(ssk); } #define MPTCP_MAX_GSO_SIZE (GSO_LEGACY_MAX_SIZE - (MAX_TCP_HEADER + 1)) static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, struct mptcp_data_frag *dfrag, struct mptcp_sendmsg_info *info) { u64 data_seq = dfrag->data_seq + info->sent; int offset = dfrag->offset + info->sent; struct mptcp_sock *msk = mptcp_sk(sk); bool zero_window_probe = false; struct mptcp_ext *mpext = NULL; bool can_coalesce = false; bool reuse_skb = true; struct sk_buff *skb; size_t copy; int i; pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u\n", msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent); if (WARN_ON_ONCE(info->sent > info->limit || info->limit > dfrag->data_len)) return 0; if (unlikely(!__tcp_can_send(ssk))) return -EAGAIN; /* compute send limit */ if (unlikely(ssk->sk_gso_max_size > MPTCP_MAX_GSO_SIZE)) ssk->sk_gso_max_size = MPTCP_MAX_GSO_SIZE; info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags); copy = info->size_goal; skb = tcp_write_queue_tail(ssk); if (skb && copy > skb->len) { /* Limit the write to the size available in the * current skb, if any, so that we create at most a new skb. * Explicitly tells TCP internals to avoid collapsing on later * queue management operation, to avoid breaking the ext <-> * SSN association set here */ mpext = mptcp_get_ext(skb); if (!mptcp_skb_can_collapse_to(data_seq, skb, mpext)) { TCP_SKB_CB(skb)->eor = 1; tcp_mark_push(tcp_sk(ssk), skb); goto alloc_skb; } i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, dfrag->page, offset); if (!can_coalesce && i >= READ_ONCE(net_hotdata.sysctl_max_skb_frags)) { tcp_mark_push(tcp_sk(ssk), skb); goto alloc_skb; } copy -= skb->len; } else { alloc_skb: skb = mptcp_alloc_tx_skb(sk, ssk, info->data_lock_held); if (!skb) return -ENOMEM; i = skb_shinfo(skb)->nr_frags; reuse_skb = false; mpext = mptcp_get_ext(skb); } /* Zero window and all data acked? Probe. */ copy = mptcp_check_allowed_size(msk, ssk, data_seq, copy); if (copy == 0) { u64 snd_una = READ_ONCE(msk->snd_una); if (snd_una != msk->snd_nxt || tcp_write_queue_tail(ssk)) { tcp_remove_empty_skb(ssk); return 0; } zero_window_probe = true; data_seq = snd_una - 1; copy = 1; } copy = min_t(size_t, copy, info->limit - info->sent); if (!sk_wmem_schedule(ssk, copy)) { tcp_remove_empty_skb(ssk); return -ENOMEM; } if (can_coalesce) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { get_page(dfrag->page); skb_fill_page_desc(skb, i, dfrag->page, offset, copy); } skb->len += copy; skb->data_len += copy; skb->truesize += copy; sk_wmem_queued_add(ssk, copy); sk_mem_charge(ssk, copy); WRITE_ONCE(tcp_sk(ssk)->write_seq, tcp_sk(ssk)->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); /* on skb reuse we just need to update the DSS len */ if (reuse_skb) { TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; mpext->data_len += copy; goto out; } memset(mpext, 0, sizeof(*mpext)); mpext->data_seq = data_seq; mpext->subflow_seq = mptcp_subflow_ctx(ssk)->rel_write_seq; mpext->data_len = copy; mpext->use_map = 1; mpext->dsn64 = 1; pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d\n", mpext->data_seq, mpext->subflow_seq, mpext->data_len, mpext->dsn64); if (zero_window_probe) { mptcp_subflow_ctx(ssk)->rel_write_seq += copy; mpext->frozen = 1; if (READ_ONCE(msk->csum_enabled)) mptcp_update_data_checksum(skb, copy); tcp_push_pending_frames(ssk); return 0; } out: if (READ_ONCE(msk->csum_enabled)) mptcp_update_data_checksum(skb, copy); if (mptcp_subflow_ctx(ssk)->send_infinite_map) mptcp_update_infinite_map(msk, ssk, mpext); trace_mptcp_sendmsg_frag(mpext); mptcp_subflow_ctx(ssk)->rel_write_seq += copy; return copy; } #define MPTCP_SEND_BURST_SIZE ((1 << 16) - \ sizeof(struct tcphdr) - \ MAX_TCP_OPTION_SPACE - \ sizeof(struct ipv6hdr) - \ sizeof(struct frag_hdr)) struct subflow_send_info { struct sock *ssk; u64 linger_time; }; void mptcp_subflow_set_active(struct mptcp_subflow_context *subflow) { if (!subflow->stale) return; subflow->stale = 0; MPTCP_INC_STATS(sock_net(mptcp_subflow_tcp_sock(subflow)), MPTCP_MIB_SUBFLOWRECOVER); } bool mptcp_subflow_active(struct mptcp_subflow_context *subflow) { if (unlikely(subflow->stale)) { u32 rcv_tstamp = READ_ONCE(tcp_sk(mptcp_subflow_tcp_sock(subflow))->rcv_tstamp); if (subflow->stale_rcv_tstamp == rcv_tstamp) return false; mptcp_subflow_set_active(subflow); } return __mptcp_subflow_active(subflow); } #define SSK_MODE_ACTIVE 0 #define SSK_MODE_BACKUP 1 #define SSK_MODE_MAX 2 /* implement the mptcp packet scheduler; * returns the subflow that will transmit the next DSS * additionally updates the rtx timeout */ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) { struct subflow_send_info send_info[SSK_MODE_MAX]; struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; u32 pace, burst, wmem; int i, nr_active = 0; struct sock *ssk; u64 linger_time; long tout = 0; /* pick the subflow with the lower wmem/wspace ratio */ for (i = 0; i < SSK_MODE_MAX; ++i) { send_info[i].ssk = NULL; send_info[i].linger_time = -1; } mptcp_for_each_subflow(msk, subflow) { bool backup = subflow->backup || subflow->request_bkup; trace_mptcp_subflow_get_send(subflow); ssk = mptcp_subflow_tcp_sock(subflow); if (!mptcp_subflow_active(subflow)) continue; tout = max(tout, mptcp_timeout_from_subflow(subflow)); nr_active += !backup; pace = subflow->avg_pacing_rate; if (unlikely(!pace)) { /* init pacing rate from socket */ subflow->avg_pacing_rate = READ_ONCE(ssk->sk_pacing_rate); pace = subflow->avg_pacing_rate; if (!pace) continue; } linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace); if (linger_time < send_info[backup].linger_time) { send_info[backup].ssk = ssk; send_info[backup].linger_time = linger_time; } } __mptcp_set_timeout(sk, tout); /* pick the best backup if no other subflow is active */ if (!nr_active) send_info[SSK_MODE_ACTIVE].ssk = send_info[SSK_MODE_BACKUP].ssk; /* According to the blest algorithm, to avoid HoL blocking for the * faster flow, we need to: * - estimate the faster flow linger time * - use the above to estimate the amount of byte transferred * by the faster flow * - check that the amount of queued data is greter than the above, * otherwise do not use the picked, slower, subflow * We select the subflow with the shorter estimated time to flush * the queued mem, which basically ensure the above. We just need * to check that subflow has a non empty cwin. */ ssk = send_info[SSK_MODE_ACTIVE].ssk; if (!ssk || !sk_stream_memory_free(ssk)) return NULL; burst = min_t(int, MPTCP_SEND_BURST_SIZE, mptcp_wnd_end(msk) - msk->snd_nxt); wmem = READ_ONCE(ssk->sk_wmem_queued); if (!burst) return ssk; subflow = mptcp_subflow_ctx(ssk); subflow->avg_pacing_rate = div_u64((u64)subflow->avg_pacing_rate * wmem + READ_ONCE(ssk->sk_pacing_rate) * burst, burst + wmem); msk->snd_burst = burst; return ssk; } static void mptcp_push_release(struct sock *ssk, struct mptcp_sendmsg_info *info) { tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle, info->size_goal); release_sock(ssk); } static void mptcp_update_post_push(struct mptcp_sock *msk, struct mptcp_data_frag *dfrag, u32 sent) { u64 snd_nxt_new = dfrag->data_seq; dfrag->already_sent += sent; msk->snd_burst -= sent; snd_nxt_new += dfrag->already_sent; /* snd_nxt_new can be smaller than snd_nxt in case mptcp * is recovering after a failover. In that event, this re-sends * old segments. * * Thus compute snd_nxt_new candidate based on * the dfrag->data_seq that was sent and the data * that has been handed to the subflow for transmission * and skip update in case it was old dfrag. */ if (likely(after64(snd_nxt_new, msk->snd_nxt))) { msk->bytes_sent += snd_nxt_new - msk->snd_nxt; WRITE_ONCE(msk->snd_nxt, snd_nxt_new); } } void mptcp_check_and_set_pending(struct sock *sk) { if (mptcp_send_head(sk)) { mptcp_data_lock(sk); mptcp_sk(sk)->cb_flags |= BIT(MPTCP_PUSH_PENDING); mptcp_data_unlock(sk); } } static int __subflow_push_pending(struct sock *sk, struct sock *ssk, struct mptcp_sendmsg_info *info) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_data_frag *dfrag; int len, copied = 0, err = 0; while ((dfrag = mptcp_send_head(sk))) { info->sent = dfrag->already_sent; info->limit = dfrag->data_len; len = dfrag->data_len - dfrag->already_sent; while (len > 0) { int ret = 0; ret = mptcp_sendmsg_frag(sk, ssk, dfrag, info); if (ret <= 0) { err = copied ? : ret; goto out; } info->sent += ret; copied += ret; len -= ret; mptcp_update_post_push(msk, dfrag, ret); } WRITE_ONCE(msk->first_pending, mptcp_send_next(sk)); if (msk->snd_burst <= 0 || !sk_stream_memory_free(ssk) || !mptcp_subflow_active(mptcp_subflow_ctx(ssk))) { err = copied; goto out; } mptcp_set_timeout(sk); } err = copied; out: if (err > 0) msk->last_data_sent = tcp_jiffies32; return err; } void __mptcp_push_pending(struct sock *sk, unsigned int flags) { struct sock *prev_ssk = NULL, *ssk = NULL; struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_sendmsg_info info = { .flags = flags, }; bool do_check_data_fin = false; int push_count = 1; while (mptcp_send_head(sk) && (push_count > 0)) { struct mptcp_subflow_context *subflow; int ret = 0; if (mptcp_sched_get_send(msk)) break; push_count = 0; mptcp_for_each_subflow(msk, subflow) { if (READ_ONCE(subflow->scheduled)) { mptcp_subflow_set_scheduled(subflow, false); prev_ssk = ssk; ssk = mptcp_subflow_tcp_sock(subflow); if (ssk != prev_ssk) { /* First check. If the ssk has changed since * the last round, release prev_ssk */ if (prev_ssk) mptcp_push_release(prev_ssk, &info); /* Need to lock the new subflow only if different * from the previous one, otherwise we are still * helding the relevant lock */ lock_sock(ssk); } push_count++; ret = __subflow_push_pending(sk, ssk, &info); if (ret <= 0) { if (ret != -EAGAIN || (1 << ssk->sk_state) & (TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSE)) push_count--; continue; } do_check_data_fin = true; } } } /* at this point we held the socket lock for the last subflow we used */ if (ssk) mptcp_push_release(ssk, &info); /* ensure the rtx timer is running */ if (!mptcp_rtx_timer_pending(sk)) mptcp_reset_rtx_timer(sk); if (do_check_data_fin) mptcp_check_send_data_fin(sk); } static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_sendmsg_info info = { .data_lock_held = true, }; bool keep_pushing = true; struct sock *xmit_ssk; int copied = 0; info.flags = 0; while (mptcp_send_head(sk) && keep_pushing) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); int ret = 0; /* check for a different subflow usage only after * spooling the first chunk of data */ if (first) { mptcp_subflow_set_scheduled(subflow, false); ret = __subflow_push_pending(sk, ssk, &info); first = false; if (ret <= 0) break; copied += ret; continue; } if (mptcp_sched_get_send(msk)) goto out; if (READ_ONCE(subflow->scheduled)) { mptcp_subflow_set_scheduled(subflow, false); ret = __subflow_push_pending(sk, ssk, &info); if (ret <= 0) keep_pushing = false; copied += ret; } mptcp_for_each_subflow(msk, subflow) { if (READ_ONCE(subflow->scheduled)) { xmit_ssk = mptcp_subflow_tcp_sock(subflow); if (xmit_ssk != ssk) { mptcp_subflow_delegate(subflow, MPTCP_DELEGATE_SEND); keep_pushing = false; } } } } out: /* __mptcp_alloc_tx_skb could have released some wmem and we are * not going to flush it via release_sock() */ if (copied) { tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); if (!mptcp_rtx_timer_pending(sk)) mptcp_reset_rtx_timer(sk); if (msk->snd_data_fin_enable && msk->snd_nxt + 1 == msk->write_seq) mptcp_schedule_work(sk); } } static int mptcp_disconnect(struct sock *sk, int flags); static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, size_t len, int *copied_syn) { unsigned int saved_flags = msg->msg_flags; struct mptcp_sock *msk = mptcp_sk(sk); struct sock *ssk; int ret; /* on flags based fastopen the mptcp is supposed to create the * first subflow right now. Otherwise we are in the defer_connect * path, and the first subflow must be already present. * Since the defer_connect flag is cleared after the first succsful * fastopen attempt, no need to check for additional subflow status. */ if (msg->msg_flags & MSG_FASTOPEN) { ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) return PTR_ERR(ssk); } if (!msk->first) return -EINVAL; ssk = msk->first; lock_sock(ssk); msg->msg_flags |= MSG_DONTWAIT; msk->fastopening = 1; ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL); msk->fastopening = 0; msg->msg_flags = saved_flags; release_sock(ssk); /* do the blocking bits of inet_stream_connect outside the ssk socket lock */ if (ret == -EINPROGRESS && !(msg->msg_flags & MSG_DONTWAIT)) { ret = __inet_stream_connect(sk->sk_socket, msg->msg_name, msg->msg_namelen, msg->msg_flags, 1); /* Keep the same behaviour of plain TCP: zero the copied bytes in * case of any error, except timeout or signal */ if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR) *copied_syn = 0; } else if (ret && ret != -EINPROGRESS) { /* The disconnect() op called by tcp_sendmsg_fastopen()/ * __inet_stream_connect() can fail, due to looking check, * see mptcp_disconnect(). * Attempt it again outside the problematic scope. */ if (!mptcp_disconnect(sk, 0)) sk->sk_socket->state = SS_UNCONNECTED; } inet_clear_bit(DEFER_CONNECT, sk); return ret; } static int do_copy_data_nocache(struct sock *sk, int copy, struct iov_iter *from, char *to) { if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) { if (!copy_from_iter_full_nocache(to, copy, from)) return -EFAULT; } else if (!copy_from_iter_full(to, copy, from)) { return -EFAULT; } return 0; } /* open-code sk_stream_memory_free() plus sent limit computation to * avoid indirect calls in fast-path. * Called under the msk socket lock, so we can avoid a bunch of ONCE * annotations. */ static u32 mptcp_send_limit(const struct sock *sk) { const struct mptcp_sock *msk = mptcp_sk(sk); u32 limit, not_sent; if (sk->sk_wmem_queued >= READ_ONCE(sk->sk_sndbuf)) return 0; limit = mptcp_notsent_lowat(sk); if (limit == UINT_MAX) return UINT_MAX; not_sent = msk->write_seq - msk->snd_nxt; if (not_sent >= limit) return 0; return limit - not_sent; } static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct mptcp_sock *msk = mptcp_sk(sk); struct page_frag *pfrag; size_t copied = 0; int ret = 0; long timeo; /* silently ignore everything else */ msg->msg_flags &= MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_FASTOPEN; lock_sock(sk); if (unlikely(inet_test_bit(DEFER_CONNECT, sk) || msg->msg_flags & MSG_FASTOPEN)) { int copied_syn = 0; ret = mptcp_sendmsg_fastopen(sk, msg, len, &copied_syn); copied += copied_syn; if (ret == -EINPROGRESS && copied_syn > 0) goto out; else if (ret) goto do_error; } timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) { ret = sk_stream_wait_connect(sk, &timeo); if (ret) goto do_error; } ret = -EPIPE; if (unlikely(sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))) goto do_error; pfrag = sk_page_frag(sk); while (msg_data_left(msg)) { int total_ts, frag_truesize = 0; struct mptcp_data_frag *dfrag; bool dfrag_collapsed; size_t psize, offset; u32 copy_limit; /* ensure fitting the notsent_lowat() constraint */ copy_limit = mptcp_send_limit(sk); if (!copy_limit) goto wait_for_memory; /* reuse tail pfrag, if possible, or carve a new one from the * page allocator */ dfrag = mptcp_pending_tail(sk); dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag); if (!dfrag_collapsed) { if (!mptcp_page_frag_refill(sk, pfrag)) goto wait_for_memory; dfrag = mptcp_carve_data_frag(msk, pfrag, pfrag->offset); frag_truesize = dfrag->overhead; } /* we do not bound vs wspace, to allow a single packet. * memory accounting will prevent execessive memory usage * anyway */ offset = dfrag->offset + dfrag->data_len; psize = pfrag->size - offset; psize = min_t(size_t, psize, msg_data_left(msg)); psize = min_t(size_t, psize, copy_limit); total_ts = psize + frag_truesize; if (!sk_wmem_schedule(sk, total_ts)) goto wait_for_memory; ret = do_copy_data_nocache(sk, psize, &msg->msg_iter, page_address(dfrag->page) + offset); if (ret) goto do_error; /* data successfully copied into the write queue */ sk_forward_alloc_add(sk, -total_ts); copied += psize; dfrag->data_len += psize; frag_truesize += psize; pfrag->offset += frag_truesize; WRITE_ONCE(msk->write_seq, msk->write_seq + psize); /* charge data on mptcp pending queue to the msk socket * Note: we charge such data both to sk and ssk */ sk_wmem_queued_add(sk, frag_truesize); if (!dfrag_collapsed) { get_page(dfrag->page); list_add_tail(&dfrag->list, &msk->rtx_queue); if (!msk->first_pending) WRITE_ONCE(msk->first_pending, dfrag); } pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d\n", msk, dfrag->data_seq, dfrag->data_len, dfrag->already_sent, !dfrag_collapsed); continue; wait_for_memory: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); __mptcp_push_pending(sk, msg->msg_flags); ret = sk_stream_wait_memory(sk, &timeo); if (ret) goto do_error; } if (copied) __mptcp_push_pending(sk, msg->msg_flags); out: release_sock(sk); return copied; do_error: if (copied) goto out; copied = sk_stream_error(sk, msg->msg_flags, ret); goto out; } static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied); static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, struct msghdr *msg, size_t len, int flags, struct scm_timestamping_internal *tss, int *cmsg_flags) { struct sk_buff *skb, *tmp; int copied = 0; skb_queue_walk_safe(&msk->receive_queue, skb, tmp) { u32 offset = MPTCP_SKB_CB(skb)->offset; u32 data_len = skb->len - offset; u32 count = min_t(size_t, len - copied, data_len); int err; if (!(flags & MSG_TRUNC)) { err = skb_copy_datagram_msg(skb, offset, msg, count); if (unlikely(err < 0)) { if (!copied) return err; break; } } if (MPTCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); *cmsg_flags |= MPTCP_CMSG_TS; } copied += count; if (count < data_len) { if (!(flags & MSG_PEEK)) { MPTCP_SKB_CB(skb)->offset += count; MPTCP_SKB_CB(skb)->map_seq += count; msk->bytes_consumed += count; } break; } if (!(flags & MSG_PEEK)) { /* we will bulk release the skb memory later */ skb->destructor = NULL; WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize); __skb_unlink(skb, &msk->receive_queue); __kfree_skb(skb); msk->bytes_consumed += count; } if (copied >= len) break; } mptcp_rcv_space_adjust(msk, copied); return copied; } /* receive buffer autotuning. See tcp_rcv_space_adjust for more information. * * Only difference: Use highest rtt estimate of the subflows in use. */ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; u8 scaling_ratio = U8_MAX; u32 time, advmss = 1; u64 rtt_us, mstamp; msk_owned_by_me(msk); if (copied <= 0) return; if (!msk->rcvspace_init) mptcp_rcv_space_init(msk, msk->first); msk->rcvq_space.copied += copied; mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC); time = tcp_stamp_us_delta(mstamp, msk->rcvq_space.time); rtt_us = msk->rcvq_space.rtt_us; if (rtt_us && time < (rtt_us >> 3)) return; rtt_us = 0; mptcp_for_each_subflow(msk, subflow) { const struct tcp_sock *tp; u64 sf_rtt_us; u32 sf_advmss; tp = tcp_sk(mptcp_subflow_tcp_sock(subflow)); sf_rtt_us = READ_ONCE(tp->rcv_rtt_est.rtt_us); sf_advmss = READ_ONCE(tp->advmss); rtt_us = max(sf_rtt_us, rtt_us); advmss = max(sf_advmss, advmss); scaling_ratio = min(tp->scaling_ratio, scaling_ratio); } msk->rcvq_space.rtt_us = rtt_us; msk->scaling_ratio = scaling_ratio; if (time < (rtt_us >> 3) || rtt_us == 0) return; if (msk->rcvq_space.copied <= msk->rcvq_space.space) goto new_measure; if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { u64 rcvwin, grow; int rcvbuf; rcvwin = ((u64)msk->rcvq_space.copied << 1) + 16 * advmss; grow = rcvwin * (msk->rcvq_space.copied - msk->rcvq_space.space); do_div(grow, msk->rcvq_space.space); rcvwin += (grow << 1); rcvbuf = min_t(u64, mptcp_space_from_win(sk, rcvwin), READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); if (rcvbuf > sk->sk_rcvbuf) { u32 window_clamp; window_clamp = mptcp_win_from_space(sk, rcvbuf); WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); /* Make subflows follow along. If we do not do this, we * get drops at subflow level if skbs can't be moved to * the mptcp rx queue fast enough (announced rcv_win can * exceed ssk->sk_rcvbuf). */ mptcp_for_each_subflow(msk, subflow) { struct sock *ssk; bool slow; ssk = mptcp_subflow_tcp_sock(subflow); slow = lock_sock_fast(ssk); WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf); WRITE_ONCE(tcp_sk(ssk)->window_clamp, window_clamp); if (tcp_can_send_ack(ssk)) tcp_cleanup_rbuf(ssk, 1); unlock_sock_fast(ssk, slow); } } } msk->rcvq_space.space = msk->rcvq_space.copied; new_measure: msk->rcvq_space.copied = 0; msk->rcvq_space.time = mstamp; } static void __mptcp_update_rmem(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); if (!msk->rmem_released) return; atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc); mptcp_rmem_uncharge(sk, msk->rmem_released); WRITE_ONCE(msk->rmem_released, 0); } static void __mptcp_splice_receive_queue(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); skb_queue_splice_tail_init(&sk->sk_receive_queue, &msk->receive_queue); } static bool __mptcp_move_skbs(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; unsigned int moved = 0; bool ret, done; do { struct sock *ssk = mptcp_subflow_recv_lookup(msk); bool slowpath; /* we can have data pending in the subflows only if the msk * receive buffer was full at subflow_data_ready() time, * that is an unlikely slow path. */ if (likely(!ssk)) break; slowpath = lock_sock_fast(ssk); mptcp_data_lock(sk); __mptcp_update_rmem(sk); done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); mptcp_data_unlock(sk); if (unlikely(ssk->sk_err)) __mptcp_error_report(sk); unlock_sock_fast(ssk, slowpath); } while (!done); /* acquire the data lock only if some input data is pending */ ret = moved > 0; if (!RB_EMPTY_ROOT(&msk->out_of_order_queue) || !skb_queue_empty_lockless(&sk->sk_receive_queue)) { mptcp_data_lock(sk); __mptcp_update_rmem(sk); ret |= __mptcp_ofo_queue(msk); __mptcp_splice_receive_queue(sk); mptcp_data_unlock(sk); } if (ret) mptcp_check_data_fin((struct sock *)msk); return !skb_queue_empty(&msk->receive_queue); } static unsigned int mptcp_inq_hint(const struct sock *sk) { const struct mptcp_sock *msk = mptcp_sk(sk); const struct sk_buff *skb; skb = skb_peek(&msk->receive_queue); if (skb) { u64 hint_val = READ_ONCE(msk->ack_seq) - MPTCP_SKB_CB(skb)->map_seq; if (hint_val >= INT_MAX) return INT_MAX; return (unsigned int)hint_val; } if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN)) return 1; return 0; } static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct mptcp_sock *msk = mptcp_sk(sk); struct scm_timestamping_internal tss; int copied = 0, cmsg_flags = 0; int target; long timeo; /* MSG_ERRQUEUE is really a no-op till we support IP_RECVERR */ if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); lock_sock(sk); if (unlikely(sk->sk_state == TCP_LISTEN)) { copied = -ENOTCONN; goto out_err; } timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); len = min_t(size_t, len, INT_MAX); target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); if (unlikely(msk->recvmsg_inq)) cmsg_flags = MPTCP_CMSG_INQ; while (copied < len) { int err, bytes_read; bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags, &tss, &cmsg_flags); if (unlikely(bytes_read < 0)) { if (!copied) copied = bytes_read; goto out_err; } copied += bytes_read; if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk)) continue; /* only the MPTCP socket status is relevant here. The exit * conditions mirror closely tcp_recvmsg() */ if (copied >= target) break; if (copied) { if (sk->sk_err || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || !timeo || signal_pending(current)) break; } else { if (sk->sk_err) { copied = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) { /* race breaker: the shutdown could be after the * previous receive queue check */ if (__mptcp_move_skbs(msk)) continue; break; } if (sk->sk_state == TCP_CLOSE) { copied = -ENOTCONN; break; } if (!timeo) { copied = -EAGAIN; break; } if (signal_pending(current)) { copied = sock_intr_errno(timeo); break; } } pr_debug("block timeout %ld\n", timeo); mptcp_cleanup_rbuf(msk, copied); err = sk_wait_data(sk, &timeo, NULL); if (err < 0) { err = copied ? : err; goto out_err; } } mptcp_cleanup_rbuf(msk, copied); out_err: if (cmsg_flags && copied >= 0) { if (cmsg_flags & MPTCP_CMSG_TS) tcp_recv_timestamp(msg, sk, &tss); if (cmsg_flags & MPTCP_CMSG_INQ) { unsigned int inq = mptcp_inq_hint(sk); put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq); } } pr_debug("msk=%p rx queue empty=%d:%d copied=%d\n", msk, skb_queue_empty_lockless(&sk->sk_receive_queue), skb_queue_empty(&msk->receive_queue), copied); release_sock(sk); return copied; } static void mptcp_retransmit_timer(struct timer_list *t) { struct inet_connection_sock *icsk = from_timer(icsk, t, icsk_retransmit_timer); struct sock *sk = &icsk->icsk_inet.sk; struct mptcp_sock *msk = mptcp_sk(sk); bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { /* we need a process context to retransmit */ if (!test_and_set_bit(MPTCP_WORK_RTX, &msk->flags)) mptcp_schedule_work(sk); } else { /* delegate our work to tcp_release_cb() */ __set_bit(MPTCP_RETRANSMIT, &msk->cb_flags); } bh_unlock_sock(sk); sock_put(sk); } static void mptcp_tout_timer(struct timer_list *t) { struct sock *sk = from_timer(sk, t, sk_timer); mptcp_schedule_work(sk); sock_put(sk); } /* Find an idle subflow. Return NULL if there is unacked data at tcp * level. * * A backup subflow is returned only if that is the only kind available. */ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk) { struct sock *backup = NULL, *pick = NULL; struct mptcp_subflow_context *subflow; int min_stale_count = INT_MAX; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (!__mptcp_subflow_active(subflow)) continue; /* still data outstanding at TCP level? skip this */ if (!tcp_rtx_and_write_queues_empty(ssk)) { mptcp_pm_subflow_chk_stale(msk, ssk); min_stale_count = min_t(int, min_stale_count, subflow->stale_count); continue; } if (subflow->backup || subflow->request_bkup) { if (!backup) backup = ssk; continue; } if (!pick) pick = ssk; } if (pick) return pick; /* use backup only if there are no progresses anywhere */ return min_stale_count > 1 ? backup : NULL; } bool __mptcp_retransmit_pending_data(struct sock *sk) { struct mptcp_data_frag *cur, *rtx_head; struct mptcp_sock *msk = mptcp_sk(sk); if (__mptcp_check_fallback(msk)) return false; /* the closing socket has some data untransmitted and/or unacked: * some data in the mptcp rtx queue has not really xmitted yet. * keep it simple and re-inject the whole mptcp level rtx queue */ mptcp_data_lock(sk); __mptcp_clean_una_wakeup(sk); rtx_head = mptcp_rtx_head(sk); if (!rtx_head) { mptcp_data_unlock(sk); return false; } msk->recovery_snd_nxt = msk->snd_nxt; msk->recovery = true; mptcp_data_unlock(sk); msk->first_pending = rtx_head; msk->snd_burst = 0; /* be sure to clear the "sent status" on all re-injected fragments */ list_for_each_entry(cur, &msk->rtx_queue, list) { if (!cur->already_sent) break; cur->already_sent = 0; } return true; } /* flags for __mptcp_close_ssk() */ #define MPTCP_CF_PUSH BIT(1) #define MPTCP_CF_FASTCLOSE BIT(2) /* be sure to send a reset only if the caller asked for it, also * clean completely the subflow status when the subflow reaches * TCP_CLOSE state */ static void __mptcp_subflow_disconnect(struct sock *ssk, struct mptcp_subflow_context *subflow, unsigned int flags) { if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || (flags & MPTCP_CF_FASTCLOSE)) { /* The MPTCP code never wait on the subflow sockets, TCP-level * disconnect should never fail */ WARN_ON_ONCE(tcp_disconnect(ssk, 0)); mptcp_subflow_ctx_reset(subflow); } else { tcp_shutdown(ssk, SEND_SHUTDOWN); } } /* subflow sockets can be either outgoing (connect) or incoming * (accept). * * Outgoing subflows use in-kernel sockets. * Incoming subflows do not have their own 'struct socket' allocated, * so we need to use tcp_close() after detaching them from the mptcp * parent socket. */ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow, unsigned int flags) { struct mptcp_sock *msk = mptcp_sk(sk); bool dispose_it, need_push = false; /* If the first subflow moved to a close state before accept, e.g. due * to an incoming reset or listener shutdown, the subflow socket is * already deleted by inet_child_forget() and the mptcp socket can't * survive too. */ if (msk->in_accept_queue && msk->first == ssk && (sock_flag(sk, SOCK_DEAD) || sock_flag(ssk, SOCK_DEAD))) { /* ensure later check in mptcp_worker() will dispose the msk */ sock_set_flag(sk, SOCK_DEAD); mptcp_set_close_tout(sk, tcp_jiffies32 - (mptcp_close_timeout(sk) + 1)); lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); mptcp_subflow_drop_ctx(ssk); goto out_release; } dispose_it = msk->free_first || ssk != msk->first; if (dispose_it) list_del(&subflow->node); lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { /* be sure to force the tcp_close path * to generate the egress reset */ ssk->sk_lingertime = 0; sock_set_flag(ssk, SOCK_LINGER); subflow->send_fastclose = 1; } need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { __mptcp_subflow_disconnect(ssk, subflow, flags); release_sock(ssk); goto out; } subflow->disposable = 1; /* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops * the ssk has been already destroyed, we just need to release the * reference owned by msk; */ if (!inet_csk(ssk)->icsk_ulp_ops) { WARN_ON_ONCE(!sock_flag(ssk, SOCK_DEAD)); kfree_rcu(subflow, rcu); } else { /* otherwise tcp will dispose of the ssk and subflow ctx */ __tcp_close(ssk, 0); /* close acquired an extra ref */ __sock_put(ssk); } out_release: __mptcp_subflow_error_report(sk, ssk); release_sock(ssk); sock_put(ssk); if (ssk == msk->first) WRITE_ONCE(msk->first, NULL); out: __mptcp_sync_sndbuf(sk); if (need_push) __mptcp_push_pending(sk, 0); /* Catch every 'all subflows closed' scenario, including peers silently * closing them, e.g. due to timeout. * For established sockets, allow an additional timeout before closing, * as the protocol can still create more subflows. */ if (list_is_singular(&msk->conn_list) && msk->first && inet_sk_state_load(msk->first) == TCP_CLOSE) { if (sk->sk_state != TCP_ESTABLISHED || msk->in_accept_queue || sock_flag(sk, SOCK_DEAD)) { mptcp_set_state(sk, TCP_CLOSE); mptcp_close_wake_up(sk); } else { mptcp_start_tout_timer(sk); } } } void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow) { /* The first subflow can already be closed and still in the list */ if (subflow->close_event_done) return; subflow->close_event_done = true; if (sk->sk_state == TCP_ESTABLISHED) mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL); /* subflow aborted before reaching the fully_established status * attempt the creation of the next subflow */ mptcp_pm_subflow_check_next(mptcp_sk(sk), subflow); __mptcp_close_ssk(sk, ssk, subflow, MPTCP_CF_PUSH); } static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu) { return 0; } static void __mptcp_close_subflow(struct sock *sk) { struct mptcp_subflow_context *subflow, *tmp; struct mptcp_sock *msk = mptcp_sk(sk); might_sleep(); mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); int ssk_state = inet_sk_state_load(ssk); if (ssk_state != TCP_CLOSE && (ssk_state != TCP_CLOSE_WAIT || inet_sk_state_load(sk) != TCP_ESTABLISHED)) continue; /* 'subflow_data_ready' will re-sched once rx queue is empty */ if (!skb_queue_empty_lockless(&ssk->sk_receive_queue)) continue; mptcp_close_ssk(sk, ssk, subflow); } } static bool mptcp_close_tout_expired(const struct sock *sk) { if (!inet_csk(sk)->icsk_mtup.probe_timestamp || sk->sk_state == TCP_CLOSE) return false; return time_after32(tcp_jiffies32, inet_csk(sk)->icsk_mtup.probe_timestamp + mptcp_close_timeout(sk)); } static void mptcp_check_fastclose(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow, *tmp; struct sock *sk = (struct sock *)msk; if (likely(!READ_ONCE(msk->rcv_fastclose))) return; mptcp_token_destroy(msk); mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); bool slow; slow = lock_sock_fast(tcp_sk); if (tcp_sk->sk_state != TCP_CLOSE) { mptcp_send_active_reset_reason(tcp_sk); tcp_set_state(tcp_sk, TCP_CLOSE); } unlock_sock_fast(tcp_sk, slow); } /* Mirror the tcp_reset() error propagation */ switch (sk->sk_state) { case TCP_SYN_SENT: WRITE_ONCE(sk->sk_err, ECONNREFUSED); break; case TCP_CLOSE_WAIT: WRITE_ONCE(sk->sk_err, EPIPE); break; case TCP_CLOSE: return; default: WRITE_ONCE(sk->sk_err, ECONNRESET); } mptcp_set_state(sk, TCP_CLOSE); WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags); /* the calling mptcp_worker will properly destroy the socket */ if (sock_flag(sk, SOCK_DEAD)) return; sk->sk_state_change(sk); sk_error_report(sk); } static void __mptcp_retrans(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_subflow_context *subflow; struct mptcp_sendmsg_info info = {}; struct mptcp_data_frag *dfrag; struct sock *ssk; int ret, err; u16 len = 0; mptcp_clean_una_wakeup(sk); /* first check ssk: need to kick "stale" logic */ err = mptcp_sched_get_retrans(msk); dfrag = mptcp_rtx_head(sk); if (!dfrag) { if (mptcp_data_fin_enabled(msk)) { struct inet_connection_sock *icsk = inet_csk(sk); icsk->icsk_retransmits++; mptcp_set_datafin_timeout(sk); mptcp_send_ack(msk); goto reset_timer; } if (!mptcp_send_head(sk)) return; goto reset_timer; } if (err) goto reset_timer; mptcp_for_each_subflow(msk, subflow) { if (READ_ONCE(subflow->scheduled)) { u16 copied = 0; mptcp_subflow_set_scheduled(subflow, false); ssk = mptcp_subflow_tcp_sock(subflow); lock_sock(ssk); /* limit retransmission to the bytes already sent on some subflows */ info.sent = 0; info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent; while (info.sent < info.limit) { ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info); if (ret <= 0) break; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS); copied += ret; info.sent += ret; } if (copied) { len = max(copied, len); tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); WRITE_ONCE(msk->allow_infinite_fallback, false); } release_sock(ssk); } } msk->bytes_retrans += len; dfrag->already_sent = max(dfrag->already_sent, len); reset_timer: mptcp_check_and_set_pending(sk); if (!mptcp_rtx_timer_pending(sk)) mptcp_reset_rtx_timer(sk); } /* schedule the timeout timer for the relevant event: either close timeout * or mp_fail timeout. The close timeout takes precedence on the mp_fail one */ void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout) { struct sock *sk = (struct sock *)msk; unsigned long timeout, close_timeout; if (!fail_tout && !inet_csk(sk)->icsk_mtup.probe_timestamp) return; close_timeout = (unsigned long)inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + mptcp_close_timeout(sk); /* the close timeout takes precedence on the fail one, and here at least one of * them is active */ timeout = inet_csk(sk)->icsk_mtup.probe_timestamp ? close_timeout : fail_tout; sk_reset_timer(sk, &sk->sk_timer, timeout); } static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) { struct sock *ssk = msk->first; bool slow; if (!ssk) return; pr_debug("MP_FAIL doesn't respond, reset the subflow\n"); slow = lock_sock_fast(ssk); mptcp_subflow_reset(ssk); WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0); unlock_sock_fast(ssk, slow); } static void mptcp_do_fastclose(struct sock *sk) { struct mptcp_subflow_context *subflow, *tmp; struct mptcp_sock *msk = mptcp_sk(sk); mptcp_set_state(sk, TCP_CLOSE); mptcp_for_each_subflow_safe(msk, subflow, tmp) __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, MPTCP_CF_FASTCLOSE); } static void mptcp_worker(struct work_struct *work) { struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work); struct sock *sk = (struct sock *)msk; unsigned long fail_tout; int state; lock_sock(sk); state = sk->sk_state; if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN))) goto unlock; mptcp_check_fastclose(msk); mptcp_pm_nl_work(msk); mptcp_check_send_data_fin(sk); mptcp_check_data_fin_ack(sk); mptcp_check_data_fin(sk); if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) __mptcp_close_subflow(sk); if (mptcp_close_tout_expired(sk)) { mptcp_do_fastclose(sk); mptcp_close_wake_up(sk); } if (sock_flag(sk, SOCK_DEAD) && sk->sk_state == TCP_CLOSE) { __mptcp_destroy_sock(sk); goto unlock; } if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) __mptcp_retrans(sk); fail_tout = msk->first ? READ_ONCE(mptcp_subflow_ctx(msk->first)->fail_tout) : 0; if (fail_tout && time_after(jiffies, fail_tout)) mptcp_mp_fail_no_response(msk); unlock: release_sock(sk); sock_put(sk); } static void __mptcp_init_sock(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); INIT_LIST_HEAD(&msk->conn_list); INIT_LIST_HEAD(&msk->join_list); INIT_LIST_HEAD(&msk->rtx_queue); INIT_WORK(&msk->work, mptcp_worker); __skb_queue_head_init(&msk->receive_queue); msk->out_of_order_queue = RB_ROOT; msk->first_pending = NULL; WRITE_ONCE(msk->rmem_fwd_alloc, 0); WRITE_ONCE(msk->rmem_released, 0); msk->timer_ival = TCP_RTO_MIN; msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO; WRITE_ONCE(msk->first, NULL); inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); WRITE_ONCE(msk->allow_infinite_fallback, true); msk->recovery = false; msk->subflow_id = 1; msk->last_data_sent = tcp_jiffies32; msk->last_data_recv = tcp_jiffies32; msk->last_ack_recv = tcp_jiffies32; mptcp_pm_data_init(msk); /* re-use the csk retrans timer for MPTCP-level retrans */ timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0); timer_setup(&sk->sk_timer, mptcp_tout_timer, 0); } static void mptcp_ca_reset(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_assign_congestion_control(sk); strscpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name, sizeof(mptcp_sk(sk)->ca_name)); /* no need to keep a reference to the ops, the name will suffice */ tcp_cleanup_congestion_control(sk); icsk->icsk_ca_ops = NULL; } static int mptcp_init_sock(struct sock *sk) { struct net *net = sock_net(sk); int ret; __mptcp_init_sock(sk); if (!mptcp_is_enabled(net)) return -ENOPROTOOPT; if (unlikely(!net->mib.mptcp_statistics) && !mptcp_mib_alloc(net)) return -ENOMEM; rcu_read_lock(); ret = mptcp_init_sched(mptcp_sk(sk), mptcp_sched_find(mptcp_get_scheduler(net))); rcu_read_unlock(); if (ret) return ret; set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags); /* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will * propagate the correct value */ mptcp_ca_reset(sk); sk_sockets_allocated_inc(sk); sk->sk_rcvbuf = READ_ONCE(net->ipv4.sysctl_tcp_rmem[1]); sk->sk_sndbuf = READ_ONCE(net->ipv4.sysctl_tcp_wmem[1]); return 0; } static void __mptcp_clear_xmit(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_data_frag *dtmp, *dfrag; WRITE_ONCE(msk->first_pending, NULL); list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) dfrag_clear(sk, dfrag); } void mptcp_cancel_work(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); if (cancel_work_sync(&msk->work)) __sock_put(sk); } void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) { lock_sock(ssk); switch (ssk->sk_state) { case TCP_LISTEN: if (!(how & RCV_SHUTDOWN)) break; fallthrough; case TCP_SYN_SENT: WARN_ON_ONCE(tcp_disconnect(ssk, O_NONBLOCK)); break; default: if (__mptcp_check_fallback(mptcp_sk(sk))) { pr_debug("Fallback\n"); ssk->sk_shutdown |= how; tcp_shutdown(ssk, how); /* simulate the data_fin ack reception to let the state * machine move forward */ WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt); mptcp_schedule_work(sk); } else { pr_debug("Sending DATA_FIN on subflow %p\n", ssk); tcp_send_ack(ssk); if (!mptcp_rtx_timer_pending(sk)) mptcp_reset_rtx_timer(sk); } break; } release_sock(ssk); } void mptcp_set_state(struct sock *sk, int state) { int oldstate = sk->sk_state; switch (state) { case TCP_ESTABLISHED: if (oldstate != TCP_ESTABLISHED) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB); break; case TCP_CLOSE_WAIT: /* Unlike TCP, MPTCP sk would not have the TCP_SYN_RECV state: * MPTCP "accepted" sockets will be created later on. So no * transition from TCP_SYN_RECV to TCP_CLOSE_WAIT. */ break; default: if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT) MPTCP_DEC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB); } inet_sk_state_store(sk, state); } static const unsigned char new_state[16] = { /* current state: new state: action: */ [0 /* (Invalid) */] = TCP_CLOSE, [TCP_ESTABLISHED] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, [TCP_SYN_SENT] = TCP_CLOSE, [TCP_SYN_RECV] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, [TCP_FIN_WAIT1] = TCP_FIN_WAIT1, [TCP_FIN_WAIT2] = TCP_FIN_WAIT2, [TCP_TIME_WAIT] = TCP_CLOSE, /* should not happen ! */ [TCP_CLOSE] = TCP_CLOSE, [TCP_CLOSE_WAIT] = TCP_LAST_ACK | TCP_ACTION_FIN, [TCP_LAST_ACK] = TCP_LAST_ACK, [TCP_LISTEN] = TCP_CLOSE, [TCP_CLOSING] = TCP_CLOSING, [TCP_NEW_SYN_RECV] = TCP_CLOSE, /* should not happen ! */ }; static int mptcp_close_state(struct sock *sk) { int next = (int)new_state[sk->sk_state]; int ns = next & TCP_STATE_MASK; mptcp_set_state(sk, ns); return next & TCP_ACTION_FIN; } static void mptcp_check_send_data_fin(struct sock *sk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu\n", msk, msk->snd_data_fin_enable, !!mptcp_send_head(sk), msk->snd_nxt, msk->write_seq); /* we still need to enqueue subflows or not really shutting down, * skip this */ if (!msk->snd_data_fin_enable || msk->snd_nxt + 1 != msk->write_seq || mptcp_send_head(sk)) return; WRITE_ONCE(msk->snd_nxt, msk->write_seq); mptcp_for_each_subflow(msk, subflow) { struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); mptcp_subflow_shutdown(sk, tcp_sk, SEND_SHUTDOWN); } } static void __mptcp_wr_shutdown(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d\n", msk, msk->snd_data_fin_enable, sk->sk_shutdown, sk->sk_state, !!mptcp_send_head(sk)); /* will be ignored by fallback sockets */ WRITE_ONCE(msk->write_seq, msk->write_seq + 1); WRITE_ONCE(msk->snd_data_fin_enable, 1); mptcp_check_send_data_fin(sk); } static void __mptcp_destroy_sock(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); pr_debug("msk=%p\n", msk); might_sleep(); mptcp_stop_rtx_timer(sk); sk_stop_timer(sk, &sk->sk_timer); msk->pm.status = 0; mptcp_release_sched(msk); sk->sk_prot->destroy(sk); WARN_ON_ONCE(READ_ONCE(msk->rmem_fwd_alloc)); WARN_ON_ONCE(msk->rmem_released); sk_stream_kill_queues(sk); xfrm_sk_free_policy(sk); sock_put(sk); } void __mptcp_unaccepted_force_close(struct sock *sk) { sock_set_flag(sk, SOCK_DEAD); mptcp_do_fastclose(sk); __mptcp_destroy_sock(sk); } static __poll_t mptcp_check_readable(struct sock *sk) { return mptcp_epollin_ready(sk) ? EPOLLIN | EPOLLRDNORM : 0; } static void mptcp_check_listen_stop(struct sock *sk) { struct sock *ssk; if (inet_sk_state_load(sk) != TCP_LISTEN) return; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); ssk = mptcp_sk(sk)->first; if (WARN_ON_ONCE(!ssk || inet_sk_state_load(ssk) != TCP_LISTEN)) return; lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); tcp_set_state(ssk, TCP_CLOSE); mptcp_subflow_queue_clean(sk, ssk); inet_csk_listen_stop(ssk); mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); release_sock(ssk); } bool __mptcp_close(struct sock *sk, long timeout) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); bool do_cancel_work = false; int subflows_alive = 0; WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) { mptcp_check_listen_stop(sk); mptcp_set_state(sk, TCP_CLOSE); goto cleanup; } if (mptcp_data_avail(msk) || timeout < 0) { /* If the msk has read data, or the caller explicitly ask it, * do the MPTCP equivalent of TCP reset, aka MPTCP fastclose */ mptcp_do_fastclose(sk); timeout = 0; } else if (mptcp_close_state(sk)) { __mptcp_wr_shutdown(sk); } sk_stream_wait_close(sk, timeout); cleanup: /* orphan all the subflows */ mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast_nested(ssk); subflows_alive += ssk->sk_state != TCP_CLOSE; /* since the close timeout takes precedence on the fail one, * cancel the latter */ if (ssk == msk->first) subflow->fail_tout = 0; /* detach from the parent socket, but allow data_ready to * push incoming data into the mptcp stack, to properly ack it */ ssk->sk_socket = NULL; ssk->sk_wq = NULL; unlock_sock_fast(ssk, slow); } sock_orphan(sk); /* all the subflows are closed, only timeout can change the msk * state, let's not keep resources busy for no reasons */ if (subflows_alive == 0) mptcp_set_state(sk, TCP_CLOSE); sock_hold(sk); pr_debug("msk=%p state=%d\n", sk, sk->sk_state); mptcp_pm_connection_closed(msk); if (sk->sk_state == TCP_CLOSE) { __mptcp_destroy_sock(sk); do_cancel_work = true; } else { mptcp_start_tout_timer(sk); } return do_cancel_work; } static void mptcp_close(struct sock *sk, long timeout) { bool do_cancel_work; lock_sock(sk); do_cancel_work = __mptcp_close(sk, timeout); release_sock(sk); if (do_cancel_work) mptcp_cancel_work(sk); sock_put(sk); } static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) const struct ipv6_pinfo *ssk6 = inet6_sk(ssk); struct ipv6_pinfo *msk6 = inet6_sk(msk); msk->sk_v6_daddr = ssk->sk_v6_daddr; msk->sk_v6_rcv_saddr = ssk->sk_v6_rcv_saddr; if (msk6 && ssk6) { msk6->saddr = ssk6->saddr; msk6->flow_label = ssk6->flow_label; } #endif inet_sk(msk)->inet_num = inet_sk(ssk)->inet_num; inet_sk(msk)->inet_dport = inet_sk(ssk)->inet_dport; inet_sk(msk)->inet_sport = inet_sk(ssk)->inet_sport; inet_sk(msk)->inet_daddr = inet_sk(ssk)->inet_daddr; inet_sk(msk)->inet_saddr = inet_sk(ssk)->inet_saddr; inet_sk(msk)->inet_rcv_saddr = inet_sk(ssk)->inet_rcv_saddr; } static int mptcp_disconnect(struct sock *sk, int flags) { struct mptcp_sock *msk = mptcp_sk(sk); /* We are on the fastopen error path. We can't call straight into the * subflows cleanup code due to lock nesting (we are already under * msk->firstsocket lock). */ if (msk->fastopening) return -EBUSY; mptcp_check_listen_stop(sk); mptcp_set_state(sk, TCP_CLOSE); mptcp_stop_rtx_timer(sk); mptcp_stop_tout_timer(sk); mptcp_pm_connection_closed(msk); /* msk->subflow is still intact, the following will not free the first * subflow */ mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE); WRITE_ONCE(msk->flags, 0); msk->cb_flags = 0; msk->recovery = false; WRITE_ONCE(msk->can_ack, false); WRITE_ONCE(msk->fully_established, false); WRITE_ONCE(msk->rcv_data_fin, false); WRITE_ONCE(msk->snd_data_fin_enable, false); WRITE_ONCE(msk->rcv_fastclose, false); WRITE_ONCE(msk->use_64bit_ack, false); WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); mptcp_pm_data_reset(msk); mptcp_ca_reset(sk); msk->bytes_consumed = 0; msk->bytes_acked = 0; msk->bytes_received = 0; msk->bytes_sent = 0; msk->bytes_retrans = 0; msk->rcvspace_init = 0; WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); return 0; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) { unsigned int offset = sizeof(struct mptcp6_sock) - sizeof(struct ipv6_pinfo); return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } static void mptcp_copy_ip6_options(struct sock *newsk, const struct sock *sk) { const struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_txoptions *opt; struct ipv6_pinfo *newnp; newnp = inet6_sk(newsk); rcu_read_lock(); opt = rcu_dereference(np->opt); if (opt) { opt = ipv6_dup_options(newsk, opt); if (!opt) net_warn_ratelimited("%s: Failed to copy ip6 options\n", __func__); } RCU_INIT_POINTER(newnp->opt, opt); rcu_read_unlock(); } #endif static void mptcp_copy_ip_options(struct sock *newsk, const struct sock *sk) { struct ip_options_rcu *inet_opt, *newopt = NULL; const struct inet_sock *inet = inet_sk(sk); struct inet_sock *newinet; newinet = inet_sk(newsk); rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt) { newopt = sock_kmalloc(newsk, sizeof(*inet_opt) + inet_opt->opt.optlen, GFP_ATOMIC); if (newopt) memcpy(newopt, inet_opt, sizeof(*inet_opt) + inet_opt->opt.optlen); else net_warn_ratelimited("%s: Failed to copy ip options\n", __func__); } RCU_INIT_POINTER(newinet->inet_opt, newopt); rcu_read_unlock(); } struct sock *mptcp_sk_clone_init(const struct sock *sk, const struct mptcp_options_received *mp_opt, struct sock *ssk, struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); struct mptcp_subflow_context *subflow; struct mptcp_sock *msk; if (!nsk) return NULL; #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (nsk->sk_family == AF_INET6) inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk); #endif __mptcp_init_sock(nsk); #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (nsk->sk_family == AF_INET6) mptcp_copy_ip6_options(nsk, sk); else #endif mptcp_copy_ip_options(nsk, sk); msk = mptcp_sk(nsk); WRITE_ONCE(msk->local_key, subflow_req->local_key); WRITE_ONCE(msk->token, subflow_req->token); msk->in_accept_queue = 1; WRITE_ONCE(msk->fully_established, false); if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD) WRITE_ONCE(msk->csum_enabled, true); WRITE_ONCE(msk->write_seq, subflow_req->idsn + 1); WRITE_ONCE(msk->snd_nxt, msk->write_seq); WRITE_ONCE(msk->snd_una, msk->write_seq); WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq; mptcp_init_sched(msk, mptcp_sk(sk)->sched); /* passive msk is created after the first/MPC subflow */ msk->subflow_id = 2; sock_reset_flag(nsk, SOCK_RCU_FREE); security_inet_csk_clone(nsk, req); /* this can't race with mptcp_close(), as the msk is * not yet exposted to user-space */ mptcp_set_state(nsk, TCP_ESTABLISHED); /* The msk maintain a ref to each subflow in the connections list */ WRITE_ONCE(msk->first, ssk); subflow = mptcp_subflow_ctx(ssk); list_add(&subflow->node, &msk->conn_list); sock_hold(ssk); /* new mpc subflow takes ownership of the newly * created mptcp socket */ mptcp_token_accept(subflow_req, msk); /* set msk addresses early to ensure mptcp_pm_get_local_id() * uses the correct data */ mptcp_copy_inaddrs(nsk, ssk); __mptcp_propagate_sndbuf(nsk, ssk); mptcp_rcv_space_init(msk, ssk); if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK) __mptcp_subflow_fully_established(msk, subflow, mp_opt); bh_unlock_sock(nsk); /* note: the newly allocated socket refcount is 2 now */ return nsk; } void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) { const struct tcp_sock *tp = tcp_sk(ssk); msk->rcvspace_init = 1; msk->rcvq_space.copied = 0; msk->rcvq_space.rtt_us = 0; msk->rcvq_space.time = tp->tcp_mstamp; /* initial rcv_space offering made to peer */ msk->rcvq_space.space = min_t(u32, tp->rcv_wnd, TCP_INIT_CWND * tp->advmss); if (msk->rcvq_space.space == 0) msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT; } void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) { struct mptcp_subflow_context *subflow, *tmp; struct sock *sk = (struct sock *)msk; __mptcp_clear_xmit(sk); /* join list will be eventually flushed (with rst) at sock lock release time */ mptcp_for_each_subflow_safe(msk, subflow, tmp) __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, flags); /* move to sk_receive_queue, sk_stream_kill_queues will purge it */ mptcp_data_lock(sk); skb_queue_splice_tail_init(&msk->receive_queue, &sk->sk_receive_queue); __skb_queue_purge(&sk->sk_receive_queue); skb_rbtree_purge(&msk->out_of_order_queue); mptcp_data_unlock(sk); /* move all the rx fwd alloc into the sk_mem_reclaim_final in * inet_sock_destruct() will dispose it */ sk_forward_alloc_add(sk, msk->rmem_fwd_alloc); WRITE_ONCE(msk->rmem_fwd_alloc, 0); mptcp_token_destroy(msk); mptcp_pm_free_anno_list(msk); mptcp_free_local_addr_list(msk); } static void mptcp_destroy(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); /* allow the following to close even the initial subflow */ msk->free_first = 1; mptcp_destroy_common(msk, 0); sk_sockets_allocated_dec(sk); } void __mptcp_data_acked(struct sock *sk) { if (!sock_owned_by_user(sk)) __mptcp_clean_una(sk); else __set_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->cb_flags); } void __mptcp_check_push(struct sock *sk, struct sock *ssk) { if (!mptcp_send_head(sk)) return; if (!sock_owned_by_user(sk)) __mptcp_subflow_push_pending(sk, ssk, false); else __set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags); } #define MPTCP_FLAGS_PROCESS_CTX_NEED (BIT(MPTCP_PUSH_PENDING) | \ BIT(MPTCP_RETRANSMIT) | \ BIT(MPTCP_FLUSH_JOIN_LIST)) /* processes deferred events and flush wmem */ static void mptcp_release_cb(struct sock *sk) __must_hold(&sk->sk_lock.slock) { struct mptcp_sock *msk = mptcp_sk(sk); for (;;) { unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED); struct list_head join_list; if (!flags) break; INIT_LIST_HEAD(&join_list); list_splice_init(&msk->join_list, &join_list); /* the following actions acquire the subflow socket lock * * 1) can't be invoked in atomic scope * 2) must avoid ABBA deadlock with msk socket spinlock: the RX * datapath acquires the msk socket spinlock while helding * the subflow socket lock */ msk->cb_flags &= ~flags; spin_unlock_bh(&sk->sk_lock.slock); if (flags & BIT(MPTCP_FLUSH_JOIN_LIST)) __mptcp_flush_join_list(sk, &join_list); if (flags & BIT(MPTCP_PUSH_PENDING)) __mptcp_push_pending(sk, 0); if (flags & BIT(MPTCP_RETRANSMIT)) __mptcp_retrans(sk); cond_resched(); spin_lock_bh(&sk->sk_lock.slock); } if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags)) __mptcp_clean_una_wakeup(sk); if (unlikely(msk->cb_flags)) { /* be sure to sync the msk state before taking actions * depending on sk_state (MPTCP_ERROR_REPORT) * On sk release avoid actions depending on the first subflow */ if (__test_and_clear_bit(MPTCP_SYNC_STATE, &msk->cb_flags) && msk->first) __mptcp_sync_state(sk, msk->pending_state); if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags)) __mptcp_error_report(sk); if (__test_and_clear_bit(MPTCP_SYNC_SNDBUF, &msk->cb_flags)) __mptcp_sync_sndbuf(sk); } __mptcp_update_rmem(sk); } /* MP_JOIN client subflow must wait for 4th ack before sending any data: * TCP can't schedule delack timer before the subflow is fully established. * MPTCP uses the delack timer to do 3rd ack retransmissions */ static void schedule_3rdack_retransmission(struct sock *ssk) { struct inet_connection_sock *icsk = inet_csk(ssk); struct tcp_sock *tp = tcp_sk(ssk); unsigned long timeout; if (READ_ONCE(mptcp_subflow_ctx(ssk)->fully_established)) return; /* reschedule with a timeout above RTT, as we must look only for drop */ if (tp->srtt_us) timeout = usecs_to_jiffies(tp->srtt_us >> (3 - 1)); else timeout = TCP_TIMEOUT_INIT; timeout += jiffies; WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER); smp_store_release(&icsk->icsk_ack.pending, icsk->icsk_ack.pending | ICSK_ACK_SCHED | ICSK_ACK_TIMER); icsk->icsk_ack.timeout = timeout; sk_reset_timer(ssk, &icsk->icsk_delack_timer, timeout); } void mptcp_subflow_process_delegated(struct sock *ssk, long status) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = subflow->conn; if (status & BIT(MPTCP_DELEGATE_SEND)) { mptcp_data_lock(sk); if (!sock_owned_by_user(sk)) __mptcp_subflow_push_pending(sk, ssk, true); else __set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); } if (status & BIT(MPTCP_DELEGATE_SNDBUF)) { mptcp_data_lock(sk); if (!sock_owned_by_user(sk)) __mptcp_sync_sndbuf(sk); else __set_bit(MPTCP_SYNC_SNDBUF, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); } if (status & BIT(MPTCP_DELEGATE_ACK)) schedule_3rdack_retransmission(ssk); } static int mptcp_hash(struct sock *sk) { /* should never be called, * we hash the TCP subflows not the MPTCP socket */ WARN_ON_ONCE(1); return 0; } static void mptcp_unhash(struct sock *sk) { /* called from sk_common_release(), but nothing to do here */ } static int mptcp_get_port(struct sock *sk, unsigned short snum) { struct mptcp_sock *msk = mptcp_sk(sk); pr_debug("msk=%p, ssk=%p\n", msk, msk->first); if (WARN_ON_ONCE(!msk->first)) return -EINVAL; return inet_csk_get_port(msk->first, snum); } void mptcp_finish_connect(struct sock *ssk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk; struct sock *sk; subflow = mptcp_subflow_ctx(ssk); sk = subflow->conn; msk = mptcp_sk(sk); pr_debug("msk=%p, token=%u\n", sk, subflow->token); subflow->map_seq = subflow->iasn; subflow->map_subflow_seq = 1; /* the socket is not connected yet, no msk/subflow ops can access/race * accessing the field below */ WRITE_ONCE(msk->local_key, subflow->local_key); mptcp_pm_new_connection(msk, ssk, 0); } void mptcp_sock_graft(struct sock *sk, struct socket *parent) { write_lock_bh(&sk->sk_callback_lock); rcu_assign_pointer(sk->sk_wq, &parent->wq); sk_set_socket(sk, parent); sk->sk_uid = SOCK_INODE(parent)->i_uid; write_unlock_bh(&sk->sk_callback_lock); } bool mptcp_finish_join(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); struct sock *parent = (void *)msk; bool ret = true; pr_debug("msk=%p, subflow=%p\n", msk, subflow); /* mptcp socket already closing? */ if (!mptcp_is_fully_established(parent)) { subflow->reset_reason = MPTCP_RST_EMPTCP; return false; } /* active subflow, already present inside the conn_list */ if (!list_empty(&subflow->node)) { mptcp_subflow_joined(msk, ssk); mptcp_propagate_sndbuf(parent, ssk); return true; } if (!mptcp_pm_allow_new_subflow(msk)) goto err_prohibited; /* If we can't acquire msk socket lock here, let the release callback * handle it */ mptcp_data_lock(parent); if (!sock_owned_by_user(parent)) { ret = __mptcp_finish_join(msk, ssk); if (ret) { sock_hold(ssk); list_add_tail(&subflow->node, &msk->conn_list); } } else { sock_hold(ssk); list_add_tail(&subflow->node, &msk->join_list); __set_bit(MPTCP_FLUSH_JOIN_LIST, &msk->cb_flags); } mptcp_data_unlock(parent); if (!ret) { err_prohibited: subflow->reset_reason = MPTCP_RST_EPROHIBIT; return false; } return true; } static void mptcp_shutdown(struct sock *sk, int how) { pr_debug("sk=%p, how=%d\n", sk, how); if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk)) __mptcp_wr_shutdown(sk); } static int mptcp_forward_alloc_get(const struct sock *sk) { return READ_ONCE(sk->sk_forward_alloc) + READ_ONCE(mptcp_sk(sk)->rmem_fwd_alloc); } static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v) { const struct sock *sk = (void *)msk; u64 delta; if (sk->sk_state == TCP_LISTEN) return -EINVAL; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) return 0; delta = msk->write_seq - v; if (__mptcp_check_fallback(msk) && msk->first) { struct tcp_sock *tp = tcp_sk(msk->first); /* the first subflow is disconnected after close - see * __mptcp_close_ssk(). tcp_disconnect() moves the write_seq * so ignore that status, too. */ if (!((1 << msk->first->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))) delta += READ_ONCE(tp->write_seq) - tp->snd_una; } if (delta > INT_MAX) delta = INT_MAX; return (int)delta; } static int mptcp_ioctl(struct sock *sk, int cmd, int *karg) { struct mptcp_sock *msk = mptcp_sk(sk); bool slow; switch (cmd) { case SIOCINQ: if (sk->sk_state == TCP_LISTEN) return -EINVAL; lock_sock(sk); __mptcp_move_skbs(msk); *karg = mptcp_inq_hint(sk); release_sock(sk); break; case SIOCOUTQ: slow = lock_sock_fast(sk); *karg = mptcp_ioctl_outq(msk, READ_ONCE(msk->snd_una)); unlock_sock_fast(sk, slow); break; case SIOCOUTQNSD: slow = lock_sock_fast(sk); *karg = mptcp_ioctl_outq(msk, msk->snd_nxt); unlock_sock_fast(sk, slow); break; default: return -ENOIOCTLCMD; } return 0; } static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); int err = -EINVAL; struct sock *ssk; ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) return PTR_ERR(ssk); mptcp_set_state(sk, TCP_SYN_SENT); subflow = mptcp_subflow_ctx(ssk); #ifdef CONFIG_TCP_MD5SIG /* no MPTCP if MD5SIG is enabled on this socket or we may run out of * TCP option space. */ if (rcu_access_pointer(tcp_sk(ssk)->md5sig_info)) mptcp_subflow_early_fallback(msk, subflow); #endif if (subflow->request_mptcp) { if (mptcp_active_should_disable(sk)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEACTIVEDISABLED); mptcp_subflow_early_fallback(msk, subflow); } else if (mptcp_token_new_connect(ssk) < 0) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_TOKENFALLBACKINIT); mptcp_subflow_early_fallback(msk, subflow); } } WRITE_ONCE(msk->write_seq, subflow->idsn); WRITE_ONCE(msk->snd_nxt, subflow->idsn); WRITE_ONCE(msk->snd_una, subflow->idsn); if (likely(!__mptcp_check_fallback(msk))) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVE); /* if reaching here via the fastopen/sendmsg path, the caller already * acquired the subflow socket lock, too. */ if (!msk->fastopening) lock_sock(ssk); /* the following mirrors closely a very small chunk of code from * __inet_stream_connect() */ if (ssk->sk_state != TCP_CLOSE) goto out; if (BPF_CGROUP_PRE_CONNECT_ENABLED(ssk)) { err = ssk->sk_prot->pre_connect(ssk, uaddr, addr_len); if (err) goto out; } err = ssk->sk_prot->connect(ssk, uaddr, addr_len); if (err < 0) goto out; inet_assign_bit(DEFER_CONNECT, sk, inet_test_bit(DEFER_CONNECT, ssk)); out: if (!msk->fastopening) release_sock(ssk); /* on successful connect, the msk state will be moved to established by * subflow_finish_connect() */ if (unlikely(err)) { /* avoid leaving a dangling token in an unconnected socket */ mptcp_token_destroy(msk); mptcp_set_state(sk, TCP_CLOSE); return err; } mptcp_copy_inaddrs(sk, ssk); return 0; } static struct proto mptcp_prot = { .name = "MPTCP", .owner = THIS_MODULE, .init = mptcp_init_sock, .connect = mptcp_connect, .disconnect = mptcp_disconnect, .close = mptcp_close, .setsockopt = mptcp_setsockopt, .getsockopt = mptcp_getsockopt, .shutdown = mptcp_shutdown, .destroy = mptcp_destroy, .sendmsg = mptcp_sendmsg, .ioctl = mptcp_ioctl, .recvmsg = mptcp_recvmsg, .release_cb = mptcp_release_cb, .hash = mptcp_hash, .unhash = mptcp_unhash, .get_port = mptcp_get_port, .forward_alloc_get = mptcp_forward_alloc_get, .stream_memory_free = mptcp_stream_memory_free, .sockets_allocated = &mptcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, .memory_pressure = &tcp_memory_pressure, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .sysctl_mem = sysctl_tcp_mem, .obj_size = sizeof(struct mptcp_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, .no_autobind = true, }; static int mptcp_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct mptcp_sock *msk = mptcp_sk(sock->sk); struct sock *ssk, *sk = sock->sk; int err = -EINVAL; lock_sock(sk); ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) { err = PTR_ERR(ssk); goto unlock; } if (sk->sk_family == AF_INET) err = inet_bind_sk(ssk, uaddr, addr_len); #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (sk->sk_family == AF_INET6) err = inet6_bind_sk(ssk, uaddr, addr_len); #endif if (!err) mptcp_copy_inaddrs(sk, ssk); unlock: release_sock(sk); return err; } static int mptcp_listen(struct socket *sock, int backlog) { struct mptcp_sock *msk = mptcp_sk(sock->sk); struct sock *sk = sock->sk; struct sock *ssk; int err; pr_debug("msk=%p\n", msk); lock_sock(sk); err = -EINVAL; if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) goto unlock; ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) { err = PTR_ERR(ssk); goto unlock; } mptcp_set_state(sk, TCP_LISTEN); sock_set_flag(sk, SOCK_RCU_FREE); lock_sock(ssk); err = __inet_listen_sk(ssk, backlog); release_sock(ssk); mptcp_set_state(sk, inet_sk_state_load(ssk)); if (!err) { sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); mptcp_copy_inaddrs(sk, ssk); mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CREATED); } unlock: release_sock(sk); return err; } static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { struct mptcp_sock *msk = mptcp_sk(sock->sk); struct sock *ssk, *newsk; pr_debug("msk=%p\n", msk); /* Buggy applications can call accept on socket states other then LISTEN * but no need to allocate the first subflow just to error out. */ ssk = READ_ONCE(msk->first); if (!ssk) return -EINVAL; pr_debug("ssk=%p, listener=%p\n", ssk, mptcp_subflow_ctx(ssk)); newsk = inet_csk_accept(ssk, arg); if (!newsk) return arg->err; pr_debug("newsk=%p, subflow is mptcp=%d\n", newsk, sk_is_mptcp(newsk)); if (sk_is_mptcp(newsk)) { struct mptcp_subflow_context *subflow; struct sock *new_mptcp_sock; subflow = mptcp_subflow_ctx(newsk); new_mptcp_sock = subflow->conn; /* is_mptcp should be false if subflow->conn is missing, see * subflow_syn_recv_sock() */ if (WARN_ON_ONCE(!new_mptcp_sock)) { tcp_sk(newsk)->is_mptcp = 0; goto tcpfallback; } newsk = new_mptcp_sock; MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEACK); newsk->sk_kern_sock = arg->kern; lock_sock(newsk); __inet_accept(sock, newsock, newsk); set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags); msk = mptcp_sk(newsk); msk->in_accept_queue = 0; /* set ssk->sk_socket of accept()ed flows to mptcp socket. * This is needed so NOSPACE flag can be set from tcp stack. */ mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (!ssk->sk_socket) mptcp_sock_graft(ssk, newsock); } /* Do late cleanup for the first subflow as necessary. Also * deal with bad peers not doing a complete shutdown. */ if (unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) { __mptcp_close_ssk(newsk, msk->first, mptcp_subflow_ctx(msk->first), 0); if (unlikely(list_is_singular(&msk->conn_list))) mptcp_set_state(newsk, TCP_CLOSE); } } else { tcpfallback: newsk->sk_kern_sock = arg->kern; lock_sock(newsk); __inet_accept(sock, newsock, newsk); /* we are being invoked after accepting a non-mp-capable * flow: sk is a tcp_sk, not an mptcp one. * * Hand the socket over to tcp so all further socket ops * bypass mptcp. */ WRITE_ONCE(newsock->sk->sk_socket->ops, mptcp_fallback_tcp_ops(newsock->sk)); } release_sock(newsk); return 0; } static __poll_t mptcp_check_writeable(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; if (__mptcp_stream_is_writeable(sk, 1)) return EPOLLOUT | EPOLLWRNORM; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); smp_mb__after_atomic(); /* NOSPACE is changed by mptcp_write_space() */ if (__mptcp_stream_is_writeable(sk, 1)) return EPOLLOUT | EPOLLWRNORM; return 0; } static __poll_t mptcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait) { struct sock *sk = sock->sk; struct mptcp_sock *msk; __poll_t mask = 0; u8 shutdown; int state; msk = mptcp_sk(sk); sock_poll_wait(file, sock, wait); state = inet_sk_state_load(sk); pr_debug("msk=%p state=%d flags=%lx\n", msk, state, msk->flags); if (state == TCP_LISTEN) { struct sock *ssk = READ_ONCE(msk->first); if (WARN_ON_ONCE(!ssk)) return 0; return inet_csk_listen_poll(ssk); } shutdown = READ_ONCE(sk->sk_shutdown); if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) mask |= EPOLLHUP; if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) { mask |= mptcp_check_readable(sk); if (shutdown & SEND_SHUTDOWN) mask |= EPOLLOUT | EPOLLWRNORM; else mask |= mptcp_check_writeable(msk); } else if (state == TCP_SYN_SENT && inet_test_bit(DEFER_CONNECT, sk)) { /* cf tcp_poll() note about TFO */ mask |= EPOLLOUT | EPOLLWRNORM; } /* This barrier is coupled with smp_wmb() in __mptcp_error_report() */ smp_rmb(); if (READ_ONCE(sk->sk_err)) mask |= EPOLLERR; return mask; } static const struct proto_ops mptcp_stream_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = mptcp_bind, .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = mptcp_stream_accept, .getname = inet_getname, .poll = mptcp_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = mptcp_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .set_rcvlowat = mptcp_set_rcvlowat, }; static struct inet_protosw mptcp_protosw = { .type = SOCK_STREAM, .protocol = IPPROTO_MPTCP, .prot = &mptcp_prot, .ops = &mptcp_stream_ops, .flags = INET_PROTOSW_ICSK, }; static int mptcp_napi_poll(struct napi_struct *napi, int budget) { struct mptcp_delegated_action *delegated; struct mptcp_subflow_context *subflow; int work_done = 0; delegated = container_of(napi, struct mptcp_delegated_action, napi); while ((subflow = mptcp_subflow_delegated_next(delegated)) != NULL) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bh_lock_sock_nested(ssk); if (!sock_owned_by_user(ssk)) { mptcp_subflow_process_delegated(ssk, xchg(&subflow->delegated_status, 0)); } else { /* tcp_release_cb_override already processed * the action or will do at next release_sock(). * In both case must dequeue the subflow here - on the same * CPU that scheduled it. */ smp_wmb(); clear_bit(MPTCP_DELEGATE_SCHEDULED, &subflow->delegated_status); } bh_unlock_sock(ssk); sock_put(ssk); if (++work_done == budget) return budget; } /* always provide a 0 'work_done' argument, so that napi_complete_done * will not try accessing the NULL napi->dev ptr */ napi_complete_done(napi, 0); return work_done; } void __init mptcp_proto_init(void) { struct mptcp_delegated_action *delegated; int cpu; mptcp_prot.h.hashinfo = tcp_prot.h.hashinfo; if (percpu_counter_init(&mptcp_sockets_allocated, 0, GFP_KERNEL)) panic("Failed to allocate MPTCP pcpu counter\n"); init_dummy_netdev(&mptcp_napi_dev); for_each_possible_cpu(cpu) { delegated = per_cpu_ptr(&mptcp_delegated_actions, cpu); INIT_LIST_HEAD(&delegated->head); netif_napi_add_tx(&mptcp_napi_dev, &delegated->napi, mptcp_napi_poll); napi_enable(&delegated->napi); } mptcp_subflow_init(); mptcp_pm_init(); mptcp_sched_init(); mptcp_token_init(); if (proto_register(&mptcp_prot, 1) != 0) panic("Failed to register MPTCP proto.\n"); inet_register_protosw(&mptcp_protosw); BUILD_BUG_ON(sizeof(struct mptcp_skb_cb) > sizeof_field(struct sk_buff, cb)); } #if IS_ENABLED(CONFIG_MPTCP_IPV6) static const struct proto_ops mptcp_v6_stream_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, .bind = mptcp_bind, .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = mptcp_stream_accept, .getname = inet6_getname, .poll = mptcp_poll, .ioctl = inet6_ioctl, .gettstamp = sock_gettstamp, .listen = mptcp_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet6_sendmsg, .recvmsg = inet6_recvmsg, .mmap = sock_no_mmap, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif .set_rcvlowat = mptcp_set_rcvlowat, }; static struct proto mptcp_v6_prot; static struct inet_protosw mptcp_v6_protosw = { .type = SOCK_STREAM, .protocol = IPPROTO_MPTCP, .prot = &mptcp_v6_prot, .ops = &mptcp_v6_stream_ops, .flags = INET_PROTOSW_ICSK, }; int __init mptcp_proto_v6_init(void) { int err; mptcp_v6_prot = mptcp_prot; strscpy(mptcp_v6_prot.name, "MPTCPv6", sizeof(mptcp_v6_prot.name)); mptcp_v6_prot.slab = NULL; mptcp_v6_prot.obj_size = sizeof(struct mptcp6_sock); mptcp_v6_prot.ipv6_pinfo_offset = offsetof(struct mptcp6_sock, np); err = proto_register(&mptcp_v6_prot, 1); if (err) return err; err = inet6_register_protosw(&mptcp_v6_protosw); if (err) proto_unregister(&mptcp_v6_prot); return err; } #endif |
| 803 781 27 799 4 807 686 805 803 802 725 72 802 799 773 25 58 56 55 3 81 82 116 118 106 106 23 66 832 831 6 1 6 6 803 797 252 728 80 17 1 1 1 802 803 805 794 803 811 119 721 803 801 797 16 9 17 16 9 1 8 9 752 750 748 755 749 641 243 244 50 53 6 9 9 8 17 16 8 9 8 9 9 18 799 19 792 742 798 859 69 804 811 1 1 27 200 114 34 34 34 34 34 108 108 34 140 227 1 225 227 225 220 166 108 108 107 9 2 6 35 35 8 30 30 16 281 158 124 285 54 54 53 34 34 35 23 31 20 20 19 4 20 4 4 50 51 22 22 7 7 7 307 311 466 461 6 357 360 288 70 67 26 67 2 2 38 35 3 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * (C) 1997 Linus Torvalds * (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation) */ #include <linux/export.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/mm.h> #include <linux/backing-dev.h> #include <linux/hash.h> #include <linux/swap.h> #include <linux/security.h> #include <linux/cdev.h> #include <linux/memblock.h> #include <linux/fsnotify.h> #include <linux/mount.h> #include <linux/posix_acl.h> #include <linux/buffer_head.h> /* for inode_has_buffers */ #include <linux/ratelimit.h> #include <linux/list_lru.h> #include <linux/iversion.h> #include <linux/rw_hint.h> #include <linux/seq_file.h> #include <linux/debugfs.h> #include <trace/events/writeback.h> #define CREATE_TRACE_POINTS #include <trace/events/timestamp.h> #include "internal.h" /* * Inode locking rules: * * inode->i_lock protects: * inode->i_state, inode->i_hash, __iget(), inode->i_io_list * Inode LRU list locks protect: * inode->i_sb->s_inode_lru, inode->i_lru * inode->i_sb->s_inode_list_lock protects: * inode->i_sb->s_inodes, inode->i_sb_list * bdi->wb.list_lock protects: * bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_io_list * inode_hash_lock protects: * inode_hashtable, inode->i_hash * * Lock ordering: * * inode->i_sb->s_inode_list_lock * inode->i_lock * Inode LRU list locks * * bdi->wb.list_lock * inode->i_lock * * inode_hash_lock * inode->i_sb->s_inode_list_lock * inode->i_lock * * iunique_lock * inode_hash_lock */ static unsigned int i_hash_mask __ro_after_init; static unsigned int i_hash_shift __ro_after_init; static struct hlist_head *inode_hashtable __ro_after_init; static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock); /* * Empty aops. Can be used for the cases where the user does not * define any of the address_space operations. */ const struct address_space_operations empty_aops = { }; EXPORT_SYMBOL(empty_aops); static DEFINE_PER_CPU(unsigned long, nr_inodes); static DEFINE_PER_CPU(unsigned long, nr_unused); static struct kmem_cache *inode_cachep __ro_after_init; static long get_nr_inodes(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_inodes, i); return sum < 0 ? 0 : sum; } static inline long get_nr_inodes_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_unused, i); return sum < 0 ? 0 : sum; } long get_nr_dirty_inodes(void) { /* not actually dirty inodes, but a wild approximation */ long nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); return nr_dirty > 0 ? nr_dirty : 0; } #ifdef CONFIG_DEBUG_FS static DEFINE_PER_CPU(long, mg_ctime_updates); static DEFINE_PER_CPU(long, mg_fine_stamps); static DEFINE_PER_CPU(long, mg_ctime_swaps); static unsigned long get_mg_ctime_updates(void) { unsigned long sum = 0; int i; for_each_possible_cpu(i) sum += data_race(per_cpu(mg_ctime_updates, i)); return sum; } static unsigned long get_mg_fine_stamps(void) { unsigned long sum = 0; int i; for_each_possible_cpu(i) sum += data_race(per_cpu(mg_fine_stamps, i)); return sum; } static unsigned long get_mg_ctime_swaps(void) { unsigned long sum = 0; int i; for_each_possible_cpu(i) sum += data_race(per_cpu(mg_ctime_swaps, i)); return sum; } #define mgtime_counter_inc(__var) this_cpu_inc(__var) static int mgts_show(struct seq_file *s, void *p) { unsigned long ctime_updates = get_mg_ctime_updates(); unsigned long ctime_swaps = get_mg_ctime_swaps(); unsigned long fine_stamps = get_mg_fine_stamps(); unsigned long floor_swaps = timekeeping_get_mg_floor_swaps(); seq_printf(s, "%lu %lu %lu %lu\n", ctime_updates, ctime_swaps, fine_stamps, floor_swaps); return 0; } DEFINE_SHOW_ATTRIBUTE(mgts); static int __init mg_debugfs_init(void) { debugfs_create_file("multigrain_timestamps", S_IFREG | S_IRUGO, NULL, NULL, &mgts_fops); return 0; } late_initcall(mg_debugfs_init); #else /* ! CONFIG_DEBUG_FS */ #define mgtime_counter_inc(__var) do { } while (0) #endif /* CONFIG_DEBUG_FS */ /* * Handle nr_inode sysctl */ #ifdef CONFIG_SYSCTL /* * Statistics gathering.. */ static struct inodes_stat_t inodes_stat; static int proc_nr_inodes(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { inodes_stat.nr_inodes = get_nr_inodes(); inodes_stat.nr_unused = get_nr_inodes_unused(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static struct ctl_table inodes_sysctls[] = { { .procname = "inode-nr", .data = &inodes_stat, .maxlen = 2*sizeof(long), .mode = 0444, .proc_handler = proc_nr_inodes, }, { .procname = "inode-state", .data = &inodes_stat, .maxlen = 7*sizeof(long), .mode = 0444, .proc_handler = proc_nr_inodes, }, }; static int __init init_fs_inode_sysctls(void) { register_sysctl_init("fs", inodes_sysctls); return 0; } early_initcall(init_fs_inode_sysctls); #endif static int no_open(struct inode *inode, struct file *file) { return -ENXIO; } /** * inode_init_always_gfp - perform inode structure initialisation * @sb: superblock inode belongs to * @inode: inode to initialise * @gfp: allocation flags * * These are initializations that need to be done on every inode * allocation as the fields are not initialised by slab allocation. * If there are additional allocations required @gfp is used. */ int inode_init_always_gfp(struct super_block *sb, struct inode *inode, gfp_t gfp) { static const struct inode_operations empty_iops; static const struct file_operations no_open_fops = {.open = no_open}; struct address_space *const mapping = &inode->i_data; inode->i_sb = sb; inode->i_blkbits = sb->s_blocksize_bits; inode->i_flags = 0; inode->i_state = 0; atomic64_set(&inode->i_sequence, 0); atomic_set(&inode->i_count, 1); inode->i_op = &empty_iops; inode->i_fop = &no_open_fops; inode->i_ino = 0; inode->__i_nlink = 1; inode->i_opflags = 0; if (sb->s_xattr) inode->i_opflags |= IOP_XATTR; if (sb->s_type->fs_flags & FS_MGTIME) inode->i_opflags |= IOP_MGTIME; i_uid_write(inode, 0); i_gid_write(inode, 0); atomic_set(&inode->i_writecount, 0); inode->i_size = 0; inode->i_write_hint = WRITE_LIFE_NOT_SET; inode->i_blocks = 0; inode->i_bytes = 0; inode->i_generation = 0; inode->i_pipe = NULL; inode->i_cdev = NULL; inode->i_link = NULL; inode->i_dir_seq = 0; inode->i_rdev = 0; inode->dirtied_when = 0; #ifdef CONFIG_CGROUP_WRITEBACK inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; #endif spin_lock_init(&inode->i_lock); lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key); init_rwsem(&inode->i_rwsem); lockdep_set_class(&inode->i_rwsem, &sb->s_type->i_mutex_key); atomic_set(&inode->i_dio_count, 0); mapping->a_ops = &empty_aops; mapping->host = inode; mapping->flags = 0; mapping->wb_err = 0; atomic_set(&mapping->i_mmap_writable, 0); #ifdef CONFIG_READ_ONLY_THP_FOR_FS atomic_set(&mapping->nr_thps, 0); #endif mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE); mapping->i_private_data = NULL; mapping->writeback_index = 0; init_rwsem(&mapping->invalidate_lock); lockdep_set_class_and_name(&mapping->invalidate_lock, &sb->s_type->invalidate_lock_key, "mapping.invalidate_lock"); if (sb->s_iflags & SB_I_STABLE_WRITES) mapping_set_stable_writes(mapping); inode->i_private = NULL; inode->i_mapping = mapping; INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ #ifdef CONFIG_FS_POSIX_ACL inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED; #endif #ifdef CONFIG_FSNOTIFY inode->i_fsnotify_mask = 0; #endif inode->i_flctx = NULL; if (unlikely(security_inode_alloc(inode, gfp))) return -ENOMEM; this_cpu_inc(nr_inodes); return 0; } EXPORT_SYMBOL(inode_init_always_gfp); void free_inode_nonrcu(struct inode *inode) { kmem_cache_free(inode_cachep, inode); } EXPORT_SYMBOL(free_inode_nonrcu); static void i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); if (inode->free_inode) inode->free_inode(inode); else free_inode_nonrcu(inode); } static struct inode *alloc_inode(struct super_block *sb) { const struct super_operations *ops = sb->s_op; struct inode *inode; if (ops->alloc_inode) inode = ops->alloc_inode(sb); else inode = alloc_inode_sb(sb, inode_cachep, GFP_KERNEL); if (!inode) return NULL; if (unlikely(inode_init_always(sb, inode))) { if (ops->destroy_inode) { ops->destroy_inode(inode); if (!ops->free_inode) return NULL; } inode->free_inode = ops->free_inode; i_callback(&inode->i_rcu); return NULL; } return inode; } void __destroy_inode(struct inode *inode) { BUG_ON(inode_has_buffers(inode)); inode_detach_wb(inode); security_inode_free(inode); fsnotify_inode_delete(inode); locks_free_lock_context(inode); if (!inode->i_nlink) { WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0); atomic_long_dec(&inode->i_sb->s_remove_count); } #ifdef CONFIG_FS_POSIX_ACL if (inode->i_acl && !is_uncached_acl(inode->i_acl)) posix_acl_release(inode->i_acl); if (inode->i_default_acl && !is_uncached_acl(inode->i_default_acl)) posix_acl_release(inode->i_default_acl); #endif this_cpu_dec(nr_inodes); } EXPORT_SYMBOL(__destroy_inode); static void destroy_inode(struct inode *inode) { const struct super_operations *ops = inode->i_sb->s_op; BUG_ON(!list_empty(&inode->i_lru)); __destroy_inode(inode); if (ops->destroy_inode) { ops->destroy_inode(inode); if (!ops->free_inode) return; } inode->free_inode = ops->free_inode; call_rcu(&inode->i_rcu, i_callback); } /** * drop_nlink - directly drop an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. In cases * where we are attempting to track writes to the * filesystem, a decrement to zero means an imminent * write when the file is truncated and actually unlinked * on the filesystem. */ void drop_nlink(struct inode *inode) { WARN_ON(inode->i_nlink == 0); inode->__i_nlink--; if (!inode->i_nlink) atomic_long_inc(&inode->i_sb->s_remove_count); } EXPORT_SYMBOL(drop_nlink); /** * clear_nlink - directly zero an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. See * drop_nlink() for why we care about i_nlink hitting zero. */ void clear_nlink(struct inode *inode) { if (inode->i_nlink) { inode->__i_nlink = 0; atomic_long_inc(&inode->i_sb->s_remove_count); } } EXPORT_SYMBOL(clear_nlink); /** * set_nlink - directly set an inode's link count * @inode: inode * @nlink: new nlink (should be non-zero) * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. */ void set_nlink(struct inode *inode, unsigned int nlink) { if (!nlink) { clear_nlink(inode); } else { /* Yes, some filesystems do change nlink from zero to one */ if (inode->i_nlink == 0) atomic_long_dec(&inode->i_sb->s_remove_count); inode->__i_nlink = nlink; } } EXPORT_SYMBOL(set_nlink); /** * inc_nlink - directly increment an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. Currently, * it is only here for parity with dec_nlink(). */ void inc_nlink(struct inode *inode) { if (unlikely(inode->i_nlink == 0)) { WARN_ON(!(inode->i_state & I_LINKABLE)); atomic_long_dec(&inode->i_sb->s_remove_count); } inode->__i_nlink++; } EXPORT_SYMBOL(inc_nlink); static void __address_space_init_once(struct address_space *mapping) { xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT); init_rwsem(&mapping->i_mmap_rwsem); INIT_LIST_HEAD(&mapping->i_private_list); spin_lock_init(&mapping->i_private_lock); mapping->i_mmap = RB_ROOT_CACHED; } void address_space_init_once(struct address_space *mapping) { memset(mapping, 0, sizeof(*mapping)); __address_space_init_once(mapping); } EXPORT_SYMBOL(address_space_init_once); /* * These are initializations that only need to be done * once, because the fields are idempotent across use * of the inode, so let the slab aware of that. */ void inode_init_once(struct inode *inode) { memset(inode, 0, sizeof(*inode)); INIT_HLIST_NODE(&inode->i_hash); INIT_LIST_HEAD(&inode->i_devices); INIT_LIST_HEAD(&inode->i_io_list); INIT_LIST_HEAD(&inode->i_wb_list); INIT_LIST_HEAD(&inode->i_lru); INIT_LIST_HEAD(&inode->i_sb_list); __address_space_init_once(&inode->i_data); i_size_ordered_init(inode); } EXPORT_SYMBOL(inode_init_once); static void init_once(void *foo) { struct inode *inode = (struct inode *) foo; inode_init_once(inode); } /* * get additional reference to inode; caller must already hold one. */ void ihold(struct inode *inode) { WARN_ON(atomic_inc_return(&inode->i_count) < 2); } EXPORT_SYMBOL(ihold); static void __inode_add_lru(struct inode *inode, bool rotate) { if (inode->i_state & (I_DIRTY_ALL | I_SYNC | I_FREEING | I_WILL_FREE)) return; if (atomic_read(&inode->i_count)) return; if (!(inode->i_sb->s_flags & SB_ACTIVE)) return; if (!mapping_shrinkable(&inode->i_data)) return; if (list_lru_add_obj(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_inc(nr_unused); else if (rotate) inode->i_state |= I_REFERENCED; } struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe, struct inode *inode, u32 bit) { void *bit_address; bit_address = inode_state_wait_address(inode, bit); init_wait_var_entry(wqe, bit_address, 0); return __var_waitqueue(bit_address); } EXPORT_SYMBOL(inode_bit_waitqueue); /* * Add inode to LRU if needed (inode is unused and clean). * * Needs inode->i_lock held. */ void inode_add_lru(struct inode *inode) { __inode_add_lru(inode, false); } static void inode_lru_list_del(struct inode *inode) { if (list_lru_del_obj(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_dec(nr_unused); } static void inode_pin_lru_isolating(struct inode *inode) { lockdep_assert_held(&inode->i_lock); WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE)); inode->i_state |= I_LRU_ISOLATING; } static void inode_unpin_lru_isolating(struct inode *inode) { spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_LRU_ISOLATING)); inode->i_state &= ~I_LRU_ISOLATING; /* Called with inode->i_lock which ensures memory ordering. */ inode_wake_up_bit(inode, __I_LRU_ISOLATING); spin_unlock(&inode->i_lock); } static void inode_wait_for_lru_isolating(struct inode *inode) { struct wait_bit_queue_entry wqe; struct wait_queue_head *wq_head; lockdep_assert_held(&inode->i_lock); if (!(inode->i_state & I_LRU_ISOLATING)) return; wq_head = inode_bit_waitqueue(&wqe, inode, __I_LRU_ISOLATING); for (;;) { prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); /* * Checking I_LRU_ISOLATING with inode->i_lock guarantees * memory ordering. */ if (!(inode->i_state & I_LRU_ISOLATING)) break; spin_unlock(&inode->i_lock); schedule(); spin_lock(&inode->i_lock); } finish_wait(wq_head, &wqe.wq_entry); WARN_ON(inode->i_state & I_LRU_ISOLATING); } /** * inode_sb_list_add - add inode to the superblock list of inodes * @inode: inode to add */ void inode_sb_list_add(struct inode *inode) { spin_lock(&inode->i_sb->s_inode_list_lock); list_add(&inode->i_sb_list, &inode->i_sb->s_inodes); spin_unlock(&inode->i_sb->s_inode_list_lock); } EXPORT_SYMBOL_GPL(inode_sb_list_add); static inline void inode_sb_list_del(struct inode *inode) { if (!list_empty(&inode->i_sb_list)) { spin_lock(&inode->i_sb->s_inode_list_lock); list_del_init(&inode->i_sb_list); spin_unlock(&inode->i_sb->s_inode_list_lock); } } static unsigned long hash(struct super_block *sb, unsigned long hashval) { unsigned long tmp; tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) / L1_CACHE_BYTES; tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> i_hash_shift); return tmp & i_hash_mask; } /** * __insert_inode_hash - hash an inode * @inode: unhashed inode * @hashval: unsigned long value used to locate this object in the * inode_hashtable. * * Add an inode to the inode hash for this superblock. */ void __insert_inode_hash(struct inode *inode, unsigned long hashval) { struct hlist_head *b = inode_hashtable + hash(inode->i_sb, hashval); spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); hlist_add_head_rcu(&inode->i_hash, b); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(__insert_inode_hash); /** * __remove_inode_hash - remove an inode from the hash * @inode: inode to unhash * * Remove an inode from the superblock. */ void __remove_inode_hash(struct inode *inode) { spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); hlist_del_init_rcu(&inode->i_hash); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(__remove_inode_hash); void dump_mapping(const struct address_space *mapping) { struct inode *host; const struct address_space_operations *a_ops; struct hlist_node *dentry_first; struct dentry *dentry_ptr; struct dentry dentry; char fname[64] = {}; unsigned long ino; /* * If mapping is an invalid pointer, we don't want to crash * accessing it, so probe everything depending on it carefully. */ if (get_kernel_nofault(host, &mapping->host) || get_kernel_nofault(a_ops, &mapping->a_ops)) { pr_warn("invalid mapping:%px\n", mapping); return; } if (!host) { pr_warn("aops:%ps\n", a_ops); return; } if (get_kernel_nofault(dentry_first, &host->i_dentry.first) || get_kernel_nofault(ino, &host->i_ino)) { pr_warn("aops:%ps invalid inode:%px\n", a_ops, host); return; } if (!dentry_first) { pr_warn("aops:%ps ino:%lx\n", a_ops, ino); return; } dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias); if (get_kernel_nofault(dentry, dentry_ptr) || !dentry.d_parent || !dentry.d_name.name) { pr_warn("aops:%ps ino:%lx invalid dentry:%px\n", a_ops, ino, dentry_ptr); return; } if (strncpy_from_kernel_nofault(fname, dentry.d_name.name, 63) < 0) strscpy(fname, "<invalid>"); /* * Even if strncpy_from_kernel_nofault() succeeded, * the fname could be unreliable */ pr_warn("aops:%ps ino:%lx dentry name(?):\"%s\"\n", a_ops, ino, fname); } void clear_inode(struct inode *inode) { /* * We have to cycle the i_pages lock here because reclaim can be in the * process of removing the last page (in __filemap_remove_folio()) * and we must not free the mapping under it. */ xa_lock_irq(&inode->i_data.i_pages); BUG_ON(inode->i_data.nrpages); /* * Almost always, mapping_empty(&inode->i_data) here; but there are * two known and long-standing ways in which nodes may get left behind * (when deep radix-tree node allocation failed partway; or when THP * collapse_file() failed). Until those two known cases are cleaned up, * or a cleanup function is called here, do not BUG_ON(!mapping_empty), * nor even WARN_ON(!mapping_empty). */ xa_unlock_irq(&inode->i_data.i_pages); BUG_ON(!list_empty(&inode->i_data.i_private_list)); BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(inode->i_state & I_CLEAR); BUG_ON(!list_empty(&inode->i_wb_list)); /* don't need i_lock here, no concurrent mods to i_state */ inode->i_state = I_FREEING | I_CLEAR; } EXPORT_SYMBOL(clear_inode); /* * Free the inode passed in, removing it from the lists it is still connected * to. We remove any pages still attached to the inode and wait for any IO that * is still in progress before finally destroying the inode. * * An inode must already be marked I_FREEING so that we avoid the inode being * moved back onto lists if we race with other code that manipulates the lists * (e.g. writeback_single_inode). The caller is responsible for setting this. * * An inode must already be removed from the LRU list before being evicted from * the cache. This should occur atomically with setting the I_FREEING state * flag, so no inodes here should ever be on the LRU when being evicted. */ static void evict(struct inode *inode) { const struct super_operations *op = inode->i_sb->s_op; BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(!list_empty(&inode->i_lru)); if (!list_empty(&inode->i_io_list)) inode_io_list_del(inode); inode_sb_list_del(inode); spin_lock(&inode->i_lock); inode_wait_for_lru_isolating(inode); /* * Wait for flusher thread to be done with the inode so that filesystem * does not start destroying it while writeback is still running. Since * the inode has I_FREEING set, flusher thread won't start new work on * the inode. We just have to wait for running writeback to finish. */ inode_wait_for_writeback(inode); spin_unlock(&inode->i_lock); if (op->evict_inode) { op->evict_inode(inode); } else { truncate_inode_pages_final(&inode->i_data); clear_inode(inode); } if (S_ISCHR(inode->i_mode) && inode->i_cdev) cd_forget(inode); remove_inode_hash(inode); /* * Wake up waiters in __wait_on_freeing_inode(). * * Lockless hash lookup may end up finding the inode before we removed * it above, but only lock it *after* we are done with the wakeup below. * In this case the potential waiter cannot safely block. * * The inode being unhashed after the call to remove_inode_hash() is * used as an indicator whether blocking on it is safe. */ spin_lock(&inode->i_lock); /* * Pairs with the barrier in prepare_to_wait_event() to make sure * ___wait_var_event() either sees the bit cleared or * waitqueue_active() check in wake_up_var() sees the waiter. */ smp_mb__after_spinlock(); inode_wake_up_bit(inode, __I_NEW); BUG_ON(inode->i_state != (I_FREEING | I_CLEAR)); spin_unlock(&inode->i_lock); destroy_inode(inode); } /* * dispose_list - dispose of the contents of a local list * @head: the head of the list to free * * Dispose-list gets a local list with local inodes in it, so it doesn't * need to worry about list corruption and SMP locks. */ static void dispose_list(struct list_head *head) { while (!list_empty(head)) { struct inode *inode; inode = list_first_entry(head, struct inode, i_lru); list_del_init(&inode->i_lru); evict(inode); cond_resched(); } } /** * evict_inodes - evict all evictable inodes for a superblock * @sb: superblock to operate on * * Make sure that no inodes with zero refcount are retained. This is * called by superblock shutdown after having SB_ACTIVE flag removed, * so any inode reaching zero refcount during or after that call will * be immediately evicted. */ void evict_inodes(struct super_block *sb) { struct inode *inode, *next; LIST_HEAD(dispose); again: spin_lock(&sb->s_inode_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { if (atomic_read(&inode->i_count)) continue; spin_lock(&inode->i_lock); if (atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); continue; } if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); continue; } inode->i_state |= I_FREEING; inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); /* * We can have a ton of inodes to evict at unmount time given * enough memory, check to see if we need to go to sleep for a * bit so we don't livelock. */ if (need_resched()) { spin_unlock(&sb->s_inode_list_lock); cond_resched(); dispose_list(&dispose); goto again; } } spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); } EXPORT_SYMBOL_GPL(evict_inodes); /** * invalidate_inodes - attempt to free all inodes on a superblock * @sb: superblock to operate on * * Attempts to free all inodes (including dirty inodes) for a given superblock. */ void invalidate_inodes(struct super_block *sb) { struct inode *inode, *next; LIST_HEAD(dispose); again: spin_lock(&sb->s_inode_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); continue; } if (atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); continue; } inode->i_state |= I_FREEING; inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); if (need_resched()) { spin_unlock(&sb->s_inode_list_lock); cond_resched(); dispose_list(&dispose); goto again; } } spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); } /* * Isolate the inode from the LRU in preparation for freeing it. * * If the inode has the I_REFERENCED flag set, then it means that it has been * used recently - the flag is set in iput_final(). When we encounter such an * inode, clear the flag and move it to the back of the LRU so it gets another * pass through the LRU before it gets reclaimed. This is necessary because of * the fact we are doing lazy LRU updates to minimise lock contention so the * LRU does not have strict ordering. Hence we don't want to reclaim inodes * with this flag set because they are the inodes that are out of order. */ static enum lru_status inode_lru_isolate(struct list_head *item, struct list_lru_one *lru, void *arg) { struct list_head *freeable = arg; struct inode *inode = container_of(item, struct inode, i_lru); /* * We are inverting the lru lock/inode->i_lock here, so use a * trylock. If we fail to get the lock, just skip it. */ if (!spin_trylock(&inode->i_lock)) return LRU_SKIP; /* * Inodes can get referenced, redirtied, or repopulated while * they're already on the LRU, and this can make them * unreclaimable for a while. Remove them lazily here; iput, * sync, or the last page cache deletion will requeue them. */ if (atomic_read(&inode->i_count) || (inode->i_state & ~I_REFERENCED) || !mapping_shrinkable(&inode->i_data)) { list_lru_isolate(lru, &inode->i_lru); spin_unlock(&inode->i_lock); this_cpu_dec(nr_unused); return LRU_REMOVED; } /* Recently referenced inodes get one more pass */ if (inode->i_state & I_REFERENCED) { inode->i_state &= ~I_REFERENCED; spin_unlock(&inode->i_lock); return LRU_ROTATE; } /* * On highmem systems, mapping_shrinkable() permits dropping * page cache in order to free up struct inodes: lowmem might * be under pressure before the cache inside the highmem zone. */ if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) { inode_pin_lru_isolating(inode); spin_unlock(&inode->i_lock); spin_unlock(&lru->lock); if (remove_inode_buffers(inode)) { unsigned long reap; reap = invalidate_mapping_pages(&inode->i_data, 0, -1); if (current_is_kswapd()) __count_vm_events(KSWAPD_INODESTEAL, reap); else __count_vm_events(PGINODESTEAL, reap); mm_account_reclaimed_pages(reap); } inode_unpin_lru_isolating(inode); return LRU_RETRY; } WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; list_lru_isolate_move(lru, &inode->i_lru, freeable); spin_unlock(&inode->i_lock); this_cpu_dec(nr_unused); return LRU_REMOVED; } /* * Walk the superblock inode LRU for freeable inodes and attempt to free them. * This is called from the superblock shrinker function with a number of inodes * to trim from the LRU. Inodes to be freed are moved to a temporary list and * then are freed outside inode_lock by dispose_list(). */ long prune_icache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(freeable); long freed; freed = list_lru_shrink_walk(&sb->s_inode_lru, sc, inode_lru_isolate, &freeable); dispose_list(&freeable); return freed; } static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_locked); /* * Called with the inode lock held. */ static struct inode *find_inode(struct super_block *sb, struct hlist_head *head, int (*test)(struct inode *, void *), void *data, bool is_inode_hash_locked) { struct inode *inode = NULL; if (is_inode_hash_locked) lockdep_assert_held(&inode_hash_lock); else lockdep_assert_not_held(&inode_hash_lock); rcu_read_lock(); repeat: hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_sb != sb) continue; if (!test(inode, data)) continue; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE)) { __wait_on_freeing_inode(inode, is_inode_hash_locked); goto repeat; } if (unlikely(inode->i_state & I_CREATING)) { spin_unlock(&inode->i_lock); rcu_read_unlock(); return ERR_PTR(-ESTALE); } __iget(inode); spin_unlock(&inode->i_lock); rcu_read_unlock(); return inode; } rcu_read_unlock(); return NULL; } /* * find_inode_fast is the fast path version of find_inode, see the comment at * iget_locked for details. */ static struct inode *find_inode_fast(struct super_block *sb, struct hlist_head *head, unsigned long ino, bool is_inode_hash_locked) { struct inode *inode = NULL; if (is_inode_hash_locked) lockdep_assert_held(&inode_hash_lock); else lockdep_assert_not_held(&inode_hash_lock); rcu_read_lock(); repeat: hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_ino != ino) continue; if (inode->i_sb != sb) continue; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE)) { __wait_on_freeing_inode(inode, is_inode_hash_locked); goto repeat; } if (unlikely(inode->i_state & I_CREATING)) { spin_unlock(&inode->i_lock); rcu_read_unlock(); return ERR_PTR(-ESTALE); } __iget(inode); spin_unlock(&inode->i_lock); rcu_read_unlock(); return inode; } rcu_read_unlock(); return NULL; } /* * Each cpu owns a range of LAST_INO_BATCH numbers. * 'shared_last_ino' is dirtied only once out of LAST_INO_BATCH allocations, * to renew the exhausted range. * * This does not significantly increase overflow rate because every CPU can * consume at most LAST_INO_BATCH-1 unused inode numbers. So there is * NR_CPUS*(LAST_INO_BATCH-1) wastage. At 4096 and 1024, this is ~0.1% of the * 2^32 range, and is a worst-case. Even a 50% wastage would only increase * overflow rate by 2x, which does not seem too significant. * * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW * error if st_ino won't fit in target struct field. Use 32bit counter * here to attempt to avoid that. */ #define LAST_INO_BATCH 1024 static DEFINE_PER_CPU(unsigned int, last_ino); unsigned int get_next_ino(void) { unsigned int *p = &get_cpu_var(last_ino); unsigned int res = *p; #ifdef CONFIG_SMP if (unlikely((res & (LAST_INO_BATCH-1)) == 0)) { static atomic_t shared_last_ino; int next = atomic_add_return(LAST_INO_BATCH, &shared_last_ino); res = next - LAST_INO_BATCH; } #endif res++; /* get_next_ino should not provide a 0 inode number */ if (unlikely(!res)) res++; *p = res; put_cpu_var(last_ino); return res; } EXPORT_SYMBOL(get_next_ino); /** * new_inode_pseudo - obtain an inode * @sb: superblock * * Allocates a new inode for given superblock. * Inode wont be chained in superblock s_inodes list * This means : * - fs can't be unmount * - quotas, fsnotify, writeback can't work */ struct inode *new_inode_pseudo(struct super_block *sb) { return alloc_inode(sb); } /** * new_inode - obtain an inode * @sb: superblock * * Allocates a new inode for given superblock. The default gfp_mask * for allocations related to inode->i_mapping is GFP_HIGHUSER_MOVABLE. * If HIGHMEM pages are unsuitable or it is known that pages allocated * for the page cache are not reclaimable or migratable, * mapping_set_gfp_mask() must be called with suitable flags on the * newly created inode's mapping * */ struct inode *new_inode(struct super_block *sb) { struct inode *inode; inode = new_inode_pseudo(sb); if (inode) inode_sb_list_add(inode); return inode; } EXPORT_SYMBOL(new_inode); #ifdef CONFIG_DEBUG_LOCK_ALLOC void lockdep_annotate_inode_mutex_key(struct inode *inode) { if (S_ISDIR(inode->i_mode)) { struct file_system_type *type = inode->i_sb->s_type; /* Set new key only if filesystem hasn't already changed it */ if (lockdep_match_class(&inode->i_rwsem, &type->i_mutex_key)) { /* * ensure nobody is actually holding i_mutex */ // mutex_destroy(&inode->i_mutex); init_rwsem(&inode->i_rwsem); lockdep_set_class(&inode->i_rwsem, &type->i_mutex_dir_key); } } } EXPORT_SYMBOL(lockdep_annotate_inode_mutex_key); #endif /** * unlock_new_inode - clear the I_NEW state and wake up any waiters * @inode: new inode to unlock * * Called when the inode is fully initialised to clear the new state of the * inode and wake up anyone waiting for the inode to finish initialisation. */ void unlock_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; /* * Pairs with the barrier in prepare_to_wait_event() to make sure * ___wait_var_event() either sees the bit cleared or * waitqueue_active() check in wake_up_var() sees the waiter. */ smp_mb(); inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(unlock_new_inode); void discard_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW; /* * Pairs with the barrier in prepare_to_wait_event() to make sure * ___wait_var_event() either sees the bit cleared or * waitqueue_active() check in wake_up_var() sees the waiter. */ smp_mb(); inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); iput(inode); } EXPORT_SYMBOL(discard_new_inode); /** * lock_two_nondirectories - take two i_mutexes on non-directory objects * * Lock any non-NULL argument. Passed objects must not be directories. * Zero, one or two objects may be locked by this function. * * @inode1: first inode to lock * @inode2: second inode to lock */ void lock_two_nondirectories(struct inode *inode1, struct inode *inode2) { if (inode1) WARN_ON_ONCE(S_ISDIR(inode1->i_mode)); if (inode2) WARN_ON_ONCE(S_ISDIR(inode2->i_mode)); if (inode1 > inode2) swap(inode1, inode2); if (inode1) inode_lock(inode1); if (inode2 && inode2 != inode1) inode_lock_nested(inode2, I_MUTEX_NONDIR2); } EXPORT_SYMBOL(lock_two_nondirectories); /** * unlock_two_nondirectories - release locks from lock_two_nondirectories() * @inode1: first inode to unlock * @inode2: second inode to unlock */ void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2) { if (inode1) { WARN_ON_ONCE(S_ISDIR(inode1->i_mode)); inode_unlock(inode1); } if (inode2 && inode2 != inode1) { WARN_ON_ONCE(S_ISDIR(inode2->i_mode)); inode_unlock(inode2); } } EXPORT_SYMBOL(unlock_two_nondirectories); /** * inode_insert5 - obtain an inode from a mounted file system * @inode: pre-allocated inode to use for insert to cache * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * * Search for the inode specified by @hashval and @data in the inode cache, * and if present return it with an increased reference count. This is a * variant of iget5_locked() that doesn't allocate an inode. * * If the inode is not present in the cache, insert the pre-allocated inode and * return it locked, hashed, and with the I_NEW flag set. The file system gets * to fill it in before unlocking it via unlock_new_inode(). * * Note that both @test and @set are called with the inode_hash_lock held, so * they can't sleep. */ struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval); struct inode *old; again: spin_lock(&inode_hash_lock); old = find_inode(inode->i_sb, head, test, data, true); if (unlikely(old)) { /* * Uhhuh, somebody else created the same inode under us. * Use the old inode instead of the preallocated one. */ spin_unlock(&inode_hash_lock); if (IS_ERR(old)) return NULL; wait_on_inode(old); if (unlikely(inode_unhashed(old))) { iput(old); goto again; } return old; } if (set && unlikely(set(inode, data))) { inode = NULL; goto unlock; } /* * Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents */ spin_lock(&inode->i_lock); inode->i_state |= I_NEW; hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); /* * Add inode to the sb list if it's not already. It has I_NEW at this * point, so it should be safe to test i_sb_list locklessly. */ if (list_empty(&inode->i_sb_list)) inode_sb_list_add(inode); unlock: spin_unlock(&inode_hash_lock); return inode; } EXPORT_SYMBOL(inode_insert5); /** * iget5_locked - obtain an inode from a mounted file system * @sb: super block of file system * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * * Search for the inode specified by @hashval and @data in the inode cache, * and if present return it with an increased reference count. This is a * generalized version of iget_locked() for file systems where the inode * number is not sufficient for unique identification of an inode. * * If the inode is not present in the cache, allocate and insert a new inode * and return it locked, hashed, and with the I_NEW flag set. The file system * gets to fill it in before unlocking it via unlock_new_inode(). * * Note that both @test and @set are called with the inode_hash_lock held, so * they can't sleep. */ struct inode *iget5_locked(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct inode *inode = ilookup5(sb, hashval, test, data); if (!inode) { struct inode *new = alloc_inode(sb); if (new) { inode = inode_insert5(new, hashval, test, set, data); if (unlikely(inode != new)) destroy_inode(new); } } return inode; } EXPORT_SYMBOL(iget5_locked); /** * iget5_locked_rcu - obtain an inode from a mounted file system * @sb: super block of file system * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * * This is equivalent to iget5_locked, except the @test callback must * tolerate the inode not being stable, including being mid-teardown. */ struct inode *iget5_locked_rcu(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode, *new; again: inode = find_inode(sb, head, test, data, false); if (inode) { if (IS_ERR(inode)) return NULL; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } return inode; } new = alloc_inode(sb); if (new) { inode = inode_insert5(new, hashval, test, set, data); if (unlikely(inode != new)) destroy_inode(new); } return inode; } EXPORT_SYMBOL_GPL(iget5_locked_rcu); /** * iget_locked - obtain an inode from a mounted file system * @sb: super block of file system * @ino: inode number to get * * Search for the inode specified by @ino in the inode cache and if present * return it with an increased reference count. This is for file systems * where the inode number is sufficient for unique identification of an inode. * * If the inode is not in cache, allocate a new inode and return it locked, * hashed, and with the I_NEW flag set. The file system gets to fill it in * before unlocking it via unlock_new_inode(). */ struct inode *iget_locked(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; again: inode = find_inode_fast(sb, head, ino, false); if (inode) { if (IS_ERR(inode)) return NULL; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } return inode; } inode = alloc_inode(sb); if (inode) { struct inode *old; spin_lock(&inode_hash_lock); /* We released the lock, so.. */ old = find_inode_fast(sb, head, ino, true); if (!old) { inode->i_ino = ino; spin_lock(&inode->i_lock); inode->i_state = I_NEW; hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); inode_sb_list_add(inode); spin_unlock(&inode_hash_lock); /* Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents */ return inode; } /* * Uhhuh, somebody else created the same inode under * us. Use the old inode instead of the one we just * allocated. */ spin_unlock(&inode_hash_lock); destroy_inode(inode); if (IS_ERR(old)) return NULL; inode = old; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(iget_locked); /* * search the inode cache for a matching inode number. * If we find one, then the inode number we are trying to * allocate is not unique and so we should not use it. * * Returns 1 if the inode number is unique, 0 if it is not. */ static int test_inode_iunique(struct super_block *sb, unsigned long ino) { struct hlist_head *b = inode_hashtable + hash(sb, ino); struct inode *inode; hlist_for_each_entry_rcu(inode, b, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb) return 0; } return 1; } /** * iunique - get a unique inode number * @sb: superblock * @max_reserved: highest reserved inode number * * Obtain an inode number that is unique on the system for a given * superblock. This is used by file systems that have no natural * permanent inode numbering system. An inode number is returned that * is higher than the reserved limit but unique. * * BUGS: * With a large number of inodes live on the file system this function * currently becomes quite slow. */ ino_t iunique(struct super_block *sb, ino_t max_reserved) { /* * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW * error if st_ino won't fit in target struct field. Use 32bit counter * here to attempt to avoid that. */ static DEFINE_SPINLOCK(iunique_lock); static unsigned int counter; ino_t res; rcu_read_lock(); spin_lock(&iunique_lock); do { if (counter <= max_reserved) counter = max_reserved + 1; res = counter++; } while (!test_inode_iunique(sb, res)); spin_unlock(&iunique_lock); rcu_read_unlock(); return res; } EXPORT_SYMBOL(iunique); struct inode *igrab(struct inode *inode) { spin_lock(&inode->i_lock); if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) { __iget(inode); spin_unlock(&inode->i_lock); } else { spin_unlock(&inode->i_lock); /* * Handle the case where s_op->clear_inode is not been * called yet, and somebody is calling igrab * while the inode is getting freed. */ inode = NULL; } return inode; } EXPORT_SYMBOL(igrab); /** * ilookup5_nowait - search for an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test * * Search for the inode specified by @hashval and @data in the inode cache. * If the inode is in the cache, the inode is returned with an incremented * reference count. * * Note: I_NEW is not waited upon so you have to be very careful what you do * with the returned inode. You probably should be using ilookup5() instead. * * Note2: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode; spin_lock(&inode_hash_lock); inode = find_inode(sb, head, test, data, true); spin_unlock(&inode_hash_lock); return IS_ERR(inode) ? NULL : inode; } EXPORT_SYMBOL(ilookup5_nowait); /** * ilookup5 - search for an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test * * Search for the inode specified by @hashval and @data in the inode cache, * and if the inode is in the cache, return the inode with an incremented * reference count. Waits on I_NEW before returning the inode. * returned with an incremented reference count. * * This is a generalized version of ilookup() for file systems where the * inode number is not sufficient for unique identification of an inode. * * Note: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct inode *inode; again: inode = ilookup5_nowait(sb, hashval, test, data); if (inode) { wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(ilookup5); /** * ilookup - search for an inode in the inode cache * @sb: super block of file system to search * @ino: inode number to search for * * Search for the inode @ino in the inode cache, and if the inode is in the * cache, the inode is returned with an incremented reference count. */ struct inode *ilookup(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; again: inode = find_inode_fast(sb, head, ino, false); if (inode) { if (IS_ERR(inode)) return NULL; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(ilookup); /** * find_inode_nowait - find an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @match: callback used for comparisons between inodes * @data: opaque data pointer to pass to @match * * Search for the inode specified by @hashval and @data in the inode * cache, where the helper function @match will return 0 if the inode * does not match, 1 if the inode does match, and -1 if the search * should be stopped. The @match function must be responsible for * taking the i_lock spin_lock and checking i_state for an inode being * freed or being initialized, and incrementing the reference count * before returning 1. It also must not sleep, since it is called with * the inode_hash_lock spinlock held. * * This is a even more generalized version of ilookup5() when the * function must never block --- find_inode() can block in * __wait_on_freeing_inode() --- or when the caller can not increment * the reference count because the resulting iput() might cause an * inode eviction. The tradeoff is that the @match funtion must be * very carefully implemented. */ struct inode *find_inode_nowait(struct super_block *sb, unsigned long hashval, int (*match)(struct inode *, unsigned long, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode, *ret_inode = NULL; int mval; spin_lock(&inode_hash_lock); hlist_for_each_entry(inode, head, i_hash) { if (inode->i_sb != sb) continue; mval = match(inode, hashval, data); if (mval == 0) continue; if (mval == 1) ret_inode = inode; goto out; } out: spin_unlock(&inode_hash_lock); return ret_inode; } EXPORT_SYMBOL(find_inode_nowait); /** * find_inode_rcu - find an inode in the inode cache * @sb: Super block of file system to search * @hashval: Key to hash * @test: Function to test match on an inode * @data: Data for test function * * Search for the inode specified by @hashval and @data in the inode cache, * where the helper function @test will return 0 if the inode does not match * and 1 if it does. The @test function must be responsible for taking the * i_lock spin_lock and checking i_state for an inode being freed or being * initialized. * * If successful, this will return the inode for which the @test function * returned 1 and NULL otherwise. * * The @test function is not permitted to take a ref on any inode presented. * It is also not permitted to sleep. * * The caller must hold the RCU read lock. */ struct inode *find_inode_rcu(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious find_inode_rcu() usage"); hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_sb == sb && !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE)) && test(inode, data)) return inode; } return NULL; } EXPORT_SYMBOL(find_inode_rcu); /** * find_inode_by_ino_rcu - Find an inode in the inode cache * @sb: Super block of file system to search * @ino: The inode number to match * * Search for the inode specified by @hashval and @data in the inode cache, * where the helper function @test will return 0 if the inode does not match * and 1 if it does. The @test function must be responsible for taking the * i_lock spin_lock and checking i_state for an inode being freed or being * initialized. * * If successful, this will return the inode for which the @test function * returned 1 and NULL otherwise. * * The @test function is not permitted to take a ref on any inode presented. * It is also not permitted to sleep. * * The caller must hold the RCU read lock. */ struct inode *find_inode_by_ino_rcu(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious find_inode_by_ino_rcu() usage"); hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb && !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE))) return inode; } return NULL; } EXPORT_SYMBOL(find_inode_by_ino_rcu); int insert_inode_locked(struct inode *inode) { struct super_block *sb = inode->i_sb; ino_t ino = inode->i_ino; struct hlist_head *head = inode_hashtable + hash(sb, ino); while (1) { struct inode *old = NULL; spin_lock(&inode_hash_lock); hlist_for_each_entry(old, head, i_hash) { if (old->i_ino != ino) continue; if (old->i_sb != sb) continue; spin_lock(&old->i_lock); if (old->i_state & (I_FREEING|I_WILL_FREE)) { spin_unlock(&old->i_lock); continue; } break; } if (likely(!old)) { spin_lock(&inode->i_lock); inode->i_state |= I_NEW | I_CREATING; hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); return 0; } if (unlikely(old->i_state & I_CREATING)) { spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); return -EBUSY; } __iget(old); spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); wait_on_inode(old); if (unlikely(!inode_unhashed(old))) { iput(old); return -EBUSY; } iput(old); } } EXPORT_SYMBOL(insert_inode_locked); int insert_inode_locked4(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct inode *old; inode->i_state |= I_CREATING; old = inode_insert5(inode, hashval, test, NULL, data); if (old != inode) { iput(old); return -EBUSY; } return 0; } EXPORT_SYMBOL(insert_inode_locked4); int generic_delete_inode(struct inode *inode) { return 1; } EXPORT_SYMBOL(generic_delete_inode); /* * Called when we're dropping the last reference * to an inode. * * Call the FS "drop_inode()" function, defaulting to * the legacy UNIX filesystem behaviour. If it tells * us to evict inode, do so. Otherwise, retain inode * in cache if fs is alive, sync and evict if fs is * shutting down. */ static void iput_final(struct inode *inode) { struct super_block *sb = inode->i_sb; const struct super_operations *op = inode->i_sb->s_op; unsigned long state; int drop; WARN_ON(inode->i_state & I_NEW); if (op->drop_inode) drop = op->drop_inode(inode); else drop = generic_drop_inode(inode); if (!drop && !(inode->i_state & I_DONTCACHE) && (sb->s_flags & SB_ACTIVE)) { __inode_add_lru(inode, true); spin_unlock(&inode->i_lock); return; } state = inode->i_state; if (!drop) { WRITE_ONCE(inode->i_state, state | I_WILL_FREE); spin_unlock(&inode->i_lock); write_inode_now(inode, 1); spin_lock(&inode->i_lock); state = inode->i_state; WARN_ON(state & I_NEW); state &= ~I_WILL_FREE; } WRITE_ONCE(inode->i_state, state | I_FREEING); if (!list_empty(&inode->i_lru)) inode_lru_list_del(inode); spin_unlock(&inode->i_lock); evict(inode); } /** * iput - put an inode * @inode: inode to put * * Puts an inode, dropping its usage count. If the inode use count hits * zero, the inode is then freed and may also be destroyed. * * Consequently, iput() can sleep. */ void iput(struct inode *inode) { if (!inode) return; BUG_ON(inode->i_state & I_CLEAR); retry: if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock)) { if (inode->i_nlink && (inode->i_state & I_DIRTY_TIME)) { atomic_inc(&inode->i_count); spin_unlock(&inode->i_lock); trace_writeback_lazytime_iput(inode); mark_inode_dirty_sync(inode); goto retry; } iput_final(inode); } } EXPORT_SYMBOL(iput); #ifdef CONFIG_BLOCK /** * bmap - find a block number in a file * @inode: inode owning the block number being requested * @block: pointer containing the block to find * * Replaces the value in ``*block`` with the block number on the device holding * corresponding to the requested block number in the file. * That is, asked for block 4 of inode 1 the function will replace the * 4 in ``*block``, with disk block relative to the disk start that holds that * block of the file. * * Returns -EINVAL in case of error, 0 otherwise. If mapping falls into a * hole, returns 0 and ``*block`` is also set to 0. */ int bmap(struct inode *inode, sector_t *block) { if (!inode->i_mapping->a_ops->bmap) return -EINVAL; *block = inode->i_mapping->a_ops->bmap(inode->i_mapping, *block); return 0; } EXPORT_SYMBOL(bmap); #endif /* * With relative atime, only update atime if the previous atime is * earlier than or equal to either the ctime or mtime, * or if at least a day has passed since the last atime update. */ static bool relatime_need_update(struct vfsmount *mnt, struct inode *inode, struct timespec64 now) { struct timespec64 atime, mtime, ctime; if (!(mnt->mnt_flags & MNT_RELATIME)) return true; /* * Is mtime younger than or equal to atime? If yes, update atime: */ atime = inode_get_atime(inode); mtime = inode_get_mtime(inode); if (timespec64_compare(&mtime, &atime) >= 0) return true; /* * Is ctime younger than or equal to atime? If yes, update atime: */ ctime = inode_get_ctime(inode); if (timespec64_compare(&ctime, &atime) >= 0) return true; /* * Is the previous atime value older than a day? If yes, * update atime: */ if ((long)(now.tv_sec - atime.tv_sec) >= 24*60*60) return true; /* * Good, we can skip the atime update: */ return false; } /** * inode_update_timestamps - update the timestamps on the inode * @inode: inode to be updated * @flags: S_* flags that needed to be updated * * The update_time function is called when an inode's timestamps need to be * updated for a read or write operation. This function handles updating the * actual timestamps. It's up to the caller to ensure that the inode is marked * dirty appropriately. * * In the case where any of S_MTIME, S_CTIME, or S_VERSION need to be updated, * attempt to update all three of them. S_ATIME updates can be handled * independently of the rest. * * Returns a set of S_* flags indicating which values changed. */ int inode_update_timestamps(struct inode *inode, int flags) { int updated = 0; struct timespec64 now; if (flags & (S_MTIME|S_CTIME|S_VERSION)) { struct timespec64 ctime = inode_get_ctime(inode); struct timespec64 mtime = inode_get_mtime(inode); now = inode_set_ctime_current(inode); if (!timespec64_equal(&now, &ctime)) updated |= S_CTIME; if (!timespec64_equal(&now, &mtime)) { inode_set_mtime_to_ts(inode, now); updated |= S_MTIME; } if (IS_I_VERSION(inode) && inode_maybe_inc_iversion(inode, updated)) updated |= S_VERSION; } else { now = current_time(inode); } if (flags & S_ATIME) { struct timespec64 atime = inode_get_atime(inode); if (!timespec64_equal(&now, &atime)) { inode_set_atime_to_ts(inode, now); updated |= S_ATIME; } } return updated; } EXPORT_SYMBOL(inode_update_timestamps); /** * generic_update_time - update the timestamps on the inode * @inode: inode to be updated * @flags: S_* flags that needed to be updated * * The update_time function is called when an inode's timestamps need to be * updated for a read or write operation. In the case where any of S_MTIME, S_CTIME, * or S_VERSION need to be updated we attempt to update all three of them. S_ATIME * updates can be handled done independently of the rest. * * Returns a S_* mask indicating which fields were updated. */ int generic_update_time(struct inode *inode, int flags) { int updated = inode_update_timestamps(inode, flags); int dirty_flags = 0; if (updated & (S_ATIME|S_MTIME|S_CTIME)) dirty_flags = inode->i_sb->s_flags & SB_LAZYTIME ? I_DIRTY_TIME : I_DIRTY_SYNC; if (updated & S_VERSION) dirty_flags |= I_DIRTY_SYNC; __mark_inode_dirty(inode, dirty_flags); return updated; } EXPORT_SYMBOL(generic_update_time); /* * This does the actual work of updating an inodes time or version. Must have * had called mnt_want_write() before calling this. */ int inode_update_time(struct inode *inode, int flags) { if (inode->i_op->update_time) return inode->i_op->update_time(inode, flags); generic_update_time(inode, flags); return 0; } EXPORT_SYMBOL(inode_update_time); /** * atime_needs_update - update the access time * @path: the &struct path to update * @inode: inode to update * * Update the accessed time on an inode and mark it for writeback. * This function automatically handles read only file systems and media, * as well as the "noatime" flag and inode specific "noatime" markers. */ bool atime_needs_update(const struct path *path, struct inode *inode) { struct vfsmount *mnt = path->mnt; struct timespec64 now, atime; if (inode->i_flags & S_NOATIME) return false; /* Atime updates will likely cause i_uid and i_gid to be written * back improprely if their true value is unknown to the vfs. */ if (HAS_UNMAPPED_ID(mnt_idmap(mnt), inode)) return false; if (IS_NOATIME(inode)) return false; if ((inode->i_sb->s_flags & SB_NODIRATIME) && S_ISDIR(inode->i_mode)) return false; if (mnt->mnt_flags & MNT_NOATIME) return false; if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)) return false; now = current_time(inode); if (!relatime_need_update(mnt, inode, now)) return false; atime = inode_get_atime(inode); if (timespec64_equal(&atime, &now)) return false; return true; } void touch_atime(const struct path *path) { struct vfsmount *mnt = path->mnt; struct inode *inode = d_inode(path->dentry); if (!atime_needs_update(path, inode)) return; if (!sb_start_write_trylock(inode->i_sb)) return; if (mnt_get_write_access(mnt) != 0) goto skip_update; /* * File systems can error out when updating inodes if they need to * allocate new space to modify an inode (such is the case for * Btrfs), but since we touch atime while walking down the path we * really don't care if we failed to update the atime of the file, * so just ignore the return value. * We may also fail on filesystems that have the ability to make parts * of the fs read only, e.g. subvolumes in Btrfs. */ inode_update_time(inode, S_ATIME); mnt_put_write_access(mnt); skip_update: sb_end_write(inode->i_sb); } EXPORT_SYMBOL(touch_atime); /* * Return mask of changes for notify_change() that need to be done as a * response to write or truncate. Return 0 if nothing has to be changed. * Negative value on error (change should be denied). */ int dentry_needs_remove_privs(struct mnt_idmap *idmap, struct dentry *dentry) { struct inode *inode = d_inode(dentry); int mask = 0; int ret; if (IS_NOSEC(inode)) return 0; mask = setattr_should_drop_suidgid(idmap, inode); ret = security_inode_need_killpriv(dentry); if (ret < 0) return ret; if (ret) mask |= ATTR_KILL_PRIV; return mask; } static int __remove_privs(struct mnt_idmap *idmap, struct dentry *dentry, int kill) { struct iattr newattrs; newattrs.ia_valid = ATTR_FORCE | kill; /* * Note we call this on write, so notify_change will not * encounter any conflicting delegations: */ return notify_change(idmap, dentry, &newattrs, NULL); } int file_remove_privs_flags(struct file *file, unsigned int flags) { struct dentry *dentry = file_dentry(file); struct inode *inode = file_inode(file); int error = 0; int kill; if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0; kill = dentry_needs_remove_privs(file_mnt_idmap(file), dentry); if (kill < 0) return kill; if (kill) { if (flags & IOCB_NOWAIT) return -EAGAIN; error = __remove_privs(file_mnt_idmap(file), dentry, kill); } if (!error) inode_has_no_xattr(inode); return error; } EXPORT_SYMBOL_GPL(file_remove_privs_flags); /** * file_remove_privs - remove special file privileges (suid, capabilities) * @file: file to remove privileges from * * When file is modified by a write or truncation ensure that special * file privileges are removed. * * Return: 0 on success, negative errno on failure. */ int file_remove_privs(struct file *file) { return file_remove_privs_flags(file, 0); } EXPORT_SYMBOL(file_remove_privs); /** * current_time - Return FS time (possibly fine-grained) * @inode: inode. * * Return the current time truncated to the time granularity supported by * the fs, as suitable for a ctime/mtime change. If the ctime is flagged * as having been QUERIED, get a fine-grained timestamp, but don't update * the floor. * * For a multigrain inode, this is effectively an estimate of the timestamp * that a file would receive. An actual update must go through * inode_set_ctime_current(). */ struct timespec64 current_time(struct inode *inode) { struct timespec64 now; u32 cns; ktime_get_coarse_real_ts64_mg(&now); if (!is_mgtime(inode)) goto out; /* If nothing has queried it, then coarse time is fine */ cns = smp_load_acquire(&inode->i_ctime_nsec); if (cns & I_CTIME_QUERIED) { /* * If there is no apparent change, then get a fine-grained * timestamp. */ if (now.tv_nsec == (cns & ~I_CTIME_QUERIED)) ktime_get_real_ts64(&now); } out: return timestamp_truncate(now, inode); } EXPORT_SYMBOL(current_time); static int inode_needs_update_time(struct inode *inode) { struct timespec64 now, ts; int sync_it = 0; /* First try to exhaust all avenues to not sync */ if (IS_NOCMTIME(inode)) return 0; now = current_time(inode); ts = inode_get_mtime(inode); if (!timespec64_equal(&ts, &now)) sync_it |= S_MTIME; ts = inode_get_ctime(inode); if (!timespec64_equal(&ts, &now)) sync_it |= S_CTIME; if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode)) sync_it |= S_VERSION; return sync_it; } static int __file_update_time(struct file *file, int sync_mode) { int ret = 0; struct inode *inode = file_inode(file); /* try to update time settings */ if (!mnt_get_write_access_file(file)) { ret = inode_update_time(inode, sync_mode); mnt_put_write_access_file(file); } return ret; } /** * file_update_time - update mtime and ctime time * @file: file accessed * * Update the mtime and ctime members of an inode and mark the inode for * writeback. Note that this function is meant exclusively for usage in * the file write path of filesystems, and filesystems may choose to * explicitly ignore updates via this function with the _NOCMTIME inode * flag, e.g. for network filesystem where these imestamps are handled * by the server. This can return an error for file systems who need to * allocate space in order to update an inode. * * Return: 0 on success, negative errno on failure. */ int file_update_time(struct file *file) { int ret; struct inode *inode = file_inode(file); ret = inode_needs_update_time(inode); if (ret <= 0) return ret; return __file_update_time(file, ret); } EXPORT_SYMBOL(file_update_time); /** * file_modified_flags - handle mandated vfs changes when modifying a file * @file: file that was modified * @flags: kiocb flags * * When file has been modified ensure that special * file privileges are removed and time settings are updated. * * If IOCB_NOWAIT is set, special file privileges will not be removed and * time settings will not be updated. It will return -EAGAIN. * * Context: Caller must hold the file's inode lock. * * Return: 0 on success, negative errno on failure. */ static int file_modified_flags(struct file *file, int flags) { int ret; struct inode *inode = file_inode(file); /* * Clear the security bits if the process is not being run by root. * This keeps people from modifying setuid and setgid binaries. */ ret = file_remove_privs_flags(file, flags); if (ret) return ret; if (unlikely(file->f_mode & FMODE_NOCMTIME)) return 0; ret = inode_needs_update_time(inode); if (ret <= 0) return ret; if (flags & IOCB_NOWAIT) return -EAGAIN; return __file_update_time(file, ret); } /** * file_modified - handle mandated vfs changes when modifying a file * @file: file that was modified * * When file has been modified ensure that special * file privileges are removed and time settings are updated. * * Context: Caller must hold the file's inode lock. * * Return: 0 on success, negative errno on failure. */ int file_modified(struct file *file) { return file_modified_flags(file, 0); } EXPORT_SYMBOL(file_modified); /** * kiocb_modified - handle mandated vfs changes when modifying a file * @iocb: iocb that was modified * * When file has been modified ensure that special * file privileges are removed and time settings are updated. * * Context: Caller must hold the file's inode lock. * * Return: 0 on success, negative errno on failure. */ int kiocb_modified(struct kiocb *iocb) { return file_modified_flags(iocb->ki_filp, iocb->ki_flags); } EXPORT_SYMBOL_GPL(kiocb_modified); int inode_needs_sync(struct inode *inode) { if (IS_SYNC(inode)) return 1; if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode)) return 1; return 0; } EXPORT_SYMBOL(inode_needs_sync); /* * If we try to find an inode in the inode hash while it is being * deleted, we have to wait until the filesystem completes its * deletion before reporting that it isn't found. This function waits * until the deletion _might_ have completed. Callers are responsible * to recheck inode state. * * It doesn't matter if I_NEW is not set initially, a call to * wake_up_bit(&inode->i_state, __I_NEW) after removing from the hash list * will DTRT. */ static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_locked) { struct wait_bit_queue_entry wqe; struct wait_queue_head *wq_head; /* * Handle racing against evict(), see that routine for more details. */ if (unlikely(inode_unhashed(inode))) { WARN_ON(is_inode_hash_locked); spin_unlock(&inode->i_lock); return; } wq_head = inode_bit_waitqueue(&wqe, inode, __I_NEW); prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&inode->i_lock); rcu_read_unlock(); if (is_inode_hash_locked) spin_unlock(&inode_hash_lock); schedule(); finish_wait(wq_head, &wqe.wq_entry); if (is_inode_hash_locked) spin_lock(&inode_hash_lock); rcu_read_lock(); } static __initdata unsigned long ihash_entries; static int __init set_ihash_entries(char *str) { if (!str) return 0; ihash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("ihash_entries=", set_ihash_entries); /* * Initialize the waitqueues and inode hash table. */ void __init inode_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; inode_hashtable = alloc_large_system_hash("Inode-cache", sizeof(struct hlist_head), ihash_entries, 14, HASH_EARLY | HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); } void __init inode_init(void) { /* inode slab cache */ inode_cachep = kmem_cache_create("inode_cache", sizeof(struct inode), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| SLAB_ACCOUNT), init_once); /* Hash may have been set up in inode_init_early */ if (!hashdist) return; inode_hashtable = alloc_large_system_hash("Inode-cache", sizeof(struct hlist_head), ihash_entries, 14, HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); } void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev) { inode->i_mode = mode; if (S_ISCHR(mode)) { inode->i_fop = &def_chr_fops; inode->i_rdev = rdev; } else if (S_ISBLK(mode)) { if (IS_ENABLED(CONFIG_BLOCK)) inode->i_fop = &def_blk_fops; inode->i_rdev = rdev; } else if (S_ISFIFO(mode)) inode->i_fop = &pipefifo_fops; else if (S_ISSOCK(mode)) ; /* leave it no_open_fops */ else printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o) for" " inode %s:%lu\n", mode, inode->i_sb->s_id, inode->i_ino); } EXPORT_SYMBOL(init_special_inode); /** * inode_init_owner - Init uid,gid,mode for new inode according to posix standards * @idmap: idmap of the mount the inode was created from * @inode: New inode * @dir: Directory inode * @mode: mode of the new inode * * If the inode has been created through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions * and initializing i_uid and i_gid. On non-idmapped mounts or if permission * checking is to be performed on the raw inode simply pass @nop_mnt_idmap. */ void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, const struct inode *dir, umode_t mode) { inode_fsuid_set(inode, idmap); if (dir && dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; /* Directories are special, and always inherit S_ISGID */ if (S_ISDIR(mode)) mode |= S_ISGID; } else inode_fsgid_set(inode, idmap); inode->i_mode = mode; } EXPORT_SYMBOL(inode_init_owner); /** * inode_owner_or_capable - check current task permissions to inode * @idmap: idmap of the mount the inode was found from * @inode: inode being checked * * Return true if current either has CAP_FOWNER in a namespace with the * inode owner uid mapped, or owns the file. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode) { vfsuid_t vfsuid; struct user_namespace *ns; vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) return true; ns = current_user_ns(); if (vfsuid_has_mapping(ns, vfsuid) && ns_capable(ns, CAP_FOWNER)) return true; return false; } EXPORT_SYMBOL(inode_owner_or_capable); /* * Direct i/o helper functions */ bool inode_dio_finished(const struct inode *inode) { return atomic_read(&inode->i_dio_count) == 0; } EXPORT_SYMBOL(inode_dio_finished); /** * inode_dio_wait - wait for outstanding DIO requests to finish * @inode: inode to wait for * * Waits for all pending direct I/O requests to finish so that we can * proceed with a truncate or equivalent operation. * * Must be called under a lock that serializes taking new references * to i_dio_count, usually by inode->i_mutex. */ void inode_dio_wait(struct inode *inode) { wait_var_event(&inode->i_dio_count, inode_dio_finished(inode)); } EXPORT_SYMBOL(inode_dio_wait); void inode_dio_wait_interruptible(struct inode *inode) { wait_var_event_interruptible(&inode->i_dio_count, inode_dio_finished(inode)); } EXPORT_SYMBOL(inode_dio_wait_interruptible); /* * inode_set_flags - atomically set some inode flags * * Note: the caller should be holding i_mutex, or else be sure that * they have exclusive access to the inode structure (i.e., while the * inode is being instantiated). The reason for the cmpxchg() loop * --- which wouldn't be necessary if all code paths which modify * i_flags actually followed this rule, is that there is at least one * code path which doesn't today so we use cmpxchg() out of an abundance * of caution. * * In the long run, i_mutex is overkill, and we should probably look * at using the i_lock spinlock to protect i_flags, and then make sure * it is so documented in include/linux/fs.h and that all code follows * the locking convention!! */ void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask) { WARN_ON_ONCE(flags & ~mask); set_mask_bits(&inode->i_flags, mask, flags); } EXPORT_SYMBOL(inode_set_flags); void inode_nohighmem(struct inode *inode) { mapping_set_gfp_mask(inode->i_mapping, GFP_USER); } EXPORT_SYMBOL(inode_nohighmem); struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts) { trace_inode_set_ctime_to_ts(inode, &ts); set_normalized_timespec64(&ts, ts.tv_sec, ts.tv_nsec); inode->i_ctime_sec = ts.tv_sec; inode->i_ctime_nsec = ts.tv_nsec; return ts; } EXPORT_SYMBOL(inode_set_ctime_to_ts); /** * timestamp_truncate - Truncate timespec to a granularity * @t: Timespec * @inode: inode being updated * * Truncate a timespec to the granularity supported by the fs * containing the inode. Always rounds down. gran must * not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns). */ struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned int gran = sb->s_time_gran; t.tv_sec = clamp(t.tv_sec, sb->s_time_min, sb->s_time_max); if (unlikely(t.tv_sec == sb->s_time_max || t.tv_sec == sb->s_time_min)) t.tv_nsec = 0; /* Avoid division in the common cases 1 ns and 1 s. */ if (gran == 1) ; /* nothing */ else if (gran == NSEC_PER_SEC) t.tv_nsec = 0; else if (gran > 1 && gran < NSEC_PER_SEC) t.tv_nsec -= t.tv_nsec % gran; else WARN(1, "invalid file time granularity: %u", gran); return t; } EXPORT_SYMBOL(timestamp_truncate); /** * inode_set_ctime_current - set the ctime to current_time * @inode: inode * * Set the inode's ctime to the current value for the inode. Returns the * current value that was assigned. If this is not a multigrain inode, then we * set it to the later of the coarse time and floor value. * * If it is multigrain, then we first see if the coarse-grained timestamp is * distinct from what is already there. If so, then use that. Otherwise, get a * fine-grained timestamp. * * After that, try to swap the new value into i_ctime_nsec. Accept the * resulting ctime, regardless of the outcome of the swap. If it has * already been replaced, then that timestamp is later than the earlier * unacceptable one, and is thus acceptable. */ struct timespec64 inode_set_ctime_current(struct inode *inode) { struct timespec64 now; u32 cns, cur; ktime_get_coarse_real_ts64_mg(&now); now = timestamp_truncate(now, inode); /* Just return that if this is not a multigrain fs */ if (!is_mgtime(inode)) { inode_set_ctime_to_ts(inode, now); goto out; } /* * A fine-grained time is only needed if someone has queried * for timestamps, and the current coarse grained time isn't * later than what's already there. */ cns = smp_load_acquire(&inode->i_ctime_nsec); if (cns & I_CTIME_QUERIED) { struct timespec64 ctime = { .tv_sec = inode->i_ctime_sec, .tv_nsec = cns & ~I_CTIME_QUERIED }; if (timespec64_compare(&now, &ctime) <= 0) { ktime_get_real_ts64_mg(&now); now = timestamp_truncate(now, inode); mgtime_counter_inc(mg_fine_stamps); } } mgtime_counter_inc(mg_ctime_updates); /* No need to cmpxchg if it's exactly the same */ if (cns == now.tv_nsec && inode->i_ctime_sec == now.tv_sec) { trace_ctime_xchg_skip(inode, &now); goto out; } cur = cns; retry: /* Try to swap the nsec value into place. */ if (try_cmpxchg(&inode->i_ctime_nsec, &cur, now.tv_nsec)) { /* If swap occurred, then we're (mostly) done */ inode->i_ctime_sec = now.tv_sec; trace_ctime_ns_xchg(inode, cns, now.tv_nsec, cur); mgtime_counter_inc(mg_ctime_swaps); } else { /* * Was the change due to someone marking the old ctime QUERIED? * If so then retry the swap. This can only happen once since * the only way to clear I_CTIME_QUERIED is to stamp the inode * with a new ctime. */ if (!(cns & I_CTIME_QUERIED) && (cns | I_CTIME_QUERIED) == cur) { cns = cur; goto retry; } /* Otherwise, keep the existing ctime */ now.tv_sec = inode->i_ctime_sec; now.tv_nsec = cur & ~I_CTIME_QUERIED; } out: return now; } EXPORT_SYMBOL(inode_set_ctime_current); /** * inode_set_ctime_deleg - try to update the ctime on a delegated inode * @inode: inode to update * @update: timespec64 to set the ctime * * Attempt to atomically update the ctime on behalf of a delegation holder. * * The nfs server can call back the holder of a delegation to get updated * inode attributes, including the mtime. When updating the mtime, update * the ctime to a value at least equal to that. * * This can race with concurrent updates to the inode, in which * case the update is skipped. * * Note that this works even when multigrain timestamps are not enabled, * so it is used in either case. */ struct timespec64 inode_set_ctime_deleg(struct inode *inode, struct timespec64 update) { struct timespec64 now, cur_ts; u32 cur, old; /* pairs with try_cmpxchg below */ cur = smp_load_acquire(&inode->i_ctime_nsec); cur_ts.tv_nsec = cur & ~I_CTIME_QUERIED; cur_ts.tv_sec = inode->i_ctime_sec; /* If the update is older than the existing value, skip it. */ if (timespec64_compare(&update, &cur_ts) <= 0) return cur_ts; ktime_get_coarse_real_ts64_mg(&now); /* Clamp the update to "now" if it's in the future */ if (timespec64_compare(&update, &now) > 0) update = now; update = timestamp_truncate(update, inode); /* No need to update if the values are already the same */ if (timespec64_equal(&update, &cur_ts)) return cur_ts; /* * Try to swap the nsec value into place. If it fails, that means * it raced with an update due to a write or similar activity. That * stamp takes precedence, so just skip the update. */ retry: old = cur; if (try_cmpxchg(&inode->i_ctime_nsec, &cur, update.tv_nsec)) { inode->i_ctime_sec = update.tv_sec; mgtime_counter_inc(mg_ctime_swaps); return update; } /* * Was the change due to another task marking the old ctime QUERIED? * * If so, then retry the swap. This can only happen once since * the only way to clear I_CTIME_QUERIED is to stamp the inode * with a new ctime. */ if (!(old & I_CTIME_QUERIED) && (cur == (old | I_CTIME_QUERIED))) goto retry; /* Otherwise, it was a new timestamp. */ cur_ts.tv_sec = inode->i_ctime_sec; cur_ts.tv_nsec = cur & ~I_CTIME_QUERIED; return cur_ts; } EXPORT_SYMBOL(inode_set_ctime_deleg); /** * in_group_or_capable - check whether caller is CAP_FSETID privileged * @idmap: idmap of the mount @inode was found from * @inode: inode to check * @vfsgid: the new/current vfsgid of @inode * * Check whether @vfsgid is in the caller's group list or if the caller is * privileged with CAP_FSETID over @inode. This can be used to determine * whether the setgid bit can be kept or must be dropped. * * Return: true if the caller is sufficiently privileged, false if not. */ bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid) { if (vfsgid_in_group_p(vfsgid)) return true; if (capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID)) return true; return false; } EXPORT_SYMBOL(in_group_or_capable); /** * mode_strip_sgid - handle the sgid bit for non-directories * @idmap: idmap of the mount the inode was created from * @dir: parent directory inode * @mode: mode of the file to be created in @dir * * If the @mode of the new file has both the S_ISGID and S_IXGRP bit * raised and @dir has the S_ISGID bit raised ensure that the caller is * either in the group of the parent directory or they have CAP_FSETID * in their user namespace and are privileged over the parent directory. * In all other cases, strip the S_ISGID bit from @mode. * * Return: the new mode to use for the file */ umode_t mode_strip_sgid(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode) { if ((mode & (S_ISGID | S_IXGRP)) != (S_ISGID | S_IXGRP)) return mode; if (S_ISDIR(mode) || !dir || !(dir->i_mode & S_ISGID)) return mode; if (in_group_or_capable(idmap, dir, i_gid_into_vfsgid(idmap, dir))) return mode; return mode & ~S_ISGID; } EXPORT_SYMBOL(mode_strip_sgid); |
| 33 33 33 2 32 10 38 23 23 23 18 6 18 6 23 8 22 38 2 36 2 33 33 4 31 33 2 31 31 1 1 1 9 1 2 1 1 4 2 5 1 1 1 1 1 3 1 58 1 23 904 893 59 32 898 34 178 29 902 860 161 63 13 32 5 3 9 2 1 49 3 29 3 1 7 28 2 7 29 39 3 3 6 7 6 2 1 1 20 1 19 1 10 8 1 1 2 1 9 1 6 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET 802.1Q VLAN * Ethernet-type device handling. * * Authors: Ben Greear <greearb@candelatech.com> * Please send support related email to: netdev@vger.kernel.org * VLAN Home Page: http://www.candelatech.com/~greear/vlan.html * * Fixes: * Fix for packet capture - Nick Eggleston <nick@dccinc.com>; * Add HW acceleration hooks - David S. Miller <davem@redhat.com>; * Correct all the locking - David S. Miller <davem@redhat.com>; * Use hash table for VLAN groups - David S. Miller <davem@redhat.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/rculist.h> #include <net/p8022.h> #include <net/arp.h> #include <linux/rtnetlink.h> #include <linux/notifier.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/uaccess.h> #include <linux/if_vlan.h> #include "vlan.h" #include "vlanproc.h" #define DRV_VERSION "1.8" /* Global VLAN variables */ unsigned int vlan_net_id __read_mostly; const char vlan_fullname[] = "802.1Q VLAN Support"; const char vlan_version[] = DRV_VERSION; /* End of global variables definitions. */ static int vlan_group_prealloc_vid(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id) { struct net_device **array; unsigned int vidx; unsigned int size; int pidx; ASSERT_RTNL(); pidx = vlan_proto_idx(vlan_proto); if (pidx < 0) return -EINVAL; vidx = vlan_id / VLAN_GROUP_ARRAY_PART_LEN; array = vg->vlan_devices_arrays[pidx][vidx]; if (array != NULL) return 0; size = sizeof(struct net_device *) * VLAN_GROUP_ARRAY_PART_LEN; array = kzalloc(size, GFP_KERNEL_ACCOUNT); if (array == NULL) return -ENOBUFS; /* paired with smp_rmb() in __vlan_group_get_device() */ smp_wmb(); vg->vlan_devices_arrays[pidx][vidx] = array; return 0; } static void vlan_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev, struct vlan_dev_priv *vlan) { if (!(vlan->flags & VLAN_FLAG_BRIDGE_BINDING)) netif_stacked_transfer_operstate(rootdev, dev); } void unregister_vlan_dev(struct net_device *dev, struct list_head *head) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; struct vlan_info *vlan_info; struct vlan_group *grp; u16 vlan_id = vlan->vlan_id; ASSERT_RTNL(); vlan_info = rtnl_dereference(real_dev->vlan_info); BUG_ON(!vlan_info); grp = &vlan_info->grp; grp->nr_vlan_devs--; if (vlan->flags & VLAN_FLAG_MVRP) vlan_mvrp_request_leave(dev); if (vlan->flags & VLAN_FLAG_GVRP) vlan_gvrp_request_leave(dev); vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, NULL); netdev_upper_dev_unlink(real_dev, dev); /* Because unregister_netdevice_queue() makes sure at least one rcu * grace period is respected before device freeing, * we dont need to call synchronize_net() here. */ unregister_netdevice_queue(dev, head); if (grp->nr_vlan_devs == 0) { vlan_mvrp_uninit_applicant(real_dev); vlan_gvrp_uninit_applicant(real_dev); } vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id); } int vlan_check_real_dev(struct net_device *real_dev, __be16 protocol, u16 vlan_id, struct netlink_ext_ack *extack) { const char *name = real_dev->name; if (real_dev->features & NETIF_F_VLAN_CHALLENGED) { pr_info("VLANs not supported on %s\n", name); NL_SET_ERR_MSG_MOD(extack, "VLANs not supported on device"); return -EOPNOTSUPP; } if (vlan_find_dev(real_dev, protocol, vlan_id) != NULL) { NL_SET_ERR_MSG_MOD(extack, "VLAN device already exists"); return -EEXIST; } return 0; } int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; u16 vlan_id = vlan->vlan_id; struct vlan_info *vlan_info; struct vlan_group *grp; int err; err = vlan_vid_add(real_dev, vlan->vlan_proto, vlan_id); if (err) return err; vlan_info = rtnl_dereference(real_dev->vlan_info); /* vlan_info should be there now. vlan_vid_add took care of it */ BUG_ON(!vlan_info); grp = &vlan_info->grp; if (grp->nr_vlan_devs == 0) { err = vlan_gvrp_init_applicant(real_dev); if (err < 0) goto out_vid_del; err = vlan_mvrp_init_applicant(real_dev); if (err < 0) goto out_uninit_gvrp; } err = vlan_group_prealloc_vid(grp, vlan->vlan_proto, vlan_id); if (err < 0) goto out_uninit_mvrp; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; err = netdev_upper_dev_link(real_dev, dev, extack); if (err) goto out_unregister_netdev; vlan_stacked_transfer_operstate(real_dev, dev, vlan); linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */ /* So, got the sucker initialized, now lets place * it into our local structure. */ vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, dev); grp->nr_vlan_devs++; return 0; out_unregister_netdev: unregister_netdevice(dev); out_uninit_mvrp: if (grp->nr_vlan_devs == 0) vlan_mvrp_uninit_applicant(real_dev); out_uninit_gvrp: if (grp->nr_vlan_devs == 0) vlan_gvrp_uninit_applicant(real_dev); out_vid_del: vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id); return err; } /* Attach a VLAN device to a mac address (ie Ethernet Card). * Returns 0 if the device was created or a negative error code otherwise. */ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) { struct net_device *new_dev; struct vlan_dev_priv *vlan; struct net *net = dev_net(real_dev); struct vlan_net *vn = net_generic(net, vlan_net_id); char name[IFNAMSIZ]; int err; if (vlan_id >= VLAN_VID_MASK) return -ERANGE; err = vlan_check_real_dev(real_dev, htons(ETH_P_8021Q), vlan_id, NULL); if (err < 0) return err; /* Gotta set up the fields for the device. */ switch (vn->name_type) { case VLAN_NAME_TYPE_RAW_PLUS_VID: /* name will look like: eth1.0005 */ snprintf(name, IFNAMSIZ, "%s.%.4i", real_dev->name, vlan_id); break; case VLAN_NAME_TYPE_PLUS_VID_NO_PAD: /* Put our vlan.VID in the name. * Name will look like: vlan5 */ snprintf(name, IFNAMSIZ, "vlan%i", vlan_id); break; case VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD: /* Put our vlan.VID in the name. * Name will look like: eth0.5 */ snprintf(name, IFNAMSIZ, "%s.%i", real_dev->name, vlan_id); break; case VLAN_NAME_TYPE_PLUS_VID: /* Put our vlan.VID in the name. * Name will look like: vlan0005 */ default: snprintf(name, IFNAMSIZ, "vlan%.4i", vlan_id); } new_dev = alloc_netdev(sizeof(struct vlan_dev_priv), name, NET_NAME_UNKNOWN, vlan_setup); if (new_dev == NULL) return -ENOBUFS; dev_net_set(new_dev, net); /* need 4 bytes for extra VLAN header info, * hope the underlying device can handle it. */ new_dev->mtu = real_dev->mtu; vlan = vlan_dev_priv(new_dev); vlan->vlan_proto = htons(ETH_P_8021Q); vlan->vlan_id = vlan_id; vlan->real_dev = real_dev; vlan->dent = NULL; vlan->flags = VLAN_FLAG_REORDER_HDR; new_dev->rtnl_link_ops = &vlan_link_ops; err = register_vlan_dev(new_dev, NULL); if (err < 0) goto out_free_newdev; return 0; out_free_newdev: free_netdev(new_dev); return err; } static void vlan_sync_address(struct net_device *dev, struct net_device *vlandev) { struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); /* May be called without an actual change */ if (ether_addr_equal(vlan->real_dev_addr, dev->dev_addr)) return; /* vlan continues to inherit address of lower device */ if (vlan_dev_inherit_address(vlandev, dev)) goto out; /* vlan address was different from the old address and is equal to * the new address */ if (!ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) && ether_addr_equal(vlandev->dev_addr, dev->dev_addr)) dev_uc_del(dev, vlandev->dev_addr); /* vlan address was equal to the old address and is different from * the new address */ if (ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) && !ether_addr_equal(vlandev->dev_addr, dev->dev_addr)) dev_uc_add(dev, vlandev->dev_addr); out: ether_addr_copy(vlan->real_dev_addr, dev->dev_addr); } static void vlan_transfer_features(struct net_device *dev, struct net_device *vlandev) { struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); netif_inherit_tso_max(vlandev, dev); if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto)) vlandev->hard_header_len = dev->hard_header_len; else vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN; #if IS_ENABLED(CONFIG_FCOE) vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid; #endif vlandev->priv_flags &= ~IFF_XMIT_DST_RELEASE; vlandev->priv_flags |= (vlan->real_dev->priv_flags & IFF_XMIT_DST_RELEASE); vlandev->hw_enc_features = vlan_tnl_features(vlan->real_dev); netdev_update_features(vlandev); } static int __vlan_device_event(struct net_device *dev, unsigned long event) { int err = 0; switch (event) { case NETDEV_CHANGENAME: vlan_proc_rem_dev(dev); err = vlan_proc_add_dev(dev); break; case NETDEV_REGISTER: err = vlan_proc_add_dev(dev); break; case NETDEV_UNREGISTER: vlan_proc_rem_dev(dev); break; } return err; } static int vlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct vlan_group *grp; struct vlan_info *vlan_info; int i, flgs; struct net_device *vlandev; struct vlan_dev_priv *vlan; bool last = false; LIST_HEAD(list); int err; if (is_vlan_dev(dev)) { int err = __vlan_device_event(dev, event); if (err) return notifier_from_errno(err); } if ((event == NETDEV_UP) && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) { pr_info("adding VLAN 0 to HW filter on device %s\n", dev->name); vlan_vid_add(dev, htons(ETH_P_8021Q), 0); } if (event == NETDEV_DOWN && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) vlan_vid_del(dev, htons(ETH_P_8021Q), 0); vlan_info = rtnl_dereference(dev->vlan_info); if (!vlan_info) goto out; grp = &vlan_info->grp; /* It is OK that we do not hold the group lock right now, * as we run under the RTNL lock. */ switch (event) { case NETDEV_CHANGE: /* Propagate real device state to vlan devices */ vlan_group_for_each_dev(grp, i, vlandev) vlan_stacked_transfer_operstate(dev, vlandev, vlan_dev_priv(vlandev)); break; case NETDEV_CHANGEADDR: /* Adjust unicast filters on underlying device */ vlan_group_for_each_dev(grp, i, vlandev) { flgs = vlandev->flags; if (!(flgs & IFF_UP)) continue; vlan_sync_address(dev, vlandev); } break; case NETDEV_CHANGEMTU: vlan_group_for_each_dev(grp, i, vlandev) { if (vlandev->mtu <= dev->mtu) continue; dev_set_mtu(vlandev, dev->mtu); } break; case NETDEV_FEAT_CHANGE: /* Propagate device features to underlying device */ vlan_group_for_each_dev(grp, i, vlandev) vlan_transfer_features(dev, vlandev); break; case NETDEV_DOWN: { struct net_device *tmp; LIST_HEAD(close_list); /* Put all VLANs for this dev in the down state too. */ vlan_group_for_each_dev(grp, i, vlandev) { flgs = vlandev->flags; if (!(flgs & IFF_UP)) continue; vlan = vlan_dev_priv(vlandev); if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) list_add(&vlandev->close_list, &close_list); } dev_close_many(&close_list, false); list_for_each_entry_safe(vlandev, tmp, &close_list, close_list) { vlan_stacked_transfer_operstate(dev, vlandev, vlan_dev_priv(vlandev)); list_del_init(&vlandev->close_list); } list_del(&close_list); break; } case NETDEV_UP: /* Put all VLANs for this dev in the up state too. */ vlan_group_for_each_dev(grp, i, vlandev) { flgs = dev_get_flags(vlandev); if (flgs & IFF_UP) continue; vlan = vlan_dev_priv(vlandev); if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) dev_change_flags(vlandev, flgs | IFF_UP, extack); vlan_stacked_transfer_operstate(dev, vlandev, vlan); } break; case NETDEV_UNREGISTER: /* twiddle thumbs on netns device moves */ if (dev->reg_state != NETREG_UNREGISTERING) break; vlan_group_for_each_dev(grp, i, vlandev) { /* removal of last vid destroys vlan_info, abort * afterwards */ if (vlan_info->nr_vids == 1) last = true; unregister_vlan_dev(vlandev, &list); if (last) break; } unregister_netdevice_many(&list); break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlaying device to change its type. */ if (vlan_uses_dev(dev)) return NOTIFY_BAD; break; case NETDEV_NOTIFY_PEERS: case NETDEV_BONDING_FAILOVER: case NETDEV_RESEND_IGMP: /* Propagate to vlan devices */ vlan_group_for_each_dev(grp, i, vlandev) call_netdevice_notifiers(event, vlandev); break; case NETDEV_CVLAN_FILTER_PUSH_INFO: err = vlan_filter_push_vids(vlan_info, htons(ETH_P_8021Q)); if (err) return notifier_from_errno(err); break; case NETDEV_CVLAN_FILTER_DROP_INFO: vlan_filter_drop_vids(vlan_info, htons(ETH_P_8021Q)); break; case NETDEV_SVLAN_FILTER_PUSH_INFO: err = vlan_filter_push_vids(vlan_info, htons(ETH_P_8021AD)); if (err) return notifier_from_errno(err); break; case NETDEV_SVLAN_FILTER_DROP_INFO: vlan_filter_drop_vids(vlan_info, htons(ETH_P_8021AD)); break; } out: return NOTIFY_DONE; } static struct notifier_block vlan_notifier_block __read_mostly = { .notifier_call = vlan_device_event, }; /* * VLAN IOCTL handler. * o execute requested action or pass command to the device driver * arg is really a struct vlan_ioctl_args __user *. */ static int vlan_ioctl_handler(struct net *net, void __user *arg) { int err; struct vlan_ioctl_args args; struct net_device *dev = NULL; if (copy_from_user(&args, arg, sizeof(struct vlan_ioctl_args))) return -EFAULT; /* Null terminate this sucker, just in case. */ args.device1[sizeof(args.device1) - 1] = 0; args.u.device2[sizeof(args.u.device2) - 1] = 0; rtnl_lock(); switch (args.cmd) { case SET_VLAN_INGRESS_PRIORITY_CMD: case SET_VLAN_EGRESS_PRIORITY_CMD: case SET_VLAN_FLAG_CMD: case ADD_VLAN_CMD: case DEL_VLAN_CMD: case GET_VLAN_REALDEV_NAME_CMD: case GET_VLAN_VID_CMD: err = -ENODEV; dev = __dev_get_by_name(net, args.device1); if (!dev) goto out; err = -EINVAL; if (args.cmd != ADD_VLAN_CMD && !is_vlan_dev(dev)) goto out; } switch (args.cmd) { case SET_VLAN_INGRESS_PRIORITY_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; vlan_dev_set_ingress_priority(dev, args.u.skb_priority, args.vlan_qos); err = 0; break; case SET_VLAN_EGRESS_PRIORITY_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = vlan_dev_set_egress_priority(dev, args.u.skb_priority, args.vlan_qos); break; case SET_VLAN_FLAG_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = vlan_dev_change_flags(dev, args.vlan_qos ? args.u.flag : 0, args.u.flag); break; case SET_VLAN_NAME_TYPE_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if (args.u.name_type < VLAN_NAME_TYPE_HIGHEST) { struct vlan_net *vn; vn = net_generic(net, vlan_net_id); vn->name_type = args.u.name_type; err = 0; } else { err = -EINVAL; } break; case ADD_VLAN_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = register_vlan_device(dev, args.u.VID); break; case DEL_VLAN_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; unregister_vlan_dev(dev, NULL); err = 0; break; case GET_VLAN_REALDEV_NAME_CMD: err = 0; vlan_dev_get_realdev_name(dev, args.u.device2, sizeof(args.u.device2)); if (copy_to_user(arg, &args, sizeof(struct vlan_ioctl_args))) err = -EFAULT; break; case GET_VLAN_VID_CMD: err = 0; args.u.VID = vlan_dev_vlan_id(dev); if (copy_to_user(arg, &args, sizeof(struct vlan_ioctl_args))) err = -EFAULT; break; default: err = -EOPNOTSUPP; break; } out: rtnl_unlock(); return err; } static int __net_init vlan_init_net(struct net *net) { struct vlan_net *vn = net_generic(net, vlan_net_id); int err; vn->name_type = VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD; err = vlan_proc_init(net); return err; } static void __net_exit vlan_exit_net(struct net *net) { vlan_proc_cleanup(net); } static struct pernet_operations vlan_net_ops = { .init = vlan_init_net, .exit = vlan_exit_net, .id = &vlan_net_id, .size = sizeof(struct vlan_net), }; static int __init vlan_proto_init(void) { int err; pr_info("%s v%s\n", vlan_fullname, vlan_version); err = register_pernet_subsys(&vlan_net_ops); if (err < 0) goto err0; err = register_netdevice_notifier(&vlan_notifier_block); if (err < 0) goto err2; err = vlan_gvrp_init(); if (err < 0) goto err3; err = vlan_mvrp_init(); if (err < 0) goto err4; err = vlan_netlink_init(); if (err < 0) goto err5; vlan_ioctl_set(vlan_ioctl_handler); return 0; err5: vlan_mvrp_uninit(); err4: vlan_gvrp_uninit(); err3: unregister_netdevice_notifier(&vlan_notifier_block); err2: unregister_pernet_subsys(&vlan_net_ops); err0: return err; } static void __exit vlan_cleanup_module(void) { vlan_ioctl_set(NULL); vlan_netlink_fini(); unregister_netdevice_notifier(&vlan_notifier_block); unregister_pernet_subsys(&vlan_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ vlan_mvrp_uninit(); vlan_gvrp_uninit(); } module_init(vlan_proto_init); module_exit(vlan_cleanup_module); MODULE_DESCRIPTION("802.1Q/802.1ad VLAN Protocol"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); |
| 1 1 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 11 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/net/sunrpc/svc.c * * High-level RPC service routines * * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> * * Multiple threads pools and NUMAisation * Copyright (c) 2006 Silicon Graphics, Inc. * by Greg Banks <gnb@melbourne.sgi.com> */ #include <linux/linkage.h> #include <linux/sched/signal.h> #include <linux/errno.h> #include <linux/net.h> #include <linux/in.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/module.h> #include <linux/kthread.h> #include <linux/slab.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/xdr.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/bc_xprt.h> #include <trace/events/sunrpc.h> #include "fail.h" #include "sunrpc.h" #define RPCDBG_FACILITY RPCDBG_SVCDSP static void svc_unregister(const struct svc_serv *serv, struct net *net); #define SVC_POOL_DEFAULT SVC_POOL_GLOBAL /* * Mode for mapping cpus to pools. */ enum { SVC_POOL_AUTO = -1, /* choose one of the others */ SVC_POOL_GLOBAL, /* no mapping, just a single global pool * (legacy & UP mode) */ SVC_POOL_PERCPU, /* one pool per cpu */ SVC_POOL_PERNODE /* one pool per numa node */ }; /* * Structure for mapping cpus to pools and vice versa. * Setup once during sunrpc initialisation. */ struct svc_pool_map { int count; /* How many svc_servs use us */ int mode; /* Note: int not enum to avoid * warnings about "enumeration value * not handled in switch" */ unsigned int npools; unsigned int *pool_to; /* maps pool id to cpu or node */ unsigned int *to_pool; /* maps cpu or node to pool id */ }; static struct svc_pool_map svc_pool_map = { .mode = SVC_POOL_DEFAULT }; static DEFINE_MUTEX(svc_pool_map_mutex);/* protects svc_pool_map.count only */ static int __param_set_pool_mode(const char *val, struct svc_pool_map *m) { int err, mode; mutex_lock(&svc_pool_map_mutex); err = 0; if (!strncmp(val, "auto", 4)) mode = SVC_POOL_AUTO; else if (!strncmp(val, "global", 6)) mode = SVC_POOL_GLOBAL; else if (!strncmp(val, "percpu", 6)) mode = SVC_POOL_PERCPU; else if (!strncmp(val, "pernode", 7)) mode = SVC_POOL_PERNODE; else err = -EINVAL; if (err) goto out; if (m->count == 0) m->mode = mode; else if (mode != m->mode) err = -EBUSY; out: mutex_unlock(&svc_pool_map_mutex); return err; } static int param_set_pool_mode(const char *val, const struct kernel_param *kp) { struct svc_pool_map *m = kp->arg; return __param_set_pool_mode(val, m); } int sunrpc_set_pool_mode(const char *val) { return __param_set_pool_mode(val, &svc_pool_map); } EXPORT_SYMBOL(sunrpc_set_pool_mode); /** * sunrpc_get_pool_mode - get the current pool_mode for the host * @buf: where to write the current pool_mode * @size: size of @buf * * Grab the current pool_mode from the svc_pool_map and write * the resulting string to @buf. Returns the number of characters * written to @buf (a'la snprintf()). */ int sunrpc_get_pool_mode(char *buf, size_t size) { struct svc_pool_map *m = &svc_pool_map; switch (m->mode) { case SVC_POOL_AUTO: return snprintf(buf, size, "auto"); case SVC_POOL_GLOBAL: return snprintf(buf, size, "global"); case SVC_POOL_PERCPU: return snprintf(buf, size, "percpu"); case SVC_POOL_PERNODE: return snprintf(buf, size, "pernode"); default: return snprintf(buf, size, "%d", m->mode); } } EXPORT_SYMBOL(sunrpc_get_pool_mode); static int param_get_pool_mode(char *buf, const struct kernel_param *kp) { char str[16]; int len; len = sunrpc_get_pool_mode(str, ARRAY_SIZE(str)); /* Ensure we have room for newline and NUL */ len = min_t(int, len, ARRAY_SIZE(str) - 2); /* tack on the newline */ str[len] = '\n'; str[len + 1] = '\0'; return sysfs_emit(buf, "%s", str); } module_param_call(pool_mode, param_set_pool_mode, param_get_pool_mode, &svc_pool_map, 0644); /* * Detect best pool mapping mode heuristically, * according to the machine's topology. */ static int svc_pool_map_choose_mode(void) { unsigned int node; if (nr_online_nodes > 1) { /* * Actually have multiple NUMA nodes, * so split pools on NUMA node boundaries */ return SVC_POOL_PERNODE; } node = first_online_node; if (nr_cpus_node(node) > 2) { /* * Non-trivial SMP, or CONFIG_NUMA on * non-NUMA hardware, e.g. with a generic * x86_64 kernel on Xeons. In this case we * want to divide the pools on cpu boundaries. */ return SVC_POOL_PERCPU; } /* default: one global pool */ return SVC_POOL_GLOBAL; } /* * Allocate the to_pool[] and pool_to[] arrays. * Returns 0 on success or an errno. */ static int svc_pool_map_alloc_arrays(struct svc_pool_map *m, unsigned int maxpools) { m->to_pool = kcalloc(maxpools, sizeof(unsigned int), GFP_KERNEL); if (!m->to_pool) goto fail; m->pool_to = kcalloc(maxpools, sizeof(unsigned int), GFP_KERNEL); if (!m->pool_to) goto fail_free; return 0; fail_free: kfree(m->to_pool); m->to_pool = NULL; fail: return -ENOMEM; } /* * Initialise the pool map for SVC_POOL_PERCPU mode. * Returns number of pools or <0 on error. */ static int svc_pool_map_init_percpu(struct svc_pool_map *m) { unsigned int maxpools = nr_cpu_ids; unsigned int pidx = 0; unsigned int cpu; int err; err = svc_pool_map_alloc_arrays(m, maxpools); if (err) return err; for_each_online_cpu(cpu) { BUG_ON(pidx >= maxpools); m->to_pool[cpu] = pidx; m->pool_to[pidx] = cpu; pidx++; } /* cpus brought online later all get mapped to pool0, sorry */ return pidx; }; /* * Initialise the pool map for SVC_POOL_PERNODE mode. * Returns number of pools or <0 on error. */ static int svc_pool_map_init_pernode(struct svc_pool_map *m) { unsigned int maxpools = nr_node_ids; unsigned int pidx = 0; unsigned int node; int err; err = svc_pool_map_alloc_arrays(m, maxpools); if (err) return err; for_each_node_with_cpus(node) { /* some architectures (e.g. SN2) have cpuless nodes */ BUG_ON(pidx > maxpools); m->to_pool[node] = pidx; m->pool_to[pidx] = node; pidx++; } /* nodes brought online later all get mapped to pool0, sorry */ return pidx; } /* * Add a reference to the global map of cpus to pools (and * vice versa) if pools are in use. * Initialise the map if we're the first user. * Returns the number of pools. If this is '1', no reference * was taken. */ static unsigned int svc_pool_map_get(void) { struct svc_pool_map *m = &svc_pool_map; int npools = -1; mutex_lock(&svc_pool_map_mutex); if (m->count++) { mutex_unlock(&svc_pool_map_mutex); return m->npools; } if (m->mode == SVC_POOL_AUTO) m->mode = svc_pool_map_choose_mode(); switch (m->mode) { case SVC_POOL_PERCPU: npools = svc_pool_map_init_percpu(m); break; case SVC_POOL_PERNODE: npools = svc_pool_map_init_pernode(m); break; } if (npools <= 0) { /* default, or memory allocation failure */ npools = 1; m->mode = SVC_POOL_GLOBAL; } m->npools = npools; mutex_unlock(&svc_pool_map_mutex); return npools; } /* * Drop a reference to the global map of cpus to pools. * When the last reference is dropped, the map data is * freed; this allows the sysadmin to change the pool. */ static void svc_pool_map_put(void) { struct svc_pool_map *m = &svc_pool_map; mutex_lock(&svc_pool_map_mutex); if (!--m->count) { kfree(m->to_pool); m->to_pool = NULL; kfree(m->pool_to); m->pool_to = NULL; m->npools = 0; } mutex_unlock(&svc_pool_map_mutex); } static int svc_pool_map_get_node(unsigned int pidx) { const struct svc_pool_map *m = &svc_pool_map; if (m->count) { if (m->mode == SVC_POOL_PERCPU) return cpu_to_node(m->pool_to[pidx]); if (m->mode == SVC_POOL_PERNODE) return m->pool_to[pidx]; } return NUMA_NO_NODE; } /* * Set the given thread's cpus_allowed mask so that it * will only run on cpus in the given pool. */ static inline void svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx) { struct svc_pool_map *m = &svc_pool_map; unsigned int node = m->pool_to[pidx]; /* * The caller checks for sv_nrpools > 1, which * implies that we've been initialized. */ WARN_ON_ONCE(m->count == 0); if (m->count == 0) return; switch (m->mode) { case SVC_POOL_PERCPU: { set_cpus_allowed_ptr(task, cpumask_of(node)); break; } case SVC_POOL_PERNODE: { set_cpus_allowed_ptr(task, cpumask_of_node(node)); break; } } } /** * svc_pool_for_cpu - Select pool to run a thread on this cpu * @serv: An RPC service * * Use the active CPU and the svc_pool_map's mode setting to * select the svc thread pool to use. Once initialized, the * svc_pool_map does not change. * * Return value: * A pointer to an svc_pool */ struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv) { struct svc_pool_map *m = &svc_pool_map; int cpu = raw_smp_processor_id(); unsigned int pidx = 0; if (serv->sv_nrpools <= 1) return serv->sv_pools; switch (m->mode) { case SVC_POOL_PERCPU: pidx = m->to_pool[cpu]; break; case SVC_POOL_PERNODE: pidx = m->to_pool[cpu_to_node(cpu)]; break; } return &serv->sv_pools[pidx % serv->sv_nrpools]; } static int svc_rpcb_setup(struct svc_serv *serv, struct net *net) { int err; err = rpcb_create_local(net); if (err) return err; /* Remove any stale portmap registrations */ svc_unregister(serv, net); return 0; } void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net) { svc_unregister(serv, net); rpcb_put_local(net); } EXPORT_SYMBOL_GPL(svc_rpcb_cleanup); static int svc_uses_rpcbind(struct svc_serv *serv) { unsigned int p, i; for (p = 0; p < serv->sv_nprogs; p++) { struct svc_program *progp = &serv->sv_programs[p]; for (i = 0; i < progp->pg_nvers; i++) { if (progp->pg_vers[i] == NULL) continue; if (!progp->pg_vers[i]->vs_hidden) return 1; } } return 0; } int svc_bind(struct svc_serv *serv, struct net *net) { if (!svc_uses_rpcbind(serv)) return 0; return svc_rpcb_setup(serv, net); } EXPORT_SYMBOL_GPL(svc_bind); #if defined(CONFIG_SUNRPC_BACKCHANNEL) static void __svc_init_bc(struct svc_serv *serv) { lwq_init(&serv->sv_cb_list); } #else static void __svc_init_bc(struct svc_serv *serv) { } #endif /* * Create an RPC service */ static struct svc_serv * __svc_create(struct svc_program *prog, int nprogs, struct svc_stat *stats, unsigned int bufsize, int npools, int (*threadfn)(void *data)) { struct svc_serv *serv; unsigned int vers; unsigned int xdrsize; unsigned int i; if (!(serv = kzalloc(sizeof(*serv), GFP_KERNEL))) return NULL; serv->sv_name = prog->pg_name; serv->sv_programs = prog; serv->sv_nprogs = nprogs; serv->sv_stats = stats; if (bufsize > RPCSVC_MAXPAYLOAD) bufsize = RPCSVC_MAXPAYLOAD; serv->sv_max_payload = bufsize? bufsize : 4096; serv->sv_max_mesg = roundup(serv->sv_max_payload + PAGE_SIZE, PAGE_SIZE); serv->sv_threadfn = threadfn; xdrsize = 0; for (i = 0; i < nprogs; i++) { struct svc_program *progp = &prog[i]; progp->pg_lovers = progp->pg_nvers-1; for (vers = 0; vers < progp->pg_nvers ; vers++) if (progp->pg_vers[vers]) { progp->pg_hivers = vers; if (progp->pg_lovers > vers) progp->pg_lovers = vers; if (progp->pg_vers[vers]->vs_xdrsize > xdrsize) xdrsize = progp->pg_vers[vers]->vs_xdrsize; } } serv->sv_xdrsize = xdrsize; INIT_LIST_HEAD(&serv->sv_tempsocks); INIT_LIST_HEAD(&serv->sv_permsocks); timer_setup(&serv->sv_temptimer, NULL, 0); spin_lock_init(&serv->sv_lock); __svc_init_bc(serv); serv->sv_nrpools = npools; serv->sv_pools = kcalloc(serv->sv_nrpools, sizeof(struct svc_pool), GFP_KERNEL); if (!serv->sv_pools) { kfree(serv); return NULL; } for (i = 0; i < serv->sv_nrpools; i++) { struct svc_pool *pool = &serv->sv_pools[i]; dprintk("svc: initialising pool %u for %s\n", i, serv->sv_name); pool->sp_id = i; lwq_init(&pool->sp_xprts); INIT_LIST_HEAD(&pool->sp_all_threads); init_llist_head(&pool->sp_idle_threads); percpu_counter_init(&pool->sp_messages_arrived, 0, GFP_KERNEL); percpu_counter_init(&pool->sp_sockets_queued, 0, GFP_KERNEL); percpu_counter_init(&pool->sp_threads_woken, 0, GFP_KERNEL); } return serv; } /** * svc_create - Create an RPC service * @prog: the RPC program the new service will handle * @bufsize: maximum message size for @prog * @threadfn: a function to service RPC requests for @prog * * Returns an instantiated struct svc_serv object or NULL. */ struct svc_serv *svc_create(struct svc_program *prog, unsigned int bufsize, int (*threadfn)(void *data)) { return __svc_create(prog, 1, NULL, bufsize, 1, threadfn); } EXPORT_SYMBOL_GPL(svc_create); /** * svc_create_pooled - Create an RPC service with pooled threads * @prog: Array of RPC programs the new service will handle * @nprogs: Number of programs in the array * @stats: the stats struct if desired * @bufsize: maximum message size for @prog * @threadfn: a function to service RPC requests for @prog * * Returns an instantiated struct svc_serv object or NULL. */ struct svc_serv *svc_create_pooled(struct svc_program *prog, unsigned int nprogs, struct svc_stat *stats, unsigned int bufsize, int (*threadfn)(void *data)) { struct svc_serv *serv; unsigned int npools = svc_pool_map_get(); serv = __svc_create(prog, nprogs, stats, bufsize, npools, threadfn); if (!serv) goto out_err; serv->sv_is_pooled = true; return serv; out_err: svc_pool_map_put(); return NULL; } EXPORT_SYMBOL_GPL(svc_create_pooled); /* * Destroy an RPC service. Should be called with appropriate locking to * protect sv_permsocks and sv_tempsocks. */ void svc_destroy(struct svc_serv **servp) { struct svc_serv *serv = *servp; unsigned int i; *servp = NULL; dprintk("svc: svc_destroy(%s)\n", serv->sv_programs->pg_name); timer_shutdown_sync(&serv->sv_temptimer); /* * Remaining transports at this point are not expected. */ WARN_ONCE(!list_empty(&serv->sv_permsocks), "SVC: permsocks remain for %s\n", serv->sv_programs->pg_name); WARN_ONCE(!list_empty(&serv->sv_tempsocks), "SVC: tempsocks remain for %s\n", serv->sv_programs->pg_name); cache_clean_deferred(serv); if (serv->sv_is_pooled) svc_pool_map_put(); for (i = 0; i < serv->sv_nrpools; i++) { struct svc_pool *pool = &serv->sv_pools[i]; percpu_counter_destroy(&pool->sp_messages_arrived); percpu_counter_destroy(&pool->sp_sockets_queued); percpu_counter_destroy(&pool->sp_threads_woken); } kfree(serv->sv_pools); kfree(serv); } EXPORT_SYMBOL_GPL(svc_destroy); static bool svc_init_buffer(struct svc_rqst *rqstp, unsigned int size, int node) { unsigned long pages, ret; /* bc_xprt uses fore channel allocated buffers */ if (svc_is_backchannel(rqstp)) return true; pages = size / PAGE_SIZE + 1; /* extra page as we hold both request and reply. * We assume one is at most one page */ WARN_ON_ONCE(pages > RPCSVC_MAXPAGES); if (pages > RPCSVC_MAXPAGES) pages = RPCSVC_MAXPAGES; ret = alloc_pages_bulk_array_node(GFP_KERNEL, node, pages, rqstp->rq_pages); return ret == pages; } /* * Release an RPC server buffer */ static void svc_release_buffer(struct svc_rqst *rqstp) { unsigned int i; for (i = 0; i < ARRAY_SIZE(rqstp->rq_pages); i++) if (rqstp->rq_pages[i]) put_page(rqstp->rq_pages[i]); } static void svc_rqst_free(struct svc_rqst *rqstp) { folio_batch_release(&rqstp->rq_fbatch); svc_release_buffer(rqstp); if (rqstp->rq_scratch_page) put_page(rqstp->rq_scratch_page); kfree(rqstp->rq_resp); kfree(rqstp->rq_argp); kfree(rqstp->rq_auth_data); kfree_rcu(rqstp, rq_rcu_head); } static struct svc_rqst * svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) { struct svc_rqst *rqstp; rqstp = kzalloc_node(sizeof(*rqstp), GFP_KERNEL, node); if (!rqstp) return rqstp; folio_batch_init(&rqstp->rq_fbatch); rqstp->rq_server = serv; rqstp->rq_pool = pool; rqstp->rq_scratch_page = alloc_pages_node(node, GFP_KERNEL, 0); if (!rqstp->rq_scratch_page) goto out_enomem; rqstp->rq_argp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node); if (!rqstp->rq_argp) goto out_enomem; rqstp->rq_resp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node); if (!rqstp->rq_resp) goto out_enomem; if (!svc_init_buffer(rqstp, serv->sv_max_mesg, node)) goto out_enomem; rqstp->rq_err = -EAGAIN; /* No error yet */ serv->sv_nrthreads += 1; pool->sp_nrthreads += 1; /* Protected by whatever lock the service uses when calling * svc_set_num_threads() */ list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads); return rqstp; out_enomem: svc_rqst_free(rqstp); return NULL; } /** * svc_pool_wake_idle_thread - Awaken an idle thread in @pool * @pool: service thread pool * * Can be called from soft IRQ or process context. Finding an idle * service thread and marking it BUSY is atomic with respect to * other calls to svc_pool_wake_idle_thread(). * */ void svc_pool_wake_idle_thread(struct svc_pool *pool) { struct svc_rqst *rqstp; struct llist_node *ln; rcu_read_lock(); ln = READ_ONCE(pool->sp_idle_threads.first); if (ln) { rqstp = llist_entry(ln, struct svc_rqst, rq_idle); WRITE_ONCE(rqstp->rq_qtime, ktime_get()); if (!task_is_running(rqstp->rq_task)) { wake_up_process(rqstp->rq_task); trace_svc_wake_up(rqstp->rq_task->pid); percpu_counter_inc(&pool->sp_threads_woken); } rcu_read_unlock(); return; } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(svc_pool_wake_idle_thread); static struct svc_pool * svc_pool_next(struct svc_serv *serv, struct svc_pool *pool, unsigned int *state) { return pool ? pool : &serv->sv_pools[(*state)++ % serv->sv_nrpools]; } static struct svc_pool * svc_pool_victim(struct svc_serv *serv, struct svc_pool *target_pool, unsigned int *state) { struct svc_pool *pool; unsigned int i; pool = target_pool; if (!pool) { for (i = 0; i < serv->sv_nrpools; i++) { pool = &serv->sv_pools[--(*state) % serv->sv_nrpools]; if (pool->sp_nrthreads) break; } } if (pool && pool->sp_nrthreads) { set_bit(SP_VICTIM_REMAINS, &pool->sp_flags); set_bit(SP_NEED_VICTIM, &pool->sp_flags); return pool; } return NULL; } static int svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) { struct svc_rqst *rqstp; struct task_struct *task; struct svc_pool *chosen_pool; unsigned int state = serv->sv_nrthreads-1; int node; int err; do { nrservs--; chosen_pool = svc_pool_next(serv, pool, &state); node = svc_pool_map_get_node(chosen_pool->sp_id); rqstp = svc_prepare_thread(serv, chosen_pool, node); if (!rqstp) return -ENOMEM; task = kthread_create_on_node(serv->sv_threadfn, rqstp, node, "%s", serv->sv_name); if (IS_ERR(task)) { svc_exit_thread(rqstp); return PTR_ERR(task); } rqstp->rq_task = task; if (serv->sv_nrpools > 1) svc_pool_map_set_cpumask(task, chosen_pool->sp_id); svc_sock_update_bufs(serv); wake_up_process(task); wait_var_event(&rqstp->rq_err, rqstp->rq_err != -EAGAIN); err = rqstp->rq_err; if (err) { svc_exit_thread(rqstp); return err; } } while (nrservs > 0); return 0; } static int svc_stop_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) { unsigned int state = serv->sv_nrthreads-1; struct svc_pool *victim; do { victim = svc_pool_victim(serv, pool, &state); if (!victim) break; svc_pool_wake_idle_thread(victim); wait_on_bit(&victim->sp_flags, SP_VICTIM_REMAINS, TASK_IDLE); nrservs++; } while (nrservs < 0); return 0; } /** * svc_set_num_threads - adjust number of threads per RPC service * @serv: RPC service to adjust * @pool: Specific pool from which to choose threads, or NULL * @nrservs: New number of threads for @serv (0 or less means kill all threads) * * Create or destroy threads to make the number of threads for @serv the * given number. If @pool is non-NULL, change only threads in that pool; * otherwise, round-robin between all pools for @serv. @serv's * sv_nrthreads is adjusted for each thread created or destroyed. * * Caller must ensure mutual exclusion between this and server startup or * shutdown. * * Returns zero on success or a negative errno if an error occurred while * starting a thread. */ int svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) { if (!pool) nrservs -= serv->sv_nrthreads; else nrservs -= pool->sp_nrthreads; if (nrservs > 0) return svc_start_kthreads(serv, pool, nrservs); if (nrservs < 0) return svc_stop_kthreads(serv, pool, nrservs); return 0; } EXPORT_SYMBOL_GPL(svc_set_num_threads); /** * svc_rqst_replace_page - Replace one page in rq_pages[] * @rqstp: svc_rqst with pages to replace * @page: replacement page * * When replacing a page in rq_pages, batch the release of the * replaced pages to avoid hammering the page allocator. * * Return values: * %true: page replaced * %false: array bounds checking failed */ bool svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page) { struct page **begin = rqstp->rq_pages; struct page **end = &rqstp->rq_pages[RPCSVC_MAXPAGES]; if (unlikely(rqstp->rq_next_page < begin || rqstp->rq_next_page > end)) { trace_svc_replace_page_err(rqstp); return false; } if (*rqstp->rq_next_page) { if (!folio_batch_add(&rqstp->rq_fbatch, page_folio(*rqstp->rq_next_page))) __folio_batch_release(&rqstp->rq_fbatch); } get_page(page); *(rqstp->rq_next_page++) = page; return true; } EXPORT_SYMBOL_GPL(svc_rqst_replace_page); /** * svc_rqst_release_pages - Release Reply buffer pages * @rqstp: RPC transaction context * * Release response pages that might still be in flight after * svc_send, and any spliced filesystem-owned pages. */ void svc_rqst_release_pages(struct svc_rqst *rqstp) { int i, count = rqstp->rq_next_page - rqstp->rq_respages; if (count) { release_pages(rqstp->rq_respages, count); for (i = 0; i < count; i++) rqstp->rq_respages[i] = NULL; } } /** * svc_exit_thread - finalise the termination of a sunrpc server thread * @rqstp: the svc_rqst which represents the thread. * * When a thread started with svc_new_thread() exits it must call * svc_exit_thread() as its last act. This must be done with the * service mutex held. Normally this is held by a DIFFERENT thread, the * one that is calling svc_set_num_threads() and which will wait for * SP_VICTIM_REMAINS to be cleared before dropping the mutex. If the * thread exits for any reason other than svc_thread_should_stop() * returning %true (which indicated that svc_set_num_threads() is * waiting for it to exit), then it must take the service mutex itself, * which can only safely be done using mutex_try_lock(). */ void svc_exit_thread(struct svc_rqst *rqstp) { struct svc_serv *serv = rqstp->rq_server; struct svc_pool *pool = rqstp->rq_pool; list_del_rcu(&rqstp->rq_all); pool->sp_nrthreads -= 1; serv->sv_nrthreads -= 1; svc_sock_update_bufs(serv); svc_rqst_free(rqstp); clear_and_wake_up_bit(SP_VICTIM_REMAINS, &pool->sp_flags); } EXPORT_SYMBOL_GPL(svc_exit_thread); /* * Register an "inet" protocol family netid with the local * rpcbind daemon via an rpcbind v4 SET request. * * No netconfig infrastructure is available in the kernel, so * we map IP_ protocol numbers to netids by hand. * * Returns zero on success; a negative errno value is returned * if any error occurs. */ static int __svc_rpcb_register4(struct net *net, const u32 program, const u32 version, const unsigned short protocol, const unsigned short port) { const struct sockaddr_in sin = { .sin_family = AF_INET, .sin_addr.s_addr = htonl(INADDR_ANY), .sin_port = htons(port), }; const char *netid; int error; switch (protocol) { case IPPROTO_UDP: netid = RPCBIND_NETID_UDP; break; case IPPROTO_TCP: netid = RPCBIND_NETID_TCP; break; default: return -ENOPROTOOPT; } error = rpcb_v4_register(net, program, version, (const struct sockaddr *)&sin, netid); /* * User space didn't support rpcbind v4, so retry this * registration request with the legacy rpcbind v2 protocol. */ if (error == -EPROTONOSUPPORT) error = rpcb_register(net, program, version, protocol, port); return error; } #if IS_ENABLED(CONFIG_IPV6) /* * Register an "inet6" protocol family netid with the local * rpcbind daemon via an rpcbind v4 SET request. * * No netconfig infrastructure is available in the kernel, so * we map IP_ protocol numbers to netids by hand. * * Returns zero on success; a negative errno value is returned * if any error occurs. */ static int __svc_rpcb_register6(struct net *net, const u32 program, const u32 version, const unsigned short protocol, const unsigned short port) { const struct sockaddr_in6 sin6 = { .sin6_family = AF_INET6, .sin6_addr = IN6ADDR_ANY_INIT, .sin6_port = htons(port), }; const char *netid; int error; switch (protocol) { case IPPROTO_UDP: netid = RPCBIND_NETID_UDP6; break; case IPPROTO_TCP: netid = RPCBIND_NETID_TCP6; break; default: return -ENOPROTOOPT; } error = rpcb_v4_register(net, program, version, (const struct sockaddr *)&sin6, netid); /* * User space didn't support rpcbind version 4, so we won't * use a PF_INET6 listener. */ if (error == -EPROTONOSUPPORT) error = -EAFNOSUPPORT; return error; } #endif /* IS_ENABLED(CONFIG_IPV6) */ /* * Register a kernel RPC service via rpcbind version 4. * * Returns zero on success; a negative errno value is returned * if any error occurs. */ static int __svc_register(struct net *net, const char *progname, const u32 program, const u32 version, const int family, const unsigned short protocol, const unsigned short port) { int error = -EAFNOSUPPORT; switch (family) { case PF_INET: error = __svc_rpcb_register4(net, program, version, protocol, port); break; #if IS_ENABLED(CONFIG_IPV6) case PF_INET6: error = __svc_rpcb_register6(net, program, version, protocol, port); #endif } trace_svc_register(progname, version, family, protocol, port, error); return error; } static int svc_rpcbind_set_version(struct net *net, const struct svc_program *progp, u32 version, int family, unsigned short proto, unsigned short port) { return __svc_register(net, progp->pg_name, progp->pg_prog, version, family, proto, port); } int svc_generic_rpcbind_set(struct net *net, const struct svc_program *progp, u32 version, int family, unsigned short proto, unsigned short port) { const struct svc_version *vers = progp->pg_vers[version]; int error; if (vers == NULL) return 0; if (vers->vs_hidden) { trace_svc_noregister(progp->pg_name, version, proto, port, family, 0); return 0; } /* * Don't register a UDP port if we need congestion * control. */ if (vers->vs_need_cong_ctrl && proto == IPPROTO_UDP) return 0; error = svc_rpcbind_set_version(net, progp, version, family, proto, port); return (vers->vs_rpcb_optnl) ? 0 : error; } EXPORT_SYMBOL_GPL(svc_generic_rpcbind_set); /** * svc_register - register an RPC service with the local portmapper * @serv: svc_serv struct for the service to register * @net: net namespace for the service to register * @family: protocol family of service's listener socket * @proto: transport protocol number to advertise * @port: port to advertise * * Service is registered for any address in the passed-in protocol family */ int svc_register(const struct svc_serv *serv, struct net *net, const int family, const unsigned short proto, const unsigned short port) { unsigned int p, i; int error = 0; WARN_ON_ONCE(proto == 0 && port == 0); if (proto == 0 && port == 0) return -EINVAL; for (p = 0; p < serv->sv_nprogs; p++) { struct svc_program *progp = &serv->sv_programs[p]; for (i = 0; i < progp->pg_nvers; i++) { error = progp->pg_rpcbind_set(net, progp, i, family, proto, port); if (error < 0) { printk(KERN_WARNING "svc: failed to register " "%sv%u RPC service (errno %d).\n", progp->pg_name, i, -error); break; } } } return error; } /* * If user space is running rpcbind, it should take the v4 UNSET * and clear everything for this [program, version]. If user space * is running portmap, it will reject the v4 UNSET, but won't have * any "inet6" entries anyway. So a PMAP_UNSET should be sufficient * in this case to clear all existing entries for [program, version]. */ static void __svc_unregister(struct net *net, const u32 program, const u32 version, const char *progname) { int error; error = rpcb_v4_register(net, program, version, NULL, ""); /* * User space didn't support rpcbind v4, so retry this * request with the legacy rpcbind v2 protocol. */ if (error == -EPROTONOSUPPORT) error = rpcb_register(net, program, version, 0, 0); trace_svc_unregister(progname, version, error); } /* * All netids, bind addresses and ports registered for [program, version] * are removed from the local rpcbind database (if the service is not * hidden) to make way for a new instance of the service. * * The result of unregistration is reported via dprintk for those who want * verification of the result, but is otherwise not important. */ static void svc_unregister(const struct svc_serv *serv, struct net *net) { struct sighand_struct *sighand; unsigned long flags; unsigned int p, i; clear_thread_flag(TIF_SIGPENDING); for (p = 0; p < serv->sv_nprogs; p++) { struct svc_program *progp = &serv->sv_programs[p]; for (i = 0; i < progp->pg_nvers; i++) { if (progp->pg_vers[i] == NULL) continue; if (progp->pg_vers[i]->vs_hidden) continue; __svc_unregister(net, progp->pg_prog, i, progp->pg_name); } } rcu_read_lock(); sighand = rcu_dereference(current->sighand); spin_lock_irqsave(&sighand->siglock, flags); recalc_sigpending(); spin_unlock_irqrestore(&sighand->siglock, flags); rcu_read_unlock(); } /* * dprintk the given error with the address of the client that caused it. */ #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static __printf(2, 3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) { struct va_format vaf; va_list args; char buf[RPC_MAX_ADDRBUFLEN]; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; dprintk("svc: %s: %pV", svc_print_addr(rqstp, buf, sizeof(buf)), &vaf); va_end(args); } #else static __printf(2,3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) {} #endif __be32 svc_generic_init_request(struct svc_rqst *rqstp, const struct svc_program *progp, struct svc_process_info *ret) { const struct svc_version *versp = NULL; /* compiler food */ const struct svc_procedure *procp = NULL; if (rqstp->rq_vers >= progp->pg_nvers ) goto err_bad_vers; versp = progp->pg_vers[rqstp->rq_vers]; if (!versp) goto err_bad_vers; /* * Some protocol versions (namely NFSv4) require some form of * congestion control. (See RFC 7530 section 3.1 paragraph 2) * In other words, UDP is not allowed. We mark those when setting * up the svc_xprt, and verify that here. * * The spec is not very clear about what error should be returned * when someone tries to access a server that is listening on UDP * for lower versions. RPC_PROG_MISMATCH seems to be the closest * fit. */ if (versp->vs_need_cong_ctrl && rqstp->rq_xprt && !test_bit(XPT_CONG_CTRL, &rqstp->rq_xprt->xpt_flags)) goto err_bad_vers; if (rqstp->rq_proc >= versp->vs_nproc) goto err_bad_proc; rqstp->rq_procinfo = procp = &versp->vs_proc[rqstp->rq_proc]; /* Initialize storage for argp and resp */ memset(rqstp->rq_argp, 0, procp->pc_argzero); memset(rqstp->rq_resp, 0, procp->pc_ressize); /* Bump per-procedure stats counter */ this_cpu_inc(versp->vs_count[rqstp->rq_proc]); ret->dispatch = versp->vs_dispatch; return rpc_success; err_bad_vers: ret->mismatch.lovers = progp->pg_lovers; ret->mismatch.hivers = progp->pg_hivers; return rpc_prog_mismatch; err_bad_proc: return rpc_proc_unavail; } EXPORT_SYMBOL_GPL(svc_generic_init_request); /* * Common routine for processing the RPC request. */ static int svc_process_common(struct svc_rqst *rqstp) { struct xdr_stream *xdr = &rqstp->rq_res_stream; struct svc_program *progp = NULL; const struct svc_procedure *procp = NULL; struct svc_serv *serv = rqstp->rq_server; struct svc_process_info process; enum svc_auth_status auth_res; unsigned int aoffset; int pr, rc; __be32 *p; /* Will be turned off only when NFSv4 Sessions are used */ set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); clear_bit(RQ_DROPME, &rqstp->rq_flags); /* Construct the first words of the reply: */ svcxdr_init_encode(rqstp); xdr_stream_encode_be32(xdr, rqstp->rq_xid); xdr_stream_encode_be32(xdr, rpc_reply); p = xdr_inline_decode(&rqstp->rq_arg_stream, XDR_UNIT * 4); if (unlikely(!p)) goto err_short_len; if (*p++ != cpu_to_be32(RPC_VERSION)) goto err_bad_rpc; xdr_stream_encode_be32(xdr, rpc_msg_accepted); rqstp->rq_prog = be32_to_cpup(p++); rqstp->rq_vers = be32_to_cpup(p++); rqstp->rq_proc = be32_to_cpup(p); for (pr = 0; pr < serv->sv_nprogs; pr++) if (rqstp->rq_prog == serv->sv_programs[pr].pg_prog) progp = &serv->sv_programs[pr]; /* * Decode auth data, and add verifier to reply buffer. * We do this before anything else in order to get a decent * auth verifier. */ auth_res = svc_authenticate(rqstp); /* Also give the program a chance to reject this call: */ if (auth_res == SVC_OK && progp) auth_res = progp->pg_authenticate(rqstp); trace_svc_authenticate(rqstp, auth_res); switch (auth_res) { case SVC_OK: break; case SVC_GARBAGE: goto err_garbage_args; case SVC_SYSERR: goto err_system_err; case SVC_DENIED: goto err_bad_auth; case SVC_CLOSE: goto close; case SVC_DROP: goto dropit; case SVC_COMPLETE: goto sendit; default: pr_warn_once("Unexpected svc_auth_status (%d)\n", auth_res); goto err_system_err; } if (progp == NULL) goto err_bad_prog; switch (progp->pg_init_request(rqstp, progp, &process)) { case rpc_success: break; case rpc_prog_unavail: goto err_bad_prog; case rpc_prog_mismatch: goto err_bad_vers; case rpc_proc_unavail: goto err_bad_proc; } procp = rqstp->rq_procinfo; /* Should this check go into the dispatcher? */ if (!procp || !procp->pc_func) goto err_bad_proc; /* Syntactic check complete */ if (serv->sv_stats) serv->sv_stats->rpccnt++; trace_svc_process(rqstp, progp->pg_name); aoffset = xdr_stream_pos(xdr); /* un-reserve some of the out-queue now that we have a * better idea of reply size */ if (procp->pc_xdrressize) svc_reserve_auth(rqstp, procp->pc_xdrressize<<2); /* Call the function that processes the request. */ rc = process.dispatch(rqstp); if (procp->pc_release) procp->pc_release(rqstp); xdr_finish_decode(xdr); if (!rc) goto dropit; if (rqstp->rq_auth_stat != rpc_auth_ok) goto err_bad_auth; if (*rqstp->rq_accept_statp != rpc_success) xdr_truncate_encode(xdr, aoffset); if (procp->pc_encode == NULL) goto dropit; sendit: if (svc_authorise(rqstp)) goto close_xprt; return 1; /* Caller can now send it */ dropit: svc_authorise(rqstp); /* doesn't hurt to call this twice */ dprintk("svc: svc_process dropit\n"); return 0; close: svc_authorise(rqstp); close_xprt: if (rqstp->rq_xprt && test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags)) svc_xprt_close(rqstp->rq_xprt); dprintk("svc: svc_process close\n"); return 0; err_short_len: svc_printk(rqstp, "short len %u, dropping request\n", rqstp->rq_arg.len); goto close_xprt; err_bad_rpc: if (serv->sv_stats) serv->sv_stats->rpcbadfmt++; xdr_stream_encode_u32(xdr, RPC_MSG_DENIED); xdr_stream_encode_u32(xdr, RPC_MISMATCH); /* Only RPCv2 supported */ xdr_stream_encode_u32(xdr, RPC_VERSION); xdr_stream_encode_u32(xdr, RPC_VERSION); return 1; /* don't wrap */ err_bad_auth: dprintk("svc: authentication failed (%d)\n", be32_to_cpu(rqstp->rq_auth_stat)); if (serv->sv_stats) serv->sv_stats->rpcbadauth++; /* Restore write pointer to location of reply status: */ xdr_truncate_encode(xdr, XDR_UNIT * 2); xdr_stream_encode_u32(xdr, RPC_MSG_DENIED); xdr_stream_encode_u32(xdr, RPC_AUTH_ERROR); xdr_stream_encode_be32(xdr, rqstp->rq_auth_stat); goto sendit; err_bad_prog: dprintk("svc: unknown program %d\n", rqstp->rq_prog); if (serv->sv_stats) serv->sv_stats->rpcbadfmt++; *rqstp->rq_accept_statp = rpc_prog_unavail; goto sendit; err_bad_vers: svc_printk(rqstp, "unknown version (%d for prog %d, %s)\n", rqstp->rq_vers, rqstp->rq_prog, progp->pg_name); if (serv->sv_stats) serv->sv_stats->rpcbadfmt++; *rqstp->rq_accept_statp = rpc_prog_mismatch; /* * svc_authenticate() has already added the verifier and * advanced the stream just past rq_accept_statp. */ xdr_stream_encode_u32(xdr, process.mismatch.lovers); xdr_stream_encode_u32(xdr, process.mismatch.hivers); goto sendit; err_bad_proc: svc_printk(rqstp, "unknown procedure (%d)\n", rqstp->rq_proc); if (serv->sv_stats) serv->sv_stats->rpcbadfmt++; *rqstp->rq_accept_statp = rpc_proc_unavail; goto sendit; err_garbage_args: svc_printk(rqstp, "failed to decode RPC header\n"); if (serv->sv_stats) serv->sv_stats->rpcbadfmt++; *rqstp->rq_accept_statp = rpc_garbage_args; goto sendit; err_system_err: if (serv->sv_stats) serv->sv_stats->rpcbadfmt++; *rqstp->rq_accept_statp = rpc_system_err; goto sendit; } /* * Drop request */ static void svc_drop(struct svc_rqst *rqstp) { trace_svc_drop(rqstp); } /** * svc_process - Execute one RPC transaction * @rqstp: RPC transaction context * */ void svc_process(struct svc_rqst *rqstp) { struct kvec *resv = &rqstp->rq_res.head[0]; __be32 *p; #if IS_ENABLED(CONFIG_FAIL_SUNRPC) if (!fail_sunrpc.ignore_server_disconnect && should_fail(&fail_sunrpc.attr, 1)) svc_xprt_deferred_close(rqstp->rq_xprt); #endif /* * Setup response xdr_buf. * Initially it has just one page */ rqstp->rq_next_page = &rqstp->rq_respages[1]; resv->iov_base = page_address(rqstp->rq_respages[0]); resv->iov_len = 0; rqstp->rq_res.pages = rqstp->rq_next_page; rqstp->rq_res.len = 0; rqstp->rq_res.page_base = 0; rqstp->rq_res.page_len = 0; rqstp->rq_res.buflen = PAGE_SIZE; rqstp->rq_res.tail[0].iov_base = NULL; rqstp->rq_res.tail[0].iov_len = 0; svcxdr_init_decode(rqstp); p = xdr_inline_decode(&rqstp->rq_arg_stream, XDR_UNIT * 2); if (unlikely(!p)) goto out_drop; rqstp->rq_xid = *p++; if (unlikely(*p != rpc_call)) goto out_baddir; if (!svc_process_common(rqstp)) goto out_drop; svc_send(rqstp); return; out_baddir: svc_printk(rqstp, "bad direction 0x%08x, dropping request\n", be32_to_cpu(*p)); if (rqstp->rq_server->sv_stats) rqstp->rq_server->sv_stats->rpcbadfmt++; out_drop: svc_drop(rqstp); } #if defined(CONFIG_SUNRPC_BACKCHANNEL) /** * svc_process_bc - process a reverse-direction RPC request * @req: RPC request to be used for client-side processing * @rqstp: server-side execution context * */ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp) { struct rpc_timeout timeout = { .to_increment = 0, }; struct rpc_task *task; int proc_error; /* Build the svc_rqst used by the common processing routine */ rqstp->rq_xid = req->rq_xid; rqstp->rq_prot = req->rq_xprt->prot; rqstp->rq_bc_net = req->rq_xprt->xprt_net; rqstp->rq_addrlen = sizeof(req->rq_xprt->addr); memcpy(&rqstp->rq_addr, &req->rq_xprt->addr, rqstp->rq_addrlen); memcpy(&rqstp->rq_arg, &req->rq_rcv_buf, sizeof(rqstp->rq_arg)); memcpy(&rqstp->rq_res, &req->rq_snd_buf, sizeof(rqstp->rq_res)); /* Adjust the argument buffer length */ rqstp->rq_arg.len = req->rq_private_buf.len; if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len) { rqstp->rq_arg.head[0].iov_len = rqstp->rq_arg.len; rqstp->rq_arg.page_len = 0; } else if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len) rqstp->rq_arg.page_len = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len; else rqstp->rq_arg.len = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len; /* Reset the response buffer */ rqstp->rq_res.head[0].iov_len = 0; /* * Skip the XID and calldir fields because they've already * been processed by the caller. */ svcxdr_init_decode(rqstp); if (!xdr_inline_decode(&rqstp->rq_arg_stream, XDR_UNIT * 2)) return; /* Parse and execute the bc call */ proc_error = svc_process_common(rqstp); atomic_dec(&req->rq_xprt->bc_slot_count); if (!proc_error) { /* Processing error: drop the request */ xprt_free_bc_request(req); return; } /* Finally, send the reply synchronously */ if (rqstp->bc_to_initval > 0) { timeout.to_initval = rqstp->bc_to_initval; timeout.to_retries = rqstp->bc_to_retries; } else { timeout.to_initval = req->rq_xprt->timeout->to_initval; timeout.to_retries = req->rq_xprt->timeout->to_retries; } timeout.to_maxval = timeout.to_initval; memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf)); task = rpc_run_bc_task(req, &timeout); if (IS_ERR(task)) return; WARN_ON_ONCE(atomic_read(&task->tk_count) != 1); rpc_put_task(task); } #endif /* CONFIG_SUNRPC_BACKCHANNEL */ /** * svc_max_payload - Return transport-specific limit on the RPC payload * @rqstp: RPC transaction context * * Returns the maximum number of payload bytes the current transport * allows. */ u32 svc_max_payload(const struct svc_rqst *rqstp) { u32 max = rqstp->rq_xprt->xpt_class->xcl_max_payload; if (rqstp->rq_server->sv_max_payload < max) max = rqstp->rq_server->sv_max_payload; return max; } EXPORT_SYMBOL_GPL(svc_max_payload); /** * svc_proc_name - Return RPC procedure name in string form * @rqstp: svc_rqst to operate on * * Return value: * Pointer to a NUL-terminated string */ const char *svc_proc_name(const struct svc_rqst *rqstp) { if (rqstp && rqstp->rq_procinfo) return rqstp->rq_procinfo->pc_name; return "unknown"; } /** * svc_encode_result_payload - mark a range of bytes as a result payload * @rqstp: svc_rqst to operate on * @offset: payload's byte offset in rqstp->rq_res * @length: size of payload, in bytes * * Returns zero on success, or a negative errno if a permanent * error occurred. */ int svc_encode_result_payload(struct svc_rqst *rqstp, unsigned int offset, unsigned int length) { return rqstp->rq_xprt->xpt_ops->xpo_result_payload(rqstp, offset, length); } EXPORT_SYMBOL_GPL(svc_encode_result_payload); /** * svc_fill_write_vector - Construct data argument for VFS write call * @rqstp: svc_rqst to operate on * @payload: xdr_buf containing only the write data payload * * Fills in rqstp::rq_vec, and returns the number of elements. */ unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, struct xdr_buf *payload) { struct page **pages = payload->pages; struct kvec *first = payload->head; struct kvec *vec = rqstp->rq_vec; size_t total = payload->len; unsigned int i; /* Some types of transport can present the write payload * entirely in rq_arg.pages. In this case, @first is empty. */ i = 0; if (first->iov_len) { vec[i].iov_base = first->iov_base; vec[i].iov_len = min_t(size_t, total, first->iov_len); total -= vec[i].iov_len; ++i; } while (total) { vec[i].iov_base = page_address(*pages); vec[i].iov_len = min_t(size_t, total, PAGE_SIZE); total -= vec[i].iov_len; ++i; ++pages; } WARN_ON_ONCE(i > ARRAY_SIZE(rqstp->rq_vec)); return i; } EXPORT_SYMBOL_GPL(svc_fill_write_vector); /** * svc_fill_symlink_pathname - Construct pathname argument for VFS symlink call * @rqstp: svc_rqst to operate on * @first: buffer containing first section of pathname * @p: buffer containing remaining section of pathname * @total: total length of the pathname argument * * The VFS symlink API demands a NUL-terminated pathname in mapped memory. * Returns pointer to a NUL-terminated string, or an ERR_PTR. Caller must free * the returned string. */ char *svc_fill_symlink_pathname(struct svc_rqst *rqstp, struct kvec *first, void *p, size_t total) { size_t len, remaining; char *result, *dst; result = kmalloc(total + 1, GFP_KERNEL); if (!result) return ERR_PTR(-ESERVERFAULT); dst = result; remaining = total; len = min_t(size_t, total, first->iov_len); if (len) { memcpy(dst, first->iov_base, len); dst += len; remaining -= len; } if (remaining) { len = min_t(size_t, remaining, PAGE_SIZE); memcpy(dst, p, len); dst += len; } *dst = '\0'; /* Sanity check: Linux doesn't allow the pathname argument to * contain a NUL byte. */ if (strlen(result) != total) { kfree(result); return ERR_PTR(-EINVAL); } return result; } EXPORT_SYMBOL_GPL(svc_fill_symlink_pathname); |
| 4 4 4 2 2 4 2 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Cryptographic API. * * RIPEMD-160 - RACE Integrity Primitives Evaluation Message Digest. * * Based on the reference implementation by Antoon Bosselaers, ESAT-COSIC * * Copyright (c) 2008 Adrian-Ken Rueegsegger <ken@codelabs.ch> */ #include <crypto/internal/hash.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/types.h> #include <asm/byteorder.h> #include "ripemd.h" struct rmd160_ctx { u64 byte_count; u32 state[5]; __le32 buffer[16]; }; #define K1 RMD_K1 #define K2 RMD_K2 #define K3 RMD_K3 #define K4 RMD_K4 #define K5 RMD_K5 #define KK1 RMD_K6 #define KK2 RMD_K7 #define KK3 RMD_K8 #define KK4 RMD_K9 #define KK5 RMD_K1 #define F1(x, y, z) (x ^ y ^ z) /* XOR */ #define F2(x, y, z) (z ^ (x & (y ^ z))) /* x ? y : z */ #define F3(x, y, z) ((x | ~y) ^ z) #define F4(x, y, z) (y ^ (z & (x ^ y))) /* z ? x : y */ #define F5(x, y, z) (x ^ (y | ~z)) #define ROUND(a, b, c, d, e, f, k, x, s) { \ (a) += f((b), (c), (d)) + le32_to_cpup(&(x)) + (k); \ (a) = rol32((a), (s)) + (e); \ (c) = rol32((c), 10); \ } static void rmd160_transform(u32 *state, const __le32 *in) { u32 aa, bb, cc, dd, ee, aaa, bbb, ccc, ddd, eee; /* Initialize left lane */ aa = state[0]; bb = state[1]; cc = state[2]; dd = state[3]; ee = state[4]; /* Initialize right lane */ aaa = state[0]; bbb = state[1]; ccc = state[2]; ddd = state[3]; eee = state[4]; /* round 1: left lane */ ROUND(aa, bb, cc, dd, ee, F1, K1, in[0], 11); ROUND(ee, aa, bb, cc, dd, F1, K1, in[1], 14); ROUND(dd, ee, aa, bb, cc, F1, K1, in[2], 15); ROUND(cc, dd, ee, aa, bb, F1, K1, in[3], 12); ROUND(bb, cc, dd, ee, aa, F1, K1, in[4], 5); ROUND(aa, bb, cc, dd, ee, F1, K1, in[5], 8); ROUND(ee, aa, bb, cc, dd, F1, K1, in[6], 7); ROUND(dd, ee, aa, bb, cc, F1, K1, in[7], 9); ROUND(cc, dd, ee, aa, bb, F1, K1, in[8], 11); ROUND(bb, cc, dd, ee, aa, F1, K1, in[9], 13); ROUND(aa, bb, cc, dd, ee, F1, K1, in[10], 14); ROUND(ee, aa, bb, cc, dd, F1, K1, in[11], 15); ROUND(dd, ee, aa, bb, cc, F1, K1, in[12], 6); ROUND(cc, dd, ee, aa, bb, F1, K1, in[13], 7); ROUND(bb, cc, dd, ee, aa, F1, K1, in[14], 9); ROUND(aa, bb, cc, dd, ee, F1, K1, in[15], 8); /* round 2: left lane" */ ROUND(ee, aa, bb, cc, dd, F2, K2, in[7], 7); ROUND(dd, ee, aa, bb, cc, F2, K2, in[4], 6); ROUND(cc, dd, ee, aa, bb, F2, K2, in[13], 8); ROUND(bb, cc, dd, ee, aa, F2, K2, in[1], 13); ROUND(aa, bb, cc, dd, ee, F2, K2, in[10], 11); ROUND(ee, aa, bb, cc, dd, F2, K2, in[6], 9); ROUND(dd, ee, aa, bb, cc, F2, K2, in[15], 7); ROUND(cc, dd, ee, aa, bb, F2, K2, in[3], 15); ROUND(bb, cc, dd, ee, aa, F2, K2, in[12], 7); ROUND(aa, bb, cc, dd, ee, F2, K2, in[0], 12); ROUND(ee, aa, bb, cc, dd, F2, K2, in[9], 15); ROUND(dd, ee, aa, bb, cc, F2, K2, in[5], 9); ROUND(cc, dd, ee, aa, bb, F2, K2, in[2], 11); ROUND(bb, cc, dd, ee, aa, F2, K2, in[14], 7); ROUND(aa, bb, cc, dd, ee, F2, K2, in[11], 13); ROUND(ee, aa, bb, cc, dd, F2, K2, in[8], 12); /* round 3: left lane" */ ROUND(dd, ee, aa, bb, cc, F3, K3, in[3], 11); ROUND(cc, dd, ee, aa, bb, F3, K3, in[10], 13); ROUND(bb, cc, dd, ee, aa, F3, K3, in[14], 6); ROUND(aa, bb, cc, dd, ee, F3, K3, in[4], 7); ROUND(ee, aa, bb, cc, dd, F3, K3, in[9], 14); ROUND(dd, ee, aa, bb, cc, F3, K3, in[15], 9); ROUND(cc, dd, ee, aa, bb, F3, K3, in[8], 13); ROUND(bb, cc, dd, ee, aa, F3, K3, in[1], 15); ROUND(aa, bb, cc, dd, ee, F3, K3, in[2], 14); ROUND(ee, aa, bb, cc, dd, F3, K3, in[7], 8); ROUND(dd, ee, aa, bb, cc, F3, K3, in[0], 13); ROUND(cc, dd, ee, aa, bb, F3, K3, in[6], 6); ROUND(bb, cc, dd, ee, aa, F3, K3, in[13], 5); ROUND(aa, bb, cc, dd, ee, F3, K3, in[11], 12); ROUND(ee, aa, bb, cc, dd, F3, K3, in[5], 7); ROUND(dd, ee, aa, bb, cc, F3, K3, in[12], 5); /* round 4: left lane" */ ROUND(cc, dd, ee, aa, bb, F4, K4, in[1], 11); ROUND(bb, cc, dd, ee, aa, F4, K4, in[9], 12); ROUND(aa, bb, cc, dd, ee, F4, K4, in[11], 14); ROUND(ee, aa, bb, cc, dd, F4, K4, in[10], 15); ROUND(dd, ee, aa, bb, cc, F4, K4, in[0], 14); ROUND(cc, dd, ee, aa, bb, F4, K4, in[8], 15); ROUND(bb, cc, dd, ee, aa, F4, K4, in[12], 9); ROUND(aa, bb, cc, dd, ee, F4, K4, in[4], 8); ROUND(ee, aa, bb, cc, dd, F4, K4, in[13], 9); ROUND(dd, ee, aa, bb, cc, F4, K4, in[3], 14); ROUND(cc, dd, ee, aa, bb, F4, K4, in[7], 5); ROUND(bb, cc, dd, ee, aa, F4, K4, in[15], 6); ROUND(aa, bb, cc, dd, ee, F4, K4, in[14], 8); ROUND(ee, aa, bb, cc, dd, F4, K4, in[5], 6); ROUND(dd, ee, aa, bb, cc, F4, K4, in[6], 5); ROUND(cc, dd, ee, aa, bb, F4, K4, in[2], 12); /* round 5: left lane" */ ROUND(bb, cc, dd, ee, aa, F5, K5, in[4], 9); ROUND(aa, bb, cc, dd, ee, F5, K5, in[0], 15); ROUND(ee, aa, bb, cc, dd, F5, K5, in[5], 5); ROUND(dd, ee, aa, bb, cc, F5, K5, in[9], 11); ROUND(cc, dd, ee, aa, bb, F5, K5, in[7], 6); ROUND(bb, cc, dd, ee, aa, F5, K5, in[12], 8); ROUND(aa, bb, cc, dd, ee, F5, K5, in[2], 13); ROUND(ee, aa, bb, cc, dd, F5, K5, in[10], 12); ROUND(dd, ee, aa, bb, cc, F5, K5, in[14], 5); ROUND(cc, dd, ee, aa, bb, F5, K5, in[1], 12); ROUND(bb, cc, dd, ee, aa, F5, K5, in[3], 13); ROUND(aa, bb, cc, dd, ee, F5, K5, in[8], 14); ROUND(ee, aa, bb, cc, dd, F5, K5, in[11], 11); ROUND(dd, ee, aa, bb, cc, F5, K5, in[6], 8); ROUND(cc, dd, ee, aa, bb, F5, K5, in[15], 5); ROUND(bb, cc, dd, ee, aa, F5, K5, in[13], 6); /* round 1: right lane */ ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[5], 8); ROUND(eee, aaa, bbb, ccc, ddd, F5, KK1, in[14], 9); ROUND(ddd, eee, aaa, bbb, ccc, F5, KK1, in[7], 9); ROUND(ccc, ddd, eee, aaa, bbb, F5, KK1, in[0], 11); ROUND(bbb, ccc, ddd, eee, aaa, F5, KK1, in[9], 13); ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[2], 15); ROUND(eee, aaa, bbb, ccc, ddd, F5, KK1, in[11], 15); ROUND(ddd, eee, aaa, bbb, ccc, F5, KK1, in[4], 5); ROUND(ccc, ddd, eee, aaa, bbb, F5, KK1, in[13], 7); ROUND(bbb, ccc, ddd, eee, aaa, F5, KK1, in[6], 7); ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[15], 8); ROUND(eee, aaa, bbb, ccc, ddd, F5, KK1, in[8], 11); ROUND(ddd, eee, aaa, bbb, ccc, F5, KK1, in[1], 14); ROUND(ccc, ddd, eee, aaa, bbb, F5, KK1, in[10], 14); ROUND(bbb, ccc, ddd, eee, aaa, F5, KK1, in[3], 12); ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[12], 6); /* round 2: right lane */ ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[6], 9); ROUND(ddd, eee, aaa, bbb, ccc, F4, KK2, in[11], 13); ROUND(ccc, ddd, eee, aaa, bbb, F4, KK2, in[3], 15); ROUND(bbb, ccc, ddd, eee, aaa, F4, KK2, in[7], 7); ROUND(aaa, bbb, ccc, ddd, eee, F4, KK2, in[0], 12); ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[13], 8); ROUND(ddd, eee, aaa, bbb, ccc, F4, KK2, in[5], 9); ROUND(ccc, ddd, eee, aaa, bbb, F4, KK2, in[10], 11); ROUND(bbb, ccc, ddd, eee, aaa, F4, KK2, in[14], 7); ROUND(aaa, bbb, ccc, ddd, eee, F4, KK2, in[15], 7); ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[8], 12); ROUND(ddd, eee, aaa, bbb, ccc, F4, KK2, in[12], 7); ROUND(ccc, ddd, eee, aaa, bbb, F4, KK2, in[4], 6); ROUND(bbb, ccc, ddd, eee, aaa, F4, KK2, in[9], 15); ROUND(aaa, bbb, ccc, ddd, eee, F4, KK2, in[1], 13); ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[2], 11); /* round 3: right lane */ ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[15], 9); ROUND(ccc, ddd, eee, aaa, bbb, F3, KK3, in[5], 7); ROUND(bbb, ccc, ddd, eee, aaa, F3, KK3, in[1], 15); ROUND(aaa, bbb, ccc, ddd, eee, F3, KK3, in[3], 11); ROUND(eee, aaa, bbb, ccc, ddd, F3, KK3, in[7], 8); ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[14], 6); ROUND(ccc, ddd, eee, aaa, bbb, F3, KK3, in[6], 6); ROUND(bbb, ccc, ddd, eee, aaa, F3, KK3, in[9], 14); ROUND(aaa, bbb, ccc, ddd, eee, F3, KK3, in[11], 12); ROUND(eee, aaa, bbb, ccc, ddd, F3, KK3, in[8], 13); ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[12], 5); ROUND(ccc, ddd, eee, aaa, bbb, F3, KK3, in[2], 14); ROUND(bbb, ccc, ddd, eee, aaa, F3, KK3, in[10], 13); ROUND(aaa, bbb, ccc, ddd, eee, F3, KK3, in[0], 13); ROUND(eee, aaa, bbb, ccc, ddd, F3, KK3, in[4], 7); ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[13], 5); /* round 4: right lane */ ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[8], 15); ROUND(bbb, ccc, ddd, eee, aaa, F2, KK4, in[6], 5); ROUND(aaa, bbb, ccc, ddd, eee, F2, KK4, in[4], 8); ROUND(eee, aaa, bbb, ccc, ddd, F2, KK4, in[1], 11); ROUND(ddd, eee, aaa, bbb, ccc, F2, KK4, in[3], 14); ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[11], 14); ROUND(bbb, ccc, ddd, eee, aaa, F2, KK4, in[15], 6); ROUND(aaa, bbb, ccc, ddd, eee, F2, KK4, in[0], 14); ROUND(eee, aaa, bbb, ccc, ddd, F2, KK4, in[5], 6); ROUND(ddd, eee, aaa, bbb, ccc, F2, KK4, in[12], 9); ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[2], 12); ROUND(bbb, ccc, ddd, eee, aaa, F2, KK4, in[13], 9); ROUND(aaa, bbb, ccc, ddd, eee, F2, KK4, in[9], 12); ROUND(eee, aaa, bbb, ccc, ddd, F2, KK4, in[7], 5); ROUND(ddd, eee, aaa, bbb, ccc, F2, KK4, in[10], 15); ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[14], 8); /* round 5: right lane */ ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[12], 8); ROUND(aaa, bbb, ccc, ddd, eee, F1, KK5, in[15], 5); ROUND(eee, aaa, bbb, ccc, ddd, F1, KK5, in[10], 12); ROUND(ddd, eee, aaa, bbb, ccc, F1, KK5, in[4], 9); ROUND(ccc, ddd, eee, aaa, bbb, F1, KK5, in[1], 12); ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[5], 5); ROUND(aaa, bbb, ccc, ddd, eee, F1, KK5, in[8], 14); ROUND(eee, aaa, bbb, ccc, ddd, F1, KK5, in[7], 6); ROUND(ddd, eee, aaa, bbb, ccc, F1, KK5, in[6], 8); ROUND(ccc, ddd, eee, aaa, bbb, F1, KK5, in[2], 13); ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[13], 6); ROUND(aaa, bbb, ccc, ddd, eee, F1, KK5, in[14], 5); ROUND(eee, aaa, bbb, ccc, ddd, F1, KK5, in[0], 15); ROUND(ddd, eee, aaa, bbb, ccc, F1, KK5, in[3], 13); ROUND(ccc, ddd, eee, aaa, bbb, F1, KK5, in[9], 11); ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[11], 11); /* combine results */ ddd += cc + state[1]; /* final result for state[0] */ state[1] = state[2] + dd + eee; state[2] = state[3] + ee + aaa; state[3] = state[4] + aa + bbb; state[4] = state[0] + bb + ccc; state[0] = ddd; } static int rmd160_init(struct shash_desc *desc) { struct rmd160_ctx *rctx = shash_desc_ctx(desc); rctx->byte_count = 0; rctx->state[0] = RMD_H0; rctx->state[1] = RMD_H1; rctx->state[2] = RMD_H2; rctx->state[3] = RMD_H3; rctx->state[4] = RMD_H4; memset(rctx->buffer, 0, sizeof(rctx->buffer)); return 0; } static int rmd160_update(struct shash_desc *desc, const u8 *data, unsigned int len) { struct rmd160_ctx *rctx = shash_desc_ctx(desc); const u32 avail = sizeof(rctx->buffer) - (rctx->byte_count & 0x3f); rctx->byte_count += len; /* Enough space in buffer? If so copy and we're done */ if (avail > len) { memcpy((char *)rctx->buffer + (sizeof(rctx->buffer) - avail), data, len); goto out; } memcpy((char *)rctx->buffer + (sizeof(rctx->buffer) - avail), data, avail); rmd160_transform(rctx->state, rctx->buffer); data += avail; len -= avail; while (len >= sizeof(rctx->buffer)) { memcpy(rctx->buffer, data, sizeof(rctx->buffer)); rmd160_transform(rctx->state, rctx->buffer); data += sizeof(rctx->buffer); len -= sizeof(rctx->buffer); } memcpy(rctx->buffer, data, len); out: return 0; } /* Add padding and return the message digest. */ static int rmd160_final(struct shash_desc *desc, u8 *out) { struct rmd160_ctx *rctx = shash_desc_ctx(desc); u32 i, index, padlen; __le64 bits; __le32 *dst = (__le32 *)out; static const u8 padding[64] = { 0x80, }; bits = cpu_to_le64(rctx->byte_count << 3); /* Pad out to 56 mod 64 */ index = rctx->byte_count & 0x3f; padlen = (index < 56) ? (56 - index) : ((64+56) - index); rmd160_update(desc, padding, padlen); /* Append length */ rmd160_update(desc, (const u8 *)&bits, sizeof(bits)); /* Store state in digest */ for (i = 0; i < 5; i++) dst[i] = cpu_to_le32p(&rctx->state[i]); /* Wipe context */ memset(rctx, 0, sizeof(*rctx)); return 0; } static struct shash_alg alg = { .digestsize = RMD160_DIGEST_SIZE, .init = rmd160_init, .update = rmd160_update, .final = rmd160_final, .descsize = sizeof(struct rmd160_ctx), .base = { .cra_name = "rmd160", .cra_driver_name = "rmd160-generic", .cra_blocksize = RMD160_BLOCK_SIZE, .cra_module = THIS_MODULE, } }; static int __init rmd160_mod_init(void) { return crypto_register_shash(&alg); } static void __exit rmd160_mod_fini(void) { crypto_unregister_shash(&alg); } subsys_initcall(rmd160_mod_init); module_exit(rmd160_mod_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>"); MODULE_DESCRIPTION("RIPEMD-160 Message Digest"); MODULE_ALIAS_CRYPTO("rmd160"); |
| 2 95 9 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PID_NS_H #define _LINUX_PID_NS_H #include <linux/sched.h> #include <linux/bug.h> #include <linux/mm.h> #include <linux/workqueue.h> #include <linux/threads.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/idr.h> /* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */ #define MAX_PID_NS_LEVEL 32 struct fs_pin; #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) /* modes for vm.memfd_noexec sysctl */ #define MEMFD_NOEXEC_SCOPE_EXEC 0 /* MFD_EXEC implied if unset */ #define MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL 1 /* MFD_NOEXEC_SEAL implied if unset */ #define MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED 2 /* same as 1, except MFD_EXEC rejected */ #endif struct pid_namespace { struct idr idr; struct rcu_head rcu; unsigned int pid_allocated; struct task_struct *child_reaper; struct kmem_cache *pid_cachep; unsigned int level; struct pid_namespace *parent; #ifdef CONFIG_BSD_PROCESS_ACCT struct fs_pin *bacct; #endif struct user_namespace *user_ns; struct ucounts *ucounts; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) int memfd_noexec_scope; #endif } __randomize_layout; extern struct pid_namespace init_pid_ns; #define PIDNS_ADDING (1U << 31) #ifdef CONFIG_PID_NS static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) { if (ns != &init_pid_ns) refcount_inc(&ns->ns.count); return ns; } #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) static inline int pidns_memfd_noexec_scope(struct pid_namespace *ns) { int scope = MEMFD_NOEXEC_SCOPE_EXEC; for (; ns; ns = ns->parent) scope = max(scope, READ_ONCE(ns->memfd_noexec_scope)); return scope; } #else static inline int pidns_memfd_noexec_scope(struct pid_namespace *ns) { return 0; } #endif extern struct pid_namespace *copy_pid_ns(unsigned long flags, struct user_namespace *user_ns, struct pid_namespace *ns); extern void zap_pid_ns_processes(struct pid_namespace *pid_ns); extern int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd); extern void put_pid_ns(struct pid_namespace *ns); #else /* !CONFIG_PID_NS */ #include <linux/err.h> static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) { return ns; } static inline int pidns_memfd_noexec_scope(struct pid_namespace *ns) { return 0; } static inline struct pid_namespace *copy_pid_ns(unsigned long flags, struct user_namespace *user_ns, struct pid_namespace *ns) { if (flags & CLONE_NEWPID) ns = ERR_PTR(-EINVAL); return ns; } static inline void put_pid_ns(struct pid_namespace *ns) { } static inline void zap_pid_ns_processes(struct pid_namespace *ns) { BUG(); } static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) { return 0; } #endif /* CONFIG_PID_NS */ extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); void pidhash_init(void); void pid_idr_init(void); static inline bool task_is_in_init_pid_ns(struct task_struct *tsk) { return task_active_pid_ns(tsk) == &init_pid_ns; } #endif /* _LINUX_PID_NS_H */ |
| 4 1 13 1 7 21 8 4 4 2 6 6 2 2 2 8 8732 42 24 65 21 47 23 8730 217 8668 3468 5264 5228 217 67 3 8 1 1 4 6 27 8487 26 8487 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * VLAN An implementation of 802.1Q VLAN tagging. * * Authors: Ben Greear <greearb@candelatech.com> */ #ifndef _LINUX_IF_VLAN_H_ #define _LINUX_IF_VLAN_H_ #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/bug.h> #include <uapi/linux/if_vlan.h> #define VLAN_HLEN 4 /* The additional bytes required by VLAN * (in addition to the Ethernet header) */ #define VLAN_ETH_HLEN 18 /* Total octets in header. */ #define VLAN_ETH_ZLEN 64 /* Min. octets in frame sans FCS */ /* * According to 802.3ac, the packet can be 4 bytes longer. --Klika Jan */ #define VLAN_ETH_DATA_LEN 1500 /* Max. octets in payload */ #define VLAN_ETH_FRAME_LEN 1518 /* Max. octets in frame sans FCS */ #define VLAN_MAX_DEPTH 8 /* Max. number of nested VLAN tags parsed */ /* * struct vlan_hdr - vlan header * @h_vlan_TCI: priority and VLAN ID * @h_vlan_encapsulated_proto: packet type ID or len */ struct vlan_hdr { __be16 h_vlan_TCI; __be16 h_vlan_encapsulated_proto; }; /** * struct vlan_ethhdr - vlan ethernet header (ethhdr + vlan_hdr) * @h_dest: destination ethernet address * @h_source: source ethernet address * @h_vlan_proto: ethernet protocol * @h_vlan_TCI: priority and VLAN ID * @h_vlan_encapsulated_proto: packet type ID or len */ struct vlan_ethhdr { struct_group(addrs, unsigned char h_dest[ETH_ALEN]; unsigned char h_source[ETH_ALEN]; ); __be16 h_vlan_proto; __be16 h_vlan_TCI; __be16 h_vlan_encapsulated_proto; }; #include <linux/skbuff.h> static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb) { return (struct vlan_ethhdr *)skb_mac_header(skb); } /* Prefer this version in TX path, instead of * skb_reset_mac_header() + vlan_eth_hdr() */ static inline struct vlan_ethhdr *skb_vlan_eth_hdr(const struct sk_buff *skb) { return (struct vlan_ethhdr *)skb->data; } #define VLAN_PRIO_MASK 0xe000 /* Priority Code Point */ #define VLAN_PRIO_SHIFT 13 #define VLAN_CFI_MASK 0x1000 /* Canonical Format Indicator / Drop Eligible Indicator */ #define VLAN_VID_MASK 0x0fff /* VLAN Identifier */ #define VLAN_N_VID 4096 /* found in socket.c */ extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *)); static inline bool is_vlan_dev(const struct net_device *dev) { return dev->priv_flags & IFF_802_1Q_VLAN; } #define skb_vlan_tag_present(__skb) (!!(__skb)->vlan_all) #define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci) #define skb_vlan_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK) #define skb_vlan_tag_get_cfi(__skb) (!!((__skb)->vlan_tci & VLAN_CFI_MASK)) #define skb_vlan_tag_get_prio(__skb) (((__skb)->vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT) static inline int vlan_get_rx_ctag_filter_info(struct net_device *dev) { ASSERT_RTNL(); return notifier_to_errno(call_netdevice_notifiers(NETDEV_CVLAN_FILTER_PUSH_INFO, dev)); } static inline void vlan_drop_rx_ctag_filter_info(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_CVLAN_FILTER_DROP_INFO, dev); } static inline int vlan_get_rx_stag_filter_info(struct net_device *dev) { ASSERT_RTNL(); return notifier_to_errno(call_netdevice_notifiers(NETDEV_SVLAN_FILTER_PUSH_INFO, dev)); } static inline void vlan_drop_rx_stag_filter_info(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_SVLAN_FILTER_DROP_INFO, dev); } /** * struct vlan_pcpu_stats - VLAN percpu rx/tx stats * @rx_packets: number of received packets * @rx_bytes: number of received bytes * @rx_multicast: number of received multicast packets * @tx_packets: number of transmitted packets * @tx_bytes: number of transmitted bytes * @syncp: synchronization point for 64bit counters * @rx_errors: number of rx errors * @tx_dropped: number of tx drops */ struct vlan_pcpu_stats { u64_stats_t rx_packets; u64_stats_t rx_bytes; u64_stats_t rx_multicast; u64_stats_t tx_packets; u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_errors; u32 tx_dropped; }; #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) extern struct net_device *__vlan_find_dev_deep_rcu(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id); extern int vlan_for_each(struct net_device *dev, int (*action)(struct net_device *dev, int vid, void *arg), void *arg); extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); extern __be16 vlan_dev_vlan_proto(const struct net_device *dev); /** * struct vlan_priority_tci_mapping - vlan egress priority mappings * @priority: skb priority * @vlan_qos: vlan priority: (skb->priority << 13) & 0xE000 * @next: pointer to next struct */ struct vlan_priority_tci_mapping { u32 priority; u16 vlan_qos; struct vlan_priority_tci_mapping *next; }; struct proc_dir_entry; struct netpoll; /** * struct vlan_dev_priv - VLAN private device data * @nr_ingress_mappings: number of ingress priority mappings * @ingress_priority_map: ingress priority mappings * @nr_egress_mappings: number of egress priority mappings * @egress_priority_map: hash of egress priority mappings * @vlan_proto: VLAN encapsulation protocol * @vlan_id: VLAN identifier * @flags: device flags * @real_dev: underlying netdevice * @dev_tracker: refcount tracker for @real_dev reference * @real_dev_addr: address of underlying netdevice * @dent: proc dir entry * @vlan_pcpu_stats: ptr to percpu rx stats */ struct vlan_dev_priv { unsigned int nr_ingress_mappings; u32 ingress_priority_map[8]; unsigned int nr_egress_mappings; struct vlan_priority_tci_mapping *egress_priority_map[16]; __be16 vlan_proto; u16 vlan_id; u16 flags; struct net_device *real_dev; netdevice_tracker dev_tracker; unsigned char real_dev_addr[ETH_ALEN]; struct proc_dir_entry *dent; struct vlan_pcpu_stats __percpu *vlan_pcpu_stats; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif }; static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev) { return netdev_priv(dev); } static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio) { struct vlan_priority_tci_mapping *mp; smp_rmb(); /* coupled with smp_wmb() in vlan_dev_set_egress_priority() */ mp = vlan_dev_priv(dev)->egress_priority_map[(skprio & 0xF)]; while (mp) { if (mp->priority == skprio) { return mp->vlan_qos; /* This should already be shifted * to mask correctly with the * VLAN's TCI */ } mp = mp->next; } return 0; } extern bool vlan_do_receive(struct sk_buff **skb); extern int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid); extern void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid); extern int vlan_vids_add_by_dev(struct net_device *dev, const struct net_device *by_dev); extern void vlan_vids_del_by_dev(struct net_device *dev, const struct net_device *by_dev); extern bool vlan_uses_dev(const struct net_device *dev); #else static inline struct net_device * __vlan_find_dev_deep_rcu(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id) { return NULL; } static inline int vlan_for_each(struct net_device *dev, int (*action)(struct net_device *dev, int vid, void *arg), void *arg) { return 0; } static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev) { BUG(); return NULL; } static inline u16 vlan_dev_vlan_id(const struct net_device *dev) { BUG(); return 0; } static inline __be16 vlan_dev_vlan_proto(const struct net_device *dev) { BUG(); return 0; } static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio) { return 0; } static inline bool vlan_do_receive(struct sk_buff **skb) { return false; } static inline int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid) { return 0; } static inline void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid) { } static inline int vlan_vids_add_by_dev(struct net_device *dev, const struct net_device *by_dev) { return 0; } static inline void vlan_vids_del_by_dev(struct net_device *dev, const struct net_device *by_dev) { } static inline bool vlan_uses_dev(const struct net_device *dev) { return false; } #endif /** * eth_type_vlan - check for valid vlan ether type. * @ethertype: ether type to check * * Returns true if the ether type is a vlan ether type. */ static inline bool eth_type_vlan(__be16 ethertype) { switch (ethertype) { case htons(ETH_P_8021Q): case htons(ETH_P_8021AD): return true; default: return false; } } static inline bool vlan_hw_offload_capable(netdev_features_t features, __be16 proto) { if (proto == htons(ETH_P_8021Q) && features & NETIF_F_HW_VLAN_CTAG_TX) return true; if (proto == htons(ETH_P_8021AD) && features & NETIF_F_HW_VLAN_STAG_TX) return true; return false; } /** * __vlan_insert_inner_tag - inner VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * @mac_len: MAC header length including outer vlan headers * * Inserts the VLAN tag into @skb as part of the payload at offset mac_len * Returns error if skb_cow_head fails. * * Does not change skb->protocol so this function can be used during receive. */ static inline int __vlan_insert_inner_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci, unsigned int mac_len) { struct vlan_ethhdr *veth; if (skb_cow_head(skb, VLAN_HLEN) < 0) return -ENOMEM; skb_push(skb, VLAN_HLEN); /* Move the mac header sans proto to the beginning of the new header. */ if (likely(mac_len > ETH_TLEN)) memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN); if (skb_mac_header_was_set(skb)) skb->mac_header -= VLAN_HLEN; veth = (struct vlan_ethhdr *)(skb->data + mac_len - ETH_HLEN); /* first, the ethernet type */ if (likely(mac_len >= ETH_TLEN)) { /* h_vlan_encapsulated_proto should already be populated, and * skb->data has space for h_vlan_proto */ veth->h_vlan_proto = vlan_proto; } else { /* h_vlan_encapsulated_proto should not be populated, and * skb->data has no space for h_vlan_proto */ veth->h_vlan_encapsulated_proto = skb->protocol; } /* now, the TCI */ veth->h_vlan_TCI = htons(vlan_tci); return 0; } /** * __vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload * Returns error if skb_cow_head fails. * * Does not change skb->protocol so this function can be used during receive. */ static inline int __vlan_insert_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { return __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN); } /** * vlan_insert_inner_tag - inner VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * @mac_len: MAC header length including outer vlan headers * * Inserts the VLAN tag into @skb as part of the payload at offset mac_len * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. * * Does not change skb->protocol so this function can be used during receive. */ static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci, unsigned int mac_len) { int err; err = __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, mac_len); if (err) { dev_kfree_skb_any(skb); return NULL; } return skb; } /** * vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. * * Does not change skb->protocol so this function can be used during receive. */ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { return vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN); } /** * vlan_insert_tag_set_proto - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. */ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { skb = vlan_insert_tag(skb, vlan_proto, vlan_tci); if (skb) skb->protocol = vlan_proto; return skb; } /** * __vlan_hwaccel_clear_tag - clear hardware accelerated VLAN info * @skb: skbuff to clear * * Clears the VLAN information from @skb */ static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) { skb->vlan_all = 0; } /** * __vlan_hwaccel_copy_tag - copy hardware accelerated VLAN info from another skb * @dst: skbuff to copy to * @src: skbuff to copy from * * Copies VLAN information from @src to @dst (for branchless code) */ static inline void __vlan_hwaccel_copy_tag(struct sk_buff *dst, const struct sk_buff *src) { dst->vlan_all = src->vlan_all; } /* * __vlan_hwaccel_push_inside - pushes vlan tag to the payload * @skb: skbuff to tag * * Pushes the VLAN tag from @skb->vlan_tci inside to the payload. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. */ static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb) { skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (likely(skb)) __vlan_hwaccel_clear_tag(skb); return skb; } /** * __vlan_hwaccel_put_tag - hardware accelerated VLAN inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Puts the VLAN TCI in @skb->vlan_tci and lets the device do the rest */ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { skb->vlan_proto = vlan_proto; skb->vlan_tci = vlan_tci; } /** * __vlan_get_tag - get the VLAN ID that is part of the payload * @skb: skbuff to query * @vlan_tci: buffer to store value * * Returns error if the skb is not of VLAN type */ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { struct vlan_ethhdr *veth = skb_vlan_eth_hdr(skb); if (!eth_type_vlan(veth->h_vlan_proto)) return -ENODATA; *vlan_tci = ntohs(veth->h_vlan_TCI); return 0; } /** * __vlan_hwaccel_get_tag - get the VLAN ID that is in @skb->cb[] * @skb: skbuff to query * @vlan_tci: buffer to store value * * Returns error if @skb->vlan_tci is not set correctly */ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { if (skb_vlan_tag_present(skb)) { *vlan_tci = skb_vlan_tag_get(skb); return 0; } else { *vlan_tci = 0; return -ENODATA; } } /** * vlan_get_tag - get the VLAN ID from the skb * @skb: skbuff to query * @vlan_tci: buffer to store value * * Returns error if the skb is not VLAN tagged */ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { if (skb->dev->features & NETIF_F_HW_VLAN_CTAG_TX) { return __vlan_hwaccel_get_tag(skb, vlan_tci); } else { return __vlan_get_tag(skb, vlan_tci); } } /** * vlan_get_protocol - get protocol EtherType. * @skb: skbuff to query * @type: first vlan protocol * @mac_offset: MAC offset * @depth: buffer to store length of eth and vlan tags in bytes * * Returns the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ static inline __be16 __vlan_get_protocol_offset(const struct sk_buff *skb, __be16 type, int mac_offset, int *depth) { unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH; /* if type is 802.1Q/AD then the header should already be * present at mac_len - VLAN_HLEN (if mac_len > 0), or at * ETH_HLEN otherwise */ if (eth_type_vlan(type)) { if (vlan_depth) { if (WARN_ON(vlan_depth < VLAN_HLEN)) return 0; vlan_depth -= VLAN_HLEN; } else { vlan_depth = ETH_HLEN; } do { struct vlan_hdr vhdr, *vh; vh = skb_header_pointer(skb, mac_offset + vlan_depth, sizeof(vhdr), &vhdr); if (unlikely(!vh || !--parse_depth)) return 0; type = vh->h_vlan_encapsulated_proto; vlan_depth += VLAN_HLEN; } while (eth_type_vlan(type)); } if (depth) *depth = vlan_depth; return type; } static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, int *depth) { return __vlan_get_protocol_offset(skb, type, 0, depth); } /** * vlan_get_protocol - get protocol EtherType. * @skb: skbuff to query * * Returns the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ static inline __be16 vlan_get_protocol(const struct sk_buff *skb) { return __vlan_get_protocol(skb, skb->protocol, NULL); } /* This version of __vlan_get_protocol() also pulls mac header in skb->head */ static inline __be16 vlan_get_protocol_and_depth(struct sk_buff *skb, __be16 type, int *depth) { int maclen; type = __vlan_get_protocol(skb, type, &maclen); if (type) { if (!pskb_may_pull(skb, maclen)) type = 0; else if (depth) *depth = maclen; } return type; } /* A getter for the SKB protocol field which will handle VLAN tags consistently * whether VLAN acceleration is enabled or not. */ static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan) { if (!skip_vlan) /* VLAN acceleration strips the VLAN header from the skb and * moves it to skb->vlan_proto */ return skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol; return vlan_get_protocol(skb); } static inline void vlan_set_encap_proto(struct sk_buff *skb, struct vlan_hdr *vhdr) { __be16 proto; unsigned short *rawp; /* * Was a VLAN packet, grab the encapsulated protocol, which the layer * three protocols care about. */ proto = vhdr->h_vlan_encapsulated_proto; if (eth_proto_is_802_3(proto)) { skb->protocol = proto; return; } rawp = (unsigned short *)(vhdr + 1); if (*rawp == 0xFFFF) /* * This is a magic hack to spot IPX packets. Older Novell * breaks the protocol design and runs IPX over 802.3 without * an 802.2 LLC layer. We look for FFFF which isn't a used * 802.2 SSAP/DSAP. This won't work for fault tolerant netware * but does for the rest. */ skb->protocol = htons(ETH_P_802_3); else /* * Real 802.2 LLC */ skb->protocol = htons(ETH_P_802_2); } /** * vlan_remove_tag - remove outer VLAN tag from payload * @skb: skbuff to remove tag from * @vlan_tci: buffer to store value * * Expects the skb to contain a VLAN tag in the payload, and to have skb->data * pointing at the MAC header. * * Returns a new pointer to skb->data, or NULL on failure to pull. */ static inline void *vlan_remove_tag(struct sk_buff *skb, u16 *vlan_tci) { struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN); *vlan_tci = ntohs(vhdr->h_vlan_TCI); memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN); vlan_set_encap_proto(skb, vhdr); return __skb_pull(skb, VLAN_HLEN); } /** * skb_vlan_tagged - check if skb is vlan tagged. * @skb: skbuff to query * * Returns true if the skb is tagged, regardless of whether it is hardware * accelerated or not. */ static inline bool skb_vlan_tagged(const struct sk_buff *skb) { if (!skb_vlan_tag_present(skb) && likely(!eth_type_vlan(skb->protocol))) return false; return true; } /** * skb_vlan_tagged_multi - check if skb is vlan tagged with multiple headers. * @skb: skbuff to query * * Returns true if the skb is tagged with multiple vlan headers, regardless * of whether it is hardware accelerated or not. */ static inline bool skb_vlan_tagged_multi(struct sk_buff *skb) { __be16 protocol = skb->protocol; if (!skb_vlan_tag_present(skb)) { struct vlan_ethhdr *veh; if (likely(!eth_type_vlan(protocol))) return false; if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN))) return false; veh = skb_vlan_eth_hdr(skb); protocol = veh->h_vlan_encapsulated_proto; } if (!eth_type_vlan(protocol)) return false; return true; } /** * vlan_features_check - drop unsafe features for skb with multiple tags. * @skb: skbuff to query * @features: features to be checked * * Returns features without unsafe ones if the skb has multiple tags. */ static inline netdev_features_t vlan_features_check(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tagged_multi(skb)) { /* In the case of multi-tagged packets, use a direct mask * instead of using netdev_interesect_features(), to make * sure that only devices supporting NETIF_F_HW_CSUM will * have checksum offloading support. */ features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; } return features; } /** * compare_vlan_header - Compare two vlan headers * @h1: Pointer to vlan header * @h2: Pointer to vlan header * * Compare two vlan headers, returns 0 if equal. * * Please note that alignment of h1 & h2 are only guaranteed to be 16 bits. */ static inline unsigned long compare_vlan_header(const struct vlan_hdr *h1, const struct vlan_hdr *h2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return *(u32 *)h1 ^ *(u32 *)h2; #else return ((__force u32)h1->h_vlan_TCI ^ (__force u32)h2->h_vlan_TCI) | ((__force u32)h1->h_vlan_encapsulated_proto ^ (__force u32)h2->h_vlan_encapsulated_proto); #endif } #endif /* !(_LINUX_IF_VLAN_H_) */ |
| 22 32 32 35 35 5 22 22 27 20 19 19 11 10 15 27 27 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Shared crypto simd helpers * * Copyright (c) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi> * Copyright (c) 2016 Herbert Xu <herbert@gondor.apana.org.au> * Copyright (c) 2019 Google LLC * * Based on aesni-intel_glue.c by: * Copyright (C) 2008, Intel Corp. * Author: Huang Ying <ying.huang@intel.com> */ /* * Shared crypto SIMD helpers. These functions dynamically create and register * an skcipher or AEAD algorithm that wraps another, internal algorithm. The * wrapper ensures that the internal algorithm is only executed in a context * where SIMD instructions are usable, i.e. where may_use_simd() returns true. * If SIMD is already usable, the wrapper directly calls the internal algorithm. * Otherwise it defers execution to a workqueue via cryptd. * * This is an alternative to the internal algorithm implementing a fallback for * the !may_use_simd() case itself. * * Note that the wrapper algorithm is asynchronous, i.e. it has the * CRYPTO_ALG_ASYNC flag set. Therefore it won't be found by users who * explicitly allocate a synchronous algorithm. */ #include <crypto/cryptd.h> #include <crypto/internal/aead.h> #include <crypto/internal/simd.h> #include <crypto/internal/skcipher.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/preempt.h> #include <asm/simd.h> /* skcipher support */ struct simd_skcipher_alg { const char *ialg_name; struct skcipher_alg alg; }; struct simd_skcipher_ctx { struct cryptd_skcipher *cryptd_tfm; }; static int simd_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int key_len) { struct simd_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm); struct crypto_skcipher *child = &ctx->cryptd_tfm->base; crypto_skcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK); crypto_skcipher_set_flags(child, crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_REQ_MASK); return crypto_skcipher_setkey(child, key, key_len); } static int simd_skcipher_encrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct simd_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm); struct skcipher_request *subreq; struct crypto_skcipher *child; subreq = skcipher_request_ctx(req); *subreq = *req; if (!crypto_simd_usable() || (in_atomic() && cryptd_skcipher_queued(ctx->cryptd_tfm))) child = &ctx->cryptd_tfm->base; else child = cryptd_skcipher_child(ctx->cryptd_tfm); skcipher_request_set_tfm(subreq, child); return crypto_skcipher_encrypt(subreq); } static int simd_skcipher_decrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); struct simd_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm); struct skcipher_request *subreq; struct crypto_skcipher *child; subreq = skcipher_request_ctx(req); *subreq = *req; if (!crypto_simd_usable() || (in_atomic() && cryptd_skcipher_queued(ctx->cryptd_tfm))) child = &ctx->cryptd_tfm->base; else child = cryptd_skcipher_child(ctx->cryptd_tfm); skcipher_request_set_tfm(subreq, child); return crypto_skcipher_decrypt(subreq); } static void simd_skcipher_exit(struct crypto_skcipher *tfm) { struct simd_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm); cryptd_free_skcipher(ctx->cryptd_tfm); } static int simd_skcipher_init(struct crypto_skcipher *tfm) { struct simd_skcipher_ctx *ctx = crypto_skcipher_ctx(tfm); struct cryptd_skcipher *cryptd_tfm; struct simd_skcipher_alg *salg; struct skcipher_alg *alg; unsigned reqsize; alg = crypto_skcipher_alg(tfm); salg = container_of(alg, struct simd_skcipher_alg, alg); cryptd_tfm = cryptd_alloc_skcipher(salg->ialg_name, CRYPTO_ALG_INTERNAL, CRYPTO_ALG_INTERNAL); if (IS_ERR(cryptd_tfm)) return PTR_ERR(cryptd_tfm); ctx->cryptd_tfm = cryptd_tfm; reqsize = crypto_skcipher_reqsize(cryptd_skcipher_child(cryptd_tfm)); reqsize = max(reqsize, crypto_skcipher_reqsize(&cryptd_tfm->base)); reqsize += sizeof(struct skcipher_request); crypto_skcipher_set_reqsize(tfm, reqsize); return 0; } struct simd_skcipher_alg *simd_skcipher_create_compat(struct skcipher_alg *ialg, const char *algname, const char *drvname, const char *basename) { struct simd_skcipher_alg *salg; struct skcipher_alg *alg; int err; salg = kzalloc(sizeof(*salg), GFP_KERNEL); if (!salg) { salg = ERR_PTR(-ENOMEM); goto out; } salg->ialg_name = basename; alg = &salg->alg; err = -ENAMETOOLONG; if (snprintf(alg->base.cra_name, CRYPTO_MAX_ALG_NAME, "%s", algname) >= CRYPTO_MAX_ALG_NAME) goto out_free_salg; if (snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s", drvname) >= CRYPTO_MAX_ALG_NAME) goto out_free_salg; alg->base.cra_flags = CRYPTO_ALG_ASYNC | (ialg->base.cra_flags & CRYPTO_ALG_INHERITED_FLAGS); alg->base.cra_priority = ialg->base.cra_priority; alg->base.cra_blocksize = ialg->base.cra_blocksize; alg->base.cra_alignmask = ialg->base.cra_alignmask; alg->base.cra_module = ialg->base.cra_module; alg->base.cra_ctxsize = sizeof(struct simd_skcipher_ctx); alg->ivsize = ialg->ivsize; alg->chunksize = ialg->chunksize; alg->min_keysize = ialg->min_keysize; alg->max_keysize = ialg->max_keysize; alg->init = simd_skcipher_init; alg->exit = simd_skcipher_exit; alg->setkey = simd_skcipher_setkey; alg->encrypt = simd_skcipher_encrypt; alg->decrypt = simd_skcipher_decrypt; err = crypto_register_skcipher(alg); if (err) goto out_free_salg; out: return salg; out_free_salg: kfree(salg); salg = ERR_PTR(err); goto out; } EXPORT_SYMBOL_GPL(simd_skcipher_create_compat); void simd_skcipher_free(struct simd_skcipher_alg *salg) { crypto_unregister_skcipher(&salg->alg); kfree(salg); } EXPORT_SYMBOL_GPL(simd_skcipher_free); int simd_register_skciphers_compat(struct skcipher_alg *algs, int count, struct simd_skcipher_alg **simd_algs) { int err; int i; const char *algname; const char *drvname; const char *basename; struct simd_skcipher_alg *simd; err = crypto_register_skciphers(algs, count); if (err) return err; for (i = 0; i < count; i++) { WARN_ON(strncmp(algs[i].base.cra_name, "__", 2)); WARN_ON(strncmp(algs[i].base.cra_driver_name, "__", 2)); algname = algs[i].base.cra_name + 2; drvname = algs[i].base.cra_driver_name + 2; basename = algs[i].base.cra_driver_name; simd = simd_skcipher_create_compat(algs + i, algname, drvname, basename); err = PTR_ERR(simd); if (IS_ERR(simd)) goto err_unregister; simd_algs[i] = simd; } return 0; err_unregister: simd_unregister_skciphers(algs, count, simd_algs); return err; } EXPORT_SYMBOL_GPL(simd_register_skciphers_compat); void simd_unregister_skciphers(struct skcipher_alg *algs, int count, struct simd_skcipher_alg **simd_algs) { int i; crypto_unregister_skciphers(algs, count); for (i = 0; i < count; i++) { if (simd_algs[i]) { simd_skcipher_free(simd_algs[i]); simd_algs[i] = NULL; } } } EXPORT_SYMBOL_GPL(simd_unregister_skciphers); /* AEAD support */ struct simd_aead_alg { const char *ialg_name; struct aead_alg alg; }; struct simd_aead_ctx { struct cryptd_aead *cryptd_tfm; }; static int simd_aead_setkey(struct crypto_aead *tfm, const u8 *key, unsigned int key_len) { struct simd_aead_ctx *ctx = crypto_aead_ctx(tfm); struct crypto_aead *child = &ctx->cryptd_tfm->base; crypto_aead_clear_flags(child, CRYPTO_TFM_REQ_MASK); crypto_aead_set_flags(child, crypto_aead_get_flags(tfm) & CRYPTO_TFM_REQ_MASK); return crypto_aead_setkey(child, key, key_len); } static int simd_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize) { struct simd_aead_ctx *ctx = crypto_aead_ctx(tfm); struct crypto_aead *child = &ctx->cryptd_tfm->base; return crypto_aead_setauthsize(child, authsize); } static int simd_aead_encrypt(struct aead_request *req) { struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct simd_aead_ctx *ctx = crypto_aead_ctx(tfm); struct aead_request *subreq; struct crypto_aead *child; subreq = aead_request_ctx(req); *subreq = *req; if (!crypto_simd_usable() || (in_atomic() && cryptd_aead_queued(ctx->cryptd_tfm))) child = &ctx->cryptd_tfm->base; else child = cryptd_aead_child(ctx->cryptd_tfm); aead_request_set_tfm(subreq, child); return crypto_aead_encrypt(subreq); } static int simd_aead_decrypt(struct aead_request *req) { struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct simd_aead_ctx *ctx = crypto_aead_ctx(tfm); struct aead_request *subreq; struct crypto_aead *child; subreq = aead_request_ctx(req); *subreq = *req; if (!crypto_simd_usable() || (in_atomic() && cryptd_aead_queued(ctx->cryptd_tfm))) child = &ctx->cryptd_tfm->base; else child = cryptd_aead_child(ctx->cryptd_tfm); aead_request_set_tfm(subreq, child); return crypto_aead_decrypt(subreq); } static void simd_aead_exit(struct crypto_aead *tfm) { struct simd_aead_ctx *ctx = crypto_aead_ctx(tfm); cryptd_free_aead(ctx->cryptd_tfm); } static int simd_aead_init(struct crypto_aead *tfm) { struct simd_aead_ctx *ctx = crypto_aead_ctx(tfm); struct cryptd_aead *cryptd_tfm; struct simd_aead_alg *salg; struct aead_alg *alg; unsigned reqsize; alg = crypto_aead_alg(tfm); salg = container_of(alg, struct simd_aead_alg, alg); cryptd_tfm = cryptd_alloc_aead(salg->ialg_name, CRYPTO_ALG_INTERNAL, CRYPTO_ALG_INTERNAL); if (IS_ERR(cryptd_tfm)) return PTR_ERR(cryptd_tfm); ctx->cryptd_tfm = cryptd_tfm; reqsize = crypto_aead_reqsize(cryptd_aead_child(cryptd_tfm)); reqsize = max(reqsize, crypto_aead_reqsize(&cryptd_tfm->base)); reqsize += sizeof(struct aead_request); crypto_aead_set_reqsize(tfm, reqsize); return 0; } static struct simd_aead_alg *simd_aead_create_compat(struct aead_alg *ialg, const char *algname, const char *drvname, const char *basename) { struct simd_aead_alg *salg; struct aead_alg *alg; int err; salg = kzalloc(sizeof(*salg), GFP_KERNEL); if (!salg) { salg = ERR_PTR(-ENOMEM); goto out; } salg->ialg_name = basename; alg = &salg->alg; err = -ENAMETOOLONG; if (snprintf(alg->base.cra_name, CRYPTO_MAX_ALG_NAME, "%s", algname) >= CRYPTO_MAX_ALG_NAME) goto out_free_salg; if (snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s", drvname) >= CRYPTO_MAX_ALG_NAME) goto out_free_salg; alg->base.cra_flags = CRYPTO_ALG_ASYNC | (ialg->base.cra_flags & CRYPTO_ALG_INHERITED_FLAGS); alg->base.cra_priority = ialg->base.cra_priority; alg->base.cra_blocksize = ialg->base.cra_blocksize; alg->base.cra_alignmask = ialg->base.cra_alignmask; alg->base.cra_module = ialg->base.cra_module; alg->base.cra_ctxsize = sizeof(struct simd_aead_ctx); alg->ivsize = ialg->ivsize; alg->maxauthsize = ialg->maxauthsize; alg->chunksize = ialg->chunksize; alg->init = simd_aead_init; alg->exit = simd_aead_exit; alg->setkey = simd_aead_setkey; alg->setauthsize = simd_aead_setauthsize; alg->encrypt = simd_aead_encrypt; alg->decrypt = simd_aead_decrypt; err = crypto_register_aead(alg); if (err) goto out_free_salg; out: return salg; out_free_salg: kfree(salg); salg = ERR_PTR(err); goto out; } static void simd_aead_free(struct simd_aead_alg *salg) { crypto_unregister_aead(&salg->alg); kfree(salg); } int simd_register_aeads_compat(struct aead_alg *algs, int count, struct simd_aead_alg **simd_algs) { int err; int i; const char *algname; const char *drvname; const char *basename; struct simd_aead_alg *simd; err = crypto_register_aeads(algs, count); if (err) return err; for (i = 0; i < count; i++) { WARN_ON(strncmp(algs[i].base.cra_name, "__", 2)); WARN_ON(strncmp(algs[i].base.cra_driver_name, "__", 2)); algname = algs[i].base.cra_name + 2; drvname = algs[i].base.cra_driver_name + 2; basename = algs[i].base.cra_driver_name; simd = simd_aead_create_compat(algs + i, algname, drvname, basename); err = PTR_ERR(simd); if (IS_ERR(simd)) goto err_unregister; simd_algs[i] = simd; } return 0; err_unregister: simd_unregister_aeads(algs, count, simd_algs); return err; } EXPORT_SYMBOL_GPL(simd_register_aeads_compat); void simd_unregister_aeads(struct aead_alg *algs, int count, struct simd_aead_alg **simd_algs) { int i; crypto_unregister_aeads(algs, count); for (i = 0; i < count; i++) { if (simd_algs[i]) { simd_aead_free(simd_algs[i]); simd_algs[i] = NULL; } } } EXPORT_SYMBOL_GPL(simd_unregister_aeads); MODULE_DESCRIPTION("Shared crypto SIMD helpers"); MODULE_LICENSE("GPL"); |
| 39 24 14 37 2 7 31 1 32 31 9 12 12 12 12 12 10 2 8 9 1 6 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/module.h> #include <linux/errno.h> #include <linux/socket.h> #include <linux/udp.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/in6.h> #include <net/udp.h> #include <net/udp_tunnel.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/ip6_tunnel.h> #include <net/ip6_checksum.h> int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { struct sockaddr_in6 udp6_addr = {}; int err; struct socket *sock = NULL; err = sock_create_kern(net, AF_INET6, SOCK_DGRAM, 0, &sock); if (err < 0) goto error; if (cfg->ipv6_v6only) { err = ip6_sock_set_v6only(sock->sk); if (err < 0) goto error; } if (cfg->bind_ifindex) { err = sock_bindtoindex(sock->sk, cfg->bind_ifindex, true); if (err < 0) goto error; } udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6, sizeof(udp6_addr.sin6_addr)); udp6_addr.sin6_port = cfg->local_udp_port; err = kernel_bind(sock, (struct sockaddr *)&udp6_addr, sizeof(udp6_addr)); if (err < 0) goto error; if (cfg->peer_udp_port) { memset(&udp6_addr, 0, sizeof(udp6_addr)); udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, &cfg->peer_ip6, sizeof(udp6_addr.sin6_addr)); udp6_addr.sin6_port = cfg->peer_udp_port; err = kernel_connect(sock, (struct sockaddr *)&udp6_addr, sizeof(udp6_addr), 0); } if (err < 0) goto error; udp_set_no_check6_tx(sock->sk, !cfg->use_udp6_tx_checksums); udp_set_no_check6_rx(sock->sk, !cfg->use_udp6_rx_checksums); *sockp = sock; return 0; error: if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } *sockp = NULL; return err; } EXPORT_SYMBOL_GPL(udp_sock_create6); int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr, __u8 prio, __u8 ttl, __be32 label, __be16 src_port, __be16 dst_port, bool nocheck) { struct udphdr *uh; struct ipv6hdr *ip6h; __skb_push(skb, sizeof(*uh)); skb_reset_transport_header(skb); uh = udp_hdr(skb); uh->dest = dst_port; uh->source = src_port; uh->len = htons(skb->len); skb_dst_set(skb, dst); udp6_set_csum(nocheck, skb, saddr, daddr, skb->len); __skb_push(skb, sizeof(*ip6h)); skb_reset_network_header(skb); ip6h = ipv6_hdr(skb); ip6_flow_hdr(ip6h, prio, label); ip6h->payload_len = htons(skb->len); ip6h->nexthdr = IPPROTO_UDP; ip6h->hop_limit = ttl; ip6h->daddr = *daddr; ip6h->saddr = *saddr; ip6tunnel_xmit(sk, skb, dev); return 0; } EXPORT_SYMBOL_GPL(udp_tunnel6_xmit_skb); /** * udp_tunnel6_dst_lookup - perform route lookup on UDP tunnel * @skb: Packet for which lookup is done * @dev: Tunnel device * @net: Network namespace of tunnel device * @sock: Socket which provides route info * @oif: Index of the output interface * @saddr: Memory to store the src ip address * @key: Tunnel information * @sport: UDP source port * @dport: UDP destination port * @dsfield: The traffic class field * @dst_cache: The dst cache to use for lookup * This function performs a route lookup on a UDP tunnel * * It returns a valid dst pointer and stores src address to be used in * tunnel in param saddr on success, else a pointer encoded error code. */ struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, struct net_device *dev, struct net *net, struct socket *sock, int oif, struct in6_addr *saddr, const struct ip_tunnel_key *key, __be16 sport, __be16 dport, u8 dsfield, struct dst_cache *dst_cache) { struct dst_entry *dst = NULL; struct flowi6 fl6; #ifdef CONFIG_DST_CACHE if (dst_cache) { dst = dst_cache_get_ip6(dst_cache, saddr); if (dst) return dst; } #endif memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = IPPROTO_UDP; fl6.flowi6_oif = oif; fl6.daddr = key->u.ipv6.dst; fl6.saddr = key->u.ipv6.src; fl6.fl6_sport = sport; fl6.fl6_dport = dport; fl6.flowlabel = ip6_make_flowinfo(dsfield, key->label); dst = ipv6_stub->ipv6_dst_lookup_flow(net, sock->sk, &fl6, NULL); if (IS_ERR(dst)) { netdev_dbg(dev, "no route to %pI6\n", &fl6.daddr); return ERR_PTR(-ENETUNREACH); } if (dst->dev == dev) { /* is this necessary? */ netdev_dbg(dev, "circular route to %pI6\n", &fl6.daddr); dst_release(dst); return ERR_PTR(-ELOOP); } #ifdef CONFIG_DST_CACHE if (dst_cache) dst_cache_set_ip6(dst_cache, dst, &fl6.saddr); #endif *saddr = fl6.saddr; return dst; } EXPORT_SYMBOL_GPL(udp_tunnel6_dst_lookup); MODULE_DESCRIPTION("IPv6 Foo over UDP tunnel driver"); MODULE_LICENSE("GPL"); |
| 5 1 1 1 85 81 5 5 5 5 1 1 1 1 2 2 1 | 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 | // SPDX-License-Identifier: GPL-2.0 #include "cgroup-internal.h" #include <linux/sched/task.h> #include <linux/slab.h> #include <linux/nsproxy.h> #include <linux/proc_ns.h> /* cgroup namespaces */ static struct ucounts *inc_cgroup_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_CGROUP_NAMESPACES); } static void dec_cgroup_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_CGROUP_NAMESPACES); } static struct cgroup_namespace *alloc_cgroup_ns(void) { struct cgroup_namespace *new_ns; int ret; new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL_ACCOUNT); if (!new_ns) return ERR_PTR(-ENOMEM); ret = ns_alloc_inum(&new_ns->ns); if (ret) { kfree(new_ns); return ERR_PTR(ret); } refcount_set(&new_ns->ns.count, 1); new_ns->ns.ops = &cgroupns_operations; return new_ns; } void free_cgroup_ns(struct cgroup_namespace *ns) { put_css_set(ns->root_cset); dec_cgroup_namespaces(ns->ucounts); put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); kfree(ns); } EXPORT_SYMBOL(free_cgroup_ns); struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, struct cgroup_namespace *old_ns) { struct cgroup_namespace *new_ns; struct ucounts *ucounts; struct css_set *cset; BUG_ON(!old_ns); if (!(flags & CLONE_NEWCGROUP)) { get_cgroup_ns(old_ns); return old_ns; } /* Allow only sysadmin to create cgroup namespace. */ if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); ucounts = inc_cgroup_namespaces(user_ns); if (!ucounts) return ERR_PTR(-ENOSPC); /* It is not safe to take cgroup_mutex here */ spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); spin_unlock_irq(&css_set_lock); new_ns = alloc_cgroup_ns(); if (IS_ERR(new_ns)) { put_css_set(cset); dec_cgroup_namespaces(ucounts); return new_ns; } new_ns->user_ns = get_user_ns(user_ns); new_ns->ucounts = ucounts; new_ns->root_cset = cset; return new_ns; } static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns) { return container_of(ns, struct cgroup_namespace, ns); } static int cgroupns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct cgroup_namespace *cgroup_ns = to_cg_ns(ns); if (!ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN) || !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; /* Don't need to do anything if we are attaching to our own cgroupns. */ if (cgroup_ns == nsproxy->cgroup_ns) return 0; get_cgroup_ns(cgroup_ns); put_cgroup_ns(nsproxy->cgroup_ns); nsproxy->cgroup_ns = cgroup_ns; return 0; } static struct ns_common *cgroupns_get(struct task_struct *task) { struct cgroup_namespace *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = nsproxy->cgroup_ns; get_cgroup_ns(ns); } task_unlock(task); return ns ? &ns->ns : NULL; } static void cgroupns_put(struct ns_common *ns) { put_cgroup_ns(to_cg_ns(ns)); } static struct user_namespace *cgroupns_owner(struct ns_common *ns) { return to_cg_ns(ns)->user_ns; } const struct proc_ns_operations cgroupns_operations = { .name = "cgroup", .type = CLONE_NEWCGROUP, .get = cgroupns_get, .put = cgroupns_put, .install = cgroupns_install, .owner = cgroupns_owner, }; |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VMALLOC_H #define _LINUX_VMALLOC_H #include <linux/alloc_tag.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <linux/init.h> #include <linux/list.h> #include <linux/llist.h> #include <asm/page.h> /* pgprot_t */ #include <linux/rbtree.h> #include <linux/overflow.h> #include <asm/vmalloc.h> struct vm_area_struct; /* vma defining user mapping in mm_types.h */ struct notifier_block; /* in notifier.h */ struct iov_iter; /* in uio.h */ /* bits in flags of vmalloc's vm_struct below */ #define VM_IOREMAP 0x00000001 /* ioremap() and friends */ #define VM_ALLOC 0x00000002 /* vmalloc() */ #define VM_MAP 0x00000004 /* vmap()ed pages */ #define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */ #define VM_DMA_COHERENT 0x00000010 /* dma_alloc_coherent */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ #define VM_NO_GUARD 0x00000040 /* ***DANGEROUS*** don't add guard page */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ #define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ #define VM_ALLOW_HUGE_VMAP 0x00000400 /* Allow for huge pages on archs with HAVE_ARCH_HUGE_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ !defined(CONFIG_KASAN_VMALLOC) #define VM_DEFER_KMEMLEAK 0x00000800 /* defer kmemleak object creation */ #else #define VM_DEFER_KMEMLEAK 0 #endif #define VM_SPARSE 0x00001000 /* sparse vm_area. not all pages are present. */ /* bits [20..32] reserved for arch specific ioremap internals */ /* * Maximum alignment for ioremap() regions. * Can be overridden by arch-specific value. */ #ifndef IOREMAP_MAX_ORDER #define IOREMAP_MAX_ORDER (7 + PAGE_SHIFT) /* 128 pages */ #endif struct vm_struct { struct vm_struct *next; void *addr; unsigned long size; unsigned long flags; struct page **pages; #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC unsigned int page_order; #endif unsigned int nr_pages; phys_addr_t phys_addr; const void *caller; }; struct vmap_area { unsigned long va_start; unsigned long va_end; struct rb_node rb_node; /* address sorted rbtree */ struct list_head list; /* address sorted list */ /* * The following two variables can be packed, because * a vmap_area object can be either: * 1) in "free" tree (root is free_vmap_area_root) * 2) or "busy" tree (root is vmap_area_root) */ union { unsigned long subtree_max_size; /* in "free" tree */ struct vm_struct *vm; /* in "busy" tree */ }; unsigned long flags; /* mark type of vm_map_ram area */ }; /* archs that select HAVE_ARCH_HUGE_VMAP should override one or more of these */ #ifndef arch_vmap_p4d_supported static inline bool arch_vmap_p4d_supported(pgprot_t prot) { return false; } #endif #ifndef arch_vmap_pud_supported static inline bool arch_vmap_pud_supported(pgprot_t prot) { return false; } #endif #ifndef arch_vmap_pmd_supported static inline bool arch_vmap_pmd_supported(pgprot_t prot) { return false; } #endif #ifndef arch_vmap_pte_range_map_size static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end, u64 pfn, unsigned int max_page_shift) { return PAGE_SIZE; } #endif #ifndef arch_vmap_pte_supported_shift static inline int arch_vmap_pte_supported_shift(unsigned long size) { return PAGE_SHIFT; } #endif #ifndef arch_vmap_pgprot_tagged static inline pgprot_t arch_vmap_pgprot_tagged(pgprot_t prot) { return prot; } #endif /* * Highlevel APIs for driver use */ extern void vm_unmap_ram(const void *mem, unsigned int count); extern void *vm_map_ram(struct page **pages, unsigned int count, int node); extern void vm_unmap_aliases(void); extern void *vmalloc_noprof(unsigned long size) __alloc_size(1); #define vmalloc(...) alloc_hooks(vmalloc_noprof(__VA_ARGS__)) extern void *vzalloc_noprof(unsigned long size) __alloc_size(1); #define vzalloc(...) alloc_hooks(vzalloc_noprof(__VA_ARGS__)) extern void *vmalloc_user_noprof(unsigned long size) __alloc_size(1); #define vmalloc_user(...) alloc_hooks(vmalloc_user_noprof(__VA_ARGS__)) extern void *vmalloc_node_noprof(unsigned long size, int node) __alloc_size(1); #define vmalloc_node(...) alloc_hooks(vmalloc_node_noprof(__VA_ARGS__)) extern void *vzalloc_node_noprof(unsigned long size, int node) __alloc_size(1); #define vzalloc_node(...) alloc_hooks(vzalloc_node_noprof(__VA_ARGS__)) extern void *vmalloc_32_noprof(unsigned long size) __alloc_size(1); #define vmalloc_32(...) alloc_hooks(vmalloc_32_noprof(__VA_ARGS__)) extern void *vmalloc_32_user_noprof(unsigned long size) __alloc_size(1); #define vmalloc_32_user(...) alloc_hooks(vmalloc_32_user_noprof(__VA_ARGS__)) extern void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask) __alloc_size(1); #define __vmalloc(...) alloc_hooks(__vmalloc_noprof(__VA_ARGS__)) extern void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller) __alloc_size(1); #define __vmalloc_node_range(...) alloc_hooks(__vmalloc_node_range_noprof(__VA_ARGS__)) void *__vmalloc_node_noprof(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) __alloc_size(1); #define __vmalloc_node(...) alloc_hooks(__vmalloc_node_noprof(__VA_ARGS__)) void *vmalloc_huge_noprof(unsigned long size, gfp_t gfp_mask) __alloc_size(1); #define vmalloc_huge(...) alloc_hooks(vmalloc_huge_noprof(__VA_ARGS__)) extern void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); #define __vmalloc_array(...) alloc_hooks(__vmalloc_array_noprof(__VA_ARGS__)) extern void *vmalloc_array_noprof(size_t n, size_t size) __alloc_size(1, 2); #define vmalloc_array(...) alloc_hooks(vmalloc_array_noprof(__VA_ARGS__)) extern void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); #define __vcalloc(...) alloc_hooks(__vcalloc_noprof(__VA_ARGS__)) extern void *vcalloc_noprof(size_t n, size_t size) __alloc_size(1, 2); #define vcalloc(...) alloc_hooks(vcalloc_noprof(__VA_ARGS__)) void * __must_check vrealloc_noprof(const void *p, size_t size, gfp_t flags) __realloc_size(2); #define vrealloc(...) alloc_hooks(vrealloc_noprof(__VA_ARGS__)) extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); extern void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot); void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot); extern void vunmap(const void *addr); extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, void *kaddr, unsigned long pgoff, unsigned long size); extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); /* * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings() * needs to be called. */ #ifndef ARCH_PAGE_TABLE_SYNC_MASK #define ARCH_PAGE_TABLE_SYNC_MASK 0 #endif /* * There is no default implementation for arch_sync_kernel_mappings(). It is * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK * is 0. */ void arch_sync_kernel_mappings(unsigned long start, unsigned long end); /* * Lowlevel-APIs (not for driver use!) */ static inline size_t get_vm_area_size(const struct vm_struct *area) { if (!(area->flags & VM_NO_GUARD)) /* return actual size without guard page */ return area->size - PAGE_SIZE; else return area->size; } extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags); extern struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller); extern struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, const void *caller); void free_vm_area(struct vm_struct *area); extern struct vm_struct *remove_vm_area(const void *addr); extern struct vm_struct *find_vm_area(const void *addr); struct vmap_area *find_vmap_area(unsigned long addr); static inline bool is_vm_area_hugepages(const void *addr) { /* * This may not 100% tell if the area is mapped with > PAGE_SIZE * page table entries, if for some reason the architecture indicates * larger sizes are available but decides not to use them, nothing * prevents that. This only indicates the size of the physical page * allocated in the vmalloc layer. */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC return find_vm_area(addr)->page_order > 0; #else return false; #endif } /* for /proc/kcore */ long vread_iter(struct iov_iter *iter, const char *addr, size_t count); /* * Internals. Don't use.. */ __init void vm_area_add_early(struct vm_struct *vm); __init void vm_area_register_early(struct vm_struct *vm, size_t align); int register_vmap_purge_notifier(struct notifier_block *nb); int unregister_vmap_purge_notifier(struct notifier_block *nb); #ifdef CONFIG_MMU #define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) unsigned long vmalloc_nr_pages(void); int vm_area_map_pages(struct vm_struct *area, unsigned long start, unsigned long end, struct page **pages); void vm_area_unmap_pages(struct vm_struct *area, unsigned long start, unsigned long end); void vunmap_range(unsigned long addr, unsigned long end); static inline void set_vm_flush_reset_perms(void *addr) { struct vm_struct *vm = find_vm_area(addr); if (vm) vm->flags |= VM_FLUSH_RESET_PERMS; } #else /* !CONFIG_MMU */ #define VMALLOC_TOTAL 0UL static inline unsigned long vmalloc_nr_pages(void) { return 0; } static inline void set_vm_flush_reset_perms(void *addr) {} #endif /* CONFIG_MMU */ #if defined(CONFIG_MMU) && defined(CONFIG_SMP) struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align); void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms); # else static inline struct vm_struct ** pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align) { return NULL; } static inline void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) {} #endif #if defined(CONFIG_MMU) && defined(CONFIG_PRINTK) bool vmalloc_dump_obj(void *object); #else static inline bool vmalloc_dump_obj(void *object) { return false; } #endif #endif /* _LINUX_VMALLOC_H */ |
| 155 150 153 1501 1503 1502 1504 1494 1501 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/irq_work.h> #include <linux/spinlock.h> #include <linux/task_work.h> #include <linux/resume_user_mode.h> static struct callback_head work_exited; /* all we need is ->next == NULL */ #ifdef CONFIG_IRQ_WORK static void task_work_set_notify_irq(struct irq_work *entry) { test_and_set_tsk_thread_flag(current, TIF_NOTIFY_RESUME); } static DEFINE_PER_CPU(struct irq_work, irq_work_NMI_resume) = IRQ_WORK_INIT_HARD(task_work_set_notify_irq); #endif /** * task_work_add - ask the @task to execute @work->func() * @task: the task which should run the callback * @work: the callback to run * @notify: how to notify the targeted task * * Queue @work for task_work_run() below and notify the @task if @notify * is @TWA_RESUME, @TWA_SIGNAL, @TWA_SIGNAL_NO_IPI or @TWA_NMI_CURRENT. * * @TWA_SIGNAL works like signals, in that the it will interrupt the targeted * task and run the task_work, regardless of whether the task is currently * running in the kernel or userspace. * @TWA_SIGNAL_NO_IPI works like @TWA_SIGNAL, except it doesn't send a * reschedule IPI to force the targeted task to reschedule and run task_work. * This can be advantageous if there's no strict requirement that the * task_work be run as soon as possible, just whenever the task enters the * kernel anyway. * @TWA_RESUME work is run only when the task exits the kernel and returns to * user mode, or before entering guest mode. * @TWA_NMI_CURRENT works like @TWA_RESUME, except it can only be used for the * current @task and if the current context is NMI. * * Fails if the @task is exiting/exited and thus it can't process this @work. * Otherwise @work->func() will be called when the @task goes through one of * the aforementioned transitions, or exits. * * If the targeted task is exiting, then an error is returned and the work item * is not queued. It's up to the caller to arrange for an alternative mechanism * in that case. * * Note: there is no ordering guarantee on works queued here. The task_work * list is LIFO. * * RETURNS: * 0 if succeeds or -ESRCH. */ int task_work_add(struct task_struct *task, struct callback_head *work, enum task_work_notify_mode notify) { struct callback_head *head; int flags = notify & TWA_FLAGS; notify &= ~TWA_FLAGS; if (notify == TWA_NMI_CURRENT) { if (WARN_ON_ONCE(task != current)) return -EINVAL; if (!IS_ENABLED(CONFIG_IRQ_WORK)) return -EINVAL; } else { /* * Record the work call stack in order to print it in KASAN * reports. * * Note that stack allocation can fail if TWAF_NO_ALLOC flag * is set and new page is needed to expand the stack buffer. */ if (flags & TWAF_NO_ALLOC) kasan_record_aux_stack_noalloc(work); else kasan_record_aux_stack(work); } head = READ_ONCE(task->task_works); do { if (unlikely(head == &work_exited)) return -ESRCH; work->next = head; } while (!try_cmpxchg(&task->task_works, &head, work)); switch (notify) { case TWA_NONE: break; case TWA_RESUME: set_notify_resume(task); break; case TWA_SIGNAL: set_notify_signal(task); break; case TWA_SIGNAL_NO_IPI: __set_notify_signal(task); break; #ifdef CONFIG_IRQ_WORK case TWA_NMI_CURRENT: irq_work_queue(this_cpu_ptr(&irq_work_NMI_resume)); break; #endif default: WARN_ON_ONCE(1); break; } return 0; } /** * task_work_cancel_match - cancel a pending work added by task_work_add() * @task: the task which should execute the work * @match: match function to call * @data: data to be passed in to match function * * RETURNS: * The found work or NULL if not found. */ struct callback_head * task_work_cancel_match(struct task_struct *task, bool (*match)(struct callback_head *, void *data), void *data) { struct callback_head **pprev = &task->task_works; struct callback_head *work; unsigned long flags; if (likely(!task_work_pending(task))) return NULL; /* * If cmpxchg() fails we continue without updating pprev. * Either we raced with task_work_add() which added the * new entry before this work, we will find it again. Or * we raced with task_work_run(), *pprev == NULL/exited. */ raw_spin_lock_irqsave(&task->pi_lock, flags); work = READ_ONCE(*pprev); while (work) { if (!match(work, data)) { pprev = &work->next; work = READ_ONCE(*pprev); } else if (try_cmpxchg(pprev, &work, work->next)) break; } raw_spin_unlock_irqrestore(&task->pi_lock, flags); return work; } static bool task_work_func_match(struct callback_head *cb, void *data) { return cb->func == data; } /** * task_work_cancel_func - cancel a pending work matching a function added by task_work_add() * @task: the task which should execute the func's work * @func: identifies the func to match with a work to remove * * Find the last queued pending work with ->func == @func and remove * it from queue. * * RETURNS: * The found work or NULL if not found. */ struct callback_head * task_work_cancel_func(struct task_struct *task, task_work_func_t func) { return task_work_cancel_match(task, task_work_func_match, func); } static bool task_work_match(struct callback_head *cb, void *data) { return cb == data; } /** * task_work_cancel - cancel a pending work added by task_work_add() * @task: the task which should execute the work * @cb: the callback to remove if queued * * Remove a callback from a task's queue if queued. * * RETURNS: * True if the callback was queued and got cancelled, false otherwise. */ bool task_work_cancel(struct task_struct *task, struct callback_head *cb) { struct callback_head *ret; ret = task_work_cancel_match(task, task_work_match, cb); return ret == cb; } /** * task_work_run - execute the works added by task_work_add() * * Flush the pending works. Should be used by the core kernel code. * Called before the task returns to the user-mode or stops, or when * it exits. In the latter case task_work_add() can no longer add the * new work after task_work_run() returns. */ void task_work_run(void) { struct task_struct *task = current; struct callback_head *work, *head, *next; for (;;) { /* * work->func() can do task_work_add(), do not set * work_exited unless the list is empty. */ work = READ_ONCE(task->task_works); do { head = NULL; if (!work) { if (task->flags & PF_EXITING) head = &work_exited; else break; } } while (!try_cmpxchg(&task->task_works, &work, head)); if (!work) break; /* * Synchronize with task_work_cancel_match(). It can not remove * the first entry == work, cmpxchg(task_works) must fail. * But it can remove another entry from the ->next list. */ raw_spin_lock_irq(&task->pi_lock); raw_spin_unlock_irq(&task->pi_lock); do { next = work->next; work->func(work); work = next; cond_resched(); } while (work); } } |
| 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved. */ #include <linux/libnvdimm.h> #include "rxe.h" #include "rxe_loc.h" /* Return a random 8 bit key value that is * different than the last_key. Set last_key to -1 * if this is the first key for an MR or MW */ u8 rxe_get_next_key(u32 last_key) { u8 key; do { get_random_bytes(&key, 1); } while (key == last_key); return key; } int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length) { switch (mr->ibmr.type) { case IB_MR_TYPE_DMA: return 0; case IB_MR_TYPE_USER: case IB_MR_TYPE_MEM_REG: if (iova < mr->ibmr.iova || iova + length > mr->ibmr.iova + mr->ibmr.length) { rxe_dbg_mr(mr, "iova/length out of range\n"); return -EINVAL; } return 0; default: rxe_dbg_mr(mr, "mr type not supported\n"); return -EINVAL; } } static void rxe_mr_init(int access, struct rxe_mr *mr) { u32 key = mr->elem.index << 8 | rxe_get_next_key(-1); /* set ibmr->l/rkey and also copy into private l/rkey * for user MRs these will always be the same * for cases where caller 'owns' the key portion * they may be different until REG_MR WQE is executed. */ mr->lkey = mr->ibmr.lkey = key; mr->rkey = mr->ibmr.rkey = key; mr->access = access; mr->ibmr.page_size = PAGE_SIZE; mr->page_mask = PAGE_MASK; mr->page_shift = PAGE_SHIFT; mr->state = RXE_MR_STATE_INVALID; } void rxe_mr_init_dma(int access, struct rxe_mr *mr) { rxe_mr_init(access, mr); mr->state = RXE_MR_STATE_VALID; mr->ibmr.type = IB_MR_TYPE_DMA; } static unsigned long rxe_mr_iova_to_index(struct rxe_mr *mr, u64 iova) { return (iova >> mr->page_shift) - (mr->ibmr.iova >> mr->page_shift); } static unsigned long rxe_mr_iova_to_page_offset(struct rxe_mr *mr, u64 iova) { return iova & (mr_page_size(mr) - 1); } static bool is_pmem_page(struct page *pg) { unsigned long paddr = page_to_phys(pg); return REGION_INTERSECTS == region_intersects(paddr, PAGE_SIZE, IORESOURCE_MEM, IORES_DESC_PERSISTENT_MEMORY); } static int rxe_mr_fill_pages_from_sgt(struct rxe_mr *mr, struct sg_table *sgt) { XA_STATE(xas, &mr->page_list, 0); struct sg_page_iter sg_iter; struct page *page; bool persistent = !!(mr->access & IB_ACCESS_FLUSH_PERSISTENT); __sg_page_iter_start(&sg_iter, sgt->sgl, sgt->orig_nents, 0); if (!__sg_page_iter_next(&sg_iter)) return 0; do { xas_lock(&xas); while (true) { page = sg_page_iter_page(&sg_iter); if (persistent && !is_pmem_page(page)) { rxe_dbg_mr(mr, "Page can't be persistent\n"); xas_set_err(&xas, -EINVAL); break; } xas_store(&xas, page); if (xas_error(&xas)) break; xas_next(&xas); if (!__sg_page_iter_next(&sg_iter)) break; } xas_unlock(&xas); } while (xas_nomem(&xas, GFP_KERNEL)); return xas_error(&xas); } int rxe_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length, int access, struct rxe_mr *mr) { struct ib_umem *umem; int err; rxe_mr_init(access, mr); xa_init(&mr->page_list); umem = ib_umem_get(&rxe->ib_dev, start, length, access); if (IS_ERR(umem)) { rxe_dbg_mr(mr, "Unable to pin memory region err = %d\n", (int)PTR_ERR(umem)); return PTR_ERR(umem); } err = rxe_mr_fill_pages_from_sgt(mr, &umem->sgt_append.sgt); if (err) { ib_umem_release(umem); return err; } mr->umem = umem; mr->ibmr.type = IB_MR_TYPE_USER; mr->state = RXE_MR_STATE_VALID; return 0; } static int rxe_mr_alloc(struct rxe_mr *mr, int num_buf) { XA_STATE(xas, &mr->page_list, 0); int i = 0; int err; xa_init(&mr->page_list); do { xas_lock(&xas); while (i != num_buf) { xas_store(&xas, XA_ZERO_ENTRY); if (xas_error(&xas)) break; xas_next(&xas); i++; } xas_unlock(&xas); } while (xas_nomem(&xas, GFP_KERNEL)); err = xas_error(&xas); if (err) return err; mr->num_buf = num_buf; return 0; } int rxe_mr_init_fast(int max_pages, struct rxe_mr *mr) { int err; /* always allow remote access for FMRs */ rxe_mr_init(RXE_ACCESS_REMOTE, mr); err = rxe_mr_alloc(mr, max_pages); if (err) goto err1; mr->state = RXE_MR_STATE_FREE; mr->ibmr.type = IB_MR_TYPE_MEM_REG; return 0; err1: return err; } static int rxe_set_page(struct ib_mr *ibmr, u64 dma_addr) { struct rxe_mr *mr = to_rmr(ibmr); struct page *page = ib_virt_dma_to_page(dma_addr); bool persistent = !!(mr->access & IB_ACCESS_FLUSH_PERSISTENT); int err; if (persistent && !is_pmem_page(page)) { rxe_dbg_mr(mr, "Page cannot be persistent\n"); return -EINVAL; } if (unlikely(mr->nbuf == mr->num_buf)) return -ENOMEM; err = xa_err(xa_store(&mr->page_list, mr->nbuf, page, GFP_KERNEL)); if (err) return err; mr->nbuf++; return 0; } int rxe_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sgl, int sg_nents, unsigned int *sg_offset) { struct rxe_mr *mr = to_rmr(ibmr); unsigned int page_size = mr_page_size(mr); mr->nbuf = 0; mr->page_shift = ilog2(page_size); mr->page_mask = ~((u64)page_size - 1); mr->page_offset = mr->ibmr.iova & (page_size - 1); return ib_sg_to_pages(ibmr, sgl, sg_nents, sg_offset, rxe_set_page); } static int rxe_mr_copy_xarray(struct rxe_mr *mr, u64 iova, void *addr, unsigned int length, enum rxe_mr_copy_dir dir) { unsigned int page_offset = rxe_mr_iova_to_page_offset(mr, iova); unsigned long index = rxe_mr_iova_to_index(mr, iova); unsigned int bytes; struct page *page; void *va; while (length) { page = xa_load(&mr->page_list, index); if (!page) return -EFAULT; bytes = min_t(unsigned int, length, mr_page_size(mr) - page_offset); va = kmap_local_page(page); if (dir == RXE_FROM_MR_OBJ) memcpy(addr, va + page_offset, bytes); else memcpy(va + page_offset, addr, bytes); kunmap_local(va); page_offset = 0; addr += bytes; length -= bytes; index++; } return 0; } static void rxe_mr_copy_dma(struct rxe_mr *mr, u64 dma_addr, void *addr, unsigned int length, enum rxe_mr_copy_dir dir) { unsigned int page_offset = dma_addr & (PAGE_SIZE - 1); unsigned int bytes; struct page *page; u8 *va; while (length) { page = ib_virt_dma_to_page(dma_addr); bytes = min_t(unsigned int, length, PAGE_SIZE - page_offset); va = kmap_local_page(page); if (dir == RXE_TO_MR_OBJ) memcpy(va + page_offset, addr, bytes); else memcpy(addr, va + page_offset, bytes); kunmap_local(va); page_offset = 0; dma_addr += bytes; addr += bytes; length -= bytes; } } int rxe_mr_copy(struct rxe_mr *mr, u64 iova, void *addr, unsigned int length, enum rxe_mr_copy_dir dir) { int err; if (length == 0) return 0; if (WARN_ON(!mr)) return -EINVAL; if (mr->ibmr.type == IB_MR_TYPE_DMA) { rxe_mr_copy_dma(mr, iova, addr, length, dir); return 0; } err = mr_check_range(mr, iova, length); if (unlikely(err)) { rxe_dbg_mr(mr, "iova out of range\n"); return err; } return rxe_mr_copy_xarray(mr, iova, addr, length, dir); } /* copy data in or out of a wqe, i.e. sg list * under the control of a dma descriptor */ int copy_data( struct rxe_pd *pd, int access, struct rxe_dma_info *dma, void *addr, int length, enum rxe_mr_copy_dir dir) { int bytes; struct rxe_sge *sge = &dma->sge[dma->cur_sge]; int offset = dma->sge_offset; int resid = dma->resid; struct rxe_mr *mr = NULL; u64 iova; int err; if (length == 0) return 0; if (length > resid) { err = -EINVAL; goto err2; } if (sge->length && (offset < sge->length)) { mr = lookup_mr(pd, access, sge->lkey, RXE_LOOKUP_LOCAL); if (!mr) { err = -EINVAL; goto err1; } } while (length > 0) { bytes = length; if (offset >= sge->length) { if (mr) { rxe_put(mr); mr = NULL; } sge++; dma->cur_sge++; offset = 0; if (dma->cur_sge >= dma->num_sge) { err = -ENOSPC; goto err2; } if (sge->length) { mr = lookup_mr(pd, access, sge->lkey, RXE_LOOKUP_LOCAL); if (!mr) { err = -EINVAL; goto err1; } } else { continue; } } if (bytes > sge->length - offset) bytes = sge->length - offset; if (bytes > 0) { iova = sge->addr + offset; err = rxe_mr_copy(mr, iova, addr, bytes, dir); if (err) goto err2; offset += bytes; resid -= bytes; length -= bytes; addr += bytes; } } dma->sge_offset = offset; dma->resid = resid; if (mr) rxe_put(mr); return 0; err2: if (mr) rxe_put(mr); err1: return err; } int rxe_flush_pmem_iova(struct rxe_mr *mr, u64 iova, unsigned int length) { unsigned int page_offset; unsigned long index; struct page *page; unsigned int bytes; int err; u8 *va; /* mr must be valid even if length is zero */ if (WARN_ON(!mr)) return -EINVAL; if (length == 0) return 0; if (mr->ibmr.type == IB_MR_TYPE_DMA) return -EFAULT; err = mr_check_range(mr, iova, length); if (err) return err; while (length > 0) { index = rxe_mr_iova_to_index(mr, iova); page = xa_load(&mr->page_list, index); page_offset = rxe_mr_iova_to_page_offset(mr, iova); if (!page) return -EFAULT; bytes = min_t(unsigned int, length, mr_page_size(mr) - page_offset); va = kmap_local_page(page); arch_wb_cache_pmem(va + page_offset, bytes); kunmap_local(va); length -= bytes; iova += bytes; page_offset = 0; } return 0; } /* Guarantee atomicity of atomic operations at the machine level. */ static DEFINE_SPINLOCK(atomic_ops_lock); int rxe_mr_do_atomic_op(struct rxe_mr *mr, u64 iova, int opcode, u64 compare, u64 swap_add, u64 *orig_val) { unsigned int page_offset; struct page *page; u64 value; u64 *va; if (unlikely(mr->state != RXE_MR_STATE_VALID)) { rxe_dbg_mr(mr, "mr not in valid state\n"); return RESPST_ERR_RKEY_VIOLATION; } if (mr->ibmr.type == IB_MR_TYPE_DMA) { page_offset = iova & (PAGE_SIZE - 1); page = ib_virt_dma_to_page(iova); } else { unsigned long index; int err; err = mr_check_range(mr, iova, sizeof(value)); if (err) { rxe_dbg_mr(mr, "iova out of range\n"); return RESPST_ERR_RKEY_VIOLATION; } page_offset = rxe_mr_iova_to_page_offset(mr, iova); index = rxe_mr_iova_to_index(mr, iova); page = xa_load(&mr->page_list, index); if (!page) return RESPST_ERR_RKEY_VIOLATION; } if (unlikely(page_offset & 0x7)) { rxe_dbg_mr(mr, "iova not aligned\n"); return RESPST_ERR_MISALIGNED_ATOMIC; } va = kmap_local_page(page); spin_lock_bh(&atomic_ops_lock); value = *orig_val = va[page_offset >> 3]; if (opcode == IB_OPCODE_RC_COMPARE_SWAP) { if (value == compare) va[page_offset >> 3] = swap_add; } else { value += swap_add; va[page_offset >> 3] = value; } spin_unlock_bh(&atomic_ops_lock); kunmap_local(va); return 0; } #if defined CONFIG_64BIT /* only implemented or called for 64 bit architectures */ int rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value) { unsigned int page_offset; struct page *page; u64 *va; /* See IBA oA19-28 */ if (unlikely(mr->state != RXE_MR_STATE_VALID)) { rxe_dbg_mr(mr, "mr not in valid state\n"); return RESPST_ERR_RKEY_VIOLATION; } if (mr->ibmr.type == IB_MR_TYPE_DMA) { page_offset = iova & (PAGE_SIZE - 1); page = ib_virt_dma_to_page(iova); } else { unsigned long index; int err; /* See IBA oA19-28 */ err = mr_check_range(mr, iova, sizeof(value)); if (unlikely(err)) { rxe_dbg_mr(mr, "iova out of range\n"); return RESPST_ERR_RKEY_VIOLATION; } page_offset = rxe_mr_iova_to_page_offset(mr, iova); index = rxe_mr_iova_to_index(mr, iova); page = xa_load(&mr->page_list, index); if (!page) return RESPST_ERR_RKEY_VIOLATION; } /* See IBA A19.4.2 */ if (unlikely(page_offset & 0x7)) { rxe_dbg_mr(mr, "misaligned address\n"); return RESPST_ERR_MISALIGNED_ATOMIC; } va = kmap_local_page(page); /* Do atomic write after all prior operations have completed */ smp_store_release(&va[page_offset >> 3], value); kunmap_local(va); return 0; } #else int rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value) { return RESPST_ERR_UNSUPPORTED_OPCODE; } #endif int advance_dma_data(struct rxe_dma_info *dma, unsigned int length) { struct rxe_sge *sge = &dma->sge[dma->cur_sge]; int offset = dma->sge_offset; int resid = dma->resid; while (length) { unsigned int bytes; if (offset >= sge->length) { sge++; dma->cur_sge++; offset = 0; if (dma->cur_sge >= dma->num_sge) return -ENOSPC; } bytes = length; if (bytes > sge->length - offset) bytes = sge->length - offset; offset += bytes; resid -= bytes; length -= bytes; } dma->sge_offset = offset; dma->resid = resid; return 0; } struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key, enum rxe_mr_lookup_type type) { struct rxe_mr *mr; struct rxe_dev *rxe = to_rdev(pd->ibpd.device); int index = key >> 8; mr = rxe_pool_get_index(&rxe->mr_pool, index); if (!mr) return NULL; if (unlikely((type == RXE_LOOKUP_LOCAL && mr->lkey != key) || (type == RXE_LOOKUP_REMOTE && mr->rkey != key) || mr_pd(mr) != pd || ((access & mr->access) != access) || mr->state != RXE_MR_STATE_VALID)) { rxe_put(mr); mr = NULL; } return mr; } int rxe_invalidate_mr(struct rxe_qp *qp, u32 key) { struct rxe_dev *rxe = to_rdev(qp->ibqp.device); struct rxe_mr *mr; int remote; int ret; mr = rxe_pool_get_index(&rxe->mr_pool, key >> 8); if (!mr) { rxe_dbg_qp(qp, "No MR for key %#x\n", key); ret = -EINVAL; goto err; } remote = mr->access & RXE_ACCESS_REMOTE; if (remote ? (key != mr->rkey) : (key != mr->lkey)) { rxe_dbg_mr(mr, "wr key (%#x) doesn't match mr key (%#x)\n", key, (remote ? mr->rkey : mr->lkey)); ret = -EINVAL; goto err_drop_ref; } if (atomic_read(&mr->num_mw) > 0) { rxe_dbg_mr(mr, "Attempt to invalidate an MR while bound to MWs\n"); ret = -EINVAL; goto err_drop_ref; } if (unlikely(mr->ibmr.type != IB_MR_TYPE_MEM_REG)) { rxe_dbg_mr(mr, "Type (%d) is wrong\n", mr->ibmr.type); ret = -EINVAL; goto err_drop_ref; } mr->state = RXE_MR_STATE_FREE; ret = 0; err_drop_ref: rxe_put(mr); err: return ret; } /* user can (re)register fast MR by executing a REG_MR WQE. * user is expected to hold a reference on the ib mr until the * WQE completes. * Once a fast MR is created this is the only way to change the * private keys. It is the responsibility of the user to maintain * the ib mr keys in sync with rxe mr keys. */ int rxe_reg_fast_mr(struct rxe_qp *qp, struct rxe_send_wqe *wqe) { struct rxe_mr *mr = to_rmr(wqe->wr.wr.reg.mr); u32 key = wqe->wr.wr.reg.key; u32 access = wqe->wr.wr.reg.access; /* user can only register MR in free state */ if (unlikely(mr->state != RXE_MR_STATE_FREE)) { rxe_dbg_mr(mr, "mr->lkey = 0x%x not free\n", mr->lkey); return -EINVAL; } /* user can only register mr with qp in same protection domain */ if (unlikely(qp->ibqp.pd != mr->ibmr.pd)) { rxe_dbg_mr(mr, "qp->pd and mr->pd don't match\n"); return -EINVAL; } /* user is only allowed to change key portion of l/rkey */ if (unlikely((mr->lkey & ~0xff) != (key & ~0xff))) { rxe_dbg_mr(mr, "key = 0x%x has wrong index mr->lkey = 0x%x\n", key, mr->lkey); return -EINVAL; } mr->access = access; mr->lkey = key; mr->rkey = key; mr->ibmr.iova = wqe->wr.wr.reg.mr->iova; mr->state = RXE_MR_STATE_VALID; return 0; } void rxe_mr_cleanup(struct rxe_pool_elem *elem) { struct rxe_mr *mr = container_of(elem, typeof(*mr), elem); rxe_put(mr_pd(mr)); ib_umem_release(mr->umem); if (mr->ibmr.type != IB_MR_TYPE_DMA) xa_destroy(&mr->page_list); } |
| 120 121 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* PIPAPO: PIle PAcket POlicies: set for arbitrary concatenations of ranges * * Copyright (c) 2019-2020 Red Hat GmbH * * Author: Stefano Brivio <sbrivio@redhat.com> */ /** * DOC: Theory of Operation * * * Problem * ------- * * Match packet bytes against entries composed of ranged or non-ranged packet * field specifiers, mapping them to arbitrary references. For example: * * :: * * --- fields ---> * | [net],[port],[net]... => [reference] * entries [net],[port],[net]... => [reference] * | [net],[port],[net]... => [reference] * V ... * * where [net] fields can be IP ranges or netmasks, and [port] fields are port * ranges. Arbitrary packet fields can be matched. * * * Algorithm Overview * ------------------ * * This algorithm is loosely inspired by [Ligatti 2010], and fundamentally * relies on the consideration that every contiguous range in a space of b bits * can be converted into b * 2 netmasks, from Theorem 3 in [Rottenstreich 2010], * as also illustrated in Section 9 of [Kogan 2014]. * * Classification against a number of entries, that require matching given bits * of a packet field, is performed by grouping those bits in sets of arbitrary * size, and classifying packet bits one group at a time. * * Example: * to match the source port (16 bits) of a packet, we can divide those 16 bits * in 4 groups of 4 bits each. Given the entry: * 0000 0001 0101 1001 * and a packet with source port: * 0000 0001 1010 1001 * first and second groups match, but the third doesn't. We conclude that the * packet doesn't match the given entry. * * Translate the set to a sequence of lookup tables, one per field. Each table * has two dimensions: bit groups to be matched for a single packet field, and * all the possible values of said groups (buckets). Input entries are * represented as one or more rules, depending on the number of composing * netmasks for the given field specifier, and a group match is indicated as a * set bit, with number corresponding to the rule index, in all the buckets * whose value matches the entry for a given group. * * Rules are mapped between fields through an array of x, n pairs, with each * item mapping a matched rule to one or more rules. The position of the pair in * the array indicates the matched rule to be mapped to the next field, x * indicates the first rule index in the next field, and n the amount of * next-field rules the current rule maps to. * * The mapping array for the last field maps to the desired references. * * To match, we perform table lookups using the values of grouped packet bits, * and use a sequence of bitwise operations to progressively evaluate rule * matching. * * A stand-alone, reference implementation, also including notes about possible * future optimisations, is available at: * https://pipapo.lameexcu.se/ * * Insertion * --------- * * - For each packet field: * * - divide the b packet bits we want to classify into groups of size t, * obtaining ceil(b / t) groups * * Example: match on destination IP address, with t = 4: 32 bits, 8 groups * of 4 bits each * * - allocate a lookup table with one column ("bucket") for each possible * value of a group, and with one row for each group * * Example: 8 groups, 2^4 buckets: * * :: * * bucket * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 * 0 * 1 * 2 * 3 * 4 * 5 * 6 * 7 * * - map the bits we want to classify for the current field, for a given * entry, to a single rule for non-ranged and netmask set items, and to one * or multiple rules for ranges. Ranges are expanded to composing netmasks * by pipapo_expand(). * * Example: 2 entries, 10.0.0.5:1024 and 192.168.1.0-192.168.2.1:2048 * - rule #0: 10.0.0.5 * - rule #1: 192.168.1.0/24 * - rule #2: 192.168.2.0/31 * * - insert references to the rules in the lookup table, selecting buckets * according to bit values of a rule in the given group. This is done by * pipapo_insert(). * * Example: given: * - rule #0: 10.0.0.5 mapping to buckets * < 0 10 0 0 0 0 0 5 > * - rule #1: 192.168.1.0/24 mapping to buckets * < 12 0 10 8 0 1 < 0..15 > < 0..15 > > * - rule #2: 192.168.2.0/31 mapping to buckets * < 12 0 10 8 0 2 0 < 0..1 > > * * these bits are set in the lookup table: * * :: * * bucket * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 * 0 0 1,2 * 1 1,2 0 * 2 0 1,2 * 3 0 1,2 * 4 0,1,2 * 5 0 1 2 * 6 0,1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 * 7 1,2 1,2 1 1 1 0,1 1 1 1 1 1 1 1 1 1 1 * * - if this is not the last field in the set, fill a mapping array that maps * rules from the lookup table to rules belonging to the same entry in * the next lookup table, done by pipapo_map(). * * Note that as rules map to contiguous ranges of rules, given how netmask * expansion and insertion is performed, &union nft_pipapo_map_bucket stores * this information as pairs of first rule index, rule count. * * Example: 2 entries, 10.0.0.5:1024 and 192.168.1.0-192.168.2.1:2048, * given lookup table #0 for field 0 (see example above): * * :: * * bucket * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 * 0 0 1,2 * 1 1,2 0 * 2 0 1,2 * 3 0 1,2 * 4 0,1,2 * 5 0 1 2 * 6 0,1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 * 7 1,2 1,2 1 1 1 0,1 1 1 1 1 1 1 1 1 1 1 * * and lookup table #1 for field 1 with: * - rule #0: 1024 mapping to buckets * < 0 0 4 0 > * - rule #1: 2048 mapping to buckets * < 0 0 5 0 > * * :: * * bucket * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 * 0 0,1 * 1 0,1 * 2 0 1 * 3 0,1 * * we need to map rules for 10.0.0.5 in lookup table #0 (rule #0) to 1024 * in lookup table #1 (rule #0) and rules for 192.168.1.0-192.168.2.1 * (rules #1, #2) to 2048 in lookup table #2 (rule #1): * * :: * * rule indices in current field: 0 1 2 * map to rules in next field: 0 1 1 * * - if this is the last field in the set, fill a mapping array that maps * rules from the last lookup table to element pointers, also done by * pipapo_map(). * * Note that, in this implementation, we have two elements (start, end) for * each entry. The pointer to the end element is stored in this array, and * the pointer to the start element is linked from it. * * Example: entry 10.0.0.5:1024 has a corresponding &struct nft_pipapo_elem * pointer, 0x66, and element for 192.168.1.0-192.168.2.1:2048 is at 0x42. * From the rules of lookup table #1 as mapped above: * * :: * * rule indices in last field: 0 1 * map to elements: 0x66 0x42 * * * Matching * -------- * * We use a result bitmap, with the size of a single lookup table bucket, to * represent the matching state that applies at every algorithm step. This is * done by pipapo_lookup(). * * - For each packet field: * * - start with an all-ones result bitmap (res_map in pipapo_lookup()) * * - perform a lookup into the table corresponding to the current field, * for each group, and at every group, AND the current result bitmap with * the value from the lookup table bucket * * :: * * Example: 192.168.1.5 < 12 0 10 8 0 1 0 5 >, with lookup table from * insertion examples. * Lookup table buckets are at least 3 bits wide, we'll assume 8 bits for * convenience in this example. Initial result bitmap is 0xff, the steps * below show the value of the result bitmap after each group is processed: * * bucket * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 * 0 0 1,2 * result bitmap is now: 0xff & 0x6 [bucket 12] = 0x6 * * 1 1,2 0 * result bitmap is now: 0x6 & 0x6 [bucket 0] = 0x6 * * 2 0 1,2 * result bitmap is now: 0x6 & 0x6 [bucket 10] = 0x6 * * 3 0 1,2 * result bitmap is now: 0x6 & 0x6 [bucket 8] = 0x6 * * 4 0,1,2 * result bitmap is now: 0x6 & 0x7 [bucket 0] = 0x6 * * 5 0 1 2 * result bitmap is now: 0x6 & 0x2 [bucket 1] = 0x2 * * 6 0,1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 * result bitmap is now: 0x2 & 0x7 [bucket 0] = 0x2 * * 7 1,2 1,2 1 1 1 0,1 1 1 1 1 1 1 1 1 1 1 * final result bitmap for this field is: 0x2 & 0x3 [bucket 5] = 0x2 * * - at the next field, start with a new, all-zeroes result bitmap. For each * bit set in the previous result bitmap, fill the new result bitmap * (fill_map in pipapo_lookup()) with the rule indices from the * corresponding buckets of the mapping field for this field, done by * pipapo_refill() * * Example: with mapping table from insertion examples, with the current * result bitmap from the previous example, 0x02: * * :: * * rule indices in current field: 0 1 2 * map to rules in next field: 0 1 1 * * the new result bitmap will be 0x02: rule 1 was set, and rule 1 will be * set. * * We can now extend this example to cover the second iteration of the step * above (lookup and AND bitmap): assuming the port field is * 2048 < 0 0 5 0 >, with starting result bitmap 0x2, and lookup table * for "port" field from pre-computation example: * * :: * * bucket * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 * 0 0,1 * 1 0,1 * 2 0 1 * 3 0,1 * * operations are: 0x2 & 0x3 [bucket 0] & 0x3 [bucket 0] & 0x2 [bucket 5] * & 0x3 [bucket 0], resulting bitmap is 0x2. * * - if this is the last field in the set, look up the value from the mapping * array corresponding to the final result bitmap * * Example: 0x2 resulting bitmap from 192.168.1.5:2048, mapping array for * last field from insertion example: * * :: * * rule indices in last field: 0 1 * map to elements: 0x66 0x42 * * the matching element is at 0x42. * * * References * ---------- * * [Ligatti 2010] * A Packet-classification Algorithm for Arbitrary Bitmask Rules, with * Automatic Time-space Tradeoffs * Jay Ligatti, Josh Kuhn, and Chris Gage. * Proceedings of the IEEE International Conference on Computer * Communication Networks (ICCCN), August 2010. * https://www.cse.usf.edu/~ligatti/papers/grouper-conf.pdf * * [Rottenstreich 2010] * Worst-Case TCAM Rule Expansion * Ori Rottenstreich and Isaac Keslassy. * 2010 Proceedings IEEE INFOCOM, San Diego, CA, 2010. * http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.212.4592&rep=rep1&type=pdf * * [Kogan 2014] * SAX-PAC (Scalable And eXpressive PAcket Classification) * Kirill Kogan, Sergey Nikolenko, Ori Rottenstreich, William Culhane, * and Patrick Eugster. * Proceedings of the 2014 ACM conference on SIGCOMM, August 2014. * https://www.sigcomm.org/sites/default/files/ccr/papers/2014/August/2619239-2626294.pdf */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <uapi/linux/netfilter/nf_tables.h> #include <linux/bitmap.h> #include <linux/bitops.h> #include "nft_set_pipapo_avx2.h" #include "nft_set_pipapo.h" /** * pipapo_refill() - For each set bit, set bits from selected mapping table item * @map: Bitmap to be scanned for set bits * @len: Length of bitmap in longs * @rules: Number of rules in field * @dst: Destination bitmap * @mt: Mapping table containing bit set specifiers * @match_only: Find a single bit and return, don't fill * * Iteration over set bits with __builtin_ctzl(): Daniel Lemire, public domain. * * For each bit set in map, select the bucket from mapping table with index * corresponding to the position of the bit set. Use start bit and amount of * bits specified in bucket to fill region in dst. * * Return: -1 on no match, bit position on 'match_only', 0 otherwise. */ int pipapo_refill(unsigned long *map, unsigned int len, unsigned int rules, unsigned long *dst, const union nft_pipapo_map_bucket *mt, bool match_only) { unsigned long bitset; unsigned int k; int ret = -1; for (k = 0; k < len; k++) { bitset = map[k]; while (bitset) { unsigned long t = bitset & -bitset; int r = __builtin_ctzl(bitset); int i = k * BITS_PER_LONG + r; if (unlikely(i >= rules)) { map[k] = 0; return -1; } if (match_only) { bitmap_clear(map, i, 1); return i; } ret = 0; bitmap_set(dst, mt[i].to, mt[i].n); bitset ^= t; } map[k] = 0; } return ret; } /** * nft_pipapo_lookup() - Lookup function * @net: Network namespace * @set: nftables API set representation * @key: nftables API element representation containing key data * @ext: nftables API extension pointer, filled with matching reference * * For more details, see DOC: Theory of Operation. * * Return: true on match, false otherwise. */ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_scratch *scratch; unsigned long *res_map, *fill_map; u8 genmask = nft_genmask_cur(net); const struct nft_pipapo_match *m; const struct nft_pipapo_field *f; const u8 *rp = (const u8 *)key; bool map_index; int i; local_bh_disable(); m = rcu_dereference(priv->match); if (unlikely(!m || !*raw_cpu_ptr(m->scratch))) goto out; scratch = *raw_cpu_ptr(m->scratch); map_index = scratch->map_index; res_map = scratch->map + (map_index ? m->bsize_max : 0); fill_map = scratch->map + (map_index ? 0 : m->bsize_max); pipapo_resmap_init(m, res_map); nft_pipapo_for_each_field(f, i, m) { bool last = i == m->field_count - 1; int b; /* For each bit group: select lookup table bucket depending on * packet bytes value, then AND bucket value */ if (likely(f->bb == 8)) pipapo_and_field_buckets_8bit(f, res_map, rp); else pipapo_and_field_buckets_4bit(f, res_map, rp); NFT_PIPAPO_GROUP_BITS_ARE_8_OR_4; rp += f->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f); /* Now populate the bitmap for the next field, unless this is * the last field, in which case return the matched 'ext' * pointer if any. * * Now res_map contains the matching bitmap, and fill_map is the * bitmap for the next field. */ next_match: b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt, last); if (b < 0) { scratch->map_index = map_index; local_bh_enable(); return false; } if (last) { *ext = &f->mt[b].e->ext; if (unlikely(nft_set_elem_expired(*ext) || !nft_set_elem_active(*ext, genmask))) goto next_match; /* Last field: we're just returning the key without * filling the initial bitmap for the next field, so the * current inactive bitmap is clean and can be reused as * *next* bitmap (not initial) for the next packet. */ scratch->map_index = map_index; local_bh_enable(); return true; } /* Swap bitmap indices: res_map is the initial bitmap for the * next field, and fill_map is guaranteed to be all-zeroes at * this point. */ map_index = !map_index; swap(res_map, fill_map); rp += NFT_PIPAPO_GROUPS_PADDING(f); } out: local_bh_enable(); return false; } /** * pipapo_get() - Get matching element reference given key data * @net: Network namespace * @set: nftables API set representation * @m: storage containing active/existing elements * @data: Key data to be matched against existing elements * @genmask: If set, check that element is active in given genmask * @tstamp: timestamp to check for expired elements * @gfp: the type of memory to allocate (see kmalloc). * * This is essentially the same as the lookup function, except that it matches * key data against the uncommitted copy and doesn't use preallocated maps for * bitmap results. * * Return: pointer to &struct nft_pipapo_elem on match, error pointer otherwise. */ static struct nft_pipapo_elem *pipapo_get(const struct net *net, const struct nft_set *set, const struct nft_pipapo_match *m, const u8 *data, u8 genmask, u64 tstamp, gfp_t gfp) { struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT); unsigned long *res_map, *fill_map = NULL; const struct nft_pipapo_field *f; int i; if (m->bsize_max == 0) return ret; res_map = kmalloc_array(m->bsize_max, sizeof(*res_map), gfp); if (!res_map) { ret = ERR_PTR(-ENOMEM); goto out; } fill_map = kcalloc(m->bsize_max, sizeof(*res_map), gfp); if (!fill_map) { ret = ERR_PTR(-ENOMEM); goto out; } pipapo_resmap_init(m, res_map); nft_pipapo_for_each_field(f, i, m) { bool last = i == m->field_count - 1; int b; /* For each bit group: select lookup table bucket depending on * packet bytes value, then AND bucket value */ if (f->bb == 8) pipapo_and_field_buckets_8bit(f, res_map, data); else if (f->bb == 4) pipapo_and_field_buckets_4bit(f, res_map, data); else BUG(); data += f->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f); /* Now populate the bitmap for the next field, unless this is * the last field, in which case return the matched 'ext' * pointer if any. * * Now res_map contains the matching bitmap, and fill_map is the * bitmap for the next field. */ next_match: b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt, last); if (b < 0) goto out; if (last) { if (__nft_set_elem_expired(&f->mt[b].e->ext, tstamp)) goto next_match; if ((genmask && !nft_set_elem_active(&f->mt[b].e->ext, genmask))) goto next_match; ret = f->mt[b].e; goto out; } data += NFT_PIPAPO_GROUPS_PADDING(f); /* Swap bitmap indices: fill_map will be the initial bitmap for * the next field (i.e. the new res_map), and res_map is * guaranteed to be all-zeroes at this point, ready to be filled * according to the next mapping table. */ swap(res_map, fill_map); } out: kfree(fill_map); kfree(res_map); return ret; } /** * nft_pipapo_get() - Get matching element reference given key data * @net: Network namespace * @set: nftables API set representation * @elem: nftables API element representation containing key data * @flags: Unused */ static struct nft_elem_priv * nft_pipapo_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m = rcu_dereference(priv->match); struct nft_pipapo_elem *e; e = pipapo_get(net, set, m, (const u8 *)elem->key.val.data, nft_genmask_cur(net), get_jiffies_64(), GFP_ATOMIC); if (IS_ERR(e)) return ERR_CAST(e); return &e->priv; } /** * pipapo_realloc_mt() - Reallocate mapping table if needed upon resize * @f: Field containing mapping table * @old_rules: Amount of existing mapped rules * @rules: Amount of new rules to map * * Return: 0 on success, negative error code on failure. */ static int pipapo_realloc_mt(struct nft_pipapo_field *f, unsigned int old_rules, unsigned int rules) { union nft_pipapo_map_bucket *new_mt = NULL, *old_mt = f->mt; const unsigned int extra = PAGE_SIZE / sizeof(*new_mt); unsigned int rules_alloc = rules; might_sleep(); if (unlikely(rules == 0)) goto out_free; /* growing and enough space left, no action needed */ if (rules > old_rules && f->rules_alloc > rules) return 0; /* downsize and extra slack has not grown too large */ if (rules < old_rules) { unsigned int remove = f->rules_alloc - rules; if (remove < (2u * extra)) return 0; } /* If set needs more than one page of memory for rules then * allocate another extra page to avoid frequent reallocation. */ if (rules > extra && check_add_overflow(rules, extra, &rules_alloc)) return -EOVERFLOW; new_mt = kvmalloc_array(rules_alloc, sizeof(*new_mt), GFP_KERNEL_ACCOUNT); if (!new_mt) return -ENOMEM; if (old_mt) memcpy(new_mt, old_mt, min(old_rules, rules) * sizeof(*new_mt)); if (rules > old_rules) { memset(new_mt + old_rules, 0, (rules - old_rules) * sizeof(*new_mt)); } out_free: f->rules_alloc = rules_alloc; f->mt = new_mt; kvfree(old_mt); return 0; } /** * pipapo_resize() - Resize lookup or mapping table, or both * @f: Field containing lookup and mapping tables * @old_rules: Previous amount of rules in field * @rules: New amount of rules * * Increase, decrease or maintain tables size depending on new amount of rules, * and copy data over. In case the new size is smaller, throw away data for * highest-numbered rules. * * Return: 0 on success, -ENOMEM on allocation failure. */ static int pipapo_resize(struct nft_pipapo_field *f, unsigned int old_rules, unsigned int rules) { long *new_lt = NULL, *new_p, *old_lt = f->lt, *old_p; unsigned int new_bucket_size, copy; int group, bucket, err; if (rules >= NFT_PIPAPO_RULE0_MAX) return -ENOSPC; new_bucket_size = DIV_ROUND_UP(rules, BITS_PER_LONG); #ifdef NFT_PIPAPO_ALIGN new_bucket_size = roundup(new_bucket_size, NFT_PIPAPO_ALIGN / sizeof(*new_lt)); #endif if (new_bucket_size == f->bsize) goto mt; if (new_bucket_size > f->bsize) copy = f->bsize; else copy = new_bucket_size; new_lt = kvzalloc(f->groups * NFT_PIPAPO_BUCKETS(f->bb) * new_bucket_size * sizeof(*new_lt) + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL); if (!new_lt) return -ENOMEM; new_p = NFT_PIPAPO_LT_ALIGN(new_lt); old_p = NFT_PIPAPO_LT_ALIGN(old_lt); for (group = 0; group < f->groups; group++) { for (bucket = 0; bucket < NFT_PIPAPO_BUCKETS(f->bb); bucket++) { memcpy(new_p, old_p, copy * sizeof(*new_p)); new_p += copy; old_p += copy; if (new_bucket_size > f->bsize) new_p += new_bucket_size - f->bsize; else old_p += f->bsize - new_bucket_size; } } mt: err = pipapo_realloc_mt(f, old_rules, rules); if (err) { kvfree(new_lt); return err; } if (new_lt) { f->bsize = new_bucket_size; f->lt = new_lt; kvfree(old_lt); } return 0; } /** * pipapo_bucket_set() - Set rule bit in bucket given group and group value * @f: Field containing lookup table * @rule: Rule index * @group: Group index * @v: Value of bit group */ static void pipapo_bucket_set(struct nft_pipapo_field *f, int rule, int group, int v) { unsigned long *pos; pos = NFT_PIPAPO_LT_ALIGN(f->lt); pos += f->bsize * NFT_PIPAPO_BUCKETS(f->bb) * group; pos += f->bsize * v; __set_bit(rule, pos); } /** * pipapo_lt_4b_to_8b() - Switch lookup table group width from 4 bits to 8 bits * @old_groups: Number of current groups * @bsize: Size of one bucket, in longs * @old_lt: Pointer to the current lookup table * @new_lt: Pointer to the new, pre-allocated lookup table * * Each bucket with index b in the new lookup table, belonging to group g, is * filled with the bit intersection between: * - bucket with index given by the upper 4 bits of b, from group g, and * - bucket with index given by the lower 4 bits of b, from group g + 1 * * That is, given buckets from the new lookup table N(x, y) and the old lookup * table O(x, y), with x bucket index, and y group index: * * N(b, g) := O(b / 16, g) & O(b % 16, g + 1) * * This ensures equivalence of the matching results on lookup. Two examples in * pictures: * * bucket * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 ... 254 255 * 0 ^ * 1 | ^ * ... ( & ) | * / \ | * / \ .-( & )-. * / bucket \ | | * group 0 / 1 2 3 \ 4 5 6 7 8 9 10 11 12 13 |14 15 | * 0 / \ | | * 1 \ | | * 2 | --' * 3 '- * ... */ static void pipapo_lt_4b_to_8b(int old_groups, int bsize, unsigned long *old_lt, unsigned long *new_lt) { int g, b, i; for (g = 0; g < old_groups / 2; g++) { int src_g0 = g * 2, src_g1 = g * 2 + 1; for (b = 0; b < NFT_PIPAPO_BUCKETS(8); b++) { int src_b0 = b / NFT_PIPAPO_BUCKETS(4); int src_b1 = b % NFT_PIPAPO_BUCKETS(4); int src_i0 = src_g0 * NFT_PIPAPO_BUCKETS(4) + src_b0; int src_i1 = src_g1 * NFT_PIPAPO_BUCKETS(4) + src_b1; for (i = 0; i < bsize; i++) { *new_lt = old_lt[src_i0 * bsize + i] & old_lt[src_i1 * bsize + i]; new_lt++; } } } } /** * pipapo_lt_8b_to_4b() - Switch lookup table group width from 8 bits to 4 bits * @old_groups: Number of current groups * @bsize: Size of one bucket, in longs * @old_lt: Pointer to the current lookup table * @new_lt: Pointer to the new, pre-allocated lookup table * * Each bucket with index b in the new lookup table, belonging to group g, is * filled with the bit union of: * - all the buckets with index such that the upper four bits of the lower byte * equal b, from group g, with g odd * - all the buckets with index such that the lower four bits equal b, from * group g, with g even * * That is, given buckets from the new lookup table N(x, y) and the old lookup * table O(x, y), with x bucket index, and y group index: * * - with g odd: N(b, g) := U(O(x, g) for each x : x = (b & 0xf0) >> 4) * - with g even: N(b, g) := U(O(x, g) for each x : x = b & 0x0f) * * where U() denotes the arbitrary union operation (binary OR of n terms). This * ensures equivalence of the matching results on lookup. */ static void pipapo_lt_8b_to_4b(int old_groups, int bsize, unsigned long *old_lt, unsigned long *new_lt) { int g, b, bsrc, i; memset(new_lt, 0, old_groups * 2 * NFT_PIPAPO_BUCKETS(4) * bsize * sizeof(unsigned long)); for (g = 0; g < old_groups * 2; g += 2) { int src_g = g / 2; for (b = 0; b < NFT_PIPAPO_BUCKETS(4); b++) { for (bsrc = NFT_PIPAPO_BUCKETS(8) * src_g; bsrc < NFT_PIPAPO_BUCKETS(8) * (src_g + 1); bsrc++) { if (((bsrc & 0xf0) >> 4) != b) continue; for (i = 0; i < bsize; i++) new_lt[i] |= old_lt[bsrc * bsize + i]; } new_lt += bsize; } for (b = 0; b < NFT_PIPAPO_BUCKETS(4); b++) { for (bsrc = NFT_PIPAPO_BUCKETS(8) * src_g; bsrc < NFT_PIPAPO_BUCKETS(8) * (src_g + 1); bsrc++) { if ((bsrc & 0x0f) != b) continue; for (i = 0; i < bsize; i++) new_lt[i] |= old_lt[bsrc * bsize + i]; } new_lt += bsize; } } } /** * pipapo_lt_bits_adjust() - Adjust group size for lookup table if needed * @f: Field containing lookup table */ static void pipapo_lt_bits_adjust(struct nft_pipapo_field *f) { unsigned int groups, bb; unsigned long *new_lt; size_t lt_size; lt_size = f->groups * NFT_PIPAPO_BUCKETS(f->bb) * f->bsize * sizeof(*f->lt); if (f->bb == NFT_PIPAPO_GROUP_BITS_SMALL_SET && lt_size > NFT_PIPAPO_LT_SIZE_HIGH) { groups = f->groups * 2; bb = NFT_PIPAPO_GROUP_BITS_LARGE_SET; lt_size = groups * NFT_PIPAPO_BUCKETS(bb) * f->bsize * sizeof(*f->lt); } else if (f->bb == NFT_PIPAPO_GROUP_BITS_LARGE_SET && lt_size < NFT_PIPAPO_LT_SIZE_LOW) { groups = f->groups / 2; bb = NFT_PIPAPO_GROUP_BITS_SMALL_SET; lt_size = groups * NFT_PIPAPO_BUCKETS(bb) * f->bsize * sizeof(*f->lt); /* Don't increase group width if the resulting lookup table size * would exceed the upper size threshold for a "small" set. */ if (lt_size > NFT_PIPAPO_LT_SIZE_HIGH) return; } else { return; } new_lt = kvzalloc(lt_size + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL_ACCOUNT); if (!new_lt) return; NFT_PIPAPO_GROUP_BITS_ARE_8_OR_4; if (f->bb == 4 && bb == 8) { pipapo_lt_4b_to_8b(f->groups, f->bsize, NFT_PIPAPO_LT_ALIGN(f->lt), NFT_PIPAPO_LT_ALIGN(new_lt)); } else if (f->bb == 8 && bb == 4) { pipapo_lt_8b_to_4b(f->groups, f->bsize, NFT_PIPAPO_LT_ALIGN(f->lt), NFT_PIPAPO_LT_ALIGN(new_lt)); } else { BUG(); } f->groups = groups; f->bb = bb; kvfree(f->lt); f->lt = new_lt; } /** * pipapo_insert() - Insert new rule in field given input key and mask length * @f: Field containing lookup table * @k: Input key for classification, without nftables padding * @mask_bits: Length of mask; matches field length for non-ranged entry * * Insert a new rule reference in lookup buckets corresponding to k and * mask_bits. * * Return: 1 on success (one rule inserted), negative error code on failure. */ static int pipapo_insert(struct nft_pipapo_field *f, const uint8_t *k, int mask_bits) { unsigned int rule = f->rules, group, ret, bit_offset = 0; ret = pipapo_resize(f, f->rules, f->rules + 1); if (ret) return ret; f->rules++; for (group = 0; group < f->groups; group++) { int i, v; u8 mask; v = k[group / (BITS_PER_BYTE / f->bb)]; v &= GENMASK(BITS_PER_BYTE - bit_offset - 1, 0); v >>= (BITS_PER_BYTE - bit_offset) - f->bb; bit_offset += f->bb; bit_offset %= BITS_PER_BYTE; if (mask_bits >= (group + 1) * f->bb) { /* Not masked */ pipapo_bucket_set(f, rule, group, v); } else if (mask_bits <= group * f->bb) { /* Completely masked */ for (i = 0; i < NFT_PIPAPO_BUCKETS(f->bb); i++) pipapo_bucket_set(f, rule, group, i); } else { /* The mask limit falls on this group */ mask = GENMASK(f->bb - 1, 0); mask >>= mask_bits - group * f->bb; for (i = 0; i < NFT_PIPAPO_BUCKETS(f->bb); i++) { if ((i & ~mask) == (v & ~mask)) pipapo_bucket_set(f, rule, group, i); } } } pipapo_lt_bits_adjust(f); return 1; } /** * pipapo_step_diff() - Check if setting @step bit in netmask would change it * @base: Mask we are expanding * @step: Step bit for given expansion step * @len: Total length of mask space (set and unset bits), bytes * * Convenience function for mask expansion. * * Return: true if step bit changes mask (i.e. isn't set), false otherwise. */ static bool pipapo_step_diff(u8 *base, int step, int len) { /* Network order, byte-addressed */ #ifdef __BIG_ENDIAN__ return !(BIT(step % BITS_PER_BYTE) & base[step / BITS_PER_BYTE]); #else return !(BIT(step % BITS_PER_BYTE) & base[len - 1 - step / BITS_PER_BYTE]); #endif } /** * pipapo_step_after_end() - Check if mask exceeds range end with given step * @base: Mask we are expanding * @end: End of range * @step: Step bit for given expansion step, highest bit to be set * @len: Total length of mask space (set and unset bits), bytes * * Convenience function for mask expansion. * * Return: true if mask exceeds range setting step bits, false otherwise. */ static bool pipapo_step_after_end(const u8 *base, const u8 *end, int step, int len) { u8 tmp[NFT_PIPAPO_MAX_BYTES]; int i; memcpy(tmp, base, len); /* Network order, byte-addressed */ for (i = 0; i <= step; i++) #ifdef __BIG_ENDIAN__ tmp[i / BITS_PER_BYTE] |= BIT(i % BITS_PER_BYTE); #else tmp[len - 1 - i / BITS_PER_BYTE] |= BIT(i % BITS_PER_BYTE); #endif return memcmp(tmp, end, len) > 0; } /** * pipapo_base_sum() - Sum step bit to given len-sized netmask base with carry * @base: Netmask base * @step: Step bit to sum * @len: Netmask length, bytes */ static void pipapo_base_sum(u8 *base, int step, int len) { bool carry = false; int i; /* Network order, byte-addressed */ #ifdef __BIG_ENDIAN__ for (i = step / BITS_PER_BYTE; i < len; i++) { #else for (i = len - 1 - step / BITS_PER_BYTE; i >= 0; i--) { #endif if (carry) base[i]++; else base[i] += 1 << (step % BITS_PER_BYTE); if (base[i]) break; carry = true; } } /** * pipapo_expand() - Expand to composing netmasks, insert into lookup table * @f: Field containing lookup table * @start: Start of range * @end: End of range * @len: Length of value in bits * * Expand range to composing netmasks and insert corresponding rule references * in lookup buckets. * * Return: number of inserted rules on success, negative error code on failure. */ static int pipapo_expand(struct nft_pipapo_field *f, const u8 *start, const u8 *end, int len) { int step, masks = 0, bytes = DIV_ROUND_UP(len, BITS_PER_BYTE); u8 base[NFT_PIPAPO_MAX_BYTES]; memcpy(base, start, bytes); while (memcmp(base, end, bytes) <= 0) { int err; step = 0; while (pipapo_step_diff(base, step, bytes)) { if (pipapo_step_after_end(base, end, step, bytes)) break; step++; if (step >= len) { if (!masks) { err = pipapo_insert(f, base, 0); if (err < 0) return err; masks = 1; } goto out; } } err = pipapo_insert(f, base, len - step); if (err < 0) return err; masks++; pipapo_base_sum(base, step, bytes); } out: return masks; } /** * pipapo_map() - Insert rules in mapping tables, mapping them between fields * @m: Matching data, including mapping table * @map: Table of rule maps: array of first rule and amount of rules * in next field a given rule maps to, for each field * @e: For last field, nft_set_ext pointer matching rules map to */ static void pipapo_map(struct nft_pipapo_match *m, union nft_pipapo_map_bucket map[NFT_PIPAPO_MAX_FIELDS], struct nft_pipapo_elem *e) { struct nft_pipapo_field *f; int i, j; for (i = 0, f = m->f; i < m->field_count - 1; i++, f++) { for (j = 0; j < map[i].n; j++) { f->mt[map[i].to + j].to = map[i + 1].to; f->mt[map[i].to + j].n = map[i + 1].n; } } /* Last field: map to ext instead of mapping to next field */ for (j = 0; j < map[i].n; j++) f->mt[map[i].to + j].e = e; } /** * pipapo_free_scratch() - Free per-CPU map at original (not aligned) address * @m: Matching data * @cpu: CPU number */ static void pipapo_free_scratch(const struct nft_pipapo_match *m, unsigned int cpu) { struct nft_pipapo_scratch *s; void *mem; s = *per_cpu_ptr(m->scratch, cpu); if (!s) return; mem = s; mem -= s->align_off; kfree(mem); } /** * pipapo_realloc_scratch() - Reallocate scratch maps for partial match results * @clone: Copy of matching data with pending insertions and deletions * @bsize_max: Maximum bucket size, scratch maps cover two buckets * * Return: 0 on success, -ENOMEM on failure. */ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, unsigned long bsize_max) { int i; for_each_possible_cpu(i) { struct nft_pipapo_scratch *scratch; #ifdef NFT_PIPAPO_ALIGN void *scratch_aligned; u32 align_off; #endif scratch = kzalloc_node(struct_size(scratch, map, bsize_max * 2) + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL_ACCOUNT, cpu_to_node(i)); if (!scratch) { /* On failure, there's no need to undo previous * allocations: this means that some scratch maps have * a bigger allocated size now (this is only called on * insertion), but the extra space won't be used by any * CPU as new elements are not inserted and m->bsize_max * is not updated. */ return -ENOMEM; } pipapo_free_scratch(clone, i); #ifdef NFT_PIPAPO_ALIGN /* Align &scratch->map (not the struct itself): the extra * %NFT_PIPAPO_ALIGN_HEADROOM bytes passed to kzalloc_node() * above guarantee we can waste up to those bytes in order * to align the map field regardless of its offset within * the struct. */ BUILD_BUG_ON(offsetof(struct nft_pipapo_scratch, map) > NFT_PIPAPO_ALIGN_HEADROOM); scratch_aligned = NFT_PIPAPO_LT_ALIGN(&scratch->map); scratch_aligned -= offsetof(struct nft_pipapo_scratch, map); align_off = scratch_aligned - (void *)scratch; scratch = scratch_aligned; scratch->align_off = align_off; #endif *per_cpu_ptr(clone->scratch, i) = scratch; } return 0; } static bool nft_pipapo_transaction_mutex_held(const struct nft_set *set) { #ifdef CONFIG_PROVE_LOCKING const struct net *net = read_pnet(&set->net); return lockdep_is_held(&nft_pernet(net)->commit_mutex); #else return true; #endif } static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old); /** * pipapo_maybe_clone() - Build clone for pending data changes, if not existing * @set: nftables API set representation * * Return: newly created or existing clone, if any. NULL on allocation failure */ static struct nft_pipapo_match *pipapo_maybe_clone(const struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m; if (priv->clone) return priv->clone; m = rcu_dereference_protected(priv->match, nft_pipapo_transaction_mutex_held(set)); priv->clone = pipapo_clone(m); return priv->clone; } /** * nft_pipapo_insert() - Validate and insert ranged elements * @net: Network namespace * @set: nftables API set representation * @elem: nftables API element representation containing key data * @elem_priv: Filled with pointer to &struct nft_set_ext in inserted element * * Return: 0 on success, error pointer on failure. */ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, struct nft_elem_priv **elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; const u8 *start = (const u8 *)elem->key.val.data, *end; struct nft_pipapo_match *m = pipapo_maybe_clone(set); u8 genmask = nft_genmask_next(net); struct nft_pipapo_elem *e, *dup; u64 tstamp = nft_net_tstamp(net); struct nft_pipapo_field *f; const u8 *start_p, *end_p; int i, bsize_max, err = 0; if (!m) return -ENOMEM; if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END)) end = (const u8 *)nft_set_ext_key_end(ext)->data; else end = start; dup = pipapo_get(net, set, m, start, genmask, tstamp, GFP_KERNEL); if (!IS_ERR(dup)) { /* Check if we already have the same exact entry */ const struct nft_data *dup_key, *dup_end; dup_key = nft_set_ext_key(&dup->ext); if (nft_set_ext_exists(&dup->ext, NFT_SET_EXT_KEY_END)) dup_end = nft_set_ext_key_end(&dup->ext); else dup_end = dup_key; if (!memcmp(start, dup_key->data, sizeof(*dup_key->data)) && !memcmp(end, dup_end->data, sizeof(*dup_end->data))) { *elem_priv = &dup->priv; return -EEXIST; } return -ENOTEMPTY; } if (PTR_ERR(dup) == -ENOENT) { /* Look for partially overlapping entries */ dup = pipapo_get(net, set, m, end, nft_genmask_next(net), tstamp, GFP_KERNEL); } if (PTR_ERR(dup) != -ENOENT) { if (IS_ERR(dup)) return PTR_ERR(dup); *elem_priv = &dup->priv; return -ENOTEMPTY; } /* Validate */ start_p = start; end_p = end; /* some helpers return -1, or 0 >= for valid rule pos, * so we cannot support more than INT_MAX rules at this time. */ BUILD_BUG_ON(NFT_PIPAPO_RULE0_MAX > INT_MAX); nft_pipapo_for_each_field(f, i, m) { if (f->rules >= NFT_PIPAPO_RULE0_MAX) return -ENOSPC; if (memcmp(start_p, end_p, f->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f)) > 0) return -EINVAL; start_p += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); end_p += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); } /* Insert */ bsize_max = m->bsize_max; nft_pipapo_for_each_field(f, i, m) { int ret; rulemap[i].to = f->rules; ret = memcmp(start, end, f->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f)); if (!ret) ret = pipapo_insert(f, start, f->groups * f->bb); else ret = pipapo_expand(f, start, end, f->groups * f->bb); if (ret < 0) return ret; if (f->bsize > bsize_max) bsize_max = f->bsize; rulemap[i].n = ret; start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); } if (!*get_cpu_ptr(m->scratch) || bsize_max > m->bsize_max) { put_cpu_ptr(m->scratch); err = pipapo_realloc_scratch(m, bsize_max); if (err) return err; m->bsize_max = bsize_max; } else { put_cpu_ptr(m->scratch); } e = nft_elem_priv_cast(elem->priv); *elem_priv = &e->priv; pipapo_map(m, rulemap, e); return 0; } /** * pipapo_clone() - Clone matching data to create new working copy * @old: Existing matching data * * Return: copy of matching data passed as 'old' or NULL. */ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old) { struct nft_pipapo_field *dst, *src; struct nft_pipapo_match *new; int i; new = kmalloc(struct_size(new, f, old->field_count), GFP_KERNEL_ACCOUNT); if (!new) return NULL; new->field_count = old->field_count; new->bsize_max = old->bsize_max; new->scratch = alloc_percpu(*new->scratch); if (!new->scratch) goto out_scratch; for_each_possible_cpu(i) *per_cpu_ptr(new->scratch, i) = NULL; if (pipapo_realloc_scratch(new, old->bsize_max)) goto out_scratch_realloc; rcu_head_init(&new->rcu); src = old->f; dst = new->f; for (i = 0; i < old->field_count; i++) { unsigned long *new_lt; memcpy(dst, src, offsetof(struct nft_pipapo_field, lt)); new_lt = kvzalloc(src->groups * NFT_PIPAPO_BUCKETS(src->bb) * src->bsize * sizeof(*dst->lt) + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL_ACCOUNT); if (!new_lt) goto out_lt; dst->lt = new_lt; memcpy(NFT_PIPAPO_LT_ALIGN(new_lt), NFT_PIPAPO_LT_ALIGN(src->lt), src->bsize * sizeof(*dst->lt) * src->groups * NFT_PIPAPO_BUCKETS(src->bb)); if (src->rules > 0) { dst->mt = kvmalloc_array(src->rules_alloc, sizeof(*src->mt), GFP_KERNEL_ACCOUNT); if (!dst->mt) goto out_mt; memcpy(dst->mt, src->mt, src->rules * sizeof(*src->mt)); } else { dst->mt = NULL; dst->rules_alloc = 0; } src++; dst++; } return new; out_mt: kvfree(dst->lt); out_lt: for (dst--; i > 0; i--) { kvfree(dst->mt); kvfree(dst->lt); dst--; } out_scratch_realloc: for_each_possible_cpu(i) pipapo_free_scratch(new, i); out_scratch: free_percpu(new->scratch); kfree(new); return NULL; } /** * pipapo_rules_same_key() - Get number of rules originated from the same entry * @f: Field containing mapping table * @first: Index of first rule in set of rules mapping to same entry * * Using the fact that all rules in a field that originated from the same entry * will map to the same set of rules in the next field, or to the same element * reference, return the cardinality of the set of rules that originated from * the same entry as the rule with index @first, @first rule included. * * In pictures: * rules * field #0 0 1 2 3 4 * map to: 0 1 2-4 2-4 5-9 * . . ....... . ... * | | | | \ \ * | | | | \ \ * | | | | \ \ * ' ' ' ' ' \ * in field #1 0 1 2 3 4 5 ... * * if this is called for rule 2 on field #0, it will return 3, as also rules 2 * and 3 in field 0 map to the same set of rules (2, 3, 4) in the next field. * * For the last field in a set, we can rely on associated entries to map to the * same element references. * * Return: Number of rules that originated from the same entry as @first. */ static unsigned int pipapo_rules_same_key(struct nft_pipapo_field *f, unsigned int first) { struct nft_pipapo_elem *e = NULL; /* Keep gcc happy */ unsigned int r; for (r = first; r < f->rules; r++) { if (r != first && e != f->mt[r].e) return r - first; e = f->mt[r].e; } if (r != first) return r - first; return 0; } /** * pipapo_unmap() - Remove rules from mapping tables, renumber remaining ones * @mt: Mapping array * @rules: Original amount of rules in mapping table * @start: First rule index to be removed * @n: Amount of rules to be removed * @to_offset: First rule index, in next field, this group of rules maps to * @is_last: If this is the last field, delete reference from mapping array * * This is used to unmap rules from the mapping table for a single field, * maintaining consistency and compactness for the existing ones. * * In pictures: let's assume that we want to delete rules 2 and 3 from the * following mapping array: * * rules * 0 1 2 3 4 * map to: 4-10 4-10 11-15 11-15 16-18 * * the result will be: * * rules * 0 1 2 * map to: 4-10 4-10 11-13 * * for fields before the last one. In case this is the mapping table for the * last field in a set, and rules map to pointers to &struct nft_pipapo_elem: * * rules * 0 1 2 3 4 * element pointers: 0x42 0x42 0x33 0x33 0x44 * * the result will be: * * rules * 0 1 2 * element pointers: 0x42 0x42 0x44 */ static void pipapo_unmap(union nft_pipapo_map_bucket *mt, unsigned int rules, unsigned int start, unsigned int n, unsigned int to_offset, bool is_last) { int i; memmove(mt + start, mt + start + n, (rules - start - n) * sizeof(*mt)); memset(mt + rules - n, 0, n * sizeof(*mt)); if (is_last) return; for (i = start; i < rules - n; i++) mt[i].to -= to_offset; } /** * pipapo_drop() - Delete entry from lookup and mapping tables, given rule map * @m: Matching data * @rulemap: Table of rule maps, arrays of first rule and amount of rules * in next field a given entry maps to, for each field * * For each rule in lookup table buckets mapping to this set of rules, drop * all bits set in lookup table mapping. In pictures, assuming we want to drop * rules 0 and 1 from this lookup table: * * bucket * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 * 0 0 1,2 * 1 1,2 0 * 2 0 1,2 * 3 0 1,2 * 4 0,1,2 * 5 0 1 2 * 6 0,1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 * 7 1,2 1,2 1 1 1 0,1 1 1 1 1 1 1 1 1 1 1 * * rule 2 becomes rule 0, and the result will be: * * bucket * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 * 0 0 * 1 0 * 2 0 * 3 0 * 4 0 * 5 0 * 6 0 * 7 0 0 * * once this is done, call unmap() to drop all the corresponding rule references * from mapping tables. */ static void pipapo_drop(struct nft_pipapo_match *m, union nft_pipapo_map_bucket rulemap[]) { struct nft_pipapo_field *f; int i; nft_pipapo_for_each_field(f, i, m) { int g; for (g = 0; g < f->groups; g++) { unsigned long *pos; int b; pos = NFT_PIPAPO_LT_ALIGN(f->lt) + g * NFT_PIPAPO_BUCKETS(f->bb) * f->bsize; for (b = 0; b < NFT_PIPAPO_BUCKETS(f->bb); b++) { bitmap_cut(pos, pos, rulemap[i].to, rulemap[i].n, f->bsize * BITS_PER_LONG); pos += f->bsize; } } pipapo_unmap(f->mt, f->rules, rulemap[i].to, rulemap[i].n, rulemap[i + 1].n, i == m->field_count - 1); if (pipapo_resize(f, f->rules, f->rules - rulemap[i].n)) { /* We can ignore this, a failure to shrink tables down * doesn't make tables invalid. */ ; } f->rules -= rulemap[i].n; pipapo_lt_bits_adjust(f); } } static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set, struct nft_pipapo_elem *e) { nft_setelem_data_deactivate(net, set, &e->priv); } /** * pipapo_gc() - Drop expired entries from set, destroy start and end elements * @set: nftables API set representation * @m: Matching data */ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) { struct nft_pipapo *priv = nft_set_priv(set); struct net *net = read_pnet(&set->net); unsigned int rules_f0, first_rule = 0; u64 tstamp = nft_net_tstamp(net); struct nft_pipapo_elem *e; struct nft_trans_gc *gc; gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); if (!gc) return; while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; const struct nft_pipapo_field *f; unsigned int i, start, rules_fx; start = first_rule; rules_fx = rules_f0; nft_pipapo_for_each_field(f, i, m) { rulemap[i].to = start; rulemap[i].n = rules_fx; if (i < m->field_count - 1) { rules_fx = f->mt[start].n; start = f->mt[start].to; } } /* Pick the last field, and its last index */ f--; i--; e = f->mt[rulemap[i].to].e; /* synchronous gc never fails, there is no need to set on * NFT_SET_ELEM_DEAD_BIT. */ if (__nft_set_elem_expired(&e->ext, tstamp)) { gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); if (!gc) return; nft_pipapo_gc_deactivate(net, set, e); pipapo_drop(m, rulemap); nft_trans_gc_elem_add(gc, e); /* And check again current first rule, which is now the * first we haven't checked. */ } else { first_rule += rules_f0; } } gc = nft_trans_gc_catchall_sync(gc); if (gc) { nft_trans_gc_queue_sync_done(gc); priv->last_gc = jiffies; } } /** * pipapo_free_fields() - Free per-field tables contained in matching data * @m: Matching data */ static void pipapo_free_fields(struct nft_pipapo_match *m) { struct nft_pipapo_field *f; int i; nft_pipapo_for_each_field(f, i, m) { kvfree(f->lt); kvfree(f->mt); } } static void pipapo_free_match(struct nft_pipapo_match *m) { int i; for_each_possible_cpu(i) pipapo_free_scratch(m, i); free_percpu(m->scratch); pipapo_free_fields(m); kfree(m); } /** * pipapo_reclaim_match - RCU callback to free fields from old matching data * @rcu: RCU head */ static void pipapo_reclaim_match(struct rcu_head *rcu) { struct nft_pipapo_match *m; m = container_of(rcu, struct nft_pipapo_match, rcu); pipapo_free_match(m); } /** * nft_pipapo_commit() - Replace lookup data with current working copy * @set: nftables API set representation * * While at it, check if we should perform garbage collection on the working * copy before committing it for lookup, and don't replace the table if the * working copy doesn't have pending changes. * * We also need to create a new working copy for subsequent insertions and * deletions. */ static void nft_pipapo_commit(struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *old; if (!priv->clone) return; if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set))) pipapo_gc(set, priv->clone); old = rcu_replace_pointer(priv->match, priv->clone, nft_pipapo_transaction_mutex_held(set)); priv->clone = NULL; if (old) call_rcu(&old->rcu, pipapo_reclaim_match); } static void nft_pipapo_abort(const struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); if (!priv->clone) return; pipapo_free_match(priv->clone); priv->clone = NULL; } /** * nft_pipapo_activate() - Mark element reference as active given key, commit * @net: Network namespace * @set: nftables API set representation * @elem_priv: nftables API element representation containing key data * * On insertion, elements are added to a copy of the matching data currently * in use for lookups, and not directly inserted into current lookup data. Both * nft_pipapo_insert() and nft_pipapo_activate() are called once for each * element, hence we can't purpose either one as a real commit operation. */ static void nft_pipapo_activate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_pipapo_elem *e = nft_elem_priv_cast(elem_priv); nft_clear(net, &e->ext); } /** * nft_pipapo_deactivate() - Search for element and make it inactive * @net: Network namespace * @set: nftables API set representation * @elem: nftables API element representation containing key data * * Return: deactivated element if found, NULL otherwise. */ static struct nft_elem_priv * nft_pipapo_deactivate(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_pipapo_match *m = pipapo_maybe_clone(set); struct nft_pipapo_elem *e; /* removal must occur on priv->clone, if we are low on memory * we have no choice and must fail the removal request. */ if (!m) return NULL; e = pipapo_get(net, set, m, (const u8 *)elem->key.val.data, nft_genmask_next(net), nft_net_tstamp(net), GFP_KERNEL); if (IS_ERR(e)) return NULL; nft_set_elem_change_active(net, set, &e->ext); return &e->priv; } /** * nft_pipapo_flush() - make element inactive * @net: Network namespace * @set: nftables API set representation * @elem_priv: nftables API element representation containing key data * * This is functionally the same as nft_pipapo_deactivate(), with a slightly * different interface, and it's also called once for each element in a set * being flushed, so we can't implement, strictly speaking, a flush operation, * which would otherwise be as simple as allocating an empty copy of the * matching data. * * Note that we could in theory do that, mark the set as flushed, and ignore * subsequent calls, but we would leak all the elements after the first one, * because they wouldn't then be freed as result of API calls. * * Return: true if element was found and deactivated. */ static void nft_pipapo_flush(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_pipapo_elem *e = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &e->ext); } /** * pipapo_get_boundaries() - Get byte interval for associated rules * @f: Field including lookup table * @first_rule: First rule (lowest index) * @rule_count: Number of associated rules * @left: Byte expression for left boundary (start of range) * @right: Byte expression for right boundary (end of range) * * Given the first rule and amount of rules that originated from the same entry, * build the original range associated with the entry, and calculate the length * of the originating netmask. * * In pictures: * * bucket * group 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 * 0 1,2 * 1 1,2 * 2 1,2 * 3 1,2 * 4 1,2 * 5 1 2 * 6 1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 * 7 1,2 1,2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 * * this is the lookup table corresponding to the IPv4 range * 192.168.1.0-192.168.2.1, which was expanded to the two composing netmasks, * rule #1: 192.168.1.0/24, and rule #2: 192.168.2.0/31. * * This function fills @left and @right with the byte values of the leftmost * and rightmost bucket indices for the lowest and highest rule indices, * respectively. If @first_rule is 1 and @rule_count is 2, we obtain, in * nibbles: * left: < 12, 0, 10, 8, 0, 1, 0, 0 > * right: < 12, 0, 10, 8, 0, 2, 2, 1 > * corresponding to bytes: * left: < 192, 168, 1, 0 > * right: < 192, 168, 2, 1 > * with mask length irrelevant here, unused on return, as the range is already * defined by its start and end points. The mask length is relevant for a single * ranged entry instead: if @first_rule is 1 and @rule_count is 1, we ignore * rule 2 above: @left becomes < 192, 168, 1, 0 >, @right becomes * < 192, 168, 1, 255 >, and the mask length, calculated from the distances * between leftmost and rightmost bucket indices for each group, would be 24. * * Return: mask length, in bits. */ static int pipapo_get_boundaries(struct nft_pipapo_field *f, int first_rule, int rule_count, u8 *left, u8 *right) { int g, mask_len = 0, bit_offset = 0; u8 *l = left, *r = right; for (g = 0; g < f->groups; g++) { int b, x0, x1; x0 = -1; x1 = -1; for (b = 0; b < NFT_PIPAPO_BUCKETS(f->bb); b++) { unsigned long *pos; pos = NFT_PIPAPO_LT_ALIGN(f->lt) + (g * NFT_PIPAPO_BUCKETS(f->bb) + b) * f->bsize; if (test_bit(first_rule, pos) && x0 == -1) x0 = b; if (test_bit(first_rule + rule_count - 1, pos)) x1 = b; } *l |= x0 << (BITS_PER_BYTE - f->bb - bit_offset); *r |= x1 << (BITS_PER_BYTE - f->bb - bit_offset); bit_offset += f->bb; if (bit_offset >= BITS_PER_BYTE) { bit_offset %= BITS_PER_BYTE; l++; r++; } if (x1 - x0 == 0) mask_len += 4; else if (x1 - x0 == 1) mask_len += 3; else if (x1 - x0 == 3) mask_len += 2; else if (x1 - x0 == 7) mask_len += 1; } return mask_len; } /** * pipapo_match_field() - Match rules against byte ranges * @f: Field including the lookup table * @first_rule: First of associated rules originating from same entry * @rule_count: Amount of associated rules * @start: Start of range to be matched * @end: End of range to be matched * * Return: true on match, false otherwise. */ static bool pipapo_match_field(struct nft_pipapo_field *f, int first_rule, int rule_count, const u8 *start, const u8 *end) { u8 right[NFT_PIPAPO_MAX_BYTES] = { 0 }; u8 left[NFT_PIPAPO_MAX_BYTES] = { 0 }; pipapo_get_boundaries(f, first_rule, rule_count, left, right); return !memcmp(start, left, f->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f)) && !memcmp(end, right, f->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f)); } /** * nft_pipapo_remove() - Remove element given key, commit * @net: Network namespace * @set: nftables API set representation * @elem_priv: nftables API element representation containing key data * * Similarly to nft_pipapo_activate(), this is used as commit operation by the * API, but it's called once per element in the pending transaction, so we can't * implement this as a single commit operation. Closest we can get is to remove * the matched element here, if any, and commit the updated matching data. */ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m = priv->clone; unsigned int rules_f0, first_rule = 0; struct nft_pipapo_elem *e; const u8 *data; e = nft_elem_priv_cast(elem_priv); data = (const u8 *)nft_set_ext_key(&e->ext); while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; const u8 *match_start, *match_end; struct nft_pipapo_field *f; int i, start, rules_fx; match_start = data; if (nft_set_ext_exists(&e->ext, NFT_SET_EXT_KEY_END)) match_end = (const u8 *)nft_set_ext_key_end(&e->ext)->data; else match_end = data; start = first_rule; rules_fx = rules_f0; nft_pipapo_for_each_field(f, i, m) { bool last = i == m->field_count - 1; if (!pipapo_match_field(f, start, rules_fx, match_start, match_end)) break; rulemap[i].to = start; rulemap[i].n = rules_fx; rules_fx = f->mt[start].n; start = f->mt[start].to; match_start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); match_end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); if (last && f->mt[rulemap[i].to].e == e) { pipapo_drop(m, rulemap); return; } } first_rule += rules_f0; } WARN_ON_ONCE(1); /* elem_priv not found */ } /** * nft_pipapo_do_walk() - Walk over elements in m * @ctx: nftables API context * @set: nftables API set representation * @m: matching data pointing to key mapping array * @iter: Iterator * * As elements are referenced in the mapping array for the last field, directly * scan that array: there's no need to follow rule mappings from the first * field. @m is protected either by RCU read lock or by transaction mutex. */ static void nft_pipapo_do_walk(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_pipapo_match *m, struct nft_set_iter *iter) { const struct nft_pipapo_field *f; unsigned int i, r; for (i = 0, f = m->f; i < m->field_count - 1; i++, f++) ; for (r = 0; r < f->rules; r++) { struct nft_pipapo_elem *e; if (r < f->rules - 1 && f->mt[r + 1].e == f->mt[r].e) continue; if (iter->count < iter->skip) goto cont; e = f->mt[r].e; iter->err = iter->fn(ctx, set, iter, &e->priv); if (iter->err < 0) return; cont: iter->count++; } } /** * nft_pipapo_walk() - Walk over elements * @ctx: nftables API context * @set: nftables API set representation * @iter: Iterator * * Test if destructive action is needed or not, clone active backend if needed * and call the real function to work on the data. */ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter) { struct nft_pipapo *priv = nft_set_priv(set); const struct nft_pipapo_match *m; switch (iter->type) { case NFT_ITER_UPDATE: m = pipapo_maybe_clone(set); if (!m) { iter->err = -ENOMEM; return; } nft_pipapo_do_walk(ctx, set, m, iter); break; case NFT_ITER_READ: rcu_read_lock(); m = rcu_dereference(priv->match); nft_pipapo_do_walk(ctx, set, m, iter); rcu_read_unlock(); break; default: iter->err = -EINVAL; WARN_ON_ONCE(1); break; } } /** * nft_pipapo_privsize() - Return the size of private data for the set * @nla: netlink attributes, ignored as size doesn't depend on them * @desc: Set description, ignored as size doesn't depend on it * * Return: size of private data for this set implementation, in bytes */ static u64 nft_pipapo_privsize(const struct nlattr * const nla[], const struct nft_set_desc *desc) { return sizeof(struct nft_pipapo); } /** * nft_pipapo_estimate() - Set size, space and lookup complexity * @desc: Set description, element count and field description used * @features: Flags: NFT_SET_INTERVAL needs to be there * @est: Storage for estimation data * * Return: true if set description is compatible, false otherwise */ static bool nft_pipapo_estimate(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est) { if (!(features & NFT_SET_INTERVAL) || desc->field_count < NFT_PIPAPO_MIN_FIELDS) return false; est->size = pipapo_estimate_size(desc); if (!est->size) return false; est->lookup = NFT_SET_CLASS_O_LOG_N; est->space = NFT_SET_CLASS_O_N; return true; } /** * nft_pipapo_init() - Initialise data for a set instance * @set: nftables API set representation * @desc: Set description * @nla: netlink attributes * * Validate number and size of fields passed as NFTA_SET_DESC_CONCAT netlink * attributes, initialise internal set parameters, current instance of matching * data and a copy for subsequent insertions. * * Return: 0 on success, negative error code on failure. */ static int nft_pipapo_init(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const nla[]) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m; struct nft_pipapo_field *f; int err, i, field_count; BUILD_BUG_ON(offsetof(struct nft_pipapo_elem, priv) != 0); field_count = desc->field_count ? : 1; BUILD_BUG_ON(NFT_PIPAPO_MAX_FIELDS > 255); BUILD_BUG_ON(NFT_PIPAPO_MAX_FIELDS != NFT_REG32_COUNT); if (field_count > NFT_PIPAPO_MAX_FIELDS) return -EINVAL; m = kmalloc(struct_size(m, f, field_count), GFP_KERNEL); if (!m) return -ENOMEM; m->field_count = field_count; m->bsize_max = 0; m->scratch = alloc_percpu(struct nft_pipapo_scratch *); if (!m->scratch) { err = -ENOMEM; goto out_scratch; } for_each_possible_cpu(i) *per_cpu_ptr(m->scratch, i) = NULL; rcu_head_init(&m->rcu); nft_pipapo_for_each_field(f, i, m) { unsigned int len = desc->field_len[i] ? : set->klen; /* f->groups is u8 */ BUILD_BUG_ON((NFT_PIPAPO_MAX_BYTES * BITS_PER_BYTE / NFT_PIPAPO_GROUP_BITS_LARGE_SET) >= 256); f->bb = NFT_PIPAPO_GROUP_BITS_INIT; f->groups = len * NFT_PIPAPO_GROUPS_PER_BYTE(f); priv->width += round_up(len, sizeof(u32)); f->bsize = 0; f->rules = 0; f->rules_alloc = 0; f->lt = NULL; f->mt = NULL; } rcu_assign_pointer(priv->match, m); return 0; out_scratch: kfree(m); return err; } /** * nft_set_pipapo_match_destroy() - Destroy elements from key mapping array * @ctx: context * @set: nftables API set representation * @m: matching data pointing to key mapping array */ static void nft_set_pipapo_match_destroy(const struct nft_ctx *ctx, const struct nft_set *set, struct nft_pipapo_match *m) { struct nft_pipapo_field *f; unsigned int i, r; for (i = 0, f = m->f; i < m->field_count - 1; i++, f++) ; for (r = 0; r < f->rules; r++) { struct nft_pipapo_elem *e; if (r < f->rules - 1 && f->mt[r + 1].e == f->mt[r].e) continue; e = f->mt[r].e; nf_tables_set_elem_destroy(ctx, set, &e->priv); } } /** * nft_pipapo_destroy() - Free private data for set and all committed elements * @ctx: context * @set: nftables API set representation */ static void nft_pipapo_destroy(const struct nft_ctx *ctx, const struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m; m = rcu_dereference_protected(priv->match, true); if (priv->clone) { nft_set_pipapo_match_destroy(ctx, set, priv->clone); pipapo_free_match(priv->clone); priv->clone = NULL; } else { nft_set_pipapo_match_destroy(ctx, set, m); } pipapo_free_match(m); } /** * nft_pipapo_gc_init() - Initialise garbage collection * @set: nftables API set representation * * Instead of actually setting up a periodic work for garbage collection, as * this operation requires a swap of matching data with the working copy, we'll * do that opportunistically with other commit operations if the interval is * elapsed, so we just need to set the current jiffies timestamp here. */ static void nft_pipapo_gc_init(const struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); priv->last_gc = jiffies; } const struct nft_set_type nft_set_pipapo_type = { .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, .ops = { .lookup = nft_pipapo_lookup, .insert = nft_pipapo_insert, .activate = nft_pipapo_activate, .deactivate = nft_pipapo_deactivate, .flush = nft_pipapo_flush, .remove = nft_pipapo_remove, .walk = nft_pipapo_walk, .get = nft_pipapo_get, .privsize = nft_pipapo_privsize, .estimate = nft_pipapo_estimate, .init = nft_pipapo_init, .destroy = nft_pipapo_destroy, .gc_init = nft_pipapo_gc_init, .commit = nft_pipapo_commit, .abort = nft_pipapo_abort, .elemsize = offsetof(struct nft_pipapo_elem, ext), }, }; #if defined(CONFIG_X86_64) && !defined(CONFIG_UML) const struct nft_set_type nft_set_pipapo_avx2_type = { .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, .ops = { .lookup = nft_pipapo_avx2_lookup, .insert = nft_pipapo_insert, .activate = nft_pipapo_activate, .deactivate = nft_pipapo_deactivate, .flush = nft_pipapo_flush, .remove = nft_pipapo_remove, .walk = nft_pipapo_walk, .get = nft_pipapo_get, .privsize = nft_pipapo_privsize, .estimate = nft_pipapo_avx2_estimate, .init = nft_pipapo_init, .destroy = nft_pipapo_destroy, .gc_init = nft_pipapo_gc_init, .commit = nft_pipapo_commit, .abort = nft_pipapo_abort, .elemsize = offsetof(struct nft_pipapo_elem, ext), }, }; #endif |
| 1 1 1 3 3 5 1 3 2 3 6 1 1 3 5 1 5 1 6 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Adiantum length-preserving encryption mode * * Copyright 2018 Google LLC */ /* * Adiantum is a tweakable, length-preserving encryption mode designed for fast * and secure disk encryption, especially on CPUs without dedicated crypto * instructions. Adiantum encrypts each sector using the XChaCha12 stream * cipher, two passes of an ε-almost-∆-universal (ε-∆U) hash function based on * NH and Poly1305, and an invocation of the AES-256 block cipher on a single * 16-byte block. See the paper for details: * * Adiantum: length-preserving encryption for entry-level processors * (https://eprint.iacr.org/2018/720.pdf) * * For flexibility, this implementation also allows other ciphers: * * - Stream cipher: XChaCha12 or XChaCha20 * - Block cipher: any with a 128-bit block size and 256-bit key * * This implementation doesn't currently allow other ε-∆U hash functions, i.e. * HPolyC is not supported. This is because Adiantum is ~20% faster than HPolyC * but still provably as secure, and also the ε-∆U hash function of HBSH is * formally defined to take two inputs (tweak, message) which makes it difficult * to wrap with the crypto_shash API. Rather, some details need to be handled * here. Nevertheless, if needed in the future, support for other ε-∆U hash * functions could be added here. */ #include <crypto/b128ops.h> #include <crypto/chacha.h> #include <crypto/internal/cipher.h> #include <crypto/internal/hash.h> #include <crypto/internal/poly1305.h> #include <crypto/internal/skcipher.h> #include <crypto/nhpoly1305.h> #include <crypto/scatterwalk.h> #include <linux/module.h> /* * Size of right-hand part of input data, in bytes; also the size of the block * cipher's block size and the hash function's output. */ #define BLOCKCIPHER_BLOCK_SIZE 16 /* Size of the block cipher key (K_E) in bytes */ #define BLOCKCIPHER_KEY_SIZE 32 /* Size of the hash key (K_H) in bytes */ #define HASH_KEY_SIZE (POLY1305_BLOCK_SIZE + NHPOLY1305_KEY_SIZE) /* * The specification allows variable-length tweaks, but Linux's crypto API * currently only allows algorithms to support a single length. The "natural" * tweak length for Adiantum is 16, since that fits into one Poly1305 block for * the best performance. But longer tweaks are useful for fscrypt, to avoid * needing to derive per-file keys. So instead we use two blocks, or 32 bytes. */ #define TWEAK_SIZE 32 struct adiantum_instance_ctx { struct crypto_skcipher_spawn streamcipher_spawn; struct crypto_cipher_spawn blockcipher_spawn; struct crypto_shash_spawn hash_spawn; }; struct adiantum_tfm_ctx { struct crypto_skcipher *streamcipher; struct crypto_cipher *blockcipher; struct crypto_shash *hash; struct poly1305_core_key header_hash_key; }; struct adiantum_request_ctx { /* * Buffer for right-hand part of data, i.e. * * P_L => P_M => C_M => C_R when encrypting, or * C_R => C_M => P_M => P_L when decrypting. * * Also used to build the IV for the stream cipher. */ union { u8 bytes[XCHACHA_IV_SIZE]; __le32 words[XCHACHA_IV_SIZE / sizeof(__le32)]; le128 bignum; /* interpret as element of Z/(2^{128}Z) */ } rbuf; bool enc; /* true if encrypting, false if decrypting */ /* * The result of the Poly1305 ε-∆U hash function applied to * (bulk length, tweak) */ le128 header_hash; /* Sub-requests, must be last */ union { struct shash_desc hash_desc; struct skcipher_request streamcipher_req; } u; }; /* * Given the XChaCha stream key K_S, derive the block cipher key K_E and the * hash key K_H as follows: * * K_E || K_H || ... = XChaCha(key=K_S, nonce=1||0^191) * * Note that this denotes using bits from the XChaCha keystream, which here we * get indirectly by encrypting a buffer containing all 0's. */ static int adiantum_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); struct { u8 iv[XCHACHA_IV_SIZE]; u8 derived_keys[BLOCKCIPHER_KEY_SIZE + HASH_KEY_SIZE]; struct scatterlist sg; struct crypto_wait wait; struct skcipher_request req; /* must be last */ } *data; u8 *keyp; int err; /* Set the stream cipher key (K_S) */ crypto_skcipher_clear_flags(tctx->streamcipher, CRYPTO_TFM_REQ_MASK); crypto_skcipher_set_flags(tctx->streamcipher, crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_REQ_MASK); err = crypto_skcipher_setkey(tctx->streamcipher, key, keylen); if (err) return err; /* Derive the subkeys */ data = kzalloc(sizeof(*data) + crypto_skcipher_reqsize(tctx->streamcipher), GFP_KERNEL); if (!data) return -ENOMEM; data->iv[0] = 1; sg_init_one(&data->sg, data->derived_keys, sizeof(data->derived_keys)); crypto_init_wait(&data->wait); skcipher_request_set_tfm(&data->req, tctx->streamcipher); skcipher_request_set_callback(&data->req, CRYPTO_TFM_REQ_MAY_SLEEP | CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &data->wait); skcipher_request_set_crypt(&data->req, &data->sg, &data->sg, sizeof(data->derived_keys), data->iv); err = crypto_wait_req(crypto_skcipher_encrypt(&data->req), &data->wait); if (err) goto out; keyp = data->derived_keys; /* Set the block cipher key (K_E) */ crypto_cipher_clear_flags(tctx->blockcipher, CRYPTO_TFM_REQ_MASK); crypto_cipher_set_flags(tctx->blockcipher, crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_REQ_MASK); err = crypto_cipher_setkey(tctx->blockcipher, keyp, BLOCKCIPHER_KEY_SIZE); if (err) goto out; keyp += BLOCKCIPHER_KEY_SIZE; /* Set the hash key (K_H) */ poly1305_core_setkey(&tctx->header_hash_key, keyp); keyp += POLY1305_BLOCK_SIZE; crypto_shash_clear_flags(tctx->hash, CRYPTO_TFM_REQ_MASK); crypto_shash_set_flags(tctx->hash, crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_REQ_MASK); err = crypto_shash_setkey(tctx->hash, keyp, NHPOLY1305_KEY_SIZE); keyp += NHPOLY1305_KEY_SIZE; WARN_ON(keyp != &data->derived_keys[ARRAY_SIZE(data->derived_keys)]); out: kfree_sensitive(data); return err; } /* Addition in Z/(2^{128}Z) */ static inline void le128_add(le128 *r, const le128 *v1, const le128 *v2) { u64 x = le64_to_cpu(v1->b); u64 y = le64_to_cpu(v2->b); r->b = cpu_to_le64(x + y); r->a = cpu_to_le64(le64_to_cpu(v1->a) + le64_to_cpu(v2->a) + (x + y < x)); } /* Subtraction in Z/(2^{128}Z) */ static inline void le128_sub(le128 *r, const le128 *v1, const le128 *v2) { u64 x = le64_to_cpu(v1->b); u64 y = le64_to_cpu(v2->b); r->b = cpu_to_le64(x - y); r->a = cpu_to_le64(le64_to_cpu(v1->a) - le64_to_cpu(v2->a) - (x - y > x)); } /* * Apply the Poly1305 ε-∆U hash function to (bulk length, tweak) and save the * result to rctx->header_hash. This is the calculation * * H_T ← Poly1305_{K_T}(bin_{128}(|L|) || T) * * from the procedure in section 6.4 of the Adiantum paper. The resulting value * is reused in both the first and second hash steps. Specifically, it's added * to the result of an independently keyed ε-∆U hash function (for equal length * inputs only) taken over the left-hand part (the "bulk") of the message, to * give the overall Adiantum hash of the (tweak, left-hand part) pair. */ static void adiantum_hash_header(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); const struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); struct adiantum_request_ctx *rctx = skcipher_request_ctx(req); const unsigned int bulk_len = req->cryptlen - BLOCKCIPHER_BLOCK_SIZE; struct { __le64 message_bits; __le64 padding; } header = { .message_bits = cpu_to_le64((u64)bulk_len * 8) }; struct poly1305_state state; poly1305_core_init(&state); BUILD_BUG_ON(sizeof(header) % POLY1305_BLOCK_SIZE != 0); poly1305_core_blocks(&state, &tctx->header_hash_key, &header, sizeof(header) / POLY1305_BLOCK_SIZE, 1); BUILD_BUG_ON(TWEAK_SIZE % POLY1305_BLOCK_SIZE != 0); poly1305_core_blocks(&state, &tctx->header_hash_key, req->iv, TWEAK_SIZE / POLY1305_BLOCK_SIZE, 1); poly1305_core_emit(&state, NULL, &rctx->header_hash); } /* Hash the left-hand part (the "bulk") of the message using NHPoly1305 */ static int adiantum_hash_message(struct skcipher_request *req, struct scatterlist *sgl, unsigned int nents, le128 *digest) { struct adiantum_request_ctx *rctx = skcipher_request_ctx(req); const unsigned int bulk_len = req->cryptlen - BLOCKCIPHER_BLOCK_SIZE; struct shash_desc *hash_desc = &rctx->u.hash_desc; struct sg_mapping_iter miter; unsigned int i, n; int err; err = crypto_shash_init(hash_desc); if (err) return err; sg_miter_start(&miter, sgl, nents, SG_MITER_FROM_SG | SG_MITER_ATOMIC); for (i = 0; i < bulk_len; i += n) { sg_miter_next(&miter); n = min_t(unsigned int, miter.length, bulk_len - i); err = crypto_shash_update(hash_desc, miter.addr, n); if (err) break; } sg_miter_stop(&miter); if (err) return err; return crypto_shash_final(hash_desc, (u8 *)digest); } /* Continue Adiantum encryption/decryption after the stream cipher step */ static int adiantum_finish(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); const struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); struct adiantum_request_ctx *rctx = skcipher_request_ctx(req); const unsigned int bulk_len = req->cryptlen - BLOCKCIPHER_BLOCK_SIZE; struct scatterlist *dst = req->dst; const unsigned int dst_nents = sg_nents(dst); le128 digest; int err; /* If decrypting, decrypt C_M with the block cipher to get P_M */ if (!rctx->enc) crypto_cipher_decrypt_one(tctx->blockcipher, rctx->rbuf.bytes, rctx->rbuf.bytes); /* * Second hash step * enc: C_R = C_M - H_{K_H}(T, C_L) * dec: P_R = P_M - H_{K_H}(T, P_L) */ rctx->u.hash_desc.tfm = tctx->hash; le128_sub(&rctx->rbuf.bignum, &rctx->rbuf.bignum, &rctx->header_hash); if (dst_nents == 1 && dst->offset + req->cryptlen <= PAGE_SIZE) { /* Fast path for single-page destination */ struct page *page = sg_page(dst); void *virt = kmap_local_page(page) + dst->offset; err = crypto_shash_digest(&rctx->u.hash_desc, virt, bulk_len, (u8 *)&digest); if (err) { kunmap_local(virt); return err; } le128_sub(&rctx->rbuf.bignum, &rctx->rbuf.bignum, &digest); memcpy(virt + bulk_len, &rctx->rbuf.bignum, sizeof(le128)); flush_dcache_page(page); kunmap_local(virt); } else { /* Slow path that works for any destination scatterlist */ err = adiantum_hash_message(req, dst, dst_nents, &digest); if (err) return err; le128_sub(&rctx->rbuf.bignum, &rctx->rbuf.bignum, &digest); scatterwalk_map_and_copy(&rctx->rbuf.bignum, dst, bulk_len, sizeof(le128), 1); } return 0; } static void adiantum_streamcipher_done(void *data, int err) { struct skcipher_request *req = data; if (!err) err = adiantum_finish(req); skcipher_request_complete(req, err); } static int adiantum_crypt(struct skcipher_request *req, bool enc) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); const struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); struct adiantum_request_ctx *rctx = skcipher_request_ctx(req); const unsigned int bulk_len = req->cryptlen - BLOCKCIPHER_BLOCK_SIZE; struct scatterlist *src = req->src; const unsigned int src_nents = sg_nents(src); unsigned int stream_len; le128 digest; int err; if (req->cryptlen < BLOCKCIPHER_BLOCK_SIZE) return -EINVAL; rctx->enc = enc; /* * First hash step * enc: P_M = P_R + H_{K_H}(T, P_L) * dec: C_M = C_R + H_{K_H}(T, C_L) */ adiantum_hash_header(req); rctx->u.hash_desc.tfm = tctx->hash; if (src_nents == 1 && src->offset + req->cryptlen <= PAGE_SIZE) { /* Fast path for single-page source */ void *virt = kmap_local_page(sg_page(src)) + src->offset; err = crypto_shash_digest(&rctx->u.hash_desc, virt, bulk_len, (u8 *)&digest); memcpy(&rctx->rbuf.bignum, virt + bulk_len, sizeof(le128)); kunmap_local(virt); } else { /* Slow path that works for any source scatterlist */ err = adiantum_hash_message(req, src, src_nents, &digest); scatterwalk_map_and_copy(&rctx->rbuf.bignum, src, bulk_len, sizeof(le128), 0); } if (err) return err; le128_add(&rctx->rbuf.bignum, &rctx->rbuf.bignum, &rctx->header_hash); le128_add(&rctx->rbuf.bignum, &rctx->rbuf.bignum, &digest); /* If encrypting, encrypt P_M with the block cipher to get C_M */ if (enc) crypto_cipher_encrypt_one(tctx->blockcipher, rctx->rbuf.bytes, rctx->rbuf.bytes); /* Initialize the rest of the XChaCha IV (first part is C_M) */ BUILD_BUG_ON(BLOCKCIPHER_BLOCK_SIZE != 16); BUILD_BUG_ON(XCHACHA_IV_SIZE != 32); /* nonce || stream position */ rctx->rbuf.words[4] = cpu_to_le32(1); rctx->rbuf.words[5] = 0; rctx->rbuf.words[6] = 0; rctx->rbuf.words[7] = 0; /* * XChaCha needs to be done on all the data except the last 16 bytes; * for disk encryption that usually means 4080 or 496 bytes. But ChaCha * implementations tend to be most efficient when passed a whole number * of 64-byte ChaCha blocks, or sometimes even a multiple of 256 bytes. * And here it doesn't matter whether the last 16 bytes are written to, * as the second hash step will overwrite them. Thus, round the XChaCha * length up to the next 64-byte boundary if possible. */ stream_len = bulk_len; if (round_up(stream_len, CHACHA_BLOCK_SIZE) <= req->cryptlen) stream_len = round_up(stream_len, CHACHA_BLOCK_SIZE); skcipher_request_set_tfm(&rctx->u.streamcipher_req, tctx->streamcipher); skcipher_request_set_crypt(&rctx->u.streamcipher_req, req->src, req->dst, stream_len, &rctx->rbuf); skcipher_request_set_callback(&rctx->u.streamcipher_req, req->base.flags, adiantum_streamcipher_done, req); return crypto_skcipher_encrypt(&rctx->u.streamcipher_req) ?: adiantum_finish(req); } static int adiantum_encrypt(struct skcipher_request *req) { return adiantum_crypt(req, true); } static int adiantum_decrypt(struct skcipher_request *req) { return adiantum_crypt(req, false); } static int adiantum_init_tfm(struct crypto_skcipher *tfm) { struct skcipher_instance *inst = skcipher_alg_instance(tfm); struct adiantum_instance_ctx *ictx = skcipher_instance_ctx(inst); struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); struct crypto_skcipher *streamcipher; struct crypto_cipher *blockcipher; struct crypto_shash *hash; unsigned int subreq_size; int err; streamcipher = crypto_spawn_skcipher(&ictx->streamcipher_spawn); if (IS_ERR(streamcipher)) return PTR_ERR(streamcipher); blockcipher = crypto_spawn_cipher(&ictx->blockcipher_spawn); if (IS_ERR(blockcipher)) { err = PTR_ERR(blockcipher); goto err_free_streamcipher; } hash = crypto_spawn_shash(&ictx->hash_spawn); if (IS_ERR(hash)) { err = PTR_ERR(hash); goto err_free_blockcipher; } tctx->streamcipher = streamcipher; tctx->blockcipher = blockcipher; tctx->hash = hash; BUILD_BUG_ON(offsetofend(struct adiantum_request_ctx, u) != sizeof(struct adiantum_request_ctx)); subreq_size = max(sizeof_field(struct adiantum_request_ctx, u.hash_desc) + crypto_shash_descsize(hash), sizeof_field(struct adiantum_request_ctx, u.streamcipher_req) + crypto_skcipher_reqsize(streamcipher)); crypto_skcipher_set_reqsize(tfm, offsetof(struct adiantum_request_ctx, u) + subreq_size); return 0; err_free_blockcipher: crypto_free_cipher(blockcipher); err_free_streamcipher: crypto_free_skcipher(streamcipher); return err; } static void adiantum_exit_tfm(struct crypto_skcipher *tfm) { struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); crypto_free_skcipher(tctx->streamcipher); crypto_free_cipher(tctx->blockcipher); crypto_free_shash(tctx->hash); } static void adiantum_free_instance(struct skcipher_instance *inst) { struct adiantum_instance_ctx *ictx = skcipher_instance_ctx(inst); crypto_drop_skcipher(&ictx->streamcipher_spawn); crypto_drop_cipher(&ictx->blockcipher_spawn); crypto_drop_shash(&ictx->hash_spawn); kfree(inst); } /* * Check for a supported set of inner algorithms. * See the comment at the beginning of this file. */ static bool adiantum_supported_algorithms(struct skcipher_alg_common *streamcipher_alg, struct crypto_alg *blockcipher_alg, struct shash_alg *hash_alg) { if (strcmp(streamcipher_alg->base.cra_name, "xchacha12") != 0 && strcmp(streamcipher_alg->base.cra_name, "xchacha20") != 0) return false; if (blockcipher_alg->cra_cipher.cia_min_keysize > BLOCKCIPHER_KEY_SIZE || blockcipher_alg->cra_cipher.cia_max_keysize < BLOCKCIPHER_KEY_SIZE) return false; if (blockcipher_alg->cra_blocksize != BLOCKCIPHER_BLOCK_SIZE) return false; if (strcmp(hash_alg->base.cra_name, "nhpoly1305") != 0) return false; return true; } static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb) { u32 mask; const char *nhpoly1305_name; struct skcipher_instance *inst; struct adiantum_instance_ctx *ictx; struct skcipher_alg_common *streamcipher_alg; struct crypto_alg *blockcipher_alg; struct shash_alg *hash_alg; int err; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SKCIPHER, &mask); if (err) return err; inst = kzalloc(sizeof(*inst) + sizeof(*ictx), GFP_KERNEL); if (!inst) return -ENOMEM; ictx = skcipher_instance_ctx(inst); /* Stream cipher, e.g. "xchacha12" */ err = crypto_grab_skcipher(&ictx->streamcipher_spawn, skcipher_crypto_instance(inst), crypto_attr_alg_name(tb[1]), 0, mask); if (err) goto err_free_inst; streamcipher_alg = crypto_spawn_skcipher_alg_common(&ictx->streamcipher_spawn); /* Block cipher, e.g. "aes" */ err = crypto_grab_cipher(&ictx->blockcipher_spawn, skcipher_crypto_instance(inst), crypto_attr_alg_name(tb[2]), 0, mask); if (err) goto err_free_inst; blockcipher_alg = crypto_spawn_cipher_alg(&ictx->blockcipher_spawn); /* NHPoly1305 ε-∆U hash function */ nhpoly1305_name = crypto_attr_alg_name(tb[3]); if (nhpoly1305_name == ERR_PTR(-ENOENT)) nhpoly1305_name = "nhpoly1305"; err = crypto_grab_shash(&ictx->hash_spawn, skcipher_crypto_instance(inst), nhpoly1305_name, 0, mask); if (err) goto err_free_inst; hash_alg = crypto_spawn_shash_alg(&ictx->hash_spawn); /* Check the set of algorithms */ if (!adiantum_supported_algorithms(streamcipher_alg, blockcipher_alg, hash_alg)) { pr_warn("Unsupported Adiantum instantiation: (%s,%s,%s)\n", streamcipher_alg->base.cra_name, blockcipher_alg->cra_name, hash_alg->base.cra_name); err = -EINVAL; goto err_free_inst; } /* Instance fields */ err = -ENAMETOOLONG; if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, "adiantum(%s,%s)", streamcipher_alg->base.cra_name, blockcipher_alg->cra_name) >= CRYPTO_MAX_ALG_NAME) goto err_free_inst; if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "adiantum(%s,%s,%s)", streamcipher_alg->base.cra_driver_name, blockcipher_alg->cra_driver_name, hash_alg->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME) goto err_free_inst; inst->alg.base.cra_blocksize = BLOCKCIPHER_BLOCK_SIZE; inst->alg.base.cra_ctxsize = sizeof(struct adiantum_tfm_ctx); inst->alg.base.cra_alignmask = streamcipher_alg->base.cra_alignmask; /* * The block cipher is only invoked once per message, so for long * messages (e.g. sectors for disk encryption) its performance doesn't * matter as much as that of the stream cipher and hash function. Thus, * weigh the block cipher's ->cra_priority less. */ inst->alg.base.cra_priority = (4 * streamcipher_alg->base.cra_priority + 2 * hash_alg->base.cra_priority + blockcipher_alg->cra_priority) / 7; inst->alg.setkey = adiantum_setkey; inst->alg.encrypt = adiantum_encrypt; inst->alg.decrypt = adiantum_decrypt; inst->alg.init = adiantum_init_tfm; inst->alg.exit = adiantum_exit_tfm; inst->alg.min_keysize = streamcipher_alg->min_keysize; inst->alg.max_keysize = streamcipher_alg->max_keysize; inst->alg.ivsize = TWEAK_SIZE; inst->free = adiantum_free_instance; err = skcipher_register_instance(tmpl, inst); if (err) { err_free_inst: adiantum_free_instance(inst); } return err; } /* adiantum(streamcipher_name, blockcipher_name [, nhpoly1305_name]) */ static struct crypto_template adiantum_tmpl = { .name = "adiantum", .create = adiantum_create, .module = THIS_MODULE, }; static int __init adiantum_module_init(void) { return crypto_register_template(&adiantum_tmpl); } static void __exit adiantum_module_exit(void) { crypto_unregister_template(&adiantum_tmpl); } subsys_initcall(adiantum_module_init); module_exit(adiantum_module_exit); MODULE_DESCRIPTION("Adiantum length-preserving encryption mode"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>"); MODULE_ALIAS_CRYPTO("adiantum"); MODULE_IMPORT_NS("CRYPTO_INTERNAL"); |
| 84 85 8 7 69 52 5 2 3 32 8 6 6 38 38 1 1 6 6 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Multipath TCP * * Copyright (c) 2019, Tessares SA. */ #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <net/net_namespace.h> #include <net/netns/generic.h> #include "protocol.h" #include "mib.h" #define MPTCP_SYSCTL_PATH "net/mptcp" static int mptcp_pernet_id; #ifdef CONFIG_SYSCTL static int mptcp_pm_type_max = __MPTCP_PM_TYPE_MAX; #endif struct mptcp_pernet { #ifdef CONFIG_SYSCTL struct ctl_table_header *ctl_table_hdr; #endif unsigned int add_addr_timeout; unsigned int blackhole_timeout; unsigned int close_timeout; unsigned int stale_loss_cnt; atomic_t active_disable_times; unsigned long active_disable_stamp; u8 mptcp_enabled; u8 checksum_enabled; u8 allow_join_initial_addr_port; u8 pm_type; char scheduler[MPTCP_SCHED_NAME_MAX]; }; static struct mptcp_pernet *mptcp_get_pernet(const struct net *net) { return net_generic(net, mptcp_pernet_id); } int mptcp_is_enabled(const struct net *net) { return mptcp_get_pernet(net)->mptcp_enabled; } unsigned int mptcp_get_add_addr_timeout(const struct net *net) { return mptcp_get_pernet(net)->add_addr_timeout; } int mptcp_is_checksum_enabled(const struct net *net) { return mptcp_get_pernet(net)->checksum_enabled; } int mptcp_allow_join_id0(const struct net *net) { return mptcp_get_pernet(net)->allow_join_initial_addr_port; } unsigned int mptcp_stale_loss_cnt(const struct net *net) { return mptcp_get_pernet(net)->stale_loss_cnt; } unsigned int mptcp_close_timeout(const struct sock *sk) { if (sock_flag(sk, SOCK_DEAD)) return TCP_TIMEWAIT_LEN; return mptcp_get_pernet(sock_net(sk))->close_timeout; } int mptcp_get_pm_type(const struct net *net) { return mptcp_get_pernet(net)->pm_type; } const char *mptcp_get_scheduler(const struct net *net) { return mptcp_get_pernet(net)->scheduler; } static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) { pernet->mptcp_enabled = 1; pernet->add_addr_timeout = TCP_RTO_MAX; pernet->blackhole_timeout = 3600; atomic_set(&pernet->active_disable_times, 0); pernet->close_timeout = TCP_TIMEWAIT_LEN; pernet->checksum_enabled = 0; pernet->allow_join_initial_addr_port = 1; pernet->stale_loss_cnt = 4; pernet->pm_type = MPTCP_PM_TYPE_KERNEL; strscpy(pernet->scheduler, "default", sizeof(pernet->scheduler)); } #ifdef CONFIG_SYSCTL static int mptcp_set_scheduler(char *scheduler, const char *name) { struct mptcp_sched_ops *sched; int ret = 0; rcu_read_lock(); sched = mptcp_sched_find(name); if (sched) strscpy(scheduler, name, MPTCP_SCHED_NAME_MAX); else ret = -ENOENT; rcu_read_unlock(); return ret; } static int proc_scheduler(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { char (*scheduler)[MPTCP_SCHED_NAME_MAX] = ctl->data; char val[MPTCP_SCHED_NAME_MAX]; struct ctl_table tbl = { .data = val, .maxlen = MPTCP_SCHED_NAME_MAX, }; int ret; strscpy(val, *scheduler, MPTCP_SCHED_NAME_MAX); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); if (write && ret == 0) ret = mptcp_set_scheduler(*scheduler, val); return ret; } static int proc_available_schedulers(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tbl = { .maxlen = MPTCP_SCHED_BUF_MAX, }; int ret; tbl.data = kmalloc(tbl.maxlen, GFP_USER); if (!tbl.data) return -ENOMEM; mptcp_get_available_schedulers(tbl.data, MPTCP_SCHED_BUF_MAX); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); kfree(tbl.data); return ret; } static int proc_blackhole_detect_timeout(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct mptcp_pernet *pernet = container_of(table->data, struct mptcp_pernet, blackhole_timeout); int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) atomic_set(&pernet->active_disable_times, 0); return ret; } static struct ctl_table mptcp_sysctl_table[] = { { .procname = "enabled", .maxlen = sizeof(u8), .mode = 0644, /* users with CAP_NET_ADMIN or root (not and) can change this * value, same as other sysctl or the 'net' tree. */ .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "add_addr_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "checksum_enabled", .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "allow_join_initial_addr_port", .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, { .procname = "stale_loss_cnt", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_douintvec_minmax, }, { .procname = "pm_type", .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &mptcp_pm_type_max }, { .procname = "scheduler", .maxlen = MPTCP_SCHED_NAME_MAX, .mode = 0644, .proc_handler = proc_scheduler, }, { .procname = "available_schedulers", .maxlen = MPTCP_SCHED_BUF_MAX, .mode = 0444, .proc_handler = proc_available_schedulers, }, { .procname = "close_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "blackhole_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_blackhole_detect_timeout, .extra1 = SYSCTL_ZERO, }, }; static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) { struct ctl_table_header *hdr; struct ctl_table *table; table = mptcp_sysctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(mptcp_sysctl_table), GFP_KERNEL); if (!table) goto err_alloc; } table[0].data = &pernet->mptcp_enabled; table[1].data = &pernet->add_addr_timeout; table[2].data = &pernet->checksum_enabled; table[3].data = &pernet->allow_join_initial_addr_port; table[4].data = &pernet->stale_loss_cnt; table[5].data = &pernet->pm_type; table[6].data = &pernet->scheduler; /* table[7] is for available_schedulers which is read-only info */ table[8].data = &pernet->close_timeout; table[9].data = &pernet->blackhole_timeout; hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table, ARRAY_SIZE(mptcp_sysctl_table)); if (!hdr) goto err_reg; pernet->ctl_table_hdr = hdr; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) { const struct ctl_table *table = pernet->ctl_table_hdr->ctl_table_arg; unregister_net_sysctl_table(pernet->ctl_table_hdr); kfree(table); } #else static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) { return 0; } static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) {} #endif /* CONFIG_SYSCTL */ /* The following code block is to deal with middle box issues with MPTCP, * similar to what is done with TFO. * The proposed solution is to disable active MPTCP globally when SYN+MPC are * dropped, while SYN without MPC aren't. In this case, active side MPTCP is * disabled globally for 1hr at first. Then if it happens again, it is disabled * for 2h, then 4h, 8h, ... * The timeout is reset back to 1hr when a successful active MPTCP connection is * fully established. */ /* Disable active MPTCP and record current jiffies and active_disable_times */ void mptcp_active_disable(struct sock *sk) { struct net *net = sock_net(sk); struct mptcp_pernet *pernet; pernet = mptcp_get_pernet(net); if (!READ_ONCE(pernet->blackhole_timeout)) return; /* Paired with READ_ONCE() in mptcp_active_should_disable() */ WRITE_ONCE(pernet->active_disable_stamp, jiffies); /* Paired with smp_rmb() in mptcp_active_should_disable(). * We want pernet->active_disable_stamp to be updated first. */ smp_mb__before_atomic(); atomic_inc(&pernet->active_disable_times); MPTCP_INC_STATS(net, MPTCP_MIB_BLACKHOLE); } /* Calculate timeout for MPTCP active disable * Return true if we are still in the active MPTCP disable period * Return false if timeout already expired and we should use active MPTCP */ bool mptcp_active_should_disable(struct sock *ssk) { struct net *net = sock_net(ssk); unsigned int blackhole_timeout; struct mptcp_pernet *pernet; unsigned long timeout; int disable_times; int multiplier; pernet = mptcp_get_pernet(net); blackhole_timeout = READ_ONCE(pernet->blackhole_timeout); if (!blackhole_timeout) return false; disable_times = atomic_read(&pernet->active_disable_times); if (!disable_times) return false; /* Paired with smp_mb__before_atomic() in mptcp_active_disable() */ smp_rmb(); /* Limit timeout to max: 2^6 * initial timeout */ multiplier = 1 << min(disable_times - 1, 6); /* Paired with the WRITE_ONCE() in mptcp_active_disable(). */ timeout = READ_ONCE(pernet->active_disable_stamp) + multiplier * blackhole_timeout * HZ; return time_before(jiffies, timeout); } /* Enable active MPTCP and reset active_disable_times if needed */ void mptcp_active_enable(struct sock *sk) { struct mptcp_pernet *pernet = mptcp_get_pernet(sock_net(sk)); if (atomic_read(&pernet->active_disable_times)) { struct dst_entry *dst = sk_dst_get(sk); if (dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK)) atomic_set(&pernet->active_disable_times, 0); } } /* Check the number of retransmissions, and fallback to TCP if needed */ void mptcp_active_detect_blackhole(struct sock *ssk, bool expired) { struct mptcp_subflow_context *subflow; u32 timeouts; if (!sk_is_mptcp(ssk)) return; timeouts = inet_csk(ssk)->icsk_retransmits; subflow = mptcp_subflow_ctx(ssk); if (subflow->request_mptcp && ssk->sk_state == TCP_SYN_SENT) { if (timeouts == 2 || (timeouts < 2 && expired)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEACTIVEDROP); subflow->mpc_drop = 1; mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow); } else { subflow->mpc_drop = 0; } } } static int __net_init mptcp_net_init(struct net *net) { struct mptcp_pernet *pernet = mptcp_get_pernet(net); mptcp_pernet_set_defaults(pernet); return mptcp_pernet_new_table(net, pernet); } /* Note: the callback will only be called per extra netns */ static void __net_exit mptcp_net_exit(struct net *net) { struct mptcp_pernet *pernet = mptcp_get_pernet(net); mptcp_pernet_del_table(pernet); } static struct pernet_operations mptcp_pernet_ops = { .init = mptcp_net_init, .exit = mptcp_net_exit, .id = &mptcp_pernet_id, .size = sizeof(struct mptcp_pernet), }; void __init mptcp_init(void) { mptcp_join_cookie_init(); mptcp_proto_init(); if (register_pernet_subsys(&mptcp_pernet_ops) < 0) panic("Failed to register MPTCP pernet subsystem.\n"); } #if IS_ENABLED(CONFIG_MPTCP_IPV6) int __init mptcpv6_init(void) { int err; err = mptcp_proto_v6_init(); return err; } #endif |
| 108 10 1681 816 214 545 202 1674 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. NET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the Ethernet handlers. * * Version: @(#)eth.h 1.0.4 05/13/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * * Relocated to include/linux where it belongs by Alan Cox * <gw4pts@gw4pts.ampr.org> */ #ifndef _LINUX_ETHERDEVICE_H #define _LINUX_ETHERDEVICE_H #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/random.h> #include <linux/crc32.h> #include <linux/unaligned.h> #include <asm/bitsperlong.h> #ifdef __KERNEL__ struct device; struct fwnode_handle; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); int platform_get_ethdev_address(struct device *dev, struct net_device *netdev); unsigned char *arch_get_platform_mac_address(void); int nvmem_get_mac_address(struct device *dev, void *addrbuf); int device_get_mac_address(struct device *dev, char *addr); int device_get_ethdev_address(struct device *dev, struct net_device *netdev); int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr); u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); extern const struct header_ops eth_header_ops; int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len); int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr); int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); void eth_header_cache_update(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr); __be16 eth_header_parse_protocol(const struct sk_buff *skb); int eth_prepare_mac_addr_change(struct net_device *dev, void *p); void eth_commit_mac_addr_change(struct net_device *dev, void *p); int eth_mac_addr(struct net_device *dev, void *p); int eth_validate_addr(struct net_device *dev); struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, unsigned int rxqs); #define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1) #define alloc_etherdev_mq(sizeof_priv, count) alloc_etherdev_mqs(sizeof_priv, count, count) struct net_device *devm_alloc_etherdev_mqs(struct device *dev, int sizeof_priv, unsigned int txqs, unsigned int rxqs); #define devm_alloc_etherdev(dev, sizeof_priv) devm_alloc_etherdev_mqs(dev, sizeof_priv, 1, 1) struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb); int eth_gro_complete(struct sk_buff *skb, int nhoff); /* Reserved Ethernet Addresses per IEEE 802.1Q */ static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; #define eth_stp_addr eth_reserved_addr_base static const u8 eth_ipv4_mcast_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 }; static const u8 eth_ipv6_mcast_addr_base[ETH_ALEN] __aligned(2) = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 }; /** * is_link_local_ether_addr - Determine if given Ethernet address is link-local * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if address is link local reserved addr (01:80:c2:00:00:0X) per * IEEE 802.1Q 8.6.3 Frame filtering. * * Please note: addr must be aligned to u16. */ static inline bool is_link_local_ether_addr(const u8 *addr) { __be16 *a = (__be16 *)addr; static const __be16 *b = (const __be16 *)eth_reserved_addr_base; static const __be16 m = cpu_to_be16(0xfff0); #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return (((*(const u32 *)addr) ^ (*(const u32 *)b)) | (__force int)((a[2] ^ b[2]) & m)) == 0; #else return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0; #endif } /** * is_zero_ether_addr - Determine if give Ethernet address is all zeros. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is all zeroes. * * Please note: addr must be aligned to u16. */ static inline bool is_zero_ether_addr(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return ((*(const u32 *)addr) | (*(const u16 *)(addr + 4))) == 0; #else return (*(const u16 *)(addr + 0) | *(const u16 *)(addr + 2) | *(const u16 *)(addr + 4)) == 0; #endif } /** * is_multicast_ether_addr - Determine if the Ethernet address is a multicast. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is a multicast address. * By definition the broadcast address is also a multicast address. */ static inline bool is_multicast_ether_addr(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) u32 a = *(const u32 *)addr; #else u16 a = *(const u16 *)addr; #endif #ifdef __BIG_ENDIAN return 0x01 & (a >> ((sizeof(a) * 8) - 8)); #else return 0x01 & a; #endif } static inline bool is_multicast_ether_addr_64bits(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 #ifdef __BIG_ENDIAN return 0x01 & ((*(const u64 *)addr) >> 56); #else return 0x01 & (*(const u64 *)addr); #endif #else return is_multicast_ether_addr(addr); #endif } /** * is_local_ether_addr - Determine if the Ethernet address is locally-assigned one (IEEE 802). * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is a local address. */ static inline bool is_local_ether_addr(const u8 *addr) { return 0x02 & addr[0]; } /** * is_broadcast_ether_addr - Determine if the Ethernet address is broadcast * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is the broadcast address. * * Please note: addr must be aligned to u16. */ static inline bool is_broadcast_ether_addr(const u8 *addr) { return (*(const u16 *)(addr + 0) & *(const u16 *)(addr + 2) & *(const u16 *)(addr + 4)) == 0xffff; } /** * is_unicast_ether_addr - Determine if the Ethernet address is unicast * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is a unicast address. */ static inline bool is_unicast_ether_addr(const u8 *addr) { return !is_multicast_ether_addr(addr); } /** * is_valid_ether_addr - Determine if the given Ethernet address is valid * @addr: Pointer to a six-byte array containing the Ethernet address * * Check that the Ethernet address (MAC) is not 00:00:00:00:00:00, is not * a multicast address, and is not FF:FF:FF:FF:FF:FF. * * Return true if the address is valid. * * Please note: addr must be aligned to u16. */ static inline bool is_valid_ether_addr(const u8 *addr) { /* FF:FF:FF:FF:FF:FF is a multicast address so we don't need to * explicitly check for it here. */ return !is_multicast_ether_addr(addr) && !is_zero_ether_addr(addr); } /** * eth_proto_is_802_3 - Determine if a given Ethertype/length is a protocol * @proto: Ethertype/length value to be tested * * Check that the value from the Ethertype/length field is a valid Ethertype. * * Return true if the valid is an 802.3 supported Ethertype. */ static inline bool eth_proto_is_802_3(__be16 proto) { #ifndef __BIG_ENDIAN /* if CPU is little endian mask off bits representing LSB */ proto &= htons(0xFF00); #endif /* cast both to u16 and compare since LSB can be ignored */ return (__force u16)proto >= (__force u16)htons(ETH_P_802_3_MIN); } /** * eth_random_addr - Generate software assigned random Ethernet address * @addr: Pointer to a six-byte array containing the Ethernet address * * Generate a random Ethernet address (MAC) that is not multicast * and has the local assigned bit set. */ static inline void eth_random_addr(u8 *addr) { get_random_bytes(addr, ETH_ALEN); addr[0] &= 0xfe; /* clear multicast bit */ addr[0] |= 0x02; /* set local assignment bit (IEEE802) */ } /** * eth_broadcast_addr - Assign broadcast address * @addr: Pointer to a six-byte array containing the Ethernet address * * Assign the broadcast address to the given address array. */ static inline void eth_broadcast_addr(u8 *addr) { memset(addr, 0xff, ETH_ALEN); } /** * eth_zero_addr - Assign zero address * @addr: Pointer to a six-byte array containing the Ethernet address * * Assign the zero address to the given address array. */ static inline void eth_zero_addr(u8 *addr) { memset(addr, 0x00, ETH_ALEN); } /** * eth_hw_addr_random - Generate software assigned random Ethernet and * set device flag * @dev: pointer to net_device structure * * Generate a random Ethernet address (MAC) to be used by a net device * and set addr_assign_type so the state can be read by sysfs and be * used by userspace. */ static inline void eth_hw_addr_random(struct net_device *dev) { u8 addr[ETH_ALEN]; eth_random_addr(addr); __dev_addr_set(dev, addr, ETH_ALEN); dev->addr_assign_type = NET_ADDR_RANDOM; } /** * eth_hw_addr_crc - Calculate CRC from netdev_hw_addr * @ha: pointer to hardware address * * Calculate CRC from a hardware address as basis for filter hashes. */ static inline u32 eth_hw_addr_crc(struct netdev_hw_addr *ha) { return ether_crc(ETH_ALEN, ha->addr); } /** * ether_addr_copy - Copy an Ethernet address * @dst: Pointer to a six-byte array Ethernet address destination * @src: Pointer to a six-byte array Ethernet address source * * Please note: dst & src must both be aligned to u16. */ static inline void ether_addr_copy(u8 *dst, const u8 *src) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) *(u32 *)dst = *(const u32 *)src; *(u16 *)(dst + 4) = *(const u16 *)(src + 4); #else u16 *a = (u16 *)dst; const u16 *b = (const u16 *)src; a[0] = b[0]; a[1] = b[1]; a[2] = b[2]; #endif } /** * eth_hw_addr_set - Assign Ethernet address to a net_device * @dev: pointer to net_device structure * @addr: address to assign * * Assign given address to the net_device, addr_assign_type is not changed. */ static inline void eth_hw_addr_set(struct net_device *dev, const u8 *addr) { __dev_addr_set(dev, addr, ETH_ALEN); } /** * eth_hw_addr_inherit - Copy dev_addr from another net_device * @dst: pointer to net_device to copy dev_addr to * @src: pointer to net_device to copy dev_addr from * * Copy the Ethernet address from one net_device to another along with * the address attributes (addr_assign_type). */ static inline void eth_hw_addr_inherit(struct net_device *dst, struct net_device *src) { dst->addr_assign_type = src->addr_assign_type; eth_hw_addr_set(dst, src->dev_addr); } /** * ether_addr_equal - Compare two Ethernet addresses * @addr1: Pointer to a six-byte array containing the Ethernet address * @addr2: Pointer other six-byte array containing the Ethernet address * * Compare two Ethernet addresses, returns true if equal * * Please note: addr1 & addr2 must both be aligned to u16. */ static inline bool ether_addr_equal(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) u32 fold = ((*(const u32 *)addr1) ^ (*(const u32 *)addr2)) | ((*(const u16 *)(addr1 + 4)) ^ (*(const u16 *)(addr2 + 4))); return fold == 0; #else const u16 *a = (const u16 *)addr1; const u16 *b = (const u16 *)addr2; return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) == 0; #endif } /** * ether_addr_equal_64bits - Compare two Ethernet addresses * @addr1: Pointer to an array of 8 bytes * @addr2: Pointer to an other array of 8 bytes * * Compare two Ethernet addresses, returns true if equal, false otherwise. * * The function doesn't need any conditional branches and possibly uses * word memory accesses on CPU allowing cheap unaligned memory reads. * arrays = { byte1, byte2, byte3, byte4, byte5, byte6, pad1, pad2 } * * Please note that alignment of addr1 & addr2 are only guaranteed to be 16 bits. */ static inline bool ether_addr_equal_64bits(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 u64 fold = (*(const u64 *)addr1) ^ (*(const u64 *)addr2); #ifdef __BIG_ENDIAN return (fold >> 16) == 0; #else return (fold << 16) == 0; #endif #else return ether_addr_equal(addr1, addr2); #endif } /** * ether_addr_equal_unaligned - Compare two not u16 aligned Ethernet addresses * @addr1: Pointer to a six-byte array containing the Ethernet address * @addr2: Pointer other six-byte array containing the Ethernet address * * Compare two Ethernet addresses, returns true if equal * * Please note: Use only when any Ethernet address may not be u16 aligned. */ static inline bool ether_addr_equal_unaligned(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return ether_addr_equal(addr1, addr2); #else return memcmp(addr1, addr2, ETH_ALEN) == 0; #endif } /** * ether_addr_equal_masked - Compare two Ethernet addresses with a mask * @addr1: Pointer to a six-byte array containing the 1st Ethernet address * @addr2: Pointer to a six-byte array containing the 2nd Ethernet address * @mask: Pointer to a six-byte array containing the Ethernet address bitmask * * Compare two Ethernet addresses with a mask, returns true if for every bit * set in the bitmask the equivalent bits in the ethernet addresses are equal. * Using a mask with all bits set is a slower ether_addr_equal. */ static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2, const u8 *mask) { int i; for (i = 0; i < ETH_ALEN; i++) { if ((addr1[i] ^ addr2[i]) & mask[i]) return false; } return true; } static inline bool ether_addr_is_ipv4_mcast(const u8 *addr) { u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0x80, 0x00, 0x00 }; return ether_addr_equal_masked(addr, eth_ipv4_mcast_addr_base, mask); } static inline bool ether_addr_is_ipv6_mcast(const u8 *addr) { u8 mask[ETH_ALEN] = { 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 }; return ether_addr_equal_masked(addr, eth_ipv6_mcast_addr_base, mask); } static inline bool ether_addr_is_ip_mcast(const u8 *addr) { return ether_addr_is_ipv4_mcast(addr) || ether_addr_is_ipv6_mcast(addr); } /** * ether_addr_to_u64 - Convert an Ethernet address into a u64 value. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return a u64 value of the address */ static inline u64 ether_addr_to_u64(const u8 *addr) { u64 u = 0; int i; for (i = 0; i < ETH_ALEN; i++) u = u << 8 | addr[i]; return u; } /** * u64_to_ether_addr - Convert a u64 to an Ethernet address. * @u: u64 to convert to an Ethernet MAC address * @addr: Pointer to a six-byte array to contain the Ethernet address */ static inline void u64_to_ether_addr(u64 u, u8 *addr) { int i; for (i = ETH_ALEN - 1; i >= 0; i--) { addr[i] = u & 0xff; u = u >> 8; } } /** * eth_addr_dec - Decrement the given MAC address * * @addr: Pointer to a six-byte array containing Ethernet address to decrement */ static inline void eth_addr_dec(u8 *addr) { u64 u = ether_addr_to_u64(addr); u--; u64_to_ether_addr(u, addr); } /** * eth_addr_inc() - Increment the given MAC address. * @addr: Pointer to a six-byte array containing Ethernet address to increment. */ static inline void eth_addr_inc(u8 *addr) { u64 u = ether_addr_to_u64(addr); u++; u64_to_ether_addr(u, addr); } /** * eth_addr_add() - Add (or subtract) an offset to/from the given MAC address. * * @offset: Offset to add. * @addr: Pointer to a six-byte array containing Ethernet address to increment. */ static inline void eth_addr_add(u8 *addr, long offset) { u64 u = ether_addr_to_u64(addr); u += offset; u64_to_ether_addr(u, addr); } /** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure * @addr: Pointer to a six-byte array containing the Ethernet address * * Compare passed address with all addresses of the device. Return true if the * address if one of the device addresses. * * Note that this function calls ether_addr_equal_64bits() so take care of * the right padding. */ static inline bool is_etherdev_addr(const struct net_device *dev, const u8 addr[6 + 2]) { struct netdev_hw_addr *ha; bool res = false; rcu_read_lock(); for_each_dev_addr(dev, ha) { res = ether_addr_equal_64bits(addr, ha->addr); if (res) break; } rcu_read_unlock(); return res; } #endif /* __KERNEL__ */ /** * compare_ether_header - Compare two Ethernet headers * @a: Pointer to Ethernet header * @b: Pointer to Ethernet header * * Compare two Ethernet headers, returns 0 if equal. * This assumes that the network header (i.e., IP header) is 4-byte * aligned OR the platform can handle unaligned access. This is the * case for all packets coming into netif_receive_skb or similar * entry points. */ static inline unsigned long compare_ether_header(const void *a, const void *b) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 unsigned long fold; /* * We want to compare 14 bytes: * [a0 ... a13] ^ [b0 ... b13] * Use two long XOR, ORed together, with an overlap of two bytes. * [a0 a1 a2 a3 a4 a5 a6 a7 ] ^ [b0 b1 b2 b3 b4 b5 b6 b7 ] | * [a6 a7 a8 a9 a10 a11 a12 a13] ^ [b6 b7 b8 b9 b10 b11 b12 b13] * This means the [a6 a7] ^ [b6 b7] part is done two times. */ fold = *(unsigned long *)a ^ *(unsigned long *)b; fold |= *(unsigned long *)(a + 6) ^ *(unsigned long *)(b + 6); return fold; #else u32 *a32 = (u32 *)((u8 *)a + 2); u32 *b32 = (u32 *)((u8 *)b + 2); return (*(u16 *)a ^ *(u16 *)b) | (a32[0] ^ b32[0]) | (a32[1] ^ b32[1]) | (a32[2] ^ b32[2]); #endif } /** * eth_hw_addr_gen - Generate and assign Ethernet address to a port * @dev: pointer to port's net_device structure * @base_addr: base Ethernet address * @id: offset to add to the base address * * Generate a MAC address using a base address and an offset and assign it * to a net_device. Commonly used by switch drivers which need to compute * addresses for all their ports. addr_assign_type is not changed. */ static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr, unsigned int id) { u64 u = ether_addr_to_u64(base_addr); u8 addr[ETH_ALEN]; u += id; u64_to_ether_addr(u, addr); eth_hw_addr_set(dev, addr); } /** * eth_skb_pkt_type - Assign packet type if destination address does not match * @skb: Assigned a packet type if address does not match @dev address * @dev: Network device used to compare packet address against * * If the destination MAC address of the packet does not match the network * device address, assign an appropriate packet type. */ static inline void eth_skb_pkt_type(struct sk_buff *skb, const struct net_device *dev) { const struct ethhdr *eth = eth_hdr(skb); if (unlikely(!ether_addr_equal_64bits(eth->h_dest, dev->dev_addr))) { if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) skb->pkt_type = PACKET_BROADCAST; else skb->pkt_type = PACKET_MULTICAST; } else { skb->pkt_type = PACKET_OTHERHOST; } } } static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb) { struct ethhdr *eth = (struct ethhdr *)skb->data; skb_pull_inline(skb, ETH_HLEN); return eth; } /** * eth_skb_pad - Pad buffer to minimum number of octets for Ethernet frame * @skb: Buffer to pad * * An Ethernet frame should have a minimum size of 60 bytes. This function * takes short frames and pads them with zeros up to the 60 byte limit. */ static inline int eth_skb_pad(struct sk_buff *skb) { return skb_put_padto(skb, ETH_ZLEN); } #endif /* _LINUX_ETHERDEVICE_H */ |
| 40 1 35 35 35 40 40 38 38 1 1 40 39 32 27 5 109 105 5 56 72 61 32 1 31 4 9 6 3 9 9 35 9 27 3 24 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/list.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <net/ip.h> #include <net/switchdev.h> #include "br_private.h" static struct static_key_false br_switchdev_tx_fwd_offload; static bool nbp_switchdev_can_offload_tx_fwd(const struct net_bridge_port *p, const struct sk_buff *skb) { if (!static_branch_unlikely(&br_switchdev_tx_fwd_offload)) return false; return (p->flags & BR_TX_FWD_OFFLOAD) && (p->hwdom != BR_INPUT_SKB_CB(skb)->src_hwdom); } bool br_switchdev_frame_uses_tx_fwd_offload(struct sk_buff *skb) { if (!static_branch_unlikely(&br_switchdev_tx_fwd_offload)) return false; return BR_INPUT_SKB_CB(skb)->tx_fwd_offload; } void br_switchdev_frame_set_offload_fwd_mark(struct sk_buff *skb) { skb->offload_fwd_mark = br_switchdev_frame_uses_tx_fwd_offload(skb); } /* Mark the frame for TX forwarding offload if this egress port supports it */ void nbp_switchdev_frame_mark_tx_fwd_offload(const struct net_bridge_port *p, struct sk_buff *skb) { if (nbp_switchdev_can_offload_tx_fwd(p, skb)) BR_INPUT_SKB_CB(skb)->tx_fwd_offload = true; } /* Lazily adds the hwdom of the egress bridge port to the bit mask of hwdoms * that the skb has been already forwarded to, to avoid further cloning to * other ports in the same hwdom by making nbp_switchdev_allowed_egress() * return false. */ void nbp_switchdev_frame_mark_tx_fwd_to_hwdom(const struct net_bridge_port *p, struct sk_buff *skb) { if (nbp_switchdev_can_offload_tx_fwd(p, skb)) set_bit(p->hwdom, &BR_INPUT_SKB_CB(skb)->fwd_hwdoms); } void nbp_switchdev_frame_mark(const struct net_bridge_port *p, struct sk_buff *skb) { if (p->hwdom) BR_INPUT_SKB_CB(skb)->src_hwdom = p->hwdom; } bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, const struct sk_buff *skb) { struct br_input_skb_cb *cb = BR_INPUT_SKB_CB(skb); return !test_bit(p->hwdom, &cb->fwd_hwdoms) && (!skb->offload_fwd_mark || cb->src_hwdom != p->hwdom); } /* Flags that can be offloaded to hardware */ #define BR_PORT_FLAGS_HW_OFFLOAD (BR_LEARNING | BR_FLOOD | BR_PORT_MAB | \ BR_MCAST_FLOOD | BR_BCAST_FLOOD | BR_PORT_LOCKED | \ BR_HAIRPIN_MODE | BR_ISOLATED | BR_MULTICAST_TO_UNICAST) int br_switchdev_set_port_flag(struct net_bridge_port *p, unsigned long flags, unsigned long mask, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = p->dev, }; struct switchdev_notifier_port_attr_info info = { .attr = &attr, }; int err; mask &= BR_PORT_FLAGS_HW_OFFLOAD; if (!mask) return 0; attr.id = SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS; attr.u.brport_flags.val = flags; attr.u.brport_flags.mask = mask; /* We run from atomic context here */ err = call_switchdev_notifiers(SWITCHDEV_PORT_ATTR_SET, p->dev, &info.info, extack); err = notifier_to_errno(err); if (err == -EOPNOTSUPP) return 0; if (err) { NL_SET_ERR_MSG_WEAK_MOD(extack, "bridge flag offload is not supported"); return -EOPNOTSUPP; } attr.id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS; attr.flags = SWITCHDEV_F_DEFER; err = switchdev_port_attr_set(p->dev, &attr, extack); if (err) { NL_SET_ERR_MSG_WEAK_MOD(extack, "error setting offload flag on port"); return err; } return 0; } static void br_switchdev_fdb_populate(struct net_bridge *br, struct switchdev_notifier_fdb_info *item, const struct net_bridge_fdb_entry *fdb, const void *ctx) { const struct net_bridge_port *p = READ_ONCE(fdb->dst); item->addr = fdb->key.addr.addr; item->vid = fdb->key.vlan_id; item->added_by_user = test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); item->offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags); item->is_local = test_bit(BR_FDB_LOCAL, &fdb->flags); item->locked = false; item->info.dev = (!p || item->is_local) ? br->dev : p->dev; item->info.ctx = ctx; } void br_switchdev_fdb_notify(struct net_bridge *br, const struct net_bridge_fdb_entry *fdb, int type) { struct switchdev_notifier_fdb_info item; if (test_bit(BR_FDB_LOCKED, &fdb->flags)) return; /* Entries with these flags were created using ndm_state == NUD_REACHABLE, * ndm_flags == NTF_MASTER( | NTF_STICKY), ext_flags == 0 by something * equivalent to 'bridge fdb add ... master dynamic (sticky)'. * Drivers don't know how to deal with these, so don't notify them to * avoid confusing them. */ if (test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags) && !test_bit(BR_FDB_STATIC, &fdb->flags) && !test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) return; br_switchdev_fdb_populate(br, &item, fdb, NULL); switch (type) { case RTM_DELNEIGH: call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_DEVICE, item.info.dev, &item.info, NULL); break; case RTM_NEWNEIGH: call_switchdev_notifiers(SWITCHDEV_FDB_ADD_TO_DEVICE, item.info.dev, &item.info, NULL); break; } } int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags, bool changed, struct netlink_ext_ack *extack) { struct switchdev_obj_port_vlan v = { .obj.orig_dev = dev, .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .flags = flags, .vid = vid, .changed = changed, }; return switchdev_port_obj_add(dev, &v.obj, extack); } int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid) { struct switchdev_obj_port_vlan v = { .obj.orig_dev = dev, .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .vid = vid, }; return switchdev_port_obj_del(dev, &v.obj); } static int nbp_switchdev_hwdom_set(struct net_bridge_port *joining) { struct net_bridge *br = joining->br; struct net_bridge_port *p; int hwdom; /* joining is yet to be added to the port list. */ list_for_each_entry(p, &br->port_list, list) { if (netdev_phys_item_id_same(&joining->ppid, &p->ppid)) { joining->hwdom = p->hwdom; return 0; } } hwdom = find_next_zero_bit(&br->busy_hwdoms, BR_HWDOM_MAX, 1); if (hwdom >= BR_HWDOM_MAX) return -EBUSY; set_bit(hwdom, &br->busy_hwdoms); joining->hwdom = hwdom; return 0; } static void nbp_switchdev_hwdom_put(struct net_bridge_port *leaving) { struct net_bridge *br = leaving->br; struct net_bridge_port *p; /* leaving is no longer in the port list. */ list_for_each_entry(p, &br->port_list, list) { if (p->hwdom == leaving->hwdom) return; } clear_bit(leaving->hwdom, &br->busy_hwdoms); } static int nbp_switchdev_add(struct net_bridge_port *p, struct netdev_phys_item_id ppid, bool tx_fwd_offload, struct netlink_ext_ack *extack) { int err; if (p->offload_count) { /* Prevent unsupported configurations such as a bridge port * which is a bonding interface, and the member ports are from * different hardware switches. */ if (!netdev_phys_item_id_same(&p->ppid, &ppid)) { NL_SET_ERR_MSG_MOD(extack, "Same bridge port cannot be offloaded by two physical switches"); return -EBUSY; } /* Tolerate drivers that call switchdev_bridge_port_offload() * more than once for the same bridge port, such as when the * bridge port is an offloaded bonding/team interface. */ p->offload_count++; return 0; } p->ppid = ppid; p->offload_count = 1; err = nbp_switchdev_hwdom_set(p); if (err) return err; if (tx_fwd_offload) { p->flags |= BR_TX_FWD_OFFLOAD; static_branch_inc(&br_switchdev_tx_fwd_offload); } return 0; } static void nbp_switchdev_del(struct net_bridge_port *p) { if (WARN_ON(!p->offload_count)) return; p->offload_count--; if (p->offload_count) return; if (p->hwdom) nbp_switchdev_hwdom_put(p); if (p->flags & BR_TX_FWD_OFFLOAD) { p->flags &= ~BR_TX_FWD_OFFLOAD; static_branch_dec(&br_switchdev_tx_fwd_offload); } } static int br_switchdev_fdb_replay_one(struct net_bridge *br, struct notifier_block *nb, const struct net_bridge_fdb_entry *fdb, unsigned long action, const void *ctx) { struct switchdev_notifier_fdb_info item; int err; br_switchdev_fdb_populate(br, &item, fdb, ctx); err = nb->notifier_call(nb, action, &item); return notifier_to_errno(err); } static int br_switchdev_fdb_replay(const struct net_device *br_dev, const void *ctx, bool adding, struct notifier_block *nb) { struct net_bridge_fdb_entry *fdb; struct net_bridge *br; unsigned long action; int err = 0; if (!nb) return 0; if (!netif_is_bridge_master(br_dev)) return -EINVAL; br = netdev_priv(br_dev); if (adding) action = SWITCHDEV_FDB_ADD_TO_DEVICE; else action = SWITCHDEV_FDB_DEL_TO_DEVICE; rcu_read_lock(); hlist_for_each_entry_rcu(fdb, &br->fdb_list, fdb_node) { err = br_switchdev_fdb_replay_one(br, nb, fdb, action, ctx); if (err) break; } rcu_read_unlock(); return err; } static int br_switchdev_vlan_attr_replay(struct net_device *br_dev, const void *ctx, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct switchdev_notifier_port_attr_info attr_info = { .info = { .dev = br_dev, .extack = extack, .ctx = ctx, }, }; struct net_bridge *br = netdev_priv(br_dev); struct net_bridge_vlan_group *vg; struct switchdev_attr attr; struct net_bridge_vlan *v; int err; attr_info.attr = &attr; attr.orig_dev = br_dev; vg = br_vlan_group(br); if (!vg) return 0; list_for_each_entry(v, &vg->vlan_list, vlist) { if (v->msti) { attr.id = SWITCHDEV_ATTR_ID_VLAN_MSTI; attr.u.vlan_msti.vid = v->vid; attr.u.vlan_msti.msti = v->msti; err = nb->notifier_call(nb, SWITCHDEV_PORT_ATTR_SET, &attr_info); err = notifier_to_errno(err); if (err) return err; } } return 0; } static int br_switchdev_vlan_replay_one(struct notifier_block *nb, struct net_device *dev, struct switchdev_obj_port_vlan *vlan, const void *ctx, unsigned long action, struct netlink_ext_ack *extack) { struct switchdev_notifier_port_obj_info obj_info = { .info = { .dev = dev, .extack = extack, .ctx = ctx, }, .obj = &vlan->obj, }; int err; err = nb->notifier_call(nb, action, &obj_info); return notifier_to_errno(err); } static int br_switchdev_vlan_replay_group(struct notifier_block *nb, struct net_device *dev, struct net_bridge_vlan_group *vg, const void *ctx, unsigned long action, struct netlink_ext_ack *extack) { struct net_bridge_vlan *v; int err = 0; u16 pvid; if (!vg) return 0; pvid = br_get_pvid(vg); list_for_each_entry(v, &vg->vlan_list, vlist) { struct switchdev_obj_port_vlan vlan = { .obj.orig_dev = dev, .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .flags = br_vlan_flags(v, pvid), .vid = v->vid, }; if (!br_vlan_should_use(v)) continue; err = br_switchdev_vlan_replay_one(nb, dev, &vlan, ctx, action, extack); if (err) return err; } return 0; } static int br_switchdev_vlan_replay(struct net_device *br_dev, const void *ctx, bool adding, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(br_dev); struct net_bridge_port *p; unsigned long action; int err; ASSERT_RTNL(); if (!nb) return 0; if (!netif_is_bridge_master(br_dev)) return -EINVAL; if (adding) action = SWITCHDEV_PORT_OBJ_ADD; else action = SWITCHDEV_PORT_OBJ_DEL; err = br_switchdev_vlan_replay_group(nb, br_dev, br_vlan_group(br), ctx, action, extack); if (err) return err; list_for_each_entry(p, &br->port_list, list) { struct net_device *dev = p->dev; err = br_switchdev_vlan_replay_group(nb, dev, nbp_vlan_group(p), ctx, action, extack); if (err) return err; } if (adding) { err = br_switchdev_vlan_attr_replay(br_dev, ctx, nb, extack); if (err) return err; } return 0; } #ifdef CONFIG_BRIDGE_IGMP_SNOOPING struct br_switchdev_mdb_complete_info { struct net_bridge_port *port; struct br_ip ip; }; static void br_switchdev_mdb_complete(struct net_device *dev, int err, void *priv) { struct br_switchdev_mdb_complete_info *data = priv; struct net_bridge_port_group __rcu **pp; struct net_bridge_port_group *p; struct net_bridge_mdb_entry *mp; struct net_bridge_port *port = data->port; struct net_bridge *br = port->br; if (err) goto err; spin_lock_bh(&br->multicast_lock); mp = br_mdb_ip_get(br, &data->ip); if (!mp) goto out; for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (p->key.port != port) continue; p->flags |= MDB_PG_FLAGS_OFFLOAD; } out: spin_unlock_bh(&br->multicast_lock); err: kfree(priv); } static void br_switchdev_mdb_populate(struct switchdev_obj_port_mdb *mdb, const struct net_bridge_mdb_entry *mp) { if (mp->addr.proto == htons(ETH_P_IP)) ip_eth_mc_map(mp->addr.dst.ip4, mdb->addr); #if IS_ENABLED(CONFIG_IPV6) else if (mp->addr.proto == htons(ETH_P_IPV6)) ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb->addr); #endif else ether_addr_copy(mdb->addr, mp->addr.dst.mac_addr); mdb->vid = mp->addr.vid; } static void br_switchdev_host_mdb_one(struct net_device *dev, struct net_device *lower_dev, struct net_bridge_mdb_entry *mp, int type) { struct switchdev_obj_port_mdb mdb = { .obj = { .id = SWITCHDEV_OBJ_ID_HOST_MDB, .flags = SWITCHDEV_F_DEFER, .orig_dev = dev, }, }; br_switchdev_mdb_populate(&mdb, mp); switch (type) { case RTM_NEWMDB: switchdev_port_obj_add(lower_dev, &mdb.obj, NULL); break; case RTM_DELMDB: switchdev_port_obj_del(lower_dev, &mdb.obj); break; } } static void br_switchdev_host_mdb(struct net_device *dev, struct net_bridge_mdb_entry *mp, int type) { struct net_device *lower_dev; struct list_head *iter; netdev_for_each_lower_dev(dev, lower_dev, iter) br_switchdev_host_mdb_one(dev, lower_dev, mp, type); } static int br_switchdev_mdb_replay_one(struct notifier_block *nb, struct net_device *dev, const struct switchdev_obj_port_mdb *mdb, unsigned long action, const void *ctx, struct netlink_ext_ack *extack) { struct switchdev_notifier_port_obj_info obj_info = { .info = { .dev = dev, .extack = extack, .ctx = ctx, }, .obj = &mdb->obj, }; int err; err = nb->notifier_call(nb, action, &obj_info); return notifier_to_errno(err); } static int br_switchdev_mdb_queue_one(struct list_head *mdb_list, struct net_device *dev, unsigned long action, enum switchdev_obj_id id, const struct net_bridge_mdb_entry *mp, struct net_device *orig_dev) { struct switchdev_obj_port_mdb mdb = { .obj = { .id = id, .orig_dev = orig_dev, }, }; struct switchdev_obj_port_mdb *pmdb; br_switchdev_mdb_populate(&mdb, mp); if (action == SWITCHDEV_PORT_OBJ_ADD && switchdev_port_obj_act_is_deferred(dev, action, &mdb.obj)) { /* This event is already in the deferred queue of * events, so this replay must be elided, lest the * driver receives duplicate events for it. This can * only happen when replaying additions, since * modifications are always immediately visible in * br->mdb_list, whereas actual event delivery may be * delayed. */ return 0; } pmdb = kmemdup(&mdb, sizeof(mdb), GFP_ATOMIC); if (!pmdb) return -ENOMEM; list_add_tail(&pmdb->obj.list, mdb_list); return 0; } void br_switchdev_mdb_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *pg, int type) { struct br_switchdev_mdb_complete_info *complete_info; struct switchdev_obj_port_mdb mdb = { .obj = { .id = SWITCHDEV_OBJ_ID_PORT_MDB, .flags = SWITCHDEV_F_DEFER, }, }; if (!pg) return br_switchdev_host_mdb(dev, mp, type); br_switchdev_mdb_populate(&mdb, mp); mdb.obj.orig_dev = pg->key.port->dev; switch (type) { case RTM_NEWMDB: complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC); if (!complete_info) break; complete_info->port = pg->key.port; complete_info->ip = mp->addr; mdb.obj.complete_priv = complete_info; mdb.obj.complete = br_switchdev_mdb_complete; if (switchdev_port_obj_add(pg->key.port->dev, &mdb.obj, NULL)) kfree(complete_info); break; case RTM_DELMDB: switchdev_port_obj_del(pg->key.port->dev, &mdb.obj); break; } } #endif static int br_switchdev_mdb_replay(struct net_device *br_dev, struct net_device *dev, const void *ctx, bool adding, struct notifier_block *nb, struct netlink_ext_ack *extack) { #ifdef CONFIG_BRIDGE_IGMP_SNOOPING const struct net_bridge_mdb_entry *mp; struct switchdev_obj *obj, *tmp; struct net_bridge *br; unsigned long action; LIST_HEAD(mdb_list); int err = 0; ASSERT_RTNL(); if (!nb) return 0; if (!netif_is_bridge_master(br_dev) || !netif_is_bridge_port(dev)) return -EINVAL; br = netdev_priv(br_dev); if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) return 0; if (adding) action = SWITCHDEV_PORT_OBJ_ADD; else action = SWITCHDEV_PORT_OBJ_DEL; /* br_switchdev_mdb_queue_one() will take care to not queue a * replay of an event that is already pending in the switchdev * deferred queue. In order to safely determine that, there * must be no new deferred MDB notifications enqueued for the * duration of the MDB scan. Therefore, grab the write-side * lock to avoid racing with any concurrent IGMP/MLD snooping. */ spin_lock_bh(&br->multicast_lock); hlist_for_each_entry(mp, &br->mdb_list, mdb_node) { struct net_bridge_port_group __rcu * const *pp; const struct net_bridge_port_group *p; if (mp->host_joined) { err = br_switchdev_mdb_queue_one(&mdb_list, dev, action, SWITCHDEV_OBJ_ID_HOST_MDB, mp, br_dev); if (err) { spin_unlock_bh(&br->multicast_lock); goto out_free_mdb; } } for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (p->key.port->dev != dev) continue; err = br_switchdev_mdb_queue_one(&mdb_list, dev, action, SWITCHDEV_OBJ_ID_PORT_MDB, mp, dev); if (err) { spin_unlock_bh(&br->multicast_lock); goto out_free_mdb; } } } spin_unlock_bh(&br->multicast_lock); list_for_each_entry(obj, &mdb_list, list) { err = br_switchdev_mdb_replay_one(nb, dev, SWITCHDEV_OBJ_PORT_MDB(obj), action, ctx, extack); if (err == -EOPNOTSUPP) err = 0; if (err) goto out_free_mdb; } out_free_mdb: list_for_each_entry_safe(obj, tmp, &mdb_list, list) { list_del(&obj->list); kfree(SWITCHDEV_OBJ_PORT_MDB(obj)); } if (err) return err; #endif return 0; } static int nbp_switchdev_sync_objs(struct net_bridge_port *p, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb, struct netlink_ext_ack *extack) { struct net_device *br_dev = p->br->dev; struct net_device *dev = p->dev; int err; err = br_switchdev_vlan_replay(br_dev, ctx, true, blocking_nb, extack); if (err && err != -EOPNOTSUPP) return err; err = br_switchdev_mdb_replay(br_dev, dev, ctx, true, blocking_nb, extack); if (err) { /* -EOPNOTSUPP not propagated from MDB replay. */ return err; } err = br_switchdev_fdb_replay(br_dev, ctx, true, atomic_nb); if (err && err != -EOPNOTSUPP) return err; return 0; } static void nbp_switchdev_unsync_objs(struct net_bridge_port *p, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb) { struct net_device *br_dev = p->br->dev; struct net_device *dev = p->dev; br_switchdev_fdb_replay(br_dev, ctx, false, atomic_nb); br_switchdev_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL); br_switchdev_vlan_replay(br_dev, ctx, false, blocking_nb, NULL); /* Make sure that the device leaving this bridge has seen all * relevant events before it is disassociated. In the normal * case, when the device is directly attached to the bridge, * this is covered by del_nbp(). If the association was indirect * however, e.g. via a team or bond, and the device is leaving * that intermediate device, then the bridge port remains in * place. */ switchdev_deferred_process(); } /* Let the bridge know that this port is offloaded, so that it can assign a * switchdev hardware domain to it. */ int br_switchdev_port_offload(struct net_bridge_port *p, struct net_device *dev, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb, bool tx_fwd_offload, struct netlink_ext_ack *extack) { struct netdev_phys_item_id ppid; int err; err = dev_get_port_parent_id(dev, &ppid, false); if (err) return err; err = nbp_switchdev_add(p, ppid, tx_fwd_offload, extack); if (err) return err; err = nbp_switchdev_sync_objs(p, ctx, atomic_nb, blocking_nb, extack); if (err) goto out_switchdev_del; return 0; out_switchdev_del: nbp_switchdev_del(p); return err; } void br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb) { nbp_switchdev_unsync_objs(p, ctx, atomic_nb, blocking_nb); nbp_switchdev_del(p); } int br_switchdev_port_replay(struct net_bridge_port *p, struct net_device *dev, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb, struct netlink_ext_ack *extack) { return nbp_switchdev_sync_objs(p, ctx, atomic_nb, blocking_nb, extack); } |
| 8 6 6 2 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _CRYPTO_INTERNAL_CHACHA_H #define _CRYPTO_INTERNAL_CHACHA_H #include <crypto/chacha.h> #include <crypto/internal/skcipher.h> #include <linux/crypto.h> struct chacha_ctx { u32 key[8]; int nrounds; }; static inline int chacha_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keysize, int nrounds) { struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); int i; if (keysize != CHACHA_KEY_SIZE) return -EINVAL; for (i = 0; i < ARRAY_SIZE(ctx->key); i++) ctx->key[i] = get_unaligned_le32(key + i * sizeof(u32)); ctx->nrounds = nrounds; return 0; } static inline int chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keysize) { return chacha_setkey(tfm, key, keysize, 20); } static inline int chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keysize) { return chacha_setkey(tfm, key, keysize, 12); } #endif /* _CRYPTO_CHACHA_H */ |
| 5 5 5 5 | 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 | /* * Copyright (c) 2006 Intel Corporation. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include <linux/completion.h> #include <linux/dma-mapping.h> #include <linux/err.h> #include <linux/interrupt.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/bitops.h> #include <linux/random.h> #include <rdma/ib_cache.h> #include "sa.h" static int mcast_add_one(struct ib_device *device); static void mcast_remove_one(struct ib_device *device, void *client_data); static struct ib_client mcast_client = { .name = "ib_multicast", .add = mcast_add_one, .remove = mcast_remove_one }; static struct ib_sa_client sa_client; static struct workqueue_struct *mcast_wq; static union ib_gid mgid0; struct mcast_device; struct mcast_port { struct mcast_device *dev; spinlock_t lock; struct rb_root table; refcount_t refcount; struct completion comp; u32 port_num; }; struct mcast_device { struct ib_device *device; struct ib_event_handler event_handler; int start_port; int end_port; struct mcast_port port[]; }; enum mcast_state { MCAST_JOINING, MCAST_MEMBER, MCAST_ERROR, }; enum mcast_group_state { MCAST_IDLE, MCAST_BUSY, MCAST_GROUP_ERROR, MCAST_PKEY_EVENT }; enum { MCAST_INVALID_PKEY_INDEX = 0xFFFF }; struct mcast_member; struct mcast_group { struct ib_sa_mcmember_rec rec; struct rb_node node; struct mcast_port *port; spinlock_t lock; struct work_struct work; struct list_head pending_list; struct list_head active_list; struct mcast_member *last_join; int members[NUM_JOIN_MEMBERSHIP_TYPES]; atomic_t refcount; enum mcast_group_state state; struct ib_sa_query *query; u16 pkey_index; u8 leave_state; int retries; }; struct mcast_member { struct ib_sa_multicast multicast; struct ib_sa_client *client; struct mcast_group *group; struct list_head list; enum mcast_state state; refcount_t refcount; struct completion comp; }; static void join_handler(int status, struct ib_sa_mcmember_rec *rec, void *context); static void leave_handler(int status, struct ib_sa_mcmember_rec *rec, void *context); static struct mcast_group *mcast_find(struct mcast_port *port, union ib_gid *mgid) { struct rb_node *node = port->table.rb_node; struct mcast_group *group; int ret; while (node) { group = rb_entry(node, struct mcast_group, node); ret = memcmp(mgid->raw, group->rec.mgid.raw, sizeof *mgid); if (!ret) return group; if (ret < 0) node = node->rb_left; else node = node->rb_right; } return NULL; } static struct mcast_group *mcast_insert(struct mcast_port *port, struct mcast_group *group, int allow_duplicates) { struct rb_node **link = &port->table.rb_node; struct rb_node *parent = NULL; struct mcast_group *cur_group; int ret; while (*link) { parent = *link; cur_group = rb_entry(parent, struct mcast_group, node); ret = memcmp(group->rec.mgid.raw, cur_group->rec.mgid.raw, sizeof group->rec.mgid); if (ret < 0) link = &(*link)->rb_left; else if (ret > 0) link = &(*link)->rb_right; else if (allow_duplicates) link = &(*link)->rb_left; else return cur_group; } rb_link_node(&group->node, parent, link); rb_insert_color(&group->node, &port->table); return NULL; } static void deref_port(struct mcast_port *port) { if (refcount_dec_and_test(&port->refcount)) complete(&port->comp); } static void release_group(struct mcast_group *group) { struct mcast_port *port = group->port; unsigned long flags; spin_lock_irqsave(&port->lock, flags); if (atomic_dec_and_test(&group->refcount)) { rb_erase(&group->node, &port->table); spin_unlock_irqrestore(&port->lock, flags); kfree(group); deref_port(port); } else spin_unlock_irqrestore(&port->lock, flags); } static void deref_member(struct mcast_member *member) { if (refcount_dec_and_test(&member->refcount)) complete(&member->comp); } static void queue_join(struct mcast_member *member) { struct mcast_group *group = member->group; unsigned long flags; spin_lock_irqsave(&group->lock, flags); list_add_tail(&member->list, &group->pending_list); if (group->state == MCAST_IDLE) { group->state = MCAST_BUSY; atomic_inc(&group->refcount); queue_work(mcast_wq, &group->work); } spin_unlock_irqrestore(&group->lock, flags); } /* * A multicast group has four types of members: full member, non member, * sendonly non member and sendonly full member. * We need to keep track of the number of members of each * type based on their join state. Adjust the number of members the belong to * the specified join states. */ static void adjust_membership(struct mcast_group *group, u8 join_state, int inc) { int i; for (i = 0; i < NUM_JOIN_MEMBERSHIP_TYPES; i++, join_state >>= 1) if (join_state & 0x1) group->members[i] += inc; } /* * If a multicast group has zero members left for a particular join state, but * the group is still a member with the SA, we need to leave that join state. * Determine which join states we still belong to, but that do not have any * active members. */ static u8 get_leave_state(struct mcast_group *group) { u8 leave_state = 0; int i; for (i = 0; i < NUM_JOIN_MEMBERSHIP_TYPES; i++) if (!group->members[i]) leave_state |= (0x1 << i); return leave_state & group->rec.join_state; } static int check_selector(ib_sa_comp_mask comp_mask, ib_sa_comp_mask selector_mask, ib_sa_comp_mask value_mask, u8 selector, u8 src_value, u8 dst_value) { int err; if (!(comp_mask & selector_mask) || !(comp_mask & value_mask)) return 0; switch (selector) { case IB_SA_GT: err = (src_value <= dst_value); break; case IB_SA_LT: err = (src_value >= dst_value); break; case IB_SA_EQ: err = (src_value != dst_value); break; default: err = 0; break; } return err; } static int cmp_rec(struct ib_sa_mcmember_rec *src, struct ib_sa_mcmember_rec *dst, ib_sa_comp_mask comp_mask) { /* MGID must already match */ if (comp_mask & IB_SA_MCMEMBER_REC_PORT_GID && memcmp(&src->port_gid, &dst->port_gid, sizeof src->port_gid)) return -EINVAL; if (comp_mask & IB_SA_MCMEMBER_REC_QKEY && src->qkey != dst->qkey) return -EINVAL; if (comp_mask & IB_SA_MCMEMBER_REC_MLID && src->mlid != dst->mlid) return -EINVAL; if (check_selector(comp_mask, IB_SA_MCMEMBER_REC_MTU_SELECTOR, IB_SA_MCMEMBER_REC_MTU, dst->mtu_selector, src->mtu, dst->mtu)) return -EINVAL; if (comp_mask & IB_SA_MCMEMBER_REC_TRAFFIC_CLASS && src->traffic_class != dst->traffic_class) return -EINVAL; if (comp_mask & IB_SA_MCMEMBER_REC_PKEY && src->pkey != dst->pkey) return -EINVAL; if (check_selector(comp_mask, IB_SA_MCMEMBER_REC_RATE_SELECTOR, IB_SA_MCMEMBER_REC_RATE, dst->rate_selector, src->rate, dst->rate)) return -EINVAL; if (check_selector(comp_mask, IB_SA_MCMEMBER_REC_PACKET_LIFE_TIME_SELECTOR, IB_SA_MCMEMBER_REC_PACKET_LIFE_TIME, dst->packet_life_time_selector, src->packet_life_time, dst->packet_life_time)) return -EINVAL; if (comp_mask & IB_SA_MCMEMBER_REC_SL && src->sl != dst->sl) return -EINVAL; if (comp_mask & IB_SA_MCMEMBER_REC_FLOW_LABEL && src->flow_label != dst->flow_label) return -EINVAL; if (comp_mask & IB_SA_MCMEMBER_REC_HOP_LIMIT && src->hop_limit != dst->hop_limit) return -EINVAL; if (comp_mask & IB_SA_MCMEMBER_REC_SCOPE && src->scope != dst->scope) return -EINVAL; /* join_state checked separately, proxy_join ignored */ return 0; } static int send_join(struct mcast_group *group, struct mcast_member *member) { struct mcast_port *port = group->port; int ret; group->last_join = member; ret = ib_sa_mcmember_rec_query(&sa_client, port->dev->device, port->port_num, IB_MGMT_METHOD_SET, &member->multicast.rec, member->multicast.comp_mask, 3000, GFP_KERNEL, join_handler, group, &group->query); return (ret > 0) ? 0 : ret; } static int send_leave(struct mcast_group *group, u8 leave_state) { struct mcast_port *port = group->port; struct ib_sa_mcmember_rec rec; int ret; rec = group->rec; rec.join_state = leave_state; group->leave_state = leave_state; ret = ib_sa_mcmember_rec_query(&sa_client, port->dev->device, port->port_num, IB_SA_METHOD_DELETE, &rec, IB_SA_MCMEMBER_REC_MGID | IB_SA_MCMEMBER_REC_PORT_GID | IB_SA_MCMEMBER_REC_JOIN_STATE, 3000, GFP_KERNEL, leave_handler, group, &group->query); return (ret > 0) ? 0 : ret; } static void join_group(struct mcast_group *group, struct mcast_member *member, u8 join_state) { member->state = MCAST_MEMBER; adjust_membership(group, join_state, 1); group->rec.join_state |= join_state; member->multicast.rec = group->rec; member->multicast.rec.join_state = join_state; list_move(&member->list, &group->active_list); } static int fail_join(struct mcast_group *group, struct mcast_member *member, int status) { spin_lock_irq(&group->lock); list_del_init(&member->list); spin_unlock_irq(&group->lock); return member->multicast.callback(status, &member->multicast); } static void process_group_error(struct mcast_group *group) { struct mcast_member *member; int ret = 0; u16 pkey_index; if (group->state == MCAST_PKEY_EVENT) ret = ib_find_pkey(group->port->dev->device, group->port->port_num, be16_to_cpu(group->rec.pkey), &pkey_index); spin_lock_irq(&group->lock); if (group->state == MCAST_PKEY_EVENT && !ret && group->pkey_index == pkey_index) goto out; while (!list_empty(&group->active_list)) { member = list_entry(group->active_list.next, struct mcast_member, list); refcount_inc(&member->refcount); list_del_init(&member->list); adjust_membership(group, member->multicast.rec.join_state, -1); member->state = MCAST_ERROR; spin_unlock_irq(&group->lock); ret = member->multicast.callback(-ENETRESET, &member->multicast); deref_member(member); if (ret) ib_sa_free_multicast(&member->multicast); spin_lock_irq(&group->lock); } group->rec.join_state = 0; out: group->state = MCAST_BUSY; spin_unlock_irq(&group->lock); } static void mcast_work_handler(struct work_struct *work) { struct mcast_group *group; struct mcast_member *member; struct ib_sa_multicast *multicast; int status, ret; u8 join_state; group = container_of(work, typeof(*group), work); retest: spin_lock_irq(&group->lock); while (!list_empty(&group->pending_list) || (group->state != MCAST_BUSY)) { if (group->state != MCAST_BUSY) { spin_unlock_irq(&group->lock); process_group_error(group); goto retest; } member = list_entry(group->pending_list.next, struct mcast_member, list); multicast = &member->multicast; join_state = multicast->rec.join_state; refcount_inc(&member->refcount); if (join_state == (group->rec.join_state & join_state)) { status = cmp_rec(&group->rec, &multicast->rec, multicast->comp_mask); if (!status) join_group(group, member, join_state); else list_del_init(&member->list); spin_unlock_irq(&group->lock); ret = multicast->callback(status, multicast); } else { spin_unlock_irq(&group->lock); status = send_join(group, member); if (!status) { deref_member(member); return; } ret = fail_join(group, member, status); } deref_member(member); if (ret) ib_sa_free_multicast(&member->multicast); spin_lock_irq(&group->lock); } join_state = get_leave_state(group); if (join_state) { group->rec.join_state &= ~join_state; spin_unlock_irq(&group->lock); if (send_leave(group, join_state)) goto retest; } else { group->state = MCAST_IDLE; spin_unlock_irq(&group->lock); release_group(group); } } /* * Fail a join request if it is still active - at the head of the pending queue. */ static void process_join_error(struct mcast_group *group, int status) { struct mcast_member *member; int ret; spin_lock_irq(&group->lock); member = list_entry(group->pending_list.next, struct mcast_member, list); if (group->last_join == member) { refcount_inc(&member->refcount); list_del_init(&member->list); spin_unlock_irq(&group->lock); ret = member->multicast.callback(status, &member->multicast); deref_member(member); if (ret) ib_sa_free_multicast(&member->multicast); } else spin_unlock_irq(&group->lock); } static void join_handler(int status, struct ib_sa_mcmember_rec *rec, void *context) { struct mcast_group *group = context; u16 pkey_index = MCAST_INVALID_PKEY_INDEX; if (status) process_join_error(group, status); else { int mgids_changed, is_mgid0; if (ib_find_pkey(group->port->dev->device, group->port->port_num, be16_to_cpu(rec->pkey), &pkey_index)) pkey_index = MCAST_INVALID_PKEY_INDEX; spin_lock_irq(&group->port->lock); if (group->state == MCAST_BUSY && group->pkey_index == MCAST_INVALID_PKEY_INDEX) group->pkey_index = pkey_index; mgids_changed = memcmp(&rec->mgid, &group->rec.mgid, sizeof(group->rec.mgid)); group->rec = *rec; if (mgids_changed) { rb_erase(&group->node, &group->port->table); is_mgid0 = !memcmp(&mgid0, &group->rec.mgid, sizeof(mgid0)); mcast_insert(group->port, group, is_mgid0); } spin_unlock_irq(&group->port->lock); } mcast_work_handler(&group->work); } static void leave_handler(int status, struct ib_sa_mcmember_rec *rec, void *context) { struct mcast_group *group = context; if (status && group->retries > 0 && !send_leave(group, group->leave_state)) group->retries--; else mcast_work_handler(&group->work); } static struct mcast_group *acquire_group(struct mcast_port *port, union ib_gid *mgid, gfp_t gfp_mask) { struct mcast_group *group, *cur_group; unsigned long flags; int is_mgid0; is_mgid0 = !memcmp(&mgid0, mgid, sizeof mgid0); if (!is_mgid0) { spin_lock_irqsave(&port->lock, flags); group = mcast_find(port, mgid); if (group) goto found; spin_unlock_irqrestore(&port->lock, flags); } group = kzalloc(sizeof *group, gfp_mask); if (!group) return NULL; group->retries = 3; group->port = port; group->rec.mgid = *mgid; group->pkey_index = MCAST_INVALID_PKEY_INDEX; INIT_LIST_HEAD(&group->pending_list); INIT_LIST_HEAD(&group->active_list); INIT_WORK(&group->work, mcast_work_handler); spin_lock_init(&group->lock); spin_lock_irqsave(&port->lock, flags); cur_group = mcast_insert(port, group, is_mgid0); if (cur_group) { kfree(group); group = cur_group; } else refcount_inc(&port->refcount); found: atomic_inc(&group->refcount); spin_unlock_irqrestore(&port->lock, flags); return group; } /* * We serialize all join requests to a single group to make our lives much * easier. Otherwise, two users could try to join the same group * simultaneously, with different configurations, one could leave while the * join is in progress, etc., which makes locking around error recovery * difficult. */ struct ib_sa_multicast * ib_sa_join_multicast(struct ib_sa_client *client, struct ib_device *device, u32 port_num, struct ib_sa_mcmember_rec *rec, ib_sa_comp_mask comp_mask, gfp_t gfp_mask, int (*callback)(int status, struct ib_sa_multicast *multicast), void *context) { struct mcast_device *dev; struct mcast_member *member; struct ib_sa_multicast *multicast; int ret; dev = ib_get_client_data(device, &mcast_client); if (!dev) return ERR_PTR(-ENODEV); member = kmalloc(sizeof *member, gfp_mask); if (!member) return ERR_PTR(-ENOMEM); ib_sa_client_get(client); member->client = client; member->multicast.rec = *rec; member->multicast.comp_mask = comp_mask; member->multicast.callback = callback; member->multicast.context = context; init_completion(&member->comp); refcount_set(&member->refcount, 1); member->state = MCAST_JOINING; member->group = acquire_group(&dev->port[port_num - dev->start_port], &rec->mgid, gfp_mask); if (!member->group) { ret = -ENOMEM; goto err; } /* * The user will get the multicast structure in their callback. They * could then free the multicast structure before we can return from * this routine. So we save the pointer to return before queuing * any callback. */ multicast = &member->multicast; queue_join(member); return multicast; err: ib_sa_client_put(client); kfree(member); return ERR_PTR(ret); } EXPORT_SYMBOL(ib_sa_join_multicast); void ib_sa_free_multicast(struct ib_sa_multicast *multicast) { struct mcast_member *member; struct mcast_group *group; member = container_of(multicast, struct mcast_member, multicast); group = member->group; spin_lock_irq(&group->lock); if (member->state == MCAST_MEMBER) adjust_membership(group, multicast->rec.join_state, -1); list_del_init(&member->list); if (group->state == MCAST_IDLE) { group->state = MCAST_BUSY; spin_unlock_irq(&group->lock); /* Continue to hold reference on group until callback */ queue_work(mcast_wq, &group->work); } else { spin_unlock_irq(&group->lock); release_group(group); } deref_member(member); wait_for_completion(&member->comp); ib_sa_client_put(member->client); kfree(member); } EXPORT_SYMBOL(ib_sa_free_multicast); int ib_sa_get_mcmember_rec(struct ib_device *device, u32 port_num, union ib_gid *mgid, struct ib_sa_mcmember_rec *rec) { struct mcast_device *dev; struct mcast_port *port; struct mcast_group *group; unsigned long flags; int ret = 0; dev = ib_get_client_data(device, &mcast_client); if (!dev) return -ENODEV; port = &dev->port[port_num - dev->start_port]; spin_lock_irqsave(&port->lock, flags); group = mcast_find(port, mgid); if (group) *rec = group->rec; else ret = -EADDRNOTAVAIL; spin_unlock_irqrestore(&port->lock, flags); return ret; } EXPORT_SYMBOL(ib_sa_get_mcmember_rec); /** * ib_init_ah_from_mcmember - Initialize AH attribute from multicast * member record and gid of the device. * @device: RDMA device * @port_num: Port of the rdma device to consider * @rec: Multicast member record to use * @ndev: Optional netdevice, applicable only for RoCE * @gid_type: GID type to consider * @ah_attr: AH attribute to fillup on successful completion * * ib_init_ah_from_mcmember() initializes AH attribute based on multicast * member record and other device properties. On success the caller is * responsible to call rdma_destroy_ah_attr on the ah_attr. Returns 0 on * success or appropriate error code. * */ int ib_init_ah_from_mcmember(struct ib_device *device, u32 port_num, struct ib_sa_mcmember_rec *rec, struct net_device *ndev, enum ib_gid_type gid_type, struct rdma_ah_attr *ah_attr) { const struct ib_gid_attr *sgid_attr; /* GID table is not based on the netdevice for IB link layer, * so ignore ndev during search. */ if (rdma_protocol_ib(device, port_num)) ndev = NULL; else if (!rdma_protocol_roce(device, port_num)) return -EINVAL; sgid_attr = rdma_find_gid_by_port(device, &rec->port_gid, gid_type, port_num, ndev); if (IS_ERR(sgid_attr)) return PTR_ERR(sgid_attr); memset(ah_attr, 0, sizeof(*ah_attr)); ah_attr->type = rdma_ah_find_type(device, port_num); rdma_ah_set_dlid(ah_attr, be16_to_cpu(rec->mlid)); rdma_ah_set_sl(ah_attr, rec->sl); rdma_ah_set_port_num(ah_attr, port_num); rdma_ah_set_static_rate(ah_attr, rec->rate); rdma_move_grh_sgid_attr(ah_attr, &rec->mgid, be32_to_cpu(rec->flow_label), rec->hop_limit, rec->traffic_class, sgid_attr); return 0; } EXPORT_SYMBOL(ib_init_ah_from_mcmember); static void mcast_groups_event(struct mcast_port *port, enum mcast_group_state state) { struct mcast_group *group; struct rb_node *node; unsigned long flags; spin_lock_irqsave(&port->lock, flags); for (node = rb_first(&port->table); node; node = rb_next(node)) { group = rb_entry(node, struct mcast_group, node); spin_lock(&group->lock); if (group->state == MCAST_IDLE) { atomic_inc(&group->refcount); queue_work(mcast_wq, &group->work); } if (group->state != MCAST_GROUP_ERROR) group->state = state; spin_unlock(&group->lock); } spin_unlock_irqrestore(&port->lock, flags); } static void mcast_event_handler(struct ib_event_handler *handler, struct ib_event *event) { struct mcast_device *dev; int index; dev = container_of(handler, struct mcast_device, event_handler); if (!rdma_cap_ib_mcast(dev->device, event->element.port_num)) return; index = event->element.port_num - dev->start_port; switch (event->event) { case IB_EVENT_PORT_ERR: case IB_EVENT_LID_CHANGE: case IB_EVENT_CLIENT_REREGISTER: mcast_groups_event(&dev->port[index], MCAST_GROUP_ERROR); break; case IB_EVENT_PKEY_CHANGE: mcast_groups_event(&dev->port[index], MCAST_PKEY_EVENT); break; default: break; } } static int mcast_add_one(struct ib_device *device) { struct mcast_device *dev; struct mcast_port *port; int i; int count = 0; dev = kmalloc(struct_size(dev, port, device->phys_port_cnt), GFP_KERNEL); if (!dev) return -ENOMEM; dev->start_port = rdma_start_port(device); dev->end_port = rdma_end_port(device); for (i = 0; i <= dev->end_port - dev->start_port; i++) { if (!rdma_cap_ib_mcast(device, dev->start_port + i)) continue; port = &dev->port[i]; port->dev = dev; port->port_num = dev->start_port + i; spin_lock_init(&port->lock); port->table = RB_ROOT; init_completion(&port->comp); refcount_set(&port->refcount, 1); ++count; } if (!count) { kfree(dev); return -EOPNOTSUPP; } dev->device = device; ib_set_client_data(device, &mcast_client, dev); INIT_IB_EVENT_HANDLER(&dev->event_handler, device, mcast_event_handler); ib_register_event_handler(&dev->event_handler); return 0; } static void mcast_remove_one(struct ib_device *device, void *client_data) { struct mcast_device *dev = client_data; struct mcast_port *port; int i; ib_unregister_event_handler(&dev->event_handler); flush_workqueue(mcast_wq); for (i = 0; i <= dev->end_port - dev->start_port; i++) { if (rdma_cap_ib_mcast(device, dev->start_port + i)) { port = &dev->port[i]; deref_port(port); wait_for_completion(&port->comp); } } kfree(dev); } int mcast_init(void) { int ret; mcast_wq = alloc_ordered_workqueue("ib_mcast", WQ_MEM_RECLAIM); if (!mcast_wq) return -ENOMEM; ib_sa_register_client(&sa_client); ret = ib_register_client(&mcast_client); if (ret) goto err; return 0; err: ib_sa_unregister_client(&sa_client); destroy_workqueue(mcast_wq); return ret; } void mcast_cleanup(void) { ib_unregister_client(&mcast_client); ib_sa_unregister_client(&sa_client); destroy_workqueue(mcast_wq); } |
| 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * crc16.c */ #include <linux/types.h> #include <linux/module.h> #include <linux/crc16.h> /** CRC table for the CRC-16. The poly is 0x8005 (x^16 + x^15 + x^2 + 1) */ u16 const crc16_table[256] = { 0x0000, 0xC0C1, 0xC181, 0x0140, 0xC301, 0x03C0, 0x0280, 0xC241, 0xC601, 0x06C0, 0x0780, 0xC741, 0x0500, 0xC5C1, 0xC481, 0x0440, 0xCC01, 0x0CC0, 0x0D80, 0xCD41, 0x0F00, 0xCFC1, 0xCE81, 0x0E40, 0x0A00, 0xCAC1, 0xCB81, 0x0B40, 0xC901, 0x09C0, 0x0880, 0xC841, 0xD801, 0x18C0, 0x1980, 0xD941, 0x1B00, 0xDBC1, 0xDA81, 0x1A40, 0x1E00, 0xDEC1, 0xDF81, 0x1F40, 0xDD01, 0x1DC0, 0x1C80, 0xDC41, 0x1400, 0xD4C1, 0xD581, 0x1540, 0xD701, 0x17C0, 0x1680, 0xD641, 0xD201, 0x12C0, 0x1380, 0xD341, 0x1100, 0xD1C1, 0xD081, 0x1040, 0xF001, 0x30C0, 0x3180, 0xF141, 0x3300, 0xF3C1, 0xF281, 0x3240, 0x3600, 0xF6C1, 0xF781, 0x3740, 0xF501, 0x35C0, 0x3480, 0xF441, 0x3C00, 0xFCC1, 0xFD81, 0x3D40, 0xFF01, 0x3FC0, 0x3E80, 0xFE41, 0xFA01, 0x3AC0, 0x3B80, 0xFB41, 0x3900, 0xF9C1, 0xF881, 0x3840, 0x2800, 0xE8C1, 0xE981, 0x2940, 0xEB01, 0x2BC0, 0x2A80, 0xEA41, 0xEE01, 0x2EC0, 0x2F80, 0xEF41, 0x2D00, 0xEDC1, 0xEC81, 0x2C40, 0xE401, 0x24C0, 0x2580, 0xE541, 0x2700, 0xE7C1, 0xE681, 0x2640, 0x2200, 0xE2C1, 0xE381, 0x2340, 0xE101, 0x21C0, 0x2080, 0xE041, 0xA001, 0x60C0, 0x6180, 0xA141, 0x6300, 0xA3C1, 0xA281, 0x6240, 0x6600, 0xA6C1, 0xA781, 0x6740, 0xA501, 0x65C0, 0x6480, 0xA441, 0x6C00, 0xACC1, 0xAD81, 0x6D40, 0xAF01, 0x6FC0, 0x6E80, 0xAE41, 0xAA01, 0x6AC0, 0x6B80, 0xAB41, 0x6900, 0xA9C1, 0xA881, 0x6840, 0x7800, 0xB8C1, 0xB981, 0x7940, 0xBB01, 0x7BC0, 0x7A80, 0xBA41, 0xBE01, 0x7EC0, 0x7F80, 0xBF41, 0x7D00, 0xBDC1, 0xBC81, 0x7C40, 0xB401, 0x74C0, 0x7580, 0xB541, 0x7700, 0xB7C1, 0xB681, 0x7640, 0x7200, 0xB2C1, 0xB381, 0x7340, 0xB101, 0x71C0, 0x7080, 0xB041, 0x5000, 0x90C1, 0x9181, 0x5140, 0x9301, 0x53C0, 0x5280, 0x9241, 0x9601, 0x56C0, 0x5780, 0x9741, 0x5500, 0x95C1, 0x9481, 0x5440, 0x9C01, 0x5CC0, 0x5D80, 0x9D41, 0x5F00, 0x9FC1, 0x9E81, 0x5E40, 0x5A00, 0x9AC1, 0x9B81, 0x5B40, 0x9901, 0x59C0, 0x5880, 0x9841, 0x8801, 0x48C0, 0x4980, 0x8941, 0x4B00, 0x8BC1, 0x8A81, 0x4A40, 0x4E00, 0x8EC1, 0x8F81, 0x4F40, 0x8D01, 0x4DC0, 0x4C80, 0x8C41, 0x4400, 0x84C1, 0x8581, 0x4540, 0x8701, 0x47C0, 0x4680, 0x8641, 0x8201, 0x42C0, 0x4380, 0x8341, 0x4100, 0x81C1, 0x8081, 0x4040 }; EXPORT_SYMBOL(crc16_table); /** * crc16 - compute the CRC-16 for the data buffer * @crc: previous CRC value * @buffer: data pointer * @len: number of bytes in the buffer * * Returns the updated CRC value. */ u16 crc16(u16 crc, u8 const *buffer, size_t len) { while (len--) crc = crc16_byte(crc, *buffer++); return crc; } EXPORT_SYMBOL(crc16); MODULE_DESCRIPTION("CRC16 calculations"); MODULE_LICENSE("GPL"); |
| 4 2 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Update: The Berkeley copyright was changed, and the change * is retroactive to all "true" BSD software (ie everything * from UCB as opposed to other peoples code that just carried * the same license). The new copyright doesn't clash with the * GPL, so the module-only restriction has been removed.. */ /* Because this code is derived from the 4.3BSD compress source: * * Copyright (c) 1985, 1986 The Regents of the University of California. * All rights reserved. * * This code is derived from software contributed to Berkeley by * James A. Woods, derived from original work by Spencer Thomas * and Joseph Orost. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ /* * This version is for use with contiguous buffers on Linux-derived systems. * * ==FILEVERSION 20000226== * * NOTE TO MAINTAINERS: * If you modify this file at all, please set the number above to the * date of the modification as YYMMDD (year month day). * bsd_comp.c is shipped with a PPP distribution as well as with * the kernel; if everyone increases the FILEVERSION number above, * then scripts can do the right thing when deciding whether to * install a new bsd_comp.c file. Don't change the format of that * line otherwise, so the installation script can recognize it. * * From: bsd_comp.c,v 1.3 1994/12/08 01:59:58 paulus Exp */ #include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/string.h> #include <linux/ppp_defs.h> #undef PACKETPTR #define PACKETPTR 1 #include <linux/ppp-comp.h> #undef PACKETPTR #include <asm/byteorder.h> /* * PPP "BSD compress" compression * The differences between this compression and the classic BSD LZW * source are obvious from the requirement that the classic code worked * with files while this handles arbitrarily long streams that * are broken into packets. They are: * * When the code size expands, a block of junk is not emitted by * the compressor and not expected by the decompressor. * * New codes are not necessarily assigned every time an old * code is output by the compressor. This is because a packet * end forces a code to be emitted, but does not imply that a * new sequence has been seen. * * The compression ratio is checked at the first end of a packet * after the appropriate gap. Besides simplifying and speeding * things up, this makes it more likely that the transmitter * and receiver will agree when the dictionary is cleared when * compression is not going well. */ /* * Macros to extract protocol version and number of bits * from the third byte of the BSD Compress CCP configuration option. */ #define BSD_VERSION(x) ((x) >> 5) #define BSD_NBITS(x) ((x) & 0x1F) #define BSD_CURRENT_VERSION 1 /* * A dictionary for doing BSD compress. */ struct bsd_dict { union { /* hash value */ unsigned long fcode; struct { #if defined(__LITTLE_ENDIAN) /* Little endian order */ unsigned short prefix; /* preceding code */ unsigned char suffix; /* last character of new code */ unsigned char pad; #elif defined(__BIG_ENDIAN) /* Big endian order */ unsigned char pad; unsigned char suffix; /* last character of new code */ unsigned short prefix; /* preceding code */ #else #error Endianness not defined... #endif } hs; } f; unsigned short codem1; /* output of hash table -1 */ unsigned short cptr; /* map code to hash table entry */ }; struct bsd_db { int totlen; /* length of this structure */ unsigned int hsize; /* size of the hash table */ unsigned char hshift; /* used in hash function */ unsigned char n_bits; /* current bits/code */ unsigned char maxbits; /* maximum bits/code */ unsigned char debug; /* non-zero if debug desired */ unsigned char unit; /* ppp unit number */ unsigned short seqno; /* sequence # of next packet */ unsigned int mru; /* size of receive (decompress) bufr */ unsigned int maxmaxcode; /* largest valid code */ unsigned int max_ent; /* largest code in use */ unsigned int in_count; /* uncompressed bytes, aged */ unsigned int bytes_out; /* compressed bytes, aged */ unsigned int ratio; /* recent compression ratio */ unsigned int checkpoint; /* when to next check the ratio */ unsigned int clear_count; /* times dictionary cleared */ unsigned int incomp_count; /* incompressible packets */ unsigned int incomp_bytes; /* incompressible bytes */ unsigned int uncomp_count; /* uncompressed packets */ unsigned int uncomp_bytes; /* uncompressed bytes */ unsigned int comp_count; /* compressed packets */ unsigned int comp_bytes; /* compressed bytes */ unsigned short *lens; /* array of lengths of codes */ struct bsd_dict *dict; /* dictionary */ }; #define BSD_OVHD 2 /* BSD compress overhead/packet */ #define MIN_BSD_BITS 9 #define BSD_INIT_BITS MIN_BSD_BITS #define MAX_BSD_BITS 15 static void bsd_free (void *state); static void *bsd_alloc(unsigned char *options, int opt_len, int decomp); static void *bsd_comp_alloc (unsigned char *options, int opt_len); static void *bsd_decomp_alloc (unsigned char *options, int opt_len); static int bsd_init (void *db, unsigned char *options, int opt_len, int unit, int debug, int decomp); static int bsd_comp_init (void *state, unsigned char *options, int opt_len, int unit, int opthdr, int debug); static int bsd_decomp_init (void *state, unsigned char *options, int opt_len, int unit, int opthdr, int mru, int debug); static void bsd_reset (void *state); static void bsd_comp_stats (void *state, struct compstat *stats); static int bsd_compress (void *state, unsigned char *rptr, unsigned char *obuf, int isize, int osize); static void bsd_incomp (void *state, unsigned char *ibuf, int icnt); static int bsd_decompress (void *state, unsigned char *ibuf, int isize, unsigned char *obuf, int osize); /* These are in ppp_generic.c */ extern int ppp_register_compressor (struct compressor *cp); extern void ppp_unregister_compressor (struct compressor *cp); /* * the next two codes should not be changed lightly, as they must not * lie within the contiguous general code space. */ #define CLEAR 256 /* table clear output code */ #define FIRST 257 /* first free entry */ #define LAST 255 #define MAXCODE(b) ((1 << (b)) - 1) #define BADCODEM1 MAXCODE(MAX_BSD_BITS) #define BSD_HASH(prefix,suffix,hshift) ((((unsigned long)(suffix))<<(hshift)) \ ^ (unsigned long)(prefix)) #define BSD_KEY(prefix,suffix) ((((unsigned long)(suffix)) << 16) \ + (unsigned long)(prefix)) #define CHECK_GAP 10000 /* Ratio check interval */ #define RATIO_SCALE_LOG 8 #define RATIO_SCALE (1<<RATIO_SCALE_LOG) #define RATIO_MAX (0x7fffffff>>RATIO_SCALE_LOG) /* * clear the dictionary */ static void bsd_clear(struct bsd_db *db) { db->clear_count++; db->max_ent = FIRST-1; db->n_bits = BSD_INIT_BITS; db->bytes_out = 0; db->in_count = 0; db->ratio = 0; db->checkpoint = CHECK_GAP; } /* * If the dictionary is full, then see if it is time to reset it. * * Compute the compression ratio using fixed-point arithmetic * with 8 fractional bits. * * Since we have an infinite stream instead of a single file, * watch only the local compression ratio. * * Since both peers must reset the dictionary at the same time even in * the absence of CLEAR codes (while packets are incompressible), they * must compute the same ratio. */ static int bsd_check (struct bsd_db *db) /* 1=output CLEAR */ { unsigned int new_ratio; if (db->in_count >= db->checkpoint) { /* age the ratio by limiting the size of the counts */ if (db->in_count >= RATIO_MAX || db->bytes_out >= RATIO_MAX) { db->in_count -= (db->in_count >> 2); db->bytes_out -= (db->bytes_out >> 2); } db->checkpoint = db->in_count + CHECK_GAP; if (db->max_ent >= db->maxmaxcode) { /* Reset the dictionary only if the ratio is worse, * or if it looks as if it has been poisoned * by incompressible data. * * This does not overflow, because * db->in_count <= RATIO_MAX. */ new_ratio = db->in_count << RATIO_SCALE_LOG; if (db->bytes_out != 0) { new_ratio /= db->bytes_out; } if (new_ratio < db->ratio || new_ratio < 1 * RATIO_SCALE) { bsd_clear (db); return 1; } db->ratio = new_ratio; } } return 0; } /* * Return statistics. */ static void bsd_comp_stats (void *state, struct compstat *stats) { struct bsd_db *db = (struct bsd_db *) state; stats->unc_bytes = db->uncomp_bytes; stats->unc_packets = db->uncomp_count; stats->comp_bytes = db->comp_bytes; stats->comp_packets = db->comp_count; stats->inc_bytes = db->incomp_bytes; stats->inc_packets = db->incomp_count; stats->in_count = db->in_count; stats->bytes_out = db->bytes_out; } /* * Reset state, as on a CCP ResetReq. */ static void bsd_reset (void *state) { struct bsd_db *db = (struct bsd_db *) state; bsd_clear(db); db->seqno = 0; db->clear_count = 0; } /* * Release the compression structure */ static void bsd_free (void *state) { struct bsd_db *db = state; if (!db) return; /* * Release the dictionary */ vfree(db->dict); db->dict = NULL; /* * Release the string buffer */ vfree(db->lens); db->lens = NULL; /* * Finally release the structure itself. */ kfree(db); } /* * Allocate space for a (de) compressor. */ static void *bsd_alloc (unsigned char *options, int opt_len, int decomp) { int bits; unsigned int hsize, hshift, maxmaxcode; struct bsd_db *db; if (opt_len != 3 || options[0] != CI_BSD_COMPRESS || options[1] != 3 || BSD_VERSION(options[2]) != BSD_CURRENT_VERSION) { return NULL; } bits = BSD_NBITS(options[2]); switch (bits) { case 9: /* needs 82152 for both directions */ case 10: /* needs 84144 */ case 11: /* needs 88240 */ case 12: /* needs 96432 */ hsize = 5003; hshift = 4; break; case 13: /* needs 176784 */ hsize = 9001; hshift = 5; break; case 14: /* needs 353744 */ hsize = 18013; hshift = 6; break; case 15: /* needs 691440 */ hsize = 35023; hshift = 7; break; case 16: /* needs 1366160--far too much, */ /* hsize = 69001; */ /* and 69001 is too big for cptr */ /* hshift = 8; */ /* in struct bsd_db */ /* break; */ default: return NULL; } /* * Allocate the main control structure for this instance. */ maxmaxcode = MAXCODE(bits); db = kzalloc(sizeof (struct bsd_db), GFP_KERNEL); if (!db) { return NULL; } /* * Allocate space for the dictionary. This may be more than one page in * length. */ db->dict = vmalloc(array_size(hsize, sizeof(struct bsd_dict))); if (!db->dict) { bsd_free (db); return NULL; } /* * If this is the compression buffer then there is no length data. */ if (!decomp) { db->lens = NULL; } /* * For decompression, the length information is needed as well. */ else { db->lens = vmalloc(array_size(sizeof(db->lens[0]), (maxmaxcode + 1))); if (!db->lens) { bsd_free (db); return NULL; } } /* * Initialize the data information for the compression code */ db->totlen = sizeof (struct bsd_db) + (sizeof (struct bsd_dict) * hsize); db->hsize = hsize; db->hshift = hshift; db->maxmaxcode = maxmaxcode; db->maxbits = bits; return (void *) db; } static void *bsd_comp_alloc (unsigned char *options, int opt_len) { return bsd_alloc (options, opt_len, 0); } static void *bsd_decomp_alloc (unsigned char *options, int opt_len) { return bsd_alloc (options, opt_len, 1); } /* * Initialize the database. */ static int bsd_init (void *state, unsigned char *options, int opt_len, int unit, int debug, int decomp) { struct bsd_db *db = state; int indx; if ((opt_len != 3) || (options[0] != CI_BSD_COMPRESS) || (options[1] != 3) || (BSD_VERSION(options[2]) != BSD_CURRENT_VERSION) || (BSD_NBITS(options[2]) != db->maxbits) || (decomp && db->lens == NULL)) { return 0; } if (decomp) { indx = LAST; do { db->lens[indx] = 1; } while (indx-- > 0); } indx = db->hsize; while (indx-- != 0) { db->dict[indx].codem1 = BADCODEM1; db->dict[indx].cptr = 0; } db->unit = unit; db->mru = 0; #ifndef DEBUG if (debug) #endif db->debug = 1; bsd_reset(db); return 1; } static int bsd_comp_init (void *state, unsigned char *options, int opt_len, int unit, int opthdr, int debug) { return bsd_init (state, options, opt_len, unit, debug, 0); } static int bsd_decomp_init (void *state, unsigned char *options, int opt_len, int unit, int opthdr, int mru, int debug) { return bsd_init (state, options, opt_len, unit, debug, 1); } /* * Obtain pointers to the various structures in the compression tables */ #define dict_ptrx(p,idx) &(p->dict[idx]) #define lens_ptrx(p,idx) &(p->lens[idx]) #ifdef DEBUG static unsigned short *lens_ptr(struct bsd_db *db, int idx) { if ((unsigned int) idx > (unsigned int) db->maxmaxcode) { printk ("<9>ppp: lens_ptr(%d) > max\n", idx); idx = 0; } return lens_ptrx (db, idx); } static struct bsd_dict *dict_ptr(struct bsd_db *db, int idx) { if ((unsigned int) idx >= (unsigned int) db->hsize) { printk ("<9>ppp: dict_ptr(%d) > max\n", idx); idx = 0; } return dict_ptrx (db, idx); } #else #define lens_ptr(db,idx) lens_ptrx(db,idx) #define dict_ptr(db,idx) dict_ptrx(db,idx) #endif /* * compress a packet * * The result of this function is the size of the compressed * packet. A zero is returned if the packet was not compressed * for some reason, such as the size being larger than uncompressed. * * One change from the BSD compress command is that when the * code size expands, we do not output a bunch of padding. */ static int bsd_compress (void *state, unsigned char *rptr, unsigned char *obuf, int isize, int osize) { struct bsd_db *db; int hshift; unsigned int max_ent; unsigned int n_bits; unsigned int bitno; unsigned long accm; int ent; unsigned long fcode; struct bsd_dict *dictp; unsigned char c; int hval; int disp; int ilen; int mxcode; unsigned char *wptr; int olen; #define PUTBYTE(v) \ { \ ++olen; \ if (wptr) \ { \ *wptr++ = (unsigned char) (v); \ if (olen >= osize) \ { \ wptr = NULL; \ } \ } \ } #define OUTPUT(ent) \ { \ bitno -= n_bits; \ accm |= ((ent) << bitno); \ do \ { \ PUTBYTE(accm >> 24); \ accm <<= 8; \ bitno += 8; \ } \ while (bitno <= 24); \ } /* * If the protocol is not in the range we're interested in, * just return without compressing the packet. If it is, * the protocol becomes the first byte to compress. */ ent = PPP_PROTOCOL(rptr); if (ent < 0x21 || ent > 0xf9) { return 0; } db = (struct bsd_db *) state; hshift = db->hshift; max_ent = db->max_ent; n_bits = db->n_bits; bitno = 32; accm = 0; mxcode = MAXCODE (n_bits); /* Initialize the output pointers */ wptr = obuf; olen = PPP_HDRLEN + BSD_OVHD; if (osize > isize) { osize = isize; } /* This is the PPP header information */ if (wptr) { *wptr++ = PPP_ADDRESS(rptr); *wptr++ = PPP_CONTROL(rptr); *wptr++ = 0; *wptr++ = PPP_COMP; *wptr++ = db->seqno >> 8; *wptr++ = db->seqno; } /* Skip the input header */ rptr += PPP_HDRLEN; isize -= PPP_HDRLEN; ilen = ++isize; /* Low byte of protocol is counted as input */ while (--ilen > 0) { c = *rptr++; fcode = BSD_KEY (ent, c); hval = BSD_HASH (ent, c, hshift); dictp = dict_ptr (db, hval); /* Validate and then check the entry. */ if (dictp->codem1 >= max_ent) { goto nomatch; } if (dictp->f.fcode == fcode) { ent = dictp->codem1 + 1; continue; /* found (prefix,suffix) */ } /* continue probing until a match or invalid entry */ disp = (hval == 0) ? 1 : hval; do { hval += disp; if (hval >= db->hsize) { hval -= db->hsize; } dictp = dict_ptr (db, hval); if (dictp->codem1 >= max_ent) { goto nomatch; } } while (dictp->f.fcode != fcode); ent = dictp->codem1 + 1; /* finally found (prefix,suffix) */ continue; nomatch: OUTPUT(ent); /* output the prefix */ /* code -> hashtable */ if (max_ent < db->maxmaxcode) { struct bsd_dict *dictp2; struct bsd_dict *dictp3; int indx; /* expand code size if needed */ if (max_ent >= mxcode) { db->n_bits = ++n_bits; mxcode = MAXCODE (n_bits); } /* Invalidate old hash table entry using * this code, and then take it over. */ dictp2 = dict_ptr (db, max_ent + 1); indx = dictp2->cptr; dictp3 = dict_ptr (db, indx); if (dictp3->codem1 == max_ent) { dictp3->codem1 = BADCODEM1; } dictp2->cptr = hval; dictp->codem1 = max_ent; dictp->f.fcode = fcode; db->max_ent = ++max_ent; if (db->lens) { unsigned short *len1 = lens_ptr (db, max_ent); unsigned short *len2 = lens_ptr (db, ent); *len1 = *len2 + 1; } } ent = c; } OUTPUT(ent); /* output the last code */ db->bytes_out += olen - PPP_HDRLEN - BSD_OVHD; db->uncomp_bytes += isize; db->in_count += isize; ++db->uncomp_count; ++db->seqno; if (bitno < 32) { ++db->bytes_out; /* must be set before calling bsd_check */ } /* * Generate the clear command if needed */ if (bsd_check(db)) { OUTPUT (CLEAR); } /* * Pad dribble bits of last code with ones. * Do not emit a completely useless byte of ones. */ if (bitno != 32) { PUTBYTE((accm | (0xff << (bitno-8))) >> 24); } /* * Increase code size if we would have without the packet * boundary because the decompressor will do so. */ if (max_ent >= mxcode && max_ent < db->maxmaxcode) { db->n_bits++; } /* If output length is too large then this is an incomplete frame. */ if (wptr == NULL) { ++db->incomp_count; db->incomp_bytes += isize; olen = 0; } else /* Count the number of compressed frames */ { ++db->comp_count; db->comp_bytes += olen; } /* Return the resulting output length */ return olen; #undef OUTPUT #undef PUTBYTE } /* * Update the "BSD Compress" dictionary on the receiver for * incompressible data by pretending to compress the incoming data. */ static void bsd_incomp (void *state, unsigned char *ibuf, int icnt) { (void) bsd_compress (state, ibuf, (char *) 0, icnt, 0); } /* * Decompress "BSD Compress". * * Because of patent problems, we return DECOMP_ERROR for errors * found by inspecting the input data and for system problems, but * DECOMP_FATALERROR for any errors which could possibly be said to * be being detected "after" decompression. For DECOMP_ERROR, * we can issue a CCP reset-request; for DECOMP_FATALERROR, we may be * infringing a patent of Motorola's if we do, so we take CCP down * instead. * * Given that the frame has the correct sequence number and a good FCS, * errors such as invalid codes in the input most likely indicate a * bug, so we return DECOMP_FATALERROR for them in order to turn off * compression, even though they are detected by inspecting the input. */ static int bsd_decompress (void *state, unsigned char *ibuf, int isize, unsigned char *obuf, int osize) { struct bsd_db *db; unsigned int max_ent; unsigned long accm; unsigned int bitno; /* 1st valid bit in accm */ unsigned int n_bits; unsigned int tgtbitno; /* bitno when we have a code */ struct bsd_dict *dictp; int explen; int seq; unsigned int incode; unsigned int oldcode; unsigned int finchar; unsigned char *p; unsigned char *wptr; int adrs; int ctrl; int ilen; int codelen; int extra; db = (struct bsd_db *) state; max_ent = db->max_ent; accm = 0; bitno = 32; /* 1st valid bit in accm */ n_bits = db->n_bits; tgtbitno = 32 - n_bits; /* bitno when we have a code */ /* * Save the address/control from the PPP header * and then get the sequence number. */ adrs = PPP_ADDRESS (ibuf); ctrl = PPP_CONTROL (ibuf); seq = (ibuf[4] << 8) + ibuf[5]; ibuf += (PPP_HDRLEN + 2); ilen = isize - (PPP_HDRLEN + 2); /* * Check the sequence number and give up if it differs from * the value we're expecting. */ if (seq != db->seqno) { if (db->debug) { printk("bsd_decomp%d: bad sequence # %d, expected %d\n", db->unit, seq, db->seqno - 1); } return DECOMP_ERROR; } ++db->seqno; db->bytes_out += ilen; /* * Fill in the ppp header, but not the last byte of the protocol * (that comes from the decompressed data). */ wptr = obuf; *wptr++ = adrs; *wptr++ = ctrl; *wptr++ = 0; oldcode = CLEAR; explen = 3; /* * Keep the checkpoint correctly so that incompressible packets * clear the dictionary at the proper times. */ for (;;) { if (ilen-- <= 0) { db->in_count += (explen - 3); /* don't count the header */ break; } /* * Accumulate bytes until we have a complete code. * Then get the next code, relying on the 32-bit, * unsigned accm to mask the result. */ bitno -= 8; accm |= *ibuf++ << bitno; if (tgtbitno < bitno) { continue; } incode = accm >> tgtbitno; accm <<= n_bits; bitno += n_bits; /* * The dictionary must only be cleared at the end of a packet. */ if (incode == CLEAR) { if (ilen > 0) { if (db->debug) { printk("bsd_decomp%d: bad CLEAR\n", db->unit); } return DECOMP_FATALERROR; /* probably a bug */ } bsd_clear(db); break; } if ((incode > max_ent + 2) || (incode > db->maxmaxcode) || (incode > max_ent && oldcode == CLEAR)) { if (db->debug) { printk("bsd_decomp%d: bad code 0x%x oldcode=0x%x ", db->unit, incode, oldcode); printk("max_ent=0x%x explen=%d seqno=%d\n", max_ent, explen, db->seqno); } return DECOMP_FATALERROR; /* probably a bug */ } /* Special case for KwKwK string. */ if (incode > max_ent) { finchar = oldcode; extra = 1; } else { finchar = incode; extra = 0; } codelen = *(lens_ptr (db, finchar)); explen += codelen + extra; if (explen > osize) { if (db->debug) { printk("bsd_decomp%d: ran out of mru\n", db->unit); #ifdef DEBUG printk(" len=%d, finchar=0x%x, codelen=%d, explen=%d\n", ilen, finchar, codelen, explen); #endif } return DECOMP_FATALERROR; } /* * Decode this code and install it in the decompressed buffer. */ wptr += codelen; p = wptr; while (finchar > LAST) { struct bsd_dict *dictp2 = dict_ptr (db, finchar); dictp = dict_ptr (db, dictp2->cptr); #ifdef DEBUG if (--codelen <= 0 || dictp->codem1 != finchar-1) { if (codelen <= 0) { printk("bsd_decomp%d: fell off end of chain ", db->unit); printk("0x%x at 0x%x by 0x%x, max_ent=0x%x\n", incode, finchar, dictp2->cptr, max_ent); } else { if (dictp->codem1 != finchar-1) { printk("bsd_decomp%d: bad code chain 0x%x " "finchar=0x%x ", db->unit, incode, finchar); printk("oldcode=0x%x cptr=0x%x codem1=0x%x\n", oldcode, dictp2->cptr, dictp->codem1); } } return DECOMP_FATALERROR; } #endif *--p = dictp->f.hs.suffix; finchar = dictp->f.hs.prefix; } *--p = finchar; #ifdef DEBUG if (--codelen != 0) { printk("bsd_decomp%d: short by %d after code 0x%x, max_ent=0x%x\n", db->unit, codelen, incode, max_ent); } #endif if (extra) /* the KwKwK case again */ { *wptr++ = finchar; } /* * If not first code in a packet, and * if not out of code space, then allocate a new code. * * Keep the hash table correct so it can be used * with uncompressed packets. */ if (oldcode != CLEAR && max_ent < db->maxmaxcode) { struct bsd_dict *dictp2, *dictp3; unsigned short *lens1, *lens2; unsigned long fcode; int hval, disp, indx; fcode = BSD_KEY(oldcode,finchar); hval = BSD_HASH(oldcode,finchar,db->hshift); dictp = dict_ptr (db, hval); /* look for a free hash table entry */ if (dictp->codem1 < max_ent) { disp = (hval == 0) ? 1 : hval; do { hval += disp; if (hval >= db->hsize) { hval -= db->hsize; } dictp = dict_ptr (db, hval); } while (dictp->codem1 < max_ent); } /* * Invalidate previous hash table entry * assigned this code, and then take it over */ dictp2 = dict_ptr (db, max_ent + 1); indx = dictp2->cptr; dictp3 = dict_ptr (db, indx); if (dictp3->codem1 == max_ent) { dictp3->codem1 = BADCODEM1; } dictp2->cptr = hval; dictp->codem1 = max_ent; dictp->f.fcode = fcode; db->max_ent = ++max_ent; /* Update the length of this string. */ lens1 = lens_ptr (db, max_ent); lens2 = lens_ptr (db, oldcode); *lens1 = *lens2 + 1; /* Expand code size if needed. */ if (max_ent >= MAXCODE(n_bits) && max_ent < db->maxmaxcode) { db->n_bits = ++n_bits; tgtbitno = 32-n_bits; } } oldcode = incode; } ++db->comp_count; ++db->uncomp_count; db->comp_bytes += isize - BSD_OVHD - PPP_HDRLEN; db->uncomp_bytes += explen; if (bsd_check(db)) { if (db->debug) { printk("bsd_decomp%d: peer should have cleared dictionary on %d\n", db->unit, db->seqno - 1); } } return explen; } /************************************************************* * Table of addresses for the BSD compression module *************************************************************/ static struct compressor ppp_bsd_compress = { .compress_proto = CI_BSD_COMPRESS, .comp_alloc = bsd_comp_alloc, .comp_free = bsd_free, .comp_init = bsd_comp_init, .comp_reset = bsd_reset, .compress = bsd_compress, .comp_stat = bsd_comp_stats, .decomp_alloc = bsd_decomp_alloc, .decomp_free = bsd_free, .decomp_init = bsd_decomp_init, .decomp_reset = bsd_reset, .decompress = bsd_decompress, .incomp = bsd_incomp, .decomp_stat = bsd_comp_stats, .owner = THIS_MODULE }; /************************************************************* * Module support routines *************************************************************/ static int __init bsdcomp_init(void) { int answer = ppp_register_compressor(&ppp_bsd_compress); if (answer == 0) printk(KERN_INFO "PPP BSD Compression module registered\n"); return answer; } static void __exit bsdcomp_cleanup(void) { ppp_unregister_compressor(&ppp_bsd_compress); } module_init(bsdcomp_init); module_exit(bsdcomp_cleanup); MODULE_DESCRIPTION("PPP BSD-Compress compression module"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS("ppp-compress-" __stringify(CI_BSD_COMPRESS)); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_BITOPS_H #define _ASM_X86_BITOPS_H /* * Copyright 1992, Linus Torvalds. * * Note: inlines with more than a single statement should be marked * __always_inline to avoid problems with older gcc's inlining heuristics. */ #ifndef _LINUX_BITOPS_H #error only <linux/bitops.h> can be included directly #endif #include <linux/compiler.h> #include <asm/alternative.h> #include <asm/rmwcc.h> #include <asm/barrier.h> #if BITS_PER_LONG == 32 # define _BITOPS_LONG_SHIFT 5 #elif BITS_PER_LONG == 64 # define _BITOPS_LONG_SHIFT 6 #else # error "Unexpected BITS_PER_LONG" #endif #define BIT_64(n) (U64_C(1) << (n)) /* * These have to be done with inline assembly: that way the bit-setting * is guaranteed to be atomic. All bit operations return 0 if the bit * was cleared before the operation and != 0 if it was not. * * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1). */ #define RLONG_ADDR(x) "m" (*(volatile long *) (x)) #define WBYTE_ADDR(x) "+m" (*(volatile char *) (x)) #define ADDR RLONG_ADDR(addr) /* * We do the locked ops that don't return the old value as * a mask operation on a byte. */ #define CONST_MASK_ADDR(nr, addr) WBYTE_ADDR((void *)(addr) + ((nr)>>3)) #define CONST_MASK(nr) (1 << ((nr) & 7)) static __always_inline void arch_set_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { asm volatile(LOCK_PREFIX "orb %b1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" (CONST_MASK(nr)) : "memory"); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } static __always_inline void arch___set_bit(unsigned long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline void arch_clear_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { asm volatile(LOCK_PREFIX "andb %b1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" (~CONST_MASK(nr))); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } static __always_inline void arch_clear_bit_unlock(long nr, volatile unsigned long *addr) { barrier(); arch_clear_bit(nr, addr); } static __always_inline void arch___clear_bit(unsigned long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, volatile unsigned long *addr) { bool negative; asm volatile(LOCK_PREFIX "xorb %2,%1" CC_SET(s) : CC_OUT(s) (negative), WBYTE_ADDR(addr) : "iq" ((char)mask) : "memory"); return negative; } #define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte static __always_inline void arch___clear_bit_unlock(long nr, volatile unsigned long *addr) { arch___clear_bit(nr, addr); } static __always_inline void arch___change_bit(unsigned long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline void arch_change_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { asm volatile(LOCK_PREFIX "xorb %b1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" (CONST_MASK(nr))); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } static __always_inline bool arch_test_and_set_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), *addr, c, "Ir", nr); } static __always_inline bool arch_test_and_set_bit_lock(long nr, volatile unsigned long *addr) { return arch_test_and_set_bit(nr, addr); } static __always_inline bool arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { bool oldbit; asm(__ASM_SIZE(bts) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch_test_and_clear_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), *addr, c, "Ir", nr); } /* * Note: the operation is performed atomically with respect to * the local CPU, but not other CPUs. Portable code should not * rely on this behaviour. * KVM relies on this behaviour on x86 for modifying memory that is also * accessed from a hypervisor on the same CPU if running in a VM: don't change * this without also updating arch/x86/kernel/kvm.c */ static __always_inline bool arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { bool oldbit; asm volatile(__ASM_SIZE(btr) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { bool oldbit; asm volatile(__ASM_SIZE(btc) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch_test_and_change_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr); } static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) { return ((1UL << (nr & (BITS_PER_LONG-1))) & (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; } static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr) { bool oldbit; asm volatile("testb %2,%1" CC_SET(nz) : CC_OUT(nz) (oldbit) : "m" (((unsigned char *)addr)[nr >> 3]), "i" (1 << (nr & 7)) :"memory"); return oldbit; } static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr) { bool oldbit; asm volatile(__ASM_SIZE(bt) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long *)addr), "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch_test_bit(unsigned long nr, const volatile unsigned long *addr) { return __builtin_constant_p(nr) ? constant_test_bit(nr, addr) : variable_test_bit(nr, addr); } static __always_inline bool arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) { return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) : variable_test_bit(nr, addr); } static __always_inline unsigned long variable__ffs(unsigned long word) { asm("rep; bsf %1,%0" : "=r" (word) : ASM_INPUT_RM (word)); return word; } /** * __ffs - find first set bit in word * @word: The word to search * * Undefined if no bit exists, so code should check against 0 first. */ #define __ffs(word) \ (__builtin_constant_p(word) ? \ (unsigned long)__builtin_ctzl(word) : \ variable__ffs(word)) static __always_inline unsigned long variable_ffz(unsigned long word) { asm("rep; bsf %1,%0" : "=r" (word) : "r" (~word)); return word; } /** * ffz - find first zero bit in word * @word: The word to search * * Undefined if no zero exists, so code should check against ~0UL first. */ #define ffz(word) \ (__builtin_constant_p(word) ? \ (unsigned long)__builtin_ctzl(~word) : \ variable_ffz(word)) /* * __fls: find last set bit in word * @word: The word to search * * Undefined if no set bit exists, so code should check against 0 first. */ static __always_inline unsigned long __fls(unsigned long word) { if (__builtin_constant_p(word)) return BITS_PER_LONG - 1 - __builtin_clzl(word); asm("bsr %1,%0" : "=r" (word) : ASM_INPUT_RM (word)); return word; } #undef ADDR #ifdef __KERNEL__ static __always_inline int variable_ffs(int x) { int r; #ifdef CONFIG_X86_64 /* * AMD64 says BSFL won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before, except that the * top 32 bits will be cleared. * * We cannot do this on 32 bits because at the very least some * 486 CPUs did not behave this way. */ asm("bsfl %1,%0" : "=r" (r) : ASM_INPUT_RM (x), "0" (-1)); #elif defined(CONFIG_X86_CMOV) asm("bsfl %1,%0\n\t" "cmovzl %2,%0" : "=&r" (r) : "rm" (x), "r" (-1)); #else asm("bsfl %1,%0\n\t" "jnz 1f\n\t" "movl $-1,%0\n" "1:" : "=r" (r) : "rm" (x)); #endif return r + 1; } /** * ffs - find first set bit in word * @x: the word to search * * This is defined the same way as the libc and compiler builtin ffs * routines, therefore differs in spirit from the other bitops. * * ffs(value) returns 0 if value is 0 or the position of the first * set bit if value is nonzero. The first (least significant) bit * is at position 1. */ #define ffs(x) (__builtin_constant_p(x) ? __builtin_ffs(x) : variable_ffs(x)) /** * fls - find last set bit in word * @x: the word to search * * This is defined in a similar way as the libc and compiler builtin * ffs, but returns the position of the most significant set bit. * * fls(value) returns 0 if value is 0 or the position of the last * set bit if value is nonzero. The last (most significant) bit is * at position 32. */ static __always_inline int fls(unsigned int x) { int r; if (__builtin_constant_p(x)) return x ? 32 - __builtin_clz(x) : 0; #ifdef CONFIG_X86_64 /* * AMD64 says BSRL won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before, except that the * top 32 bits will be cleared. * * We cannot do this on 32 bits because at the very least some * 486 CPUs did not behave this way. */ asm("bsrl %1,%0" : "=r" (r) : ASM_INPUT_RM (x), "0" (-1)); #elif defined(CONFIG_X86_CMOV) asm("bsrl %1,%0\n\t" "cmovzl %2,%0" : "=&r" (r) : "rm" (x), "rm" (-1)); #else asm("bsrl %1,%0\n\t" "jnz 1f\n\t" "movl $-1,%0\n" "1:" : "=r" (r) : "rm" (x)); #endif return r + 1; } /** * fls64 - find last set bit in a 64-bit word * @x: the word to search * * This is defined in a similar way as the libc and compiler builtin * ffsll, but returns the position of the most significant set bit. * * fls64(value) returns 0 if value is 0 or the position of the last * set bit if value is nonzero. The last (most significant) bit is * at position 64. */ #ifdef CONFIG_X86_64 static __always_inline int fls64(__u64 x) { int bitpos = -1; if (__builtin_constant_p(x)) return x ? 64 - __builtin_clzll(x) : 0; /* * AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before. */ asm("bsrq %1,%q0" : "+r" (bitpos) : ASM_INPUT_RM (x)); return bitpos + 1; } #else #include <asm-generic/bitops/fls64.h> #endif #include <asm-generic/bitops/sched.h> #include <asm/arch_hweight.h> #include <asm-generic/bitops/const_hweight.h> #include <asm-generic/bitops/instrumented-atomic.h> #include <asm-generic/bitops/instrumented-non-atomic.h> #include <asm-generic/bitops/instrumented-lock.h> #include <asm-generic/bitops/le.h> #include <asm-generic/bitops/ext2-atomic-setbit.h> #endif /* __KERNEL__ */ #endif /* _ASM_X86_BITOPS_H */ |
| 38 20 17 3 | 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 /* * Copyright (c) 2014 Patrick McHardy <kaber@trash.net> */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nft_reject.h> #include <net/netfilter/ipv4/nf_reject.h> #include <net/netfilter/ipv6/nf_reject.h> static void nft_reject_inet_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_reject *priv = nft_expr_priv(expr); switch (nft_pf(pkt)) { case NFPROTO_IPV4: switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: nf_send_unreach(pkt->skb, priv->icmp_code, nft_hook(pkt)); break; case NFT_REJECT_TCP_RST: nf_send_reset(nft_net(pkt), nft_sk(pkt), pkt->skb, nft_hook(pkt)); break; case NFT_REJECT_ICMPX_UNREACH: nf_send_unreach(pkt->skb, nft_reject_icmp_code(priv->icmp_code), nft_hook(pkt)); break; } break; case NFPROTO_IPV6: switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: nf_send_unreach6(nft_net(pkt), pkt->skb, priv->icmp_code, nft_hook(pkt)); break; case NFT_REJECT_TCP_RST: nf_send_reset6(nft_net(pkt), nft_sk(pkt), pkt->skb, nft_hook(pkt)); break; case NFT_REJECT_ICMPX_UNREACH: nf_send_unreach6(nft_net(pkt), pkt->skb, nft_reject_icmpv6_code(priv->icmp_code), nft_hook(pkt)); break; } break; } regs->verdict.code = NF_DROP; } static int nft_reject_inet_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_INGRESS)); } static struct nft_expr_type nft_reject_inet_type; static const struct nft_expr_ops nft_reject_inet_ops = { .type = &nft_reject_inet_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)), .eval = nft_reject_inet_eval, .init = nft_reject_init, .dump = nft_reject_dump, .validate = nft_reject_inet_validate, .reduce = NFT_REDUCE_READONLY, }; static struct nft_expr_type nft_reject_inet_type __read_mostly = { .family = NFPROTO_INET, .name = "reject", .ops = &nft_reject_inet_ops, .policy = nft_reject_policy, .maxattr = NFTA_REJECT_MAX, .owner = THIS_MODULE, }; static int __init nft_reject_inet_module_init(void) { return nft_register_expr(&nft_reject_inet_type); } static void __exit nft_reject_inet_module_exit(void) { nft_unregister_expr(&nft_reject_inet_type); } module_init(nft_reject_inet_module_init); module_exit(nft_reject_inet_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_ALIAS_NFT_AF_EXPR(1, "reject"); MODULE_DESCRIPTION("Netfilter nftables reject inet support"); |
| 582 584 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * x86 specific code for irq_work * * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra */ #include <linux/kernel.h> #include <linux/irq_work.h> #include <linux/hardirq.h> #include <asm/apic.h> #include <asm/idtentry.h> #include <asm/trace/irq_vectors.h> #include <linux/interrupt.h> #ifdef CONFIG_X86_LOCAL_APIC DEFINE_IDTENTRY_SYSVEC(sysvec_irq_work) { apic_eoi(); trace_irq_work_entry(IRQ_WORK_VECTOR); inc_irq_stat(apic_irq_work_irqs); irq_work_run(); trace_irq_work_exit(IRQ_WORK_VECTOR); } void arch_irq_work_raise(void) { if (!arch_irq_work_has_interrupt()) return; __apic_send_IPI_self(IRQ_WORK_VECTOR); apic_wait_icr_idle(); } #endif |
| 1 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@netfilter.org> * Copyright (C) 2013 Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa> */ /* Kernel module implementing an IP set type: the hash:net type */ #include <linux/jhash.h> #include <linux/module.h> #include <linux/ip.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/random.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/ipset/pfxlen.h> #include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 /* 1 Forceadd support added */ /* 2 skbinfo support added */ /* 3 bucketsize, initval support added */ #define IPSET_TYPE_REV_MAX 4 /* bitmask support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>"); IP_SET_MODULE_DESC("hash:net,net", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_hash:net,net"); /* Type specific function prefix */ #define HTYPE hash_netnet #define IP_SET_HASH_WITH_NETS #define IP_SET_HASH_WITH_NETMASK #define IP_SET_HASH_WITH_BITMASK #define IPSET_NET_COUNT 2 /* IPv4 variants */ /* Member elements */ struct hash_netnet4_elem { union { __be32 ip[2]; __be64 ipcmp; }; u8 nomatch; u8 padding; union { u8 cidr[2]; u16 ccmp; }; }; /* Common functions */ static bool hash_netnet4_data_equal(const struct hash_netnet4_elem *ip1, const struct hash_netnet4_elem *ip2, u32 *multi) { return ip1->ipcmp == ip2->ipcmp && ip1->ccmp == ip2->ccmp; } static int hash_netnet4_do_data_match(const struct hash_netnet4_elem *elem) { return elem->nomatch ? -ENOTEMPTY : 1; } static void hash_netnet4_data_set_flags(struct hash_netnet4_elem *elem, u32 flags) { elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH; } static void hash_netnet4_data_reset_flags(struct hash_netnet4_elem *elem, u8 *flags) { swap(*flags, elem->nomatch); } static void hash_netnet4_data_reset_elem(struct hash_netnet4_elem *elem, struct hash_netnet4_elem *orig) { elem->ip[1] = orig->ip[1]; } static void hash_netnet4_data_netmask(struct hash_netnet4_elem *elem, u8 cidr, bool inner) { if (inner) { elem->ip[1] &= ip_set_netmask(cidr); elem->cidr[1] = cidr; } else { elem->ip[0] &= ip_set_netmask(cidr); elem->cidr[0] = cidr; } } static bool hash_netnet4_data_list(struct sk_buff *skb, const struct hash_netnet4_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip[0]) || nla_put_ipaddr4(skb, IPSET_ATTR_IP2, data->ip[1]) || nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr[0]) || nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr[1]) || (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_netnet4_data_next(struct hash_netnet4_elem *next, const struct hash_netnet4_elem *d) { next->ipcmp = d->ipcmp; } #define MTYPE hash_netnet4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" static void hash_netnet4_init(struct hash_netnet4_elem *e) { e->cidr[0] = HOST_MASK; e->cidr[1] = HOST_MASK; } static int hash_netnet4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { const struct hash_netnet4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); e.cidr[0] = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); e.cidr[1] = INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); if (adt == IPSET_TEST) e.ccmp = (HOST_MASK << (sizeof(e.cidr[0]) * 8)) | HOST_MASK; ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip[0]); ip4addrptr(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.ip[1]); e.ip[0] &= (ip_set_netmask(e.cidr[0]) & h->bitmask.ip); e.ip[1] &= (ip_set_netmask(e.cidr[1]) & h->bitmask.ip); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { struct hash_netnet4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netnet4_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0; u32 ip2 = 0, ip2_from = 0, ip2_to = 0, i = 0; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); hash_netnet4_init(&e); if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); if (ret) return ret; ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2], &ip2_from); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; if (tb[IPSET_ATTR_CIDR]) { e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (!e.cidr[0] || e.cidr[0] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } if (tb[IPSET_ATTR_CIDR2]) { e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); if (!e.cidr[1] || e.cidr[1] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_IP2_TO])) { e.ip[0] = htonl(ip & ntohl(h->bitmask.ip) & ip_set_hostmask(e.cidr[0])); e.ip[1] = htonl(ip2_from & ntohl(h->bitmask.ip) & ip_set_hostmask(e.cidr[1])); ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } ip_to = ip; if (tb[IPSET_ATTR_IP_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; if (ip_to < ip) swap(ip, ip_to); if (unlikely(ip + UINT_MAX == ip_to)) return -IPSET_ERR_HASH_RANGE; } else { ip_set_mask_from_to(ip, ip_to, e.cidr[0]); } ip2_to = ip2_from; if (tb[IPSET_ATTR_IP2_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to); if (ret) return ret; if (ip2_to < ip2_from) swap(ip2_from, ip2_to); if (unlikely(ip2_from + UINT_MAX == ip2_to)) return -IPSET_ERR_HASH_RANGE; } else { ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]); } if (retried) { ip = ntohl(h->next.ip[0]); ip2 = ntohl(h->next.ip[1]); } else { ip2 = ip2_from; } do { e.ip[0] = htonl(ip); ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]); do { i++; e.ip[1] = htonl(ip2); if (i > IPSET_MAX_RANGE) { hash_netnet4_data_next(&h->next, &e); return -ERANGE; } ip2 = ip_set_range_to_cidr(ip2, ip2_to, &e.cidr[1]); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } while (ip2++ < ip2_to); ip2 = ip2_from; } while (ip++ < ip_to); return ret; } /* IPv6 variants */ struct hash_netnet6_elem { union nf_inet_addr ip[2]; u8 nomatch; u8 padding; union { u8 cidr[2]; u16 ccmp; }; }; /* Common functions */ static bool hash_netnet6_data_equal(const struct hash_netnet6_elem *ip1, const struct hash_netnet6_elem *ip2, u32 *multi) { return ipv6_addr_equal(&ip1->ip[0].in6, &ip2->ip[0].in6) && ipv6_addr_equal(&ip1->ip[1].in6, &ip2->ip[1].in6) && ip1->ccmp == ip2->ccmp; } static int hash_netnet6_do_data_match(const struct hash_netnet6_elem *elem) { return elem->nomatch ? -ENOTEMPTY : 1; } static void hash_netnet6_data_set_flags(struct hash_netnet6_elem *elem, u32 flags) { elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH; } static void hash_netnet6_data_reset_flags(struct hash_netnet6_elem *elem, u8 *flags) { swap(*flags, elem->nomatch); } static void hash_netnet6_data_reset_elem(struct hash_netnet6_elem *elem, struct hash_netnet6_elem *orig) { elem->ip[1] = orig->ip[1]; } static void hash_netnet6_data_netmask(struct hash_netnet6_elem *elem, u8 cidr, bool inner) { if (inner) { ip6_netmask(&elem->ip[1], cidr); elem->cidr[1] = cidr; } else { ip6_netmask(&elem->ip[0], cidr); elem->cidr[0] = cidr; } } static bool hash_netnet6_data_list(struct sk_buff *skb, const struct hash_netnet6_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip[0].in6) || nla_put_ipaddr6(skb, IPSET_ATTR_IP2, &data->ip[1].in6) || nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr[0]) || nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr[1]) || (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_netnet6_data_next(struct hash_netnet6_elem *next, const struct hash_netnet6_elem *d) { } #undef MTYPE #undef HOST_MASK #define MTYPE hash_netnet6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" static void hash_netnet6_init(struct hash_netnet6_elem *e) { e->cidr[0] = HOST_MASK; e->cidr[1] = HOST_MASK; } static int hash_netnet6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { const struct hash_netnet6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netnet6_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); e.cidr[0] = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK); e.cidr[1] = INIT_CIDR(h->nets[0].cidr[1], HOST_MASK); if (adt == IPSET_TEST) e.ccmp = (HOST_MASK << (sizeof(u8) * 8)) | HOST_MASK; ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip[0].in6); ip6addrptr(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.ip[1].in6); ip6_netmask(&e.ip[0], e.cidr[0]); ip6_netmask(&e.ip[1], e.cidr[1]); nf_inet_addr_mask_inplace(&e.ip[0], &h->bitmask); nf_inet_addr_mask_inplace(&e.ip[1], &h->bitmask); if (e.cidr[0] == HOST_MASK && ipv6_addr_any(&e.ip[0].in6)) return -EINVAL; return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_netnet6_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netnet6_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); const struct hash_netnet6 *h = set->data; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); hash_netnet6_init(&e); if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_IP2_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip[0]); if (ret) return ret; ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip[1]); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; if (tb[IPSET_ATTR_CIDR]) { e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (!e.cidr[0] || e.cidr[0] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } if (tb[IPSET_ATTR_CIDR2]) { e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); if (!e.cidr[1] || e.cidr[1] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } ip6_netmask(&e.ip[0], e.cidr[0]); ip6_netmask(&e.ip[1], e.cidr[1]); nf_inet_addr_mask_inplace(&e.ip[0], &h->bitmask); nf_inet_addr_mask_inplace(&e.ip[1], &h->bitmask); if (e.cidr[0] == HOST_MASK && ipv6_addr_any(&e.ip[0].in6)) return -IPSET_ERR_HASH_ELEM; if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } static struct ip_set_type hash_netnet_type __read_mostly = { .name = "hash:net,net", .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP | IPSET_TYPE_IP2 | IPSET_TYPE_NOMATCH, .dimension = IPSET_DIM_TWO, .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_netnet_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_NETMASK] = { .type = NLA_U8 }, [IPSET_ATTR_BITMASK] = { .type = NLA_NESTED }, }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_IP2] = { .type = NLA_NESTED }, [IPSET_ATTR_IP2_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_CIDR2] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, }, .me = THIS_MODULE, }; static int __init hash_netnet_init(void) { return ip_set_type_register(&hash_netnet_type); } static void __exit hash_netnet_fini(void) { rcu_barrier(); ip_set_type_unregister(&hash_netnet_type); } module_init(hash_netnet_init); module_exit(hash_netnet_fini); |
| 141 143 59 93 55 160 14 81 46 4 43 103 85 185 185 65 172 2 15 103 103 1 65 168 91 91 92 92 91 91 92 33 26 1 23 42 59 2 43 42 24 2 20 3 43 42 5 38 92 89 2 33 71 62 13 13 13 63 20 19 2 2 19 19 19 19 19 45 151 151 152 152 107 45 150 108 107 11 1 1 1 2 38 40 39 40 27 12 12 31 9 31 39 17 17 112 116 32 26 20 6 25 26 66 67 4 1 9 1 5 4 75 187 36 31 31 18 13 68 58 156 154 155 61 107 24 23 24 6 20 23 23 22 24 21 3 127 76 11 64 133 31 108 107 108 106 108 1 107 107 108 108 107 106 108 107 73 20 53 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Generic INET transport hashtables * * Authors: Lotsa people, from code originally in tcp */ #include <linux/module.h> #include <linux/random.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/wait.h> #include <linux/vmalloc.h> #include <linux/memblock.h> #include <net/addrconf.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/inet6_hashtables.h> #endif #include <net/secure_seq.h> #include <net/hotdata.h> #include <net/ip.h> #include <net/tcp.h> #include <net/sock_reuseport.h> u32 inet_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport) { net_get_random_once(&inet_ehash_secret, sizeof(inet_ehash_secret)); return __inet_ehashfn(laddr, lport, faddr, fport, inet_ehash_secret + net_hash_mix(net)); } EXPORT_SYMBOL_GPL(inet_ehashfn); /* This function handles inet_sock, but also timewait and request sockets * for IPv4/IPv6. */ static u32 sk_ehashfn(const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6 && !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) return inet6_ehashfn(sock_net(sk), &sk->sk_v6_rcv_saddr, sk->sk_num, &sk->sk_v6_daddr, sk->sk_dport); #endif return inet_ehashfn(sock_net(sk), sk->sk_rcv_saddr, sk->sk_num, sk->sk_daddr, sk->sk_dport); } /* * Allocate and initialize a new local port bind bucket. * The bindhash mutex for snum's hash chain must be held here. */ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net, struct inet_bind_hashbucket *head, const unsigned short snum, int l3mdev) { struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC); if (tb) { write_pnet(&tb->ib_net, net); tb->l3mdev = l3mdev; tb->port = snum; tb->fastreuse = 0; tb->fastreuseport = 0; INIT_HLIST_HEAD(&tb->bhash2); hlist_add_head(&tb->node, &head->chain); } return tb; } /* * Caller must hold hashbucket lock for this tb with local BH disabled */ void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb) { if (hlist_empty(&tb->bhash2)) { __hlist_del(&tb->node); kmem_cache_free(cachep, tb); } } bool inet_bind_bucket_match(const struct inet_bind_bucket *tb, const struct net *net, unsigned short port, int l3mdev) { return net_eq(ib_net(tb), net) && tb->port == port && tb->l3mdev == l3mdev; } static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb2, struct net *net, struct inet_bind_hashbucket *head, struct inet_bind_bucket *tb, const struct sock *sk) { write_pnet(&tb2->ib_net, net); tb2->l3mdev = tb->l3mdev; tb2->port = tb->port; #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(USHRT_MAX < (IPV6_ADDR_ANY | IPV6_ADDR_MAPPED)); if (sk->sk_family == AF_INET6) { tb2->addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); tb2->v6_rcv_saddr = sk->sk_v6_rcv_saddr; } else { tb2->addr_type = IPV6_ADDR_MAPPED; ipv6_addr_set_v4mapped(sk->sk_rcv_saddr, &tb2->v6_rcv_saddr); } #else tb2->rcv_saddr = sk->sk_rcv_saddr; #endif INIT_HLIST_HEAD(&tb2->owners); hlist_add_head(&tb2->node, &head->chain); hlist_add_head(&tb2->bhash_node, &tb->bhash2); } struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep, struct net *net, struct inet_bind_hashbucket *head, struct inet_bind_bucket *tb, const struct sock *sk) { struct inet_bind2_bucket *tb2 = kmem_cache_alloc(cachep, GFP_ATOMIC); if (tb2) inet_bind2_bucket_init(tb2, net, head, tb, sk); return tb2; } /* Caller must hold hashbucket lock for this tb with local BH disabled */ void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb) { if (hlist_empty(&tb->owners)) { __hlist_del(&tb->node); __hlist_del(&tb->bhash_node); kmem_cache_free(cachep, tb); } } static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2, const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) return ipv6_addr_equal(&tb2->v6_rcv_saddr, &sk->sk_v6_rcv_saddr); if (tb2->addr_type != IPV6_ADDR_MAPPED) return false; #endif return tb2->rcv_saddr == sk->sk_rcv_saddr; } void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, struct inet_bind2_bucket *tb2, unsigned short port) { inet_sk(sk)->inet_num = port; inet_csk(sk)->icsk_bind_hash = tb; inet_csk(sk)->icsk_bind2_hash = tb2; sk_add_bind_node(sk, &tb2->owners); } /* * Get rid of any references to a local port held by the given sock. */ static void __inet_put_port(struct sock *sk) { struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); struct inet_bind_hashbucket *head, *head2; struct net *net = sock_net(sk); struct inet_bind_bucket *tb; int bhash; bhash = inet_bhashfn(net, inet_sk(sk)->inet_num, hashinfo->bhash_size); head = &hashinfo->bhash[bhash]; head2 = inet_bhashfn_portaddr(hashinfo, sk, net, inet_sk(sk)->inet_num); spin_lock(&head->lock); tb = inet_csk(sk)->icsk_bind_hash; inet_csk(sk)->icsk_bind_hash = NULL; inet_sk(sk)->inet_num = 0; spin_lock(&head2->lock); if (inet_csk(sk)->icsk_bind2_hash) { struct inet_bind2_bucket *tb2 = inet_csk(sk)->icsk_bind2_hash; __sk_del_bind_node(sk); inet_csk(sk)->icsk_bind2_hash = NULL; inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2); } spin_unlock(&head2->lock); inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); spin_unlock(&head->lock); } void inet_put_port(struct sock *sk) { local_bh_disable(); __inet_put_port(sk); local_bh_enable(); } EXPORT_SYMBOL(inet_put_port); int __inet_inherit_port(const struct sock *sk, struct sock *child) { struct inet_hashinfo *table = tcp_or_dccp_get_hashinfo(sk); unsigned short port = inet_sk(child)->inet_num; struct inet_bind_hashbucket *head, *head2; bool created_inet_bind_bucket = false; struct net *net = sock_net(sk); bool update_fastreuse = false; struct inet_bind2_bucket *tb2; struct inet_bind_bucket *tb; int bhash, l3mdev; bhash = inet_bhashfn(net, port, table->bhash_size); head = &table->bhash[bhash]; head2 = inet_bhashfn_portaddr(table, child, net, port); spin_lock(&head->lock); spin_lock(&head2->lock); tb = inet_csk(sk)->icsk_bind_hash; tb2 = inet_csk(sk)->icsk_bind2_hash; if (unlikely(!tb || !tb2)) { spin_unlock(&head2->lock); spin_unlock(&head->lock); return -ENOENT; } if (tb->port != port) { l3mdev = inet_sk_bound_l3mdev(sk); /* NOTE: using tproxy and redirecting skbs to a proxy * on a different listener port breaks the assumption * that the listener socket's icsk_bind_hash is the same * as that of the child socket. We have to look up or * create a new bind bucket for the child here. */ inet_bind_bucket_for_each(tb, &head->chain) { if (inet_bind_bucket_match(tb, net, port, l3mdev)) break; } if (!tb) { tb = inet_bind_bucket_create(table->bind_bucket_cachep, net, head, port, l3mdev); if (!tb) { spin_unlock(&head2->lock); spin_unlock(&head->lock); return -ENOMEM; } created_inet_bind_bucket = true; } update_fastreuse = true; goto bhash2_find; } else if (!inet_bind2_bucket_addr_match(tb2, child)) { l3mdev = inet_sk_bound_l3mdev(sk); bhash2_find: tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, child); if (!tb2) { tb2 = inet_bind2_bucket_create(table->bind2_bucket_cachep, net, head2, tb, child); if (!tb2) goto error; } } if (update_fastreuse) inet_csk_update_fastreuse(tb, child); inet_bind_hash(child, tb, tb2, port); spin_unlock(&head2->lock); spin_unlock(&head->lock); return 0; error: if (created_inet_bind_bucket) inet_bind_bucket_destroy(table->bind_bucket_cachep, tb); spin_unlock(&head2->lock); spin_unlock(&head->lock); return -ENOMEM; } EXPORT_SYMBOL_GPL(__inet_inherit_port); static struct inet_listen_hashbucket * inet_lhash2_bucket_sk(struct inet_hashinfo *h, struct sock *sk) { u32 hash; #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) hash = ipv6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, inet_sk(sk)->inet_num); else #endif hash = ipv4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, inet_sk(sk)->inet_num); return inet_lhash2_bucket(h, hash); } static inline int compute_score(struct sock *sk, const struct net *net, const unsigned short hnum, const __be32 daddr, const int dif, const int sdif) { int score = -1; if (net_eq(sock_net(sk), net) && sk->sk_num == hnum && !ipv6_only_sock(sk)) { if (sk->sk_rcv_saddr != daddr) return -1; if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) return -1; score = sk->sk_bound_dev_if ? 2 : 1; if (sk->sk_family == PF_INET) score++; if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; } return score; } /** * inet_lookup_reuseport() - execute reuseport logic on AF_INET socket if necessary. * @net: network namespace. * @sk: AF_INET socket, must be in TCP_LISTEN state for TCP or TCP_CLOSE for UDP. * @skb: context for a potential SK_REUSEPORT program. * @doff: header offset. * @saddr: source address. * @sport: source port. * @daddr: destination address. * @hnum: destination port in host byte order. * @ehashfn: hash function used to generate the fallback hash. * * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to * the selected sock or an error. */ struct sock *inet_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, inet_ehashfn_t *ehashfn) { struct sock *reuse_sk = NULL; u32 phash; if (sk->sk_reuseport) { phash = INDIRECT_CALL_2(ehashfn, udp_ehashfn, inet_ehashfn, net, daddr, hnum, saddr, sport); reuse_sk = reuseport_select_sock(sk, phash, skb, doff); } return reuse_sk; } EXPORT_SYMBOL_GPL(inet_lookup_reuseport); /* * Here are some nice properties to exploit here. The BSD API * does not allow a listening sock to specify the remote port nor the * remote address for the connection. So always assume those are both * wildcarded during the search since they can never be otherwise. */ /* called with rcu_read_lock() : No refcount taken on the socket */ static struct sock *inet_lhash2_lookup(const struct net *net, struct inet_listen_hashbucket *ilb2, struct sk_buff *skb, int doff, const __be32 saddr, __be16 sport, const __be32 daddr, const unsigned short hnum, const int dif, const int sdif) { struct sock *sk, *result = NULL; struct hlist_nulls_node *node; int score, hiscore = 0; sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) { score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { result = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum, inet_ehashfn); if (result) return result; result = sk; hiscore = score; } } return result; } struct sock *inet_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, __be32 daddr, u16 hnum, const int dif, inet_ehashfn_t *ehashfn) { struct sock *sk, *reuse_sk; bool no_reuseport; no_reuseport = bpf_sk_lookup_run_v4(net, protocol, saddr, sport, daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum, ehashfn); if (reuse_sk) sk = reuse_sk; return sk; } struct sock *__inet_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be32 saddr, __be16 sport, const __be32 daddr, const unsigned short hnum, const int dif, const int sdif) { struct inet_listen_hashbucket *ilb2; struct sock *result = NULL; unsigned int hash2; /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled) && hashinfo == net->ipv4.tcp_death_row.hashinfo) { result = inet_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff, saddr, sport, daddr, hnum, dif, inet_ehashfn); if (result) goto done; } hash2 = ipv4_portaddr_hash(net, daddr, hnum); ilb2 = inet_lhash2_bucket(hashinfo, hash2); result = inet_lhash2_lookup(net, ilb2, skb, doff, saddr, sport, daddr, hnum, dif, sdif); if (result) goto done; /* Lookup lhash2 with INADDR_ANY */ hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum); ilb2 = inet_lhash2_bucket(hashinfo, hash2); result = inet_lhash2_lookup(net, ilb2, skb, doff, saddr, sport, htonl(INADDR_ANY), hnum, dif, sdif); done: if (IS_ERR(result)) return NULL; return result; } EXPORT_SYMBOL_GPL(__inet_lookup_listener); /* All sockets share common refcount, but have different destructors */ void sock_gen_put(struct sock *sk) { if (!refcount_dec_and_test(&sk->sk_refcnt)) return; if (sk->sk_state == TCP_TIME_WAIT) inet_twsk_free(inet_twsk(sk)); else if (sk->sk_state == TCP_NEW_SYN_RECV) reqsk_free(inet_reqsk(sk)); else sk_free(sk); } EXPORT_SYMBOL_GPL(sock_gen_put); void sock_edemux(struct sk_buff *skb) { sock_gen_put(skb->sk); } EXPORT_SYMBOL(sock_edemux); struct sock *__inet_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 hnum, const int dif, const int sdif) { INET_ADDR_COOKIE(acookie, saddr, daddr); const __portpair ports = INET_COMBINED_PORTS(sport, hnum); struct sock *sk; const struct hlist_nulls_node *node; /* Optimize here for direct hit, only listening connections can * have wildcards anyways. */ unsigned int hash = inet_ehashfn(net, daddr, hnum, saddr, sport); unsigned int slot = hash & hashinfo->ehash_mask; struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; begin: sk_nulls_for_each_rcu(sk, node, &head->chain) { if (sk->sk_hash != hash) continue; if (likely(inet_match(net, sk, acookie, ports, dif, sdif))) { if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) goto out; if (unlikely(!inet_match(net, sk, acookie, ports, dif, sdif))) { sock_gen_put(sk); goto begin; } goto found; } } /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (get_nulls_value(node) != slot) goto begin; out: sk = NULL; found: return sk; } EXPORT_SYMBOL_GPL(__inet_lookup_established); /* called with local bh disabled */ static int __inet_check_established(struct inet_timewait_death_row *death_row, struct sock *sk, __u16 lport, struct inet_timewait_sock **twp) { struct inet_hashinfo *hinfo = death_row->hashinfo; struct inet_sock *inet = inet_sk(sk); __be32 daddr = inet->inet_rcv_saddr; __be32 saddr = inet->inet_daddr; int dif = sk->sk_bound_dev_if; struct net *net = sock_net(sk); int sdif = l3mdev_master_ifindex_by_index(net, dif); INET_ADDR_COOKIE(acookie, saddr, daddr); const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); unsigned int hash = inet_ehashfn(net, daddr, lport, saddr, inet->inet_dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); spinlock_t *lock = inet_ehash_lockp(hinfo, hash); struct sock *sk2; const struct hlist_nulls_node *node; struct inet_timewait_sock *tw = NULL; spin_lock(lock); sk_nulls_for_each(sk2, node, &head->chain) { if (sk2->sk_hash != hash) continue; if (likely(inet_match(net, sk2, acookie, ports, dif, sdif))) { if (sk2->sk_state == TCP_TIME_WAIT) { tw = inet_twsk(sk2); if (sk->sk_protocol == IPPROTO_TCP && tcp_twsk_unique(sk, sk2, twp)) break; } goto not_unique; } } /* Must record num and sport now. Otherwise we will see * in hash table socket with a funny identity. */ inet->inet_num = lport; inet->inet_sport = htons(lport); sk->sk_hash = hash; WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); if (tw) { sk_nulls_del_node_init_rcu((struct sock *)tw); __NET_INC_STATS(net, LINUX_MIB_TIMEWAITRECYCLED); } spin_unlock(lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); if (twp) { *twp = tw; } else if (tw) { /* Silly. Should hash-dance instead... */ inet_twsk_deschedule_put(tw); } return 0; not_unique: spin_unlock(lock); return -EADDRNOTAVAIL; } static u64 inet_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); return secure_ipv4_port_ephemeral(inet->inet_rcv_saddr, inet->inet_daddr, inet->inet_dport); } /* Searches for an exsiting socket in the ehash bucket list. * Returns true if found, false otherwise. */ static bool inet_ehash_lookup_by_sk(struct sock *sk, struct hlist_nulls_head *list) { const __portpair ports = INET_COMBINED_PORTS(sk->sk_dport, sk->sk_num); const int sdif = sk->sk_bound_dev_if; const int dif = sk->sk_bound_dev_if; const struct hlist_nulls_node *node; struct net *net = sock_net(sk); struct sock *esk; INET_ADDR_COOKIE(acookie, sk->sk_daddr, sk->sk_rcv_saddr); sk_nulls_for_each_rcu(esk, node, list) { if (esk->sk_hash != sk->sk_hash) continue; if (sk->sk_family == AF_INET) { if (unlikely(inet_match(net, esk, acookie, ports, dif, sdif))) { return true; } } #if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { if (unlikely(inet6_match(net, esk, &sk->sk_v6_daddr, &sk->sk_v6_rcv_saddr, ports, dif, sdif))) { return true; } } #endif } return false; } /* Insert a socket into ehash, and eventually remove another one * (The another one can be a SYN_RECV or TIMEWAIT) * If an existing socket already exists, socket sk is not inserted, * and sets found_dup_sk parameter to true. */ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) { struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); struct inet_ehash_bucket *head; struct hlist_nulls_head *list; spinlock_t *lock; bool ret = true; WARN_ON_ONCE(!sk_unhashed(sk)); sk->sk_hash = sk_ehashfn(sk); head = inet_ehash_bucket(hashinfo, sk->sk_hash); list = &head->chain; lock = inet_ehash_lockp(hashinfo, sk->sk_hash); spin_lock(lock); if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); ret = sk_nulls_del_node_init_rcu(osk); } else if (found_dup_sk) { *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); if (*found_dup_sk) ret = false; } if (ret) __sk_nulls_add_node_rcu(sk, list); spin_unlock(lock); return ret; } bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk) { bool ok = inet_ehash_insert(sk, osk, found_dup_sk); if (ok) { sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); } else { this_cpu_inc(*sk->sk_prot->orphan_count); inet_sk_set_state(sk, TCP_CLOSE); sock_set_flag(sk, SOCK_DEAD); inet_csk_destroy_sock(sk); } return ok; } EXPORT_SYMBOL_GPL(inet_ehash_nolisten); static int inet_reuseport_add_sock(struct sock *sk, struct inet_listen_hashbucket *ilb) { struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash; const struct hlist_nulls_node *node; struct sock *sk2; kuid_t uid = sock_i_uid(sk); sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) { if (sk2 != sk && sk2->sk_family == sk->sk_family && ipv6_only_sock(sk2) == ipv6_only_sock(sk) && sk2->sk_bound_dev_if == sk->sk_bound_dev_if && inet_csk(sk2)->icsk_bind_hash == tb && sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) && inet_rcv_saddr_equal(sk, sk2, false)) return reuseport_add_sock(sk, sk2, inet_rcv_saddr_any(sk)); } return reuseport_alloc(sk, inet_rcv_saddr_any(sk)); } int __inet_hash(struct sock *sk, struct sock *osk) { struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); struct inet_listen_hashbucket *ilb2; int err = 0; if (sk->sk_state != TCP_LISTEN) { local_bh_disable(); inet_ehash_nolisten(sk, osk, NULL); local_bh_enable(); return 0; } WARN_ON(!sk_unhashed(sk)); ilb2 = inet_lhash2_bucket_sk(hashinfo, sk); spin_lock(&ilb2->lock); if (sk->sk_reuseport) { err = inet_reuseport_add_sock(sk, ilb2); if (err) goto unlock; } sock_set_flag(sk, SOCK_RCU_FREE); if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) __sk_nulls_add_node_tail_rcu(sk, &ilb2->nulls_head); else __sk_nulls_add_node_rcu(sk, &ilb2->nulls_head); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); unlock: spin_unlock(&ilb2->lock); return err; } EXPORT_SYMBOL(__inet_hash); int inet_hash(struct sock *sk) { int err = 0; if (sk->sk_state != TCP_CLOSE) err = __inet_hash(sk, NULL); return err; } EXPORT_SYMBOL_GPL(inet_hash); void inet_unhash(struct sock *sk) { struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); if (sk_unhashed(sk)) return; if (sk->sk_state == TCP_LISTEN) { struct inet_listen_hashbucket *ilb2; ilb2 = inet_lhash2_bucket_sk(hashinfo, sk); /* Don't disable bottom halves while acquiring the lock to * avoid circular locking dependency on PREEMPT_RT. */ spin_lock(&ilb2->lock); if (sk_unhashed(sk)) { spin_unlock(&ilb2->lock); return; } if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_stop_listen_sock(sk); __sk_nulls_del_node_init_rcu(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); spin_unlock(&ilb2->lock); } else { spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash); spin_lock_bh(lock); if (sk_unhashed(sk)) { spin_unlock_bh(lock); return; } __sk_nulls_del_node_init_rcu(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); spin_unlock_bh(lock); } } EXPORT_SYMBOL_GPL(inet_unhash); static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb, const struct net *net, unsigned short port, int l3mdev, const struct sock *sk) { if (!net_eq(ib2_net(tb), net) || tb->port != port || tb->l3mdev != l3mdev) return false; return inet_bind2_bucket_addr_match(tb, sk); } bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const struct net *net, unsigned short port, int l3mdev, const struct sock *sk) { if (!net_eq(ib2_net(tb), net) || tb->port != port || tb->l3mdev != l3mdev) return false; #if IS_ENABLED(CONFIG_IPV6) if (tb->addr_type == IPV6_ADDR_ANY) return true; if (tb->addr_type != IPV6_ADDR_MAPPED) return false; if (sk->sk_family == AF_INET6 && !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) return false; #endif return tb->rcv_saddr == 0; } /* The socket's bhash2 hashbucket spinlock must be held when this is called */ struct inet_bind2_bucket * inet_bind2_bucket_find(const struct inet_bind_hashbucket *head, const struct net *net, unsigned short port, int l3mdev, const struct sock *sk) { struct inet_bind2_bucket *bhash2 = NULL; inet_bind_bucket_for_each(bhash2, &head->chain) if (inet_bind2_bucket_match(bhash2, net, port, l3mdev, sk)) break; return bhash2; } struct inet_bind_hashbucket * inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, int port) { struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); u32 hash; #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) hash = ipv6_portaddr_hash(net, &in6addr_any, port); else #endif hash = ipv4_portaddr_hash(net, 0, port); return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)]; } static void inet_update_saddr(struct sock *sk, void *saddr, int family) { if (family == AF_INET) { inet_sk(sk)->inet_saddr = *(__be32 *)saddr; sk_rcv_saddr_set(sk, inet_sk(sk)->inet_saddr); } #if IS_ENABLED(CONFIG_IPV6) else { sk->sk_v6_rcv_saddr = *(struct in6_addr *)saddr; } #endif } static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, bool reset) { struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); struct inet_bind_hashbucket *head, *head2; struct inet_bind2_bucket *tb2, *new_tb2; int l3mdev = inet_sk_bound_l3mdev(sk); int port = inet_sk(sk)->inet_num; struct net *net = sock_net(sk); int bhash; if (!inet_csk(sk)->icsk_bind2_hash) { /* Not bind()ed before. */ if (reset) inet_reset_saddr(sk); else inet_update_saddr(sk, saddr, family); return 0; } /* Allocate a bind2 bucket ahead of time to avoid permanently putting * the bhash2 table in an inconsistent state if a new tb2 bucket * allocation fails. */ new_tb2 = kmem_cache_alloc(hinfo->bind2_bucket_cachep, GFP_ATOMIC); if (!new_tb2) { if (reset) { /* The (INADDR_ANY, port) bucket might have already * been freed, then we cannot fixup icsk_bind2_hash, * so we give up and unlink sk from bhash/bhash2 not * to leave inconsistency in bhash2. */ inet_put_port(sk); inet_reset_saddr(sk); } return -ENOMEM; } bhash = inet_bhashfn(net, port, hinfo->bhash_size); head = &hinfo->bhash[bhash]; head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); /* If we change saddr locklessly, another thread * iterating over bhash might see corrupted address. */ spin_lock_bh(&head->lock); spin_lock(&head2->lock); __sk_del_bind_node(sk); inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash); spin_unlock(&head2->lock); if (reset) inet_reset_saddr(sk); else inet_update_saddr(sk, saddr, family); head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); spin_lock(&head2->lock); tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); if (!tb2) { tb2 = new_tb2; inet_bind2_bucket_init(tb2, net, head2, inet_csk(sk)->icsk_bind_hash, sk); } inet_csk(sk)->icsk_bind2_hash = tb2; sk_add_bind_node(sk, &tb2->owners); spin_unlock(&head2->lock); spin_unlock_bh(&head->lock); if (tb2 != new_tb2) kmem_cache_free(hinfo->bind2_bucket_cachep, new_tb2); return 0; } int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family) { return __inet_bhash2_update_saddr(sk, saddr, family, false); } EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr); void inet_bhash2_reset_saddr(struct sock *sk) { if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) __inet_bhash2_update_saddr(sk, NULL, 0, true); } EXPORT_SYMBOL_GPL(inet_bhash2_reset_saddr); /* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm * Note that we use 32bit integers (vs RFC 'short integers') * because 2^16 is not a multiple of num_ephemeral and this * property might be used by clever attacker. * * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though * attacks were since demonstrated, thus we use 65536 by default instead * to really give more isolation and privacy, at the expense of 256kB * of kernel memory. */ #define INET_TABLE_PERTURB_SIZE (1 << CONFIG_INET_TABLE_PERTURB_ORDER) static u32 *table_perturb; int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u64 port_offset, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, struct inet_timewait_sock **)) { struct inet_hashinfo *hinfo = death_row->hashinfo; struct inet_bind_hashbucket *head, *head2; struct inet_timewait_sock *tw = NULL; int port = inet_sk(sk)->inet_num; struct net *net = sock_net(sk); struct inet_bind2_bucket *tb2; struct inet_bind_bucket *tb; bool tb_created = false; u32 remaining, offset; int ret, i, low, high; bool local_ports; int step, l3mdev; u32 index; if (port) { local_bh_disable(); ret = check_established(death_row, sk, port, NULL); local_bh_enable(); return ret; } l3mdev = inet_sk_bound_l3mdev(sk); local_ports = inet_sk_get_local_port_range(sk, &low, &high); step = local_ports ? 1 : 2; high++; /* [32768, 60999] -> [32768, 61000[ */ remaining = high - low; if (!local_ports && remaining > 1) remaining &= ~1U; get_random_sleepable_once(table_perturb, INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb)); index = port_offset & (INET_TABLE_PERTURB_SIZE - 1); offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32); offset %= remaining; /* In first pass we try ports of @low parity. * inet_csk_get_port() does the opposite choice. */ if (!local_ports) offset &= ~1U; other_parity_scan: port = low + offset; for (i = 0; i < remaining; i += step, port += step) { if (unlikely(port >= high)) port -= remaining; if (inet_is_local_reserved_port(net, port)) continue; head = &hinfo->bhash[inet_bhashfn(net, port, hinfo->bhash_size)]; spin_lock_bh(&head->lock); /* Does not bother with rcv_saddr checks, because * the established check is already unique enough. */ inet_bind_bucket_for_each(tb, &head->chain) { if (inet_bind_bucket_match(tb, net, port, l3mdev)) { if (tb->fastreuse >= 0 || tb->fastreuseport >= 0) goto next_port; WARN_ON(hlist_empty(&tb->bhash2)); if (!check_established(death_row, sk, port, &tw)) goto ok; goto next_port; } } tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep, net, head, port, l3mdev); if (!tb) { spin_unlock_bh(&head->lock); return -ENOMEM; } tb_created = true; tb->fastreuse = -1; tb->fastreuseport = -1; goto ok; next_port: spin_unlock_bh(&head->lock); cond_resched(); } if (!local_ports) { offset++; if ((offset & 1) && remaining > 1) goto other_parity_scan; } return -EADDRNOTAVAIL; ok: /* Find the corresponding tb2 bucket since we need to * add the socket to the bhash2 table as well */ head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); spin_lock(&head2->lock); tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); if (!tb2) { tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep, net, head2, tb, sk); if (!tb2) goto error; } /* Here we want to add a little bit of randomness to the next source * port that will be chosen. We use a max() with a random here so that * on low contention the randomness is maximal and on high contention * it may be inexistent. */ i = max_t(int, i, get_random_u32_below(8) * step); WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + step); /* Head lock still held and bh's disabled */ inet_bind_hash(sk, tb, tb2, port); if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); inet_ehash_nolisten(sk, (struct sock *)tw, NULL); } if (tw) inet_twsk_bind_unhash(tw, hinfo); spin_unlock(&head2->lock); spin_unlock(&head->lock); if (tw) inet_twsk_deschedule_put(tw); local_bh_enable(); return 0; error: if (sk_hashed(sk)) { spinlock_t *lock = inet_ehash_lockp(hinfo, sk->sk_hash); sock_prot_inuse_add(net, sk->sk_prot, -1); spin_lock(lock); __sk_nulls_del_node_init_rcu(sk); spin_unlock(lock); sk->sk_hash = 0; inet_sk(sk)->inet_sport = 0; inet_sk(sk)->inet_num = 0; if (tw) inet_twsk_bind_unhash(tw, hinfo); } spin_unlock(&head2->lock); if (tb_created) inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb); spin_unlock(&head->lock); if (tw) inet_twsk_deschedule_put(tw); local_bh_enable(); return -ENOMEM; } /* * Bind a port for a connect operation and hash it. */ int inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { u64 port_offset = 0; if (!inet_sk(sk)->inet_num) port_offset = inet_sk_port_offset(sk); return __inet_hash_connect(death_row, sk, port_offset, __inet_check_established); } EXPORT_SYMBOL_GPL(inet_hash_connect); static void init_hashinfo_lhash2(struct inet_hashinfo *h) { int i; for (i = 0; i <= h->lhash2_mask; i++) { spin_lock_init(&h->lhash2[i].lock); INIT_HLIST_NULLS_HEAD(&h->lhash2[i].nulls_head, i + LISTENING_NULLS_BASE); } } void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, unsigned long numentries, int scale, unsigned long low_limit, unsigned long high_limit) { h->lhash2 = alloc_large_system_hash(name, sizeof(*h->lhash2), numentries, scale, 0, NULL, &h->lhash2_mask, low_limit, high_limit); init_hashinfo_lhash2(h); /* this one is used for source ports of outgoing connections */ table_perturb = alloc_large_system_hash("Table-perturb", sizeof(*table_perturb), INET_TABLE_PERTURB_SIZE, 0, 0, NULL, NULL, INET_TABLE_PERTURB_SIZE, INET_TABLE_PERTURB_SIZE); } int inet_hashinfo2_init_mod(struct inet_hashinfo *h) { h->lhash2 = kmalloc_array(INET_LHTABLE_SIZE, sizeof(*h->lhash2), GFP_KERNEL); if (!h->lhash2) return -ENOMEM; h->lhash2_mask = INET_LHTABLE_SIZE - 1; /* INET_LHTABLE_SIZE must be a power of 2 */ BUG_ON(INET_LHTABLE_SIZE & h->lhash2_mask); init_hashinfo_lhash2(h); return 0; } EXPORT_SYMBOL_GPL(inet_hashinfo2_init_mod); int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo) { unsigned int locksz = sizeof(spinlock_t); unsigned int i, nblocks = 1; if (locksz != 0) { /* allocate 2 cache lines or at least one spinlock per cpu */ nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U); nblocks = roundup_pow_of_two(nblocks * num_possible_cpus()); /* no more locks than number of hash buckets */ nblocks = min(nblocks, hashinfo->ehash_mask + 1); hashinfo->ehash_locks = kvmalloc_array(nblocks, locksz, GFP_KERNEL); if (!hashinfo->ehash_locks) return -ENOMEM; for (i = 0; i < nblocks; i++) spin_lock_init(&hashinfo->ehash_locks[i]); } hashinfo->ehash_locks_mask = nblocks - 1; return 0; } EXPORT_SYMBOL_GPL(inet_ehash_locks_alloc); struct inet_hashinfo *inet_pernet_hashinfo_alloc(struct inet_hashinfo *hashinfo, unsigned int ehash_entries) { struct inet_hashinfo *new_hashinfo; int i; new_hashinfo = kmemdup(hashinfo, sizeof(*hashinfo), GFP_KERNEL); if (!new_hashinfo) goto err; new_hashinfo->ehash = vmalloc_huge(ehash_entries * sizeof(struct inet_ehash_bucket), GFP_KERNEL_ACCOUNT); if (!new_hashinfo->ehash) goto free_hashinfo; new_hashinfo->ehash_mask = ehash_entries - 1; if (inet_ehash_locks_alloc(new_hashinfo)) goto free_ehash; for (i = 0; i < ehash_entries; i++) INIT_HLIST_NULLS_HEAD(&new_hashinfo->ehash[i].chain, i); new_hashinfo->pernet = true; return new_hashinfo; free_ehash: vfree(new_hashinfo->ehash); free_hashinfo: kfree(new_hashinfo); err: return NULL; } EXPORT_SYMBOL_GPL(inet_pernet_hashinfo_alloc); void inet_pernet_hashinfo_free(struct inet_hashinfo *hashinfo) { if (!hashinfo->pernet) return; inet_ehash_locks_free(hashinfo); vfree(hashinfo->ehash); kfree(hashinfo); } EXPORT_SYMBOL_GPL(inet_pernet_hashinfo_free); |
| 11 1 9 1 4 4 10 1 9 10 12 7 2 1 1 1 10 1 10 12 15 15 6 8 12 7 2 2 1 2 5 3 3 6 6 3 2 2 2 2 2 1 2 12 11 3 5 5 10 1 5 4 6 3 7 2 7 2 5 4 6 3 6 6 4 4 38 81 1 1 1 79 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: IP/IP protocol decoder modified to support * virtual tunnel interface * * Authors: * Saurabh Mohan (saurabh.mohan@vyatta.com) 05/07/2012 */ /* This version of net/ipv4/ip_vti.c is cloned of net/ipv4/ipip.c For comments look at net/ipv4/ip_gre.c --ANK */ #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/netfilter_ipv4.h> #include <linux/if_ether.h> #include <linux/icmpv6.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/ip_tunnels.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> static struct rtnl_link_ops vti_link_ops __read_mostly; static unsigned int vti_net_id __read_mostly; static int vti_tunnel_init(struct net_device *dev); static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type, bool update_skb_dev) { struct ip_tunnel *tunnel; const struct iphdr *iph = ip_hdr(skb); struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, vti_net_id); IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, 0); if (tunnel) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel; if (update_skb_dev) skb->dev = tunnel->dev; return xfrm_input(skb, nexthdr, spi, encap_type); } return -EINVAL; drop: kfree_skb(skb); return 0; } static int vti_input_proto(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { return vti_input(skb, nexthdr, spi, encap_type, false); } static int vti_rcv(struct sk_buff *skb, __be32 spi, bool update_skb_dev) { XFRM_SPI_SKB_CB(skb)->family = AF_INET; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); return vti_input(skb, ip_hdr(skb)->protocol, spi, 0, update_skb_dev); } static int vti_rcv_proto(struct sk_buff *skb) { return vti_rcv(skb, 0, false); } static int vti_rcv_cb(struct sk_buff *skb, int err) { unsigned short family; struct net_device *dev; struct xfrm_state *x; const struct xfrm_mode *inner_mode; struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4; u32 orig_mark = skb->mark; int ret; if (!tunnel) return 1; dev = tunnel->dev; if (err) { DEV_STATS_INC(dev, rx_errors); DEV_STATS_INC(dev, rx_dropped); return 0; } x = xfrm_input_state(skb); inner_mode = &x->inner_mode; if (x->sel.family == AF_UNSPEC) { inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); if (inner_mode == NULL) { XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMINSTATEMODEERROR); return -EINVAL; } } family = inner_mode->family; skb->mark = be32_to_cpu(tunnel->parms.i_key); ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family); skb->mark = orig_mark; if (!ret) return -EPERM; skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev))); skb->dev = dev; dev_sw_netstats_rx_add(dev, skb->len); return 0; } static bool vti_state_check(const struct xfrm_state *x, __be32 dst, __be32 src) { xfrm_address_t *daddr = (xfrm_address_t *)&dst; xfrm_address_t *saddr = (xfrm_address_t *)&src; /* if there is no transform then this tunnel is not functional. * Or if the xfrm is not mode tunnel. */ if (!x || x->props.mode != XFRM_MODE_TUNNEL || x->props.family != AF_INET) return false; if (!dst) return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET); if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET)) return false; return true; } static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_parm_kern *parms = &tunnel->parms; struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; /* Device to other host */ int pkt_len = skb->len; int err; int mtu; if (!dst) { switch (skb->protocol) { case htons(ETH_P_IP): { struct rtable *rt; fl->u.ip4.flowi4_oif = dev->ifindex; fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4); if (IS_ERR(rt)) { DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } dst = &rt->dst; skb_dst_set(skb, dst); break; } #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): fl->u.ip6.flowi6_oif = dev->ifindex; fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6); if (dst->error) { dst_release(dst); dst = NULL; DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } skb_dst_set(skb, dst); break; #endif default: DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } } dst_hold(dst); dst = xfrm_lookup_route(tunnel->net, dst, fl, NULL, 0); if (IS_ERR(dst)) { DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } if (dst->flags & DST_XFRM_QUEUE) goto xmit; if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) { DEV_STATS_INC(dev, tx_carrier_errors); dst_release(dst); goto tx_error_icmp; } tdev = dst->dev; if (tdev == dev) { dst_release(dst); DEV_STATS_INC(dev, collisions); goto tx_error; } mtu = dst_mtu(dst); if (skb->len > mtu) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { if (!(ip_hdr(skb)->frag_off & htons(IP_DF))) goto xmit; icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); } else { if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } dst_release(dst); goto tx_error; } xmit: skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; err = dst_output(tunnel->net, skb->sk, skb); if (net_xmit_eval(err) == 0) err = pkt_len; iptunnel_xmit_stats(dev, err); return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return NETDEV_TX_OK; } /* This function assumes it is being called from dev_queue_xmit() * and that skb is filled properly by that function. */ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct flowi fl; if (!pskb_inet_may_pull(skb)) goto tx_err; memset(&fl, 0, sizeof(fl)); switch (skb->protocol) { case htons(ETH_P_IP): memset(IPCB(skb), 0, sizeof(*IPCB(skb))); xfrm_decode_session(dev_net(dev), skb, &fl, AF_INET); break; case htons(ETH_P_IPV6): memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); xfrm_decode_session(dev_net(dev), skb, &fl, AF_INET6); break; default: goto tx_err; } /* override mark with tunnel output key */ fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key); return vti_xmit(skb, dev, &fl); tx_err: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return NETDEV_TX_OK; } static int vti4_err(struct sk_buff *skb, u32 info) { __be32 spi; __u32 mark; struct xfrm_state *x; struct ip_tunnel *tunnel; struct ip_esp_hdr *esph; struct ip_auth_hdr *ah ; struct ip_comp_hdr *ipch; struct net *net = dev_net(skb->dev); const struct iphdr *iph = (const struct iphdr *)skb->data; int protocol = iph->protocol; struct ip_tunnel_net *itn = net_generic(net, vti_net_id); IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->daddr, iph->saddr, 0); if (!tunnel) return -1; mark = be32_to_cpu(tunnel->parms.o_key); switch (protocol) { case IPPROTO_ESP: esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); spi = esph->spi; break; case IPPROTO_AH: ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); spi = ah->spi; break; case IPPROTO_COMP: ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); spi = htonl(ntohs(ipch->cpi)); break; default: return 0; } switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) return 0; break; case ICMP_REDIRECT: break; default: return 0; } x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr, spi, protocol, AF_INET); if (!x) return 0; if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, protocol); else ipv4_redirect(skb, net, 0, protocol); xfrm_state_put(x); return 0; } static int vti_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; int err = 0; if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || p->iph.protocol != IPPROTO_IPIP || p->iph.ihl != 5) return -EINVAL; } if (!ip_tunnel_flags_is_be16_compat(p->i_flags) || !ip_tunnel_flags_is_be16_compat(p->o_flags)) return -EOVERFLOW; if (!(ip_tunnel_flags_to_be16(p->i_flags) & GRE_KEY)) p->i_key = 0; if (!(ip_tunnel_flags_to_be16(p->o_flags) & GRE_KEY)) p->o_key = 0; __set_bit(IP_TUNNEL_VTI_BIT, flags); ip_tunnel_flags_copy(p->i_flags, flags); err = ip_tunnel_ctl(dev, p, cmd); if (err) return err; if (cmd != SIOCDELTUNNEL) { ip_tunnel_flags_from_be16(flags, GRE_KEY); ip_tunnel_flags_or(p->i_flags, p->i_flags, flags); ip_tunnel_flags_or(p->o_flags, p->o_flags, flags); } return 0; } static const struct net_device_ops vti_netdev_ops = { .ndo_init = vti_tunnel_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = vti_tunnel_xmit, .ndo_siocdevprivate = ip_tunnel_siocdevprivate, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = vti_tunnel_ctl, }; static void vti_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &vti_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->type = ARPHRD_TUNNEL; ip_tunnel_setup(dev, vti_net_id); } static int vti_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; __dev_addr_set(dev, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); dev->flags = IFF_NOARP; dev->addr_len = 4; dev->lltx = true; netif_keep_dst(dev); return ip_tunnel_init(dev); } static void __net_init vti_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; iph->version = 4; iph->protocol = IPPROTO_IPIP; iph->ihl = 5; } static struct xfrm4_protocol vti_esp4_protocol __read_mostly = { .handler = vti_rcv_proto, .input_handler = vti_input_proto, .cb_handler = vti_rcv_cb, .err_handler = vti4_err, .priority = 100, }; static struct xfrm4_protocol vti_ah4_protocol __read_mostly = { .handler = vti_rcv_proto, .input_handler = vti_input_proto, .cb_handler = vti_rcv_cb, .err_handler = vti4_err, .priority = 100, }; static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = { .handler = vti_rcv_proto, .input_handler = vti_input_proto, .cb_handler = vti_rcv_cb, .err_handler = vti4_err, .priority = 100, }; #if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) static int vti_rcv_tunnel(struct sk_buff *skb) { XFRM_SPI_SKB_CB(skb)->family = AF_INET; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); return vti_input(skb, IPPROTO_IPIP, ip_hdr(skb)->saddr, 0, false); } static struct xfrm_tunnel vti_ipip_handler __read_mostly = { .handler = vti_rcv_tunnel, .cb_handler = vti_rcv_cb, .err_handler = vti4_err, .priority = 0, }; #if IS_ENABLED(CONFIG_IPV6) static struct xfrm_tunnel vti_ipip6_handler __read_mostly = { .handler = vti_rcv_tunnel, .cb_handler = vti_rcv_cb, .err_handler = vti4_err, .priority = 0, }; #endif #endif static int __net_init vti_init_net(struct net *net) { int err; struct ip_tunnel_net *itn; err = ip_tunnel_init_net(net, vti_net_id, &vti_link_ops, "ip_vti0"); if (err) return err; itn = net_generic(net, vti_net_id); if (itn->fb_tunnel_dev) vti_fb_tunnel_init(itn->fb_tunnel_dev); return 0; } static void __net_exit vti_exit_batch_rtnl(struct list_head *list_net, struct list_head *dev_to_kill) { ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops, dev_to_kill); } static struct pernet_operations vti_net_ops = { .init = vti_init_net, .exit_batch_rtnl = vti_exit_batch_rtnl, .id = &vti_net_id, .size = sizeof(struct ip_tunnel_net), }; static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { return 0; } static void vti_netlink_parms(struct nlattr *data[], struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); parms->iph.protocol = IPPROTO_IPIP; if (!data) return; __set_bit(IP_TUNNEL_VTI_BIT, parms->i_flags); if (data[IFLA_VTI_LINK]) parms->link = nla_get_u32(data[IFLA_VTI_LINK]); if (data[IFLA_VTI_IKEY]) parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]); if (data[IFLA_VTI_OKEY]) parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]); if (data[IFLA_VTI_LOCAL]) parms->iph.saddr = nla_get_in_addr(data[IFLA_VTI_LOCAL]); if (data[IFLA_VTI_REMOTE]) parms->iph.daddr = nla_get_in_addr(data[IFLA_VTI_REMOTE]); if (data[IFLA_VTI_FWMARK]) *fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]); } static int vti_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel_parm_kern parms; __u32 fwmark = 0; vti_netlink_parms(data, &parms, &fwmark); return ip_tunnel_newlink(dev, tb, &parms, fwmark); } static int vti_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; vti_netlink_parms(data, &p, &fwmark); return ip_tunnel_changelink(dev, tb, &p, fwmark); } static size_t vti_get_size(const struct net_device *dev) { return /* IFLA_VTI_LINK */ nla_total_size(4) + /* IFLA_VTI_IKEY */ nla_total_size(4) + /* IFLA_VTI_OKEY */ nla_total_size(4) + /* IFLA_VTI_LOCAL */ nla_total_size(4) + /* IFLA_VTI_REMOTE */ nla_total_size(4) + /* IFLA_VTI_FWMARK */ nla_total_size(4) + 0; } static int vti_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern *p = &t->parms; if (nla_put_u32(skb, IFLA_VTI_LINK, p->link) || nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key) || nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key) || nla_put_in_addr(skb, IFLA_VTI_LOCAL, p->iph.saddr) || nla_put_in_addr(skb, IFLA_VTI_REMOTE, p->iph.daddr) || nla_put_u32(skb, IFLA_VTI_FWMARK, t->fwmark)) return -EMSGSIZE; return 0; } static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = { [IFLA_VTI_LINK] = { .type = NLA_U32 }, [IFLA_VTI_IKEY] = { .type = NLA_U32 }, [IFLA_VTI_OKEY] = { .type = NLA_U32 }, [IFLA_VTI_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, [IFLA_VTI_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VTI_FWMARK] = { .type = NLA_U32 }, }; static struct rtnl_link_ops vti_link_ops __read_mostly = { .kind = "vti", .maxtype = IFLA_VTI_MAX, .policy = vti_policy, .priv_size = sizeof(struct ip_tunnel), .setup = vti_tunnel_setup, .validate = vti_tunnel_validate, .newlink = vti_newlink, .changelink = vti_changelink, .dellink = ip_tunnel_dellink, .get_size = vti_get_size, .fill_info = vti_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static int __init vti_init(void) { const char *msg; int err; pr_info("IPv4 over IPsec tunneling driver\n"); msg = "tunnel device"; err = register_pernet_device(&vti_net_ops); if (err < 0) goto pernet_dev_failed; msg = "tunnel protocols"; err = xfrm4_protocol_register(&vti_esp4_protocol, IPPROTO_ESP); if (err < 0) goto xfrm_proto_esp_failed; err = xfrm4_protocol_register(&vti_ah4_protocol, IPPROTO_AH); if (err < 0) goto xfrm_proto_ah_failed; err = xfrm4_protocol_register(&vti_ipcomp4_protocol, IPPROTO_COMP); if (err < 0) goto xfrm_proto_comp_failed; #if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) msg = "ipip tunnel"; err = xfrm4_tunnel_register(&vti_ipip_handler, AF_INET); if (err < 0) goto xfrm_tunnel_ipip_failed; #if IS_ENABLED(CONFIG_IPV6) err = xfrm4_tunnel_register(&vti_ipip6_handler, AF_INET6); if (err < 0) goto xfrm_tunnel_ipip6_failed; #endif #endif msg = "netlink interface"; err = rtnl_link_register(&vti_link_ops); if (err < 0) goto rtnl_link_failed; return err; rtnl_link_failed: #if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) #if IS_ENABLED(CONFIG_IPV6) xfrm4_tunnel_deregister(&vti_ipip6_handler, AF_INET6); xfrm_tunnel_ipip6_failed: #endif xfrm4_tunnel_deregister(&vti_ipip_handler, AF_INET); xfrm_tunnel_ipip_failed: #endif xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); xfrm_proto_comp_failed: xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm_proto_ah_failed: xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); xfrm_proto_esp_failed: unregister_pernet_device(&vti_net_ops); pernet_dev_failed: pr_err("vti init: failed to register %s\n", msg); return err; } static void __exit vti_fini(void) { rtnl_link_unregister(&vti_link_ops); #if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) #if IS_ENABLED(CONFIG_IPV6) xfrm4_tunnel_deregister(&vti_ipip6_handler, AF_INET6); #endif xfrm4_tunnel_deregister(&vti_ipip_handler, AF_INET); #endif xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); } module_init(vti_init); module_exit(vti_fini); MODULE_DESCRIPTION("Virtual (secure) IP tunneling library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("vti"); MODULE_ALIAS_NETDEV("ip_vti0"); |
| 2 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Poly1305 authenticator algorithm, RFC7539 * * Copyright (C) 2015 Martin Willi * * Based on public domain code by Andrew Moon and Daniel J. Bernstein. */ #include <crypto/internal/poly1305.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/unaligned.h> void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 key[POLY1305_KEY_SIZE]) { poly1305_core_setkey(&desc->core_r, key); desc->s[0] = get_unaligned_le32(key + 16); desc->s[1] = get_unaligned_le32(key + 20); desc->s[2] = get_unaligned_le32(key + 24); desc->s[3] = get_unaligned_le32(key + 28); poly1305_core_init(&desc->h); desc->buflen = 0; desc->sset = true; desc->rset = 2; } EXPORT_SYMBOL_GPL(poly1305_init_generic); void poly1305_update_generic(struct poly1305_desc_ctx *desc, const u8 *src, unsigned int nbytes) { unsigned int bytes; if (unlikely(desc->buflen)) { bytes = min(nbytes, POLY1305_BLOCK_SIZE - desc->buflen); memcpy(desc->buf + desc->buflen, src, bytes); src += bytes; nbytes -= bytes; desc->buflen += bytes; if (desc->buflen == POLY1305_BLOCK_SIZE) { poly1305_core_blocks(&desc->h, &desc->core_r, desc->buf, 1, 1); desc->buflen = 0; } } if (likely(nbytes >= POLY1305_BLOCK_SIZE)) { poly1305_core_blocks(&desc->h, &desc->core_r, src, nbytes / POLY1305_BLOCK_SIZE, 1); src += nbytes - (nbytes % POLY1305_BLOCK_SIZE); nbytes %= POLY1305_BLOCK_SIZE; } if (unlikely(nbytes)) { desc->buflen = nbytes; memcpy(desc->buf, src, nbytes); } } EXPORT_SYMBOL_GPL(poly1305_update_generic); void poly1305_final_generic(struct poly1305_desc_ctx *desc, u8 *dst) { if (unlikely(desc->buflen)) { desc->buf[desc->buflen++] = 1; memset(desc->buf + desc->buflen, 0, POLY1305_BLOCK_SIZE - desc->buflen); poly1305_core_blocks(&desc->h, &desc->core_r, desc->buf, 1, 0); } poly1305_core_emit(&desc->h, desc->s, dst); *desc = (struct poly1305_desc_ctx){}; } EXPORT_SYMBOL_GPL(poly1305_final_generic); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Martin Willi <martin@strongswan.org>"); MODULE_DESCRIPTION("Poly1305 authenticator algorithm, RFC7539"); |
| 4 4 4 3 1 1 1 4 4 4 6 6 2 5 3 4 6 6 4 7 7 1 6 8 1 1 6 | 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 | // SPDX-License-Identifier: GPL-2.0 /* XDP sockets monitoring support * * Copyright(c) 2019 Intel Corporation. * * Author: Björn Töpel <bjorn.topel@intel.com> */ #include <linux/module.h> #include <net/xdp_sock.h> #include <linux/xdp_diag.h> #include <linux/sock_diag.h> #include "xsk_queue.h" #include "xsk.h" static int xsk_diag_put_info(const struct xdp_sock *xs, struct sk_buff *nlskb) { struct xdp_diag_info di = {}; di.ifindex = xs->dev ? xs->dev->ifindex : 0; di.queue_id = xs->queue_id; return nla_put(nlskb, XDP_DIAG_INFO, sizeof(di), &di); } static int xsk_diag_put_ring(const struct xsk_queue *queue, int nl_type, struct sk_buff *nlskb) { struct xdp_diag_ring dr = {}; dr.entries = queue->nentries; return nla_put(nlskb, nl_type, sizeof(dr), &dr); } static int xsk_diag_put_rings_cfg(const struct xdp_sock *xs, struct sk_buff *nlskb) { int err = 0; if (xs->rx) err = xsk_diag_put_ring(xs->rx, XDP_DIAG_RX_RING, nlskb); if (!err && xs->tx) err = xsk_diag_put_ring(xs->tx, XDP_DIAG_TX_RING, nlskb); return err; } static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb) { struct xsk_buff_pool *pool = xs->pool; struct xdp_umem *umem = xs->umem; struct xdp_diag_umem du = {}; int err; if (!umem) return 0; du.id = umem->id; du.size = umem->size; du.num_pages = umem->npgs; du.chunk_size = umem->chunk_size; du.headroom = umem->headroom; du.ifindex = (pool && pool->netdev) ? pool->netdev->ifindex : 0; du.queue_id = pool ? pool->queue_id : 0; du.flags = 0; if (umem->zc) du.flags |= XDP_DU_F_ZEROCOPY; du.refs = refcount_read(&umem->users); err = nla_put(nlskb, XDP_DIAG_UMEM, sizeof(du), &du); if (!err && pool && pool->fq) err = xsk_diag_put_ring(pool->fq, XDP_DIAG_UMEM_FILL_RING, nlskb); if (!err && pool && pool->cq) err = xsk_diag_put_ring(pool->cq, XDP_DIAG_UMEM_COMPLETION_RING, nlskb); return err; } static int xsk_diag_put_stats(const struct xdp_sock *xs, struct sk_buff *nlskb) { struct xdp_diag_stats du = {}; du.n_rx_dropped = xs->rx_dropped; du.n_rx_invalid = xskq_nb_invalid_descs(xs->rx); du.n_rx_full = xs->rx_queue_full; du.n_fill_ring_empty = xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0; du.n_tx_invalid = xskq_nb_invalid_descs(xs->tx); du.n_tx_ring_empty = xskq_nb_queue_empty_descs(xs->tx); return nla_put(nlskb, XDP_DIAG_STATS, sizeof(du), &du); } static int xsk_diag_fill(struct sock *sk, struct sk_buff *nlskb, struct xdp_diag_req *req, struct user_namespace *user_ns, u32 portid, u32 seq, u32 flags, int sk_ino) { struct xdp_sock *xs = xdp_sk(sk); struct xdp_diag_msg *msg; struct nlmsghdr *nlh; nlh = nlmsg_put(nlskb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*msg), flags); if (!nlh) return -EMSGSIZE; msg = nlmsg_data(nlh); memset(msg, 0, sizeof(*msg)); msg->xdiag_family = AF_XDP; msg->xdiag_type = sk->sk_type; msg->xdiag_ino = sk_ino; sock_diag_save_cookie(sk, msg->xdiag_cookie); mutex_lock(&xs->mutex); if (READ_ONCE(xs->state) == XSK_UNBOUND) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_INFO) && xsk_diag_put_info(xs, nlskb)) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_INFO) && nla_put_u32(nlskb, XDP_DIAG_UID, from_kuid_munged(user_ns, sock_i_uid(sk)))) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_RING_CFG) && xsk_diag_put_rings_cfg(xs, nlskb)) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_UMEM) && xsk_diag_put_umem(xs, nlskb)) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_MEMINFO) && sock_diag_put_meminfo(sk, nlskb, XDP_DIAG_MEMINFO)) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_STATS) && xsk_diag_put_stats(xs, nlskb)) goto out_nlmsg_trim; mutex_unlock(&xs->mutex); nlmsg_end(nlskb, nlh); return 0; out_nlmsg_trim: mutex_unlock(&xs->mutex); nlmsg_cancel(nlskb, nlh); return -EMSGSIZE; } static int xsk_diag_dump(struct sk_buff *nlskb, struct netlink_callback *cb) { struct xdp_diag_req *req = nlmsg_data(cb->nlh); struct net *net = sock_net(nlskb->sk); int num = 0, s_num = cb->args[0]; struct sock *sk; mutex_lock(&net->xdp.lock); sk_for_each(sk, &net->xdp.list) { if (!net_eq(sock_net(sk), net)) continue; if (num++ < s_num) continue; if (xsk_diag_fill(sk, nlskb, req, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, sock_i_ino(sk)) < 0) { num--; break; } } mutex_unlock(&net->xdp.lock); cb->args[0] = num; return nlskb->len; } static int xsk_diag_handler_dump(struct sk_buff *nlskb, struct nlmsghdr *hdr) { struct netlink_dump_control c = { .dump = xsk_diag_dump }; int hdrlen = sizeof(struct xdp_diag_req); struct net *net = sock_net(nlskb->sk); if (nlmsg_len(hdr) < hdrlen) return -EINVAL; if (!(hdr->nlmsg_flags & NLM_F_DUMP)) return -EOPNOTSUPP; return netlink_dump_start(net->diag_nlsk, nlskb, hdr, &c); } static const struct sock_diag_handler xsk_diag_handler = { .owner = THIS_MODULE, .family = AF_XDP, .dump = xsk_diag_handler_dump, }; static int __init xsk_diag_init(void) { return sock_diag_register(&xsk_diag_handler); } static void __exit xsk_diag_exit(void) { sock_diag_unregister(&xsk_diag_handler); } module_init(xsk_diag_init); module_exit(xsk_diag_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("XDP socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, AF_XDP); |
| 3 3 | 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 | /* 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 { unsigned long *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, unsigned long *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(unsigned long *word, int bit); int out_of_line_wait_on_bit(unsigned long *word, int, wait_bit_action_f *action, unsigned int mode); int out_of_line_wait_on_bit_timeout(unsigned long *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout); int out_of_line_wait_on_bit_lock(unsigned long *word, int, wait_bit_action_f *action, unsigned int mode); struct wait_queue_head *bit_waitqueue(unsigned long *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); /** * wait_on_bit - wait for a bit to be cleared * @word: the address containing the bit being waited on * @bit: the bit at that address being waited on * @mode: the task state to sleep in * * Wait for the given bit in an unsigned long or bitmap (see DECLARE_BITMAP()) * to be cleared. The clearing of the bit must be signalled with * wake_up_bit(), often as clear_and_wake_up_bit(). * * The process will wait on a waitqueue selected by hash from a shared * pool. It will only be woken on a wake_up for the target bit, even * if other processes on the same queue are waiting for other bits. * * Returned value will be zero if the bit was cleared in which case the * call has ACQUIRE semantics, or %-EINTR if the process received a * signal and the mode permitted wake up on that signal. */ static inline int wait_on_bit(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_bit_acquire(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 address containing the bit being waited on * @bit: the bit at that address being waited on * @mode: the task state to sleep in * * Wait for the given bit in an unsigned long or bitmap (see DECLARE_BITMAP()) * to be cleared. The clearing of the bit must be signalled with * wake_up_bit(), often as clear_and_wake_up_bit(). * * 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 in which case the * call has ACQUIRE semantics, or %-EINTR if the process received a * signal and the mode permitted wake up on that signal. */ static inline int wait_on_bit_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_bit_acquire(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 to elapse * @word: the address containing the bit being waited on * @bit: the bit at that address being waited on * @mode: the task state to sleep in * @timeout: timeout, in jiffies * * Wait for the given bit in an unsigned long or bitmap (see * DECLARE_BITMAP()) to be cleared, or for a timeout to expire. The * clearing of the bit must be signalled with wake_up_bit(), often as * clear_and_wake_up_bit(). * * This is similar to wait_on_bit(), except it also takes a timeout * parameter. * * Returned value will be zero if the bit was cleared in which case the * call has ACQUIRE semantics, or %-EINTR if the process received a * signal and the mode permitted wake up on that signal, or %-EAGAIN if the * timeout elapsed. */ static inline int wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, unsigned long timeout) { might_sleep(); if (!test_bit_acquire(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 address containing the bit waited on * @bit: the bit at that address being waited on * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * Wait for the given bit in an unsigned long or bitmap (see DECLARE_BITMAP()) * to be cleared. The clearing of the bit must be signalled with * wake_up_bit(), often as clear_and_wake_up_bit(). * * This is similar to wait_on_bit(), but calls @action() instead of * schedule() for the actual waiting. * * Returned value will be zero if the bit was cleared in which case the * call has ACQUIRE semantics, or the error code returned by @action if * that call returned non-zero. */ static inline int wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, unsigned mode) { might_sleep(); if (!test_bit_acquire(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, then set it * @word: the address containing the bit being waited on * @bit: the bit of the word being waited on and set * @mode: the task state to sleep in * * Wait for the given bit in an unsigned long or bitmap (see * DECLARE_BITMAP()) to be cleared. The clearing of the bit must be * signalled with wake_up_bit(), often as clear_and_wake_up_bit(). As * soon as it is clear, atomically set it and return. * * This is similar to wait_on_bit(), but sets the bit before returning. * * Returned value will be zero if the bit was successfully set in which * case the call has the same memory sequencing semantics as * test_and_clear_bit(), or %-EINTR if the process received a signal and * the mode permitted wake up on that signal. */ 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, then set it * @word: the address containing the bit being waited on * @bit: the bit of the word being waited on and set * @mode: the task state to sleep in * * Wait for the given bit in an unsigned long or bitmap (see * DECLARE_BITMAP()) to be cleared. The clearing of the bit must be * signalled with wake_up_bit(), often as clear_and_wake_up_bit(). As * soon as it is clear, atomically set it and return. * * This is similar to wait_on_bit_lock(), but calls io_schedule() instead * of schedule(). * * 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, then set it * @word: the address containing the bit being waited on * @bit: the bit of the word being waited on and set * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * This is similar to wait_on_bit_lock(), but calls @action() instead of * schedule() for the actual waiting. * * Returned value will be zero if the bit was successfully set in which * case the call has the same memory sequencing semantics as * test_and_clear_bit(), or the error code returned by @action if that * call returned non-zero. */ 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_io(var, condition) \ ___wait_var_event(var, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ io_schedule()) /** * wait_var_event - wait for a variable to be updated and notified * @var: the address of variable being waited on * @condition: the condition to wait for * * Wait for a @condition to be true, only re-checking when a wake up is * received for the given @var (an arbitrary kernel address which need * not be directly related to the given condition, but usually is). * * The process will wait on a waitqueue selected by hash from a shared * pool. It will only be woken on a wake_up for the given address. * * The condition should normally use smp_load_acquire() or a similarly * ordered access to ensure that any changes to memory made before the * condition became true will be visible after the wait completes. */ #define wait_var_event(var, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __wait_var_event(var, condition); \ } while (0) /** * wait_var_event_io - wait for a variable to be updated and notified * @var: the address of variable being waited on * @condition: the condition to wait for * * Wait for an IO related @condition to be true, only re-checking when a * wake up is received for the given @var (an arbitrary kernel address * which need not be directly related to the given condition, but * usually is). * * The process will wait on a waitqueue selected by hash from a shared * pool. It will only be woken on a wake_up for the given address. * * This is similar to wait_var_event(), but calls io_schedule() instead * of schedule(). * * The condition should normally use smp_load_acquire() or a similarly * ordered access to ensure that any changes to memory made before the * condition became true will be visible after the wait completes. */ #define wait_var_event_io(var, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __wait_var_event_io(var, condition); \ } while (0) #define __wait_var_event_killable(var, condition) \ ___wait_var_event(var, condition, TASK_KILLABLE, 0, 0, \ schedule()) /** * wait_var_event_killable - wait for a variable to be updated and notified * @var: the address of variable being waited on * @condition: the condition to wait for * * Wait for a @condition to be true or a fatal signal to be received, * only re-checking the condition when a wake up is received for the given * @var (an arbitrary kernel address which need not be directly related * to the given condition, but usually is). * * This is similar to wait_var_event() but returns a value which is * 0 if the condition became true, or %-ERESTARTSYS if a fatal signal * was received. * * The condition should normally use smp_load_acquire() or a similarly * ordered access to ensure that any changes to memory made before the * condition became true will be visible after the wait completes. */ #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)) /** * wait_var_event_timeout - wait for a variable to be updated or a timeout to expire * @var: the address of variable being waited on * @condition: the condition to wait for * @timeout: maximum time to wait in jiffies * * Wait for a @condition to be true or a timeout to expire, only * re-checking the condition when a wake up is received for the given * @var (an arbitrary kernel address which need not be directly related * to the given condition, but usually is). * * This is similar to wait_var_event() but returns a value which is 0 if * the timeout expired and the condition was still false, or the * remaining time left in the timeout (but at least 1) if the condition * was found to be true. * * The condition should normally use smp_load_acquire() or a similarly * ordered access to ensure that any changes to memory made before the * condition became true will be visible after the wait completes. */ #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()) /** * wait_var_event_killable - wait for a variable to be updated and notified * @var: the address of variable being waited on * @condition: the condition to wait for * * Wait for a @condition to be true or a signal to be received, only * re-checking the condition when a wake up is received for the given * @var (an arbitrary kernel address which need not be directly related * to the given condition, but usually is). * * This is similar to wait_var_event() but returns a value which is 0 if * the condition became true, or %-ERESTARTSYS if a signal was received. * * The condition should normally use smp_load_acquire() or a similarly * ordered access to ensure that any changes to memory made before the * condition became true will be visible after the wait completes. */ #define wait_var_event_interruptible(var, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_var_event_interruptible(var, condition); \ __ret; \ }) /** * wait_var_event_any_lock - wait for a variable to be updated under a lock * @var: the address of the variable being waited on * @condition: condition to wait for * @lock: the object that is locked to protect updates to the variable * @type: prefix on lock and unlock operations * @state: waiting state, %TASK_UNINTERRUPTIBLE etc. * * Wait for a condition which can only be reliably tested while holding * a lock. The variables assessed in the condition will normal be updated * under the same lock, and the wake up should be signalled with * wake_up_var_locked() under the same lock. * * This is similar to wait_var_event(), but assumes a lock is held * while calling this function and while updating the variable. * * This must be called while the given lock is held and the lock will be * dropped when schedule() is called to wait for a wake up, and will be * reclaimed before testing the condition again. The functions used to * unlock and lock the object are constructed by appending _unlock and _lock * to @type. * * Return %-ERESTARTSYS if a signal arrives which is allowed to interrupt * the wait according to @state. */ #define wait_var_event_any_lock(var, condition, lock, type, state) \ ({ \ int __ret = 0; \ if (!(condition)) \ __ret = ___wait_var_event(var, condition, state, 0, 0, \ type ## _unlock(lock); \ schedule(); \ type ## _lock(lock)); \ __ret; \ }) /** * wait_var_event_spinlock - wait for a variable to be updated under a spinlock * @var: the address of the variable being waited on * @condition: condition to wait for * @lock: the spinlock which protects updates to the variable * * Wait for a condition which can only be reliably tested while holding * a spinlock. The variables assessed in the condition will normal be updated * under the same spinlock, and the wake up should be signalled with * wake_up_var_locked() under the same spinlock. * * This is similar to wait_var_event(), but assumes a spinlock is held * while calling this function and while updating the variable. * * This must be called while the given lock is held and the lock will be * dropped when schedule() is called to wait for a wake up, and will be * reclaimed before testing the condition again. */ #define wait_var_event_spinlock(var, condition, lock) \ wait_var_event_any_lock(var, condition, lock, spin, TASK_UNINTERRUPTIBLE) /** * wait_var_event_mutex - wait for a variable to be updated under a mutex * @var: the address of the variable being waited on * @condition: condition to wait for * @mutex: the mutex which protects updates to the variable * * Wait for a condition which can only be reliably tested while holding * a mutex. The variables assessed in the condition will normal be * updated under the same mutex, and the wake up should be signalled * with wake_up_var_locked() under the same mutex. * * This is similar to wait_var_event(), but assumes a mutex is held * while calling this function and while updating the variable. * * This must be called while the given mutex is held and the mutex will be * dropped when schedule() is called to wait for a wake up, and will be * reclaimed before testing the condition again. */ #define wait_var_event_mutex(var, condition, lock) \ wait_var_event_any_lock(var, condition, lock, mutex, TASK_UNINTERRUPTIBLE) /** * wake_up_var_protected - wake up waiters for a variable asserting that it is safe * @var: the address of the variable being waited on * @cond: the condition which afirms this is safe * * When waking waiters which use wait_var_event_any_lock() the waker must be * holding the reelvant lock to avoid races. This version of wake_up_var() * asserts that the relevant lock is held and so no barrier is needed. * The @cond is only tested when CONFIG_LOCKDEP is enabled. */ #define wake_up_var_protected(var, cond) \ do { \ lockdep_assert(cond); \ wake_up_var(var); \ } while (0) /** * wake_up_var_locked - wake up waiters for a variable while holding a spinlock or mutex * @var: the address of the variable being waited on * @lock: The spinlock or mutex what protects the variable * * Send a wake up for the given variable which should be waited for with * wait_var_event_spinlock() or wait_var_event_mutex(). Unlike wake_up_var(), * no extra barriers are needed as the locking provides sufficient sequencing. */ #define wake_up_var_locked(var, lock) \ wake_up_var_protected(var, lockdep_is_held(lock)) /** * 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 address containing the bit being waited on * * The designated bit is cleared and any tasks waiting in wait_on_bit() * or similar will be woken. This call has RELEASE semantics so that * any changes to memory made before this call are guaranteed to be visible * after the corresponding wait_on_bit() completes. */ static inline void clear_and_wake_up_bit(int bit, unsigned long *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); } /** * test_and_clear_wake_up_bit - clear a bit if it was set: wake up anyone waiting on that bit * @bit: the bit of the word being waited on * @word: the address of memory containing that bit * * If the bit is set and can be atomically cleared, any tasks waiting in * wait_on_bit() or similar will be woken. This call has the same * complete ordering semantics as test_and_clear_bit(). Any changes to * memory made before this call are guaranteed to be visible after the * corresponding wait_on_bit() completes. * * Returns %true if the bit was successfully set and the wake up was sent. */ static inline bool test_and_clear_wake_up_bit(int bit, unsigned long *word) { if (!test_and_clear_bit(bit, word)) return false; /* no extra barrier required */ wake_up_bit(word, bit); return true; } /** * atomic_dec_and_wake_up - decrement an atomic_t and if zero, wake up waiters * @var: the variable to dec and test * * Decrements the atomic variable and if it reaches zero, send a wake_up to any * processes waiting on the variable. * * This function has the same complete ordering semantics as atomic_dec_and_test. * * Returns %true is the variable reaches zero and the wake up was sent. */ static inline bool atomic_dec_and_wake_up(atomic_t *var) { if (!atomic_dec_and_test(var)) return false; /* No extra barrier required */ wake_up_var(var); return true; } /** * store_release_wake_up - update a variable and send a wake_up * @var: the address of the variable to be updated and woken * @val: the value to store in the variable. * * Store the given value in the variable send a wake up to any tasks * waiting on the variable. All necessary barriers are included to ensure * the task calling wait_var_event() sees the new value and all values * written to memory before this call. */ #define store_release_wake_up(var, val) \ do { \ smp_store_release(var, val); \ smp_mb(); \ wake_up_var(var); \ } while (0) #endif /* _LINUX_WAIT_BIT_H */ |
| 3 12204 12433 310 1 1 670 | 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-only */ /* * kref.h - library routines for handling generic reference counted objects * * Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Corp. * * based on kobject.h which was: * Copyright (C) 2002-2003 Patrick Mochel <mochel@osdl.org> * Copyright (C) 2002-2003 Open Source Development Labs */ #ifndef _KREF_H_ #define _KREF_H_ #include <linux/spinlock.h> #include <linux/refcount.h> struct kref { refcount_t refcount; }; #define KREF_INIT(n) { .refcount = REFCOUNT_INIT(n), } /** * kref_init - initialize object. * @kref: object in question. */ static inline void kref_init(struct kref *kref) { refcount_set(&kref->refcount, 1); } static inline unsigned int kref_read(const struct kref *kref) { return refcount_read(&kref->refcount); } /** * kref_get - increment refcount for object. * @kref: object. */ static inline void kref_get(struct kref *kref) { refcount_inc(&kref->refcount); } /** * kref_put - decrement refcount for object. * @kref: object. * @release: pointer to the function that will clean up the object when the * last reference to the object is released. * This pointer is required, and it is not acceptable to pass kfree * in as this function. * * Decrement the refcount, and if 0, call release(). * Return 1 if the object was removed, otherwise return 0. Beware, if this * function returns 0, you still can not count on the kref from remaining in * memory. Only use the return value if you want to see if the kref is now * gone, not present. */ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)) { if (refcount_dec_and_test(&kref->refcount)) { release(kref); return 1; } return 0; } static inline int kref_put_mutex(struct kref *kref, |