| 1 1 1 1 7 6 6 6 7 2 2 3 3 5 2 3 1 1 1 1 5 1 1 4 10 2 1 7 1 2 3 2 6 5 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Point-to-Point Tunneling Protocol for Linux * * Authors: Dmitry Kozlov <xeb@mail.ru> */ #include <linux/string.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/net.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/init.h> #include <linux/ppp_channel.h> #include <linux/ppp_defs.h> #include <linux/if_pppox.h> #include <linux/ppp-ioctl.h> #include <linux/notifier.h> #include <linux/file.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/rcupdate.h> #include <linux/security.h> #include <linux/spinlock.h> #include <net/sock.h> #include <net/protocol.h> #include <net/ip.h> #include <net/icmp.h> #include <net/route.h> #include <net/gre.h> #include <net/pptp.h> #include <linux/uaccess.h> #define PPTP_DRIVER_VERSION "0.8.5" #define MAX_CALLID 65535 static DECLARE_BITMAP(callid_bitmap, MAX_CALLID + 1); static struct pppox_sock __rcu **callid_sock; static DEFINE_SPINLOCK(chan_lock); static struct proto pptp_sk_proto __read_mostly; static const struct ppp_channel_ops pptp_chan_ops; static const struct proto_ops pptp_ops; static struct pppox_sock *lookup_chan(u16 call_id, __be32 s_addr) { struct pppox_sock *sock; struct pptp_opt *opt; rcu_read_lock(); sock = rcu_dereference(callid_sock[call_id]); if (sock) { opt = &sock->proto.pptp; if (opt->dst_addr.sin_addr.s_addr != s_addr) sock = NULL; else sock_hold(sk_pppox(sock)); } rcu_read_unlock(); return sock; } static int lookup_chan_dst(u16 call_id, __be32 d_addr) { struct pppox_sock *sock; struct pptp_opt *opt; int i; rcu_read_lock(); i = 1; for_each_set_bit_from(i, callid_bitmap, MAX_CALLID) { sock = rcu_dereference(callid_sock[i]); if (!sock) continue; opt = &sock->proto.pptp; if (opt->dst_addr.call_id == call_id && opt->dst_addr.sin_addr.s_addr == d_addr) break; } rcu_read_unlock(); return i < MAX_CALLID; } static int add_chan(struct pppox_sock *sock, struct pptp_addr *sa) { static int call_id; spin_lock(&chan_lock); if (!sa->call_id) { call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, call_id + 1); if (call_id == MAX_CALLID) { call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, 1); if (call_id == MAX_CALLID) goto out_err; } sa->call_id = call_id; } else if (test_bit(sa->call_id, callid_bitmap)) { goto out_err; } sock->proto.pptp.src_addr = *sa; set_bit(sa->call_id, callid_bitmap); rcu_assign_pointer(callid_sock[sa->call_id], sock); spin_unlock(&chan_lock); return 0; out_err: spin_unlock(&chan_lock); return -1; } static void del_chan(struct pppox_sock *sock) { spin_lock(&chan_lock); clear_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap); RCU_INIT_POINTER(callid_sock[sock->proto.pptp.src_addr.call_id], NULL); spin_unlock(&chan_lock); } static struct rtable *pptp_route_output(const struct pppox_sock *po, struct flowi4 *fl4) { const struct sock *sk = &po->sk; struct net *net; net = sock_net(sk); flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, 0, RT_SCOPE_UNIVERSE, IPPROTO_GRE, 0, po->proto.pptp.dst_addr.sin_addr.s_addr, po->proto.pptp.src_addr.sin_addr.s_addr, 0, 0, sock_net_uid(net, sk)); security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(net, fl4, sk); } static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) { struct sock *sk = chan->private; struct pppox_sock *po = pppox_sk(sk); struct net *net = sock_net(sk); struct pptp_opt *opt = &po->proto.pptp; struct pptp_gre_header *hdr; unsigned int header_len = sizeof(*hdr); struct flowi4 fl4; int islcp; int len; unsigned char *data; __u32 seq_recv; struct rtable *rt; struct net_device *tdev; struct iphdr *iph; int max_headroom; if (sk_pppox(po)->sk_state & PPPOX_DEAD) goto tx_error; rt = pptp_route_output(po, &fl4); if (IS_ERR(rt)) goto tx_error; tdev = rt->dst.dev; max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(*iph) + sizeof(*hdr) + 2; if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); goto tx_error; } if (skb->sk) skb_set_owner_w(new_skb, skb->sk); consume_skb(skb); skb = new_skb; } data = skb->data; islcp = ((data[0] << 8) + data[1]) == PPP_LCP && 1 <= data[2] && data[2] <= 7; /* compress protocol field */ if ((opt->ppp_flags & SC_COMP_PROT) && data[0] == 0 && !islcp) skb_pull(skb, 1); /* Put in the address/control bytes if necessary */ if ((opt->ppp_flags & SC_COMP_AC) == 0 || islcp) { data = skb_push(skb, 2); data[0] = PPP_ALLSTATIONS; data[1] = PPP_UI; } len = skb->len; seq_recv = opt->seq_recv; if (opt->ack_sent == seq_recv) header_len -= sizeof(hdr->ack); /* Push down and install GRE header */ skb_push(skb, header_len); hdr = (struct pptp_gre_header *)(skb->data); hdr->gre_hd.flags = GRE_KEY | GRE_VERSION_1 | GRE_SEQ; hdr->gre_hd.protocol = GRE_PROTO_PPP; hdr->call_id = htons(opt->dst_addr.call_id); hdr->seq = htonl(++opt->seq_sent); if (opt->ack_sent != seq_recv) { /* send ack with this message */ hdr->gre_hd.flags |= GRE_ACK; hdr->ack = htonl(seq_recv); opt->ack_sent = seq_recv; } hdr->payload_len = htons(len); /* Push down and install the IP header. */ skb_reset_transport_header(skb); skb_push(skb, sizeof(*iph)); skb_reset_network_header(skb); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); iph = ip_hdr(skb); iph->version = 4; iph->ihl = sizeof(struct iphdr) >> 2; if (ip_dont_fragment(sk, &rt->dst)) iph->frag_off = htons(IP_DF); else iph->frag_off = 0; iph->protocol = IPPROTO_GRE; iph->tos = 0; iph->daddr = fl4.daddr; iph->saddr = fl4.saddr; iph->ttl = ip4_dst_hoplimit(&rt->dst); iph->tot_len = htons(skb->len); skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); nf_reset_ct(skb); skb->ip_summed = CHECKSUM_NONE; ip_select_ident(net, skb, NULL); ip_send_check(iph); ip_local_out(net, skb->sk, skb); return 1; tx_error: kfree_skb(skb); return 1; } static int pptp_rcv_core(struct sock *sk, struct sk_buff *skb) { struct pppox_sock *po = pppox_sk(sk); struct pptp_opt *opt = &po->proto.pptp; int headersize, payload_len, seq; __u8 *payload; struct pptp_gre_header *header; if (!(sk->sk_state & PPPOX_CONNECTED)) { if (sock_queue_rcv_skb(sk, skb)) goto drop; return NET_RX_SUCCESS; } header = (struct pptp_gre_header *)(skb->data); headersize = sizeof(*header); /* test if acknowledgement present */ if (GRE_IS_ACK(header->gre_hd.flags)) { __u32 ack; if (!pskb_may_pull(skb, headersize)) goto drop; header = (struct pptp_gre_header *)(skb->data); /* ack in different place if S = 0 */ ack = GRE_IS_SEQ(header->gre_hd.flags) ? ntohl(header->ack) : ntohl(header->seq); if (ack > opt->ack_recv) opt->ack_recv = ack; /* also handle sequence number wrap-around */ if (WRAPPED(ack, opt->ack_recv)) opt->ack_recv = ack; } else { headersize -= sizeof(header->ack); } /* test if payload present */ if (!GRE_IS_SEQ(header->gre_hd.flags)) goto drop; payload_len = ntohs(header->payload_len); seq = ntohl(header->seq); /* check for incomplete packet (length smaller than expected) */ if (!pskb_may_pull(skb, headersize + payload_len)) goto drop; payload = skb->data + headersize; /* check for expected sequence number */ if (seq < opt->seq_recv + 1 || WRAPPED(opt->seq_recv, seq)) { if ((payload[0] == PPP_ALLSTATIONS) && (payload[1] == PPP_UI) && (PPP_PROTOCOL(payload) == PPP_LCP) && ((payload[4] == PPP_LCP_ECHOREQ) || (payload[4] == PPP_LCP_ECHOREP))) goto allow_packet; } else { opt->seq_recv = seq; allow_packet: skb_pull(skb, headersize); if (payload[0] == PPP_ALLSTATIONS && payload[1] == PPP_UI) { /* chop off address/control */ if (skb->len < 3) goto drop; skb_pull(skb, 2); } skb->ip_summed = CHECKSUM_NONE; skb_set_network_header(skb, skb->head-skb->data); ppp_input(&po->chan, skb); return NET_RX_SUCCESS; } drop: kfree_skb(skb); return NET_RX_DROP; } static int pptp_rcv(struct sk_buff *skb) { struct pppox_sock *po; struct pptp_gre_header *header; struct iphdr *iph; if (skb->pkt_type != PACKET_HOST) goto drop; if (!pskb_may_pull(skb, 12)) goto drop; iph = ip_hdr(skb); header = (struct pptp_gre_header *)skb->data; if (header->gre_hd.protocol != GRE_PROTO_PPP || /* PPTP-GRE protocol for PPTP */ GRE_IS_CSUM(header->gre_hd.flags) || /* flag CSUM should be clear */ GRE_IS_ROUTING(header->gre_hd.flags) || /* flag ROUTING should be clear */ !GRE_IS_KEY(header->gre_hd.flags) || /* flag KEY should be set */ (header->gre_hd.flags & GRE_FLAGS)) /* flag Recursion Ctrl should be clear */ /* if invalid, discard this packet */ goto drop; po = lookup_chan(ntohs(header->call_id), iph->saddr); if (po) { skb_dst_drop(skb); nf_reset_ct(skb); return sk_receive_skb(sk_pppox(po), skb, 0); } drop: kfree_skb(skb); return NET_RX_DROP; } static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr, int sockaddr_len) { struct sock *sk = sock->sk; struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr; struct pppox_sock *po = pppox_sk(sk); int error = 0; if (sockaddr_len < sizeof(struct sockaddr_pppox)) return -EINVAL; lock_sock(sk); if (sk->sk_state & PPPOX_DEAD) { error = -EALREADY; goto out; } if (sk->sk_state & PPPOX_BOUND) { error = -EBUSY; goto out; } if (add_chan(po, &sp->sa_addr.pptp)) error = -EBUSY; else sk->sk_state |= PPPOX_BOUND; out: release_sock(sk); return error; } static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr, int sockaddr_len, int flags) { struct sock *sk = sock->sk; struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr; struct pppox_sock *po = pppox_sk(sk); struct pptp_opt *opt = &po->proto.pptp; struct rtable *rt; struct flowi4 fl4; int error = 0; if (sockaddr_len < sizeof(struct sockaddr_pppox)) return -EINVAL; if (sp->sa_protocol != PX_PROTO_PPTP) return -EINVAL; if (lookup_chan_dst(sp->sa_addr.pptp.call_id, sp->sa_addr.pptp.sin_addr.s_addr)) return -EALREADY; lock_sock(sk); /* Check for already bound sockets */ if (sk->sk_state & PPPOX_CONNECTED) { error = -EBUSY; goto end; } /* Check for already disconnected sockets, on attempts to disconnect */ if (sk->sk_state & PPPOX_DEAD) { error = -EALREADY; goto end; } if (!opt->src_addr.sin_addr.s_addr || !sp->sa_addr.pptp.sin_addr.s_addr) { error = -EINVAL; goto end; } po->chan.private = sk; po->chan.ops = &pptp_chan_ops; rt = pptp_route_output(po, &fl4); if (IS_ERR(rt)) { error = -EHOSTUNREACH; goto end; } sk_setup_caps(sk, &rt->dst); po->chan.mtu = dst_mtu(&rt->dst); if (!po->chan.mtu) po->chan.mtu = PPP_MRU; po->chan.mtu -= PPTP_HEADER_OVERHEAD; po->chan.hdrlen = 2 + sizeof(struct pptp_gre_header); po->chan.direct_xmit = true; error = ppp_register_channel(&po->chan); if (error) { pr_err("PPTP: failed to register PPP channel (%d)\n", error); goto end; } opt->dst_addr = sp->sa_addr.pptp; sk->sk_state |= PPPOX_CONNECTED; end: release_sock(sk); return error; } static int pptp_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { int len = sizeof(struct sockaddr_pppox); struct sockaddr_pppox sp; memset(&sp.sa_addr, 0, sizeof(sp.sa_addr)); sp.sa_family = AF_PPPOX; sp.sa_protocol = PX_PROTO_PPTP; sp.sa_addr.pptp = pppox_sk(sock->sk)->proto.pptp.src_addr; memcpy(uaddr, &sp, len); return len; } static int pptp_release(struct socket *sock) { struct sock *sk = sock->sk; struct pppox_sock *po; int error = 0; if (!sk) return 0; lock_sock(sk); if (sock_flag(sk, SOCK_DEAD)) { release_sock(sk); return -EBADF; } po = pppox_sk(sk); del_chan(po); synchronize_rcu(); pppox_unbind_sock(sk); sk->sk_state = PPPOX_DEAD; sock_orphan(sk); sock->sk = NULL; release_sock(sk); sock_put(sk); return error; } static void pptp_sock_destruct(struct sock *sk) { if (!(sk->sk_state & PPPOX_DEAD)) { del_chan(pppox_sk(sk)); pppox_unbind_sock(sk); } skb_queue_purge(&sk->sk_receive_queue); dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); } static int pptp_create(struct net *net, struct socket *sock, int kern) { int error = -ENOMEM; struct sock *sk; struct pppox_sock *po; struct pptp_opt *opt; sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pptp_sk_proto, kern); if (!sk) goto out; sock_init_data(sock, sk); sock->state = SS_UNCONNECTED; sock->ops = &pptp_ops; sk->sk_backlog_rcv = pptp_rcv_core; sk->sk_state = PPPOX_NONE; sk->sk_type = SOCK_STREAM; sk->sk_family = PF_PPPOX; sk->sk_protocol = PX_PROTO_PPTP; sk->sk_destruct = pptp_sock_destruct; po = pppox_sk(sk); opt = &po->proto.pptp; opt->seq_sent = 0; opt->seq_recv = 0xffffffff; opt->ack_recv = 0; opt->ack_sent = 0xffffffff; error = 0; out: return error; } static int pptp_ppp_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg) { struct sock *sk = chan->private; struct pppox_sock *po = pppox_sk(sk); struct pptp_opt *opt = &po->proto.pptp; void __user *argp = (void __user *)arg; int __user *p = argp; int err, val; err = -EFAULT; switch (cmd) { case PPPIOCGFLAGS: val = opt->ppp_flags; if (put_user(val, p)) break; err = 0; break; case PPPIOCSFLAGS: if (get_user(val, p)) break; opt->ppp_flags = val & ~SC_RCV_BITS; err = 0; break; default: err = -ENOTTY; } return err; } static const struct ppp_channel_ops pptp_chan_ops = { .start_xmit = pptp_xmit, .ioctl = pptp_ppp_ioctl, }; static struct proto pptp_sk_proto __read_mostly = { .name = "PPTP", .owner = THIS_MODULE, .obj_size = sizeof(struct pppox_sock), }; static const struct proto_ops pptp_ops = { .family = AF_PPPOX, .owner = THIS_MODULE, .release = pptp_release, .bind = pptp_bind, .connect = pptp_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = pptp_getname, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .sendmsg = sock_no_sendmsg, .recvmsg = sock_no_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = pppox_compat_ioctl, #endif }; static const struct pppox_proto pppox_pptp_proto = { .create = pptp_create, .owner = THIS_MODULE, }; static const struct gre_protocol gre_pptp_protocol = { .handler = pptp_rcv, }; static int __init pptp_init_module(void) { int err = 0; pr_info("PPTP driver version " PPTP_DRIVER_VERSION "\n"); callid_sock = vzalloc(array_size(sizeof(void *), (MAX_CALLID + 1))); if (!callid_sock) return -ENOMEM; err = gre_add_protocol(&gre_pptp_protocol, GREPROTO_PPTP); if (err) { pr_err("PPTP: can't add gre protocol\n"); goto out_mem_free; } err = proto_register(&pptp_sk_proto, 0); if (err) { pr_err("PPTP: can't register sk_proto\n"); goto out_gre_del_protocol; } err = register_pppox_proto(PX_PROTO_PPTP, &pppox_pptp_proto); if (err) { pr_err("PPTP: can't register pppox_proto\n"); goto out_unregister_sk_proto; } return 0; out_unregister_sk_proto: proto_unregister(&pptp_sk_proto); out_gre_del_protocol: gre_del_protocol(&gre_pptp_protocol, GREPROTO_PPTP); out_mem_free: vfree(callid_sock); return err; } static void __exit pptp_exit_module(void) { unregister_pppox_proto(PX_PROTO_PPTP); proto_unregister(&pptp_sk_proto); gre_del_protocol(&gre_pptp_protocol, GREPROTO_PPTP); vfree(callid_sock); } module_init(pptp_init_module); module_exit(pptp_exit_module); MODULE_DESCRIPTION("Point-to-Point Tunneling Protocol"); MODULE_AUTHOR("D. Kozlov <xeb@mail.ru>"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NET_PF_PROTO(PF_PPPOX, PX_PROTO_PPTP); |
| 51 54 53 50 53 49 51 51 51 48 47 45 46 52 51 52 52 52 9 51 51 203 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 7 9 7 5 7 5 9 7 9 9 9 48 6 6 4 4 6 4 6 6 6 6 6 6 6 6 6 6 4 4 45 45 2 1 1 8 7 5 1 3 47 47 47 41 41 46 46 46 40 40 40 41 41 13 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Media entity * * Copyright (C) 2010 Nokia Corporation * * Contacts: Laurent Pinchart <laurent.pinchart@ideasonboard.com> * Sakari Ailus <sakari.ailus@iki.fi> */ #include <linux/bitmap.h> #include <linux/list.h> #include <linux/property.h> #include <linux/slab.h> #include <media/media-entity.h> #include <media/media-device.h> static inline const char *intf_type(struct media_interface *intf) { switch (intf->type) { case MEDIA_INTF_T_DVB_FE: return "dvb-frontend"; case MEDIA_INTF_T_DVB_DEMUX: return "dvb-demux"; case MEDIA_INTF_T_DVB_DVR: return "dvb-dvr"; case MEDIA_INTF_T_DVB_CA: return "dvb-ca"; case MEDIA_INTF_T_DVB_NET: return "dvb-net"; case MEDIA_INTF_T_V4L_VIDEO: return "v4l-video"; case MEDIA_INTF_T_V4L_VBI: return "v4l-vbi"; case MEDIA_INTF_T_V4L_RADIO: return "v4l-radio"; case MEDIA_INTF_T_V4L_SUBDEV: return "v4l-subdev"; case MEDIA_INTF_T_V4L_SWRADIO: return "v4l-swradio"; case MEDIA_INTF_T_V4L_TOUCH: return "v4l-touch"; default: return "unknown-intf"; } }; static inline const char *link_type_name(struct media_link *link) { switch (link->flags & MEDIA_LNK_FL_LINK_TYPE) { case MEDIA_LNK_FL_DATA_LINK: return "data"; case MEDIA_LNK_FL_INTERFACE_LINK: return "interface"; case MEDIA_LNK_FL_ANCILLARY_LINK: return "ancillary"; default: return "unknown"; } } __must_check int media_entity_enum_init(struct media_entity_enum *ent_enum, struct media_device *mdev) { int idx_max; idx_max = ALIGN(mdev->entity_internal_idx_max + 1, BITS_PER_LONG); ent_enum->bmap = bitmap_zalloc(idx_max, GFP_KERNEL); if (!ent_enum->bmap) return -ENOMEM; ent_enum->idx_max = idx_max; return 0; } EXPORT_SYMBOL_GPL(media_entity_enum_init); void media_entity_enum_cleanup(struct media_entity_enum *ent_enum) { bitmap_free(ent_enum->bmap); } EXPORT_SYMBOL_GPL(media_entity_enum_cleanup); /** * dev_dbg_obj - Prints in debug mode a change on some object * * @event_name: Name of the event to report. Could be __func__ * @gobj: Pointer to the object * * Enabled only if DEBUG or CONFIG_DYNAMIC_DEBUG. Otherwise, it * won't produce any code. */ static void dev_dbg_obj(const char *event_name, struct media_gobj *gobj) { #if defined(DEBUG) || defined (CONFIG_DYNAMIC_DEBUG) switch (media_type(gobj)) { case MEDIA_GRAPH_ENTITY: dev_dbg(gobj->mdev->dev, "%s id %u: entity '%s'\n", event_name, media_id(gobj), gobj_to_entity(gobj)->name); break; case MEDIA_GRAPH_LINK: { struct media_link *link = gobj_to_link(gobj); dev_dbg(gobj->mdev->dev, "%s id %u: %s link id %u ==> id %u\n", event_name, media_id(gobj), link_type_name(link), media_id(link->gobj0), media_id(link->gobj1)); break; } case MEDIA_GRAPH_PAD: { struct media_pad *pad = gobj_to_pad(gobj); dev_dbg(gobj->mdev->dev, "%s id %u: %s%spad '%s':%d\n", event_name, media_id(gobj), pad->flags & MEDIA_PAD_FL_SINK ? "sink " : "", pad->flags & MEDIA_PAD_FL_SOURCE ? "source " : "", pad->entity->name, pad->index); break; } case MEDIA_GRAPH_INTF_DEVNODE: { struct media_interface *intf = gobj_to_intf(gobj); struct media_intf_devnode *devnode = intf_to_devnode(intf); dev_dbg(gobj->mdev->dev, "%s id %u: intf_devnode %s - major: %d, minor: %d\n", event_name, media_id(gobj), intf_type(intf), devnode->major, devnode->minor); break; } } #endif } void media_gobj_create(struct media_device *mdev, enum media_gobj_type type, struct media_gobj *gobj) { BUG_ON(!mdev); gobj->mdev = mdev; /* Create a per-type unique object ID */ gobj->id = media_gobj_gen_id(type, ++mdev->id); switch (type) { case MEDIA_GRAPH_ENTITY: list_add_tail(&gobj->list, &mdev->entities); break; case MEDIA_GRAPH_PAD: list_add_tail(&gobj->list, &mdev->pads); break; case MEDIA_GRAPH_LINK: list_add_tail(&gobj->list, &mdev->links); break; case MEDIA_GRAPH_INTF_DEVNODE: list_add_tail(&gobj->list, &mdev->interfaces); break; } mdev->topology_version++; dev_dbg_obj(__func__, gobj); } void media_gobj_destroy(struct media_gobj *gobj) { /* Do nothing if the object is not linked. */ if (gobj->mdev == NULL) return; dev_dbg_obj(__func__, gobj); gobj->mdev->topology_version++; /* Remove the object from mdev list */ list_del(&gobj->list); gobj->mdev = NULL; } /* * TODO: Get rid of this. */ #define MEDIA_ENTITY_MAX_PADS 512 int media_entity_pads_init(struct media_entity *entity, u16 num_pads, struct media_pad *pads) { struct media_device *mdev = entity->graph_obj.mdev; struct media_pad *iter; unsigned int i = 0; int ret = 0; if (num_pads >= MEDIA_ENTITY_MAX_PADS) return -E2BIG; entity->num_pads = num_pads; entity->pads = pads; if (mdev) mutex_lock(&mdev->graph_mutex); media_entity_for_each_pad(entity, iter) { iter->entity = entity; iter->index = i++; if (hweight32(iter->flags & (MEDIA_PAD_FL_SINK | MEDIA_PAD_FL_SOURCE)) != 1) { ret = -EINVAL; break; } if (mdev) media_gobj_create(mdev, MEDIA_GRAPH_PAD, &iter->graph_obj); } if (ret && mdev) { media_entity_for_each_pad(entity, iter) media_gobj_destroy(&iter->graph_obj); } if (mdev) mutex_unlock(&mdev->graph_mutex); return ret; } EXPORT_SYMBOL_GPL(media_entity_pads_init); /* ----------------------------------------------------------------------------- * Graph traversal */ /** * media_entity_has_pad_interdep - Check interdependency between two pads * * @entity: The entity * @pad0: The first pad index * @pad1: The second pad index * * This function checks the interdependency inside the entity between @pad0 * and @pad1. If two pads are interdependent they are part of the same pipeline * and enabling one of the pads means that the other pad will become "locked" * and doesn't allow configuration changes. * * This function uses the &media_entity_operations.has_pad_interdep() operation * to check the dependency inside the entity between @pad0 and @pad1. If the * has_pad_interdep operation is not implemented, all pads of the entity are * considered to be interdependent. * * One of @pad0 and @pad1 must be a sink pad and the other one a source pad. * The function returns false if both pads are sinks or sources. * * The caller must hold entity->graph_obj.mdev->mutex. * * Return: true if the pads are connected internally and false otherwise. */ static bool media_entity_has_pad_interdep(struct media_entity *entity, unsigned int pad0, unsigned int pad1) { if (pad0 >= entity->num_pads || pad1 >= entity->num_pads) return false; if (entity->pads[pad0].flags & entity->pads[pad1].flags & (MEDIA_PAD_FL_SINK | MEDIA_PAD_FL_SOURCE)) return false; if (!entity->ops || !entity->ops->has_pad_interdep) return true; return entity->ops->has_pad_interdep(entity, pad0, pad1); } static struct media_entity * media_entity_other(struct media_entity *entity, struct media_link *link) { if (link->source->entity == entity) return link->sink->entity; else return link->source->entity; } /* push an entity to traversal stack */ static void stack_push(struct media_graph *graph, struct media_entity *entity) { if (graph->top == MEDIA_ENTITY_ENUM_MAX_DEPTH - 1) { WARN_ON(1); return; } graph->top++; graph->stack[graph->top].link = entity->links.next; graph->stack[graph->top].entity = entity; } static struct media_entity *stack_pop(struct media_graph *graph) { struct media_entity *entity; entity = graph->stack[graph->top].entity; graph->top--; return entity; } #define link_top(en) ((en)->stack[(en)->top].link) #define stack_top(en) ((en)->stack[(en)->top].entity) /** * media_graph_walk_init - Allocate resources for graph walk * @graph: Media graph structure that will be used to walk the graph * @mdev: Media device * * Reserve resources for graph walk in media device's current * state. The memory must be released using * media_graph_walk_cleanup(). * * Returns error on failure, zero on success. */ __must_check int media_graph_walk_init( struct media_graph *graph, struct media_device *mdev) { return media_entity_enum_init(&graph->ent_enum, mdev); } EXPORT_SYMBOL_GPL(media_graph_walk_init); /** * media_graph_walk_cleanup - Release resources related to graph walking * @graph: Media graph structure that was used to walk the graph */ void media_graph_walk_cleanup(struct media_graph *graph) { media_entity_enum_cleanup(&graph->ent_enum); } EXPORT_SYMBOL_GPL(media_graph_walk_cleanup); void media_graph_walk_start(struct media_graph *graph, struct media_entity *entity) { media_entity_enum_zero(&graph->ent_enum); media_entity_enum_set(&graph->ent_enum, entity); graph->top = 0; graph->stack[graph->top].entity = NULL; stack_push(graph, entity); dev_dbg(entity->graph_obj.mdev->dev, "begin graph walk at '%s'\n", entity->name); } EXPORT_SYMBOL_GPL(media_graph_walk_start); static void media_graph_walk_iter(struct media_graph *graph) { struct media_entity *entity = stack_top(graph); struct media_link *link; struct media_entity *next; link = list_entry(link_top(graph), typeof(*link), list); /* If the link is not a data link, don't follow it */ if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) != MEDIA_LNK_FL_DATA_LINK) { link_top(graph) = link_top(graph)->next; return; } /* The link is not enabled so we do not follow. */ if (!(link->flags & MEDIA_LNK_FL_ENABLED)) { link_top(graph) = link_top(graph)->next; dev_dbg(entity->graph_obj.mdev->dev, "walk: skipping disabled link '%s':%u -> '%s':%u\n", link->source->entity->name, link->source->index, link->sink->entity->name, link->sink->index); return; } /* Get the entity at the other end of the link. */ next = media_entity_other(entity, link); /* Has the entity already been visited? */ if (media_entity_enum_test_and_set(&graph->ent_enum, next)) { link_top(graph) = link_top(graph)->next; dev_dbg(entity->graph_obj.mdev->dev, "walk: skipping entity '%s' (already seen)\n", next->name); return; } /* Push the new entity to stack and start over. */ link_top(graph) = link_top(graph)->next; stack_push(graph, next); dev_dbg(entity->graph_obj.mdev->dev, "walk: pushing '%s' on stack\n", next->name); lockdep_assert_held(&entity->graph_obj.mdev->graph_mutex); } struct media_entity *media_graph_walk_next(struct media_graph *graph) { struct media_entity *entity; if (stack_top(graph) == NULL) return NULL; /* * Depth first search. Push entity to stack and continue from * top of the stack until no more entities on the level can be * found. */ while (link_top(graph) != &stack_top(graph)->links) media_graph_walk_iter(graph); entity = stack_pop(graph); dev_dbg(entity->graph_obj.mdev->dev, "walk: returning entity '%s'\n", entity->name); return entity; } EXPORT_SYMBOL_GPL(media_graph_walk_next); /* ----------------------------------------------------------------------------- * Pipeline management */ /* * The pipeline traversal stack stores pads that are reached during graph * traversal, with a list of links to be visited to continue the traversal. * When a new pad is reached, an entry is pushed on the top of the stack and * points to the incoming pad and the first link of the entity. * * To find further pads in the pipeline, the traversal algorithm follows * internal pad dependencies in the entity, and then links in the graph. It * does so by iterating over all links of the entity, and following enabled * links that originate from a pad that is internally connected to the incoming * pad, as reported by the media_entity_has_pad_interdep() function. */ /** * struct media_pipeline_walk_entry - Entry in the pipeline traversal stack * * @pad: The media pad being visited * @links: Links left to be visited */ struct media_pipeline_walk_entry { struct media_pad *pad; struct list_head *links; }; /** * struct media_pipeline_walk - State used by the media pipeline traversal * algorithm * * @mdev: The media device * @stack: Depth-first search stack * @stack.size: Number of allocated entries in @stack.entries * @stack.top: Index of the top stack entry (-1 if the stack is empty) * @stack.entries: Stack entries */ struct media_pipeline_walk { struct media_device *mdev; struct { unsigned int size; int top; struct media_pipeline_walk_entry *entries; } stack; }; #define MEDIA_PIPELINE_STACK_GROW_STEP 16 static struct media_pipeline_walk_entry * media_pipeline_walk_top(struct media_pipeline_walk *walk) { return &walk->stack.entries[walk->stack.top]; } static bool media_pipeline_walk_empty(struct media_pipeline_walk *walk) { return walk->stack.top == -1; } /* Increase the stack size by MEDIA_PIPELINE_STACK_GROW_STEP elements. */ static int media_pipeline_walk_resize(struct media_pipeline_walk *walk) { struct media_pipeline_walk_entry *entries; unsigned int new_size; /* Safety check, to avoid stack overflows in case of bugs. */ if (walk->stack.size >= 256) return -E2BIG; new_size = walk->stack.size + MEDIA_PIPELINE_STACK_GROW_STEP; entries = krealloc(walk->stack.entries, new_size * sizeof(*walk->stack.entries), GFP_KERNEL); if (!entries) return -ENOMEM; walk->stack.entries = entries; walk->stack.size = new_size; return 0; } /* Push a new entry on the stack. */ static int media_pipeline_walk_push(struct media_pipeline_walk *walk, struct media_pad *pad) { struct media_pipeline_walk_entry *entry; int ret; if (walk->stack.top + 1 >= walk->stack.size) { ret = media_pipeline_walk_resize(walk); if (ret) return ret; } walk->stack.top++; entry = media_pipeline_walk_top(walk); entry->pad = pad; entry->links = pad->entity->links.next; dev_dbg(walk->mdev->dev, "media pipeline: pushed entry %u: '%s':%u\n", walk->stack.top, pad->entity->name, pad->index); return 0; } /* * Move the top entry link cursor to the next link. If all links of the entry * have been visited, pop the entry itself. Return true if the entry has been * popped. */ static bool media_pipeline_walk_pop(struct media_pipeline_walk *walk) { struct media_pipeline_walk_entry *entry; if (WARN_ON(walk->stack.top < 0)) return false; entry = media_pipeline_walk_top(walk); if (entry->links->next == &entry->pad->entity->links) { dev_dbg(walk->mdev->dev, "media pipeline: entry %u has no more links, popping\n", walk->stack.top); walk->stack.top--; return true; } entry->links = entry->links->next; dev_dbg(walk->mdev->dev, "media pipeline: moved entry %u to next link\n", walk->stack.top); return false; } /* Free all memory allocated while walking the pipeline. */ static void media_pipeline_walk_destroy(struct media_pipeline_walk *walk) { kfree(walk->stack.entries); } /* Add a pad to the pipeline and push it to the stack. */ static int media_pipeline_add_pad(struct media_pipeline *pipe, struct media_pipeline_walk *walk, struct media_pad *pad) { struct media_pipeline_pad *ppad; list_for_each_entry(ppad, &pipe->pads, list) { if (ppad->pad == pad) { dev_dbg(pad->graph_obj.mdev->dev, "media pipeline: already contains pad '%s':%u\n", pad->entity->name, pad->index); return 0; } } ppad = kzalloc(sizeof(*ppad), GFP_KERNEL); if (!ppad) return -ENOMEM; ppad->pipe = pipe; ppad->pad = pad; list_add_tail(&ppad->list, &pipe->pads); dev_dbg(pad->graph_obj.mdev->dev, "media pipeline: added pad '%s':%u\n", pad->entity->name, pad->index); return media_pipeline_walk_push(walk, pad); } /* Explore the next link of the entity at the top of the stack. */ static int media_pipeline_explore_next_link(struct media_pipeline *pipe, struct media_pipeline_walk *walk) { struct media_pipeline_walk_entry *entry = media_pipeline_walk_top(walk); struct media_pad *origin; struct media_link *link; struct media_pad *local; struct media_pad *remote; bool last_link; int ret; origin = entry->pad; link = list_entry(entry->links, typeof(*link), list); last_link = media_pipeline_walk_pop(walk); if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) != MEDIA_LNK_FL_DATA_LINK) { dev_dbg(walk->mdev->dev, "media pipeline: skipping link (not data-link)\n"); return 0; } dev_dbg(walk->mdev->dev, "media pipeline: exploring link '%s':%u -> '%s':%u\n", link->source->entity->name, link->source->index, link->sink->entity->name, link->sink->index); /* Get the local pad and remote pad. */ if (link->source->entity == origin->entity) { local = link->source; remote = link->sink; } else { local = link->sink; remote = link->source; } /* * Skip links that originate from a different pad than the incoming pad * that is not connected internally in the entity to the incoming pad. */ if (origin != local && !media_entity_has_pad_interdep(origin->entity, origin->index, local->index)) { dev_dbg(walk->mdev->dev, "media pipeline: skipping link (no route)\n"); goto done; } /* * Add the local pad of the link to the pipeline and push it to the * stack, if not already present. */ ret = media_pipeline_add_pad(pipe, walk, local); if (ret) return ret; /* Similarly, add the remote pad, but only if the link is enabled. */ if (!(link->flags & MEDIA_LNK_FL_ENABLED)) { dev_dbg(walk->mdev->dev, "media pipeline: skipping link (disabled)\n"); goto done; } ret = media_pipeline_add_pad(pipe, walk, remote); if (ret) return ret; done: /* * If we're done iterating over links, iterate over pads of the entity. * This is necessary to discover pads that are not connected with any * link. Those are dead ends from a pipeline exploration point of view, * but are still part of the pipeline and need to be added to enable * proper validation. */ if (!last_link) return 0; dev_dbg(walk->mdev->dev, "media pipeline: adding unconnected pads of '%s'\n", local->entity->name); media_entity_for_each_pad(origin->entity, local) { /* * Skip the origin pad (already handled), pad that have links * (already discovered through iterating over links) and pads * not internally connected. */ if (origin == local || !local->num_links || !media_entity_has_pad_interdep(origin->entity, origin->index, local->index)) continue; ret = media_pipeline_add_pad(pipe, walk, local); if (ret) return ret; } return 0; } static void media_pipeline_cleanup(struct media_pipeline *pipe) { while (!list_empty(&pipe->pads)) { struct media_pipeline_pad *ppad; ppad = list_first_entry(&pipe->pads, typeof(*ppad), list); list_del(&ppad->list); kfree(ppad); } } static int media_pipeline_populate(struct media_pipeline *pipe, struct media_pad *pad) { struct media_pipeline_walk walk = { }; struct media_pipeline_pad *ppad; int ret; /* * Populate the media pipeline by walking the media graph, starting * from @pad. */ INIT_LIST_HEAD(&pipe->pads); pipe->mdev = pad->graph_obj.mdev; walk.mdev = pipe->mdev; walk.stack.top = -1; ret = media_pipeline_add_pad(pipe, &walk, pad); if (ret) goto done; /* * Use a depth-first search algorithm: as long as the stack is not * empty, explore the next link of the top entry. The * media_pipeline_explore_next_link() function will either move to the * next link, pop the entry if fully visited, or add new entries on * top. */ while (!media_pipeline_walk_empty(&walk)) { ret = media_pipeline_explore_next_link(pipe, &walk); if (ret) goto done; } dev_dbg(pad->graph_obj.mdev->dev, "media pipeline populated, found pads:\n"); list_for_each_entry(ppad, &pipe->pads, list) dev_dbg(pad->graph_obj.mdev->dev, "- '%s':%u\n", ppad->pad->entity->name, ppad->pad->index); WARN_ON(walk.stack.top != -1); ret = 0; done: media_pipeline_walk_destroy(&walk); if (ret) media_pipeline_cleanup(pipe); return ret; } __must_check int __media_pipeline_start(struct media_pad *origin, struct media_pipeline *pipe) { struct media_device *mdev = origin->graph_obj.mdev; struct media_pipeline_pad *err_ppad; struct media_pipeline_pad *ppad; int ret; lockdep_assert_held(&mdev->graph_mutex); /* * If the pad is already part of a pipeline, that pipeline must be the * same as the pipe given to media_pipeline_start(). */ if (WARN_ON(origin->pipe && origin->pipe != pipe)) return -EINVAL; /* * If the pipeline has already been started, it is guaranteed to be * valid, so just increase the start count. */ if (pipe->start_count) { pipe->start_count++; return 0; } /* * Populate the pipeline. This populates the media_pipeline pads list * with media_pipeline_pad instances for each pad found during graph * walk. */ ret = media_pipeline_populate(pipe, origin); if (ret) return ret; /* * Now that all the pads in the pipeline have been gathered, perform * the validation steps. */ list_for_each_entry(ppad, &pipe->pads, list) { struct media_pad *pad = ppad->pad; struct media_entity *entity = pad->entity; bool has_enabled_link = false; struct media_link *link; dev_dbg(mdev->dev, "Validating pad '%s':%u\n", pad->entity->name, pad->index); /* * 1. Ensure that the pad doesn't already belong to a different * pipeline. */ if (pad->pipe) { dev_dbg(mdev->dev, "Failed to start pipeline: pad '%s':%u busy\n", pad->entity->name, pad->index); ret = -EBUSY; goto error; } /* * 2. Validate all active links whose sink is the current pad. * Validation of the source pads is performed in the context of * the connected sink pad to avoid duplicating checks. */ for_each_media_entity_data_link(entity, link) { /* Skip links unrelated to the current pad. */ if (link->sink != pad && link->source != pad) continue; /* Record if the pad has links and enabled links. */ if (link->flags & MEDIA_LNK_FL_ENABLED) has_enabled_link = true; /* * Validate the link if it's enabled and has the * current pad as its sink. */ if (!(link->flags & MEDIA_LNK_FL_ENABLED)) continue; if (link->sink != pad) continue; if (!entity->ops || !entity->ops->link_validate) continue; ret = entity->ops->link_validate(link); if (ret) { dev_dbg(mdev->dev, "Link '%s':%u -> '%s':%u failed validation: %d\n", link->source->entity->name, link->source->index, link->sink->entity->name, link->sink->index, ret); goto error; } dev_dbg(mdev->dev, "Link '%s':%u -> '%s':%u is valid\n", link->source->entity->name, link->source->index, link->sink->entity->name, link->sink->index); } /* * 3. If the pad has the MEDIA_PAD_FL_MUST_CONNECT flag set, * ensure that it has either no link or an enabled link. */ if ((pad->flags & MEDIA_PAD_FL_MUST_CONNECT) && !has_enabled_link) { dev_dbg(mdev->dev, "Pad '%s':%u must be connected by an enabled link\n", pad->entity->name, pad->index); ret = -ENOLINK; goto error; } /* Validation passed, store the pipe pointer in the pad. */ pad->pipe = pipe; } pipe->start_count++; return 0; error: /* * Link validation on graph failed. We revert what we did and * return the error. */ list_for_each_entry(err_ppad, &pipe->pads, list) { if (err_ppad == ppad) break; err_ppad->pad->pipe = NULL; } media_pipeline_cleanup(pipe); return ret; } EXPORT_SYMBOL_GPL(__media_pipeline_start); __must_check int media_pipeline_start(struct media_pad *origin, struct media_pipeline *pipe) { struct media_device *mdev = origin->graph_obj.mdev; int ret; mutex_lock(&mdev->graph_mutex); ret = __media_pipeline_start(origin, pipe); mutex_unlock(&mdev->graph_mutex); return ret; } EXPORT_SYMBOL_GPL(media_pipeline_start); void __media_pipeline_stop(struct media_pad *pad) { struct media_pipeline *pipe = pad->pipe; struct media_pipeline_pad *ppad; /* * If the following check fails, the driver has performed an * unbalanced call to media_pipeline_stop() */ if (WARN_ON(!pipe)) return; if (--pipe->start_count) return; list_for_each_entry(ppad, &pipe->pads, list) ppad->pad->pipe = NULL; media_pipeline_cleanup(pipe); if (pipe->allocated) kfree(pipe); } EXPORT_SYMBOL_GPL(__media_pipeline_stop); void media_pipeline_stop(struct media_pad *pad) { struct media_device *mdev = pad->graph_obj.mdev; mutex_lock(&mdev->graph_mutex); __media_pipeline_stop(pad); mutex_unlock(&mdev->graph_mutex); } EXPORT_SYMBOL_GPL(media_pipeline_stop); __must_check int media_pipeline_alloc_start(struct media_pad *pad) { struct media_device *mdev = pad->graph_obj.mdev; struct media_pipeline *new_pipe = NULL; struct media_pipeline *pipe; int ret; mutex_lock(&mdev->graph_mutex); /* * Is the pad already part of a pipeline? If not, we need to allocate * a pipe. */ pipe = media_pad_pipeline(pad); if (!pipe) { new_pipe = kzalloc(sizeof(*new_pipe), GFP_KERNEL); if (!new_pipe) { ret = -ENOMEM; goto out; } pipe = new_pipe; pipe->allocated = true; } ret = __media_pipeline_start(pad, pipe); if (ret) kfree(new_pipe); out: mutex_unlock(&mdev->graph_mutex); return ret; } EXPORT_SYMBOL_GPL(media_pipeline_alloc_start); struct media_pad * __media_pipeline_pad_iter_next(struct media_pipeline *pipe, struct media_pipeline_pad_iter *iter, struct media_pad *pad) { if (!pad) iter->cursor = pipe->pads.next; if (iter->cursor == &pipe->pads) return NULL; pad = list_entry(iter->cursor, struct media_pipeline_pad, list)->pad; iter->cursor = iter->cursor->next; return pad; } EXPORT_SYMBOL_GPL(__media_pipeline_pad_iter_next); int media_pipeline_entity_iter_init(struct media_pipeline *pipe, struct media_pipeline_entity_iter *iter) { return media_entity_enum_init(&iter->ent_enum, pipe->mdev); } EXPORT_SYMBOL_GPL(media_pipeline_entity_iter_init); void media_pipeline_entity_iter_cleanup(struct media_pipeline_entity_iter *iter) { media_entity_enum_cleanup(&iter->ent_enum); } EXPORT_SYMBOL_GPL(media_pipeline_entity_iter_cleanup); struct media_entity * __media_pipeline_entity_iter_next(struct media_pipeline *pipe, struct media_pipeline_entity_iter *iter, struct media_entity *entity) { if (!entity) iter->cursor = pipe->pads.next; while (iter->cursor != &pipe->pads) { struct media_pipeline_pad *ppad; struct media_entity *entity; ppad = list_entry(iter->cursor, struct media_pipeline_pad, list); entity = ppad->pad->entity; iter->cursor = iter->cursor->next; if (!media_entity_enum_test_and_set(&iter->ent_enum, entity)) return entity; } return NULL; } EXPORT_SYMBOL_GPL(__media_pipeline_entity_iter_next); /* ----------------------------------------------------------------------------- * Links management */ static struct media_link *media_add_link(struct list_head *head) { struct media_link *link; link = kzalloc(sizeof(*link), GFP_KERNEL); if (link == NULL) return NULL; list_add_tail(&link->list, head); return link; } static void __media_entity_remove_link(struct media_entity *entity, struct media_link *link) { struct media_link *rlink, *tmp; struct media_entity *remote; /* Remove the reverse links for a data link. */ if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) == MEDIA_LNK_FL_DATA_LINK) { link->source->num_links--; link->sink->num_links--; if (link->source->entity == entity) remote = link->sink->entity; else remote = link->source->entity; list_for_each_entry_safe(rlink, tmp, &remote->links, list) { if (rlink != link->reverse) continue; if (link->source->entity == entity) remote->num_backlinks--; /* Remove the remote link */ list_del(&rlink->list); media_gobj_destroy(&rlink->graph_obj); kfree(rlink); if (--remote->num_links == 0) break; } } list_del(&link->list); media_gobj_destroy(&link->graph_obj); kfree(link); } int media_get_pad_index(struct media_entity *entity, u32 pad_type, enum media_pad_signal_type sig_type) { unsigned int i; if (!entity) return -EINVAL; for (i = 0; i < entity->num_pads; i++) { if ((entity->pads[i].flags & (MEDIA_PAD_FL_SINK | MEDIA_PAD_FL_SOURCE)) != pad_type) continue; if (entity->pads[i].sig_type == sig_type) return i; } return -EINVAL; } EXPORT_SYMBOL_GPL(media_get_pad_index); int media_create_pad_link(struct media_entity *source, u16 source_pad, struct media_entity *sink, u16 sink_pad, u32 flags) { struct media_link *link; struct media_link *backlink; if (flags & MEDIA_LNK_FL_LINK_TYPE) return -EINVAL; flags |= MEDIA_LNK_FL_DATA_LINK; if (WARN_ON(!source || !sink) || WARN_ON(source_pad >= source->num_pads) || WARN_ON(sink_pad >= sink->num_pads)) return -EINVAL; if (WARN_ON(!(source->pads[source_pad].flags & MEDIA_PAD_FL_SOURCE))) return -EINVAL; if (WARN_ON(!(sink->pads[sink_pad].flags & MEDIA_PAD_FL_SINK))) return -EINVAL; link = media_add_link(&source->links); if (link == NULL) return -ENOMEM; link->source = &source->pads[source_pad]; link->sink = &sink->pads[sink_pad]; link->flags = flags; /* Initialize graph object embedded at the new link */ media_gobj_create(source->graph_obj.mdev, MEDIA_GRAPH_LINK, &link->graph_obj); /* Create the backlink. Backlinks are used to help graph traversal and * are not reported to userspace. */ backlink = media_add_link(&sink->links); if (backlink == NULL) { __media_entity_remove_link(source, link); return -ENOMEM; } backlink->source = &source->pads[source_pad]; backlink->sink = &sink->pads[sink_pad]; backlink->flags = flags; backlink->is_backlink = true; /* Initialize graph object embedded at the new link */ media_gobj_create(sink->graph_obj.mdev, MEDIA_GRAPH_LINK, &backlink->graph_obj); link->reverse = backlink; backlink->reverse = link; sink->num_backlinks++; sink->num_links++; source->num_links++; link->source->num_links++; link->sink->num_links++; return 0; } EXPORT_SYMBOL_GPL(media_create_pad_link); int media_create_pad_links(const struct media_device *mdev, const u32 source_function, struct media_entity *source, const u16 source_pad, const u32 sink_function, struct media_entity *sink, const u16 sink_pad, u32 flags, const bool allow_both_undefined) { struct media_entity *entity; unsigned function; int ret; /* Trivial case: 1:1 relation */ if (source && sink) return media_create_pad_link(source, source_pad, sink, sink_pad, flags); /* Worse case scenario: n:n relation */ if (!source && !sink) { if (!allow_both_undefined) return 0; media_device_for_each_entity(source, mdev) { if (source->function != source_function) continue; media_device_for_each_entity(sink, mdev) { if (sink->function != sink_function) continue; ret = media_create_pad_link(source, source_pad, sink, sink_pad, flags); if (ret) return ret; flags &= ~(MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE); } } return 0; } /* Handle 1:n and n:1 cases */ if (source) function = sink_function; else function = source_function; media_device_for_each_entity(entity, mdev) { if (entity->function != function) continue; if (source) ret = media_create_pad_link(source, source_pad, entity, sink_pad, flags); else ret = media_create_pad_link(entity, source_pad, sink, sink_pad, flags); if (ret) return ret; flags &= ~(MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE); } return 0; } EXPORT_SYMBOL_GPL(media_create_pad_links); void __media_entity_remove_links(struct media_entity *entity) { struct media_link *link, *tmp; list_for_each_entry_safe(link, tmp, &entity->links, list) __media_entity_remove_link(entity, link); entity->num_links = 0; entity->num_backlinks = 0; } EXPORT_SYMBOL_GPL(__media_entity_remove_links); void media_entity_remove_links(struct media_entity *entity) { struct media_device *mdev = entity->graph_obj.mdev; /* Do nothing if the entity is not registered. */ if (mdev == NULL) return; mutex_lock(&mdev->graph_mutex); __media_entity_remove_links(entity); mutex_unlock(&mdev->graph_mutex); } EXPORT_SYMBOL_GPL(media_entity_remove_links); static int __media_entity_setup_link_notify(struct media_link *link, u32 flags) { int ret; /* Notify both entities. */ ret = media_entity_call(link->source->entity, link_setup, link->source, link->sink, flags); if (ret < 0 && ret != -ENOIOCTLCMD) return ret; ret = media_entity_call(link->sink->entity, link_setup, link->sink, link->source, flags); if (ret < 0 && ret != -ENOIOCTLCMD) { media_entity_call(link->source->entity, link_setup, link->source, link->sink, link->flags); return ret; } link->flags = flags; link->reverse->flags = link->flags; return 0; } int __media_entity_setup_link(struct media_link *link, u32 flags) { const u32 mask = MEDIA_LNK_FL_ENABLED; struct media_device *mdev; struct media_pad *source, *sink; int ret = -EBUSY; if (link == NULL) return -EINVAL; /* The non-modifiable link flags must not be modified. */ if ((link->flags & ~mask) != (flags & ~mask)) return -EINVAL; if (link->flags & MEDIA_LNK_FL_IMMUTABLE) return link->flags == flags ? 0 : -EINVAL; if (link->flags == flags) return 0; source = link->source; sink = link->sink; if (!(link->flags & MEDIA_LNK_FL_DYNAMIC) && (media_pad_is_streaming(source) || media_pad_is_streaming(sink))) return -EBUSY; mdev = source->graph_obj.mdev; if (mdev->ops && mdev->ops->link_notify) { ret = mdev->ops->link_notify(link, flags, MEDIA_DEV_NOTIFY_PRE_LINK_CH); if (ret < 0) return ret; } ret = __media_entity_setup_link_notify(link, flags); if (mdev->ops && mdev->ops->link_notify) mdev->ops->link_notify(link, flags, MEDIA_DEV_NOTIFY_POST_LINK_CH); return ret; } EXPORT_SYMBOL_GPL(__media_entity_setup_link); int media_entity_setup_link(struct media_link *link, u32 flags) { int ret; mutex_lock(&link->graph_obj.mdev->graph_mutex); ret = __media_entity_setup_link(link, flags); mutex_unlock(&link->graph_obj.mdev->graph_mutex); return ret; } EXPORT_SYMBOL_GPL(media_entity_setup_link); struct media_link * media_entity_find_link(struct media_pad *source, struct media_pad *sink) { struct media_link *link; for_each_media_entity_data_link(source->entity, link) { if (link->source->entity == source->entity && link->source->index == source->index && link->sink->entity == sink->entity && link->sink->index == sink->index) return link; } return NULL; } EXPORT_SYMBOL_GPL(media_entity_find_link); struct media_pad *media_pad_remote_pad_first(const struct media_pad *pad) { struct media_link *link; for_each_media_entity_data_link(pad->entity, link) { if (!(link->flags & MEDIA_LNK_FL_ENABLED)) continue; if (link->source == pad) return link->sink; if (link->sink == pad) return link->source; } return NULL; } EXPORT_SYMBOL_GPL(media_pad_remote_pad_first); struct media_pad * media_entity_remote_pad_unique(const struct media_entity *entity, unsigned int type) { struct media_pad *pad = NULL; struct media_link *link; list_for_each_entry(link, &entity->links, list) { struct media_pad *local_pad; struct media_pad *remote_pad; if (((link->flags & MEDIA_LNK_FL_LINK_TYPE) != MEDIA_LNK_FL_DATA_LINK) || !(link->flags & MEDIA_LNK_FL_ENABLED)) continue; if (type == MEDIA_PAD_FL_SOURCE) { local_pad = link->sink; remote_pad = link->source; } else { local_pad = link->source; remote_pad = link->sink; } if (local_pad->entity == entity) { if (pad) return ERR_PTR(-ENOTUNIQ); pad = remote_pad; } } if (!pad) return ERR_PTR(-ENOLINK); return pad; } EXPORT_SYMBOL_GPL(media_entity_remote_pad_unique); struct media_pad *media_pad_remote_pad_unique(const struct media_pad *pad) { struct media_pad *found_pad = NULL; struct media_link *link; list_for_each_entry(link, &pad->entity->links, list) { struct media_pad *remote_pad; if (!(link->flags & MEDIA_LNK_FL_ENABLED)) continue; if (link->sink == pad) remote_pad = link->source; else if (link->source == pad) remote_pad = link->sink; else continue; if (found_pad) return ERR_PTR(-ENOTUNIQ); found_pad = remote_pad; } if (!found_pad) return ERR_PTR(-ENOLINK); return found_pad; } EXPORT_SYMBOL_GPL(media_pad_remote_pad_unique); int media_entity_get_fwnode_pad(struct media_entity *entity, const struct fwnode_handle *fwnode, unsigned long direction_flags) { struct fwnode_endpoint endpoint; unsigned int i; int ret; if (!entity->ops || !entity->ops->get_fwnode_pad) { for (i = 0; i < entity->num_pads; i++) { if (entity->pads[i].flags & direction_flags) return i; } return -ENXIO; } ret = fwnode_graph_parse_endpoint(fwnode, &endpoint); if (ret) return ret; ret = entity->ops->get_fwnode_pad(entity, &endpoint); if (ret < 0) return ret; if (ret >= entity->num_pads) return -ENXIO; if (!(entity->pads[ret].flags & direction_flags)) return -ENXIO; return ret; } EXPORT_SYMBOL_GPL(media_entity_get_fwnode_pad); struct media_pipeline *media_entity_pipeline(struct media_entity *entity) { struct media_pad *pad; media_entity_for_each_pad(entity, pad) { if (pad->pipe) return pad->pipe; } return NULL; } EXPORT_SYMBOL_GPL(media_entity_pipeline); struct media_pipeline *media_pad_pipeline(struct media_pad *pad) { return pad->pipe; } EXPORT_SYMBOL_GPL(media_pad_pipeline); static void media_interface_init(struct media_device *mdev, struct media_interface *intf, u32 gobj_type, u32 intf_type, u32 flags) { intf->type = intf_type; intf->flags = flags; INIT_LIST_HEAD(&intf->links); media_gobj_create(mdev, gobj_type, &intf->graph_obj); } /* Functions related to the media interface via device nodes */ struct media_intf_devnode *media_devnode_create(struct media_device *mdev, u32 type, u32 flags, u32 major, u32 minor) { struct media_intf_devnode *devnode; devnode = kzalloc(sizeof(*devnode), GFP_KERNEL); if (!devnode) return NULL; devnode->major = major; devnode->minor = minor; media_interface_init(mdev, &devnode->intf, MEDIA_GRAPH_INTF_DEVNODE, type, flags); return devnode; } EXPORT_SYMBOL_GPL(media_devnode_create); void media_devnode_remove(struct media_intf_devnode *devnode) { media_remove_intf_links(&devnode->intf); media_gobj_destroy(&devnode->intf.graph_obj); kfree(devnode); } EXPORT_SYMBOL_GPL(media_devnode_remove); struct media_link *media_create_intf_link(struct media_entity *entity, struct media_interface *intf, u32 flags) { struct media_link *link; link = media_add_link(&intf->links); if (link == NULL) return NULL; link->intf = intf; link->entity = entity; link->flags = flags | MEDIA_LNK_FL_INTERFACE_LINK; /* Initialize graph object embedded at the new link */ media_gobj_create(intf->graph_obj.mdev, MEDIA_GRAPH_LINK, &link->graph_obj); return link; } EXPORT_SYMBOL_GPL(media_create_intf_link); void __media_remove_intf_link(struct media_link *link) { list_del(&link->list); media_gobj_destroy(&link->graph_obj); kfree(link); } EXPORT_SYMBOL_GPL(__media_remove_intf_link); void media_remove_intf_link(struct media_link *link) { struct media_device *mdev = link->graph_obj.mdev; /* Do nothing if the intf is not registered. */ if (mdev == NULL) return; mutex_lock(&mdev->graph_mutex); __media_remove_intf_link(link); mutex_unlock(&mdev->graph_mutex); } EXPORT_SYMBOL_GPL(media_remove_intf_link); void __media_remove_intf_links(struct media_interface *intf) { struct media_link *link, *tmp; list_for_each_entry_safe(link, tmp, &intf->links, list) __media_remove_intf_link(link); } EXPORT_SYMBOL_GPL(__media_remove_intf_links); void media_remove_intf_links(struct media_interface *intf) { struct media_device *mdev = intf->graph_obj.mdev; /* Do nothing if the intf is not registered. */ if (mdev == NULL) return; mutex_lock(&mdev->graph_mutex); __media_remove_intf_links(intf); mutex_unlock(&mdev->graph_mutex); } EXPORT_SYMBOL_GPL(media_remove_intf_links); struct media_link *media_create_ancillary_link(struct media_entity *primary, struct media_entity *ancillary) { struct media_link *link; link = media_add_link(&primary->links); if (!link) return ERR_PTR(-ENOMEM); link->gobj0 = &primary->graph_obj; link->gobj1 = &ancillary->graph_obj; link->flags = MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_ANCILLARY_LINK; /* Initialize graph object embedded in the new link */ media_gobj_create(primary->graph_obj.mdev, MEDIA_GRAPH_LINK, &link->graph_obj); return link; } EXPORT_SYMBOL_GPL(media_create_ancillary_link); struct media_link *__media_entity_next_link(struct media_entity *entity, struct media_link *link, unsigned long link_type) { link = link ? list_next_entry(link, list) : list_first_entry(&entity->links, typeof(*link), list); list_for_each_entry_from(link, &entity->links, list) if ((link->flags & MEDIA_LNK_FL_LINK_TYPE) == link_type) return link; return NULL; } EXPORT_SYMBOL_GPL(__media_entity_next_link); |
| 17 3 14 2 15 11 108 264 6 6 112 109 2 276 271 2 1 160 2 159 3 1 15 15 272 1 2 9 9 5 8 7 3 4 3 56 48 1 2 4 37 4 51 50 51 3 1 3 151 141 2 4 114 122 138 4 136 3 1 137 139 139 258 267 174 175 79 37 156 323 202 123 120 121 123 121 121 16 16 7 8 11 24 16 376 337 335 362 367 205 204 154 154 154 153 154 154 154 154 93 93 154 2 154 154 154 154 154 24 154 154 154 154 154 154 154 154 154 154 48 35 13 24 24 48 48 48 48 153 154 37 36 37 7 7 2 2 2 17 53 53 53 38 39 39 39 39 32 30 39 1 1 1 1 1 1 23 2 32 112 142 141 23 142 141 142 1 139 137 139 137 1 25 25 23 49 49 48 49 115 115 115 115 113 113 112 13 120 5 115 9 1 3 3 1 4 9 9 9 9 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * V4L2 controls framework core implementation. * * Copyright (C) 2010-2021 Hans Verkuil <hverkuil-cisco@xs4all.nl> */ #include <linux/export.h> #include <linux/mm.h> #include <linux/slab.h> #include <media/v4l2-ctrls.h> #include <media/v4l2-event.h> #include <media/v4l2-fwnode.h> #include "v4l2-ctrls-priv.h" static const union v4l2_ctrl_ptr ptr_null; static void fill_event(struct v4l2_event *ev, struct v4l2_ctrl *ctrl, u32 changes) { memset(ev, 0, sizeof(*ev)); ev->type = V4L2_EVENT_CTRL; ev->id = ctrl->id; ev->u.ctrl.changes = changes; ev->u.ctrl.type = ctrl->type; ev->u.ctrl.flags = user_flags(ctrl); if (ctrl->is_ptr) ev->u.ctrl.value64 = 0; else ev->u.ctrl.value64 = *ctrl->p_cur.p_s64; ev->u.ctrl.minimum = ctrl->minimum; ev->u.ctrl.maximum = ctrl->maximum; if (ctrl->type == V4L2_CTRL_TYPE_MENU || ctrl->type == V4L2_CTRL_TYPE_INTEGER_MENU) ev->u.ctrl.step = 1; else ev->u.ctrl.step = ctrl->step; ev->u.ctrl.default_value = ctrl->default_value; } void send_initial_event(struct v4l2_fh *fh, struct v4l2_ctrl *ctrl) { struct v4l2_event ev; u32 changes = V4L2_EVENT_CTRL_CH_FLAGS; if (!(ctrl->flags & V4L2_CTRL_FLAG_WRITE_ONLY)) changes |= V4L2_EVENT_CTRL_CH_VALUE; fill_event(&ev, ctrl, changes); v4l2_event_queue_fh(fh, &ev); } void send_event(struct v4l2_fh *fh, struct v4l2_ctrl *ctrl, u32 changes) { struct v4l2_event ev; struct v4l2_subscribed_event *sev; if (list_empty(&ctrl->ev_subs)) return; fill_event(&ev, ctrl, changes); list_for_each_entry(sev, &ctrl->ev_subs, node) if (sev->fh != fh || (sev->flags & V4L2_EVENT_SUB_FL_ALLOW_FEEDBACK)) v4l2_event_queue_fh(sev->fh, &ev); } bool v4l2_ctrl_type_op_equal(const struct v4l2_ctrl *ctrl, union v4l2_ctrl_ptr ptr1, union v4l2_ctrl_ptr ptr2) { unsigned int i; switch (ctrl->type) { case V4L2_CTRL_TYPE_BUTTON: return false; case V4L2_CTRL_TYPE_STRING: for (i = 0; i < ctrl->elems; i++) { unsigned int idx = i * ctrl->elem_size; /* strings are always 0-terminated */ if (strcmp(ptr1.p_char + idx, ptr2.p_char + idx)) return false; } return true; default: return !memcmp(ptr1.p_const, ptr2.p_const, ctrl->elems * ctrl->elem_size); } } EXPORT_SYMBOL(v4l2_ctrl_type_op_equal); /* Default intra MPEG-2 quantisation coefficients, from the specification. */ static const u8 mpeg2_intra_quant_matrix[64] = { 8, 16, 16, 19, 16, 19, 22, 22, 22, 22, 22, 22, 26, 24, 26, 27, 27, 27, 26, 26, 26, 26, 27, 27, 27, 29, 29, 29, 34, 34, 34, 29, 29, 29, 27, 27, 29, 29, 32, 32, 34, 34, 37, 38, 37, 35, 35, 34, 35, 38, 38, 40, 40, 40, 48, 48, 46, 46, 56, 56, 58, 69, 69, 83 }; static void std_init_compound(const struct v4l2_ctrl *ctrl, u32 idx, union v4l2_ctrl_ptr ptr) { struct v4l2_ctrl_mpeg2_sequence *p_mpeg2_sequence; struct v4l2_ctrl_mpeg2_picture *p_mpeg2_picture; struct v4l2_ctrl_mpeg2_quantisation *p_mpeg2_quant; struct v4l2_ctrl_vp8_frame *p_vp8_frame; struct v4l2_ctrl_vp9_frame *p_vp9_frame; struct v4l2_ctrl_fwht_params *p_fwht_params; struct v4l2_ctrl_h264_scaling_matrix *p_h264_scaling_matrix; struct v4l2_ctrl_av1_sequence *p_av1_sequence; void *p = ptr.p + idx * ctrl->elem_size; if (ctrl->p_def.p_const) memcpy(p, ctrl->p_def.p_const, ctrl->elem_size); else memset(p, 0, ctrl->elem_size); switch ((u32)ctrl->type) { case V4L2_CTRL_TYPE_MPEG2_SEQUENCE: p_mpeg2_sequence = p; /* 4:2:0 */ p_mpeg2_sequence->chroma_format = 1; break; case V4L2_CTRL_TYPE_MPEG2_PICTURE: p_mpeg2_picture = p; /* interlaced top field */ p_mpeg2_picture->picture_structure = V4L2_MPEG2_PIC_TOP_FIELD; p_mpeg2_picture->picture_coding_type = V4L2_MPEG2_PIC_CODING_TYPE_I; break; case V4L2_CTRL_TYPE_MPEG2_QUANTISATION: p_mpeg2_quant = p; memcpy(p_mpeg2_quant->intra_quantiser_matrix, mpeg2_intra_quant_matrix, ARRAY_SIZE(mpeg2_intra_quant_matrix)); /* * The default non-intra MPEG-2 quantisation * coefficients are all 16, as per the specification. */ memset(p_mpeg2_quant->non_intra_quantiser_matrix, 16, sizeof(p_mpeg2_quant->non_intra_quantiser_matrix)); break; case V4L2_CTRL_TYPE_VP8_FRAME: p_vp8_frame = p; p_vp8_frame->num_dct_parts = 1; break; case V4L2_CTRL_TYPE_VP9_FRAME: p_vp9_frame = p; p_vp9_frame->profile = 0; p_vp9_frame->bit_depth = 8; p_vp9_frame->flags |= V4L2_VP9_FRAME_FLAG_X_SUBSAMPLING | V4L2_VP9_FRAME_FLAG_Y_SUBSAMPLING; break; case V4L2_CTRL_TYPE_AV1_SEQUENCE: p_av1_sequence = p; p_av1_sequence->bit_depth = 8; break; case V4L2_CTRL_TYPE_FWHT_PARAMS: p_fwht_params = p; p_fwht_params->version = V4L2_FWHT_VERSION; p_fwht_params->width = 1280; p_fwht_params->height = 720; p_fwht_params->flags = V4L2_FWHT_FL_PIXENC_YUV | (2 << V4L2_FWHT_FL_COMPONENTS_NUM_OFFSET); break; case V4L2_CTRL_TYPE_H264_SCALING_MATRIX: p_h264_scaling_matrix = p; /* * The default (flat) H.264 scaling matrix when none are * specified in the bitstream, this is according to formulas * (7-8) and (7-9) of the specification. */ memset(p_h264_scaling_matrix, 16, sizeof(*p_h264_scaling_matrix)); break; } } static void std_min_compound(const struct v4l2_ctrl *ctrl, u32 idx, union v4l2_ctrl_ptr ptr) { void *p = ptr.p + idx * ctrl->elem_size; if (ctrl->p_min.p_const) memcpy(p, ctrl->p_min.p_const, ctrl->elem_size); else memset(p, 0, ctrl->elem_size); } static void std_max_compound(const struct v4l2_ctrl *ctrl, u32 idx, union v4l2_ctrl_ptr ptr) { void *p = ptr.p + idx * ctrl->elem_size; if (ctrl->p_max.p_const) memcpy(p, ctrl->p_max.p_const, ctrl->elem_size); else memset(p, 0, ctrl->elem_size); } static void __v4l2_ctrl_type_op_init(const struct v4l2_ctrl *ctrl, u32 from_idx, u32 which, union v4l2_ctrl_ptr ptr) { unsigned int i; u32 tot_elems = ctrl->elems; u32 elems = tot_elems - from_idx; s64 value; switch (which) { case V4L2_CTRL_WHICH_DEF_VAL: value = ctrl->default_value; break; case V4L2_CTRL_WHICH_MAX_VAL: value = ctrl->maximum; break; case V4L2_CTRL_WHICH_MIN_VAL: value = ctrl->minimum; break; default: return; } switch (ctrl->type) { case V4L2_CTRL_TYPE_STRING: if (which == V4L2_CTRL_WHICH_DEF_VAL) value = ctrl->minimum; for (i = from_idx; i < tot_elems; i++) { unsigned int offset = i * ctrl->elem_size; memset(ptr.p_char + offset, ' ', value); ptr.p_char[offset + value] = '\0'; } break; case V4L2_CTRL_TYPE_INTEGER64: if (value) { for (i = from_idx; i < tot_elems; i++) ptr.p_s64[i] = value; } else { memset(ptr.p_s64 + from_idx, 0, elems * sizeof(s64)); } break; case V4L2_CTRL_TYPE_INTEGER: case V4L2_CTRL_TYPE_INTEGER_MENU: case V4L2_CTRL_TYPE_MENU: case V4L2_CTRL_TYPE_BITMASK: case V4L2_CTRL_TYPE_BOOLEAN: if (value) { for (i = from_idx; i < tot_elems; i++) ptr.p_s32[i] = value; } else { memset(ptr.p_s32 + from_idx, 0, elems * sizeof(s32)); } break; case V4L2_CTRL_TYPE_BUTTON: case V4L2_CTRL_TYPE_CTRL_CLASS: memset(ptr.p_s32 + from_idx, 0, elems * sizeof(s32)); break; case V4L2_CTRL_TYPE_U8: memset(ptr.p_u8 + from_idx, value, elems); break; case V4L2_CTRL_TYPE_U16: if (value) { for (i = from_idx; i < tot_elems; i++) ptr.p_u16[i] = value; } else { memset(ptr.p_u16 + from_idx, 0, elems * sizeof(u16)); } break; case V4L2_CTRL_TYPE_U32: if (value) { for (i = from_idx; i < tot_elems; i++) ptr.p_u32[i] = value; } else { memset(ptr.p_u32 + from_idx, 0, elems * sizeof(u32)); } break; default: for (i = from_idx; i < tot_elems; i++) { switch (which) { case V4L2_CTRL_WHICH_DEF_VAL: std_init_compound(ctrl, i, ptr); break; case V4L2_CTRL_WHICH_MAX_VAL: std_max_compound(ctrl, i, ptr); break; case V4L2_CTRL_WHICH_MIN_VAL: std_min_compound(ctrl, i, ptr); break; } } break; } } void v4l2_ctrl_type_op_init(const struct v4l2_ctrl *ctrl, u32 from_idx, union v4l2_ctrl_ptr ptr) { __v4l2_ctrl_type_op_init(ctrl, from_idx, V4L2_CTRL_WHICH_DEF_VAL, ptr); } EXPORT_SYMBOL(v4l2_ctrl_type_op_init); static void v4l2_ctrl_type_op_minimum(const struct v4l2_ctrl *ctrl, u32 from_idx, union v4l2_ctrl_ptr ptr) { __v4l2_ctrl_type_op_init(ctrl, from_idx, V4L2_CTRL_WHICH_MIN_VAL, ptr); } static void v4l2_ctrl_type_op_maximum(const struct v4l2_ctrl *ctrl, u32 from_idx, union v4l2_ctrl_ptr ptr) { __v4l2_ctrl_type_op_init(ctrl, from_idx, V4L2_CTRL_WHICH_MAX_VAL, ptr); } void v4l2_ctrl_type_op_log(const struct v4l2_ctrl *ctrl) { union v4l2_ctrl_ptr ptr = ctrl->p_cur; if (ctrl->is_array) { unsigned i; for (i = 0; i < ctrl->nr_of_dims; i++) pr_cont("[%u]", ctrl->dims[i]); pr_cont(" "); } switch (ctrl->type) { case V4L2_CTRL_TYPE_INTEGER: pr_cont("%d", *ptr.p_s32); break; case V4L2_CTRL_TYPE_BOOLEAN: pr_cont("%s", *ptr.p_s32 ? "true" : "false"); break; case V4L2_CTRL_TYPE_MENU: pr_cont("%s", ctrl->qmenu[*ptr.p_s32]); break; case V4L2_CTRL_TYPE_INTEGER_MENU: pr_cont("%lld", ctrl->qmenu_int[*ptr.p_s32]); break; case V4L2_CTRL_TYPE_BITMASK: pr_cont("0x%08x", *ptr.p_s32); break; case V4L2_CTRL_TYPE_INTEGER64: pr_cont("%lld", *ptr.p_s64); break; case V4L2_CTRL_TYPE_STRING: pr_cont("%s", ptr.p_char); break; case V4L2_CTRL_TYPE_U8: pr_cont("%u", (unsigned)*ptr.p_u8); break; case V4L2_CTRL_TYPE_U16: pr_cont("%u", (unsigned)*ptr.p_u16); break; case V4L2_CTRL_TYPE_U32: pr_cont("%u", (unsigned)*ptr.p_u32); break; case V4L2_CTRL_TYPE_AREA: pr_cont("%ux%u", ptr.p_area->width, ptr.p_area->height); break; case V4L2_CTRL_TYPE_H264_SPS: pr_cont("H264_SPS"); break; case V4L2_CTRL_TYPE_H264_PPS: pr_cont("H264_PPS"); break; case V4L2_CTRL_TYPE_H264_SCALING_MATRIX: pr_cont("H264_SCALING_MATRIX"); break; case V4L2_CTRL_TYPE_H264_SLICE_PARAMS: pr_cont("H264_SLICE_PARAMS"); break; case V4L2_CTRL_TYPE_H264_DECODE_PARAMS: pr_cont("H264_DECODE_PARAMS"); break; case V4L2_CTRL_TYPE_H264_PRED_WEIGHTS: pr_cont("H264_PRED_WEIGHTS"); break; case V4L2_CTRL_TYPE_FWHT_PARAMS: pr_cont("FWHT_PARAMS"); break; case V4L2_CTRL_TYPE_VP8_FRAME: pr_cont("VP8_FRAME"); break; case V4L2_CTRL_TYPE_HDR10_CLL_INFO: pr_cont("HDR10_CLL_INFO"); break; case V4L2_CTRL_TYPE_HDR10_MASTERING_DISPLAY: pr_cont("HDR10_MASTERING_DISPLAY"); break; case V4L2_CTRL_TYPE_MPEG2_QUANTISATION: pr_cont("MPEG2_QUANTISATION"); break; case V4L2_CTRL_TYPE_MPEG2_SEQUENCE: pr_cont("MPEG2_SEQUENCE"); break; case V4L2_CTRL_TYPE_MPEG2_PICTURE: pr_cont("MPEG2_PICTURE"); break; case V4L2_CTRL_TYPE_VP9_COMPRESSED_HDR: pr_cont("VP9_COMPRESSED_HDR"); break; case V4L2_CTRL_TYPE_VP9_FRAME: pr_cont("VP9_FRAME"); break; case V4L2_CTRL_TYPE_HEVC_SPS: pr_cont("HEVC_SPS"); break; case V4L2_CTRL_TYPE_HEVC_PPS: pr_cont("HEVC_PPS"); break; case V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS: pr_cont("HEVC_SLICE_PARAMS"); break; case V4L2_CTRL_TYPE_HEVC_SCALING_MATRIX: pr_cont("HEVC_SCALING_MATRIX"); break; case V4L2_CTRL_TYPE_HEVC_DECODE_PARAMS: pr_cont("HEVC_DECODE_PARAMS"); break; case V4L2_CTRL_TYPE_AV1_SEQUENCE: pr_cont("AV1_SEQUENCE"); break; case V4L2_CTRL_TYPE_AV1_TILE_GROUP_ENTRY: pr_cont("AV1_TILE_GROUP_ENTRY"); break; case V4L2_CTRL_TYPE_AV1_FRAME: pr_cont("AV1_FRAME"); break; case V4L2_CTRL_TYPE_AV1_FILM_GRAIN: pr_cont("AV1_FILM_GRAIN"); break; case V4L2_CTRL_TYPE_RECT: pr_cont("(%d,%d)/%ux%u", ptr.p_rect->left, ptr.p_rect->top, ptr.p_rect->width, ptr.p_rect->height); break; default: pr_cont("unknown type %d", ctrl->type); break; } } EXPORT_SYMBOL(v4l2_ctrl_type_op_log); /* * Round towards the closest legal value. Be careful when we are * close to the maximum range of the control type to prevent * wrap-arounds. */ #define ROUND_TO_RANGE(val, offset_type, ctrl) \ ({ \ offset_type offset; \ if ((ctrl)->maximum >= 0 && \ val >= (ctrl)->maximum - (s32)((ctrl)->step / 2)) \ val = (ctrl)->maximum; \ else \ val += (s32)((ctrl)->step / 2); \ val = clamp_t(typeof(val), val, \ (ctrl)->minimum, (ctrl)->maximum); \ offset = (val) - (ctrl)->minimum; \ offset = (ctrl)->step * (offset / (u32)(ctrl)->step); \ val = (ctrl)->minimum + offset; \ 0; \ }) /* Validate a new control */ #define zero_padding(s) \ memset(&(s).padding, 0, sizeof((s).padding)) #define zero_reserved(s) \ memset(&(s).reserved, 0, sizeof((s).reserved)) static int validate_vp9_lf_params(struct v4l2_vp9_loop_filter *lf) { unsigned int i; if (lf->flags & ~(V4L2_VP9_LOOP_FILTER_FLAG_DELTA_ENABLED | V4L2_VP9_LOOP_FILTER_FLAG_DELTA_UPDATE)) return -EINVAL; /* That all values are in the accepted range. */ if (lf->level > GENMASK(5, 0)) return -EINVAL; if (lf->sharpness > GENMASK(2, 0)) return -EINVAL; for (i = 0; i < ARRAY_SIZE(lf->ref_deltas); i++) if (lf->ref_deltas[i] < -63 || lf->ref_deltas[i] > 63) return -EINVAL; for (i = 0; i < ARRAY_SIZE(lf->mode_deltas); i++) if (lf->mode_deltas[i] < -63 || lf->mode_deltas[i] > 63) return -EINVAL; zero_reserved(*lf); return 0; } static int validate_vp9_quant_params(struct v4l2_vp9_quantization *quant) { if (quant->delta_q_y_dc < -15 || quant->delta_q_y_dc > 15 || quant->delta_q_uv_dc < -15 || quant->delta_q_uv_dc > 15 || quant->delta_q_uv_ac < -15 || quant->delta_q_uv_ac > 15) return -EINVAL; zero_reserved(*quant); return 0; } static int validate_vp9_seg_params(struct v4l2_vp9_segmentation *seg) { unsigned int i, j; if (seg->flags & ~(V4L2_VP9_SEGMENTATION_FLAG_ENABLED | V4L2_VP9_SEGMENTATION_FLAG_UPDATE_MAP | V4L2_VP9_SEGMENTATION_FLAG_TEMPORAL_UPDATE | V4L2_VP9_SEGMENTATION_FLAG_UPDATE_DATA | V4L2_VP9_SEGMENTATION_FLAG_ABS_OR_DELTA_UPDATE)) return -EINVAL; for (i = 0; i < ARRAY_SIZE(seg->feature_enabled); i++) { if (seg->feature_enabled[i] & ~V4L2_VP9_SEGMENT_FEATURE_ENABLED_MASK) return -EINVAL; } for (i = 0; i < ARRAY_SIZE(seg->feature_data); i++) { static const int range[] = { 255, 63, 3, 0 }; for (j = 0; j < ARRAY_SIZE(seg->feature_data[j]); j++) { if (seg->feature_data[i][j] < -range[j] || seg->feature_data[i][j] > range[j]) return -EINVAL; } } zero_reserved(*seg); return 0; } static int validate_vp9_compressed_hdr(struct v4l2_ctrl_vp9_compressed_hdr *hdr) { if (hdr->tx_mode > V4L2_VP9_TX_MODE_SELECT) return -EINVAL; return 0; } static int validate_vp9_frame(struct v4l2_ctrl_vp9_frame *frame) { int ret; /* Make sure we're not passed invalid flags. */ if (frame->flags & ~(V4L2_VP9_FRAME_FLAG_KEY_FRAME | V4L2_VP9_FRAME_FLAG_SHOW_FRAME | V4L2_VP9_FRAME_FLAG_ERROR_RESILIENT | V4L2_VP9_FRAME_FLAG_INTRA_ONLY | V4L2_VP9_FRAME_FLAG_ALLOW_HIGH_PREC_MV | V4L2_VP9_FRAME_FLAG_REFRESH_FRAME_CTX | V4L2_VP9_FRAME_FLAG_PARALLEL_DEC_MODE | V4L2_VP9_FRAME_FLAG_X_SUBSAMPLING | V4L2_VP9_FRAME_FLAG_Y_SUBSAMPLING | V4L2_VP9_FRAME_FLAG_COLOR_RANGE_FULL_SWING)) return -EINVAL; if (frame->flags & V4L2_VP9_FRAME_FLAG_ERROR_RESILIENT && frame->flags & V4L2_VP9_FRAME_FLAG_REFRESH_FRAME_CTX) return -EINVAL; if (frame->profile > V4L2_VP9_PROFILE_MAX) return -EINVAL; if (frame->reset_frame_context > V4L2_VP9_RESET_FRAME_CTX_ALL) return -EINVAL; if (frame->frame_context_idx >= V4L2_VP9_NUM_FRAME_CTX) return -EINVAL; /* * Profiles 0 and 1 only support 8-bit depth, profiles 2 and 3 only 10 * and 12 bit depths. */ if ((frame->profile < 2 && frame->bit_depth != 8) || (frame->profile >= 2 && (frame->bit_depth != 10 && frame->bit_depth != 12))) return -EINVAL; /* Profile 0 and 2 only accept YUV 4:2:0. */ if ((frame->profile == 0 || frame->profile == 2) && (!(frame->flags & V4L2_VP9_FRAME_FLAG_X_SUBSAMPLING) || !(frame->flags & V4L2_VP9_FRAME_FLAG_Y_SUBSAMPLING))) return -EINVAL; /* Profile 1 and 3 only accept YUV 4:2:2, 4:4:0 and 4:4:4. */ if ((frame->profile == 1 || frame->profile == 3) && ((frame->flags & V4L2_VP9_FRAME_FLAG_X_SUBSAMPLING) && (frame->flags & V4L2_VP9_FRAME_FLAG_Y_SUBSAMPLING))) return -EINVAL; if (frame->interpolation_filter > V4L2_VP9_INTERP_FILTER_SWITCHABLE) return -EINVAL; /* * According to the spec, tile_cols_log2 shall be less than or equal * to 6. */ if (frame->tile_cols_log2 > 6) return -EINVAL; if (frame->reference_mode > V4L2_VP9_REFERENCE_MODE_SELECT) return -EINVAL; ret = validate_vp9_lf_params(&frame->lf); if (ret) return ret; ret = validate_vp9_quant_params(&frame->quant); if (ret) return ret; ret = validate_vp9_seg_params(&frame->seg); if (ret) return ret; zero_reserved(*frame); return 0; } static int validate_av1_quantization(struct v4l2_av1_quantization *q) { if (q->flags > GENMASK(2, 0)) return -EINVAL; if (q->delta_q_y_dc < -64 || q->delta_q_y_dc > 63 || q->delta_q_u_dc < -64 || q->delta_q_u_dc > 63 || q->delta_q_v_dc < -64 || q->delta_q_v_dc > 63 || q->delta_q_u_ac < -64 || q->delta_q_u_ac > 63 || q->delta_q_v_ac < -64 || q->delta_q_v_ac > 63 || q->delta_q_res > GENMASK(1, 0)) return -EINVAL; if (q->qm_y > GENMASK(3, 0) || q->qm_u > GENMASK(3, 0) || q->qm_v > GENMASK(3, 0)) return -EINVAL; return 0; } static int validate_av1_segmentation(struct v4l2_av1_segmentation *s) { u32 i; u32 j; if (s->flags > GENMASK(4, 0)) return -EINVAL; for (i = 0; i < ARRAY_SIZE(s->feature_data); i++) { static const int segmentation_feature_signed[] = { 1, 1, 1, 1, 1, 0, 0, 0 }; static const int segmentation_feature_max[] = { 255, 63, 63, 63, 63, 7, 0, 0}; for (j = 0; j < ARRAY_SIZE(s->feature_data[j]); j++) { s32 limit = segmentation_feature_max[j]; if (segmentation_feature_signed[j]) { if (s->feature_data[i][j] < -limit || s->feature_data[i][j] > limit) return -EINVAL; } else { if (s->feature_data[i][j] < 0 || s->feature_data[i][j] > limit) return -EINVAL; } } } return 0; } static int validate_av1_loop_filter(struct v4l2_av1_loop_filter *lf) { u32 i; if (lf->flags > GENMASK(3, 0)) return -EINVAL; for (i = 0; i < ARRAY_SIZE(lf->level); i++) { if (lf->level[i] > GENMASK(5, 0)) return -EINVAL; } if (lf->sharpness > GENMASK(2, 0)) return -EINVAL; for (i = 0; i < ARRAY_SIZE(lf->ref_deltas); i++) { if (lf->ref_deltas[i] < -64 || lf->ref_deltas[i] > 63) return -EINVAL; } for (i = 0; i < ARRAY_SIZE(lf->mode_deltas); i++) { if (lf->mode_deltas[i] < -64 || lf->mode_deltas[i] > 63) return -EINVAL; } return 0; } static int validate_av1_cdef(struct v4l2_av1_cdef *cdef) { u32 i; if (cdef->damping_minus_3 > GENMASK(1, 0) || cdef->bits > GENMASK(1, 0)) return -EINVAL; for (i = 0; i < 1 << cdef->bits; i++) { if (cdef->y_pri_strength[i] > GENMASK(3, 0) || cdef->y_sec_strength[i] > 4 || cdef->uv_pri_strength[i] > GENMASK(3, 0) || cdef->uv_sec_strength[i] > 4) return -EINVAL; } return 0; } static int validate_av1_loop_restauration(struct v4l2_av1_loop_restoration *lr) { if (lr->lr_unit_shift > 3 || lr->lr_uv_shift > 1) return -EINVAL; return 0; } static int validate_av1_film_grain(struct v4l2_ctrl_av1_film_grain *fg) { u32 i; if (fg->flags > GENMASK(4, 0)) return -EINVAL; if (fg->film_grain_params_ref_idx > GENMASK(2, 0) || fg->num_y_points > 14 || fg->num_cb_points > 10 || fg->num_cr_points > GENMASK(3, 0) || fg->grain_scaling_minus_8 > GENMASK(1, 0) || fg->ar_coeff_lag > GENMASK(1, 0) || fg->ar_coeff_shift_minus_6 > GENMASK(1, 0) || fg->grain_scale_shift > GENMASK(1, 0)) return -EINVAL; if (!(fg->flags & V4L2_AV1_FILM_GRAIN_FLAG_APPLY_GRAIN)) return 0; for (i = 1; i < fg->num_y_points; i++) if (fg->point_y_value[i] <= fg->point_y_value[i - 1]) return -EINVAL; for (i = 1; i < fg->num_cb_points; i++) if (fg->point_cb_value[i] <= fg->point_cb_value[i - 1]) return -EINVAL; for (i = 1; i < fg->num_cr_points; i++) if (fg->point_cr_value[i] <= fg->point_cr_value[i - 1]) return -EINVAL; return 0; } static int validate_av1_frame(struct v4l2_ctrl_av1_frame *f) { int ret = 0; ret = validate_av1_quantization(&f->quantization); if (ret) return ret; ret = validate_av1_segmentation(&f->segmentation); if (ret) return ret; ret = validate_av1_loop_filter(&f->loop_filter); if (ret) return ret; ret = validate_av1_cdef(&f->cdef); if (ret) return ret; ret = validate_av1_loop_restauration(&f->loop_restoration); if (ret) return ret; if (f->flags & ~(V4L2_AV1_FRAME_FLAG_SHOW_FRAME | V4L2_AV1_FRAME_FLAG_SHOWABLE_FRAME | V4L2_AV1_FRAME_FLAG_ERROR_RESILIENT_MODE | V4L2_AV1_FRAME_FLAG_DISABLE_CDF_UPDATE | V4L2_AV1_FRAME_FLAG_ALLOW_SCREEN_CONTENT_TOOLS | V4L2_AV1_FRAME_FLAG_FORCE_INTEGER_MV | V4L2_AV1_FRAME_FLAG_ALLOW_INTRABC | V4L2_AV1_FRAME_FLAG_USE_SUPERRES | V4L2_AV1_FRAME_FLAG_ALLOW_HIGH_PRECISION_MV | V4L2_AV1_FRAME_FLAG_IS_MOTION_MODE_SWITCHABLE | V4L2_AV1_FRAME_FLAG_USE_REF_FRAME_MVS | V4L2_AV1_FRAME_FLAG_DISABLE_FRAME_END_UPDATE_CDF | V4L2_AV1_FRAME_FLAG_ALLOW_WARPED_MOTION | V4L2_AV1_FRAME_FLAG_REFERENCE_SELECT | V4L2_AV1_FRAME_FLAG_REDUCED_TX_SET | V4L2_AV1_FRAME_FLAG_SKIP_MODE_ALLOWED | V4L2_AV1_FRAME_FLAG_SKIP_MODE_PRESENT | V4L2_AV1_FRAME_FLAG_FRAME_SIZE_OVERRIDE | V4L2_AV1_FRAME_FLAG_BUFFER_REMOVAL_TIME_PRESENT | V4L2_AV1_FRAME_FLAG_FRAME_REFS_SHORT_SIGNALING)) return -EINVAL; if (f->superres_denom > GENMASK(2, 0) + 9) return -EINVAL; return 0; } static int validate_av1_sequence(struct v4l2_ctrl_av1_sequence *s) { if (s->flags & ~(V4L2_AV1_SEQUENCE_FLAG_STILL_PICTURE | V4L2_AV1_SEQUENCE_FLAG_USE_128X128_SUPERBLOCK | V4L2_AV1_SEQUENCE_FLAG_ENABLE_FILTER_INTRA | V4L2_AV1_SEQUENCE_FLAG_ENABLE_INTRA_EDGE_FILTER | V4L2_AV1_SEQUENCE_FLAG_ENABLE_INTERINTRA_COMPOUND | V4L2_AV1_SEQUENCE_FLAG_ENABLE_MASKED_COMPOUND | V4L2_AV1_SEQUENCE_FLAG_ENABLE_WARPED_MOTION | V4L2_AV1_SEQUENCE_FLAG_ENABLE_DUAL_FILTER | V4L2_AV1_SEQUENCE_FLAG_ENABLE_ORDER_HINT | V4L2_AV1_SEQUENCE_FLAG_ENABLE_JNT_COMP | V4L2_AV1_SEQUENCE_FLAG_ENABLE_REF_FRAME_MVS | V4L2_AV1_SEQUENCE_FLAG_ENABLE_SUPERRES | V4L2_AV1_SEQUENCE_FLAG_ENABLE_CDEF | V4L2_AV1_SEQUENCE_FLAG_ENABLE_RESTORATION | V4L2_AV1_SEQUENCE_FLAG_MONO_CHROME | V4L2_AV1_SEQUENCE_FLAG_COLOR_RANGE | V4L2_AV1_SEQUENCE_FLAG_SUBSAMPLING_X | V4L2_AV1_SEQUENCE_FLAG_SUBSAMPLING_Y | V4L2_AV1_SEQUENCE_FLAG_FILM_GRAIN_PARAMS_PRESENT | V4L2_AV1_SEQUENCE_FLAG_SEPARATE_UV_DELTA_Q)) return -EINVAL; if (s->seq_profile == 1 && s->flags & V4L2_AV1_SEQUENCE_FLAG_MONO_CHROME) return -EINVAL; /* reserved */ if (s->seq_profile > 2) return -EINVAL; /* TODO: PROFILES */ return 0; } /* * Compound controls validation requires setting unused fields/flags to zero * in order to properly detect unchanged controls with v4l2_ctrl_type_op_equal's * memcmp. */ static int std_validate_compound(const struct v4l2_ctrl *ctrl, u32 idx, union v4l2_ctrl_ptr ptr) { struct v4l2_ctrl_mpeg2_sequence *p_mpeg2_sequence; struct v4l2_ctrl_mpeg2_picture *p_mpeg2_picture; struct v4l2_ctrl_vp8_frame *p_vp8_frame; struct v4l2_ctrl_fwht_params *p_fwht_params; struct v4l2_ctrl_h264_sps *p_h264_sps; struct v4l2_ctrl_h264_pps *p_h264_pps; struct v4l2_ctrl_h264_pred_weights *p_h264_pred_weights; struct v4l2_ctrl_h264_slice_params *p_h264_slice_params; struct v4l2_ctrl_h264_decode_params *p_h264_dec_params; struct v4l2_ctrl_hevc_sps *p_hevc_sps; struct v4l2_ctrl_hevc_pps *p_hevc_pps; struct v4l2_ctrl_hdr10_mastering_display *p_hdr10_mastering; struct v4l2_ctrl_hevc_decode_params *p_hevc_decode_params; struct v4l2_area *area; struct v4l2_rect *rect; void *p = ptr.p + idx * ctrl->elem_size; unsigned int i; switch ((u32)ctrl->type) { case V4L2_CTRL_TYPE_MPEG2_SEQUENCE: p_mpeg2_sequence = p; switch (p_mpeg2_sequence->chroma_format) { case 1: /* 4:2:0 */ case 2: /* 4:2:2 */ case 3: /* 4:4:4 */ break; default: return -EINVAL; } break; case V4L2_CTRL_TYPE_MPEG2_PICTURE: p_mpeg2_picture = p; switch (p_mpeg2_picture->intra_dc_precision) { case 0: /* 8 bits */ case 1: /* 9 bits */ case 2: /* 10 bits */ case 3: /* 11 bits */ break; default: return -EINVAL; } switch (p_mpeg2_picture->picture_structure) { case V4L2_MPEG2_PIC_TOP_FIELD: case V4L2_MPEG2_PIC_BOTTOM_FIELD: case V4L2_MPEG2_PIC_FRAME: break; default: return -EINVAL; } switch (p_mpeg2_picture->picture_coding_type) { case V4L2_MPEG2_PIC_CODING_TYPE_I: case V4L2_MPEG2_PIC_CODING_TYPE_P: case V4L2_MPEG2_PIC_CODING_TYPE_B: break; default: return -EINVAL; } zero_reserved(*p_mpeg2_picture); break; case V4L2_CTRL_TYPE_MPEG2_QUANTISATION: break; case V4L2_CTRL_TYPE_FWHT_PARAMS: p_fwht_params = p; if (p_fwht_params->version < V4L2_FWHT_VERSION) return -EINVAL; if (!p_fwht_params->width || !p_fwht_params->height) return -EINVAL; break; case V4L2_CTRL_TYPE_H264_SPS: p_h264_sps = p; /* Some syntax elements are only conditionally valid */ if (p_h264_sps->pic_order_cnt_type != 0) { p_h264_sps->log2_max_pic_order_cnt_lsb_minus4 = 0; } else if (p_h264_sps->pic_order_cnt_type != 1) { p_h264_sps->num_ref_frames_in_pic_order_cnt_cycle = 0; p_h264_sps->offset_for_non_ref_pic = 0; p_h264_sps->offset_for_top_to_bottom_field = 0; memset(&p_h264_sps->offset_for_ref_frame, 0, sizeof(p_h264_sps->offset_for_ref_frame)); } if (!V4L2_H264_SPS_HAS_CHROMA_FORMAT(p_h264_sps)) { p_h264_sps->chroma_format_idc = 1; p_h264_sps->bit_depth_luma_minus8 = 0; p_h264_sps->bit_depth_chroma_minus8 = 0; p_h264_sps->flags &= ~V4L2_H264_SPS_FLAG_QPPRIME_Y_ZERO_TRANSFORM_BYPASS; if (p_h264_sps->chroma_format_idc < 3) p_h264_sps->flags &= ~V4L2_H264_SPS_FLAG_SEPARATE_COLOUR_PLANE; } if (p_h264_sps->flags & V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY) p_h264_sps->flags &= ~V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD; /* * Chroma 4:2:2 format require at least High 4:2:2 profile. * * The H264 specification and well-known parser implementations * use profile-idc values directly, as that is clearer and * less ambiguous. We do the same here. */ if (p_h264_sps->profile_idc < 122 && p_h264_sps->chroma_format_idc > 1) return -EINVAL; /* Chroma 4:4:4 format require at least High 4:2:2 profile */ if (p_h264_sps->profile_idc < 244 && p_h264_sps->chroma_format_idc > 2) return -EINVAL; if (p_h264_sps->chroma_format_idc > 3) return -EINVAL; if (p_h264_sps->bit_depth_luma_minus8 > 6) return -EINVAL; if (p_h264_sps->bit_depth_chroma_minus8 > 6) return -EINVAL; if (p_h264_sps->log2_max_frame_num_minus4 > 12) return -EINVAL; if (p_h264_sps->pic_order_cnt_type > 2) return -EINVAL; if (p_h264_sps->log2_max_pic_order_cnt_lsb_minus4 > 12) return -EINVAL; if (p_h264_sps->max_num_ref_frames > V4L2_H264_REF_LIST_LEN) return -EINVAL; break; case V4L2_CTRL_TYPE_H264_PPS: p_h264_pps = p; if (p_h264_pps->num_slice_groups_minus1 > 7) return -EINVAL; if (p_h264_pps->num_ref_idx_l0_default_active_minus1 > (V4L2_H264_REF_LIST_LEN - 1)) return -EINVAL; if (p_h264_pps->num_ref_idx_l1_default_active_minus1 > (V4L2_H264_REF_LIST_LEN - 1)) return -EINVAL; if (p_h264_pps->weighted_bipred_idc > 2) return -EINVAL; /* * pic_init_qp_minus26 shall be in the range of * -(26 + QpBdOffset_y) to +25, inclusive, * where QpBdOffset_y is 6 * bit_depth_luma_minus8 */ if (p_h264_pps->pic_init_qp_minus26 < -62 || p_h264_pps->pic_init_qp_minus26 > 25) return -EINVAL; if (p_h264_pps->pic_init_qs_minus26 < -26 || p_h264_pps->pic_init_qs_minus26 > 25) return -EINVAL; if (p_h264_pps->chroma_qp_index_offset < -12 || p_h264_pps->chroma_qp_index_offset > 12) return -EINVAL; if (p_h264_pps->second_chroma_qp_index_offset < -12 || p_h264_pps->second_chroma_qp_index_offset > 12) return -EINVAL; break; case V4L2_CTRL_TYPE_H264_SCALING_MATRIX: break; case V4L2_CTRL_TYPE_H264_PRED_WEIGHTS: p_h264_pred_weights = p; if (p_h264_pred_weights->luma_log2_weight_denom > 7) return -EINVAL; if (p_h264_pred_weights->chroma_log2_weight_denom > 7) return -EINVAL; break; case V4L2_CTRL_TYPE_H264_SLICE_PARAMS: p_h264_slice_params = p; if (p_h264_slice_params->slice_type != V4L2_H264_SLICE_TYPE_B) p_h264_slice_params->flags &= ~V4L2_H264_SLICE_FLAG_DIRECT_SPATIAL_MV_PRED; if (p_h264_slice_params->colour_plane_id > 2) return -EINVAL; if (p_h264_slice_params->cabac_init_idc > 2) return -EINVAL; if (p_h264_slice_params->disable_deblocking_filter_idc > 2) return -EINVAL; if (p_h264_slice_params->slice_alpha_c0_offset_div2 < -6 || p_h264_slice_params->slice_alpha_c0_offset_div2 > 6) return -EINVAL; if (p_h264_slice_params->slice_beta_offset_div2 < -6 || p_h264_slice_params->slice_beta_offset_div2 > 6) return -EINVAL; if (p_h264_slice_params->slice_type == V4L2_H264_SLICE_TYPE_I || p_h264_slice_params->slice_type == V4L2_H264_SLICE_TYPE_SI) p_h264_slice_params->num_ref_idx_l0_active_minus1 = 0; if (p_h264_slice_params->slice_type != V4L2_H264_SLICE_TYPE_B) p_h264_slice_params->num_ref_idx_l1_active_minus1 = 0; if (p_h264_slice_params->num_ref_idx_l0_active_minus1 > (V4L2_H264_REF_LIST_LEN - 1)) return -EINVAL; if (p_h264_slice_params->num_ref_idx_l1_active_minus1 > (V4L2_H264_REF_LIST_LEN - 1)) return -EINVAL; zero_reserved(*p_h264_slice_params); break; case V4L2_CTRL_TYPE_H264_DECODE_PARAMS: p_h264_dec_params = p; if (p_h264_dec_params->nal_ref_idc > 3) return -EINVAL; for (i = 0; i < V4L2_H264_NUM_DPB_ENTRIES; i++) { struct v4l2_h264_dpb_entry *dpb_entry = &p_h264_dec_params->dpb[i]; zero_reserved(*dpb_entry); } zero_reserved(*p_h264_dec_params); break; case V4L2_CTRL_TYPE_VP8_FRAME: p_vp8_frame = p; switch (p_vp8_frame->num_dct_parts) { case 1: case 2: case 4: case 8: break; default: return -EINVAL; } zero_padding(p_vp8_frame->segment); zero_padding(p_vp8_frame->lf); zero_padding(p_vp8_frame->quant); zero_padding(p_vp8_frame->entropy); zero_padding(p_vp8_frame->coder_state); break; case V4L2_CTRL_TYPE_HEVC_SPS: p_hevc_sps = p; if (!(p_hevc_sps->flags & V4L2_HEVC_SPS_FLAG_PCM_ENABLED)) { p_hevc_sps->pcm_sample_bit_depth_luma_minus1 = 0; p_hevc_sps->pcm_sample_bit_depth_chroma_minus1 = 0; p_hevc_sps->log2_min_pcm_luma_coding_block_size_minus3 = 0; p_hevc_sps->log2_diff_max_min_pcm_luma_coding_block_size = 0; } if (!(p_hevc_sps->flags & V4L2_HEVC_SPS_FLAG_LONG_TERM_REF_PICS_PRESENT)) p_hevc_sps->num_long_term_ref_pics_sps = 0; break; case V4L2_CTRL_TYPE_HEVC_PPS: p_hevc_pps = p; if (!(p_hevc_pps->flags & V4L2_HEVC_PPS_FLAG_CU_QP_DELTA_ENABLED)) p_hevc_pps->diff_cu_qp_delta_depth = 0; if (!(p_hevc_pps->flags & V4L2_HEVC_PPS_FLAG_TILES_ENABLED)) { p_hevc_pps->num_tile_columns_minus1 = 0; p_hevc_pps->num_tile_rows_minus1 = 0; memset(&p_hevc_pps->column_width_minus1, 0, sizeof(p_hevc_pps->column_width_minus1)); memset(&p_hevc_pps->row_height_minus1, 0, sizeof(p_hevc_pps->row_height_minus1)); p_hevc_pps->flags &= ~V4L2_HEVC_PPS_FLAG_LOOP_FILTER_ACROSS_TILES_ENABLED; } if (p_hevc_pps->flags & V4L2_HEVC_PPS_FLAG_PPS_DISABLE_DEBLOCKING_FILTER) { p_hevc_pps->pps_beta_offset_div2 = 0; p_hevc_pps->pps_tc_offset_div2 = 0; } break; case V4L2_CTRL_TYPE_HEVC_DECODE_PARAMS: p_hevc_decode_params = p; if (p_hevc_decode_params->num_active_dpb_entries > V4L2_HEVC_DPB_ENTRIES_NUM_MAX) return -EINVAL; break; case V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS: break; case V4L2_CTRL_TYPE_HDR10_CLL_INFO: break; case V4L2_CTRL_TYPE_HDR10_MASTERING_DISPLAY: p_hdr10_mastering = p; for (i = 0; i < 3; ++i) { if (p_hdr10_mastering->display_primaries_x[i] < V4L2_HDR10_MASTERING_PRIMARIES_X_LOW || p_hdr10_mastering->display_primaries_x[i] > V4L2_HDR10_MASTERING_PRIMARIES_X_HIGH || p_hdr10_mastering->display_primaries_y[i] < V4L2_HDR10_MASTERING_PRIMARIES_Y_LOW || p_hdr10_mastering->display_primaries_y[i] > V4L2_HDR10_MASTERING_PRIMARIES_Y_HIGH) return -EINVAL; } if (p_hdr10_mastering->white_point_x < V4L2_HDR10_MASTERING_WHITE_POINT_X_LOW || p_hdr10_mastering->white_point_x > V4L2_HDR10_MASTERING_WHITE_POINT_X_HIGH || p_hdr10_mastering->white_point_y < V4L2_HDR10_MASTERING_WHITE_POINT_Y_LOW || p_hdr10_mastering->white_point_y > V4L2_HDR10_MASTERING_WHITE_POINT_Y_HIGH) return -EINVAL; if (p_hdr10_mastering->max_display_mastering_luminance < V4L2_HDR10_MASTERING_MAX_LUMA_LOW || p_hdr10_mastering->max_display_mastering_luminance > V4L2_HDR10_MASTERING_MAX_LUMA_HIGH || p_hdr10_mastering->min_display_mastering_luminance < V4L2_HDR10_MASTERING_MIN_LUMA_LOW || p_hdr10_mastering->min_display_mastering_luminance > V4L2_HDR10_MASTERING_MIN_LUMA_HIGH) return -EINVAL; /* The following restriction comes from ITU-T Rec. H.265 spec */ if (p_hdr10_mastering->max_display_mastering_luminance == V4L2_HDR10_MASTERING_MAX_LUMA_LOW && p_hdr10_mastering->min_display_mastering_luminance == V4L2_HDR10_MASTERING_MIN_LUMA_HIGH) return -EINVAL; break; case V4L2_CTRL_TYPE_HEVC_SCALING_MATRIX: break; case V4L2_CTRL_TYPE_VP9_COMPRESSED_HDR: return validate_vp9_compressed_hdr(p); case V4L2_CTRL_TYPE_VP9_FRAME: return validate_vp9_frame(p); case V4L2_CTRL_TYPE_AV1_FRAME: return validate_av1_frame(p); case V4L2_CTRL_TYPE_AV1_SEQUENCE: return validate_av1_sequence(p); case V4L2_CTRL_TYPE_AV1_TILE_GROUP_ENTRY: break; case V4L2_CTRL_TYPE_AV1_FILM_GRAIN: return validate_av1_film_grain(p); case V4L2_CTRL_TYPE_AREA: area = p; if (!area->width || !area->height) return -EINVAL; break; case V4L2_CTRL_TYPE_RECT: rect = p; if (!rect->width || !rect->height) return -EINVAL; break; default: return -EINVAL; } return 0; } static int std_validate_elem(const struct v4l2_ctrl *ctrl, u32 idx, union v4l2_ctrl_ptr ptr) { size_t len; u64 offset; s64 val; switch ((u32)ctrl->type) { case V4L2_CTRL_TYPE_INTEGER: return ROUND_TO_RANGE(ptr.p_s32[idx], u32, ctrl); case V4L2_CTRL_TYPE_INTEGER64: /* * We can't use the ROUND_TO_RANGE define here due to * the u64 divide that needs special care. */ val = ptr.p_s64[idx]; if (ctrl->maximum >= 0 && val >= ctrl->maximum - (s64)(ctrl->step / 2)) val = ctrl->maximum; else val += (s64)(ctrl->step / 2); val = clamp_t(s64, val, ctrl->minimum, ctrl->maximum); offset = val - ctrl->minimum; do_div(offset, ctrl->step); ptr.p_s64[idx] = ctrl->minimum + offset * ctrl->step; return 0; case V4L2_CTRL_TYPE_U8: return ROUND_TO_RANGE(ptr.p_u8[idx], u8, ctrl); case V4L2_CTRL_TYPE_U16: return ROUND_TO_RANGE(ptr.p_u16[idx], u16, ctrl); case V4L2_CTRL_TYPE_U32: return ROUND_TO_RANGE(ptr.p_u32[idx], u32, ctrl); case V4L2_CTRL_TYPE_BOOLEAN: ptr.p_s32[idx] = !!ptr.p_s32[idx]; return 0; case V4L2_CTRL_TYPE_MENU: case V4L2_CTRL_TYPE_INTEGER_MENU: if (ptr.p_s32[idx] < ctrl->minimum || ptr.p_s32[idx] > ctrl->maximum) return -ERANGE; if (ptr.p_s32[idx] < BITS_PER_LONG_LONG && (ctrl->menu_skip_mask & BIT_ULL(ptr.p_s32[idx]))) return -EINVAL; if (ctrl->type == V4L2_CTRL_TYPE_MENU && ctrl->qmenu[ptr.p_s32[idx]][0] == '\0') return -EINVAL; return 0; case V4L2_CTRL_TYPE_BITMASK: ptr.p_s32[idx] &= ctrl->maximum; return 0; case V4L2_CTRL_TYPE_BUTTON: case V4L2_CTRL_TYPE_CTRL_CLASS: ptr.p_s32[idx] = 0; return 0; case V4L2_CTRL_TYPE_STRING: idx *= ctrl->elem_size; len = strlen(ptr.p_char + idx); if (len < ctrl->minimum) return -ERANGE; if ((len - (u32)ctrl->minimum) % (u32)ctrl->step) return -ERANGE; return 0; default: return std_validate_compound(ctrl, idx, ptr); } } int v4l2_ctrl_type_op_validate(const struct v4l2_ctrl *ctrl, union v4l2_ctrl_ptr ptr) { unsigned int i; int ret = 0; switch ((u32)ctrl->type) { case V4L2_CTRL_TYPE_U8: if (ctrl->maximum == 0xff && ctrl->minimum == 0 && ctrl->step == 1) return 0; break; case V4L2_CTRL_TYPE_U16: if (ctrl->maximum == 0xffff && ctrl->minimum == 0 && ctrl->step == 1) return 0; break; case V4L2_CTRL_TYPE_U32: if (ctrl->maximum == 0xffffffff && ctrl->minimum == 0 && ctrl->step == 1) return 0; break; case V4L2_CTRL_TYPE_BUTTON: case V4L2_CTRL_TYPE_CTRL_CLASS: memset(ptr.p_s32, 0, ctrl->new_elems * sizeof(s32)); return 0; } for (i = 0; !ret && i < ctrl->new_elems; i++) ret = std_validate_elem(ctrl, i, ptr); return ret; } EXPORT_SYMBOL(v4l2_ctrl_type_op_validate); static const struct v4l2_ctrl_type_ops std_type_ops = { .equal = v4l2_ctrl_type_op_equal, .init = v4l2_ctrl_type_op_init, .minimum = v4l2_ctrl_type_op_minimum, .maximum = v4l2_ctrl_type_op_maximum, .log = v4l2_ctrl_type_op_log, .validate = v4l2_ctrl_type_op_validate, }; void v4l2_ctrl_notify(struct v4l2_ctrl *ctrl, v4l2_ctrl_notify_fnc notify, void *priv) { if (!ctrl) return; if (!notify) { ctrl->call_notify = 0; return; } if (WARN_ON(ctrl->handler->notify && ctrl->handler->notify != notify)) return; ctrl->handler->notify = notify; ctrl->handler->notify_priv = priv; ctrl->call_notify = 1; } EXPORT_SYMBOL(v4l2_ctrl_notify); /* Copy the one value to another. */ static void ptr_to_ptr(struct v4l2_ctrl *ctrl, union v4l2_ctrl_ptr from, union v4l2_ctrl_ptr to, unsigned int elems) { if (ctrl == NULL) return; memcpy(to.p, from.p_const, elems * ctrl->elem_size); } /* Copy the new value to the current value. */ void new_to_cur(struct v4l2_fh *fh, struct v4l2_ctrl *ctrl, u32 ch_flags) { bool changed; if (ctrl == NULL) return; /* has_changed is set by cluster_changed */ changed = ctrl->has_changed; if (changed) { if (ctrl->is_dyn_array) ctrl->elems = ctrl->new_elems; ptr_to_ptr(ctrl, ctrl->p_new, ctrl->p_cur, ctrl->elems); } if (ch_flags & V4L2_EVENT_CTRL_CH_FLAGS) { /* Note: CH_FLAGS is only set for auto clusters. */ ctrl->flags &= ~(V4L2_CTRL_FLAG_INACTIVE | V4L2_CTRL_FLAG_VOLATILE); if (!is_cur_manual(ctrl->cluster[0])) { ctrl->flags |= V4L2_CTRL_FLAG_INACTIVE; if (ctrl->cluster[0]->has_volatiles) ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE; } fh = NULL; } if (changed || ch_flags) { /* If a control was changed that was not one of the controls modified by the application, then send the event to all. */ if (!ctrl->is_new) fh = NULL; send_event(fh, ctrl, (changed ? V4L2_EVENT_CTRL_CH_VALUE : 0) | ch_flags); if (ctrl->call_notify && changed && ctrl->handler->notify) ctrl->handler->notify(ctrl, ctrl->handler->notify_priv); } } /* Copy the current value to the new value */ void cur_to_new(struct v4l2_ctrl *ctrl) { if (ctrl == NULL) return; if (ctrl->is_dyn_array) ctrl->new_elems = ctrl->elems; ptr_to_ptr(ctrl, ctrl->p_cur, ctrl->p_new, ctrl->new_elems); } static bool req_alloc_array(struct v4l2_ctrl_ref *ref, u32 elems) { void *tmp; if (elems == ref->p_req_array_alloc_elems) return true; if (ref->ctrl->is_dyn_array && elems < ref->p_req_array_alloc_elems) return true; tmp = kvmalloc(elems * ref->ctrl->elem_size, GFP_KERNEL); if (!tmp) { ref->p_req_array_enomem = true; return false; } ref->p_req_array_enomem = false; kvfree(ref->p_req.p); ref->p_req.p = tmp; ref->p_req_array_alloc_elems = elems; return true; } /* Copy the new value to the request value */ void new_to_req(struct v4l2_ctrl_ref *ref) { struct v4l2_ctrl *ctrl; if (!ref) return; ctrl = ref->ctrl; if (ctrl->is_array && !req_alloc_array(ref, ctrl->new_elems)) return; ref->p_req_elems = ctrl->new_elems; ptr_to_ptr(ctrl, ctrl->p_new, ref->p_req, ref->p_req_elems); ref->p_req_valid = true; } /* Copy the current value to the request value */ void cur_to_req(struct v4l2_ctrl_ref *ref) { struct v4l2_ctrl *ctrl; if (!ref) return; ctrl = ref->ctrl; if (ctrl->is_array && !req_alloc_array(ref, ctrl->elems)) return; ref->p_req_elems = ctrl->elems; ptr_to_ptr(ctrl, ctrl->p_cur, ref->p_req, ctrl->elems); ref->p_req_valid = true; } /* Copy the request value to the new value */ int req_to_new(struct v4l2_ctrl_ref *ref) { struct v4l2_ctrl *ctrl; if (!ref) return 0; ctrl = ref->ctrl; /* * This control was never set in the request, so just use the current * value. */ if (!ref->p_req_valid) { if (ctrl->is_dyn_array) ctrl->new_elems = ctrl->elems; ptr_to_ptr(ctrl, ctrl->p_cur, ctrl->p_new, ctrl->new_elems); return 0; } /* Not an array, so just copy the request value */ if (!ctrl->is_array) { ptr_to_ptr(ctrl, ref->p_req, ctrl->p_new, ctrl->new_elems); return 0; } /* Sanity check, should never happen */ if (WARN_ON(!ref->p_req_array_alloc_elems)) return -ENOMEM; if (!ctrl->is_dyn_array && ref->p_req_elems != ctrl->p_array_alloc_elems) return -ENOMEM; /* * Check if the number of elements in the request is more than the * elements in ctrl->p_array. If so, attempt to realloc ctrl->p_array. * Note that p_array is allocated with twice the number of elements * in the dynamic array since it has to store both the current and * new value of such a control. */ if (ref->p_req_elems > ctrl->p_array_alloc_elems) { unsigned int sz = ref->p_req_elems * ctrl->elem_size; void *old = ctrl->p_array; void *tmp = kvzalloc(2 * sz, GFP_KERNEL); if (!tmp) return -ENOMEM; memcpy(tmp, ctrl->p_new.p, ctrl->elems * ctrl->elem_size); memcpy(tmp + sz, ctrl->p_cur.p, ctrl->elems * ctrl->elem_size); ctrl->p_new.p = tmp; ctrl->p_cur.p = tmp + sz; ctrl->p_array = tmp; ctrl->p_array_alloc_elems = ref->p_req_elems; kvfree(old); } ctrl->new_elems = ref->p_req_elems; ptr_to_ptr(ctrl, ref->p_req, ctrl->p_new, ctrl->new_elems); return 0; } /* Control range checking */ int check_range(enum v4l2_ctrl_type type, s64 min, s64 max, u64 step, s64 def) { switch (type) { case V4L2_CTRL_TYPE_BOOLEAN: if (step != 1 || max > 1 || min < 0) return -ERANGE; fallthrough; case V4L2_CTRL_TYPE_U8: case V4L2_CTRL_TYPE_U16: case V4L2_CTRL_TYPE_U32: case V4L2_CTRL_TYPE_INTEGER: case V4L2_CTRL_TYPE_INTEGER64: if (step == 0 || min > max || def < min || def > max) return -ERANGE; return 0; case V4L2_CTRL_TYPE_BITMASK: if (step || min || !max || (def & ~max)) return -ERANGE; return 0; case V4L2_CTRL_TYPE_MENU: case V4L2_CTRL_TYPE_INTEGER_MENU: if (min > max || def < min || def > max || min < 0 || (step && max >= BITS_PER_LONG_LONG)) return -ERANGE; /* Note: step == menu_skip_mask for menu controls. So here we check if the default value is masked out. */ if (def < BITS_PER_LONG_LONG && (step & BIT_ULL(def))) return -EINVAL; return 0; case V4L2_CTRL_TYPE_STRING: if (min > max || min < 0 || step < 1 || def) return -ERANGE; return 0; default: return 0; } } /* Set the handler's error code if it wasn't set earlier already */ static inline int handler_set_err(struct v4l2_ctrl_handler *hdl, int err) { if (hdl->error == 0) hdl->error = err; return err; } /* Initialize the handler */ int v4l2_ctrl_handler_init_class(struct v4l2_ctrl_handler *hdl, unsigned nr_of_controls_hint, struct lock_class_key *key, const char *name) { mutex_init(&hdl->_lock); hdl->lock = &hdl->_lock; lockdep_set_class_and_name(hdl->lock, key, name); INIT_LIST_HEAD(&hdl->ctrls); INIT_LIST_HEAD(&hdl->ctrl_refs); hdl->nr_of_buckets = 1 + nr_of_controls_hint / 8; hdl->buckets = kvcalloc(hdl->nr_of_buckets, sizeof(hdl->buckets[0]), GFP_KERNEL); hdl->error = hdl->buckets ? 0 : -ENOMEM; v4l2_ctrl_handler_init_request(hdl); return hdl->error; } EXPORT_SYMBOL(v4l2_ctrl_handler_init_class); /* Free all controls and control refs */ void v4l2_ctrl_handler_free(struct v4l2_ctrl_handler *hdl) { struct v4l2_ctrl_ref *ref, *next_ref; struct v4l2_ctrl *ctrl, *next_ctrl; struct v4l2_subscribed_event *sev, *next_sev; if (hdl == NULL || hdl->buckets == NULL) return; v4l2_ctrl_handler_free_request(hdl); mutex_lock(hdl->lock); /* Free all nodes */ list_for_each_entry_safe(ref, next_ref, &hdl->ctrl_refs, node) { list_del(&ref->node); if (ref->p_req_array_alloc_elems) kvfree(ref->p_req.p); kfree(ref); } /* Free all controls owned by the handler */ list_for_each_entry_safe(ctrl, next_ctrl, &hdl->ctrls, node) { list_del(&ctrl->node); list_for_each_entry_safe(sev, next_sev, &ctrl->ev_subs, node) list_del(&sev->node); kvfree(ctrl->p_array); kvfree(ctrl); } kvfree(hdl->buckets); hdl->buckets = NULL; hdl->cached = NULL; hdl->error = 0; mutex_unlock(hdl->lock); mutex_destroy(&hdl->_lock); } EXPORT_SYMBOL(v4l2_ctrl_handler_free); /* For backwards compatibility: V4L2_CID_PRIVATE_BASE should no longer be used except in G_CTRL, S_CTRL, QUERYCTRL and QUERYMENU when dealing with applications that do not use the NEXT_CTRL flag. We just find the n-th private user control. It's O(N), but that should not be an issue in this particular case. */ static struct v4l2_ctrl_ref *find_private_ref( struct v4l2_ctrl_handler *hdl, u32 id) { struct v4l2_ctrl_ref *ref; id -= V4L2_CID_PRIVATE_BASE; list_for_each_entry(ref, &hdl->ctrl_refs, node) { /* Search for private user controls that are compatible with VIDIOC_G/S_CTRL. */ if (V4L2_CTRL_ID2WHICH(ref->ctrl->id) == V4L2_CTRL_CLASS_USER && V4L2_CTRL_DRIVER_PRIV(ref->ctrl->id)) { if (!ref->ctrl->is_int) continue; if (id == 0) return ref; id--; } } return NULL; } /* Find a control with the given ID. */ struct v4l2_ctrl_ref *find_ref(struct v4l2_ctrl_handler *hdl, u32 id) { struct v4l2_ctrl_ref *ref; int bucket; id &= V4L2_CTRL_ID_MASK; /* Old-style private controls need special handling */ if (id >= V4L2_CID_PRIVATE_BASE) return find_private_ref(hdl, id); bucket = id % hdl->nr_of_buckets; /* Simple optimization: cache the last control found */ if (hdl->cached && hdl->cached->ctrl->id == id) return hdl->cached; /* Not in cache, search the hash */ ref = hdl->buckets ? hdl->buckets[bucket] : NULL; while (ref && ref->ctrl->id != id) ref = ref->next; if (ref) hdl->cached = ref; /* cache it! */ return ref; } /* Find a control with the given ID. Take the handler's lock first. */ struct v4l2_ctrl_ref *find_ref_lock(struct v4l2_ctrl_handler *hdl, u32 id) { struct v4l2_ctrl_ref *ref = NULL; if (hdl) { mutex_lock(hdl->lock); ref = find_ref(hdl, id); mutex_unlock(hdl->lock); } return ref; } /* Find a control with the given ID. */ struct v4l2_ctrl *v4l2_ctrl_find(struct v4l2_ctrl_handler *hdl, u32 id) { struct v4l2_ctrl_ref *ref = find_ref_lock(hdl, id); return ref ? ref->ctrl : NULL; } EXPORT_SYMBOL(v4l2_ctrl_find); /* Allocate a new v4l2_ctrl_ref and hook it into the handler. */ int handler_new_ref(struct v4l2_ctrl_handler *hdl, struct v4l2_ctrl *ctrl, struct v4l2_ctrl_ref **ctrl_ref, bool from_other_dev, bool allocate_req) { struct v4l2_ctrl_ref *ref; struct v4l2_ctrl_ref *new_ref; u32 id = ctrl->id; u32 class_ctrl = V4L2_CTRL_ID2WHICH(id) | 1; int bucket = id % hdl->nr_of_buckets; /* which bucket to use */ unsigned int size_extra_req = 0; if (ctrl_ref) *ctrl_ref = NULL; /* * Automatically add the control class if it is not yet present and * the new control is not a compound control. */ if (ctrl->type < V4L2_CTRL_COMPOUND_TYPES && id != class_ctrl && find_ref_lock(hdl, class_ctrl) == NULL) if (!v4l2_ctrl_new_std(hdl, NULL, class_ctrl, 0, 0, 0, 0)) return hdl->error; if (hdl->error) return hdl->error; if (allocate_req && !ctrl->is_array) size_extra_req = ctrl->elems * ctrl->elem_size; new_ref = kzalloc(sizeof(*new_ref) + size_extra_req, GFP_KERNEL); if (!new_ref) return handler_set_err(hdl, -ENOMEM); new_ref->ctrl = ctrl; new_ref->from_other_dev = from_other_dev; if (size_extra_req) new_ref->p_req.p = &new_ref[1]; INIT_LIST_HEAD(&new_ref->node); mutex_lock(hdl->lock); /* Add immediately at the end of the list if the list is empty, or if the last element in the list has a lower ID. This ensures that when elements are added in ascending order the insertion is an O(1) operation. */ if (list_empty(&hdl->ctrl_refs) || id > node2id(hdl->ctrl_refs.prev)) { list_add_tail(&new_ref->node, &hdl->ctrl_refs); goto insert_in_hash; } /* Find insert position in sorted list */ list_for_each_entry(ref, &hdl->ctrl_refs, node) { if (ref->ctrl->id < id) continue; /* Don't add duplicates */ if (ref->ctrl->id == id) { kfree(new_ref); goto unlock; } list_add(&new_ref->node, ref->node.prev); break; } insert_in_hash: /* Insert the control node in the hash */ new_ref->next = hdl->buckets[bucket]; hdl->buckets[bucket] = new_ref; if (ctrl_ref) *ctrl_ref = new_ref; if (ctrl->handler == hdl) { /* By default each control starts in a cluster of its own. * new_ref->ctrl is basically a cluster array with one * element, so that's perfect to use as the cluster pointer. * But only do this for the handler that owns the control. */ ctrl->cluster = &new_ref->ctrl; ctrl->ncontrols = 1; } unlock: mutex_unlock(hdl->lock); return 0; } /* Add a new control */ static struct v4l2_ctrl *v4l2_ctrl_new(struct v4l2_ctrl_handler *hdl, const struct v4l2_ctrl_ops *ops, const struct v4l2_ctrl_type_ops *type_ops, u32 id, const char *name, enum v4l2_ctrl_type type, s64 min, s64 max, u64 step, s64 def, const u32 dims[V4L2_CTRL_MAX_DIMS], u32 elem_size, u32 flags, const char * const *qmenu, const s64 *qmenu_int, const union v4l2_ctrl_ptr p_def, const union v4l2_ctrl_ptr p_min, const union v4l2_ctrl_ptr p_max, void *priv) { struct v4l2_ctrl *ctrl; unsigned sz_extra; unsigned nr_of_dims = 0; unsigned elems = 1; bool is_array; unsigned tot_ctrl_size; void *data; int err; if (hdl->error) return NULL; while (dims && dims[nr_of_dims]) { elems *= dims[nr_of_dims]; nr_of_dims++; if (nr_of_dims == V4L2_CTRL_MAX_DIMS) break; } is_array = nr_of_dims > 0; /* Prefill elem_size for all types handled by std_type_ops */ switch ((u32)type) { case V4L2_CTRL_TYPE_INTEGER64: elem_size = sizeof(s64); break; case V4L2_CTRL_TYPE_STRING: elem_size = max + 1; break; case V4L2_CTRL_TYPE_U8: elem_size = sizeof(u8); break; case V4L2_CTRL_TYPE_U16: elem_size = sizeof(u16); break; case V4L2_CTRL_TYPE_U32: elem_size = sizeof(u32); break; case V4L2_CTRL_TYPE_MPEG2_SEQUENCE: elem_size = sizeof(struct v4l2_ctrl_mpeg2_sequence); break; case V4L2_CTRL_TYPE_MPEG2_PICTURE: elem_size = sizeof(struct v4l2_ctrl_mpeg2_picture); break; case V4L2_CTRL_TYPE_MPEG2_QUANTISATION: elem_size = sizeof(struct v4l2_ctrl_mpeg2_quantisation); break; case V4L2_CTRL_TYPE_FWHT_PARAMS: elem_size = sizeof(struct v4l2_ctrl_fwht_params); break; case V4L2_CTRL_TYPE_H264_SPS: elem_size = sizeof(struct v4l2_ctrl_h264_sps); break; case V4L2_CTRL_TYPE_H264_PPS: elem_size = sizeof(struct v4l2_ctrl_h264_pps); break; case V4L2_CTRL_TYPE_H264_SCALING_MATRIX: elem_size = sizeof(struct v4l2_ctrl_h264_scaling_matrix); break; case V4L2_CTRL_TYPE_H264_SLICE_PARAMS: elem_size = sizeof(struct v4l2_ctrl_h264_slice_params); break; case V4L2_CTRL_TYPE_H264_DECODE_PARAMS: elem_size = sizeof(struct v4l2_ctrl_h264_decode_params); break; case V4L2_CTRL_TYPE_H264_PRED_WEIGHTS: elem_size = sizeof(struct v4l2_ctrl_h264_pred_weights); break; case V4L2_CTRL_TYPE_VP8_FRAME: elem_size = sizeof(struct v4l2_ctrl_vp8_frame); break; case V4L2_CTRL_TYPE_HEVC_SPS: elem_size = sizeof(struct v4l2_ctrl_hevc_sps); break; case V4L2_CTRL_TYPE_HEVC_PPS: elem_size = sizeof(struct v4l2_ctrl_hevc_pps); break; case V4L2_CTRL_TYPE_HEVC_SLICE_PARAMS: elem_size = sizeof(struct v4l2_ctrl_hevc_slice_params); break; case V4L2_CTRL_TYPE_HEVC_SCALING_MATRIX: elem_size = sizeof(struct v4l2_ctrl_hevc_scaling_matrix); break; case V4L2_CTRL_TYPE_HEVC_DECODE_PARAMS: elem_size = sizeof(struct v4l2_ctrl_hevc_decode_params); break; case V4L2_CTRL_TYPE_HDR10_CLL_INFO: elem_size = sizeof(struct v4l2_ctrl_hdr10_cll_info); break; case V4L2_CTRL_TYPE_HDR10_MASTERING_DISPLAY: elem_size = sizeof(struct v4l2_ctrl_hdr10_mastering_display); break; case V4L2_CTRL_TYPE_VP9_COMPRESSED_HDR: elem_size = sizeof(struct v4l2_ctrl_vp9_compressed_hdr); break; case V4L2_CTRL_TYPE_VP9_FRAME: elem_size = sizeof(struct v4l2_ctrl_vp9_frame); break; case V4L2_CTRL_TYPE_AV1_SEQUENCE: elem_size = sizeof(struct v4l2_ctrl_av1_sequence); break; case V4L2_CTRL_TYPE_AV1_TILE_GROUP_ENTRY: elem_size = sizeof(struct v4l2_ctrl_av1_tile_group_entry); break; case V4L2_CTRL_TYPE_AV1_FRAME: elem_size = sizeof(struct v4l2_ctrl_av1_frame); break; case V4L2_CTRL_TYPE_AV1_FILM_GRAIN: elem_size = sizeof(struct v4l2_ctrl_av1_film_grain); break; case V4L2_CTRL_TYPE_AREA: elem_size = sizeof(struct v4l2_area); break; case V4L2_CTRL_TYPE_RECT: elem_size = sizeof(struct v4l2_rect); break; default: if (type < V4L2_CTRL_COMPOUND_TYPES) elem_size = sizeof(s32); break; } if (type < V4L2_CTRL_COMPOUND_TYPES && type != V4L2_CTRL_TYPE_BUTTON && type != V4L2_CTRL_TYPE_CTRL_CLASS && type != V4L2_CTRL_TYPE_STRING) flags |= V4L2_CTRL_FLAG_HAS_WHICH_MIN_MAX; /* Sanity checks */ if (id == 0 || name == NULL || !elem_size || id >= V4L2_CID_PRIVATE_BASE || (type == V4L2_CTRL_TYPE_MENU && qmenu == NULL) || (type == V4L2_CTRL_TYPE_INTEGER_MENU && qmenu_int == NULL)) { handler_set_err(hdl, -ERANGE); return NULL; } err = check_range(type, min, max, step, def); if (err) { handler_set_err(hdl, err); return NULL; } if (is_array && (type == V4L2_CTRL_TYPE_BUTTON || type == V4L2_CTRL_TYPE_CTRL_CLASS)) { handler_set_err(hdl, -EINVAL); return NULL; } if (flags & V4L2_CTRL_FLAG_DYNAMIC_ARRAY) { /* * For now only support this for one-dimensional arrays only. * * This can be relaxed in the future, but this will * require more effort. */ if (nr_of_dims != 1) { handler_set_err(hdl, -EINVAL); return NULL; } /* Start with just 1 element */ elems = 1; } tot_ctrl_size = elem_size * elems; sz_extra = 0; if (type == V4L2_CTRL_TYPE_BUTTON) flags |= V4L2_CTRL_FLAG_WRITE_ONLY | V4L2_CTRL_FLAG_EXECUTE_ON_WRITE; else if (type == V4L2_CTRL_TYPE_CTRL_CLASS) flags |= V4L2_CTRL_FLAG_READ_ONLY; else if (!is_array && (type == V4L2_CTRL_TYPE_INTEGER64 || type == V4L2_CTRL_TYPE_STRING || type >= V4L2_CTRL_COMPOUND_TYPES)) sz_extra += 2 * tot_ctrl_size; if (type >= V4L2_CTRL_COMPOUND_TYPES && p_def.p_const) sz_extra += elem_size; if (type >= V4L2_CTRL_COMPOUND_TYPES && p_min.p_const) sz_extra += elem_size; if (type >= V4L2_CTRL_COMPOUND_TYPES && p_max.p_const) sz_extra += elem_size; ctrl = kvzalloc(sizeof(*ctrl) + sz_extra, GFP_KERNEL); if (ctrl == NULL) { handler_set_err(hdl, -ENOMEM); return NULL; } INIT_LIST_HEAD(&ctrl->node); INIT_LIST_HEAD(&ctrl->ev_subs); ctrl->handler = hdl; ctrl->ops = ops; ctrl->type_ops = type_ops ? type_ops : &std_type_ops; ctrl->id = id; ctrl->name = name; ctrl->type = type; ctrl->flags = flags; ctrl->minimum = min; ctrl->maximum = max; ctrl->step = step; ctrl->default_value = def; ctrl->is_string = !is_array && type == V4L2_CTRL_TYPE_STRING; ctrl->is_ptr = is_array || type >= V4L2_CTRL_COMPOUND_TYPES || ctrl->is_string; ctrl->is_int = !ctrl->is_ptr && type != V4L2_CTRL_TYPE_INTEGER64; ctrl->is_array = is_array; ctrl->is_dyn_array = !!(flags & V4L2_CTRL_FLAG_DYNAMIC_ARRAY); ctrl->elems = elems; ctrl->new_elems = elems; ctrl->nr_of_dims = nr_of_dims; if (nr_of_dims) memcpy(ctrl->dims, dims, nr_of_dims * sizeof(dims[0])); ctrl->elem_size = elem_size; if (type == V4L2_CTRL_TYPE_MENU) ctrl->qmenu = qmenu; else if (type == V4L2_CTRL_TYPE_INTEGER_MENU) ctrl->qmenu_int = qmenu_int; ctrl->priv = priv; ctrl->cur.val = ctrl->val = def; data = &ctrl[1]; if (ctrl->is_array) { ctrl->p_array_alloc_elems = elems; ctrl->p_array = kvzalloc(2 * elems * elem_size, GFP_KERNEL); if (!ctrl->p_array) { kvfree(ctrl); return NULL; } data = ctrl->p_array; } if (!ctrl->is_int) { ctrl->p_new.p = data; ctrl->p_cur.p = data + tot_ctrl_size; } else { ctrl->p_new.p = &ctrl->val; ctrl->p_cur.p = &ctrl->cur.val; } if (type >= V4L2_CTRL_COMPOUND_TYPES && p_def.p_const) { if (ctrl->is_array) ctrl->p_def.p = &ctrl[1]; else ctrl->p_def.p = ctrl->p_cur.p + tot_ctrl_size; memcpy(ctrl->p_def.p, p_def.p_const, elem_size); } if (flags & V4L2_CTRL_FLAG_HAS_WHICH_MIN_MAX) { void *ptr = ctrl->p_def.p; if (p_min.p_const) { ptr += elem_size; ctrl->p_min.p = ptr; memcpy(ctrl->p_min.p, p_min.p_const, elem_size); } if (p_max.p_const) { ptr += elem_size; ctrl->p_max.p = ptr; memcpy(ctrl->p_max.p, p_max.p_const, elem_size); } } ctrl->type_ops->init(ctrl, 0, ctrl->p_cur); cur_to_new(ctrl); if (handler_new_ref(hdl, ctrl, NULL, false, false)) { kvfree(ctrl->p_array); kvfree(ctrl); return NULL; } mutex_lock(hdl->lock); list_add_tail(&ctrl->node, &hdl->ctrls); mutex_unlock(hdl->lock); return ctrl; } struct v4l2_ctrl *v4l2_ctrl_new_custom(struct v4l2_ctrl_handler *hdl, const struct v4l2_ctrl_config *cfg, void *priv) { bool is_menu; struct v4l2_ctrl *ctrl; const char *name = cfg->name; const char * const *qmenu = cfg->qmenu; const s64 *qmenu_int = cfg->qmenu_int; enum v4l2_ctrl_type type = cfg->type; u32 flags = cfg->flags; s64 min = cfg->min; s64 max = cfg->max; u64 step = cfg->step; s64 def = cfg->def; if (name == NULL) v4l2_ctrl_fill(cfg->id, &name, &type, &min, &max, &step, &def, &flags); is_menu = (type == V4L2_CTRL_TYPE_MENU || type == V4L2_CTRL_TYPE_INTEGER_MENU); if (is_menu) WARN_ON(step); else WARN_ON(cfg->menu_skip_mask); if (type == V4L2_CTRL_TYPE_MENU && !qmenu) { qmenu = v4l2_ctrl_get_menu(cfg->id); } else if (type == V4L2_CTRL_TYPE_INTEGER_MENU && !qmenu_int) { handler_set_err(hdl, -EINVAL); return NULL; } ctrl = v4l2_ctrl_new(hdl, cfg->ops, cfg->type_ops, cfg->id, name, type, min, max, is_menu ? cfg->menu_skip_mask : step, def, cfg->dims, cfg->elem_size, flags, qmenu, qmenu_int, cfg->p_def, cfg->p_min, cfg->p_max, priv); if (ctrl) ctrl->is_private = cfg->is_private; return ctrl; } EXPORT_SYMBOL(v4l2_ctrl_new_custom); /* Helper function for standard non-menu controls */ struct v4l2_ctrl *v4l2_ctrl_new_std(struct v4l2_ctrl_handler *hdl, const struct v4l2_ctrl_ops *ops, u32 id, s64 min, s64 max, u64 step, s64 def) { const char *name; enum v4l2_ctrl_type type; u32 flags; v4l2_ctrl_fill(id, &name, &type, &min, &max, &step, &def, &flags); if (type == V4L2_CTRL_TYPE_MENU || type == V4L2_CTRL_TYPE_INTEGER_MENU || type >= V4L2_CTRL_COMPOUND_TYPES) { handler_set_err(hdl, -EINVAL); return NULL; } return v4l2_ctrl_new(hdl, ops, NULL, id, name, type, min, max, step, def, NULL, 0, flags, NULL, NULL, ptr_null, ptr_null, ptr_null, NULL); } EXPORT_SYMBOL(v4l2_ctrl_new_std); /* Helper function for standard menu controls */ struct v4l2_ctrl *v4l2_ctrl_new_std_menu(struct v4l2_ctrl_handler *hdl, const struct v4l2_ctrl_ops *ops, u32 id, u8 _max, u64 mask, u8 _def) { const char * const *qmenu = NULL; const s64 *qmenu_int = NULL; unsigned int qmenu_int_len = 0; const char *name; enum v4l2_ctrl_type type; s64 min; s64 max = _max; s64 def = _def; u64 step; u32 flags; v4l2_ctrl_fill(id, &name, &type, &min, &max, &step, &def, &flags); if (type == V4L2_CTRL_TYPE_MENU) qmenu = v4l2_ctrl_get_menu(id); else if (type == V4L2_CTRL_TYPE_INTEGER_MENU) qmenu_int = v4l2_ctrl_get_int_menu(id, &qmenu_int_len); if ((!qmenu && !qmenu_int) || (qmenu_int && max >= qmenu_int_len)) { handler_set_err(hdl, -EINVAL); return NULL; } return v4l2_ctrl_new(hdl, ops, NULL, id, name, type, 0, max, mask, def, NULL, 0, flags, qmenu, qmenu_int, ptr_null, ptr_null, ptr_null, NULL); } EXPORT_SYMBOL(v4l2_ctrl_new_std_menu); /* Helper function for standard menu controls with driver defined menu */ struct v4l2_ctrl *v4l2_ctrl_new_std_menu_items(struct v4l2_ctrl_handler *hdl, const struct v4l2_ctrl_ops *ops, u32 id, u8 _max, u64 mask, u8 _def, const char * const *qmenu) { enum v4l2_ctrl_type type; const char *name; u32 flags; u64 step; s64 min; s64 max = _max; s64 def = _def; /* v4l2_ctrl_new_std_menu_items() should only be called for * standard controls without a standard menu. */ if (v4l2_ctrl_get_menu(id)) { handler_set_err(hdl, -EINVAL); return NULL; } v4l2_ctrl_fill(id, &name, &type, &min, &max, &step, &def, &flags); if (type != V4L2_CTRL_TYPE_MENU || qmenu == NULL) { handler_set_err(hdl, -EINVAL); return NULL; } return v4l2_ctrl_new(hdl, ops, NULL, id, name, type, 0, max, mask, def, NULL, 0, flags, qmenu, NULL, ptr_null, ptr_null, ptr_null, NULL); } EXPORT_SYMBOL(v4l2_ctrl_new_std_menu_items); /* Helper function for standard compound controls */ struct v4l2_ctrl *v4l2_ctrl_new_std_compound(struct v4l2_ctrl_handler *hdl, const struct v4l2_ctrl_ops *ops, u32 id, const union v4l2_ctrl_ptr p_def, const union v4l2_ctrl_ptr p_min, const union v4l2_ctrl_ptr p_max) { const char *name; enum v4l2_ctrl_type type; u32 flags; s64 min, max, step, def; v4l2_ctrl_fill(id, &name, &type, &min, &max, &step, &def, &flags); if (type < V4L2_CTRL_COMPOUND_TYPES) { handler_set_err(hdl, -EINVAL); return NULL; } return v4l2_ctrl_new(hdl, ops, NULL, id, name, type, min, max, step, def, NULL, 0, flags, NULL, NULL, p_def, p_min, p_max, NULL); } EXPORT_SYMBOL(v4l2_ctrl_new_std_compound); /* Helper function for standard integer menu controls */ struct v4l2_ctrl *v4l2_ctrl_new_int_menu(struct v4l2_ctrl_handler *hdl, const struct v4l2_ctrl_ops *ops, u32 id, u8 _max, u8 _def, const s64 *qmenu_int) { const char *name; enum v4l2_ctrl_type type; s64 min; u64 step; s64 max = _max; s64 def = _def; u32 flags; v4l2_ctrl_fill(id, &name, &type, &min, &max, &step, &def, &flags); if (type != V4L2_CTRL_TYPE_INTEGER_MENU) { handler_set_err(hdl, -EINVAL); return NULL; } return v4l2_ctrl_new(hdl, ops, NULL, id, name, type, 0, max, 0, def, NULL, 0, flags, NULL, qmenu_int, ptr_null, ptr_null, ptr_null, NULL); } EXPORT_SYMBOL(v4l2_ctrl_new_int_menu); /* Add the controls from another handler to our own. */ int v4l2_ctrl_add_handler(struct v4l2_ctrl_handler *hdl, struct v4l2_ctrl_handler *add, bool (*filter)(const struct v4l2_ctrl *ctrl), bool from_other_dev) { struct v4l2_ctrl_ref *ref; int ret = 0; /* Do nothing if either handler is NULL or if they are the same */ if (!hdl || !add || hdl == add) return 0; if (hdl->error) return hdl->error; mutex_lock(add->lock); list_for_each_entry(ref, &add->ctrl_refs, node) { struct v4l2_ctrl *ctrl = ref->ctrl; /* Skip handler-private controls. */ if (ctrl->is_private) continue; /* And control classes */ if (ctrl->type == V4L2_CTRL_TYPE_CTRL_CLASS) continue; /* Filter any unwanted controls */ if (filter && !filter(ctrl)) continue; ret = handler_new_ref(hdl, ctrl, NULL, from_other_dev, false); if (ret) break; } mutex_unlock(add->lock); return ret; } EXPORT_SYMBOL(v4l2_ctrl_add_handler); bool v4l2_ctrl_radio_filter(const struct v4l2_ctrl *ctrl) { if (V4L2_CTRL_ID2WHICH(ctrl->id) == V4L2_CTRL_CLASS_FM_TX) return true; if (V4L2_CTRL_ID2WHICH(ctrl->id) == V4L2_CTRL_CLASS_FM_RX) return true; switch (ctrl->id) { case V4L2_CID_AUDIO_MUTE: case V4L2_CID_AUDIO_VOLUME: case V4L2_CID_AUDIO_BALANCE: case V4L2_CID_AUDIO_BASS: case V4L2_CID_AUDIO_TREBLE: case V4L2_CID_AUDIO_LOUDNESS: return true; default: break; } return false; } EXPORT_SYMBOL(v4l2_ctrl_radio_filter); /* Cluster controls */ void v4l2_ctrl_cluster(unsigned ncontrols, struct v4l2_ctrl **controls) { bool has_volatiles = false; int i; /* The first control is the master control and it must not be NULL */ if (WARN_ON(ncontrols == 0 || controls[0] == NULL)) return; for (i = 0; i < ncontrols; i++) { if (controls[i]) { controls[i]->cluster = controls; controls[i]->ncontrols = ncontrols; if (controls[i]->flags & V4L2_CTRL_FLAG_VOLATILE) has_volatiles = true; } } controls[0]->has_volatiles = has_volatiles; } EXPORT_SYMBOL(v4l2_ctrl_cluster); void v4l2_ctrl_auto_cluster(unsigned ncontrols, struct v4l2_ctrl **controls, u8 manual_val, bool set_volatile) { struct v4l2_ctrl *master = controls[0]; u32 flag = 0; int i; v4l2_ctrl_cluster(ncontrols, controls); WARN_ON(ncontrols <= 1); WARN_ON(manual_val < master->minimum || manual_val > master->maximum); WARN_ON(set_volatile && !has_op(master, g_volatile_ctrl)); master->is_auto = true; master->has_volatiles = set_volatile; master->manual_mode_value = manual_val; master->flags |= V4L2_CTRL_FLAG_UPDATE; if (!is_cur_manual(master)) flag = V4L2_CTRL_FLAG_INACTIVE | (set_volatile ? V4L2_CTRL_FLAG_VOLATILE : 0); for (i = 1; i < ncontrols; i++) if (controls[i]) controls[i]->flags |= flag; } EXPORT_SYMBOL(v4l2_ctrl_auto_cluster); /* * Obtain the current volatile values of an autocluster and mark them * as new. */ void update_from_auto_cluster(struct v4l2_ctrl *master) { int i; for (i = 1; i < master->ncontrols; i++) cur_to_new(master->cluster[i]); if (!call_op(master, g_volatile_ctrl)) for (i = 1; i < master->ncontrols; i++) if (master->cluster[i]) master->cluster[i]->is_new = 1; } /* * Return non-zero if one or more of the controls in the cluster has a new * value that differs from the current value. */ static int cluster_changed(struct v4l2_ctrl *master) { bool changed = false; int i; for (i = 0; i < master->ncontrols; i++) { struct v4l2_ctrl *ctrl = master->cluster[i]; bool ctrl_changed = false; if (!ctrl) continue; if (ctrl->flags & V4L2_CTRL_FLAG_EXECUTE_ON_WRITE) { changed = true; ctrl_changed = true; } /* * Set has_changed to false to avoid generating * the event V4L2_EVENT_CTRL_CH_VALUE */ if (ctrl->flags & V4L2_CTRL_FLAG_VOLATILE) { ctrl->has_changed = false; continue; } if (ctrl->elems != ctrl->new_elems) ctrl_changed = true; if (!ctrl_changed) ctrl_changed = !ctrl->type_ops->equal(ctrl, ctrl->p_cur, ctrl->p_new); ctrl->has_changed = ctrl_changed; changed |= ctrl->has_changed; } return changed; } /* * Core function that calls try/s_ctrl and ensures that the new value is * copied to the current value on a set. * Must be called with ctrl->handler->lock held. */ int try_or_set_cluster(struct v4l2_fh *fh, struct v4l2_ctrl *master, bool set, u32 ch_flags) { bool update_flag; int ret; int i; /* * Go through the cluster and either validate the new value or * (if no new value was set), copy the current value to the new * value, ensuring a consistent view for the control ops when * called. */ for (i = 0; i < master->ncontrols; i++) { struct v4l2_ctrl *ctrl = master->cluster[i]; if (!ctrl) continue; if (!ctrl->is_new) { cur_to_new(ctrl); continue; } /* * Check again: it may have changed since the * previous check in try_or_set_ext_ctrls(). */ if (set && (ctrl->flags & V4L2_CTRL_FLAG_GRABBED)) return -EBUSY; } ret = call_op(master, try_ctrl); /* Don't set if there is no change */ if (ret || !set || !cluster_changed(master)) return ret; ret = call_op(master, s_ctrl); if (ret) return ret; /* If OK, then make the new values permanent. */ update_flag = is_cur_manual(master) != is_new_manual(master); for (i = 0; i < master->ncontrols; i++) { /* * If we switch from auto to manual mode, and this cluster * contains volatile controls, then all non-master controls * have to be marked as changed. The 'new' value contains * the volatile value (obtained by update_from_auto_cluster), * which now has to become the current value. */ if (i && update_flag && is_new_manual(master) && master->has_volatiles && master->cluster[i]) master->cluster[i]->has_changed = true; new_to_cur(fh, master->cluster[i], ch_flags | ((update_flag && i > 0) ? V4L2_EVENT_CTRL_CH_FLAGS : 0)); } return 0; } /* Activate/deactivate a control. */ void v4l2_ctrl_activate(struct v4l2_ctrl *ctrl, bool active) { /* invert since the actual flag is called 'inactive' */ bool inactive = !active; bool old; if (ctrl == NULL) return; if (inactive) /* set V4L2_CTRL_FLAG_INACTIVE */ old = test_and_set_bit(4, &ctrl->flags); else /* clear V4L2_CTRL_FLAG_INACTIVE */ old = test_and_clear_bit(4, &ctrl->flags); if (old != inactive) send_event(NULL, ctrl, V4L2_EVENT_CTRL_CH_FLAGS); } EXPORT_SYMBOL(v4l2_ctrl_activate); void __v4l2_ctrl_grab(struct v4l2_ctrl *ctrl, bool grabbed) { bool old; if (ctrl == NULL) return; lockdep_assert_held(ctrl->handler->lock); if (grabbed) /* set V4L2_CTRL_FLAG_GRABBED */ old = test_and_set_bit(1, &ctrl->flags); else /* clear V4L2_CTRL_FLAG_GRABBED */ old = test_and_clear_bit(1, &ctrl->flags); if (old != grabbed) send_event(NULL, ctrl, V4L2_EVENT_CTRL_CH_FLAGS); } EXPORT_SYMBOL(__v4l2_ctrl_grab); /* Call s_ctrl for all controls owned by the handler */ int __v4l2_ctrl_handler_setup(struct v4l2_ctrl_handler *hdl) { struct v4l2_ctrl *ctrl; int ret = 0; if (hdl == NULL) return 0; lockdep_assert_held(hdl->lock); list_for_each_entry(ctrl, &hdl->ctrls, node) ctrl->done = false; list_for_each_entry(ctrl, &hdl->ctrls, node) { struct v4l2_ctrl *master = ctrl->cluster[0]; int i; /* Skip if this control was already handled by a cluster. */ /* Skip button controls and read-only controls. */ if (ctrl->done || ctrl->type == V4L2_CTRL_TYPE_BUTTON || (ctrl->flags & V4L2_CTRL_FLAG_READ_ONLY)) continue; for (i = 0; i < master->ncontrols; i++) { if (master->cluster[i]) { cur_to_new(master->cluster[i]); master->cluster[i]->is_new = 1; master->cluster[i]->done = true; } } ret = call_op(master, s_ctrl); if (ret) break; } return ret; } EXPORT_SYMBOL_GPL(__v4l2_ctrl_handler_setup); int v4l2_ctrl_handler_setup(struct v4l2_ctrl_handler *hdl) { int ret; if (hdl == NULL) return 0; mutex_lock(hdl->lock); ret = __v4l2_ctrl_handler_setup(hdl); mutex_unlock(hdl->lock); return ret; } EXPORT_SYMBOL(v4l2_ctrl_handler_setup); /* Log the control name and value */ static void log_ctrl(const struct v4l2_ctrl *ctrl, const char *prefix, const char *colon) { if (ctrl->flags & (V4L2_CTRL_FLAG_DISABLED | V4L2_CTRL_FLAG_WRITE_ONLY)) return; if (ctrl->type == V4L2_CTRL_TYPE_CTRL_CLASS) return; pr_info("%s%s%s: ", prefix, colon, ctrl->name); ctrl->type_ops->log(ctrl); if (ctrl->flags & (V4L2_CTRL_FLAG_INACTIVE | V4L2_CTRL_FLAG_GRABBED | V4L2_CTRL_FLAG_VOLATILE)) { if (ctrl->flags & V4L2_CTRL_FLAG_INACTIVE) pr_cont(" inactive"); if (ctrl->flags & V4L2_CTRL_FLAG_GRABBED) pr_cont(" grabbed"); if (ctrl->flags & V4L2_CTRL_FLAG_VOLATILE) pr_cont(" volatile"); } pr_cont("\n"); } /* Log all controls owned by the handler */ void v4l2_ctrl_handler_log_status(struct v4l2_ctrl_handler *hdl, const char *prefix) { struct v4l2_ctrl *ctrl; const char *colon = ""; int len; if (!hdl) return; if (!prefix) prefix = ""; len = strlen(prefix); if (len && prefix[len - 1] != ' ') colon = ": "; mutex_lock(hdl->lock); list_for_each_entry(ctrl, &hdl->ctrls, node) if (!(ctrl->flags & V4L2_CTRL_FLAG_DISABLED)) log_ctrl(ctrl, prefix, colon); mutex_unlock(hdl->lock); } EXPORT_SYMBOL(v4l2_ctrl_handler_log_status); int v4l2_ctrl_new_fwnode_properties(struct v4l2_ctrl_handler *hdl, const struct v4l2_ctrl_ops *ctrl_ops, const struct v4l2_fwnode_device_properties *p) { if (hdl->error) return hdl->error; if (p->orientation != V4L2_FWNODE_PROPERTY_UNSET) { u32 orientation_ctrl; switch (p->orientation) { case V4L2_FWNODE_ORIENTATION_FRONT: orientation_ctrl = V4L2_CAMERA_ORIENTATION_FRONT; break; case V4L2_FWNODE_ORIENTATION_BACK: orientation_ctrl = V4L2_CAMERA_ORIENTATION_BACK; break; case V4L2_FWNODE_ORIENTATION_EXTERNAL: orientation_ctrl = V4L2_CAMERA_ORIENTATION_EXTERNAL; break; default: return -EINVAL; } if (!v4l2_ctrl_new_std_menu(hdl, ctrl_ops, V4L2_CID_CAMERA_ORIENTATION, V4L2_CAMERA_ORIENTATION_EXTERNAL, 0, orientation_ctrl)) return hdl->error; } if (p->rotation != V4L2_FWNODE_PROPERTY_UNSET) { if (!v4l2_ctrl_new_std(hdl, ctrl_ops, V4L2_CID_CAMERA_SENSOR_ROTATION, p->rotation, p->rotation, 1, p->rotation)) return hdl->error; } return hdl->error; } EXPORT_SYMBOL(v4l2_ctrl_new_fwnode_properties); |
| 98 97 35 17 17 188 187 189 188 19 96 97 20 20 20 20 57 45 1246 1254 1254 18 18 18 1332 1333 1329 109 108 97 98 108 106 84 84 19 1 56 57 57 57 57 20 20 20 57 57 44 10 34 1 19 17 17 101 100 101 76 76 77 5 5 19 7 6 3082 3074 1 20 20 20 20 5 19 13 7 19 47 47 47 2 47 47 18 5 19 19 19 19 19 19 19 19 19 19 1570 1573 1556 1560 1549 8 1560 117 488 1322 4 1318 83 1238 185 187 93 97 4 1145 57 57 57 57 19 19 19 57 56 54 1 56 74 37 57 57 28 29 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/fs-writeback.c * * Copyright (C) 2002, Linus Torvalds. * * Contains all the functions related to writing back and waiting * upon dirty inodes against superblocks, and writing back dirty * pages against inodes. ie: data writeback. Writeout of the * inode itself is not handled here. * * 10Apr2002 Andrew Morton * Split out of fs/inode.c * Additions for address_space-based writeback */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/kthread.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/tracepoint.h> #include <linux/device.h> #include <linux/memcontrol.h> #include "internal.h" /* * 4MB minimal write chunk size */ #define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) /* * Passed into wb_writeback(), essentially a subset of writeback_control */ struct wb_writeback_work { long nr_pages; struct super_block *sb; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ unsigned int auto_free:1; /* free on completion */ enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ struct wb_completion *done; /* set if the caller waits */ }; /* * If an inode is constantly having its pages dirtied, but then the * updates stop dirtytime_expire_interval seconds in the past, it's * possible for the worst case time between when an inode has its * timestamps updated and when they finally get written out to be two * dirtytime_expire_intervals. We set the default to 12 hours (in * seconds), which means most of the time inodes will have their * timestamps written to disk after 12 hours, but in the worst case a * few inodes might not their timestamps updated for 24 hours. */ static unsigned int dirtytime_expire_interval = 12 * 60 * 60; static inline struct inode *wb_inode(struct list_head *head) { return list_entry(head, struct inode, i_io_list); } /* * Include the creation of the trace points after defining the * wb_writeback_work structure and inline functions so that the definition * remains local to this file. */ #define CREATE_TRACE_POINTS #include <trace/events/writeback.h> EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage); static bool wb_io_lists_populated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb)) { return false; } else { set_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(!wb->avg_write_bandwidth); atomic_long_add(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth); return true; } } static void wb_io_lists_depopulated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) && list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) { clear_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth) < 0); } } /** * inode_io_list_move_locked - move an inode onto a bdi_writeback IO list * @inode: inode to be moved * @wb: target bdi_writeback * @head: one of @wb->b_{dirty|io|more_io|dirty_time} * * Move @inode->i_io_list to @list of @wb and set %WB_has_dirty_io. * Returns %true if @inode is the first occupant of the !dirty_time IO * lists; otherwise, %false. */ static bool inode_io_list_move_locked(struct inode *inode, struct bdi_writeback *wb, struct list_head *head) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); WARN_ON_ONCE(inode->i_state & I_FREEING); list_move(&inode->i_io_list, head); /* dirty_time doesn't count as dirty_io until expiration */ if (head != &wb->b_dirty_time) return wb_io_lists_populated(wb); wb_io_lists_depopulated(wb); return false; } static void wb_wakeup(struct bdi_writeback *wb) { spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) mod_delayed_work(bdi_wq, &wb->dwork, 0); spin_unlock_irq(&wb->work_lock); } /* * This function is used when the first inode for this wb is marked dirty. It * wakes-up the corresponding bdi thread which should then take care of the * periodic background write-out of dirty inodes. Since the write-out would * starts only 'dirty_writeback_interval' centisecs from now anyway, we just * set up a timer which wakes the bdi thread up later. * * Note, we wouldn't bother setting up the timer, but this function is on the * fast-path (used by '__mark_inode_dirty()'), so we save few context switches * by delaying the wake-up. * * We have to be careful not to postpone flush work if it is scheduled for * earlier. Thus we use queue_delayed_work(). */ static void wb_wakeup_delayed(struct bdi_writeback *wb) { unsigned long timeout; timeout = msecs_to_jiffies(dirty_writeback_interval * 10); spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) queue_delayed_work(bdi_wq, &wb->dwork, timeout); spin_unlock_irq(&wb->work_lock); } static void finish_writeback_work(struct wb_writeback_work *work) { struct wb_completion *done = work->done; if (work->auto_free) kfree(work); if (done) { wait_queue_head_t *waitq = done->waitq; /* @done can't be accessed after the following dec */ if (atomic_dec_and_test(&done->cnt)) wake_up_all(waitq); } } static void wb_queue_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { trace_writeback_queue(wb, work); if (work->done) atomic_inc(&work->done->cnt); spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) { list_add_tail(&work->list, &wb->work_list); mod_delayed_work(bdi_wq, &wb->dwork, 0); } else finish_writeback_work(work); spin_unlock_irq(&wb->work_lock); } /** * wb_wait_for_completion - wait for completion of bdi_writeback_works * @done: target wb_completion * * Wait for one or more work items issued to @bdi with their ->done field * set to @done, which should have been initialized with * DEFINE_WB_COMPLETION(). This function returns after all such work items * are completed. Work items which are waited upon aren't freed * automatically on completion. */ void wb_wait_for_completion(struct wb_completion *done) { atomic_dec(&done->cnt); /* put down the initial count */ wait_event(*done->waitq, !atomic_read(&done->cnt)); } #ifdef CONFIG_CGROUP_WRITEBACK /* * Parameters for foreign inode detection, see wbc_detach_inode() to see * how they're used. * * These paramters are inherently heuristical as the detection target * itself is fuzzy. All we want to do is detaching an inode from the * current owner if it's being written to by some other cgroups too much. * * The current cgroup writeback is built on the assumption that multiple * cgroups writing to the same inode concurrently is very rare and a mode * of operation which isn't well supported. As such, the goal is not * taking too long when a different cgroup takes over an inode while * avoiding too aggressive flip-flops from occasional foreign writes. * * We record, very roughly, 2s worth of IO time history and if more than * half of that is foreign, trigger the switch. The recording is quantized * to 16 slots. To avoid tiny writes from swinging the decision too much, * writes smaller than 1/8 of avg size are ignored. */ #define WB_FRN_TIME_SHIFT 13 /* 1s = 2^13, upto 8 secs w/ 16bit */ #define WB_FRN_TIME_AVG_SHIFT 3 /* avg = avg * 7/8 + new * 1/8 */ #define WB_FRN_TIME_CUT_DIV 8 /* ignore rounds < avg / 8 */ #define WB_FRN_TIME_PERIOD (2 * (1 << WB_FRN_TIME_SHIFT)) /* 2s */ #define WB_FRN_HIST_SLOTS 16 /* inode->i_wb_frn_history is 16bit */ #define WB_FRN_HIST_UNIT (WB_FRN_TIME_PERIOD / WB_FRN_HIST_SLOTS) /* each slot's duration is 2s / 16 */ #define WB_FRN_HIST_THR_SLOTS (WB_FRN_HIST_SLOTS / 2) /* if foreign slots >= 8, switch */ #define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) /* one round can affect upto 5 slots */ #define WB_FRN_MAX_IN_FLIGHT 1024 /* don't queue too many concurrently */ /* * Maximum inodes per isw. A specific value has been chosen to make * struct inode_switch_wbs_context fit into 1024 bytes kmalloc. */ #define WB_MAX_INODES_PER_ISW ((1024UL - sizeof(struct inode_switch_wbs_context)) \ / sizeof(struct inode *)) static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); static struct workqueue_struct *isw_wq; void __inode_attach_wb(struct inode *inode, struct folio *folio) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; if (inode_cgwb_enabled(inode)) { struct cgroup_subsys_state *memcg_css; if (folio) { memcg_css = mem_cgroup_css_from_folio(folio); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); } else { /* must pin memcg_css, see wb_get_create() */ memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); } } if (!wb) wb = &bdi->wb; /* * There may be multiple instances of this function racing to * update the same inode. Use cmpxchg() to tell the winner. */ if (unlikely(cmpxchg(&inode->i_wb, NULL, wb))) wb_put(wb); } /** * inode_cgwb_move_to_attached - put the inode onto wb->b_attached list * @inode: inode of interest with i_lock held * @wb: target bdi_writeback * * Remove the inode from wb's io lists and if necessarily put onto b_attached * list. Only inodes attached to cgwb's are kept on this list. */ static void inode_cgwb_move_to_attached(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); WARN_ON_ONCE(inode->i_state & I_FREEING); inode->i_state &= ~I_SYNC_QUEUED; if (wb != &wb->bdi->wb) list_move(&inode->i_io_list, &wb->b_attached); else list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } /** * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it * @inode: inode of interest with i_lock held * * Returns @inode's wb with its list_lock held. @inode->i_lock must be * held on entry and is released on return. The returned wb is guaranteed * to stay @inode's associated wb until its list_lock is released. */ static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { while (true) { struct bdi_writeback *wb = inode_to_wb(inode); /* * inode_to_wb() association is protected by both * @inode->i_lock and @wb->list_lock but list_lock nests * outside i_lock. Drop i_lock and verify that the * association hasn't changed after acquiring list_lock. */ wb_get(wb); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); /* i_wb may have changed inbetween, can't use inode_to_wb() */ if (likely(wb == inode->i_wb)) { wb_put(wb); /* @inode already has ref */ return wb; } spin_unlock(&wb->list_lock); wb_put(wb); cpu_relax(); spin_lock(&inode->i_lock); } } /** * inode_to_wb_and_lock_list - determine an inode's wb and lock it * @inode: inode of interest * * Same as locked_inode_to_wb_and_lock_list() but @inode->i_lock isn't held * on entry. */ static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { spin_lock(&inode->i_lock); return locked_inode_to_wb_and_lock_list(inode); } struct inode_switch_wbs_context { struct rcu_work work; /* * Multiple inodes can be switched at once. The switching procedure * consists of two parts, separated by a RCU grace period. To make * sure that the second part is executed for each inode gone through * the first part, all inode pointers are placed into a NULL-terminated * array embedded into struct inode_switch_wbs_context. Otherwise * an inode could be left in a non-consistent state. */ struct bdi_writeback *new_wb; struct inode *inodes[]; }; static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { down_write(&bdi->wb_switch_rwsem); } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { up_write(&bdi->wb_switch_rwsem); } static bool inode_do_switch_wbs(struct inode *inode, struct bdi_writeback *old_wb, struct bdi_writeback *new_wb) { struct address_space *mapping = inode->i_mapping; XA_STATE(xas, &mapping->i_pages, 0); struct folio *folio; bool switched = false; spin_lock(&inode->i_lock); xa_lock_irq(&mapping->i_pages); /* * Once I_FREEING or I_WILL_FREE are visible under i_lock, the eviction * path owns the inode and we shouldn't modify ->i_io_list. */ if (unlikely(inode->i_state & (I_FREEING | I_WILL_FREE))) goto skip_switch; trace_inode_switch_wbs(inode, old_wb, new_wb); /* * Count and transfer stats. Note that PAGECACHE_TAG_DIRTY points * to possibly dirty folios while PAGECACHE_TAG_WRITEBACK points to * folios actually under writeback. */ xas_for_each_marked(&xas, folio, ULONG_MAX, PAGECACHE_TAG_DIRTY) { if (folio_test_dirty(folio)) { long nr = folio_nr_pages(folio); wb_stat_mod(old_wb, WB_RECLAIMABLE, -nr); wb_stat_mod(new_wb, WB_RECLAIMABLE, nr); } } xas_set(&xas, 0); xas_for_each_marked(&xas, folio, ULONG_MAX, PAGECACHE_TAG_WRITEBACK) { long nr = folio_nr_pages(folio); WARN_ON_ONCE(!folio_test_writeback(folio)); wb_stat_mod(old_wb, WB_WRITEBACK, -nr); wb_stat_mod(new_wb, WB_WRITEBACK, nr); } if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) { atomic_dec(&old_wb->writeback_inodes); atomic_inc(&new_wb->writeback_inodes); } wb_get(new_wb); /* * Transfer to @new_wb's IO list if necessary. If the @inode is dirty, * the specific list @inode was on is ignored and the @inode is put on * ->b_dirty which is always correct including from ->b_dirty_time. * The transfer preserves @inode->dirtied_when ordering. If the @inode * was clean, it means it was on the b_attached list, so move it onto * the b_attached list of @new_wb. */ if (!list_empty(&inode->i_io_list)) { inode->i_wb = new_wb; if (inode->i_state & I_DIRTY_ALL) { struct inode *pos; list_for_each_entry(pos, &new_wb->b_dirty, i_io_list) if (time_after_eq(inode->dirtied_when, pos->dirtied_when)) break; inode_io_list_move_locked(inode, new_wb, pos->i_io_list.prev); } else { inode_cgwb_move_to_attached(inode, new_wb); } } else { inode->i_wb = new_wb; } /* ->i_wb_frn updates may race wbc_detach_inode() but doesn't matter */ inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; switched = true; skip_switch: /* * Paired with load_acquire in unlocked_inode_to_wb_begin() and * ensures that the new wb is visible if they see !I_WB_SWITCH. */ smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH); xa_unlock_irq(&mapping->i_pages); spin_unlock(&inode->i_lock); return switched; } static void inode_switch_wbs_work_fn(struct work_struct *work) { struct inode_switch_wbs_context *isw = container_of(to_rcu_work(work), struct inode_switch_wbs_context, work); struct backing_dev_info *bdi = inode_to_bdi(isw->inodes[0]); struct bdi_writeback *old_wb = isw->inodes[0]->i_wb; struct bdi_writeback *new_wb = isw->new_wb; unsigned long nr_switched = 0; struct inode **inodep; /* * If @inode switches cgwb membership while sync_inodes_sb() is * being issued, sync_inodes_sb() might miss it. Synchronize. */ down_read(&bdi->wb_switch_rwsem); /* * By the time control reaches here, RCU grace period has passed * since I_WB_SWITCH assertion and all wb stat update transactions * between unlocked_inode_to_wb_begin/end() are guaranteed to be * synchronizing against the i_pages lock. * * Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock * gives us exclusion against all wb related operations on @inode * including IO list manipulations and stat updates. */ if (old_wb < new_wb) { spin_lock(&old_wb->list_lock); spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING); } else { spin_lock(&new_wb->list_lock); spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); } for (inodep = isw->inodes; *inodep; inodep++) { WARN_ON_ONCE((*inodep)->i_wb != old_wb); if (inode_do_switch_wbs(*inodep, old_wb, new_wb)) nr_switched++; } spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); up_read(&bdi->wb_switch_rwsem); if (nr_switched) { wb_wakeup(new_wb); wb_put_many(old_wb, nr_switched); } for (inodep = isw->inodes; *inodep; inodep++) iput(*inodep); wb_put(new_wb); kfree(isw); atomic_dec(&isw_nr_in_flight); } static bool inode_prepare_wbs_switch(struct inode *inode, struct bdi_writeback *new_wb) { /* * Paired with smp_mb() in cgroup_writeback_umount(). * isw_nr_in_flight must be increased before checking SB_ACTIVE and * grabbing an inode, otherwise isw_nr_in_flight can be observed as 0 * in cgroup_writeback_umount() and the isw_wq will be not flushed. */ smp_mb(); if (IS_DAX(inode)) return false; /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); if (!(inode->i_sb->s_flags & SB_ACTIVE) || inode->i_state & (I_WB_SWITCH | I_FREEING | I_WILL_FREE) || inode_to_wb(inode) == new_wb) { spin_unlock(&inode->i_lock); return false; } inode->i_state |= I_WB_SWITCH; __iget(inode); spin_unlock(&inode->i_lock); return true; } /** * inode_switch_wbs - change the wb association of an inode * @inode: target inode * @new_wb_id: ID of the new wb * * Switch @inode's wb association to the wb identified by @new_wb_id. The * switching is performed asynchronously and may fail silently. */ static void inode_switch_wbs(struct inode *inode, int new_wb_id) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; /* noop if seems to be already in progress */ if (inode->i_state & I_WB_SWITCH) return; /* avoid queueing a new switch if too many are already in flight */ if (atomic_read(&isw_nr_in_flight) > WB_FRN_MAX_IN_FLIGHT) return; isw = kzalloc(struct_size(isw, inodes, 2), GFP_ATOMIC); if (!isw) return; atomic_inc(&isw_nr_in_flight); /* find and pin the new wb */ rcu_read_lock(); memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) goto out_free; isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); if (!isw->new_wb) goto out_free; if (!inode_prepare_wbs_switch(inode, isw->new_wb)) goto out_free; isw->inodes[0] = inode; /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn); queue_rcu_work(isw_wq, &isw->work); return; out_free: atomic_dec(&isw_nr_in_flight); if (isw->new_wb) wb_put(isw->new_wb); kfree(isw); } static bool isw_prepare_wbs_switch(struct inode_switch_wbs_context *isw, struct list_head *list, int *nr) { struct inode *inode; list_for_each_entry(inode, list, i_io_list) { if (!inode_prepare_wbs_switch(inode, isw->new_wb)) continue; isw->inodes[*nr] = inode; (*nr)++; if (*nr >= WB_MAX_INODES_PER_ISW - 1) return true; } return false; } /** * cleanup_offline_cgwb - detach associated inodes * @wb: target wb * * Switch all inodes attached to @wb to a nearest living ancestor's wb in order * to eventually release the dying @wb. Returns %true if not all inodes were * switched and the function has to be restarted. */ bool cleanup_offline_cgwb(struct bdi_writeback *wb) { struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; int nr; bool restart = false; isw = kzalloc(struct_size(isw, inodes, WB_MAX_INODES_PER_ISW), GFP_KERNEL); if (!isw) return restart; atomic_inc(&isw_nr_in_flight); for (memcg_css = wb->memcg_css->parent; memcg_css; memcg_css = memcg_css->parent) { isw->new_wb = wb_get_create(wb->bdi, memcg_css, GFP_KERNEL); if (isw->new_wb) break; } if (unlikely(!isw->new_wb)) isw->new_wb = &wb->bdi->wb; /* wb_get() is noop for bdi's wb */ nr = 0; spin_lock(&wb->list_lock); /* * In addition to the inodes that have completed writeback, also switch * cgwbs for those inodes only with dirty timestamps. Otherwise, those * inodes won't be written back for a long time when lazytime is * enabled, and thus pinning the dying cgwbs. It won't break the * bandwidth restrictions, as writeback of inode metadata is not * accounted for. */ restart = isw_prepare_wbs_switch(isw, &wb->b_attached, &nr); if (!restart) restart = isw_prepare_wbs_switch(isw, &wb->b_dirty_time, &nr); spin_unlock(&wb->list_lock); /* no attached inodes? bail out */ if (nr == 0) { atomic_dec(&isw_nr_in_flight); wb_put(isw->new_wb); kfree(isw); return restart; } /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn); queue_rcu_work(isw_wq, &isw->work); return restart; } /** * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it * @wbc: writeback_control of interest * @inode: target inode * * @inode is locked and about to be written back under the control of @wbc. * Record @inode's writeback context into @wbc and unlock the i_lock. On * writeback completion, wbc_detach_inode() should be called. This is used * to track the cgroup writeback context. */ static void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) __releases(&inode->i_lock) { if (!inode_cgwb_enabled(inode)) { spin_unlock(&inode->i_lock); return; } wbc->wb = inode_to_wb(inode); wbc->inode = inode; wbc->wb_id = wbc->wb->memcg_css->id; wbc->wb_lcand_id = inode->i_wb_frn_winner; wbc->wb_tcand_id = 0; wbc->wb_bytes = 0; wbc->wb_lcand_bytes = 0; wbc->wb_tcand_bytes = 0; wb_get(wbc->wb); spin_unlock(&inode->i_lock); /* * A dying wb indicates that either the blkcg associated with the * memcg changed or the associated memcg is dying. In the first * case, a replacement wb should already be available and we should * refresh the wb immediately. In the second case, trying to * refresh will keep failing. */ if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css))) inode_switch_wbs(inode, wbc->wb_id); } /** * wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite * @wbc: writeback_control of interest * @inode: target inode * * This function is to be used by __filemap_fdatawrite_range(), which is an * alternative entry point into writeback code, and first ensures @inode is * associated with a bdi_writeback and attaches it to @wbc. */ void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, struct inode *inode) { spin_lock(&inode->i_lock); inode_attach_wb(inode, NULL); wbc_attach_and_unlock_inode(wbc, inode); } EXPORT_SYMBOL_GPL(wbc_attach_fdatawrite_inode); /** * wbc_detach_inode - disassociate wbc from inode and perform foreign detection * @wbc: writeback_control of the just finished writeback * * To be called after a writeback attempt of an inode finishes and undoes * wbc_attach_and_unlock_inode(). Can be called under any context. * * As concurrent write sharing of an inode is expected to be very rare and * memcg only tracks page ownership on first-use basis severely confining * the usefulness of such sharing, cgroup writeback tracks ownership * per-inode. While the support for concurrent write sharing of an inode * is deemed unnecessary, an inode being written to by different cgroups at * different points in time is a lot more common, and, more importantly, * charging only by first-use can too readily lead to grossly incorrect * behaviors (single foreign page can lead to gigabytes of writeback to be * incorrectly attributed). * * To resolve this issue, cgroup writeback detects the majority dirtier of * an inode and transfers the ownership to it. To avoid unnecessary * oscillation, the detection mechanism keeps track of history and gives * out the switch verdict only if the foreign usage pattern is stable over * a certain amount of time and/or writeback attempts. * * On each writeback attempt, @wbc tries to detect the majority writer * using Boyer-Moore majority vote algorithm. In addition to the byte * count from the majority voting, it also counts the bytes written for the * current wb and the last round's winner wb (max of last round's current * wb, the winner from two rounds ago, and the last round's majority * candidate). Keeping track of the historical winner helps the algorithm * to semi-reliably detect the most active writer even when it's not the * absolute majority. * * Once the winner of the round is determined, whether the winner is * foreign or not and how much IO time the round consumed is recorded in * inode->i_wb_frn_history. If the amount of recorded foreign IO time is * over a certain threshold, the switch verdict is given. */ void wbc_detach_inode(struct writeback_control *wbc) { struct bdi_writeback *wb = wbc->wb; struct inode *inode = wbc->inode; unsigned long avg_time, max_bytes, max_time; u16 history; int max_id; if (!wb) return; history = inode->i_wb_frn_history; avg_time = inode->i_wb_frn_avg_time; /* pick the winner of this round */ if (wbc->wb_bytes >= wbc->wb_lcand_bytes && wbc->wb_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_id; max_bytes = wbc->wb_bytes; } else if (wbc->wb_lcand_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_lcand_id; max_bytes = wbc->wb_lcand_bytes; } else { max_id = wbc->wb_tcand_id; max_bytes = wbc->wb_tcand_bytes; } /* * Calculate the amount of IO time the winner consumed and fold it * into the running average kept per inode. If the consumed IO * time is lower than avag / WB_FRN_TIME_CUT_DIV, ignore it for * deciding whether to switch or not. This is to prevent one-off * small dirtiers from skewing the verdict. */ max_time = DIV_ROUND_UP((max_bytes >> PAGE_SHIFT) << WB_FRN_TIME_SHIFT, wb->avg_write_bandwidth); if (avg_time) avg_time += (max_time >> WB_FRN_TIME_AVG_SHIFT) - (avg_time >> WB_FRN_TIME_AVG_SHIFT); else avg_time = max_time; /* immediate catch up on first run */ if (max_time >= avg_time / WB_FRN_TIME_CUT_DIV) { int slots; /* * The switch verdict is reached if foreign wb's consume * more than a certain proportion of IO time in a * WB_FRN_TIME_PERIOD. This is loosely tracked by 16 slot * history mask where each bit represents one sixteenth of * the period. Determine the number of slots to shift into * history from @max_time. */ slots = min(DIV_ROUND_UP(max_time, WB_FRN_HIST_UNIT), (unsigned long)WB_FRN_HIST_MAX_SLOTS); history <<= slots; if (wbc->wb_id != max_id) history |= (1U << slots) - 1; if (history) trace_inode_foreign_history(inode, wbc, history); /* * Switch if the current wb isn't the consistent winner. * If there are multiple closely competing dirtiers, the * inode may switch across them repeatedly over time, which * is okay. The main goal is avoiding keeping an inode on * the wrong wb for an extended period of time. */ if (hweight16(history) > WB_FRN_HIST_THR_SLOTS) inode_switch_wbs(inode, max_id); } /* * Multiple instances of this function may race to update the * following fields but we don't mind occassional inaccuracies. */ inode->i_wb_frn_winner = max_id; inode->i_wb_frn_avg_time = min(avg_time, (unsigned long)U16_MAX); inode->i_wb_frn_history = history; wb_put(wbc->wb); wbc->wb = NULL; } EXPORT_SYMBOL_GPL(wbc_detach_inode); /** * wbc_account_cgroup_owner - account writeback to update inode cgroup ownership * @wbc: writeback_control of the writeback in progress * @folio: folio being written out * @bytes: number of bytes being written out * * @bytes from @folio are about to written out during the writeback * controlled by @wbc. Keep the book for foreign inode detection. See * wbc_detach_inode(). */ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio, size_t bytes) { struct cgroup_subsys_state *css; int id; /* * pageout() path doesn't attach @wbc to the inode being written * out. This is intentional as we don't want the function to block * behind a slow cgroup. Ultimately, we want pageout() to kick off * regular writeback instead of writing things out itself. */ if (!wbc->wb || wbc->no_cgroup_owner) return; css = mem_cgroup_css_from_folio(folio); /* dead cgroups shouldn't contribute to inode ownership arbitration */ if (!(css->flags & CSS_ONLINE)) return; id = css->id; if (id == wbc->wb_id) { wbc->wb_bytes += bytes; return; } if (id == wbc->wb_lcand_id) wbc->wb_lcand_bytes += bytes; /* Boyer-Moore majority vote algorithm */ if (!wbc->wb_tcand_bytes) wbc->wb_tcand_id = id; if (id == wbc->wb_tcand_id) wbc->wb_tcand_bytes += bytes; else wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes); } EXPORT_SYMBOL_GPL(wbc_account_cgroup_owner); /** * wb_split_bdi_pages - split nr_pages to write according to bandwidth * @wb: target bdi_writeback to split @nr_pages to * @nr_pages: number of pages to write for the whole bdi * * Split @wb's portion of @nr_pages according to @wb's write bandwidth in * relation to the total write bandwidth of all wb's w/ dirty inodes on * @wb->bdi. */ static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { unsigned long this_bw = wb->avg_write_bandwidth; unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); if (nr_pages == LONG_MAX) return LONG_MAX; /* * This may be called on clean wb's and proportional distribution * may not make sense, just use the original @nr_pages in those * cases. In general, we wanna err on the side of writing more. */ if (!tot_bw || this_bw >= tot_bw) return nr_pages; else return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw); } /** * bdi_split_work_to_wbs - split a wb_writeback_work to all wb's of a bdi * @bdi: target backing_dev_info * @base_work: wb_writeback_work to issue * @skip_if_busy: skip wb's which already have writeback in progress * * Split and issue @base_work to all wb's (bdi_writeback's) of @bdi which * have dirty inodes. If @base_work->nr_page isn't %LONG_MAX, it's * distributed to the busy wbs according to each wb's proportion in the * total active write bandwidth of @bdi. */ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { struct bdi_writeback *last_wb = NULL; struct bdi_writeback *wb = list_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); might_sleep(); restart: rcu_read_lock(); list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) { DEFINE_WB_COMPLETION(fallback_work_done, bdi); struct wb_writeback_work fallback_work; struct wb_writeback_work *work; long nr_pages; if (last_wb) { wb_put(last_wb); last_wb = NULL; } /* SYNC_ALL writes out I_DIRTY_TIME too */ if (!wb_has_dirty_io(wb) && (base_work->sync_mode == WB_SYNC_NONE || list_empty(&wb->b_dirty_time))) continue; if (skip_if_busy && writeback_in_progress(wb)) continue; nr_pages = wb_split_bdi_pages(wb, base_work->nr_pages); work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 1; wb_queue_work(wb, work); continue; } /* * If wb_tryget fails, the wb has been shutdown, skip it. * * Pin @wb so that it stays on @bdi->wb_list. This allows * continuing iteration from @wb after dropping and * regrabbing rcu read lock. */ if (!wb_tryget(wb)) continue; /* alloc failed, execute synchronously using on-stack fallback */ work = &fallback_work; *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 0; work->done = &fallback_work_done; wb_queue_work(wb, work); last_wb = wb; rcu_read_unlock(); wb_wait_for_completion(&fallback_work_done); goto restart; } rcu_read_unlock(); if (last_wb) wb_put(last_wb); } /** * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs * @bdi_id: target bdi id * @memcg_id: target memcg css id * @reason: reason why some writeback work initiated * @done: target wb_completion * * Initiate flush of the bdi_writeback identified by @bdi_id and @memcg_id * with the specified parameters. */ int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, enum wb_reason reason, struct wb_completion *done) { struct backing_dev_info *bdi; struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; struct wb_writeback_work *work; unsigned long dirty; int ret; /* lookup bdi and memcg */ bdi = bdi_get_by_id(bdi_id); if (!bdi) return -ENOENT; rcu_read_lock(); memcg_css = css_from_id(memcg_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) { ret = -ENOENT; goto out_bdi_put; } /* * And find the associated wb. If the wb isn't there already * there's nothing to flush, don't create one. */ wb = wb_get_lookup(bdi, memcg_css); if (!wb) { ret = -ENOENT; goto out_css_put; } /* * The caller is attempting to write out most of * the currently dirty pages. Let's take the current dirty page * count and inflate it by 25% which should be large enough to * flush out most dirty pages while avoiding getting livelocked by * concurrent dirtiers. * * BTW the memcg stats are flushed periodically and this is best-effort * estimation, so some potential error is ok. */ dirty = memcg_page_state(mem_cgroup_from_css(memcg_css), NR_FILE_DIRTY); dirty = dirty * 10 / 8; /* issue the writeback work */ work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN); if (work) { work->nr_pages = dirty; work->sync_mode = WB_SYNC_NONE; work->range_cyclic = 1; work->reason = reason; work->done = done; work->auto_free = 1; wb_queue_work(wb, work); ret = 0; } else { ret = -ENOMEM; } wb_put(wb); out_css_put: css_put(memcg_css); out_bdi_put: bdi_put(bdi); return ret; } /** * cgroup_writeback_umount - flush inode wb switches for umount * @sb: target super_block * * This function is called when a super_block is about to be destroyed and * flushes in-flight inode wb switches. An inode wb switch goes through * RCU and then workqueue, so the two need to be flushed in order to ensure * that all previously scheduled switches are finished. As wb switches are * rare occurrences and synchronize_rcu() can take a while, perform * flushing iff wb switches are in flight. */ void cgroup_writeback_umount(struct super_block *sb) { if (!(sb->s_bdi->capabilities & BDI_CAP_WRITEBACK)) return; /* * SB_ACTIVE should be reliably cleared before checking * isw_nr_in_flight, see generic_shutdown_super(). */ smp_mb(); if (atomic_read(&isw_nr_in_flight)) { /* * Use rcu_barrier() to wait for all pending callbacks to * ensure that all in-flight wb switches are in the workqueue. */ rcu_barrier(); flush_workqueue(isw_wq); } } static int __init cgroup_writeback_init(void) { isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0); if (!isw_wq) return -ENOMEM; return 0; } fs_initcall(cgroup_writeback_init); #else /* CONFIG_CGROUP_WRITEBACK */ static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void inode_cgwb_move_to_attached(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); WARN_ON_ONCE(inode->i_state & I_FREEING); inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); return wb; } static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_lock(&wb->list_lock); return wb; } static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { return nr_pages; } static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { might_sleep(); if (!skip_if_busy || !writeback_in_progress(&bdi->wb)) { base_work->auto_free = 0; wb_queue_work(&bdi->wb, base_work); } } static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) __releases(&inode->i_lock) { spin_unlock(&inode->i_lock); } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * Add in the number of potentially dirty inodes, because each inode * write can dirty pagecache in the underlying blockdev. */ static unsigned long get_nr_dirty_pages(void) { return global_node_page_state(NR_FILE_DIRTY) + get_nr_dirty_inodes(); } static void wb_start_writeback(struct bdi_writeback *wb, enum wb_reason reason) { if (!wb_has_dirty_io(wb)) return; /* * All callers of this function want to start writeback of all * dirty pages. Places like vmscan can call this at a very * high frequency, causing pointless allocations of tons of * work items and keeping the flusher threads busy retrieving * that work. Ensure that we only allow one of them pending and * inflight at the time. */ if (test_bit(WB_start_all, &wb->state) || test_and_set_bit(WB_start_all, &wb->state)) return; wb->start_all_reason = reason; wb_wakeup(wb); } /** * wb_start_background_writeback - start background writeback * @wb: bdi_writback to write from * * Description: * This makes sure WB_SYNC_NONE background writeback happens. When * this function returns, it is only guaranteed that for given wb * some IO is happening if we are over background dirty threshold. * Caller need not hold sb s_umount semaphore. */ void wb_start_background_writeback(struct bdi_writeback *wb) { /* * We just wake up the flusher thread. It will perform background * writeback as soon as there is no other work to do. */ trace_writeback_wake_background(wb); wb_wakeup(wb); } /* * Remove the inode from the writeback list it is on. */ void inode_io_list_del(struct inode *inode) { struct bdi_writeback *wb; wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } EXPORT_SYMBOL(inode_io_list_del); /* * mark an inode as under writeback on the sb */ void sb_mark_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (list_empty(&inode->i_wb_list)) { list_add_tail(&inode->i_wb_list, &sb->s_inodes_wb); trace_sb_mark_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * clear an inode as under writeback on the sb */ void sb_clear_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (!list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (!list_empty(&inode->i_wb_list)) { list_del_init(&inode->i_wb_list); trace_sb_clear_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * Redirty an inode: set its when-it-was dirtied timestamp and move it to the * furthest end of its superblock's dirty-inode list. * * Before stamping the inode's ->dirtied_when, we check to see whether it is * already the most-recently-dirtied inode on the b_dirty list. If that is * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&inode->i_lock); inode->i_state &= ~I_SYNC_QUEUED; /* * When the inode is being freed just don't bother with dirty list * tracking. Flush worker will ignore this inode anyway and it will * trigger assertions in inode_io_list_move_locked(). */ if (inode->i_state & I_FREEING) { list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); return; } if (!list_empty(&wb->b_dirty)) { struct inode *tail; tail = wb_inode(wb->b_dirty.next); if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } inode_io_list_move_locked(inode, wb, &wb->b_dirty); } static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) { spin_lock(&inode->i_lock); redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); } /* * requeue inode for re-scanning after bdi->b_io list is exhausted. */ static void requeue_io(struct inode *inode, struct bdi_writeback *wb) { inode_io_list_move_locked(inode, wb, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) { assert_spin_locked(&inode->i_lock); inode->i_state &= ~I_SYNC; /* If inode is clean an unused, put it into LRU now... */ inode_add_lru(inode); /* Called with inode->i_lock which ensures memory ordering. */ inode_wake_up_bit(inode, __I_SYNC); } static bool inode_dirtied_after(struct inode *inode, unsigned long t) { bool ret = time_after(inode->dirtied_when, t); #ifndef CONFIG_64BIT /* * For inodes being constantly redirtied, dirtied_when can get stuck. * It _appears_ to be in the future, but is actually in distant past. * This test is necessary to prevent such wrapped-around relative times * from permanently stopping the whole bdi writeback. */ ret = ret && time_before_eq(inode->dirtied_when, jiffies); #endif return ret; } /* * Move expired (dirtied before dirtied_before) dirty inodes from * @delaying_queue to @dispatch_queue. */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, unsigned long dirtied_before) { LIST_HEAD(tmp); struct list_head *pos, *node; struct super_block *sb = NULL; struct inode *inode; int do_sb_sort = 0; int moved = 0; while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); if (inode_dirtied_after(inode, dirtied_before)) break; spin_lock(&inode->i_lock); list_move(&inode->i_io_list, &tmp); moved++; inode->i_state |= I_SYNC_QUEUED; spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) continue; if (sb && sb != inode->i_sb) do_sb_sort = 1; sb = inode->i_sb; } /* just one sb in list, splice to dispatch_queue and we're done */ if (!do_sb_sort) { list_splice(&tmp, dispatch_queue); goto out; } /* * Although inode's i_io_list is moved from 'tmp' to 'dispatch_queue', * we don't take inode->i_lock here because it is just a pointless overhead. * Inode is already marked as I_SYNC_QUEUED so writeback list handling is * fully under our control. */ while (!list_empty(&tmp)) { sb = wb_inode(tmp.prev)->i_sb; list_for_each_prev_safe(pos, node, &tmp) { inode = wb_inode(pos); if (inode->i_sb == sb) list_move(&inode->i_io_list, dispatch_queue); } } out: return moved; } /* * Queue all expired dirty inodes for io, eldest first. * Before * newly dirtied b_dirty b_io b_more_io * =============> gf edc BA * After * newly dirtied b_dirty b_io b_more_io * =============> g fBAedc * | * +--> dequeue for IO */ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before) { int moved; unsigned long time_expire_jif = dirtied_before; assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before); if (!work->for_sync) time_expire_jif = jiffies - dirtytime_expire_interval * HZ; moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, time_expire_jif); if (moved) wb_io_lists_populated(wb); trace_writeback_queue_io(wb, work, dirtied_before, moved); } static int write_inode(struct inode *inode, struct writeback_control *wbc) { int ret; if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) { trace_writeback_write_inode_start(inode, wbc); ret = inode->i_sb->s_op->write_inode(inode, wbc); trace_writeback_write_inode(inode, wbc); return ret; } return 0; } /* * Wait for writeback on an inode to complete. Called with i_lock held. * Caller must make sure inode cannot go away when we drop i_lock. */ void inode_wait_for_writeback(struct inode *inode) { struct wait_bit_queue_entry wqe; struct wait_queue_head *wq_head; assert_spin_locked(&inode->i_lock); if (!(inode->i_state & I_SYNC)) return; wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC); for (;;) { prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); /* Checking I_SYNC with inode->i_lock guarantees memory ordering. */ if (!(inode->i_state & I_SYNC)) break; spin_unlock(&inode->i_lock); schedule(); spin_lock(&inode->i_lock); } finish_wait(wq_head, &wqe.wq_entry); } /* * Sleep until I_SYNC is cleared. This function must be called with i_lock * held and drops it. It is aimed for callers not holding any inode reference * so once i_lock is dropped, inode can go away. */ static void inode_sleep_on_writeback(struct inode *inode) __releases(inode->i_lock) { struct wait_bit_queue_entry wqe; struct wait_queue_head *wq_head; bool sleep; assert_spin_locked(&inode->i_lock); wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC); prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); /* Checking I_SYNC with inode->i_lock guarantees memory ordering. */ sleep = !!(inode->i_state & I_SYNC); spin_unlock(&inode->i_lock); if (sleep) schedule(); finish_wait(wq_head, &wqe.wq_entry); } /* * Find proper writeback list for the inode depending on its current state and * possibly also change of its state while we were doing writeback. Here we * handle things such as livelock prevention or fairness of writeback among * inodes. This function can be called only by flusher thread - noone else * processes all inodes in writeback lists and requeueing inodes behind flusher * thread's back can have unexpected consequences. */ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, struct writeback_control *wbc, unsigned long dirtied_before) { if (inode->i_state & I_FREEING) return; /* * Sync livelock prevention. Each inode is tagged and synced in one * shot. If still dirty, it will be redirty_tail()'ed below. Update * the dirty time to prevent enqueue and sync it again. */ if ((inode->i_state & I_DIRTY) && (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)) inode->dirtied_when = jiffies; if (wbc->pages_skipped) { /* * Writeback is not making progress due to locked buffers. * Skip this inode for now. Although having skipped pages * is odd for clean inodes, it can happen for some * filesystems so handle that gracefully. */ if (inode->i_state & I_DIRTY_ALL) redirty_tail_locked(inode, wb); else inode_cgwb_move_to_attached(inode, wb); return; } if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) { /* * We didn't write back all the pages. nfs_writepages() * sometimes bales out without doing anything. */ if (wbc->nr_to_write <= 0 && !inode_dirtied_after(inode, dirtied_before)) { /* Slice used up. Queue for next turn. */ requeue_io(inode, wb); } else { /* * Writeback blocked by something other than * congestion. Delay the inode for some time to * avoid spinning on the CPU (100% iowait) * retrying writeback of the dirty page/inode * that cannot be performed immediately. */ redirty_tail_locked(inode, wb); } } else if (inode->i_state & I_DIRTY) { /* * Filesystems can dirty the inode during writeback operations, * such as delayed allocation during submission or metadata * updates after data IO completion. */ redirty_tail_locked(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ inode_cgwb_move_to_attached(inode, wb); } } /* * Write out an inode and its dirty pages (or some of its dirty pages, depending * on @wbc->nr_to_write), and clear the relevant dirty flags from i_state. * * This doesn't remove the inode from the writeback list it is on, except * potentially to move it from b_dirty_time to b_dirty due to timestamp * expiration. The caller is otherwise responsible for writeback list handling. * * The caller is also responsible for setting the I_SYNC flag beforehand and * calling inode_sync_complete() to clear it afterwards. */ static int __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct address_space *mapping = inode->i_mapping; long nr_to_write = wbc->nr_to_write; unsigned dirty; int ret; WARN_ON(!(inode->i_state & I_SYNC)); trace_writeback_single_inode_start(inode, wbc, nr_to_write); ret = do_writepages(mapping, wbc); /* * Make sure to wait on the data before writing out the metadata. * This is important for filesystems that modify metadata on data * I/O completion. We don't do it for sync(2) writeback because it has a * separate, external IO completion path and ->sync_fs for guaranteeing * inode metadata is written back correctly. */ if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) { int err = filemap_fdatawait(mapping); if (ret == 0) ret = err; } /* * If the inode has dirty timestamps and we need to write them, call * mark_inode_dirty_sync() to notify the filesystem about it and to * change I_DIRTY_TIME into I_DIRTY_SYNC. */ if ((inode->i_state & I_DIRTY_TIME) && (wbc->sync_mode == WB_SYNC_ALL || time_after(jiffies, inode->dirtied_time_when + dirtytime_expire_interval * HZ))) { trace_writeback_lazytime(inode); mark_inode_dirty_sync(inode); } /* * Get and clear the dirty flags from i_state. This needs to be done * after calling writepages because some filesystems may redirty the * inode during writepages due to delalloc. It also needs to be done * after handling timestamp expiration, as that may dirty the inode too. */ spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; inode->i_state &= ~dirty; /* * Paired with smp_mb() in __mark_inode_dirty(). This allows * __mark_inode_dirty() to test i_state without grabbing i_lock - * either they see the I_DIRTY bits cleared or we see the dirtied * inode. * * I_DIRTY_PAGES is always cleared together above even if @mapping * still has dirty pages. The flag is reinstated after smp_mb() if * necessary. This guarantees that either __mark_inode_dirty() * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY. */ smp_mb(); if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) inode->i_state |= I_DIRTY_PAGES; else if (unlikely(inode->i_state & I_PINNING_NETFS_WB)) { if (!(inode->i_state & I_DIRTY_PAGES)) { inode->i_state &= ~I_PINNING_NETFS_WB; wbc->unpinned_netfs_wb = true; dirty |= I_PINNING_NETFS_WB; /* Cause write_inode */ } } spin_unlock(&inode->i_lock); /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & ~I_DIRTY_PAGES) { int err = write_inode(inode, wbc); if (ret == 0) ret = err; } wbc->unpinned_netfs_wb = false; trace_writeback_single_inode(inode, wbc, nr_to_write); return ret; } /* * Write out an inode's dirty data and metadata on-demand, i.e. separately from * the regular batched writeback done by the flusher threads in * writeback_sb_inodes(). @wbc controls various aspects of the write, such as * whether it is a data-integrity sync (%WB_SYNC_ALL) or not (%WB_SYNC_NONE). * * To prevent the inode from going away, either the caller must have a reference * to the inode, or the inode must have I_WILL_FREE or I_FREEING set. */ static int writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct bdi_writeback *wb; int ret = 0; spin_lock(&inode->i_lock); if (!atomic_read(&inode->i_count)) WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); else WARN_ON(inode->i_state & I_WILL_FREE); if (inode->i_state & I_SYNC) { /* * Writeback is already running on the inode. For WB_SYNC_NONE, * that's enough and we can just return. For WB_SYNC_ALL, we * must wait for the existing writeback to complete, then do * writeback again if there's anything left. */ if (wbc->sync_mode != WB_SYNC_ALL) goto out; inode_wait_for_writeback(inode); } WARN_ON(inode->i_state & I_SYNC); /* * If the inode is already fully clean, then there's nothing to do. * * For data-integrity syncs we also need to check whether any pages are * still under writeback, e.g. due to prior WB_SYNC_NONE writeback. If * there are any such pages, we'll need to wait for them. */ if (!(inode->i_state & I_DIRTY_ALL) && (wbc->sync_mode != WB_SYNC_ALL || !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))) goto out; inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(wbc, inode); ret = __writeback_single_inode(inode, wbc); wbc_detach_inode(wbc); wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); /* * If the inode is freeing, its i_io_list shoudn't be updated * as it can be finally deleted at this moment. */ if (!(inode->i_state & I_FREEING)) { /* * If the inode is now fully clean, then it can be safely * removed from its writeback list (if any). Otherwise the * flusher threads are responsible for the writeback lists. */ if (!(inode->i_state & I_DIRTY_ALL)) inode_cgwb_move_to_attached(inode, wb); else if (!(inode->i_state & I_SYNC_QUEUED)) { if ((inode->i_state & I_DIRTY)) redirty_tail_locked(inode, wb); else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); } } } spin_unlock(&wb->list_lock); inode_sync_complete(inode); out: spin_unlock(&inode->i_lock); return ret; } static long writeback_chunk_size(struct bdi_writeback *wb, struct wb_writeback_work *work) { long pages; /* * WB_SYNC_ALL mode does livelock avoidance by syncing dirty * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX * here avoids calling into writeback_inodes_wb() more than once. * * The intended call sequence for WB_SYNC_ALL writeback is: * * wb_writeback() * writeback_sb_inodes() <== called only once * write_cache_pages() <== called once for each inode * (quickly) tag currently dirty pages * (maybe slowly) sync all tagged pages */ if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages) pages = LONG_MAX; else { pages = min(wb->avg_write_bandwidth / 2, global_wb_domain.dirty_limit / DIRTY_SCOPE); pages = min(pages, work->nr_pages); pages = round_down(pages + MIN_WRITEBACK_PAGES, MIN_WRITEBACK_PAGES); } return pages; } /* * Write a portion of b_io inodes which belong to @sb. * * Return the number of pages and/or inodes written. * * NOTE! This is called with wb->list_lock held, and will * unlock and relock that for each inode it ends up doing * IO for. */ static long writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, struct wb_writeback_work *work) { struct writeback_control wbc = { .sync_mode = work->sync_mode, .tagged_writepages = work->tagged_writepages, .for_kupdate = work->for_kupdate, .for_background = work->for_background, .for_sync = work->for_sync, .range_cyclic = work->range_cyclic, .range_start = 0, .range_end = LLONG_MAX, }; unsigned long start_time = jiffies; long write_chunk; long total_wrote = 0; /* count both pages and inodes */ unsigned long dirtied_before = jiffies; if (work->for_kupdate) dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct bdi_writeback *tmp_wb; long wrote; if (inode->i_sb != sb) { if (work->sb) { /* * We only want to write back data for this * superblock, move all inodes not belonging * to it back onto the dirty list. */ redirty_tail(inode, wb); continue; } /* * The inode belongs to a different superblock. * Bounce back to the caller to unpin this and * pin the next superblock. */ break; } /* * Don't bother with new inodes or inodes being freed, first * kind does not need periodic writeout yet, and for the latter * kind writeout is handled by the freer. */ spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); continue; } if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { /* * If this inode is locked for writeback and we are not * doing writeback-for-data-integrity, move it to * b_more_io so that writeback can proceed with the * other inodes on s_io. * * We'll have another go at writing back this inode * when we completed a full scan of b_io. */ requeue_io(inode, wb); spin_unlock(&inode->i_lock); trace_writeback_sb_inodes_requeue(inode); continue; } spin_unlock(&wb->list_lock); /* * We already requeued the inode if it had I_SYNC set and we * are doing WB_SYNC_NONE writeback. So this catches only the * WB_SYNC_ALL case. */ if (inode->i_state & I_SYNC) { /* Wait for I_SYNC. This function drops i_lock... */ inode_sleep_on_writeback(inode); /* Inode may be gone, start again */ spin_lock(&wb->list_lock); continue; } inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(&wbc, inode); write_chunk = writeback_chunk_size(wb, work); wbc.nr_to_write = write_chunk; wbc.pages_skipped = 0; /* * We use I_SYNC to pin the inode in memory. While it is set * evict_inode() will wait so the inode cannot be freed. */ __writeback_single_inode(inode, &wbc); wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; wrote = write_chunk - wbc.nr_to_write - wbc.pages_skipped; wrote = wrote < 0 ? 0 : wrote; total_wrote += wrote; if (need_resched()) { /* * We're trying to balance between building up a nice * long list of IOs to improve our merge rate, and * getting those IOs out quickly for anyone throttling * in balance_dirty_pages(). cond_resched() doesn't * unplug, so get our IOs out the door before we * give up the CPU. */ blk_flush_plug(current->plug, false); cond_resched(); } /* * Requeue @inode if still dirty. Be careful as @inode may * have been switched to another wb in the meantime. */ tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY_ALL)) total_wrote++; requeue_inode(inode, tmp_wb, &wbc, dirtied_before); inode_sync_complete(inode); spin_unlock(&inode->i_lock); if (unlikely(tmp_wb != wb)) { spin_unlock(&tmp_wb->list_lock); spin_lock(&wb->list_lock); } /* * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. */ if (total_wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } return total_wrote; } static long __writeback_inodes_wb(struct bdi_writeback *wb, struct wb_writeback_work *work) { unsigned long start_time = jiffies; long wrote = 0; while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct super_block *sb = inode->i_sb; if (!super_trylock_shared(sb)) { /* * super_trylock_shared() may fail consistently due to * s_umount being grabbed by someone else. Don't use * requeue_io() to avoid busy retrying the inode/sb. */ redirty_tail(inode, wb); continue; } wrote += writeback_sb_inodes(sb, wb, work); up_read(&sb->s_umount); /* refer to the same tests at the end of writeback_sb_inodes */ if (wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } /* Leave any unwritten inodes on b_io */ return wrote; } static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, enum wb_reason reason) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = reason, }; struct blk_plug plug; blk_start_plug(&plug); spin_lock(&wb->list_lock); if (list_empty(&wb->b_io)) queue_io(wb, &work, jiffies); __writeback_inodes_wb(wb, &work); spin_unlock(&wb->list_lock); blk_finish_plug(&plug); return nr_pages - work.nr_pages; } /* * Explicit flushing or periodic writeback of "old" data. * * Define "old": the first time one of an inode's pages is dirtied, we mark the * dirtying-time in the inode's address_space. So this periodic writeback code * just walks the superblock inode list, writing back any inodes which are * older than a specific point in time. * * Try to run once per dirty_writeback_interval. But if a writeback event * takes longer than a dirty_writeback_interval interval, then leave a * one-second gap. * * dirtied_before takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ static long wb_writeback(struct bdi_writeback *wb, struct wb_writeback_work *work) { long nr_pages = work->nr_pages; unsigned long dirtied_before = jiffies; struct inode *inode; long progress; struct blk_plug plug; bool queued = false; blk_start_plug(&plug); for (;;) { /* * Stop writeback when nr_pages has been consumed */ if (work->nr_pages <= 0) break; /* * Background writeout and kupdate-style writeback may * run forever. Stop them if there is other work to do * so that e.g. sync can proceed. They'll be restarted * after the other works are all done. */ if ((work->for_background || work->for_kupdate) && !list_empty(&wb->work_list)) break; /* * For background writeout, stop when we are below the * background dirty threshold */ if (work->for_background && !wb_over_bg_thresh(wb)) break; spin_lock(&wb->list_lock); trace_writeback_start(wb, work); if (list_empty(&wb->b_io)) { /* * Kupdate and background works are special and we want * to include all inodes that need writing. Livelock * avoidance is handled by these works yielding to any * other work so we are safe. */ if (work->for_kupdate) { dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) dirtied_before = jiffies; queue_io(wb, work, dirtied_before); queued = true; } if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else progress = __writeback_inodes_wb(wb, work); trace_writeback_written(wb, work); /* * Did we write something? Try for more * * Dirty inodes are moved to b_io for writeback in batches. * The completion of the current batch does not necessarily * mean the overall work is done. So we keep looping as long * as made some progress on cleaning pages or inodes. */ if (progress || !queued) { spin_unlock(&wb->list_lock); continue; } /* * No more inodes for IO, bail */ if (list_empty(&wb->b_more_io)) { spin_unlock(&wb->list_lock); break; } /* * Nothing written. Wait for some inode to * become available for writeback. Otherwise * we'll just busyloop. */ trace_writeback_wait(wb, work); inode = wb_inode(wb->b_more_io.prev); spin_lock(&inode->i_lock); spin_unlock(&wb->list_lock); /* This function drops i_lock... */ inode_sleep_on_writeback(inode); } blk_finish_plug(&plug); return nr_pages - work->nr_pages; } /* * Return the next wb_writeback_work struct that hasn't been processed yet. */ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb) { struct wb_writeback_work *work = NULL; spin_lock_irq(&wb->work_lock); if (!list_empty(&wb->work_list)) { work = list_entry(wb->work_list.next, struct wb_writeback_work, list); list_del_init(&work->list); } spin_unlock_irq(&wb->work_lock); return work; } static long wb_check_background_flush(struct bdi_writeback *wb) { if (wb_over_bg_thresh(wb)) { struct wb_writeback_work work = { .nr_pages = LONG_MAX, .sync_mode = WB_SYNC_NONE, .for_background = 1, .range_cyclic = 1, .reason = WB_REASON_BACKGROUND, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_old_data_flush(struct bdi_writeback *wb) { unsigned long expired; long nr_pages; /* * When set to zero, disable periodic writeback */ if (!dirty_writeback_interval) return 0; expired = wb->last_old_flush + msecs_to_jiffies(dirty_writeback_interval * 10); if (time_before(jiffies, expired)) return 0; wb->last_old_flush = jiffies; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .for_kupdate = 1, .range_cyclic = 1, .reason = WB_REASON_PERIODIC, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_start_all(struct bdi_writeback *wb) { long nr_pages; if (!test_bit(WB_start_all, &wb->state)) return 0; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = wb_split_bdi_pages(wb, nr_pages), .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = wb->start_all_reason, }; nr_pages = wb_writeback(wb, &work); } clear_bit(WB_start_all, &wb->state); return nr_pages; } /* * Retrieve work items and do the writeback they describe */ static long wb_do_writeback(struct bdi_writeback *wb) { struct wb_writeback_work *work; long wrote = 0; set_bit(WB_writeback_running, &wb->state); while ((work = get_next_work_item(wb)) != NULL) { trace_writeback_exec(wb, work); wrote += wb_writeback(wb, work); finish_writeback_work(work); } /* * Check for a flush-everything request */ wrote += wb_check_start_all(wb); /* * Check for periodic writeback, kupdated() style */ wrote += wb_check_old_data_flush(wb); wrote += wb_check_background_flush(wb); clear_bit(WB_writeback_running, &wb->state); return wrote; } /* * Handle writeback of dirty data for the device backed by this bdi. Also * reschedules periodically and does kupdated style flushing. */ void wb_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, dwork); long pages_written; set_worker_desc("flush-%s", bdi_dev_name(wb->bdi)); if (likely(!current_is_workqueue_rescuer() || !test_bit(WB_registered, &wb->state))) { /* * The normal path. Keep writing back @wb until its * work_list is empty. Note that this path is also taken * if @wb is shutting down even when we're running off the * rescuer as work_list needs to be drained. */ do { pages_written = wb_do_writeback(wb); trace_writeback_pages_written(pages_written); } while (!list_empty(&wb->work_list)); } else { /* * bdi_wq can't get enough workers and we're running off * the emergency worker. Don't hog it. Hopefully, 1024 is * enough for efficient IO. */ pages_written = writeback_inodes_wb(wb, 1024, WB_REASON_FORKER_THREAD); trace_writeback_pages_written(pages_written); } if (!list_empty(&wb->work_list)) wb_wakeup(wb); else if (wb_has_dirty_io(wb) && dirty_writeback_interval) wb_wakeup_delayed(wb); } /* * Start writeback of all dirty pages on this bdi. */ static void __wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { struct bdi_writeback *wb; if (!bdi_has_dirty_io(bdi)) return; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) wb_start_writeback(wb, reason); } void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { rcu_read_lock(); __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wakeup the flusher threads to start writeback of all currently dirty pages */ void wakeup_flusher_threads(enum wb_reason reason) { struct backing_dev_info *bdi; /* * If we are expecting writeback progress we must submit plugged IO. */ blk_flush_plug(current->plug, true); rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wake up bdi's periodically to make sure dirtytime inodes gets * written back periodically. We deliberately do *not* check the * b_dirtytime list in wb_has_dirty_io(), since this would cause the * kernel to be constantly waking up once there are any dirtytime * inodes on the system. So instead we define a separate delayed work * function which gets called much more rarely. (By default, only * once every 12 hours.) * * If there is any other write activity going on in the file system, * this function won't be necessary. But if the only thing that has * happened on the file system is a dirtytime inode caused by an atime * update, we need this infrastructure below to make sure that inode * eventually gets pushed out to disk. */ static void wakeup_dirtytime_writeback(struct work_struct *w); static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback); static void wakeup_dirtytime_writeback(struct work_struct *w) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) if (!list_empty(&wb->b_dirty_time)) wb_wakeup(wb); } rcu_read_unlock(); schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); } static int dirtytime_interval_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) mod_delayed_work(system_wq, &dirtytime_work, 0); return ret; } static const struct ctl_table vm_fs_writeback_table[] = { { .procname = "dirtytime_expire_seconds", .data = &dirtytime_expire_interval, .maxlen = sizeof(dirtytime_expire_interval), .mode = 0644, .proc_handler = dirtytime_interval_handler, .extra1 = SYSCTL_ZERO, }, }; static int __init start_dirtytime_writeback(void) { schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); register_sysctl_init("vm", vm_fs_writeback_table); return 0; } __initcall(start_dirtytime_writeback); /** * __mark_inode_dirty - internal function to mark an inode dirty * * @inode: inode to mark * @flags: what kind of dirty, e.g. I_DIRTY_SYNC. This can be a combination of * multiple I_DIRTY_* flags, except that I_DIRTY_TIME can't be combined * with I_DIRTY_PAGES. * * Mark an inode as dirty. We notify the filesystem, then update the inode's * dirty flags. Then, if needed we add the inode to the appropriate dirty list. * * Most callers should use mark_inode_dirty() or mark_inode_dirty_sync() * instead of calling this directly. * * CAREFUL! We only add the inode to the dirty list if it is hashed or if it * refers to a blockdev. Unhashed inodes will never be added to the dirty list * even if they are later hashed, as they will have been marked dirty already. * * In short, ensure you hash any inodes _before_ you start marking them dirty. * * Note that for blockdevs, inode->dirtied_when represents the dirtying time of * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of * the kernel-internal blockdev inode represents the dirtying time of the * blockdev's pages. This is why for I_DIRTY_PAGES we always use * page->mapping->host, so the page-dirtying time is recorded in the internal * blockdev inode. */ void __mark_inode_dirty(struct inode *inode, int flags) { struct super_block *sb = inode->i_sb; int dirtytime = 0; struct bdi_writeback *wb = NULL; trace_writeback_mark_inode_dirty(inode, flags); if (flags & I_DIRTY_INODE) { /* * Inode timestamp update will piggback on this dirtying. * We tell ->dirty_inode callback that timestamps need to * be updated by setting I_DIRTY_TIME in flags. */ if (inode->i_state & I_DIRTY_TIME) { spin_lock(&inode->i_lock); if (inode->i_state & I_DIRTY_TIME) { inode->i_state &= ~I_DIRTY_TIME; flags |= I_DIRTY_TIME; } spin_unlock(&inode->i_lock); } /* * Notify the filesystem about the inode being dirtied, so that * (if needed) it can update on-disk fields and journal the * inode. This is only needed when the inode itself is being * dirtied now. I.e. it's only needed for I_DIRTY_INODE, not * for just I_DIRTY_PAGES or I_DIRTY_TIME. */ trace_writeback_dirty_inode_start(inode, flags); if (sb->s_op->dirty_inode) sb->s_op->dirty_inode(inode, flags & (I_DIRTY_INODE | I_DIRTY_TIME)); trace_writeback_dirty_inode(inode, flags); /* I_DIRTY_INODE supersedes I_DIRTY_TIME. */ flags &= ~I_DIRTY_TIME; } else { /* * Else it's either I_DIRTY_PAGES, I_DIRTY_TIME, or nothing. * (We don't support setting both I_DIRTY_PAGES and I_DIRTY_TIME * in one call to __mark_inode_dirty().) */ dirtytime = flags & I_DIRTY_TIME; WARN_ON_ONCE(dirtytime && flags != I_DIRTY_TIME); } /* * Paired with smp_mb() in __writeback_single_inode() for the * following lockless i_state test. See there for details. */ smp_mb(); if ((inode->i_state & flags) == flags) return; spin_lock(&inode->i_lock); if ((inode->i_state & flags) != flags) { const int was_dirty = inode->i_state & I_DIRTY; inode_attach_wb(inode, NULL); inode->i_state |= flags; /* * Grab inode's wb early because it requires dropping i_lock and we * need to make sure following checks happen atomically with dirty * list handling so that we don't move inodes under flush worker's * hands. */ if (!was_dirty) { wb = locked_inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); } /* * If the inode is queued for writeback by flush worker, just * update its dirty state. Once the flush worker is done with * the inode it will place it on the appropriate superblock * list, based upon its state. */ if (inode->i_state & I_SYNC_QUEUED) goto out_unlock; /* * Only add valid (hashed) inodes to the superblock's * dirty list. Add blockdev inodes as well. */ if (!S_ISBLK(inode->i_mode)) { if (inode_unhashed(inode)) goto out_unlock; } if (inode->i_state & I_FREEING) goto out_unlock; /* * If the inode was already on b_dirty/b_io/b_more_io, don't * reposition it (that would break b_dirty time-ordering). */ if (!was_dirty) { struct list_head *dirty_list; bool wakeup_bdi = false; inode->dirtied_when = jiffies; if (dirtytime) inode->dirtied_time_when = jiffies; if (inode->i_state & I_DIRTY) dirty_list = &wb->b_dirty; else dirty_list = &wb->b_dirty_time; wakeup_bdi = inode_io_list_move_locked(inode, wb, dirty_list); spin_unlock(&wb->list_lock); spin_unlock(&inode->i_lock); trace_writeback_dirty_inode_enqueue(inode); /* * If this is the first dirty inode for this bdi, * we have to wake-up the corresponding bdi thread * to make sure background write-back happens * later. */ if (wakeup_bdi && (wb->bdi->capabilities & BDI_CAP_WRITEBACK)) wb_wakeup_delayed(wb); return; } } out_unlock: if (wb) spin_unlock(&wb->list_lock); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(__mark_inode_dirty); /* * The @s_sync_lock is used to serialise concurrent sync operations * to avoid lock contention problems with concurrent wait_sb_inodes() calls. * Concurrent callers will block on the s_sync_lock rather than doing contending * walks. The queueing maintains sync(2) required behaviour as all the IO that * has been issued up to the time this function is enter is guaranteed to be * completed by the time we have gained the lock and waited for all IO that is * in progress regardless of the order callers are granted the lock. */ static void wait_sb_inodes(struct super_block *sb) { LIST_HEAD(sync_list); /* * We need to be protected against the filesystem going from * r/o to r/w or vice versa. */ WARN_ON(!rwsem_is_locked(&sb->s_umount)); mutex_lock(&sb->s_sync_lock); /* * Splice the writeback list onto a temporary list to avoid waiting on * inodes that have started writeback after this point. * * Use rcu_read_lock() to keep the inodes around until we have a * reference. s_inode_wblist_lock protects sb->s_inodes_wb as well as * the local list because inodes can be dropped from either by writeback * completion. */ rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); list_splice_init(&sb->s_inodes_wb, &sync_list); /* * Data integrity sync. Must wait for all pages under writeback, because * there may have been pages dirtied before our sync call, but which had * writeout started before we write it out. In which case, the inode * may not be on the dirty list, but we still have to wait for that * writeout. */ while (!list_empty(&sync_list)) { struct inode *inode = list_first_entry(&sync_list, struct inode, i_wb_list); struct address_space *mapping = inode->i_mapping; /* * Move each inode back to the wb list before we drop the lock * to preserve consistency between i_wb_list and the mapping * writeback tag. Writeback completion is responsible to remove * the inode from either list once the writeback tag is cleared. */ list_move_tail(&inode->i_wb_list, &sb->s_inodes_wb); /* * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. */ if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { spin_unlock(&inode->i_lock); spin_lock_irq(&sb->s_inode_wblist_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); rcu_read_unlock(); /* * We keep the error status of individual mapping so that * applications can catch the writeback error using fsync(2). * See filemap_fdatawait_keep_errors() for details. */ filemap_fdatawait_keep_errors(mapping); cond_resched(); iput(inode); rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); } spin_unlock_irq(&sb->s_inode_wblist_lock); rcu_read_unlock(); mutex_unlock(&sb->s_sync_lock); } static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason, bool skip_if_busy) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_NONE, .tagged_writepages = 1, .done = &done, .nr_pages = nr, .reason = reason, }; if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy); wb_wait_for_completion(&done); } /** * writeback_inodes_sb_nr - writeback dirty inodes from given super_block * @sb: the superblock * @nr: the number of pages to write * @reason: reason why some writeback work initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason) { __writeback_inodes_sb_nr(sb, nr, reason, false); } EXPORT_SYMBOL(writeback_inodes_sb_nr); /** * writeback_inodes_sb - writeback dirty inodes from given super_block * @sb: the superblock * @reason: reason why some writeback work was initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } EXPORT_SYMBOL(writeback_inodes_sb); /** * try_to_writeback_inodes_sb - try to start writeback if none underway * @sb: the superblock * @reason: reason why some writeback work was initiated * * Invoke __writeback_inodes_sb_nr if no writeback is currently underway. */ void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { if (!down_read_trylock(&sb->s_umount)) return; __writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason, true); up_read(&sb->s_umount); } EXPORT_SYMBOL(try_to_writeback_inodes_sb); /** * sync_inodes_sb - sync sb inode pages * @sb: the superblock * * This function writes and waits on any dirty inode belonging to this * super_block. */ void sync_inodes_sb(struct super_block *sb) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, .range_cyclic = 0, .done = &done, .reason = WB_REASON_SYNC, .for_sync = 1, }; /* * Can't skip on !bdi_has_dirty() because we should wait for !dirty * inodes under writeback and I_DIRTY_TIME inodes ignored by * bdi_has_dirty() need to be written out too. */ if (bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ bdi_down_write_wb_switch_rwsem(bdi); bdi_split_work_to_wbs(bdi, &work, false); wb_wait_for_completion(&done); bdi_up_write_wb_switch_rwsem(bdi); wait_sb_inodes(sb); } EXPORT_SYMBOL(sync_inodes_sb); /** * write_inode_now - write an inode to disk * @inode: inode to write to disk * @sync: whether the write should be synchronous or not * * This function commits an inode to disk immediately if it is dirty. This is * primarily needed by knfsd. * * The caller must either have a ref on the inode or must have set I_WILL_FREE. */ int write_inode_now(struct inode *inode, int sync) { struct writeback_control wbc = { .nr_to_write = LONG_MAX, .sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE, .range_start = 0, .range_end = LLONG_MAX, }; if (!mapping_can_writeback(inode->i_mapping)) wbc.nr_to_write = 0; might_sleep(); return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(write_inode_now); /** * sync_inode_metadata - write an inode to disk * @inode: the inode to sync * @wait: wait for I/O to complete. * * Write an inode to disk and adjust its dirty state after completion. * * Note: only writes the actual inode, no associated data or other metadata. */ int sync_inode_metadata(struct inode *inode, int wait) { struct writeback_control wbc = { .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE, .nr_to_write = 0, /* metadata-only */ }; return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(sync_inode_metadata); |
| 2 3 3 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Sally Floyd's High Speed TCP (RFC 3649) congestion control * * See https://www.icir.org/floyd/hstcp.html * * John Heffner <jheffner@psc.edu> */ #include <linux/module.h> #include <net/tcp.h> /* From AIMD tables from RFC 3649 appendix B, * with fixed-point MD scaled <<8. */ static const struct hstcp_aimd_val { unsigned int cwnd; unsigned int md; } hstcp_aimd_vals[] = { { 38, 128, /* 0.50 */ }, { 118, 112, /* 0.44 */ }, { 221, 104, /* 0.41 */ }, { 347, 98, /* 0.38 */ }, { 495, 93, /* 0.37 */ }, { 663, 89, /* 0.35 */ }, { 851, 86, /* 0.34 */ }, { 1058, 83, /* 0.33 */ }, { 1284, 81, /* 0.32 */ }, { 1529, 78, /* 0.31 */ }, { 1793, 76, /* 0.30 */ }, { 2076, 74, /* 0.29 */ }, { 2378, 72, /* 0.28 */ }, { 2699, 71, /* 0.28 */ }, { 3039, 69, /* 0.27 */ }, { 3399, 68, /* 0.27 */ }, { 3778, 66, /* 0.26 */ }, { 4177, 65, /* 0.26 */ }, { 4596, 64, /* 0.25 */ }, { 5036, 62, /* 0.25 */ }, { 5497, 61, /* 0.24 */ }, { 5979, 60, /* 0.24 */ }, { 6483, 59, /* 0.23 */ }, { 7009, 58, /* 0.23 */ }, { 7558, 57, /* 0.22 */ }, { 8130, 56, /* 0.22 */ }, { 8726, 55, /* 0.22 */ }, { 9346, 54, /* 0.21 */ }, { 9991, 53, /* 0.21 */ }, { 10661, 52, /* 0.21 */ }, { 11358, 52, /* 0.20 */ }, { 12082, 51, /* 0.20 */ }, { 12834, 50, /* 0.20 */ }, { 13614, 49, /* 0.19 */ }, { 14424, 48, /* 0.19 */ }, { 15265, 48, /* 0.19 */ }, { 16137, 47, /* 0.19 */ }, { 17042, 46, /* 0.18 */ }, { 17981, 45, /* 0.18 */ }, { 18955, 45, /* 0.18 */ }, { 19965, 44, /* 0.17 */ }, { 21013, 43, /* 0.17 */ }, { 22101, 43, /* 0.17 */ }, { 23230, 42, /* 0.17 */ }, { 24402, 41, /* 0.16 */ }, { 25618, 41, /* 0.16 */ }, { 26881, 40, /* 0.16 */ }, { 28193, 39, /* 0.16 */ }, { 29557, 39, /* 0.15 */ }, { 30975, 38, /* 0.15 */ }, { 32450, 38, /* 0.15 */ }, { 33986, 37, /* 0.15 */ }, { 35586, 36, /* 0.14 */ }, { 37253, 36, /* 0.14 */ }, { 38992, 35, /* 0.14 */ }, { 40808, 35, /* 0.14 */ }, { 42707, 34, /* 0.13 */ }, { 44694, 33, /* 0.13 */ }, { 46776, 33, /* 0.13 */ }, { 48961, 32, /* 0.13 */ }, { 51258, 32, /* 0.13 */ }, { 53677, 31, /* 0.12 */ }, { 56230, 30, /* 0.12 */ }, { 58932, 30, /* 0.12 */ }, { 61799, 29, /* 0.12 */ }, { 64851, 28, /* 0.11 */ }, { 68113, 28, /* 0.11 */ }, { 71617, 27, /* 0.11 */ }, { 75401, 26, /* 0.10 */ }, { 79517, 26, /* 0.10 */ }, { 84035, 25, /* 0.10 */ }, { 89053, 24, /* 0.10 */ }, }; #define HSTCP_AIMD_MAX ARRAY_SIZE(hstcp_aimd_vals) struct hstcp { u32 ai; }; static void hstcp_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct hstcp *ca = inet_csk_ca(sk); ca->ai = 0; /* Ensure the MD arithmetic works. This is somewhat pedantic, * since I don't think we will see a cwnd this large. :) */ tp->snd_cwnd_clamp = min_t(u32, tp->snd_cwnd_clamp, 0xffffffff/128); } static void hstcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct hstcp *ca = inet_csk_ca(sk); if (!tcp_is_cwnd_limited(sk)) return; if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { /* Update AIMD parameters. * * We want to guarantee that: * hstcp_aimd_vals[ca->ai-1].cwnd < * snd_cwnd <= * hstcp_aimd_vals[ca->ai].cwnd */ if (tcp_snd_cwnd(tp) > hstcp_aimd_vals[ca->ai].cwnd) { while (tcp_snd_cwnd(tp) > hstcp_aimd_vals[ca->ai].cwnd && ca->ai < HSTCP_AIMD_MAX - 1) ca->ai++; } else if (ca->ai && tcp_snd_cwnd(tp) <= hstcp_aimd_vals[ca->ai-1].cwnd) { while (ca->ai && tcp_snd_cwnd(tp) <= hstcp_aimd_vals[ca->ai-1].cwnd) ca->ai--; } /* Do additive increase */ if (tcp_snd_cwnd(tp) < tp->snd_cwnd_clamp) { /* cwnd = cwnd + a(w) / cwnd */ tp->snd_cwnd_cnt += ca->ai + 1; if (tp->snd_cwnd_cnt >= tcp_snd_cwnd(tp)) { tp->snd_cwnd_cnt -= tcp_snd_cwnd(tp); tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) + 1); } } } } static u32 hstcp_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct hstcp *ca = inet_csk_ca(sk); /* Do multiplicative decrease */ return max(tcp_snd_cwnd(tp) - ((tcp_snd_cwnd(tp) * hstcp_aimd_vals[ca->ai].md) >> 8), 2U); } static struct tcp_congestion_ops tcp_highspeed __read_mostly = { .init = hstcp_init, .ssthresh = hstcp_ssthresh, .undo_cwnd = tcp_reno_undo_cwnd, .cong_avoid = hstcp_cong_avoid, .owner = THIS_MODULE, .name = "highspeed" }; static int __init hstcp_register(void) { BUILD_BUG_ON(sizeof(struct hstcp) > ICSK_CA_PRIV_SIZE); return tcp_register_congestion_control(&tcp_highspeed); } static void __exit hstcp_unregister(void) { tcp_unregister_congestion_control(&tcp_highspeed); } module_init(hstcp_register); module_exit(hstcp_unregister); MODULE_AUTHOR("John Heffner"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("High Speed TCP"); |
| 10370 52 236 235 4312 4237 3925 183 27 2504 31 145 153 12 334 3593 34 57 28 3 18 707 36 4 278 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* audit.h -- Auditing support * * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. * All Rights Reserved. * * Written by Rickard E. (Rik) Faith <faith@redhat.com> */ #ifndef _LINUX_AUDIT_H_ #define _LINUX_AUDIT_H_ #include <linux/sched.h> #include <linux/ptrace.h> #include <linux/audit_arch.h> #include <uapi/linux/audit.h> #include <uapi/linux/netfilter/nf_tables.h> #include <uapi/linux/fanotify.h> #define AUDIT_INO_UNSET ((unsigned long)-1) #define AUDIT_DEV_UNSET ((dev_t)-1) struct audit_sig_info { uid_t uid; pid_t pid; char ctx[]; }; struct audit_buffer; struct audit_context; struct inode; struct netlink_skb_parms; struct path; struct linux_binprm; struct mq_attr; struct mqstat; struct audit_watch; struct audit_tree; struct sk_buff; struct kern_ipc_perm; struct audit_krule { u32 pflags; u32 flags; u32 listnr; u32 action; u32 mask[AUDIT_BITMASK_SIZE]; u32 buflen; /* for data alloc on list rules */ u32 field_count; char *filterkey; /* ties events to rules */ struct audit_field *fields; struct audit_field *arch_f; /* quick access to arch field */ struct audit_field *inode_f; /* quick access to an inode field */ struct audit_watch *watch; /* associated watch */ struct audit_tree *tree; /* associated watched tree */ struct audit_fsnotify_mark *exe; struct list_head rlist; /* entry in audit_{watch,tree}.rules list */ struct list_head list; /* for AUDIT_LIST* purposes only */ u64 prio; }; /* Flag to indicate legacy AUDIT_LOGINUID unset usage */ #define AUDIT_LOGINUID_LEGACY 0x1 struct audit_field { u32 type; union { u32 val; kuid_t uid; kgid_t gid; struct { char *lsm_str; void *lsm_rule; }; }; u32 op; }; enum audit_ntp_type { AUDIT_NTP_OFFSET, AUDIT_NTP_FREQ, AUDIT_NTP_STATUS, AUDIT_NTP_TAI, AUDIT_NTP_TICK, AUDIT_NTP_ADJUST, AUDIT_NTP_NVALS /* count */ }; #ifdef CONFIG_AUDITSYSCALL struct audit_ntp_val { long long oldval, newval; }; struct audit_ntp_data { struct audit_ntp_val vals[AUDIT_NTP_NVALS]; }; #else struct audit_ntp_data {}; #endif enum audit_nfcfgop { AUDIT_XT_OP_REGISTER, AUDIT_XT_OP_REPLACE, AUDIT_XT_OP_UNREGISTER, AUDIT_NFT_OP_TABLE_REGISTER, AUDIT_NFT_OP_TABLE_UNREGISTER, AUDIT_NFT_OP_CHAIN_REGISTER, AUDIT_NFT_OP_CHAIN_UNREGISTER, AUDIT_NFT_OP_RULE_REGISTER, AUDIT_NFT_OP_RULE_UNREGISTER, AUDIT_NFT_OP_SET_REGISTER, AUDIT_NFT_OP_SET_UNREGISTER, AUDIT_NFT_OP_SETELEM_REGISTER, AUDIT_NFT_OP_SETELEM_UNREGISTER, AUDIT_NFT_OP_GEN_REGISTER, AUDIT_NFT_OP_OBJ_REGISTER, AUDIT_NFT_OP_OBJ_UNREGISTER, AUDIT_NFT_OP_OBJ_RESET, AUDIT_NFT_OP_FLOWTABLE_REGISTER, AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, AUDIT_NFT_OP_SETELEM_RESET, AUDIT_NFT_OP_RULE_RESET, AUDIT_NFT_OP_INVALID, }; extern int __init audit_register_class(int class, unsigned *list); extern int audit_classify_syscall(int abi, unsigned syscall); extern int audit_classify_arch(int arch); /* only for compat system calls */ extern unsigned compat_write_class[]; extern unsigned compat_read_class[]; extern unsigned compat_dir_class[]; extern unsigned compat_chattr_class[]; extern unsigned compat_signal_class[]; /* audit_names->type values */ #define AUDIT_TYPE_UNKNOWN 0 /* we don't know yet */ #define AUDIT_TYPE_NORMAL 1 /* a "normal" audit record */ #define AUDIT_TYPE_PARENT 2 /* a parent audit record */ #define AUDIT_TYPE_CHILD_DELETE 3 /* a child being deleted */ #define AUDIT_TYPE_CHILD_CREATE 4 /* a child being created */ /* maximized args number that audit_socketcall can process */ #define AUDITSC_ARGS 6 /* bit values for ->signal->audit_tty */ #define AUDIT_TTY_ENABLE BIT(0) #define AUDIT_TTY_LOG_PASSWD BIT(1) struct filename; #define AUDIT_OFF 0 #define AUDIT_ON 1 #define AUDIT_LOCKED 2 #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ extern __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...); extern struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type); extern __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...); extern void audit_log_end(struct audit_buffer *ab); extern bool audit_string_contains_control(const char *string, size_t len); extern void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len); extern void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n); extern void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n); extern void audit_log_untrustedstring(struct audit_buffer *ab, const char *string); extern void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path); extern void audit_log_key(struct audit_buffer *ab, char *key); extern void audit_log_path_denied(int type, const char *operation); extern void audit_log_lost(const char *message); extern int audit_log_task_context(struct audit_buffer *ab); extern void audit_log_task_info(struct audit_buffer *ab); extern int audit_update_lsm_rules(void); /* Private API (for audit.c only) */ extern int audit_rule_change(int type, int seq, void *data, size_t datasz); extern int audit_list_rules_send(struct sk_buff *request_skb, int seq); extern int audit_set_loginuid(kuid_t loginuid); static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return tsk->loginuid; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return tsk->sessionid; } extern u32 audit_enabled; extern int audit_signal_info(int sig, struct task_struct *t); #else /* CONFIG_AUDIT */ static inline __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...) { } static inline struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) { return NULL; } static inline __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) { } static inline void audit_log_end(struct audit_buffer *ab) { } static inline void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len) { } static inline void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n) { } static inline void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n) { } static inline void audit_log_untrustedstring(struct audit_buffer *ab, const char *string) { } static inline void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path) { } static inline void audit_log_key(struct audit_buffer *ab, char *key) { } static inline void audit_log_path_denied(int type, const char *operation) { } static inline int audit_log_task_context(struct audit_buffer *ab) { return 0; } static inline void audit_log_task_info(struct audit_buffer *ab) { } static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return INVALID_UID; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return AUDIT_SID_UNSET; } #define audit_enabled AUDIT_OFF static inline int audit_signal_info(int sig, struct task_struct *t) { return 0; } #endif /* CONFIG_AUDIT */ #ifdef CONFIG_AUDIT_COMPAT_GENERIC #define audit_is_compat(arch) (!((arch) & __AUDIT_ARCH_64BIT)) #else #define audit_is_compat(arch) false #endif #define AUDIT_INODE_PARENT 1 /* dentry represents the parent */ #define AUDIT_INODE_HIDDEN 2 /* audit record should be hidden */ #define AUDIT_INODE_NOEVAL 4 /* audit record incomplete */ #ifdef CONFIG_AUDITSYSCALL #include <asm/syscall.h> /* for syscall_get_arch() */ /* These are defined in auditsc.c */ /* Public API */ extern int audit_alloc(struct task_struct *task); extern void __audit_free(struct task_struct *task); extern void __audit_uring_entry(u8 op); extern void __audit_uring_exit(int success, long code); extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); extern struct filename *__audit_reusename(const __user char *uptr); extern void __audit_getname(struct filename *name); extern void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags); extern void __audit_file(const struct file *); extern void __audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type); extern void audit_seccomp(unsigned long syscall, long signr, int code); extern void audit_seccomp_actions_logged(const char *names, const char *old_names, int res); extern void __audit_ptrace(struct task_struct *t); static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { task->audit_context = ctx; } static inline struct audit_context *audit_context(void) { return current->audit_context; } static inline bool audit_dummy_context(void) { void *p = audit_context(); return !p || *(int *)p; } static inline void audit_free(struct task_struct *task) { if (unlikely(task->audit_context)) __audit_free(task); } static inline void audit_uring_entry(u8 op) { /* * We intentionally check audit_context() before audit_enabled as most * Linux systems (as of ~2021) rely on systemd which forces audit to * be enabled regardless of the user's audit configuration. */ if (unlikely(audit_context() && audit_enabled)) __audit_uring_entry(op); } static inline void audit_uring_exit(int success, long code) { if (unlikely(audit_context())) __audit_uring_exit(success, code); } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { if (unlikely(audit_context())) __audit_syscall_entry(major, a0, a1, a2, a3); } static inline void audit_syscall_exit(void *pt_regs) { if (unlikely(audit_context())) { int success = is_syscall_success(pt_regs); long return_code = regs_return_value(pt_regs); __audit_syscall_exit(success, return_code); } } static inline struct filename *audit_reusename(const __user char *name) { if (unlikely(!audit_dummy_context())) return __audit_reusename(name); return NULL; } static inline void audit_getname(struct filename *name) { if (unlikely(!audit_dummy_context())) __audit_getname(name); } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, aflags); } static inline void audit_file(struct file *file) { if (unlikely(!audit_dummy_context())) __audit_file(file); } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, AUDIT_INODE_PARENT | AUDIT_INODE_HIDDEN); } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { if (unlikely(!audit_dummy_context())) __audit_inode_child(parent, dentry, type); } void audit_core_dumps(long signr); static inline void audit_ptrace(struct task_struct *t) { if (unlikely(!audit_dummy_context())) __audit_ptrace(t); } /* Private API (for audit.c only) */ extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); extern void __audit_bprm(struct linux_binprm *bprm); extern int __audit_socketcall(int nargs, unsigned long *args); extern int __audit_sockaddr(int len, void *addr); extern void __audit_fd_pair(int fd1, int fd2); extern void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr); extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout); extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification); extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old); extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); extern void __audit_openat2_how(struct open_how *how); extern void __audit_log_kern_module(char *name); extern void __audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar); extern void __audit_tk_injoffset(struct timespec64 offset); extern void __audit_ntp_log(const struct audit_ntp_data *ad); extern void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp); static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { if (unlikely(!audit_dummy_context())) __audit_ipc_obj(ipcp); } static inline void audit_fd_pair(int fd1, int fd2) { if (unlikely(!audit_dummy_context())) __audit_fd_pair(fd1, fd2); } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { if (unlikely(!audit_dummy_context())) __audit_ipc_set_perm(qbytes, uid, gid, mode); } static inline void audit_bprm(struct linux_binprm *bprm) { if (unlikely(!audit_dummy_context())) __audit_bprm(bprm); } static inline int audit_socketcall(int nargs, unsigned long *args) { if (unlikely(!audit_dummy_context())) return __audit_socketcall(nargs, args); return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { unsigned long a[AUDITSC_ARGS]; int i; if (audit_dummy_context()) return 0; for (i = 0; i < nargs; i++) a[i] = (unsigned long)args[i]; return __audit_socketcall(nargs, a); } static inline int audit_sockaddr(int len, void *addr) { if (unlikely(!audit_dummy_context())) return __audit_sockaddr(len, addr); return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { if (unlikely(!audit_dummy_context())) __audit_mq_open(oflag, mode, attr); } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { if (unlikely(!audit_dummy_context())) __audit_mq_sendrecv(mqdes, msg_len, msg_prio, abs_timeout); } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { if (unlikely(!audit_dummy_context())) __audit_mq_notify(mqdes, notification); } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { if (unlikely(!audit_dummy_context())) __audit_mq_getsetattr(mqdes, mqstat); } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) return __audit_log_bprm_fcaps(bprm, new, old); return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) __audit_log_capset(new, old); } static inline void audit_mmap_fd(int fd, int flags) { if (unlikely(!audit_dummy_context())) __audit_mmap_fd(fd, flags); } static inline void audit_openat2_how(struct open_how *how) { if (unlikely(!audit_dummy_context())) __audit_openat2_how(how); } static inline void audit_log_kern_module(char *name) { if (!audit_dummy_context()) __audit_log_kern_module(name); } static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { if (!audit_dummy_context()) __audit_fanotify(response, friar); } static inline void audit_tk_injoffset(struct timespec64 offset) { /* ignore no-op events */ if (offset.tv_sec == 0 && offset.tv_nsec == 0) return; if (!audit_dummy_context()) __audit_tk_injoffset(offset); } static inline void audit_ntp_init(struct audit_ntp_data *ad) { memset(ad, 0, sizeof(*ad)); } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].oldval = val; } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].newval = val; } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { if (!audit_dummy_context()) __audit_ntp_log(ad); } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { if (audit_enabled) __audit_log_nfcfg(name, af, nentries, op, gfp); } extern int audit_n_rules; extern int audit_signals; #else /* CONFIG_AUDITSYSCALL */ static inline int audit_alloc(struct task_struct *task) { return 0; } static inline void audit_free(struct task_struct *task) { } static inline void audit_uring_entry(u8 op) { } static inline void audit_uring_exit(int success, long code) { } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { } static inline void audit_syscall_exit(void *pt_regs) { } static inline bool audit_dummy_context(void) { return true; } static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { } static inline struct audit_context *audit_context(void) { return NULL; } static inline struct filename *audit_reusename(const __user char *name) { return NULL; } static inline void audit_getname(struct filename *name) { } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { } static inline void audit_file(struct file *file) { } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { } static inline void audit_core_dumps(long signr) { } static inline void audit_seccomp(unsigned long syscall, long signr, int code) { } static inline void audit_seccomp_actions_logged(const char *names, const char *old_names, int res) { } static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { } static inline void audit_bprm(struct linux_binprm *bprm) { } static inline int audit_socketcall(int nargs, unsigned long *args) { return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { return 0; } static inline void audit_fd_pair(int fd1, int fd2) { } static inline int audit_sockaddr(int len, void *addr) { return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { } static inline void audit_mmap_fd(int fd, int flags) { } static inline void audit_openat2_how(struct open_how *how) { } static inline void audit_log_kern_module(char *name) { } static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { } static inline void audit_tk_injoffset(struct timespec64 offset) { } static inline void audit_ntp_init(struct audit_ntp_data *ad) { } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { } static inline void audit_ptrace(struct task_struct *t) { } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { } #define audit_n_rules 0 #define audit_signals 0 #endif /* CONFIG_AUDITSYSCALL */ static inline bool audit_loginuid_set(struct task_struct *tsk) { return uid_valid(audit_get_loginuid(tsk)); } #endif |
| 6 511 17 14 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Flexible mmap layout support * * Based on code by Ingo Molnar and Andi Kleen, copyrighted * as follows: * * Copyright 2003-2009 Red Hat Inc. * All Rights Reserved. * Copyright 2005 Andi Kleen, SUSE Labs. * Copyright 2007 Jiri Kosina, SUSE Labs. */ #include <linux/personality.h> #include <linux/mm.h> #include <linux/random.h> #include <linux/limits.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> #include <linux/compat.h> #include <linux/elf-randomize.h> #include <asm/elf.h> #include <asm/io.h> #include "physaddr.h" struct va_alignment __read_mostly va_align = { .flags = -1, }; unsigned long task_size_32bit(void) { return IA32_PAGE_OFFSET; } unsigned long task_size_64bit(int full_addr_space) { return full_addr_space ? TASK_SIZE_MAX : DEFAULT_MAP_WINDOW; } static unsigned long stack_maxrandom_size(unsigned long task_size) { unsigned long max = 0; if (current->flags & PF_RANDOMIZE) { max = (-1UL) & __STACK_RND_MASK(task_size == task_size_32bit()); max <<= PAGE_SHIFT; } return max; } #ifdef CONFIG_COMPAT # define mmap32_rnd_bits mmap_rnd_compat_bits # define mmap64_rnd_bits mmap_rnd_bits #else # define mmap32_rnd_bits mmap_rnd_bits # define mmap64_rnd_bits mmap_rnd_bits #endif #define SIZE_128M (128 * 1024 * 1024UL) static int mmap_is_legacy(void) { if (current->personality & ADDR_COMPAT_LAYOUT) return 1; return sysctl_legacy_va_layout; } static unsigned long arch_rnd(unsigned int rndbits) { if (!(current->flags & PF_RANDOMIZE)) return 0; return (get_random_long() & ((1UL << rndbits) - 1)) << PAGE_SHIFT; } unsigned long arch_mmap_rnd(void) { return arch_rnd(mmap_is_ia32() ? mmap32_rnd_bits : mmap64_rnd_bits); } static unsigned long mmap_base(unsigned long rnd, unsigned long task_size, struct rlimit *rlim_stack) { unsigned long gap = rlim_stack->rlim_cur; unsigned long pad = stack_maxrandom_size(task_size) + stack_guard_gap; /* Values close to RLIM_INFINITY can overflow. */ if (gap + pad > gap) gap += pad; /* * Top of mmap area (just below the process stack). * Leave an at least ~128 MB hole with possible stack randomization. */ gap = clamp(gap, SIZE_128M, (task_size / 6) * 5); return PAGE_ALIGN(task_size - gap - rnd); } static unsigned long mmap_legacy_base(unsigned long rnd, unsigned long task_size) { return __TASK_UNMAPPED_BASE(task_size) + rnd; } /* * This function, called very early during the creation of a new * process VM image, sets up which VM layout function to use: */ static void arch_pick_mmap_base(unsigned long *base, unsigned long *legacy_base, unsigned long random_factor, unsigned long task_size, struct rlimit *rlim_stack) { *legacy_base = mmap_legacy_base(random_factor, task_size); if (mmap_is_legacy()) *base = *legacy_base; else *base = mmap_base(random_factor, task_size, rlim_stack); } void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { if (mmap_is_legacy()) clear_bit(MMF_TOPDOWN, &mm->flags); else set_bit(MMF_TOPDOWN, &mm->flags); arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base, arch_rnd(mmap64_rnd_bits), task_size_64bit(0), rlim_stack); #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES /* * The mmap syscall mapping base decision depends solely on the * syscall type (64-bit or compat). This applies for 64bit * applications and 32bit applications. The 64bit syscall uses * mmap_base, the compat syscall uses mmap_compat_base. */ arch_pick_mmap_base(&mm->mmap_compat_base, &mm->mmap_compat_legacy_base, arch_rnd(mmap32_rnd_bits), task_size_32bit(), rlim_stack); #endif } unsigned long get_mmap_base(int is_legacy) { struct mm_struct *mm = current->mm; #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES if (in_32bit_syscall()) { return is_legacy ? mm->mmap_compat_legacy_base : mm->mmap_compat_base; } #endif return is_legacy ? mm->mmap_legacy_base : mm->mmap_base; } /** * mmap_address_hint_valid - Validate the address hint of mmap * @addr: Address hint * @len: Mapping length * * Check whether @addr and @addr + @len result in a valid mapping. * * On 32bit this only checks whether @addr + @len is <= TASK_SIZE. * * On 64bit with 5-level page tables another sanity check is required * because mappings requested by mmap(@addr, 0) which cross the 47-bit * virtual address boundary can cause the following theoretical issue: * * An application calls mmap(addr, 0), i.e. without MAP_FIXED, where @addr * is below the border of the 47-bit address space and @addr + @len is * above the border. * * With 4-level paging this request succeeds, but the resulting mapping * address will always be within the 47-bit virtual address space, because * the hint address does not result in a valid mapping and is * ignored. Hence applications which are not prepared to handle virtual * addresses above 47-bit work correctly. * * With 5-level paging this request would be granted and result in a * mapping which crosses the border of the 47-bit virtual address * space. If the application cannot handle addresses above 47-bit this * will lead to misbehaviour and hard to diagnose failures. * * Therefore ignore address hints which would result in a mapping crossing * the 47-bit virtual address boundary. * * Note, that in the same scenario with MAP_FIXED the behaviour is * different. The request with @addr < 47-bit and @addr + @len > 47-bit * fails on a 4-level paging machine but succeeds on a 5-level paging * machine. It is reasonable to expect that an application does not rely on * the failure of such a fixed mapping request, so the restriction is not * applied. */ bool mmap_address_hint_valid(unsigned long addr, unsigned long len) { if (TASK_SIZE - len < addr) return false; return (addr > DEFAULT_MAP_WINDOW) == (addr + len > DEFAULT_MAP_WINDOW); } /* Can we access it for direct reading/writing? Must be RAM: */ int valid_phys_addr_range(phys_addr_t addr, size_t count) { return addr + count - 1 <= __pa(high_memory - 1); } /* Can we access it through mmap? Must be a valid physical address: */ int valid_mmap_phys_addr_range(unsigned long pfn, size_t count) { phys_addr_t addr = (phys_addr_t)pfn << PAGE_SHIFT; return phys_addr_valid(addr + count - 1); } /* * Only allow root to set high MMIO mappings to PROT_NONE. * This prevents an unpriv. user to set them to PROT_NONE and invert * them, then pointing to valid memory for L1TF speculation. * * Note: for locked down kernels may want to disable the root override. */ bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) { if (!boot_cpu_has_bug(X86_BUG_L1TF)) return true; if (!__pte_needs_invert(pgprot_val(prot))) return true; /* If it's real memory always allow */ if (pfn_valid(pfn)) return true; if (pfn >= l1tf_pfn_limit() && !capable(CAP_SYS_ADMIN)) return false; return true; } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2011-2012, Pavel Zubarev <pavel.zubarev@gmail.com> * Copyright 2011-2012, Marco Porsch <marco.porsch@s2005.tu-chemnitz.de> * Copyright 2011-2012, cozybit Inc. * Copyright (C) 2021,2023 Intel Corporation */ #include "ieee80211_i.h" #include "mesh.h" #include "driver-ops.h" /* This is not in the standard. It represents a tolerable tsf drift below * which we do no TSF adjustment. */ #define TOFFSET_MINIMUM_ADJUSTMENT 10 /* This is not in the standard. It is a margin added to the * Toffset setpoint to mitigate TSF overcorrection * introduced by TSF adjustment latency. */ #define TOFFSET_SET_MARGIN 20 /* This is not in the standard. It represents the maximum Toffset jump above * which we'll invalidate the Toffset setpoint and choose a new setpoint. This * could be, for instance, in case a neighbor is restarted and its TSF counter * reset. */ #define TOFFSET_MAXIMUM_ADJUSTMENT 800 /* 0.8 ms */ struct sync_method { u8 method; struct ieee80211_mesh_sync_ops ops; }; /** * mesh_peer_tbtt_adjusting - check if an mp is currently adjusting its TBTT * * @cfg: mesh config element from the mesh peer (or %NULL) * * Returns: If the mesh peer is currently adjusting its TBTT */ static bool mesh_peer_tbtt_adjusting(const struct ieee80211_meshconf_ie *cfg) { return cfg && (cfg->meshconf_cap & IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING); } void mesh_sync_adjust_tsf(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; /* sdata->vif.bss_conf.beacon_int in 1024us units, 0.04% */ u64 beacon_int_fraction = sdata->vif.bss_conf.beacon_int * 1024 / 2500; u64 tsf; u64 tsfdelta; spin_lock_bh(&ifmsh->sync_offset_lock); if (ifmsh->sync_offset_clockdrift_max < beacon_int_fraction) { msync_dbg(sdata, "TSF : max clockdrift=%lld; adjusting\n", (long long) ifmsh->sync_offset_clockdrift_max); tsfdelta = -ifmsh->sync_offset_clockdrift_max; ifmsh->sync_offset_clockdrift_max = 0; } else { msync_dbg(sdata, "TSF : max clockdrift=%lld; adjusting by %llu\n", (long long) ifmsh->sync_offset_clockdrift_max, (unsigned long long) beacon_int_fraction); tsfdelta = -beacon_int_fraction; ifmsh->sync_offset_clockdrift_max -= beacon_int_fraction; } spin_unlock_bh(&ifmsh->sync_offset_lock); if (local->ops->offset_tsf) { drv_offset_tsf(local, sdata, tsfdelta); } else { tsf = drv_get_tsf(local, sdata); if (tsf != -1ULL) drv_set_tsf(local, sdata, tsf + tsfdelta); } } static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, u16 stype, struct ieee80211_mgmt *mgmt, unsigned int len, const struct ieee80211_meshconf_ie *mesh_cfg, struct ieee80211_rx_status *rx_status) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct ieee80211_local *local = sdata->local; struct sta_info *sta; u64 t_t, t_r; WARN_ON(ifmsh->mesh_sp_id != IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET); /* standard mentions only beacons */ if (stype != IEEE80211_STYPE_BEACON) return; /* * Get time when timestamp field was received. If we don't * have rx timestamps, then use current tsf as an approximation. * drv_get_tsf() must be called before entering the rcu-read * section. */ if (ieee80211_have_rx_timestamp(rx_status)) t_r = ieee80211_calculate_rx_timestamp(local, rx_status, len + FCS_LEN, 24); else t_r = drv_get_tsf(local, sdata); rcu_read_lock(); sta = sta_info_get(sdata, mgmt->sa); if (!sta) goto no_sync; /* check offset sync conditions (13.13.2.2.1) * * TODO also sync to * dot11MeshNbrOffsetMaxNeighbor non-peer non-MBSS neighbors */ if (mesh_peer_tbtt_adjusting(mesh_cfg)) { msync_dbg(sdata, "STA %pM : is adjusting TBTT\n", sta->sta.addr); goto no_sync; } /* Timing offset calculation (see 13.13.2.2.2) */ t_t = le64_to_cpu(mgmt->u.beacon.timestamp); sta->mesh->t_offset = t_t - t_r; if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) { s64 t_clockdrift = sta->mesh->t_offset_setpoint - sta->mesh->t_offset; msync_dbg(sdata, "STA %pM : t_offset=%lld, t_offset_setpoint=%lld, t_clockdrift=%lld\n", sta->sta.addr, (long long) sta->mesh->t_offset, (long long) sta->mesh->t_offset_setpoint, (long long) t_clockdrift); if (t_clockdrift > TOFFSET_MAXIMUM_ADJUSTMENT || t_clockdrift < -TOFFSET_MAXIMUM_ADJUSTMENT) { msync_dbg(sdata, "STA %pM : t_clockdrift=%lld too large, setpoint reset\n", sta->sta.addr, (long long) t_clockdrift); clear_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN); goto no_sync; } spin_lock_bh(&ifmsh->sync_offset_lock); if (t_clockdrift > ifmsh->sync_offset_clockdrift_max) ifmsh->sync_offset_clockdrift_max = t_clockdrift; spin_unlock_bh(&ifmsh->sync_offset_lock); } else { sta->mesh->t_offset_setpoint = sta->mesh->t_offset - TOFFSET_SET_MARGIN; set_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN); msync_dbg(sdata, "STA %pM : offset was invalid, t_offset=%lld\n", sta->sta.addr, (long long) sta->mesh->t_offset); } no_sync: rcu_read_unlock(); } static void mesh_sync_offset_adjust_tsf(struct ieee80211_sub_if_data *sdata, struct beacon_data *beacon) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; WARN_ON(ifmsh->mesh_sp_id != IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET); WARN_ON(!rcu_read_lock_held()); spin_lock_bh(&ifmsh->sync_offset_lock); if (ifmsh->sync_offset_clockdrift_max > TOFFSET_MINIMUM_ADJUSTMENT) { /* Since adjusting the tsf here would * require a possibly blocking call * to the driver tsf setter, we punt * the tsf adjustment to the mesh tasklet */ msync_dbg(sdata, "TSF : kicking off TSF adjustment with clockdrift_max=%lld\n", ifmsh->sync_offset_clockdrift_max); set_bit(MESH_WORK_DRIFT_ADJUST, &ifmsh->wrkq_flags); } else { msync_dbg(sdata, "TSF : max clockdrift=%lld; too small to adjust\n", (long long)ifmsh->sync_offset_clockdrift_max); ifmsh->sync_offset_clockdrift_max = 0; } spin_unlock_bh(&ifmsh->sync_offset_lock); } static const struct sync_method sync_methods[] = { { .method = IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET, .ops = { .rx_bcn_presp = &mesh_sync_offset_rx_bcn_presp, .adjust_tsf = &mesh_sync_offset_adjust_tsf, } }, }; const struct ieee80211_mesh_sync_ops *ieee80211_mesh_sync_ops_get(u8 method) { int i; for (i = 0 ; i < ARRAY_SIZE(sync_methods); ++i) { if (sync_methods[i].method == method) return &sync_methods[i].ops; } return NULL; } |
| 35 35 32 32 6 6 32 14 7 32 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 | /* * net/tipc/addr.c: TIPC address utility routines * * Copyright (c) 2000-2006, 2018, Ericsson AB * Copyright (c) 2004-2005, 2010-2011, Wind River Systems * Copyright (c) 2020-2021, Red Hat Inc * All rights reserved. * * 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. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS 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 COPYRIGHT OWNER 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. */ #include "addr.h" #include "core.h" bool tipc_in_scope(bool legacy_format, u32 domain, u32 addr) { if (!domain || (domain == addr)) return true; if (!legacy_format) return false; if (domain == tipc_cluster_mask(addr)) /* domain <Z.C.0> */ return true; if (domain == (addr & TIPC_ZONE_CLUSTER_MASK)) /* domain <Z.C.0> */ return true; if (domain == (addr & TIPC_ZONE_MASK)) /* domain <Z.0.0> */ return true; return false; } void tipc_set_node_id(struct net *net, u8 *id) { struct tipc_net *tn = tipc_net(net); memcpy(tn->node_id, id, NODE_ID_LEN); tipc_nodeid2string(tn->node_id_string, id); tn->trial_addr = hash128to32(id); pr_info("Node identity %s, cluster identity %u\n", tipc_own_id_string(net), tn->net_id); } void tipc_set_node_addr(struct net *net, u32 addr) { struct tipc_net *tn = tipc_net(net); u8 node_id[NODE_ID_LEN] = {0,}; tn->node_addr = addr; if (!tipc_own_id(net)) { sprintf(node_id, "%x", addr); tipc_set_node_id(net, node_id); } tn->trial_addr = addr; tn->addr_trial_end = jiffies; pr_info("Node number set to %u\n", addr); } char *tipc_nodeid2string(char *str, u8 *id) { int i; u8 c; /* Already a string ? */ for (i = 0; i < NODE_ID_LEN; i++) { c = id[i]; if (c >= '0' && c <= '9') continue; if (c >= 'A' && c <= 'Z') continue; if (c >= 'a' && c <= 'z') continue; if (c == '.') continue; if (c == ':') continue; if (c == '_') continue; if (c == '-') continue; if (c == '@') continue; if (c != 0) break; } if (i == NODE_ID_LEN) { memcpy(str, id, NODE_ID_LEN); str[NODE_ID_LEN] = 0; return str; } /* Translate to hex string */ for (i = 0; i < NODE_ID_LEN; i++) sprintf(&str[2 * i], "%02x", id[i]); /* Strip off trailing zeroes */ for (i = NODE_ID_STR_LEN - 2; str[i] == '0'; i--) str[i] = 0; return str; } |
| 23 2 112 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 | #undef TRACE_SYSTEM #define TRACE_SYSTEM bridge #if !defined(_TRACE_BRIDGE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_BRIDGE_H #include <linux/netdevice.h> #include <linux/tracepoint.h> #include "../../../net/bridge/br_private.h" TRACE_EVENT(br_fdb_add, TP_PROTO(struct ndmsg *ndm, struct net_device *dev, const unsigned char *addr, u16 vid, u16 nlh_flags), TP_ARGS(ndm, dev, addr, vid, nlh_flags), TP_STRUCT__entry( __field(u8, ndm_flags) __string(dev, dev->name) __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) __field(u16, nlh_flags) ), TP_fast_assign( __assign_str(dev); memcpy(__entry->addr, addr, ETH_ALEN); __entry->vid = vid; __entry->nlh_flags = nlh_flags; __entry->ndm_flags = ndm->ndm_flags; ), TP_printk("dev %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u nlh_flags %04x ndm_flags %02x", __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid, __entry->nlh_flags, __entry->ndm_flags) ); TRACE_EVENT(br_fdb_external_learn_add, TP_PROTO(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid), TP_ARGS(br, p, addr, vid), TP_STRUCT__entry( __string(br_dev, br->dev->name) __string(dev, p ? p->dev->name : "null") __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) ), TP_fast_assign( __assign_str(br_dev); __assign_str(dev); memcpy(__entry->addr, addr, ETH_ALEN); __entry->vid = vid; ), TP_printk("br_dev %s port %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u", __get_str(br_dev), __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid) ); TRACE_EVENT(fdb_delete, TP_PROTO(struct net_bridge *br, struct net_bridge_fdb_entry *f), TP_ARGS(br, f), TP_STRUCT__entry( __string(br_dev, br->dev->name) __string(dev, f->dst ? f->dst->dev->name : "null") __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) ), TP_fast_assign( __assign_str(br_dev); __assign_str(dev); memcpy(__entry->addr, f->key.addr.addr, ETH_ALEN); __entry->vid = f->key.vlan_id; ), TP_printk("br_dev %s dev %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u", __get_str(br_dev), __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid) ); TRACE_EVENT(br_fdb_update, TP_PROTO(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr, u16 vid, unsigned long flags), TP_ARGS(br, source, addr, vid, flags), TP_STRUCT__entry( __string(br_dev, br->dev->name) __string(dev, source->dev->name) __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) __field(unsigned long, flags) ), TP_fast_assign( __assign_str(br_dev); __assign_str(dev); memcpy(__entry->addr, addr, ETH_ALEN); __entry->vid = vid; __entry->flags = flags; ), TP_printk("br_dev %s source %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u flags 0x%lx", __get_str(br_dev), __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid, __entry->flags) ); TRACE_EVENT(br_mdb_full, TP_PROTO(const struct net_device *dev, const struct br_ip *group), TP_ARGS(dev, group), TP_STRUCT__entry( __string(dev, dev->name) __field(int, af) __field(u16, vid) __array(__u8, src, 16) __array(__u8, grp, 16) __array(__u8, grpmac, ETH_ALEN) /* For af == 0. */ ), TP_fast_assign( struct in6_addr *in6; __assign_str(dev); __entry->vid = group->vid; if (!group->proto) { __entry->af = 0; memset(__entry->src, 0, sizeof(__entry->src)); memset(__entry->grp, 0, sizeof(__entry->grp)); memcpy(__entry->grpmac, group->dst.mac_addr, ETH_ALEN); } else if (group->proto == htons(ETH_P_IP)) { __entry->af = AF_INET; in6 = (struct in6_addr *)__entry->src; ipv6_addr_set_v4mapped(group->src.ip4, in6); in6 = (struct in6_addr *)__entry->grp; ipv6_addr_set_v4mapped(group->dst.ip4, in6); memset(__entry->grpmac, 0, ETH_ALEN); #if IS_ENABLED(CONFIG_IPV6) } else { __entry->af = AF_INET6; in6 = (struct in6_addr *)__entry->src; *in6 = group->src.ip6; in6 = (struct in6_addr *)__entry->grp; *in6 = group->dst.ip6; memset(__entry->grpmac, 0, ETH_ALEN); #endif } ), TP_printk("dev %s af %u src %pI6c grp %pI6c/%pM vid %u", __get_str(dev), __entry->af, __entry->src, __entry->grp, __entry->grpmac, __entry->vid) ); #endif /* _TRACE_BRIDGE_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 1 1 2 2 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 | // SPDX-License-Identifier: GPL-2.0-or-later /* * SPCA500 chip based cameras initialization data * * V4L2 by Jean-Francois Moine <http://moinejf.free.fr> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define MODULE_NAME "spca500" #include "gspca.h" #include "jpeg.h" MODULE_AUTHOR("Michel Xhaard <mxhaard@users.sourceforge.net>"); MODULE_DESCRIPTION("GSPCA/SPCA500 USB Camera Driver"); MODULE_LICENSE("GPL"); #define QUALITY 85 /* specific webcam descriptor */ struct sd { struct gspca_dev gspca_dev; /* !! must be the first item */ char subtype; #define AgfaCl20 0 #define AiptekPocketDV 1 #define BenqDC1016 2 #define CreativePCCam300 3 #define DLinkDSC350 4 #define Gsmartmini 5 #define IntelPocketPCCamera 6 #define KodakEZ200 7 #define LogitechClickSmart310 8 #define LogitechClickSmart510 9 #define LogitechTraveler 10 #define MustekGsmart300 11 #define Optimedia 12 #define PalmPixDC85 13 #define ToptroIndus 14 u8 jpeg_hdr[JPEG_HDR_SZ]; }; static const struct v4l2_pix_format vga_mode[] = { {320, 240, V4L2_PIX_FMT_JPEG, V4L2_FIELD_NONE, .bytesperline = 320, .sizeimage = 320 * 240 * 3 / 8 + 590, .colorspace = V4L2_COLORSPACE_JPEG, .priv = 1}, {640, 480, V4L2_PIX_FMT_JPEG, V4L2_FIELD_NONE, .bytesperline = 640, .sizeimage = 640 * 480 * 3 / 8 + 590, .colorspace = V4L2_COLORSPACE_JPEG, .priv = 0}, }; static const struct v4l2_pix_format sif_mode[] = { {176, 144, V4L2_PIX_FMT_JPEG, V4L2_FIELD_NONE, .bytesperline = 176, .sizeimage = 176 * 144 * 3 / 8 + 590, .colorspace = V4L2_COLORSPACE_JPEG, .priv = 1}, {352, 288, V4L2_PIX_FMT_JPEG, V4L2_FIELD_NONE, .bytesperline = 352, .sizeimage = 352 * 288 * 3 / 8 + 590, .colorspace = V4L2_COLORSPACE_JPEG, .priv = 0}, }; /* Frame packet header offsets for the spca500 */ #define SPCA500_OFFSET_PADDINGLB 2 #define SPCA500_OFFSET_PADDINGHB 3 #define SPCA500_OFFSET_MODE 4 #define SPCA500_OFFSET_IMGWIDTH 5 #define SPCA500_OFFSET_IMGHEIGHT 6 #define SPCA500_OFFSET_IMGMODE 7 #define SPCA500_OFFSET_QTBLINDEX 8 #define SPCA500_OFFSET_FRAMSEQ 9 #define SPCA500_OFFSET_CDSPINFO 10 #define SPCA500_OFFSET_GPIO 11 #define SPCA500_OFFSET_AUGPIO 12 #define SPCA500_OFFSET_DATA 16 static const __u16 spca500_visual_defaults[][3] = { {0x00, 0x0003, 0x816b}, /* SSI not active sync with vsync, * hue (H byte) = 0, * saturation/hue enable, * brightness/contrast enable. */ {0x00, 0x0000, 0x8167}, /* brightness = 0 */ {0x00, 0x0020, 0x8168}, /* contrast = 0 */ {0x00, 0x0003, 0x816b}, /* SSI not active sync with vsync, * hue (H byte) = 0, saturation/hue enable, * brightness/contrast enable. * was 0x0003, now 0x0000. */ {0x00, 0x0000, 0x816a}, /* hue (L byte) = 0 */ {0x00, 0x0020, 0x8169}, /* saturation = 0x20 */ {0x00, 0x0050, 0x8157}, /* edge gain high threshold */ {0x00, 0x0030, 0x8158}, /* edge gain low threshold */ {0x00, 0x0028, 0x8159}, /* edge bandwidth high threshold */ {0x00, 0x000a, 0x815a}, /* edge bandwidth low threshold */ {0x00, 0x0001, 0x8202}, /* clock rate compensation = 1/25 sec/frame */ {0x0c, 0x0004, 0x0000}, /* set interface */ {} }; static const __u16 Clicksmart510_defaults[][3] = { {0x00, 0x00, 0x8211}, {0x00, 0x01, 0x82c0}, {0x00, 0x10, 0x82cb}, {0x00, 0x0f, 0x800d}, {0x00, 0x82, 0x8225}, {0x00, 0x21, 0x8228}, {0x00, 0x00, 0x8203}, {0x00, 0x00, 0x8204}, {0x00, 0x08, 0x8205}, {0x00, 0xf8, 0x8206}, {0x00, 0x28, 0x8207}, {0x00, 0xa0, 0x8208}, {0x00, 0x08, 0x824a}, {0x00, 0x08, 0x8214}, {0x00, 0x80, 0x82c1}, {0x00, 0x00, 0x82c2}, {0x00, 0x00, 0x82ca}, {0x00, 0x80, 0x82c1}, {0x00, 0x04, 0x82c2}, {0x00, 0x00, 0x82ca}, {0x00, 0xfc, 0x8100}, {0x00, 0xfc, 0x8105}, {0x00, 0x30, 0x8101}, {0x00, 0x00, 0x8102}, {0x00, 0x00, 0x8103}, {0x00, 0x66, 0x8107}, {0x00, 0x00, 0x816b}, {0x00, 0x00, 0x8155}, {0x00, 0x01, 0x8156}, {0x00, 0x60, 0x8157}, {0x00, 0x40, 0x8158}, {0x00, 0x0a, 0x8159}, {0x00, 0x06, 0x815a}, {0x00, 0x00, 0x813f}, {0x00, 0x00, 0x8200}, {0x00, 0x19, 0x8201}, {0x00, 0x00, 0x82c1}, {0x00, 0xa0, 0x82c2}, {0x00, 0x00, 0x82ca}, {0x00, 0x00, 0x8117}, {0x00, 0x00, 0x8118}, {0x00, 0x65, 0x8119}, {0x00, 0x00, 0x811a}, {0x00, 0x00, 0x811b}, {0x00, 0x55, 0x811c}, {0x00, 0x65, 0x811d}, {0x00, 0x55, 0x811e}, {0x00, 0x16, 0x811f}, {0x00, 0x19, 0x8120}, {0x00, 0x80, 0x8103}, {0x00, 0x83, 0x816b}, {0x00, 0x25, 0x8168}, {0x00, 0x01, 0x820f}, {0x00, 0xff, 0x8115}, {0x00, 0x48, 0x8116}, {0x00, 0x50, 0x8151}, {0x00, 0x40, 0x8152}, {0x00, 0x78, 0x8153}, {0x00, 0x40, 0x8154}, {0x00, 0x00, 0x8167}, {0x00, 0x20, 0x8168}, {0x00, 0x00, 0x816a}, {0x00, 0x03, 0x816b}, {0x00, 0x20, 0x8169}, {0x00, 0x60, 0x8157}, {0x00, 0x00, 0x8190}, {0x00, 0x00, 0x81a1}, {0x00, 0x00, 0x81b2}, {0x00, 0x27, 0x8191}, {0x00, 0x27, 0x81a2}, {0x00, 0x27, 0x81b3}, {0x00, 0x4b, 0x8192}, {0x00, 0x4b, 0x81a3}, {0x00, 0x4b, 0x81b4}, {0x00, 0x66, 0x8193}, {0x00, 0x66, 0x81a4}, {0x00, 0x66, 0x81b5}, {0x00, 0x79, 0x8194}, {0x00, 0x79, 0x81a5}, {0x00, 0x79, 0x81b6}, {0x00, 0x8a, 0x8195}, {0x00, 0x8a, 0x81a6}, {0x00, 0x8a, 0x81b7}, {0x00, 0x9b, 0x8196}, {0x00, 0x9b, 0x81a7}, {0x00, 0x9b, 0x81b8}, {0x00, 0xa6, 0x8197}, {0x00, 0xa6, 0x81a8}, {0x00, 0xa6, 0x81b9}, {0x00, 0xb2, 0x8198}, {0x00, 0xb2, 0x81a9}, {0x00, 0xb2, 0x81ba}, {0x00, 0xbe, 0x8199}, {0x00, 0xbe, 0x81aa}, {0x00, 0xbe, 0x81bb}, {0x00, 0xc8, 0x819a}, {0x00, 0xc8, 0x81ab}, {0x00, 0xc8, 0x81bc}, {0x00, 0xd2, 0x819b}, {0x00, 0xd2, 0x81ac}, {0x00, 0xd2, 0x81bd}, {0x00, 0xdb, 0x819c}, {0x00, 0xdb, 0x81ad}, {0x00, 0xdb, 0x81be}, {0x00, 0xe4, 0x819d}, {0x00, 0xe4, 0x81ae}, {0x00, 0xe4, 0x81bf}, {0x00, 0xed, 0x819e}, {0x00, 0xed, 0x81af}, {0x00, 0xed, 0x81c0}, {0x00, 0xf7, 0x819f}, {0x00, 0xf7, 0x81b0}, {0x00, 0xf7, 0x81c1}, {0x00, 0xff, 0x81a0}, {0x00, 0xff, 0x81b1}, {0x00, 0xff, 0x81c2}, {0x00, 0x03, 0x8156}, {0x00, 0x00, 0x8211}, {0x00, 0x20, 0x8168}, {0x00, 0x01, 0x8202}, {0x00, 0x30, 0x8101}, {0x00, 0x00, 0x8111}, {0x00, 0x00, 0x8112}, {0x00, 0x00, 0x8113}, {0x00, 0x00, 0x8114}, {} }; static const __u8 qtable_creative_pccam[2][64] = { { /* Q-table Y-components */ 0x05, 0x03, 0x03, 0x05, 0x07, 0x0c, 0x0f, 0x12, 0x04, 0x04, 0x04, 0x06, 0x08, 0x11, 0x12, 0x11, 0x04, 0x04, 0x05, 0x07, 0x0c, 0x11, 0x15, 0x11, 0x04, 0x05, 0x07, 0x09, 0x0f, 0x1a, 0x18, 0x13, 0x05, 0x07, 0x0b, 0x11, 0x14, 0x21, 0x1f, 0x17, 0x07, 0x0b, 0x11, 0x13, 0x18, 0x1f, 0x22, 0x1c, 0x0f, 0x13, 0x17, 0x1a, 0x1f, 0x24, 0x24, 0x1e, 0x16, 0x1c, 0x1d, 0x1d, 0x22, 0x1e, 0x1f, 0x1e}, { /* Q-table C-components */ 0x05, 0x05, 0x07, 0x0e, 0x1e, 0x1e, 0x1e, 0x1e, 0x05, 0x06, 0x08, 0x14, 0x1e, 0x1e, 0x1e, 0x1e, 0x07, 0x08, 0x11, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x0e, 0x14, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e} }; static const __u8 qtable_kodak_ez200[2][64] = { { /* Q-table Y-components */ 0x02, 0x01, 0x01, 0x02, 0x02, 0x04, 0x05, 0x06, 0x01, 0x01, 0x01, 0x02, 0x03, 0x06, 0x06, 0x06, 0x01, 0x01, 0x02, 0x02, 0x04, 0x06, 0x07, 0x06, 0x01, 0x02, 0x02, 0x03, 0x05, 0x09, 0x08, 0x06, 0x02, 0x02, 0x04, 0x06, 0x07, 0x0b, 0x0a, 0x08, 0x02, 0x04, 0x06, 0x06, 0x08, 0x0a, 0x0b, 0x09, 0x05, 0x06, 0x08, 0x09, 0x0a, 0x0c, 0x0c, 0x0a, 0x07, 0x09, 0x0a, 0x0a, 0x0b, 0x0a, 0x0a, 0x0a}, { /* Q-table C-components */ 0x02, 0x02, 0x02, 0x05, 0x0a, 0x0a, 0x0a, 0x0a, 0x02, 0x02, 0x03, 0x07, 0x0a, 0x0a, 0x0a, 0x0a, 0x02, 0x03, 0x06, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x05, 0x07, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a, 0x0a} }; static const __u8 qtable_pocketdv[2][64] = { { /* Q-table Y-components start registers 0x8800 */ 0x06, 0x04, 0x04, 0x06, 0x0a, 0x10, 0x14, 0x18, 0x05, 0x05, 0x06, 0x08, 0x0a, 0x17, 0x18, 0x16, 0x06, 0x05, 0x06, 0x0a, 0x10, 0x17, 0x1c, 0x16, 0x06, 0x07, 0x09, 0x0c, 0x14, 0x23, 0x20, 0x19, 0x07, 0x09, 0x0f, 0x16, 0x1b, 0x2c, 0x29, 0x1f, 0x0a, 0x0e, 0x16, 0x1a, 0x20, 0x2a, 0x2d, 0x25, 0x14, 0x1a, 0x1f, 0x23, 0x29, 0x30, 0x30, 0x28, 0x1d, 0x25, 0x26, 0x27, 0x2d, 0x28, 0x29, 0x28, }, { /* Q-table C-components start registers 0x8840 */ 0x07, 0x07, 0x0a, 0x13, 0x28, 0x28, 0x28, 0x28, 0x07, 0x08, 0x0a, 0x1a, 0x28, 0x28, 0x28, 0x28, 0x0a, 0x0a, 0x16, 0x28, 0x28, 0x28, 0x28, 0x28, 0x13, 0x1a, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28, 0x28} }; /* read 'len' bytes to gspca_dev->usb_buf */ static void reg_r(struct gspca_dev *gspca_dev, __u16 index, __u16 length) { usb_control_msg(gspca_dev->dev, usb_rcvctrlpipe(gspca_dev->dev, 0), 0, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, /* value */ index, gspca_dev->usb_buf, length, 500); } static int reg_w(struct gspca_dev *gspca_dev, __u16 req, __u16 index, __u16 value) { int ret; gspca_dbg(gspca_dev, D_USBO, "reg write: [0x%02x] = 0x%02x\n", index, value); ret = usb_control_msg(gspca_dev->dev, usb_sndctrlpipe(gspca_dev->dev, 0), req, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, NULL, 0, 500); if (ret < 0) pr_err("reg write: error %d\n", ret); return ret; } /* returns: negative is error, pos or zero is data */ static int reg_r_12(struct gspca_dev *gspca_dev, __u16 req, /* bRequest */ __u16 index, /* wIndex */ __u16 length) /* wLength (1 or 2 only) */ { int ret; gspca_dev->usb_buf[1] = 0; ret = usb_control_msg(gspca_dev->dev, usb_rcvctrlpipe(gspca_dev->dev, 0), req, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, /* value */ index, gspca_dev->usb_buf, length, 500); /* timeout */ if (ret < 0) { pr_err("reg_r_12 err %d\n", ret); return ret; } return (gspca_dev->usb_buf[1] << 8) + gspca_dev->usb_buf[0]; } /* * Simple function to wait for a given 8-bit value to be returned from * a reg_read call. * Returns: negative is error or timeout, zero is success. */ static int reg_r_wait(struct gspca_dev *gspca_dev, __u16 reg, __u16 index, __u16 value) { int ret, cnt = 20; while (--cnt > 0) { ret = reg_r_12(gspca_dev, reg, index, 1); if (ret == value) return 0; msleep(50); } return -EIO; } static int write_vector(struct gspca_dev *gspca_dev, const __u16 data[][3]) { int ret, i = 0; while (data[i][0] != 0 || data[i][1] != 0 || data[i][2] != 0) { ret = reg_w(gspca_dev, data[i][0], data[i][2], data[i][1]); if (ret < 0) return ret; i++; } return 0; } static int spca50x_setup_qtable(struct gspca_dev *gspca_dev, unsigned int request, unsigned int ybase, unsigned int cbase, const __u8 qtable[2][64]) { int i, err; /* loop over y components */ for (i = 0; i < 64; i++) { err = reg_w(gspca_dev, request, ybase + i, qtable[0][i]); if (err < 0) return err; } /* loop over c components */ for (i = 0; i < 64; i++) { err = reg_w(gspca_dev, request, cbase + i, qtable[1][i]); if (err < 0) return err; } return 0; } static void spca500_ping310(struct gspca_dev *gspca_dev) { reg_r(gspca_dev, 0x0d04, 2); gspca_dbg(gspca_dev, D_STREAM, "ClickSmart310 ping 0x0d04 0x%02x 0x%02x\n", gspca_dev->usb_buf[0], gspca_dev->usb_buf[1]); } static void spca500_clksmart310_init(struct gspca_dev *gspca_dev) { reg_r(gspca_dev, 0x0d05, 2); gspca_dbg(gspca_dev, D_STREAM, "ClickSmart310 init 0x0d05 0x%02x 0x%02x\n", gspca_dev->usb_buf[0], gspca_dev->usb_buf[1]); reg_w(gspca_dev, 0x00, 0x8167, 0x5a); spca500_ping310(gspca_dev); reg_w(gspca_dev, 0x00, 0x8168, 0x22); reg_w(gspca_dev, 0x00, 0x816a, 0xc0); reg_w(gspca_dev, 0x00, 0x816b, 0x0b); reg_w(gspca_dev, 0x00, 0x8169, 0x25); reg_w(gspca_dev, 0x00, 0x8157, 0x5b); reg_w(gspca_dev, 0x00, 0x8158, 0x5b); reg_w(gspca_dev, 0x00, 0x813f, 0x03); reg_w(gspca_dev, 0x00, 0x8151, 0x4a); reg_w(gspca_dev, 0x00, 0x8153, 0x78); reg_w(gspca_dev, 0x00, 0x0d01, 0x04); /* 00 for adjust shutter */ reg_w(gspca_dev, 0x00, 0x0d02, 0x01); reg_w(gspca_dev, 0x00, 0x8169, 0x25); reg_w(gspca_dev, 0x00, 0x0d01, 0x02); } static void spca500_setmode(struct gspca_dev *gspca_dev, __u8 xmult, __u8 ymult) { int mode; /* set x multiplier */ reg_w(gspca_dev, 0, 0x8001, xmult); /* set y multiplier */ reg_w(gspca_dev, 0, 0x8002, ymult); /* use compressed mode, VGA, with mode specific subsample */ mode = gspca_dev->cam.cam_mode[(int) gspca_dev->curr_mode].priv; reg_w(gspca_dev, 0, 0x8003, mode << 4); } static int spca500_full_reset(struct gspca_dev *gspca_dev) { int err; /* send the reset command */ err = reg_w(gspca_dev, 0xe0, 0x0001, 0x0000); if (err < 0) return err; /* wait for the reset to complete */ err = reg_r_wait(gspca_dev, 0x06, 0x0000, 0x0000); if (err < 0) return err; err = reg_w(gspca_dev, 0xe0, 0x0000, 0x0000); if (err < 0) return err; err = reg_r_wait(gspca_dev, 0x06, 0, 0); if (err < 0) { gspca_err(gspca_dev, "reg_r_wait() failed\n"); return err; } /* all ok */ return 0; } /* Synchro the Bridge with sensor */ /* Maybe that will work on all spca500 chip */ /* because i only own a clicksmart310 try for that chip */ /* using spca50x_set_packet_size() cause an Ooops here */ /* usb_set_interface from kernel 2.6.x clear all the urb stuff */ /* up-port the same feature as in 2.4.x kernel */ static int spca500_synch310(struct gspca_dev *gspca_dev) { if (usb_set_interface(gspca_dev->dev, gspca_dev->iface, 0) < 0) { gspca_err(gspca_dev, "Set packet size: set interface error\n"); goto error; } spca500_ping310(gspca_dev); reg_r(gspca_dev, 0x0d00, 1); /* need alt setting here */ gspca_dbg(gspca_dev, D_PACK, "ClickSmart310 sync alt: %d\n", gspca_dev->alt); /* Windoze use pipe with altsetting 6 why 7 here */ if (usb_set_interface(gspca_dev->dev, gspca_dev->iface, gspca_dev->alt) < 0) { gspca_err(gspca_dev, "Set packet size: set interface error\n"); goto error; } return 0; error: return -EBUSY; } static void spca500_reinit(struct gspca_dev *gspca_dev) { int err; __u8 Data; /* some unknown command from Aiptek pocket dv and family300 */ reg_w(gspca_dev, 0x00, 0x0d01, 0x01); reg_w(gspca_dev, 0x00, 0x0d03, 0x00); reg_w(gspca_dev, 0x00, 0x0d02, 0x01); /* enable drop packet */ reg_w(gspca_dev, 0x00, 0x850a, 0x0001); err = spca50x_setup_qtable(gspca_dev, 0x00, 0x8800, 0x8840, qtable_pocketdv); if (err < 0) gspca_err(gspca_dev, "spca50x_setup_qtable failed on init\n"); /* set qtable index */ reg_w(gspca_dev, 0x00, 0x8880, 2); /* family cam Quicksmart stuff */ reg_w(gspca_dev, 0x00, 0x800a, 0x00); /* Set agc transfer: synced between frames */ reg_w(gspca_dev, 0x00, 0x820f, 0x01); /* Init SDRAM - needed for SDRAM access */ reg_w(gspca_dev, 0x00, 0x870a, 0x04); /*Start init sequence or stream */ reg_w(gspca_dev, 0, 0x8003, 0x00); /* switch to video camera mode */ reg_w(gspca_dev, 0x00, 0x8000, 0x0004); msleep(2000); if (reg_r_wait(gspca_dev, 0, 0x8000, 0x44) != 0) { reg_r(gspca_dev, 0x816b, 1); Data = gspca_dev->usb_buf[0]; reg_w(gspca_dev, 0x00, 0x816b, Data); } } /* this function is called at probe time */ static int sd_config(struct gspca_dev *gspca_dev, const struct usb_device_id *id) { struct sd *sd = (struct sd *) gspca_dev; struct cam *cam; cam = &gspca_dev->cam; sd->subtype = id->driver_info; if (sd->subtype != LogitechClickSmart310) { cam->cam_mode = vga_mode; cam->nmodes = ARRAY_SIZE(vga_mode); } else { cam->cam_mode = sif_mode; cam->nmodes = ARRAY_SIZE(sif_mode); } return 0; } /* this function is called at probe and resume time */ static int sd_init(struct gspca_dev *gspca_dev) { struct sd *sd = (struct sd *) gspca_dev; /* initialisation of spca500 based cameras is deferred */ gspca_dbg(gspca_dev, D_STREAM, "SPCA500 init\n"); if (sd->subtype == LogitechClickSmart310) spca500_clksmart310_init(gspca_dev); /* else spca500_initialise(gspca_dev); */ gspca_dbg(gspca_dev, D_STREAM, "SPCA500 init done\n"); return 0; } static int sd_start(struct gspca_dev *gspca_dev) { struct sd *sd = (struct sd *) gspca_dev; int err; __u8 Data; __u8 xmult, ymult; /* create the JPEG header */ jpeg_define(sd->jpeg_hdr, gspca_dev->pixfmt.height, gspca_dev->pixfmt.width, 0x22); /* JPEG 411 */ jpeg_set_qual(sd->jpeg_hdr, QUALITY); if (sd->subtype == LogitechClickSmart310) { xmult = 0x16; ymult = 0x12; } else { xmult = 0x28; ymult = 0x1e; } /* is there a sensor here ? */ reg_r(gspca_dev, 0x8a04, 1); gspca_dbg(gspca_dev, D_STREAM, "Spca500 Sensor Address 0x%02x\n", gspca_dev->usb_buf[0]); gspca_dbg(gspca_dev, D_STREAM, "Spca500 curr_mode: %d Xmult: 0x%02x, Ymult: 0x%02x", gspca_dev->curr_mode, xmult, ymult); /* setup qtable */ switch (sd->subtype) { case LogitechClickSmart310: spca500_setmode(gspca_dev, xmult, ymult); /* enable drop packet */ reg_w(gspca_dev, 0x00, 0x850a, 0x0001); reg_w(gspca_dev, 0x00, 0x8880, 3); err = spca50x_setup_qtable(gspca_dev, 0x00, 0x8800, 0x8840, qtable_creative_pccam); if (err < 0) gspca_err(gspca_dev, "spca50x_setup_qtable failed\n"); /* Init SDRAM - needed for SDRAM access */ reg_w(gspca_dev, 0x00, 0x870a, 0x04); /* switch to video camera mode */ reg_w(gspca_dev, 0x00, 0x8000, 0x0004); msleep(500); if (reg_r_wait(gspca_dev, 0, 0x8000, 0x44) != 0) gspca_err(gspca_dev, "reg_r_wait() failed\n"); reg_r(gspca_dev, 0x816b, 1); Data = gspca_dev->usb_buf[0]; reg_w(gspca_dev, 0x00, 0x816b, Data); spca500_synch310(gspca_dev); write_vector(gspca_dev, spca500_visual_defaults); spca500_setmode(gspca_dev, xmult, ymult); /* enable drop packet */ err = reg_w(gspca_dev, 0x00, 0x850a, 0x0001); if (err < 0) gspca_err(gspca_dev, "failed to enable drop packet\n"); reg_w(gspca_dev, 0x00, 0x8880, 3); err = spca50x_setup_qtable(gspca_dev, 0x00, 0x8800, 0x8840, qtable_creative_pccam); if (err < 0) gspca_err(gspca_dev, "spca50x_setup_qtable failed\n"); /* Init SDRAM - needed for SDRAM access */ reg_w(gspca_dev, 0x00, 0x870a, 0x04); /* switch to video camera mode */ reg_w(gspca_dev, 0x00, 0x8000, 0x0004); if (reg_r_wait(gspca_dev, 0, 0x8000, 0x44) != 0) gspca_err(gspca_dev, "reg_r_wait() failed\n"); reg_r(gspca_dev, 0x816b, 1); Data = gspca_dev->usb_buf[0]; reg_w(gspca_dev, 0x00, 0x816b, Data); break; case CreativePCCam300: /* Creative PC-CAM 300 640x480 CCD */ case IntelPocketPCCamera: /* FIXME: Temporary fix for * Intel Pocket PC Camera * - NWG (Sat 29th March 2003) */ /* do a full reset */ err = spca500_full_reset(gspca_dev); if (err < 0) gspca_err(gspca_dev, "spca500_full_reset failed\n"); /* enable drop packet */ err = reg_w(gspca_dev, 0x00, 0x850a, 0x0001); if (err < 0) gspca_err(gspca_dev, "failed to enable drop packet\n"); reg_w(gspca_dev, 0x00, 0x8880, 3); err = spca50x_setup_qtable(gspca_dev, 0x00, 0x8800, 0x8840, qtable_creative_pccam); if (err < 0) gspca_err(gspca_dev, "spca50x_setup_qtable failed\n"); spca500_setmode(gspca_dev, xmult, ymult); reg_w(gspca_dev, 0x20, 0x0001, 0x0004); /* switch to video camera mode */ reg_w(gspca_dev, 0x00, 0x8000, 0x0004); if (reg_r_wait(gspca_dev, 0, 0x8000, 0x44) != 0) gspca_err(gspca_dev, "reg_r_wait() failed\n"); reg_r(gspca_dev, 0x816b, 1); Data = gspca_dev->usb_buf[0]; reg_w(gspca_dev, 0x00, 0x816b, Data); /* write_vector(gspca_dev, spca500_visual_defaults); */ break; case KodakEZ200: /* Kodak EZ200 */ /* do a full reset */ err = spca500_full_reset(gspca_dev); if (err < 0) gspca_err(gspca_dev, "spca500_full_reset failed\n"); /* enable drop packet */ reg_w(gspca_dev, 0x00, 0x850a, 0x0001); reg_w(gspca_dev, 0x00, 0x8880, 0); err = spca50x_setup_qtable(gspca_dev, 0x00, 0x8800, 0x8840, qtable_kodak_ez200); if (err < 0) gspca_err(gspca_dev, "spca50x_setup_qtable failed\n"); spca500_setmode(gspca_dev, xmult, ymult); reg_w(gspca_dev, 0x20, 0x0001, 0x0004); /* switch to video camera mode */ reg_w(gspca_dev, 0x00, 0x8000, 0x0004); if (reg_r_wait(gspca_dev, 0, 0x8000, 0x44) != 0) gspca_err(gspca_dev, "reg_r_wait() failed\n"); reg_r(gspca_dev, 0x816b, 1); Data = gspca_dev->usb_buf[0]; reg_w(gspca_dev, 0x00, 0x816b, Data); /* write_vector(gspca_dev, spca500_visual_defaults); */ break; case BenqDC1016: case DLinkDSC350: /* FamilyCam 300 */ case AiptekPocketDV: /* Aiptek PocketDV */ case Gsmartmini: /*Mustek Gsmart Mini */ case MustekGsmart300: /* Mustek Gsmart 300 */ case PalmPixDC85: case Optimedia: case ToptroIndus: case AgfaCl20: spca500_reinit(gspca_dev); reg_w(gspca_dev, 0x00, 0x0d01, 0x01); /* enable drop packet */ reg_w(gspca_dev, 0x00, 0x850a, 0x0001); err = spca50x_setup_qtable(gspca_dev, 0x00, 0x8800, 0x8840, qtable_pocketdv); if (err < 0) gspca_err(gspca_dev, "spca50x_setup_qtable failed\n"); reg_w(gspca_dev, 0x00, 0x8880, 2); /* familycam Quicksmart pocketDV stuff */ reg_w(gspca_dev, 0x00, 0x800a, 0x00); /* Set agc transfer: synced between frames */ reg_w(gspca_dev, 0x00, 0x820f, 0x01); /* Init SDRAM - needed for SDRAM access */ reg_w(gspca_dev, 0x00, 0x870a, 0x04); spca500_setmode(gspca_dev, xmult, ymult); /* switch to video camera mode */ reg_w(gspca_dev, 0x00, 0x8000, 0x0004); reg_r_wait(gspca_dev, 0, 0x8000, 0x44); reg_r(gspca_dev, 0x816b, 1); Data = gspca_dev->usb_buf[0]; reg_w(gspca_dev, 0x00, 0x816b, Data); break; case LogitechTraveler: case LogitechClickSmart510: reg_w(gspca_dev, 0x02, 0x00, 0x00); /* enable drop packet */ reg_w(gspca_dev, 0x00, 0x850a, 0x0001); err = spca50x_setup_qtable(gspca_dev, 0x00, 0x8800, 0x8840, qtable_creative_pccam); if (err < 0) gspca_err(gspca_dev, "spca50x_setup_qtable failed\n"); reg_w(gspca_dev, 0x00, 0x8880, 3); reg_w(gspca_dev, 0x00, 0x800a, 0x00); /* Init SDRAM - needed for SDRAM access */ reg_w(gspca_dev, 0x00, 0x870a, 0x04); spca500_setmode(gspca_dev, xmult, ymult); /* switch to video camera mode */ reg_w(gspca_dev, 0x00, 0x8000, 0x0004); reg_r_wait(gspca_dev, 0, 0x8000, 0x44); reg_r(gspca_dev, 0x816b, 1); Data = gspca_dev->usb_buf[0]; reg_w(gspca_dev, 0x00, 0x816b, Data); write_vector(gspca_dev, Clicksmart510_defaults); break; } return 0; } static void sd_stopN(struct gspca_dev *gspca_dev) { reg_w(gspca_dev, 0, 0x8003, 0x00); /* switch to video camera mode */ reg_w(gspca_dev, 0x00, 0x8000, 0x0004); reg_r(gspca_dev, 0x8000, 1); gspca_dbg(gspca_dev, D_STREAM, "stop SPCA500 done reg8000: 0x%2x\n", gspca_dev->usb_buf[0]); } static void sd_pkt_scan(struct gspca_dev *gspca_dev, u8 *data, /* isoc packet */ int len) /* iso packet length */ { struct sd *sd = (struct sd *) gspca_dev; int i; static __u8 ffd9[] = {0xff, 0xd9}; /* frames are jpeg 4.1.1 without 0xff escape */ if (data[0] == 0xff) { if (data[1] != 0x01) { /* drop packet */ /* gspca_dev->last_packet_type = DISCARD_PACKET; */ return; } gspca_frame_add(gspca_dev, LAST_PACKET, ffd9, 2); /* put the JPEG header in the new frame */ gspca_frame_add(gspca_dev, FIRST_PACKET, sd->jpeg_hdr, JPEG_HDR_SZ); data += SPCA500_OFFSET_DATA; len -= SPCA500_OFFSET_DATA; } else { data += 1; len -= 1; } /* add 0x00 after 0xff */ i = 0; do { if (data[i] == 0xff) { gspca_frame_add(gspca_dev, INTER_PACKET, data, i + 1); len -= i; data += i; *data = 0x00; i = 0; } i++; } while (i < len); gspca_frame_add(gspca_dev, INTER_PACKET, data, len); } static void setbrightness(struct gspca_dev *gspca_dev, s32 val) { reg_w(gspca_dev, 0x00, 0x8167, (__u8) (val - 128)); } static void setcontrast(struct gspca_dev *gspca_dev, s32 val) { reg_w(gspca_dev, 0x00, 0x8168, val); } static void setcolors(struct gspca_dev *gspca_dev, s32 val) { reg_w(gspca_dev, 0x00, 0x8169, val); } static int sd_s_ctrl(struct v4l2_ctrl *ctrl) { struct gspca_dev *gspca_dev = container_of(ctrl->handler, struct gspca_dev, ctrl_handler); gspca_dev->usb_err = 0; if (!gspca_dev->streaming) return 0; switch (ctrl->id) { case V4L2_CID_BRIGHTNESS: setbrightness(gspca_dev, ctrl->val); break; case V4L2_CID_CONTRAST: setcontrast(gspca_dev, ctrl->val); break; case V4L2_CID_SATURATION: setcolors(gspca_dev, ctrl->val); break; } return gspca_dev->usb_err; } static const struct v4l2_ctrl_ops sd_ctrl_ops = { .s_ctrl = sd_s_ctrl, }; static int sd_init_controls(struct gspca_dev *gspca_dev) { struct v4l2_ctrl_handler *hdl = &gspca_dev->ctrl_handler; gspca_dev->vdev.ctrl_handler = hdl; v4l2_ctrl_handler_init(hdl, 3); v4l2_ctrl_new_std(hdl, &sd_ctrl_ops, V4L2_CID_BRIGHTNESS, 0, 255, 1, 127); v4l2_ctrl_new_std(hdl, &sd_ctrl_ops, V4L2_CID_CONTRAST, 0, 63, 1, 31); v4l2_ctrl_new_std(hdl, &sd_ctrl_ops, V4L2_CID_SATURATION, 0, 63, 1, 31); if (hdl->error) { pr_err("Could not initialize controls\n"); return hdl->error; } return 0; } /* sub-driver description */ static const struct sd_desc sd_desc = { .name = MODULE_NAME, .config = sd_config, .init = sd_init, .init_controls = sd_init_controls, .start = sd_start, .stopN = sd_stopN, .pkt_scan = sd_pkt_scan, }; /* -- module initialisation -- */ static const struct usb_device_id device_table[] = { {USB_DEVICE(0x040a, 0x0300), .driver_info = KodakEZ200}, {USB_DEVICE(0x041e, 0x400a), .driver_info = CreativePCCam300}, {USB_DEVICE(0x046d, 0x0890), .driver_info = LogitechTraveler}, {USB_DEVICE(0x046d, 0x0900), .driver_info = LogitechClickSmart310}, {USB_DEVICE(0x046d, 0x0901), .driver_info = LogitechClickSmart510}, {USB_DEVICE(0x04a5, 0x300c), .driver_info = BenqDC1016}, {USB_DEVICE(0x04fc, 0x7333), .driver_info = PalmPixDC85}, {USB_DEVICE(0x055f, 0xc200), .driver_info = MustekGsmart300}, {USB_DEVICE(0x055f, 0xc220), .driver_info = Gsmartmini}, {USB_DEVICE(0x06bd, 0x0404), .driver_info = AgfaCl20}, {USB_DEVICE(0x06be, 0x0800), .driver_info = Optimedia}, {USB_DEVICE(0x084d, 0x0003), .driver_info = DLinkDSC350}, {USB_DEVICE(0x08ca, 0x0103), .driver_info = AiptekPocketDV}, {USB_DEVICE(0x2899, 0x012c), .driver_info = ToptroIndus}, {USB_DEVICE(0x8086, 0x0630), .driver_info = IntelPocketPCCamera}, {} }; MODULE_DEVICE_TABLE(usb, device_table); /* -- device connect -- */ static int sd_probe(struct usb_interface *intf, const struct usb_device_id *id) { return gspca_dev_probe(intf, id, &sd_desc, sizeof(struct sd), THIS_MODULE); } static struct usb_driver sd_driver = { .name = MODULE_NAME, .id_table = device_table, .probe = sd_probe, .disconnect = gspca_disconnect, #ifdef CONFIG_PM .suspend = gspca_suspend, .resume = gspca_resume, .reset_resume = gspca_resume, #endif }; module_usb_driver(sd_driver); |
| 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 | #ifndef __DRM_VMA_MANAGER_H__ #define __DRM_VMA_MANAGER_H__ /* * Copyright (c) 2013 David Herrmann <dh.herrmann@gmail.com> * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), * to deal in the Software without restriction, including without limitation * the rights to use, copy, modify, merge, publish, distribute, sublicense, * and/or sell copies of the Software, and to permit persons to whom the * Software is furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice shall be included in * all copies or substantial portions of the Software. * * 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 COPYRIGHT HOLDER(S) OR AUTHOR(S) 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 <drm/drm_mm.h> #include <linux/mm.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/types.h> /* We make up offsets for buffer objects so we can recognize them at * mmap time. pgoff in mmap is an unsigned long, so we need to make sure * that the faked up offset will fit */ #if BITS_PER_LONG == 64 #define DRM_FILE_PAGE_OFFSET_START ((0xFFFFFFFFUL >> PAGE_SHIFT) + 1) #define DRM_FILE_PAGE_OFFSET_SIZE ((0xFFFFFFFFUL >> PAGE_SHIFT) * 256) #else #define DRM_FILE_PAGE_OFFSET_START ((0xFFFFFFFUL >> PAGE_SHIFT) + 1) #define DRM_FILE_PAGE_OFFSET_SIZE ((0xFFFFFFFUL >> PAGE_SHIFT) * 16) #endif struct drm_file; struct drm_vma_offset_file { struct rb_node vm_rb; struct drm_file *vm_tag; unsigned long vm_count; }; struct drm_vma_offset_node { rwlock_t vm_lock; struct drm_mm_node vm_node; struct rb_root vm_files; void *driver_private; }; struct drm_vma_offset_manager { rwlock_t vm_lock; struct drm_mm vm_addr_space_mm; }; void drm_vma_offset_manager_init(struct drm_vma_offset_manager *mgr, unsigned long page_offset, unsigned long size); void drm_vma_offset_manager_destroy(struct drm_vma_offset_manager *mgr); struct drm_vma_offset_node *drm_vma_offset_lookup_locked(struct drm_vma_offset_manager *mgr, unsigned long start, unsigned long pages); int drm_vma_offset_add(struct drm_vma_offset_manager *mgr, struct drm_vma_offset_node *node, unsigned long pages); void drm_vma_offset_remove(struct drm_vma_offset_manager *mgr, struct drm_vma_offset_node *node); int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag); int drm_vma_node_allow_once(struct drm_vma_offset_node *node, struct drm_file *tag); void drm_vma_node_revoke(struct drm_vma_offset_node *node, struct drm_file *tag); bool drm_vma_node_is_allowed(struct drm_vma_offset_node *node, struct drm_file *tag); /** * drm_vma_offset_exact_lookup_locked() - Look up node by exact address * @mgr: Manager object * @start: Start address (page-based, not byte-based) * @pages: Size of object (page-based) * * Same as drm_vma_offset_lookup_locked() but does not allow any offset into the node. * It only returns the exact object with the given start address. * * RETURNS: * Node at exact start address @start. */ static inline struct drm_vma_offset_node * drm_vma_offset_exact_lookup_locked(struct drm_vma_offset_manager *mgr, unsigned long start, unsigned long pages) { struct drm_vma_offset_node *node; node = drm_vma_offset_lookup_locked(mgr, start, pages); return (node && node->vm_node.start == start) ? node : NULL; } /** * drm_vma_offset_lock_lookup() - Lock lookup for extended private use * @mgr: Manager object * * Lock VMA manager for extended lookups. Only locked VMA function calls * are allowed while holding this lock. All other contexts are blocked from VMA * until the lock is released via drm_vma_offset_unlock_lookup(). * * Use this if you need to take a reference to the objects returned by * drm_vma_offset_lookup_locked() before releasing this lock again. * * This lock must not be used for anything else than extended lookups. You must * not call any other VMA helpers while holding this lock. * * Note: You're in atomic-context while holding this lock! */ static inline void drm_vma_offset_lock_lookup(struct drm_vma_offset_manager *mgr) { read_lock(&mgr->vm_lock); } /** * drm_vma_offset_unlock_lookup() - Unlock lookup for extended private use * @mgr: Manager object * * Release lookup-lock. See drm_vma_offset_lock_lookup() for more information. */ static inline void drm_vma_offset_unlock_lookup(struct drm_vma_offset_manager *mgr) { read_unlock(&mgr->vm_lock); } /** * drm_vma_node_reset() - Initialize or reset node object * @node: Node to initialize or reset * * Reset a node to its initial state. This must be called before using it with * any VMA offset manager. * * This must not be called on an already allocated node, or you will leak * memory. */ static inline void drm_vma_node_reset(struct drm_vma_offset_node *node) { memset(node, 0, sizeof(*node)); node->vm_files = RB_ROOT; rwlock_init(&node->vm_lock); } /** * drm_vma_node_start() - Return start address for page-based addressing * @node: Node to inspect * * Return the start address of the given node. This can be used as offset into * the linear VM space that is provided by the VMA offset manager. Note that * this can only be used for page-based addressing. If you need a proper offset * for user-space mappings, you must apply "<< PAGE_SHIFT" or use the * drm_vma_node_offset_addr() helper instead. * * RETURNS: * Start address of @node for page-based addressing. 0 if the node does not * have an offset allocated. */ static inline unsigned long drm_vma_node_start(const struct drm_vma_offset_node *node) { return node->vm_node.start; } /** * drm_vma_node_size() - Return size (page-based) * @node: Node to inspect * * Return the size as number of pages for the given node. This is the same size * that was passed to drm_vma_offset_add(). If no offset is allocated for the * node, this is 0. * * RETURNS: * Size of @node as number of pages. 0 if the node does not have an offset * allocated. */ static inline unsigned long drm_vma_node_size(struct drm_vma_offset_node *node) { return node->vm_node.size; } /** * drm_vma_node_offset_addr() - Return sanitized offset for user-space mmaps * @node: Linked offset node * * Same as drm_vma_node_start() but returns the address as a valid offset that * can be used for user-space mappings during mmap(). * This must not be called on unlinked nodes. * * RETURNS: * Offset of @node for byte-based addressing. 0 if the node does not have an * object allocated. */ static inline __u64 drm_vma_node_offset_addr(struct drm_vma_offset_node *node) { return ((__u64)node->vm_node.start) << PAGE_SHIFT; } /** * drm_vma_node_unmap() - Unmap offset node * @node: Offset node * @file_mapping: Address space to unmap @node from * * Unmap all userspace mappings for a given offset node. The mappings must be * associated with the @file_mapping address-space. If no offset exists * nothing is done. * * This call is unlocked. The caller must guarantee that drm_vma_offset_remove() * is not called on this node concurrently. */ static inline void drm_vma_node_unmap(struct drm_vma_offset_node *node, struct address_space *file_mapping) { if (drm_mm_node_allocated(&node->vm_node)) unmap_mapping_range(file_mapping, drm_vma_node_offset_addr(node), drm_vma_node_size(node) << PAGE_SHIFT, 1); } /** * drm_vma_node_verify_access() - Access verification helper for TTM * @node: Offset node * @tag: Tag of file to check * * This checks whether @tag is granted access to @node. It is the same as * drm_vma_node_is_allowed() but suitable as drop-in helper for TTM * verify_access() callbacks. * * RETURNS: * 0 if access is granted, -EACCES otherwise. */ static inline int drm_vma_node_verify_access(struct drm_vma_offset_node *node, struct drm_file *tag) { return drm_vma_node_is_allowed(node, tag) ? 0 : -EACCES; } #endif /* __DRM_VMA_MANAGER_H__ */ |
| 89 89 18 17 19 2 2 4 5 7 7 6 2 2 2 2 220 274 221 2 221 103 149 282 221 149 283 283 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/kernel.h> #include <linux/slab.h> #include <net/act_api.h> #include <net/flow_offload.h> #include <linux/rtnetlink.h> #include <linux/mutex.h> #include <linux/rhashtable.h> struct flow_rule *flow_rule_alloc(unsigned int num_actions) { struct flow_rule *rule; int i; rule = kzalloc(struct_size(rule, action.entries, num_actions), GFP_KERNEL); if (!rule) return NULL; rule->action.num_entries = num_actions; /* Pre-fill each action hw_stats with DONT_CARE. * Caller can override this if it wants stats for a given action. */ for (i = 0; i < num_actions; i++) rule->action.entries[i].hw_stats = FLOW_ACTION_HW_STATS_DONT_CARE; return rule; } EXPORT_SYMBOL(flow_rule_alloc); struct flow_offload_action *offload_action_alloc(unsigned int num_actions) { struct flow_offload_action *fl_action; int i; fl_action = kzalloc(struct_size(fl_action, action.entries, num_actions), GFP_KERNEL); if (!fl_action) return NULL; fl_action->action.num_entries = num_actions; /* Pre-fill each action hw_stats with DONT_CARE. * Caller can override this if it wants stats for a given action. */ for (i = 0; i < num_actions; i++) fl_action->action.entries[i].hw_stats = FLOW_ACTION_HW_STATS_DONT_CARE; return fl_action; } #define FLOW_DISSECTOR_MATCH(__rule, __type, __out) \ const struct flow_match *__m = &(__rule)->match; \ struct flow_dissector *__d = (__m)->dissector; \ \ (__out)->key = skb_flow_dissector_target(__d, __type, (__m)->key); \ (__out)->mask = skb_flow_dissector_target(__d, __type, (__m)->mask); \ void flow_rule_match_meta(const struct flow_rule *rule, struct flow_match_meta *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_META, out); } EXPORT_SYMBOL(flow_rule_match_meta); void flow_rule_match_basic(const struct flow_rule *rule, struct flow_match_basic *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_BASIC, out); } EXPORT_SYMBOL(flow_rule_match_basic); void flow_rule_match_control(const struct flow_rule *rule, struct flow_match_control *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_CONTROL, out); } EXPORT_SYMBOL(flow_rule_match_control); void flow_rule_match_eth_addrs(const struct flow_rule *rule, struct flow_match_eth_addrs *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS, out); } EXPORT_SYMBOL(flow_rule_match_eth_addrs); void flow_rule_match_vlan(const struct flow_rule *rule, struct flow_match_vlan *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_VLAN, out); } EXPORT_SYMBOL(flow_rule_match_vlan); void flow_rule_match_cvlan(const struct flow_rule *rule, struct flow_match_vlan *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_CVLAN, out); } EXPORT_SYMBOL(flow_rule_match_cvlan); void flow_rule_match_arp(const struct flow_rule *rule, struct flow_match_arp *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ARP, out); } EXPORT_SYMBOL(flow_rule_match_arp); void flow_rule_match_ipv4_addrs(const struct flow_rule *rule, struct flow_match_ipv4_addrs *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS, out); } EXPORT_SYMBOL(flow_rule_match_ipv4_addrs); void flow_rule_match_ipv6_addrs(const struct flow_rule *rule, struct flow_match_ipv6_addrs *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS, out); } EXPORT_SYMBOL(flow_rule_match_ipv6_addrs); void flow_rule_match_ip(const struct flow_rule *rule, struct flow_match_ip *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IP, out); } EXPORT_SYMBOL(flow_rule_match_ip); void flow_rule_match_ports(const struct flow_rule *rule, struct flow_match_ports *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_PORTS, out); } EXPORT_SYMBOL(flow_rule_match_ports); void flow_rule_match_ports_range(const struct flow_rule *rule, struct flow_match_ports_range *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_PORTS_RANGE, out); } EXPORT_SYMBOL(flow_rule_match_ports_range); void flow_rule_match_tcp(const struct flow_rule *rule, struct flow_match_tcp *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_TCP, out); } EXPORT_SYMBOL(flow_rule_match_tcp); void flow_rule_match_ipsec(const struct flow_rule *rule, struct flow_match_ipsec *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IPSEC, out); } EXPORT_SYMBOL(flow_rule_match_ipsec); void flow_rule_match_icmp(const struct flow_rule *rule, struct flow_match_icmp *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ICMP, out); } EXPORT_SYMBOL(flow_rule_match_icmp); void flow_rule_match_mpls(const struct flow_rule *rule, struct flow_match_mpls *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_MPLS, out); } EXPORT_SYMBOL(flow_rule_match_mpls); void flow_rule_match_enc_control(const struct flow_rule *rule, struct flow_match_control *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL, out); } EXPORT_SYMBOL(flow_rule_match_enc_control); void flow_rule_match_enc_ipv4_addrs(const struct flow_rule *rule, struct flow_match_ipv4_addrs *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, out); } EXPORT_SYMBOL(flow_rule_match_enc_ipv4_addrs); void flow_rule_match_enc_ipv6_addrs(const struct flow_rule *rule, struct flow_match_ipv6_addrs *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, out); } EXPORT_SYMBOL(flow_rule_match_enc_ipv6_addrs); void flow_rule_match_enc_ip(const struct flow_rule *rule, struct flow_match_ip *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IP, out); } EXPORT_SYMBOL(flow_rule_match_enc_ip); void flow_rule_match_enc_ports(const struct flow_rule *rule, struct flow_match_ports *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_PORTS, out); } EXPORT_SYMBOL(flow_rule_match_enc_ports); void flow_rule_match_enc_keyid(const struct flow_rule *rule, struct flow_match_enc_keyid *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_KEYID, out); } EXPORT_SYMBOL(flow_rule_match_enc_keyid); void flow_rule_match_enc_opts(const struct flow_rule *rule, struct flow_match_enc_opts *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_OPTS, out); } EXPORT_SYMBOL(flow_rule_match_enc_opts); struct flow_action_cookie *flow_action_cookie_create(void *data, unsigned int len, gfp_t gfp) { struct flow_action_cookie *cookie; cookie = kmalloc(sizeof(*cookie) + len, gfp); if (!cookie) return NULL; cookie->cookie_len = len; memcpy(cookie->cookie, data, len); return cookie; } EXPORT_SYMBOL(flow_action_cookie_create); void flow_action_cookie_destroy(struct flow_action_cookie *cookie) { kfree(cookie); } EXPORT_SYMBOL(flow_action_cookie_destroy); void flow_rule_match_ct(const struct flow_rule *rule, struct flow_match_ct *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_CT, out); } EXPORT_SYMBOL(flow_rule_match_ct); void flow_rule_match_pppoe(const struct flow_rule *rule, struct flow_match_pppoe *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_PPPOE, out); } EXPORT_SYMBOL(flow_rule_match_pppoe); void flow_rule_match_l2tpv3(const struct flow_rule *rule, struct flow_match_l2tpv3 *out) { FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_L2TPV3, out); } EXPORT_SYMBOL(flow_rule_match_l2tpv3); struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv)) { struct flow_block_cb *block_cb; block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL); if (!block_cb) return ERR_PTR(-ENOMEM); block_cb->cb = cb; block_cb->cb_ident = cb_ident; block_cb->cb_priv = cb_priv; block_cb->release = release; return block_cb; } EXPORT_SYMBOL(flow_block_cb_alloc); void flow_block_cb_free(struct flow_block_cb *block_cb) { if (block_cb->release) block_cb->release(block_cb->cb_priv); kfree(block_cb); } EXPORT_SYMBOL(flow_block_cb_free); struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block, flow_setup_cb_t *cb, void *cb_ident) { struct flow_block_cb *block_cb; list_for_each_entry(block_cb, &block->cb_list, list) { if (block_cb->cb == cb && block_cb->cb_ident == cb_ident) return block_cb; } return NULL; } EXPORT_SYMBOL(flow_block_cb_lookup); void *flow_block_cb_priv(struct flow_block_cb *block_cb) { return block_cb->cb_priv; } EXPORT_SYMBOL(flow_block_cb_priv); void flow_block_cb_incref(struct flow_block_cb *block_cb) { block_cb->refcnt++; } EXPORT_SYMBOL(flow_block_cb_incref); unsigned int flow_block_cb_decref(struct flow_block_cb *block_cb) { return --block_cb->refcnt; } EXPORT_SYMBOL(flow_block_cb_decref); bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident, struct list_head *driver_block_list) { struct flow_block_cb *block_cb; list_for_each_entry(block_cb, driver_block_list, driver_list) { if (block_cb->cb == cb && block_cb->cb_ident == cb_ident) return true; } return false; } EXPORT_SYMBOL(flow_block_cb_is_busy); int flow_block_cb_setup_simple(struct flow_block_offload *f, struct list_head *driver_block_list, flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, bool ingress_only) { struct flow_block_cb *block_cb; if (ingress_only && f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) return -EOPNOTSUPP; f->driver_block_list = driver_block_list; switch (f->command) { case FLOW_BLOCK_BIND: if (flow_block_cb_is_busy(cb, cb_ident, driver_block_list)) return -EBUSY; block_cb = flow_block_cb_alloc(cb, cb_ident, cb_priv, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); flow_block_cb_add(block_cb, f); list_add_tail(&block_cb->driver_list, driver_block_list); return 0; case FLOW_BLOCK_UNBIND: block_cb = flow_block_cb_lookup(f->block, cb, cb_ident); if (!block_cb) return -ENOENT; flow_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); return 0; default: return -EOPNOTSUPP; } } EXPORT_SYMBOL(flow_block_cb_setup_simple); static DEFINE_MUTEX(flow_indr_block_lock); static LIST_HEAD(flow_block_indr_list); static LIST_HEAD(flow_block_indr_dev_list); static LIST_HEAD(flow_indir_dev_list); struct flow_indr_dev { struct list_head list; flow_indr_block_bind_cb_t *cb; void *cb_priv; refcount_t refcnt; }; static struct flow_indr_dev *flow_indr_dev_alloc(flow_indr_block_bind_cb_t *cb, void *cb_priv) { struct flow_indr_dev *indr_dev; indr_dev = kmalloc(sizeof(*indr_dev), GFP_KERNEL); if (!indr_dev) return NULL; indr_dev->cb = cb; indr_dev->cb_priv = cb_priv; refcount_set(&indr_dev->refcnt, 1); return indr_dev; } struct flow_indir_dev_info { void *data; struct net_device *dev; struct Qdisc *sch; enum tc_setup_type type; void (*cleanup)(struct flow_block_cb *block_cb); struct list_head list; enum flow_block_command command; enum flow_block_binder_type binder_type; struct list_head *cb_list; }; static void existing_qdiscs_register(flow_indr_block_bind_cb_t *cb, void *cb_priv) { struct flow_block_offload bo; struct flow_indir_dev_info *cur; list_for_each_entry(cur, &flow_indir_dev_list, list) { memset(&bo, 0, sizeof(bo)); bo.command = cur->command; bo.binder_type = cur->binder_type; INIT_LIST_HEAD(&bo.cb_list); cb(cur->dev, cur->sch, cb_priv, cur->type, &bo, cur->data, cur->cleanup); list_splice(&bo.cb_list, cur->cb_list); } } int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv) { struct flow_indr_dev *indr_dev; mutex_lock(&flow_indr_block_lock); list_for_each_entry(indr_dev, &flow_block_indr_dev_list, list) { if (indr_dev->cb == cb && indr_dev->cb_priv == cb_priv) { refcount_inc(&indr_dev->refcnt); mutex_unlock(&flow_indr_block_lock); return 0; } } indr_dev = flow_indr_dev_alloc(cb, cb_priv); if (!indr_dev) { mutex_unlock(&flow_indr_block_lock); return -ENOMEM; } list_add(&indr_dev->list, &flow_block_indr_dev_list); existing_qdiscs_register(cb, cb_priv); mutex_unlock(&flow_indr_block_lock); tcf_action_reoffload_cb(cb, cb_priv, true); return 0; } EXPORT_SYMBOL(flow_indr_dev_register); static void __flow_block_indr_cleanup(void (*release)(void *cb_priv), void *cb_priv, struct list_head *cleanup_list) { struct flow_block_cb *this, *next; list_for_each_entry_safe(this, next, &flow_block_indr_list, indr.list) { if (this->release == release && this->indr.cb_priv == cb_priv) list_move(&this->indr.list, cleanup_list); } } static void flow_block_indr_notify(struct list_head *cleanup_list) { struct flow_block_cb *this, *next; list_for_each_entry_safe(this, next, cleanup_list, indr.list) { list_del(&this->indr.list); this->indr.cleanup(this); } } void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv, void (*release)(void *cb_priv)) { struct flow_indr_dev *this, *next, *indr_dev = NULL; LIST_HEAD(cleanup_list); mutex_lock(&flow_indr_block_lock); list_for_each_entry_safe(this, next, &flow_block_indr_dev_list, list) { if (this->cb == cb && this->cb_priv == cb_priv && refcount_dec_and_test(&this->refcnt)) { indr_dev = this; list_del(&indr_dev->list); break; } } if (!indr_dev) { mutex_unlock(&flow_indr_block_lock); return; } __flow_block_indr_cleanup(release, cb_priv, &cleanup_list); mutex_unlock(&flow_indr_block_lock); tcf_action_reoffload_cb(cb, cb_priv, false); flow_block_indr_notify(&cleanup_list); kfree(indr_dev); } EXPORT_SYMBOL(flow_indr_dev_unregister); static void flow_block_indr_init(struct flow_block_cb *flow_block, struct flow_block_offload *bo, struct net_device *dev, struct Qdisc *sch, void *data, void *cb_priv, void (*cleanup)(struct flow_block_cb *block_cb)) { flow_block->indr.binder_type = bo->binder_type; flow_block->indr.data = data; flow_block->indr.cb_priv = cb_priv; flow_block->indr.dev = dev; flow_block->indr.sch = sch; flow_block->indr.cleanup = cleanup; } struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv), struct flow_block_offload *bo, struct net_device *dev, struct Qdisc *sch, void *data, void *indr_cb_priv, void (*cleanup)(struct flow_block_cb *block_cb)) { struct flow_block_cb *block_cb; block_cb = flow_block_cb_alloc(cb, cb_ident, cb_priv, release); if (IS_ERR(block_cb)) goto out; flow_block_indr_init(block_cb, bo, dev, sch, data, indr_cb_priv, cleanup); list_add(&block_cb->indr.list, &flow_block_indr_list); out: return block_cb; } EXPORT_SYMBOL(flow_indr_block_cb_alloc); static struct flow_indir_dev_info *find_indir_dev(void *data) { struct flow_indir_dev_info *cur; list_for_each_entry(cur, &flow_indir_dev_list, list) { if (cur->data == data) return cur; } return NULL; } static int indir_dev_add(void *data, struct net_device *dev, struct Qdisc *sch, enum tc_setup_type type, void (*cleanup)(struct flow_block_cb *block_cb), struct flow_block_offload *bo) { struct flow_indir_dev_info *info; info = find_indir_dev(data); if (info) return -EEXIST; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; info->data = data; info->dev = dev; info->sch = sch; info->type = type; info->cleanup = cleanup; info->command = bo->command; info->binder_type = bo->binder_type; info->cb_list = bo->cb_list_head; list_add(&info->list, &flow_indir_dev_list); return 0; } static int indir_dev_remove(void *data) { struct flow_indir_dev_info *info; info = find_indir_dev(data); if (!info) return -ENOENT; list_del(&info->list); kfree(info); return 0; } int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch, enum tc_setup_type type, void *data, struct flow_block_offload *bo, void (*cleanup)(struct flow_block_cb *block_cb)) { struct flow_indr_dev *this; u32 count = 0; int err; mutex_lock(&flow_indr_block_lock); if (bo) { if (bo->command == FLOW_BLOCK_BIND) indir_dev_add(data, dev, sch, type, cleanup, bo); else if (bo->command == FLOW_BLOCK_UNBIND) indir_dev_remove(data); } list_for_each_entry(this, &flow_block_indr_dev_list, list) { err = this->cb(dev, sch, this->cb_priv, type, bo, data, cleanup); if (!err) count++; } mutex_unlock(&flow_indr_block_lock); return (bo && list_empty(&bo->cb_list)) ? -EOPNOTSUPP : count; } EXPORT_SYMBOL(flow_indr_dev_setup_offload); bool flow_indr_dev_exists(void) { return !list_empty(&flow_block_indr_dev_list); } EXPORT_SYMBOL(flow_indr_dev_exists); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* md.h : kernel internal structure of the Linux MD driver Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman */ #ifndef _MD_MD_H #define _MD_MD_H #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/badblocks.h> #include <linux/kobject.h> #include <linux/list.h> #include <linux/mm.h> #include <linux/mutex.h> #include <linux/timer.h> #include <linux/wait.h> #include <linux/workqueue.h> #include <linux/raid/md_u.h> #include <trace/events/block.h> #define MaxSector (~(sector_t)0) enum md_submodule_type { MD_PERSONALITY = 0, MD_CLUSTER, MD_BITMAP, /* TODO */ }; enum md_submodule_id { ID_LINEAR = LEVEL_LINEAR, ID_RAID0 = 0, ID_RAID1 = 1, ID_RAID4 = 4, ID_RAID5 = 5, ID_RAID6 = 6, ID_RAID10 = 10, ID_CLUSTER, ID_BITMAP, /* TODO */ ID_LLBITMAP, /* TODO */ }; struct md_submodule_head { enum md_submodule_type type; enum md_submodule_id id; const char *name; struct module *owner; }; /* * These flags should really be called "NO_RETRY" rather than * "FAILFAST" because they don't make any promise about time lapse, * only about the number of retries, which will be zero. * REQ_FAILFAST_DRIVER is not included because * Commit: 4a27446f3e39 ("[SCSI] modify scsi to handle new fail fast flags.") * seems to suggest that the errors it avoids retrying should usually * be retried. */ #define MD_FAILFAST (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT) /* Status of sync thread. */ enum sync_action { /* * Represent by MD_RECOVERY_SYNC, start when: * 1) after assemble, sync data from first rdev to other copies, this * must be done first before other sync actions and will only execute * once; * 2) resize the array(notice that this is not reshape), sync data for * the new range; */ ACTION_RESYNC, /* * Represent by MD_RECOVERY_RECOVER, start when: * 1) for new replacement, sync data based on the replace rdev or * available copies from other rdev; * 2) for new member disk while the array is degraded, sync data from * other rdev; * 3) reassemble after power failure or re-add a hot removed rdev, sync * data from first rdev to other copies based on bitmap; */ ACTION_RECOVER, /* * Represent by MD_RECOVERY_SYNC | MD_RECOVERY_REQUESTED | * MD_RECOVERY_CHECK, start when user echo "check" to sysfs api * sync_action, used to check if data copies from differenct rdev are * the same. The number of mismatch sectors will be exported to user * by sysfs api mismatch_cnt; */ ACTION_CHECK, /* * Represent by MD_RECOVERY_SYNC | MD_RECOVERY_REQUESTED, start when * user echo "repair" to sysfs api sync_action, usually paired with * ACTION_CHECK, used to force syncing data once user found that there * are inconsistent data, */ ACTION_REPAIR, /* * Represent by MD_RECOVERY_RESHAPE, start when new member disk is added * to the conf, notice that this is different from spares or * replacement; */ ACTION_RESHAPE, /* * Represent by MD_RECOVERY_FROZEN, can be set by sysfs api sync_action * or internal usage like setting the array read-only, will forbid above * actions. */ ACTION_FROZEN, /* * All above actions don't match. */ ACTION_IDLE, NR_SYNC_ACTIONS, }; /* * The struct embedded in rdev is used to serialize IO. */ struct serial_in_rdev { struct rb_root_cached serial_rb; spinlock_t serial_lock; wait_queue_head_t serial_io_wait; }; /* * MD's 'extended' device */ struct md_rdev { struct list_head same_set; /* RAID devices within the same set */ sector_t sectors; /* Device size (in 512bytes sectors) */ struct mddev *mddev; /* RAID array if running */ int last_events; /* IO event timestamp */ /* * If meta_bdev is non-NULL, it means that a separate device is * being used to store the metadata (superblock/bitmap) which * would otherwise be contained on the same device as the data (bdev). */ struct block_device *meta_bdev; struct block_device *bdev; /* block device handle */ struct file *bdev_file; /* Handle from open for bdev */ struct page *sb_page, *bb_page; int sb_loaded; __u64 sb_events; sector_t data_offset; /* start of data in array */ sector_t new_data_offset;/* only relevant while reshaping */ sector_t sb_start; /* offset of the super block (in 512byte sectors) */ int sb_size; /* bytes in the superblock */ int preferred_minor; /* autorun support */ struct kobject kobj; /* A device can be in one of three states based on two flags: * Not working: faulty==1 in_sync==0 * Fully working: faulty==0 in_sync==1 * Working, but not * in sync with array * faulty==0 in_sync==0 * * It can never have faulty==1, in_sync==1 * This reduces the burden of testing multiple flags in many cases */ unsigned long flags; /* bit set of 'enum flag_bits' bits. */ wait_queue_head_t blocked_wait; int desc_nr; /* descriptor index in the superblock */ int raid_disk; /* role of device in array */ int new_raid_disk; /* role that the device will have in * the array after a level-change completes. */ int saved_raid_disk; /* role that device used to have in the * array and could again if we did a partial * resync from the bitmap */ union { sector_t recovery_offset;/* If this device has been partially * recovered, this is where we were * up to. */ sector_t journal_tail; /* If this device is a journal device, * this is the journal tail (journal * recovery start point) */ }; atomic_t nr_pending; /* number of pending requests. * only maintained for arrays that * support hot removal */ atomic_t read_errors; /* number of consecutive read errors that * we have tried to ignore. */ time64_t last_read_error; /* monotonic time since our * last read error */ atomic_t corrected_errors; /* number of corrected read errors, * for reporting to userspace and storing * in superblock. */ struct serial_in_rdev *serial; /* used for raid1 io serialization */ struct kernfs_node *sysfs_state; /* handle for 'state' * sysfs entry */ /* handle for 'unacknowledged_bad_blocks' sysfs dentry */ struct kernfs_node *sysfs_unack_badblocks; /* handle for 'bad_blocks' sysfs dentry */ struct kernfs_node *sysfs_badblocks; struct badblocks badblocks; struct { short offset; /* Offset from superblock to start of PPL. * Not used by external metadata. */ unsigned int size; /* Size in sectors of the PPL space */ sector_t sector; /* First sector of the PPL space */ } ppl; }; enum flag_bits { Faulty, /* device is known to have a fault */ In_sync, /* device is in_sync with rest of array */ Bitmap_sync, /* ..actually, not quite In_sync. Need a * bitmap-based recovery to get fully in sync. * The bit is only meaningful before device * has been passed to pers->hot_add_disk. */ WriteMostly, /* Avoid reading if at all possible */ AutoDetected, /* added by auto-detect */ Blocked, /* An error occurred but has not yet * been acknowledged by the metadata * handler, so don't allow writes * until it is cleared */ WriteErrorSeen, /* A write error has been seen on this * device */ FaultRecorded, /* Intermediate state for clearing * Blocked. The Fault is/will-be * recorded in the metadata, but that * metadata hasn't been stored safely * on disk yet. */ BlockedBadBlocks, /* A writer is blocked because they * found an unacknowledged bad-block. * This can safely be cleared at any * time, and the writer will re-check. * It may be set at any time, and at * worst the writer will timeout and * re-check. So setting it as * accurately as possible is good, but * not absolutely critical. */ WantReplacement, /* This device is a candidate to be * hot-replaced, either because it has * reported some faults, or because * of explicit request. */ Replacement, /* This device is a replacement for * a want_replacement device with same * raid_disk number. */ Candidate, /* For clustered environments only: * This device is seen locally but not * by the whole cluster */ Journal, /* This device is used as journal for * raid-5/6. * Usually, this device should be faster * than other devices in the array */ ClusterRemove, ExternalBbl, /* External metadata provides bad * block management for a disk */ FailFast, /* Minimal retries should be attempted on * this device, so use REQ_FAILFAST_DEV. * Also don't try to repair failed reads. * It is expects that no bad block log * is present. */ LastDev, /* Seems to be the last working dev as * it didn't fail, so don't use FailFast * any more for metadata */ CollisionCheck, /* * check if there is collision between raid1 * serial bios. */ Nonrot, /* non-rotational device (SSD) */ }; static inline int is_badblock(struct md_rdev *rdev, sector_t s, sector_t sectors, sector_t *first_bad, sector_t *bad_sectors) { if (unlikely(rdev->badblocks.count)) { int rv = badblocks_check(&rdev->badblocks, rdev->data_offset + s, sectors, first_bad, bad_sectors); if (rv) *first_bad -= rdev->data_offset; return rv; } return 0; } static inline int rdev_has_badblock(struct md_rdev *rdev, sector_t s, int sectors) { sector_t first_bad; sector_t bad_sectors; return is_badblock(rdev, s, sectors, &first_bad, &bad_sectors); } extern bool rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int is_new); extern void rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int is_new); struct md_cluster_info; struct md_cluster_operations; /** * enum mddev_flags - md device flags. * @MD_ARRAY_FIRST_USE: First use of array, needs initialization. * @MD_CLOSING: If set, we are closing the array, do not open it then. * @MD_JOURNAL_CLEAN: A raid with journal is already clean. * @MD_HAS_JOURNAL: The raid array has journal feature set. * @MD_CLUSTER_RESYNC_LOCKED: cluster raid only, which means node, already took * resync lock, need to release the lock. * @MD_FAILFAST_SUPPORTED: Using MD_FAILFAST on metadata writes is supported as * calls to md_error() will never cause the array to * become failed. * @MD_HAS_PPL: The raid array has PPL feature set. * @MD_HAS_MULTIPLE_PPLS: The raid array has multiple PPLs feature set. * @MD_NOT_READY: do_md_run() is active, so 'array_state', ust not report that * array is ready yet. * @MD_BROKEN: This is used to stop writes and mark array as failed. * @MD_DELETED: This device is being deleted * * change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */ enum mddev_flags { MD_ARRAY_FIRST_USE, MD_CLOSING, MD_JOURNAL_CLEAN, MD_HAS_JOURNAL, MD_CLUSTER_RESYNC_LOCKED, MD_FAILFAST_SUPPORTED, MD_HAS_PPL, MD_HAS_MULTIPLE_PPLS, MD_NOT_READY, MD_BROKEN, MD_DELETED, }; enum mddev_sb_flags { MD_SB_CHANGE_DEVS, /* Some device status has changed */ MD_SB_CHANGE_CLEAN, /* transition to or from 'clean' */ MD_SB_CHANGE_PENDING, /* switch from 'clean' to 'active' in progress */ MD_SB_NEED_REWRITE, /* metadata write needs to be repeated */ }; #define NR_SERIAL_INFOS 8 /* record current range of serialize IOs */ struct serial_info { struct rb_node node; sector_t start; /* start sector of rb node */ sector_t last; /* end sector of rb node */ sector_t _subtree_last; /* highest sector in subtree of rb node */ }; /* * mddev->curr_resync stores the current sector of the resync but * also has some overloaded values. */ enum { /* No resync in progress */ MD_RESYNC_NONE = 0, /* Yielded to allow another conflicting resync to commence */ MD_RESYNC_YIELDED = 1, /* Delayed to check that there is no conflict with another sync */ MD_RESYNC_DELAYED = 2, /* Any value greater than or equal to this is in an active resync */ MD_RESYNC_ACTIVE = 3, }; struct mddev { void *private; struct md_personality *pers; dev_t unit; int md_minor; struct list_head disks; unsigned long flags; unsigned long sb_flags; int suspended; struct mutex suspend_mutex; struct percpu_ref active_io; int ro; int sysfs_active; /* set when sysfs deletes * are happening, so run/ * takeover/stop are not safe */ struct gendisk *gendisk; struct kobject kobj; int hold_active; #define UNTIL_IOCTL 1 #define UNTIL_STOP 2 /* Superblock information */ int major_version, minor_version, patch_version; int persistent; int external; /* metadata is * managed externally */ char metadata_type[17]; /* externally set*/ int chunk_sectors; time64_t ctime, utime; int level, layout; char clevel[16]; int raid_disks; int max_disks; sector_t dev_sectors; /* used size of * component devices */ sector_t array_sectors; /* exported array size */ int external_size; /* size managed * externally */ __u64 events; /* If the last 'event' was simply a clean->dirty transition, and * we didn't write it to the spares, then it is safe and simple * to just decrement the event count on a dirty->clean transition. * So we record that possibility here. */ int can_decrease_events; char uuid[16]; /* If the array is being reshaped, we need to record the * new shape and an indication of where we are up to. * This is written to the superblock. * If reshape_position is MaxSector, then no reshape is happening (yet). */ sector_t reshape_position; int delta_disks, new_level, new_layout; int new_chunk_sectors; int reshape_backwards; struct md_thread __rcu *thread; /* management thread */ struct md_thread __rcu *sync_thread; /* doing resync or reconstruct */ /* * Set when a sync operation is started. It holds this value even * when the sync thread is "frozen" (interrupted) or "idle" (stopped * or finished). It is overwritten when a new sync operation is begun. */ enum sync_action last_sync_action; sector_t curr_resync; /* last block scheduled */ /* As resync requests can complete out of order, we cannot easily track * how much resync has been completed. So we occasionally pause until * everything completes, then set curr_resync_completed to curr_resync. * As such it may be well behind the real resync mark, but it is a value * we are certain of. */ sector_t curr_resync_completed; unsigned long resync_mark; /* a recent timestamp */ sector_t resync_mark_cnt;/* blocks written at resync_mark */ sector_t curr_mark_cnt; /* blocks scheduled now */ sector_t resync_max_sectors; /* may be set by personality */ atomic64_t resync_mismatches; /* count of sectors where * parity/replica mismatch found */ /* allow user-space to request suspension of IO to regions of the array */ sector_t suspend_lo; sector_t suspend_hi; /* if zero, use the system-wide default */ int sync_speed_min; int sync_speed_max; /* resync even though the same disks are shared among md-devices */ int parallel_resync; int ok_start_degraded; unsigned long recovery; /* If a RAID personality determines that recovery (of a particular * device) will fail due to a read error on the source device, it * takes a copy of this number and does not attempt recovery again * until this number changes. */ int recovery_disabled; int in_sync; /* know to not need resync */ /* 'open_mutex' avoids races between 'md_open' and 'do_md_stop', so * that we are never stopping an array while it is open. * 'reconfig_mutex' protects all other reconfiguration. * These locks are separate due to conflicting interactions * with disk->open_mutex. * Lock ordering is: * reconfig_mutex -> disk->open_mutex * disk->open_mutex -> open_mutex: e.g. __blkdev_get -> md_open */ struct mutex open_mutex; struct mutex reconfig_mutex; atomic_t active; /* general refcount */ atomic_t openers; /* number of active opens */ int changed; /* True if we might need to * reread partition info */ int degraded; /* whether md should consider * adding a spare */ atomic_t recovery_active; /* blocks scheduled, but not written */ wait_queue_head_t recovery_wait; sector_t recovery_cp; sector_t resync_min; /* user requested sync * starts here */ sector_t resync_max; /* resync should pause * when it gets here */ struct kernfs_node *sysfs_state; /* handle for 'array_state' * file in sysfs. */ struct kernfs_node *sysfs_action; /* handle for 'sync_action' */ struct kernfs_node *sysfs_completed; /*handle for 'sync_completed' */ struct kernfs_node *sysfs_degraded; /*handle for 'degraded' */ struct kernfs_node *sysfs_level; /*handle for 'level' */ /* used for delayed sysfs removal */ struct work_struct del_work; /* used for register new sync thread */ struct work_struct sync_work; /* "lock" protects: * flush_bio transition from NULL to !NULL * rdev superblocks, events * clearing MD_CHANGE_* * in_sync - and related safemode and MD_CHANGE changes * pers (also protected by reconfig_mutex and pending IO). * clearing ->bitmap * clearing ->bitmap_info.file * changing ->resync_{min,max} * setting MD_RECOVERY_RUNNING (which interacts with resync_{min,max}) */ spinlock_t lock; wait_queue_head_t sb_wait; /* for waiting on superblock updates */ atomic_t pending_writes; /* number of active superblock writes */ unsigned int safemode; /* if set, update "clean" superblock * when no writes pending. */ unsigned int safemode_delay; struct timer_list safemode_timer; struct percpu_ref writes_pending; int sync_checkers; /* # of threads checking writes_pending */ void *bitmap; /* the bitmap for the device */ struct bitmap_operations *bitmap_ops; struct { struct file *file; /* the bitmap file */ loff_t offset; /* offset from superblock of * start of bitmap. May be * negative, but not '0' * For external metadata, offset * from start of device. */ unsigned long space; /* space available at this offset */ loff_t default_offset; /* this is the offset to use when * hot-adding a bitmap. It should * eventually be settable by sysfs. */ unsigned long default_space; /* space available at * default offset */ struct mutex mutex; unsigned long chunksize; unsigned long daemon_sleep; /* how many jiffies between updates? */ unsigned long max_write_behind; /* write-behind mode */ int external; int nodes; /* Maximum number of nodes in the cluster */ char cluster_name[64]; /* Name of the cluster */ } bitmap_info; atomic_t max_corr_read_errors; /* max read retries */ struct list_head all_mddevs; const struct attribute_group *to_remove; struct bio_set bio_set; struct bio_set sync_set; /* for sync operations like * metadata and bitmap writes */ struct bio_set io_clone_set; struct work_struct event_work; /* used by dm to report failure event */ mempool_t *serial_info_pool; void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev); struct md_cluster_info *cluster_info; struct md_cluster_operations *cluster_ops; unsigned int good_device_nr; /* good device num within cluster raid */ unsigned int noio_flag; /* for memalloc scope API */ /* * Temporarily store rdev that will be finally removed when * reconfig_mutex is unlocked, protected by reconfig_mutex. */ struct list_head deleting; /* The sequence number for sync thread */ atomic_t sync_seq; bool has_superblocks:1; bool fail_last_dev:1; bool serialize_policy:1; }; enum recovery_flags { /* flags for sync thread running status */ /* * set when one of sync action is set and new sync thread need to be * registered, or just add/remove spares from conf. */ MD_RECOVERY_NEEDED, /* sync thread is running, or about to be started */ MD_RECOVERY_RUNNING, /* sync thread needs to be aborted for some reason */ MD_RECOVERY_INTR, /* sync thread is done and is waiting to be unregistered */ MD_RECOVERY_DONE, /* running sync thread must abort immediately, and not restart */ MD_RECOVERY_FROZEN, /* waiting for pers->start() to finish */ MD_RECOVERY_WAIT, /* interrupted because io-error */ MD_RECOVERY_ERROR, /* flags determines sync action, see details in enum sync_action */ /* if just this flag is set, action is resync. */ MD_RECOVERY_SYNC, /* * paired with MD_RECOVERY_SYNC, if MD_RECOVERY_CHECK is not set, * action is repair, means user requested resync. */ MD_RECOVERY_REQUESTED, /* * paired with MD_RECOVERY_SYNC and MD_RECOVERY_REQUESTED, action is * check. */ MD_RECOVERY_CHECK, /* recovery, or need to try it */ MD_RECOVERY_RECOVER, /* reshape */ MD_RECOVERY_RESHAPE, /* remote node is running resync thread */ MD_RESYNCING_REMOTE, }; enum md_ro_state { MD_RDWR, MD_RDONLY, MD_AUTO_READ, MD_MAX_STATE }; static inline bool md_is_rdwr(struct mddev *mddev) { return (mddev->ro == MD_RDWR); } static inline bool reshape_interrupted(struct mddev *mddev) { /* reshape never start */ if (mddev->reshape_position == MaxSector) return false; /* interrupted */ if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) return true; /* running reshape will be interrupted soon. */ if (test_bit(MD_RECOVERY_WAIT, &mddev->recovery) || test_bit(MD_RECOVERY_INTR, &mddev->recovery) || test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) return true; return false; } static inline int __must_check mddev_lock(struct mddev *mddev) { return mutex_lock_interruptible(&mddev->reconfig_mutex); } /* Sometimes we need to take the lock in a situation where * failure due to interrupts is not acceptable. */ static inline void mddev_lock_nointr(struct mddev *mddev) { mutex_lock(&mddev->reconfig_mutex); } static inline int mddev_trylock(struct mddev *mddev) { return mutex_trylock(&mddev->reconfig_mutex); } extern void mddev_unlock(struct mddev *mddev); static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors) { if (blk_queue_io_stat(bdev->bd_disk->queue)) atomic_add(nr_sectors, &bdev->bd_disk->sync_io); } static inline void md_sync_acct_bio(struct bio *bio, unsigned long nr_sectors) { md_sync_acct(bio->bi_bdev, nr_sectors); } struct md_personality { struct md_submodule_head head; bool __must_check (*make_request)(struct mddev *mddev, struct bio *bio); /* * start up works that do NOT require md_thread. tasks that * requires md_thread should go into start() */ int (*run)(struct mddev *mddev); /* start up works that require md threads */ int (*start)(struct mddev *mddev); void (*free)(struct mddev *mddev, void *priv); void (*status)(struct seq_file *seq, struct mddev *mddev); /* error_handler must set ->faulty and clear ->in_sync * if appropriate, and should abort recovery if needed */ void (*error_handler)(struct mddev *mddev, struct md_rdev *rdev); int (*hot_add_disk) (struct mddev *mddev, struct md_rdev *rdev); int (*hot_remove_disk) (struct mddev *mddev, struct md_rdev *rdev); int (*spare_active) (struct mddev *mddev); sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr, sector_t max_sector, int *skipped); int (*resize) (struct mddev *mddev, sector_t sectors); sector_t (*size) (struct mddev *mddev, sector_t sectors, int raid_disks); int (*check_reshape) (struct mddev *mddev); int (*start_reshape) (struct mddev *mddev); void (*finish_reshape) (struct mddev *mddev); void (*update_reshape_pos) (struct mddev *mddev); void (*prepare_suspend) (struct mddev *mddev); /* quiesce suspends or resumes internal processing. * 1 - stop new actions and wait for action io to complete * 0 - return to normal behaviour */ void (*quiesce) (struct mddev *mddev, int quiesce); /* takeover is used to transition an array from one * personality to another. The new personality must be able * to handle the data in the current layout. * e.g. 2drive raid1 -> 2drive raid5 * ndrive raid5 -> degraded n+1drive raid6 with special layout * If the takeover succeeds, a new 'private' structure is returned. * This needs to be installed and then ->run used to activate the * array. */ void *(*takeover) (struct mddev *mddev); /* Changes the consistency policy of an active array. */ int (*change_consistency_policy)(struct mddev *mddev, const char *buf); /* convert io ranges from array to bitmap */ void (*bitmap_sector)(struct mddev *mddev, sector_t *offset, unsigned long *sectors); }; struct md_sysfs_entry { struct attribute attr; ssize_t (*show)(struct mddev *, char *); ssize_t (*store)(struct mddev *, const char *, size_t); }; extern const struct attribute_group md_bitmap_group; static inline struct kernfs_node *sysfs_get_dirent_safe(struct kernfs_node *sd, char *name) { if (sd) return sysfs_get_dirent(sd, name); return sd; } static inline void sysfs_notify_dirent_safe(struct kernfs_node *sd) { if (sd) sysfs_notify_dirent(sd); } static inline char * mdname (struct mddev * mddev) { return mddev->gendisk ? mddev->gendisk->disk_name : "mdX"; } static inline int sysfs_link_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; if (!test_bit(Replacement, &rdev->flags) && !test_bit(Journal, &rdev->flags) && mddev->kobj.sd) { sprintf(nm, "rd%d", rdev->raid_disk); return sysfs_create_link(&mddev->kobj, &rdev->kobj, nm); } else return 0; } static inline void sysfs_unlink_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; if (!test_bit(Replacement, &rdev->flags) && !test_bit(Journal, &rdev->flags) && mddev->kobj.sd) { sprintf(nm, "rd%d", rdev->raid_disk); sysfs_remove_link(&mddev->kobj, nm); } } /* * iterates through some rdev ringlist. It's safe to remove the * current 'rdev'. Dont touch 'tmp' though. */ #define rdev_for_each_list(rdev, tmp, head) \ list_for_each_entry_safe(rdev, tmp, head, same_set) /* * iterates through the 'same array disks' ringlist */ #define rdev_for_each(rdev, mddev) \ list_for_each_entry(rdev, &((mddev)->disks), same_set) #define rdev_for_each_safe(rdev, tmp, mddev) \ list_for_each_entry_safe(rdev, tmp, &((mddev)->disks), same_set) #define rdev_for_each_rcu(rdev, mddev) \ list_for_each_entry_rcu(rdev, &((mddev)->disks), same_set) struct md_thread { void (*run) (struct md_thread *thread); struct mddev *mddev; wait_queue_head_t wqueue; unsigned long flags; struct task_struct *tsk; unsigned long timeout; void *private; }; struct md_io_clone { struct mddev *mddev; struct bio *orig_bio; unsigned long start_time; sector_t offset; unsigned long sectors; struct bio bio_clone; }; #define THREAD_WAKEUP 0 static inline void safe_put_page(struct page *p) { if (p) put_page(p); } int register_md_submodule(struct md_submodule_head *msh); void unregister_md_submodule(struct md_submodule_head *msh); extern struct md_thread *md_register_thread( void (*run)(struct md_thread *thread), struct mddev *mddev, const char *name); extern void md_unregister_thread(struct mddev *mddev, struct md_thread __rcu **threadp); extern void md_wakeup_thread(struct md_thread __rcu *thread); extern void md_check_recovery(struct mddev *mddev); extern void md_reap_sync_thread(struct mddev *mddev); extern enum sync_action md_sync_action(struct mddev *mddev); extern enum sync_action md_sync_action_by_name(const char *page); extern const char *md_sync_action_name(enum sync_action action); extern void md_write_start(struct mddev *mddev, struct bio *bi); extern void md_write_inc(struct mddev *mddev, struct bio *bi); extern void md_write_end(struct mddev *mddev); extern void md_done_sync(struct mddev *mddev, int blocks, int ok); extern void md_error(struct mddev *mddev, struct md_rdev *rdev); extern void md_finish_reshape(struct mddev *mddev); void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, struct bio *bio, sector_t start, sector_t size); void md_account_bio(struct mddev *mddev, struct bio **bio); void md_free_cloned_bio(struct bio *bio); extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, sector_t sector, int size, struct page *page); extern int md_super_wait(struct mddev *mddev); extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size, struct page *page, blk_opf_t opf, bool metadata_op); extern void md_do_sync(struct md_thread *thread); extern void md_new_event(void); extern void md_allow_write(struct mddev *mddev); extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev); extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors); extern int md_check_no_bitmap(struct mddev *mddev); extern int md_integrity_register(struct mddev *mddev); extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale); extern int mddev_init(struct mddev *mddev); extern void mddev_destroy(struct mddev *mddev); void md_init_stacking_limits(struct queue_limits *lim); struct mddev *md_alloc(dev_t dev, char *name); void mddev_put(struct mddev *mddev); extern int md_run(struct mddev *mddev); extern int md_start(struct mddev *mddev); extern void md_stop(struct mddev *mddev); extern void md_stop_writes(struct mddev *mddev); extern int md_rdev_init(struct md_rdev *rdev); extern void md_rdev_clear(struct md_rdev *rdev); extern bool md_handle_request(struct mddev *mddev, struct bio *bio); extern int mddev_suspend(struct mddev *mddev, bool interruptible); extern void mddev_resume(struct mddev *mddev); extern void md_idle_sync_thread(struct mddev *mddev); extern void md_frozen_sync_thread(struct mddev *mddev); extern void md_unfrozen_sync_thread(struct mddev *mddev); extern void md_update_sb(struct mddev *mddev, int force); extern void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev); extern void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev); struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr); struct md_rdev *md_find_rdev_rcu(struct mddev *mddev, dev_t dev); static inline bool is_rdev_broken(struct md_rdev *rdev) { return !disk_live(rdev->bdev->bd_disk); } static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev) { int faulty = test_bit(Faulty, &rdev->flags); if (atomic_dec_and_test(&rdev->nr_pending) && faulty) { set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); } } static inline int mddev_is_clustered(struct mddev *mddev) { return mddev->cluster_info && mddev->bitmap_info.nodes > 1; } /* clear unsupported mddev_flags */ static inline void mddev_clear_unsupported_flags(struct mddev *mddev, unsigned long unsupported_flags) { mddev->flags &= ~unsupported_flags; } static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio) { if (bio_op(bio) == REQ_OP_WRITE_ZEROES && !bio->bi_bdev->bd_disk->queue->limits.max_write_zeroes_sectors) mddev->gendisk->queue->limits.max_write_zeroes_sectors = 0; } static inline int mddev_suspend_and_lock(struct mddev *mddev) { int ret; ret = mddev_suspend(mddev, true); if (ret) return ret; ret = mddev_lock(mddev); if (ret) mddev_resume(mddev); return ret; } static inline void mddev_suspend_and_lock_nointr(struct mddev *mddev) { mddev_suspend(mddev, false); mutex_lock(&mddev->reconfig_mutex); } static inline void mddev_unlock_and_resume(struct mddev *mddev) { mddev_unlock(mddev); mddev_resume(mddev); } struct mdu_array_info_s; struct mdu_disk_info_s; extern int mdp_major; extern struct workqueue_struct *md_bitmap_wq; void md_autostart_arrays(int part); int md_set_array_info(struct mddev *mddev, struct mdu_array_info_s *info); int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info); int do_md_run(struct mddev *mddev); #define MDDEV_STACK_INTEGRITY (1u << 0) int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim, unsigned int flags); int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev); void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes); extern const struct block_device_operations md_fops; /* * MD devices can be used undeneath by DM, in which case ->gendisk is NULL. */ static inline bool mddev_is_dm(struct mddev *mddev) { return !mddev->gendisk; } static inline void mddev_trace_remap(struct mddev *mddev, struct bio *bio, sector_t sector) { if (!mddev_is_dm(mddev)) trace_block_bio_remap(bio, disk_devt(mddev->gendisk), sector); } static inline bool rdev_blocked(struct md_rdev *rdev) { /* * Blocked will be set by error handler and cleared by daemon after * updating superblock, meanwhile write IO should be blocked to prevent * reading old data after power failure. */ if (test_bit(Blocked, &rdev->flags)) return true; /* * Faulty device should not be accessed anymore, there is no need to * wait for bad block to be acknowledged. */ if (test_bit(Faulty, &rdev->flags)) return false; /* rdev is blocked by badblocks. */ if (test_bit(BlockedBadBlocks, &rdev->flags)) return true; return false; } #define mddev_add_trace_msg(mddev, fmt, args...) \ do { \ if (!mddev_is_dm(mddev)) \ blk_add_trace_msg((mddev)->gendisk->queue, fmt, ##args); \ } while (0) #endif /* _MD_MD_H */ |
| 23 22 6 19 19 62 62 12 38 59 58 59 208 208 207 180 48 33 138 62 181 64 144 160 48 4 180 28 15 13 28 114 55 154 150 40 181 181 62 62 6 6 1 6 2 2 2 1 1 148 97 70 136 136 135 80 37 67 52 20 81 56 56 1 56 17 40 55 2 49 20 56 56 40 16 16 16 16 3 2 15 2 16 1 1 13 13 2 13 13 146 103 83 2 146 94 36 29 144 14 145 2 142 8 68 100 146 144 145 146 2 28 120 144 144 2 145 11 1 1 135 137 137 1 17 17 1 1 1 1 1 1 11 6 1 1 2 2 2 149 99 70 2 148 146 93 68 24 8 21 15 12 5 24 17 12 24 5 24 24 122 122 122 12 129 5 2 2 130 60 85 3 12 128 130 124 99 27 9 119 121 121 121 57 79 9 1 29 29 12 16 3 4 28 3 29 14 16 28 7 7 29 8 7 2 3 6 157 109 131 29 29 29 28 7 121 124 124 124 156 9 156 157 131 118 132 130 125 15 3 131 124 124 124 156 156 156 155 23 23 155 157 157 115 6 131 131 60 87 82 1 156 151 149 6 152 128 128 127 1 28 29 6 6 22 5 24 6 9 2 2 9 1 5 2 9 9 9 33 33 17 12 22 22 33 40 31 2 12 32 39 1 5 4 33 4 5 33 14 5 20 24 10 8 13 2 8 10 24 24 1 25 24 24 24 63 1 10 11 11 1 73 71 1 40 31 74 74 1 1 1 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Memory Migration functionality - linux/mm/migrate.c * * Copyright (C) 2006 Silicon Graphics, Inc., Christoph Lameter * * Page migration was first developed in the context of the memory hotplug * project. The main authors of the migration code are: * * IWAMOTO Toshihiro <iwamoto@valinux.co.jp> * Hirokazu Takahashi <taka@valinux.co.jp> * Dave Hansen <haveblue@us.ibm.com> * Christoph Lameter */ #include <linux/migrate.h> #include <linux/export.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/pagemap.h> #include <linux/buffer_head.h> #include <linux/mm_inline.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/topology.h> #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/writeback.h> #include <linux/mempolicy.h> #include <linux/vmalloc.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/compaction.h> #include <linux/syscalls.h> #include <linux/compat.h> #include <linux/hugetlb.h> #include <linux/gfp.h> #include <linux/pfn_t.h> #include <linux/page_idle.h> #include <linux/page_owner.h> #include <linux/sched/mm.h> #include <linux/ptrace.h> #include <linux/memory.h> #include <linux/sched/sysctl.h> #include <linux/memory-tiers.h> #include <linux/pagewalk.h> #include <asm/tlbflush.h> #include <trace/events/migrate.h> #include "internal.h" bool isolate_movable_page(struct page *page, isolate_mode_t mode) { struct folio *folio = folio_get_nontail_page(page); const struct movable_operations *mops; /* * Avoid burning cycles with pages that are yet under __free_pages(), * or just got freed under us. * * In case we 'win' a race for a movable page being freed under us and * raise its refcount preventing __free_pages() from doing its job * the put_page() at the end of this block will take care of * release this page, thus avoiding a nasty leakage. */ if (!folio) goto out; /* * Check movable flag before taking the page lock because * we use non-atomic bitops on newly allocated page flags so * unconditionally grabbing the lock ruins page's owner side. */ if (unlikely(!__folio_test_movable(folio))) goto out_putfolio; /* * As movable pages are not isolated from LRU lists, concurrent * compaction threads can race against page migration functions * as well as race against the releasing a page. * * In order to avoid having an already isolated movable page * being (wrongly) re-isolated while it is under migration, * or to avoid attempting to isolate pages being released, * lets be sure we have the page lock * before proceeding with the movable page isolation steps. */ if (unlikely(!folio_trylock(folio))) goto out_putfolio; if (!folio_test_movable(folio) || folio_test_isolated(folio)) goto out_no_isolated; mops = folio_movable_ops(folio); VM_BUG_ON_FOLIO(!mops, folio); if (!mops->isolate_page(&folio->page, mode)) goto out_no_isolated; /* Driver shouldn't use the isolated flag */ WARN_ON_ONCE(folio_test_isolated(folio)); folio_set_isolated(folio); folio_unlock(folio); return true; out_no_isolated: folio_unlock(folio); out_putfolio: folio_put(folio); out: return false; } static void putback_movable_folio(struct folio *folio) { const struct movable_operations *mops = folio_movable_ops(folio); mops->putback_page(&folio->page); folio_clear_isolated(folio); } /* * Put previously isolated pages back onto the appropriate lists * from where they were once taken off for compaction/migration. * * This function shall be used whenever the isolated pageset has been * built from lru, balloon, hugetlbfs page. See isolate_migratepages_range() * and folio_isolate_hugetlb(). */ void putback_movable_pages(struct list_head *l) { struct folio *folio; struct folio *folio2; list_for_each_entry_safe(folio, folio2, l, lru) { if (unlikely(folio_test_hugetlb(folio))) { folio_putback_hugetlb(folio); continue; } list_del(&folio->lru); /* * We isolated non-lru movable folio so here we can use * __folio_test_movable because LRU folio's mapping cannot * have PAGE_MAPPING_MOVABLE. */ if (unlikely(__folio_test_movable(folio))) { VM_BUG_ON_FOLIO(!folio_test_isolated(folio), folio); folio_lock(folio); if (folio_test_movable(folio)) putback_movable_folio(folio); else folio_clear_isolated(folio); folio_unlock(folio); folio_put(folio); } else { node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), -folio_nr_pages(folio)); folio_putback_lru(folio); } } } /* Must be called with an elevated refcount on the non-hugetlb folio */ bool isolate_folio_to_list(struct folio *folio, struct list_head *list) { bool isolated, lru; if (folio_test_hugetlb(folio)) return folio_isolate_hugetlb(folio, list); lru = !__folio_test_movable(folio); if (lru) isolated = folio_isolate_lru(folio); else isolated = isolate_movable_page(&folio->page, ISOLATE_UNEVICTABLE); if (!isolated) return false; list_add(&folio->lru, list); if (lru) node_stat_add_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio)); return true; } static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw, struct folio *folio, unsigned long idx) { struct page *page = folio_page(folio, idx); bool contains_data; pte_t newpte; void *addr; if (PageCompound(page)) return false; VM_BUG_ON_PAGE(!PageAnon(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(pte_present(ptep_get(pvmw->pte)), page); if (folio_test_mlocked(folio) || (pvmw->vma->vm_flags & VM_LOCKED) || mm_forbids_zeropage(pvmw->vma->vm_mm)) return false; /* * The pmd entry mapping the old thp was flushed and the pte mapping * this subpage has been non present. If the subpage is only zero-filled * then map it to the shared zeropage. */ addr = kmap_local_page(page); contains_data = memchr_inv(addr, 0, PAGE_SIZE); kunmap_local(addr); if (contains_data) return false; newpte = pte_mkspecial(pfn_pte(my_zero_pfn(pvmw->address), pvmw->vma->vm_page_prot)); set_pte_at(pvmw->vma->vm_mm, pvmw->address, pvmw->pte, newpte); dec_mm_counter(pvmw->vma->vm_mm, mm_counter(folio)); return true; } struct rmap_walk_arg { struct folio *folio; bool map_unused_to_zeropage; }; /* * Restore a potential migration pte to a working pte entry */ static bool remove_migration_pte(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg) { struct rmap_walk_arg *rmap_walk_arg = arg; DEFINE_FOLIO_VMA_WALK(pvmw, rmap_walk_arg->folio, vma, addr, PVMW_SYNC | PVMW_MIGRATION); while (page_vma_mapped_walk(&pvmw)) { rmap_t rmap_flags = RMAP_NONE; pte_t old_pte; pte_t pte; swp_entry_t entry; struct page *new; unsigned long idx = 0; /* pgoff is invalid for ksm pages, but they are never large */ if (folio_test_large(folio) && !folio_test_hugetlb(folio)) idx = linear_page_index(vma, pvmw.address) - pvmw.pgoff; new = folio_page(folio, idx); #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION /* PMD-mapped THP migration entry */ if (!pvmw.pte) { VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) || !folio_test_pmd_mappable(folio), folio); remove_migration_pmd(&pvmw, new); continue; } #endif if (rmap_walk_arg->map_unused_to_zeropage && try_to_map_unused_to_zeropage(&pvmw, folio, idx)) continue; folio_get(folio); pte = mk_pte(new, READ_ONCE(vma->vm_page_prot)); old_pte = ptep_get(pvmw.pte); entry = pte_to_swp_entry(old_pte); if (!is_migration_entry_young(entry)) pte = pte_mkold(pte); if (folio_test_dirty(folio) && is_migration_entry_dirty(entry)) pte = pte_mkdirty(pte); if (pte_swp_soft_dirty(old_pte)) pte = pte_mksoft_dirty(pte); else pte = pte_clear_soft_dirty(pte); if (is_writable_migration_entry(entry)) pte = pte_mkwrite(pte, vma); else if (pte_swp_uffd_wp(old_pte)) pte = pte_mkuffd_wp(pte); if (folio_test_anon(folio) && !is_readable_migration_entry(entry)) rmap_flags |= RMAP_EXCLUSIVE; if (unlikely(is_device_private_page(new))) { if (pte_write(pte)) entry = make_writable_device_private_entry( page_to_pfn(new)); else entry = make_readable_device_private_entry( page_to_pfn(new)); pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(old_pte)) pte = pte_swp_mksoft_dirty(pte); if (pte_swp_uffd_wp(old_pte)) pte = pte_swp_mkuffd_wp(pte); } #ifdef CONFIG_HUGETLB_PAGE if (folio_test_hugetlb(folio)) { struct hstate *h = hstate_vma(vma); unsigned int shift = huge_page_shift(h); unsigned long psize = huge_page_size(h); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (folio_test_anon(folio)) hugetlb_add_anon_rmap(folio, vma, pvmw.address, rmap_flags); else hugetlb_add_file_rmap(folio); set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte, psize); } else #endif { if (folio_test_anon(folio)) folio_add_anon_rmap_pte(folio, new, vma, pvmw.address, rmap_flags); else folio_add_file_rmap_pte(folio, new, vma); set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); } if (READ_ONCE(vma->vm_flags) & VM_LOCKED) mlock_drain_local(); trace_remove_migration_pte(pvmw.address, pte_val(pte), compound_order(new)); /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, pvmw.address, pvmw.pte); } return true; } /* * Get rid of all migration entries and replace them by * references to the indicated page. */ void remove_migration_ptes(struct folio *src, struct folio *dst, int flags) { struct rmap_walk_arg rmap_walk_arg = { .folio = src, .map_unused_to_zeropage = flags & RMP_USE_SHARED_ZEROPAGE, }; struct rmap_walk_control rwc = { .rmap_one = remove_migration_pte, .arg = &rmap_walk_arg, }; VM_BUG_ON_FOLIO((flags & RMP_USE_SHARED_ZEROPAGE) && (src != dst), src); if (flags & RMP_LOCKED) rmap_walk_locked(dst, &rwc); else rmap_walk(dst, &rwc); } /* * Something used the pte of a page under migration. We need to * get to the page and wait until migration is finished. * When we return from this function the fault will be retried. */ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { spinlock_t *ptl; pte_t *ptep; pte_t pte; swp_entry_t entry; ptep = pte_offset_map_lock(mm, pmd, address, &ptl); if (!ptep) return; pte = ptep_get(ptep); pte_unmap(ptep); if (!is_swap_pte(pte)) goto out; entry = pte_to_swp_entry(pte); if (!is_migration_entry(entry)) goto out; migration_entry_wait_on_locked(entry, ptl); return; out: spin_unlock(ptl); } #ifdef CONFIG_HUGETLB_PAGE /* * The vma read lock must be held upon entry. Holding that lock prevents either * the pte or the ptl from being freed. * * This function will release the vma lock before returning. */ void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), vma->vm_mm, ptep); pte_t pte; hugetlb_vma_assert_locked(vma); spin_lock(ptl); pte = huge_ptep_get(vma->vm_mm, addr, ptep); if (unlikely(!is_hugetlb_entry_migration(pte))) { spin_unlock(ptl); hugetlb_vma_unlock_read(vma); } else { /* * If migration entry existed, safe to release vma lock * here because the pgtable page won't be freed without the * pgtable lock released. See comment right above pgtable * lock release in migration_entry_wait_on_locked(). */ hugetlb_vma_unlock_read(vma); migration_entry_wait_on_locked(pte_to_swp_entry(pte), ptl); } } #endif #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl; ptl = pmd_lock(mm, pmd); if (!is_pmd_migration_entry(*pmd)) goto unlock; migration_entry_wait_on_locked(pmd_to_swp_entry(*pmd), ptl); return; unlock: spin_unlock(ptl); } #endif static int folio_expected_refs(struct address_space *mapping, struct folio *folio) { int refs = 1; if (!mapping) return refs; refs += folio_nr_pages(folio); if (folio_test_private(folio)) refs++; return refs; } /* * Replace the folio in the mapping. * * The number of remaining references must be: * 1 for anonymous folios without a mapping * 2 for folios with a mapping * 3 for folios with a mapping and the private flag set. */ static int __folio_migrate_mapping(struct address_space *mapping, struct folio *newfolio, struct folio *folio, int expected_count) { XA_STATE(xas, &mapping->i_pages, folio_index(folio)); struct zone *oldzone, *newzone; int dirty; long nr = folio_nr_pages(folio); long entries, i; if (!mapping) { /* Take off deferred split queue while frozen and memcg set */ if (folio_test_large(folio) && folio_test_large_rmappable(folio)) { if (!folio_ref_freeze(folio, expected_count)) return -EAGAIN; folio_unqueue_deferred_split(folio); folio_ref_unfreeze(folio, expected_count); } /* No turning back from here */ newfolio->index = folio->index; newfolio->mapping = folio->mapping; if (folio_test_anon(folio) && folio_test_large(folio)) mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); if (folio_test_swapbacked(folio)) __folio_set_swapbacked(newfolio); return MIGRATEPAGE_SUCCESS; } oldzone = folio_zone(folio); newzone = folio_zone(newfolio); xas_lock_irq(&xas); if (!folio_ref_freeze(folio, expected_count)) { xas_unlock_irq(&xas); return -EAGAIN; } /* Take off deferred split queue while frozen and memcg set */ folio_unqueue_deferred_split(folio); /* * Now we know that no one else is looking at the folio: * no turning back from here. */ newfolio->index = folio->index; newfolio->mapping = folio->mapping; if (folio_test_anon(folio) && folio_test_large(folio)) mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); folio_ref_add(newfolio, nr); /* add cache reference */ if (folio_test_swapbacked(folio)) __folio_set_swapbacked(newfolio); if (folio_test_swapcache(folio)) { folio_set_swapcache(newfolio); newfolio->private = folio_get_private(folio); entries = nr; } else { entries = 1; } /* Move dirty while folio refs frozen and newfolio not yet exposed */ dirty = folio_test_dirty(folio); if (dirty) { folio_clear_dirty(folio); folio_set_dirty(newfolio); } /* Swap cache still stores N entries instead of a high-order entry */ for (i = 0; i < entries; i++) { xas_store(&xas, newfolio); xas_next(&xas); } /* * Drop cache reference from old folio by unfreezing * to one less reference. * We know this isn't the last reference. */ folio_ref_unfreeze(folio, expected_count - nr); xas_unlock(&xas); /* Leave irq disabled to prevent preemption while updating stats */ /* * If moved to a different zone then also account * the folio for that zone. Other VM counters will be * taken care of when we establish references to the * new folio and drop references to the old folio. * * Note that anonymous folios are accounted for * via NR_FILE_PAGES and NR_ANON_MAPPED if they * are mapped to swap space. */ if (newzone != oldzone) { struct lruvec *old_lruvec, *new_lruvec; struct mem_cgroup *memcg; memcg = folio_memcg(folio); old_lruvec = mem_cgroup_lruvec(memcg, oldzone->zone_pgdat); new_lruvec = mem_cgroup_lruvec(memcg, newzone->zone_pgdat); __mod_lruvec_state(old_lruvec, NR_FILE_PAGES, -nr); __mod_lruvec_state(new_lruvec, NR_FILE_PAGES, nr); if (folio_test_swapbacked(folio) && !folio_test_swapcache(folio)) { __mod_lruvec_state(old_lruvec, NR_SHMEM, -nr); __mod_lruvec_state(new_lruvec, NR_SHMEM, nr); if (folio_test_pmd_mappable(folio)) { __mod_lruvec_state(old_lruvec, NR_SHMEM_THPS, -nr); __mod_lruvec_state(new_lruvec, NR_SHMEM_THPS, nr); } } #ifdef CONFIG_SWAP if (folio_test_swapcache(folio)) { __mod_lruvec_state(old_lruvec, NR_SWAPCACHE, -nr); __mod_lruvec_state(new_lruvec, NR_SWAPCACHE, nr); } #endif if (dirty && mapping_can_writeback(mapping)) { __mod_lruvec_state(old_lruvec, NR_FILE_DIRTY, -nr); __mod_zone_page_state(oldzone, NR_ZONE_WRITE_PENDING, -nr); __mod_lruvec_state(new_lruvec, NR_FILE_DIRTY, nr); __mod_zone_page_state(newzone, NR_ZONE_WRITE_PENDING, nr); } } local_irq_enable(); return MIGRATEPAGE_SUCCESS; } int folio_migrate_mapping(struct address_space *mapping, struct folio *newfolio, struct folio *folio, int extra_count) { int expected_count = folio_expected_refs(mapping, folio) + extra_count; if (folio_ref_count(folio) != expected_count) return -EAGAIN; return __folio_migrate_mapping(mapping, newfolio, folio, expected_count); } EXPORT_SYMBOL(folio_migrate_mapping); /* * The expected number of remaining references is the same as that * of folio_migrate_mapping(). */ int migrate_huge_page_move_mapping(struct address_space *mapping, struct folio *dst, struct folio *src) { XA_STATE(xas, &mapping->i_pages, folio_index(src)); int rc, expected_count = folio_expected_refs(mapping, src); if (folio_ref_count(src) != expected_count) return -EAGAIN; rc = folio_mc_copy(dst, src); if (unlikely(rc)) return rc; xas_lock_irq(&xas); if (!folio_ref_freeze(src, expected_count)) { xas_unlock_irq(&xas); return -EAGAIN; } dst->index = src->index; dst->mapping = src->mapping; folio_ref_add(dst, folio_nr_pages(dst)); xas_store(&xas, dst); folio_ref_unfreeze(src, expected_count - folio_nr_pages(src)); xas_unlock_irq(&xas); return MIGRATEPAGE_SUCCESS; } /* * Copy the flags and some other ancillary information */ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) { int cpupid; if (folio_test_referenced(folio)) folio_set_referenced(newfolio); if (folio_test_uptodate(folio)) folio_mark_uptodate(newfolio); if (folio_test_clear_active(folio)) { VM_BUG_ON_FOLIO(folio_test_unevictable(folio), folio); folio_set_active(newfolio); } else if (folio_test_clear_unevictable(folio)) folio_set_unevictable(newfolio); if (folio_test_workingset(folio)) folio_set_workingset(newfolio); if (folio_test_checked(folio)) folio_set_checked(newfolio); /* * PG_anon_exclusive (-> PG_mappedtodisk) is always migrated via * migration entries. We can still have PG_anon_exclusive set on an * effectively unmapped and unreferenced first sub-pages of an * anonymous THP: we can simply copy it here via PG_mappedtodisk. */ if (folio_test_mappedtodisk(folio)) folio_set_mappedtodisk(newfolio); /* Move dirty on pages not done by folio_migrate_mapping() */ if (folio_test_dirty(folio)) folio_set_dirty(newfolio); if (folio_test_young(folio)) folio_set_young(newfolio); if (folio_test_idle(folio)) folio_set_idle(newfolio); folio_migrate_refs(newfolio, folio); /* * Copy NUMA information to the new page, to prevent over-eager * future migrations of this same page. */ cpupid = folio_xchg_last_cpupid(folio, -1); /* * For memory tiering mode, when migrate between slow and fast * memory node, reset cpupid, because that is used to record * page access time in slow memory node. */ if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) { bool f_toptier = node_is_toptier(folio_nid(folio)); bool t_toptier = node_is_toptier(folio_nid(newfolio)); if (f_toptier != t_toptier) cpupid = -1; } folio_xchg_last_cpupid(newfolio, cpupid); folio_migrate_ksm(newfolio, folio); /* * Please do not reorder this without considering how mm/ksm.c's * ksm_get_folio() depends upon ksm_migrate_page() and the * swapcache flag. */ if (folio_test_swapcache(folio)) folio_clear_swapcache(folio); folio_clear_private(folio); /* page->private contains hugetlb specific flags */ if (!folio_test_hugetlb(folio)) folio->private = NULL; /* * If any waiters have accumulated on the new page then * wake them up. */ if (folio_test_writeback(newfolio)) folio_end_writeback(newfolio); /* * PG_readahead shares the same bit with PG_reclaim. The above * end_page_writeback() may clear PG_readahead mistakenly, so set the * bit after that. */ if (folio_test_readahead(folio)) folio_set_readahead(newfolio); folio_copy_owner(newfolio, folio); pgalloc_tag_swap(newfolio, folio); mem_cgroup_migrate(folio, newfolio); } EXPORT_SYMBOL(folio_migrate_flags); /************************************************************ * Migration functions ***********************************************************/ static int __migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, void *src_private, enum migrate_mode mode) { int rc, expected_count = folio_expected_refs(mapping, src); /* Check whether src does not have extra refs before we do more work */ if (folio_ref_count(src) != expected_count) return -EAGAIN; rc = folio_mc_copy(dst, src); if (unlikely(rc)) return rc; rc = __folio_migrate_mapping(mapping, dst, src, expected_count); if (rc != MIGRATEPAGE_SUCCESS) return rc; if (src_private) folio_attach_private(dst, folio_detach_private(src)); folio_migrate_flags(dst, src); return MIGRATEPAGE_SUCCESS; } /** * migrate_folio() - Simple folio migration. * @mapping: The address_space containing the folio. * @dst: The folio to migrate the data to. * @src: The folio containing the current data. * @mode: How to migrate the page. * * Common logic to directly migrate a single LRU folio suitable for * folios that do not have private data. * * Folios are locked upon entry and exit. */ int migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { BUG_ON(folio_test_writeback(src)); /* Writeback must be complete */ return __migrate_folio(mapping, dst, src, NULL, mode); } EXPORT_SYMBOL(migrate_folio); #ifdef CONFIG_BUFFER_HEAD /* Returns true if all buffers are successfully locked */ static bool buffer_migrate_lock_buffers(struct buffer_head *head, enum migrate_mode mode) { struct buffer_head *bh = head; struct buffer_head *failed_bh; do { if (!trylock_buffer(bh)) { if (mode == MIGRATE_ASYNC) goto unlock; if (mode == MIGRATE_SYNC_LIGHT && !buffer_uptodate(bh)) goto unlock; lock_buffer(bh); } bh = bh->b_this_page; } while (bh != head); return true; unlock: /* We failed to lock the buffer and cannot stall. */ failed_bh = bh; bh = head; while (bh != failed_bh) { unlock_buffer(bh); bh = bh->b_this_page; } return false; } static int __buffer_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode, bool check_refs) { struct buffer_head *bh, *head; int rc; int expected_count; head = folio_buffers(src); if (!head) return migrate_folio(mapping, dst, src, mode); /* Check whether page does not have extra refs before we do more work */ expected_count = folio_expected_refs(mapping, src); if (folio_ref_count(src) != expected_count) return -EAGAIN; if (!buffer_migrate_lock_buffers(head, mode)) return -EAGAIN; if (check_refs) { bool busy; bool invalidated = false; recheck_buffers: busy = false; spin_lock(&mapping->i_private_lock); bh = head; do { if (atomic_read(&bh->b_count)) { busy = true; break; } bh = bh->b_this_page; } while (bh != head); if (busy) { if (invalidated) { rc = -EAGAIN; goto unlock_buffers; } spin_unlock(&mapping->i_private_lock); invalidate_bh_lrus(); invalidated = true; goto recheck_buffers; } } rc = filemap_migrate_folio(mapping, dst, src, mode); if (rc != MIGRATEPAGE_SUCCESS) goto unlock_buffers; bh = head; do { folio_set_bh(bh, dst, bh_offset(bh)); bh = bh->b_this_page; } while (bh != head); unlock_buffers: if (check_refs) spin_unlock(&mapping->i_private_lock); bh = head; do { unlock_buffer(bh); bh = bh->b_this_page; } while (bh != head); return rc; } /** * buffer_migrate_folio() - Migration function for folios with buffers. * @mapping: The address space containing @src. * @dst: The folio to migrate to. * @src: The folio to migrate from. * @mode: How to migrate the folio. * * This function can only be used if the underlying filesystem guarantees * that no other references to @src exist. For example attached buffer * heads are accessed only under the folio lock. If your filesystem cannot * provide this guarantee, buffer_migrate_folio_norefs() may be more * appropriate. * * Return: 0 on success or a negative errno on failure. */ int buffer_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { return __buffer_migrate_folio(mapping, dst, src, mode, false); } EXPORT_SYMBOL(buffer_migrate_folio); /** * buffer_migrate_folio_norefs() - Migration function for folios with buffers. * @mapping: The address space containing @src. * @dst: The folio to migrate to. * @src: The folio to migrate from. * @mode: How to migrate the folio. * * Like buffer_migrate_folio() except that this variant is more careful * and checks that there are also no buffer head references. This function * is the right one for mappings where buffer heads are directly looked * up and referenced (such as block device mappings). * * Return: 0 on success or a negative errno on failure. */ int buffer_migrate_folio_norefs(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { return __buffer_migrate_folio(mapping, dst, src, mode, true); } EXPORT_SYMBOL_GPL(buffer_migrate_folio_norefs); #endif /* CONFIG_BUFFER_HEAD */ int filemap_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { return __migrate_folio(mapping, dst, src, folio_get_private(src), mode); } EXPORT_SYMBOL_GPL(filemap_migrate_folio); /* * Writeback a folio to clean the dirty state */ static int writeout(struct address_space *mapping, struct folio *folio) { struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .nr_to_write = 1, .range_start = 0, .range_end = LLONG_MAX, .for_reclaim = 1 }; int rc; if (!mapping->a_ops->writepage) /* No write method for the address space */ return -EINVAL; if (!folio_clear_dirty_for_io(folio)) /* Someone else already triggered a write */ return -EAGAIN; /* * A dirty folio may imply that the underlying filesystem has * the folio on some queue. So the folio must be clean for * migration. Writeout may mean we lose the lock and the * folio state is no longer what we checked for earlier. * At this point we know that the migration attempt cannot * be successful. */ remove_migration_ptes(folio, folio, 0); rc = mapping->a_ops->writepage(&folio->page, &wbc); if (rc != AOP_WRITEPAGE_ACTIVATE) /* unlocked. Relock */ folio_lock(folio); return (rc < 0) ? -EIO : -EAGAIN; } /* * Default handling if a filesystem does not provide a migration function. */ static int fallback_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { if (folio_test_dirty(src)) { /* Only writeback folios in full synchronous migration */ switch (mode) { case MIGRATE_SYNC: break; default: return -EBUSY; } return writeout(mapping, src); } /* * Buffers may be managed in a filesystem specific way. * We must have no buffers or drop them. */ if (!filemap_release_folio(src, GFP_KERNEL)) return mode == MIGRATE_SYNC ? -EAGAIN : -EBUSY; return migrate_folio(mapping, dst, src, mode); } /* * Move a page to a newly allocated page * The page is locked and all ptes have been successfully removed. * * The new page will have replaced the old page if this function * is successful. * * Return value: * < 0 - error code * MIGRATEPAGE_SUCCESS - success */ static int move_to_new_folio(struct folio *dst, struct folio *src, enum migrate_mode mode) { int rc = -EAGAIN; bool is_lru = !__folio_test_movable(src); VM_BUG_ON_FOLIO(!folio_test_locked(src), src); VM_BUG_ON_FOLIO(!folio_test_locked(dst), dst); if (likely(is_lru)) { struct address_space *mapping = folio_mapping(src); if (!mapping) rc = migrate_folio(mapping, dst, src, mode); else if (mapping_inaccessible(mapping)) rc = -EOPNOTSUPP; else if (mapping->a_ops->migrate_folio) /* * Most folios have a mapping and most filesystems * provide a migrate_folio callback. Anonymous folios * are part of swap space which also has its own * migrate_folio callback. This is the most common path * for page migration. */ rc = mapping->a_ops->migrate_folio(mapping, dst, src, mode); else rc = fallback_migrate_folio(mapping, dst, src, mode); } else { const struct movable_operations *mops; /* * In case of non-lru page, it could be released after * isolation step. In that case, we shouldn't try migration. */ VM_BUG_ON_FOLIO(!folio_test_isolated(src), src); if (!folio_test_movable(src)) { rc = MIGRATEPAGE_SUCCESS; folio_clear_isolated(src); goto out; } mops = folio_movable_ops(src); rc = mops->migrate_page(&dst->page, &src->page, mode); WARN_ON_ONCE(rc == MIGRATEPAGE_SUCCESS && !folio_test_isolated(src)); } /* * When successful, old pagecache src->mapping must be cleared before * src is freed; but stats require that PageAnon be left as PageAnon. */ if (rc == MIGRATEPAGE_SUCCESS) { if (__folio_test_movable(src)) { VM_BUG_ON_FOLIO(!folio_test_isolated(src), src); /* * We clear PG_movable under page_lock so any compactor * cannot try to migrate this page. */ folio_clear_isolated(src); } /* * Anonymous and movable src->mapping will be cleared by * free_pages_prepare so don't reset it here for keeping * the type to work PageAnon, for example. */ if (!folio_mapping_flags(src)) src->mapping = NULL; if (likely(!folio_is_zone_device(dst))) flush_dcache_folio(dst); } out: return rc; } /* * To record some information during migration, we use unused private * field of struct folio of the newly allocated destination folio. * This is safe because nobody is using it except us. */ enum { PAGE_WAS_MAPPED = BIT(0), PAGE_WAS_MLOCKED = BIT(1), PAGE_OLD_STATES = PAGE_WAS_MAPPED | PAGE_WAS_MLOCKED, }; static void __migrate_folio_record(struct folio *dst, int old_page_state, struct anon_vma *anon_vma) { dst->private = (void *)anon_vma + old_page_state; } static void __migrate_folio_extract(struct folio *dst, int *old_page_state, struct anon_vma **anon_vmap) { unsigned long private = (unsigned long)dst->private; *anon_vmap = (struct anon_vma *)(private & ~PAGE_OLD_STATES); *old_page_state = private & PAGE_OLD_STATES; dst->private = NULL; } /* Restore the source folio to the original state upon failure */ static void migrate_folio_undo_src(struct folio *src, int page_was_mapped, struct anon_vma *anon_vma, bool locked, struct list_head *ret) { if (page_was_mapped) remove_migration_ptes(src, src, 0); /* Drop an anon_vma reference if we took one */ if (anon_vma) put_anon_vma(anon_vma); if (locked) folio_unlock(src); if (ret) list_move_tail(&src->lru, ret); } /* Restore the destination folio to the original state upon failure */ static void migrate_folio_undo_dst(struct folio *dst, bool locked, free_folio_t put_new_folio, unsigned long private) { if (locked) folio_unlock(dst); if (put_new_folio) put_new_folio(dst, private); else folio_put(dst); } /* Cleanup src folio upon migration success */ static void migrate_folio_done(struct folio *src, enum migrate_reason reason) { /* * Compaction can migrate also non-LRU pages which are * not accounted to NR_ISOLATED_*. They can be recognized * as __folio_test_movable */ if (likely(!__folio_test_movable(src)) && reason != MR_DEMOTION) mod_node_page_state(folio_pgdat(src), NR_ISOLATED_ANON + folio_is_file_lru(src), -folio_nr_pages(src)); if (reason != MR_MEMORY_FAILURE) /* We release the page in page_handle_poison. */ folio_put(src); } /* Obtain the lock on page, remove all ptes. */ static int migrate_folio_unmap(new_folio_t get_new_folio, free_folio_t put_new_folio, unsigned long private, struct folio *src, struct folio **dstp, enum migrate_mode mode, enum migrate_reason reason, struct list_head *ret) { struct folio *dst; int rc = -EAGAIN; int old_page_state = 0; struct anon_vma *anon_vma = NULL; bool is_lru = data_race(!__folio_test_movable(src)); bool locked = false; bool dst_locked = false; if (folio_ref_count(src) == 1) { /* Folio was freed from under us. So we are done. */ folio_clear_active(src); folio_clear_unevictable(src); /* free_pages_prepare() will clear PG_isolated. */ list_del(&src->lru); migrate_folio_done(src, reason); return MIGRATEPAGE_SUCCESS; } dst = get_new_folio(src, private); if (!dst) return -ENOMEM; *dstp = dst; dst->private = NULL; if (!folio_trylock(src)) { if (mode == MIGRATE_ASYNC) goto out; /* * It's not safe for direct compaction to call lock_page. * For example, during page readahead pages are added locked * to the LRU. Later, when the IO completes the pages are * marked uptodate and unlocked. However, the queueing * could be merging multiple pages for one bio (e.g. * mpage_readahead). If an allocation happens for the * second or third page, the process can end up locking * the same page twice and deadlocking. Rather than * trying to be clever about what pages can be locked, * avoid the use of lock_page for direct compaction * altogether. */ if (current->flags & PF_MEMALLOC) goto out; /* * In "light" mode, we can wait for transient locks (eg * inserting a page into the page table), but it's not * worth waiting for I/O. */ if (mode == MIGRATE_SYNC_LIGHT && !folio_test_uptodate(src)) goto out; folio_lock(src); } locked = true; if (folio_test_mlocked(src)) old_page_state |= PAGE_WAS_MLOCKED; if (folio_test_writeback(src)) { /* * Only in the case of a full synchronous migration is it * necessary to wait for PageWriteback. In the async case, * the retry loop is too short and in the sync-light case, * the overhead of stalling is too much */ switch (mode) { case MIGRATE_SYNC: break; default: rc = -EBUSY; goto out; } folio_wait_writeback(src); } /* * By try_to_migrate(), src->mapcount goes down to 0 here. In this case, * we cannot notice that anon_vma is freed while we migrate a page. * This get_anon_vma() delays freeing anon_vma pointer until the end * of migration. File cache pages are no problem because of page_lock() * File Caches may use write_page() or lock_page() in migration, then, * just care Anon page here. * * Only folio_get_anon_vma() understands the subtleties of * getting a hold on an anon_vma from outside one of its mms. * But if we cannot get anon_vma, then we won't need it anyway, * because that implies that the anon page is no longer mapped * (and cannot be remapped so long as we hold the page lock). */ if (folio_test_anon(src) && !folio_test_ksm(src)) anon_vma = folio_get_anon_vma(src); /* * Block others from accessing the new page when we get around to * establishing additional references. We are usually the only one * holding a reference to dst at this point. We used to have a BUG * here if folio_trylock(dst) fails, but would like to allow for * cases where there might be a race with the previous use of dst. * This is much like races on refcount of oldpage: just don't BUG(). */ if (unlikely(!folio_trylock(dst))) goto out; dst_locked = true; if (unlikely(!is_lru)) { __migrate_folio_record(dst, old_page_state, anon_vma); return MIGRATEPAGE_UNMAP; } /* * Corner case handling: * 1. When a new swap-cache page is read into, it is added to the LRU * and treated as swapcache but it has no rmap yet. * Calling try_to_unmap() against a src->mapping==NULL page will * trigger a BUG. So handle it here. * 2. An orphaned page (see truncate_cleanup_page) might have * fs-private metadata. The page can be picked up due to memory * offlining. Everywhere else except page reclaim, the page is * invisible to the vm, so the page can not be migrated. So try to * free the metadata, so the page can be freed. */ if (!src->mapping) { if (folio_test_private(src)) { try_to_free_buffers(src); goto out; } } else if (folio_mapped(src)) { /* Establish migration ptes */ VM_BUG_ON_FOLIO(folio_test_anon(src) && !folio_test_ksm(src) && !anon_vma, src); try_to_migrate(src, mode == MIGRATE_ASYNC ? TTU_BATCH_FLUSH : 0); old_page_state |= PAGE_WAS_MAPPED; } if (!folio_mapped(src)) { __migrate_folio_record(dst, old_page_state, anon_vma); return MIGRATEPAGE_UNMAP; } out: /* * A folio that has not been unmapped will be restored to * right list unless we want to retry. */ if (rc == -EAGAIN) ret = NULL; migrate_folio_undo_src(src, old_page_state & PAGE_WAS_MAPPED, anon_vma, locked, ret); migrate_folio_undo_dst(dst, dst_locked, put_new_folio, private); return rc; } /* Migrate the folio to the newly allocated folio in dst. */ static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private, struct folio *src, struct folio *dst, enum migrate_mode mode, enum migrate_reason reason, struct list_head *ret) { int rc; int old_page_state = 0; struct anon_vma *anon_vma = NULL; bool is_lru = !__folio_test_movable(src); struct list_head *prev; __migrate_folio_extract(dst, &old_page_state, &anon_vma); prev = dst->lru.prev; list_del(&dst->lru); rc = move_to_new_folio(dst, src, mode); if (rc) goto out; if (unlikely(!is_lru)) goto out_unlock_both; /* * When successful, push dst to LRU immediately: so that if it * turns out to be an mlocked page, remove_migration_ptes() will * automatically build up the correct dst->mlock_count for it. * * We would like to do something similar for the old page, when * unsuccessful, and other cases when a page has been temporarily * isolated from the unevictable LRU: but this case is the easiest. */ folio_add_lru(dst); if (old_page_state & PAGE_WAS_MLOCKED) lru_add_drain(); if (old_page_state & PAGE_WAS_MAPPED) remove_migration_ptes(src, dst, 0); out_unlock_both: folio_unlock(dst); set_page_owner_migrate_reason(&dst->page, reason); /* * If migration is successful, decrease refcount of dst, * which will not free the page because new page owner increased * refcounter. */ folio_put(dst); /* * A folio that has been migrated has all references removed * and will be freed. */ list_del(&src->lru); /* Drop an anon_vma reference if we took one */ if (anon_vma) put_anon_vma(anon_vma); folio_unlock(src); migrate_folio_done(src, reason); return rc; out: /* * A folio that has not been migrated will be restored to * right list unless we want to retry. */ if (rc == -EAGAIN) { list_add(&dst->lru, prev); __migrate_folio_record(dst, old_page_state, anon_vma); return rc; } migrate_folio_undo_src(src, old_page_state & PAGE_WAS_MAPPED, anon_vma, true, ret); migrate_folio_undo_dst(dst, true, put_new_folio, private); return rc; } /* * Counterpart of unmap_and_move_page() for hugepage migration. * * This function doesn't wait the completion of hugepage I/O * because there is no race between I/O and migration for hugepage. * Note that currently hugepage I/O occurs only in direct I/O * where no lock is held and PG_writeback is irrelevant, * and writeback status of all subpages are counted in the reference * count of the head page (i.e. if all subpages of a 2MB hugepage are * under direct I/O, the reference of the head page is 512 and a bit more.) * This means that when we try to migrate hugepage whose subpages are * doing direct I/O, some references remain after try_to_unmap() and * hugepage migration fails without data corruption. * * There is also no race when direct I/O is issued on the page under migration, * because then pte is replaced with migration swap entry and direct I/O code * will wait in the page fault for migration to complete. */ static int unmap_and_move_huge_page(new_folio_t get_new_folio, free_folio_t put_new_folio, unsigned long private, struct folio *src, int force, enum migrate_mode mode, int reason, struct list_head *ret) { struct folio *dst; int rc = -EAGAIN; int page_was_mapped = 0; struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; if (folio_ref_count(src) == 1) { /* page was freed from under us. So we are done. */ folio_putback_hugetlb(src); return MIGRATEPAGE_SUCCESS; } dst = get_new_folio(src, private); if (!dst) return -ENOMEM; if (!folio_trylock(src)) { if (!force) goto out; switch (mode) { case MIGRATE_SYNC: break; default: goto out; } folio_lock(src); } /* * Check for pages which are in the process of being freed. Without * folio_mapping() set, hugetlbfs specific move page routine will not * be called and we could leak usage counts for subpools. */ if (hugetlb_folio_subpool(src) && !folio_mapping(src)) { rc = -EBUSY; goto out_unlock; } if (folio_test_anon(src)) anon_vma = folio_get_anon_vma(src); if (unlikely(!folio_trylock(dst))) goto put_anon; if (folio_mapped(src)) { enum ttu_flags ttu = 0; if (!folio_test_anon(src)) { /* * In shared mappings, try_to_unmap could potentially * call huge_pmd_unshare. Because of this, take * semaphore in write mode here and set TTU_RMAP_LOCKED * to let lower levels know we have taken the lock. */ mapping = hugetlb_folio_mapping_lock_write(src); if (unlikely(!mapping)) goto unlock_put_anon; ttu = TTU_RMAP_LOCKED; } try_to_migrate(src, ttu); page_was_mapped = 1; if (ttu & TTU_RMAP_LOCKED) i_mmap_unlock_write(mapping); } if (!folio_mapped(src)) rc = move_to_new_folio(dst, src, mode); if (page_was_mapped) remove_migration_ptes(src, rc == MIGRATEPAGE_SUCCESS ? dst : src, 0); unlock_put_anon: folio_unlock(dst); put_anon: if (anon_vma) put_anon_vma(anon_vma); if (rc == MIGRATEPAGE_SUCCESS) { move_hugetlb_state(src, dst, reason); put_new_folio = NULL; } out_unlock: folio_unlock(src); out: if (rc == MIGRATEPAGE_SUCCESS) folio_putback_hugetlb(src); else if (rc != -EAGAIN) list_move_tail(&src->lru, ret); /* * If migration was not successful and there's a freeing callback, * return the folio to that special allocator. Otherwise, simply drop * our additional reference. */ if (put_new_folio) put_new_folio(dst, private); else folio_put(dst); return rc; } static inline int try_split_folio(struct folio *folio, struct list_head *split_folios, enum migrate_mode mode) { int rc; if (mode == MIGRATE_ASYNC) { if (!folio_trylock(folio)) return -EAGAIN; } else { folio_lock(folio); } rc = split_folio_to_list(folio, split_folios); folio_unlock(folio); if (!rc) list_move_tail(&folio->lru, split_folios); return rc; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define NR_MAX_BATCHED_MIGRATION HPAGE_PMD_NR #else #define NR_MAX_BATCHED_MIGRATION 512 #endif #define NR_MAX_MIGRATE_PAGES_RETRY 10 #define NR_MAX_MIGRATE_ASYNC_RETRY 3 #define NR_MAX_MIGRATE_SYNC_RETRY \ (NR_MAX_MIGRATE_PAGES_RETRY - NR_MAX_MIGRATE_ASYNC_RETRY) struct migrate_pages_stats { int nr_succeeded; /* Normal and large folios migrated successfully, in units of base pages */ int nr_failed_pages; /* Normal and large folios failed to be migrated, in units of base pages. Untried folios aren't counted */ int nr_thp_succeeded; /* THP migrated successfully */ int nr_thp_failed; /* THP failed to be migrated */ int nr_thp_split; /* THP split before migrating */ int nr_split; /* Large folio (include THP) split before migrating */ }; /* * Returns the number of hugetlb folios that were not migrated, or an error code * after NR_MAX_MIGRATE_PAGES_RETRY attempts or if no hugetlb folios are movable * any more because the list has become empty or no retryable hugetlb folios * exist any more. It is caller's responsibility to call putback_movable_pages() * only if ret != 0. */ static int migrate_hugetlbs(struct list_head *from, new_folio_t get_new_folio, free_folio_t put_new_folio, unsigned long private, enum migrate_mode mode, int reason, struct migrate_pages_stats *stats, struct list_head *ret_folios) { int retry = 1; int nr_failed = 0; int nr_retry_pages = 0; int pass = 0; struct folio *folio, *folio2; int rc, nr_pages; for (pass = 0; pass < NR_MAX_MIGRATE_PAGES_RETRY && retry; pass++) { retry = 0; nr_retry_pages = 0; list_for_each_entry_safe(folio, folio2, from, lru) { if (!folio_test_hugetlb(folio)) continue; nr_pages = folio_nr_pages(folio); cond_resched(); /* * Migratability of hugepages depends on architectures and * their size. This check is necessary because some callers * of hugepage migration like soft offline and memory * hotremove don't walk through page tables or check whether * the hugepage is pmd-based or not before kicking migration. */ if (!hugepage_migration_supported(folio_hstate(folio))) { nr_failed++; stats->nr_failed_pages += nr_pages; list_move_tail(&folio->lru, ret_folios); continue; } rc = unmap_and_move_huge_page(get_new_folio, put_new_folio, private, folio, pass > 2, mode, reason, ret_folios); /* * The rules are: * Success: hugetlb folio will be put back * -EAGAIN: stay on the from list * -ENOMEM: stay on the from list * Other errno: put on ret_folios list */ switch(rc) { case -ENOMEM: /* * When memory is low, don't bother to try to migrate * other folios, just exit. */ stats->nr_failed_pages += nr_pages + nr_retry_pages; return -ENOMEM; case -EAGAIN: retry++; nr_retry_pages += nr_pages; break; case MIGRATEPAGE_SUCCESS: stats->nr_succeeded += nr_pages; break; default: /* * Permanent failure (-EBUSY, etc.): * unlike -EAGAIN case, the failed folio is * removed from migration folio list and not * retried in the next outer loop. */ nr_failed++; stats->nr_failed_pages += nr_pages; break; } } } /* * nr_failed is number of hugetlb folios failed to be migrated. After * NR_MAX_MIGRATE_PAGES_RETRY attempts, give up and count retried hugetlb * folios as failed. */ nr_failed += retry; stats->nr_failed_pages += nr_retry_pages; return nr_failed; } static void migrate_folios_move(struct list_head *src_folios, struct list_head *dst_folios, free_folio_t put_new_folio, unsigned long private, enum migrate_mode mode, int reason, struct list_head *ret_folios, struct migrate_pages_stats *stats, int *retry, int *thp_retry, int *nr_failed, int *nr_retry_pages) { struct folio *folio, *folio2, *dst, *dst2; bool is_thp; int nr_pages; int rc; dst = list_first_entry(dst_folios, struct folio, lru); dst2 = list_next_entry(dst, lru); list_for_each_entry_safe(folio, folio2, src_folios, lru) { is_thp = folio_test_large(folio) && folio_test_pmd_mappable(folio); nr_pages = folio_nr_pages(folio); cond_resched(); rc = migrate_folio_move(put_new_folio, private, folio, dst, mode, reason, ret_folios); /* * The rules are: * Success: folio will be freed * -EAGAIN: stay on the unmap_folios list * Other errno: put on ret_folios list */ switch (rc) { case -EAGAIN: *retry += 1; *thp_retry += is_thp; *nr_retry_pages += nr_pages; break; case MIGRATEPAGE_SUCCESS: stats->nr_succeeded += nr_pages; stats->nr_thp_succeeded += is_thp; break; default: *nr_failed += 1; stats->nr_thp_failed += is_thp; stats->nr_failed_pages += nr_pages; break; } dst = dst2; dst2 = list_next_entry(dst, lru); } } static void migrate_folios_undo(struct list_head *src_folios, struct list_head *dst_folios, free_folio_t put_new_folio, unsigned long private, struct list_head *ret_folios) { struct folio *folio, *folio2, *dst, *dst2; dst = list_first_entry(dst_folios, struct folio, lru); dst2 = list_next_entry(dst, lru); list_for_each_entry_safe(folio, folio2, src_folios, lru) { int old_page_state = 0; struct anon_vma *anon_vma = NULL; __migrate_folio_extract(dst, &old_page_state, &anon_vma); migrate_folio_undo_src(folio, old_page_state & PAGE_WAS_MAPPED, anon_vma, true, ret_folios); list_del(&dst->lru); migrate_folio_undo_dst(dst, true, put_new_folio, private); dst = dst2; dst2 = list_next_entry(dst, lru); } } /* * migrate_pages_batch() first unmaps folios in the from list as many as * possible, then move the unmapped folios. * * We only batch migration if mode == MIGRATE_ASYNC to avoid to wait a * lock or bit when we have locked more than one folio. Which may cause * deadlock (e.g., for loop device). So, if mode != MIGRATE_ASYNC, the * length of the from list must be <= 1. */ static int migrate_pages_batch(struct list_head *from, new_folio_t get_new_folio, free_folio_t put_new_folio, unsigned long private, enum migrate_mode mode, int reason, struct list_head *ret_folios, struct list_head *split_folios, struct migrate_pages_stats *stats, int nr_pass) { int retry = 1; int thp_retry = 1; int nr_failed = 0; int nr_retry_pages = 0; int pass = 0; bool is_thp = false; bool is_large = false; struct folio *folio, *folio2, *dst = NULL; int rc, rc_saved = 0, nr_pages; LIST_HEAD(unmap_folios); LIST_HEAD(dst_folios); bool nosplit = (reason == MR_NUMA_MISPLACED); VM_WARN_ON_ONCE(mode != MIGRATE_ASYNC && !list_empty(from) && !list_is_singular(from)); for (pass = 0; pass < nr_pass && retry; pass++) { retry = 0; thp_retry = 0; nr_retry_pages = 0; list_for_each_entry_safe(folio, folio2, from, lru) { is_large = folio_test_large(folio); is_thp = folio_test_pmd_mappable(folio); nr_pages = folio_nr_pages(folio); cond_resched(); /* * The rare folio on the deferred split list should * be split now. It should not count as a failure: * but increment nr_failed because, without doing so, * migrate_pages() may report success with (split but * unmigrated) pages still on its fromlist; whereas it * always reports success when its fromlist is empty. * stats->nr_thp_failed should be increased too, * otherwise stats inconsistency will happen when * migrate_pages_batch is called via migrate_pages() * with MIGRATE_SYNC and MIGRATE_ASYNC. * * Only check it without removing it from the list. * Since the folio can be on deferred_split_scan() * local list and removing it can cause the local list * corruption. Folio split process below can handle it * with the help of folio_ref_freeze(). * * nr_pages > 2 is needed to avoid checking order-1 * page cache folios. They exist, in contrast to * non-existent order-1 anonymous folios, and do not * use _deferred_list. */ if (nr_pages > 2 && !list_empty(&folio->_deferred_list) && folio_test_partially_mapped(folio)) { if (!try_split_folio(folio, split_folios, mode)) { nr_failed++; stats->nr_thp_failed += is_thp; stats->nr_thp_split += is_thp; stats->nr_split++; continue; } } /* * Large folio migration might be unsupported or * the allocation might be failed so we should retry * on the same folio with the large folio split * to normal folios. * * Split folios are put in split_folios, and * we will migrate them after the rest of the * list is processed. */ if (!thp_migration_supported() && is_thp) { nr_failed++; stats->nr_thp_failed++; if (!try_split_folio(folio, split_folios, mode)) { stats->nr_thp_split++; stats->nr_split++; continue; } stats->nr_failed_pages += nr_pages; list_move_tail(&folio->lru, ret_folios); continue; } rc = migrate_folio_unmap(get_new_folio, put_new_folio, private, folio, &dst, mode, reason, ret_folios); /* * The rules are: * Success: folio will be freed * Unmap: folio will be put on unmap_folios list, * dst folio put on dst_folios list * -EAGAIN: stay on the from list * -ENOMEM: stay on the from list * Other errno: put on ret_folios list */ switch(rc) { case -ENOMEM: /* * When memory is low, don't bother to try to migrate * other folios, move unmapped folios, then exit. */ nr_failed++; stats->nr_thp_failed += is_thp; /* Large folio NUMA faulting doesn't split to retry. */ if (is_large && !nosplit) { int ret = try_split_folio(folio, split_folios, mode); if (!ret) { stats->nr_thp_split += is_thp; stats->nr_split++; break; } else if (reason == MR_LONGTERM_PIN && ret == -EAGAIN) { /* * Try again to split large folio to * mitigate the failure of longterm pinning. */ retry++; thp_retry += is_thp; nr_retry_pages += nr_pages; /* Undo duplicated failure counting. */ nr_failed--; stats->nr_thp_failed -= is_thp; break; } } stats->nr_failed_pages += nr_pages + nr_retry_pages; /* nr_failed isn't updated for not used */ stats->nr_thp_failed += thp_retry; rc_saved = rc; if (list_empty(&unmap_folios)) goto out; else goto move; case -EAGAIN: retry++; thp_retry += is_thp; nr_retry_pages += nr_pages; break; case MIGRATEPAGE_SUCCESS: stats->nr_succeeded += nr_pages; stats->nr_thp_succeeded += is_thp; break; case MIGRATEPAGE_UNMAP: list_move_tail(&folio->lru, &unmap_folios); list_add_tail(&dst->lru, &dst_folios); break; default: /* * Permanent failure (-EBUSY, etc.): * unlike -EAGAIN case, the failed folio is * removed from migration folio list and not * retried in the next outer loop. */ nr_failed++; stats->nr_thp_failed += is_thp; stats->nr_failed_pages += nr_pages; break; } } } nr_failed += retry; stats->nr_thp_failed += thp_retry; stats->nr_failed_pages += nr_retry_pages; move: /* Flush TLBs for all unmapped folios */ try_to_unmap_flush(); retry = 1; for (pass = 0; pass < nr_pass && retry; pass++) { retry = 0; thp_retry = 0; nr_retry_pages = 0; /* Move the unmapped folios */ migrate_folios_move(&unmap_folios, &dst_folios, put_new_folio, private, mode, reason, ret_folios, stats, &retry, &thp_retry, &nr_failed, &nr_retry_pages); } nr_failed += retry; stats->nr_thp_failed += thp_retry; stats->nr_failed_pages += nr_retry_pages; rc = rc_saved ? : nr_failed; out: /* Cleanup remaining folios */ migrate_folios_undo(&unmap_folios, &dst_folios, put_new_folio, private, ret_folios); return rc; } static int migrate_pages_sync(struct list_head *from, new_folio_t get_new_folio, free_folio_t put_new_folio, unsigned long private, enum migrate_mode mode, int reason, struct list_head *ret_folios, struct list_head *split_folios, struct migrate_pages_stats *stats) { int rc, nr_failed = 0; LIST_HEAD(folios); struct migrate_pages_stats astats; memset(&astats, 0, sizeof(astats)); /* Try to migrate in batch with MIGRATE_ASYNC mode firstly */ rc = migrate_pages_batch(from, get_new_folio, put_new_folio, private, MIGRATE_ASYNC, reason, &folios, split_folios, &astats, NR_MAX_MIGRATE_ASYNC_RETRY); stats->nr_succeeded += astats.nr_succeeded; stats->nr_thp_succeeded += astats.nr_thp_succeeded; stats->nr_thp_split += astats.nr_thp_split; stats->nr_split += astats.nr_split; if (rc < 0) { stats->nr_failed_pages += astats.nr_failed_pages; stats->nr_thp_failed += astats.nr_thp_failed; list_splice_tail(&folios, ret_folios); return rc; } stats->nr_thp_failed += astats.nr_thp_split; /* * Do not count rc, as pages will be retried below. * Count nr_split only, since it includes nr_thp_split. */ nr_failed += astats.nr_split; /* * Fall back to migrate all failed folios one by one synchronously. All * failed folios except split THPs will be retried, so their failure * isn't counted */ list_splice_tail_init(&folios, from); while (!list_empty(from)) { list_move(from->next, &folios); rc = migrate_pages_batch(&folios, get_new_folio, put_new_folio, private, mode, reason, ret_folios, split_folios, stats, NR_MAX_MIGRATE_SYNC_RETRY); list_splice_tail_init(&folios, ret_folios); if (rc < 0) return rc; nr_failed += rc; } return nr_failed; } /* * migrate_pages - migrate the folios specified in a list, to the free folios * supplied as the target for the page migration * * @from: The list of folios to be migrated. * @get_new_folio: The function used to allocate free folios to be used * as the target of the folio migration. * @put_new_folio: The function used to free target folios if migration * fails, or NULL if no special handling is necessary. * @private: Private data to be passed on to get_new_folio() * @mode: The migration mode that specifies the constraints for * folio migration, if any. * @reason: The reason for folio migration. * @ret_succeeded: Set to the number of folios migrated successfully if * the caller passes a non-NULL pointer. * * The function returns after NR_MAX_MIGRATE_PAGES_RETRY attempts or if no folios * are movable any more because the list has become empty or no retryable folios * exist any more. It is caller's responsibility to call putback_movable_pages() * only if ret != 0. * * Returns the number of {normal folio, large folio, hugetlb} that were not * migrated, or an error code. The number of large folio splits will be * considered as the number of non-migrated large folio, no matter how many * split folios of the large folio are migrated successfully. */ int migrate_pages(struct list_head *from, new_folio_t get_new_folio, free_folio_t put_new_folio, unsigned long private, enum migrate_mode mode, int reason, unsigned int *ret_succeeded) { int rc, rc_gather; int nr_pages; struct folio *folio, *folio2; LIST_HEAD(folios); LIST_HEAD(ret_folios); LIST_HEAD(split_folios); struct migrate_pages_stats stats; trace_mm_migrate_pages_start(mode, reason); memset(&stats, 0, sizeof(stats)); rc_gather = migrate_hugetlbs(from, get_new_folio, put_new_folio, private, mode, reason, &stats, &ret_folios); if (rc_gather < 0) goto out; again: nr_pages = 0; list_for_each_entry_safe(folio, folio2, from, lru) { /* Retried hugetlb folios will be kept in list */ if (folio_test_hugetlb(folio)) { list_move_tail(&folio->lru, &ret_folios); continue; } nr_pages += folio_nr_pages(folio); if (nr_pages >= NR_MAX_BATCHED_MIGRATION) break; } if (nr_pages >= NR_MAX_BATCHED_MIGRATION) list_cut_before(&folios, from, &folio2->lru); else list_splice_init(from, &folios); if (mode == MIGRATE_ASYNC) rc = migrate_pages_batch(&folios, get_new_folio, put_new_folio, private, mode, reason, &ret_folios, &split_folios, &stats, NR_MAX_MIGRATE_PAGES_RETRY); else rc = migrate_pages_sync(&folios, get_new_folio, put_new_folio, private, mode, reason, &ret_folios, &split_folios, &stats); list_splice_tail_init(&folios, &ret_folios); if (rc < 0) { rc_gather = rc; list_splice_tail(&split_folios, &ret_folios); goto out; } if (!list_empty(&split_folios)) { /* * Failure isn't counted since all split folios of a large folio * is counted as 1 failure already. And, we only try to migrate * with minimal effort, force MIGRATE_ASYNC mode and retry once. */ migrate_pages_batch(&split_folios, get_new_folio, put_new_folio, private, MIGRATE_ASYNC, reason, &ret_folios, NULL, &stats, 1); list_splice_tail_init(&split_folios, &ret_folios); } rc_gather += rc; if (!list_empty(from)) goto again; out: /* * Put the permanent failure folio back to migration list, they * will be put back to the right list by the caller. */ list_splice(&ret_folios, from); /* * Return 0 in case all split folios of fail-to-migrate large folios * are migrated successfully. */ if (list_empty(from)) rc_gather = 0; count_vm_events(PGMIGRATE_SUCCESS, stats.nr_succeeded); count_vm_events(PGMIGRATE_FAIL, stats.nr_failed_pages); count_vm_events(THP_MIGRATION_SUCCESS, stats.nr_thp_succeeded); count_vm_events(THP_MIGRATION_FAIL, stats.nr_thp_failed); count_vm_events(THP_MIGRATION_SPLIT, stats.nr_thp_split); trace_mm_migrate_pages(stats.nr_succeeded, stats.nr_failed_pages, stats.nr_thp_succeeded, stats.nr_thp_failed, stats.nr_thp_split, stats.nr_split, mode, reason); if (ret_succeeded) *ret_succeeded = stats.nr_succeeded; return rc_gather; } struct folio *alloc_migration_target(struct folio *src, unsigned long private) { struct migration_target_control *mtc; gfp_t gfp_mask; unsigned int order = 0; int nid; int zidx; mtc = (struct migration_target_control *)private; gfp_mask = mtc->gfp_mask; nid = mtc->nid; if (nid == NUMA_NO_NODE) nid = folio_nid(src); if (folio_test_hugetlb(src)) { struct hstate *h = folio_hstate(src); gfp_mask = htlb_modify_alloc_mask(h, gfp_mask); return alloc_hugetlb_folio_nodemask(h, nid, mtc->nmask, gfp_mask, htlb_allow_alloc_fallback(mtc->reason)); } if (folio_test_large(src)) { /* * clear __GFP_RECLAIM to make the migration callback * consistent with regular THP allocations. */ gfp_mask &= ~__GFP_RECLAIM; gfp_mask |= GFP_TRANSHUGE; order = folio_order(src); } zidx = zone_idx(folio_zone(src)); if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE) gfp_mask |= __GFP_HIGHMEM; return __folio_alloc(gfp_mask, order, nid, mtc->nmask); } #ifdef CONFIG_NUMA static int store_status(int __user *status, int start, int value, int nr) { while (nr-- > 0) { if (put_user(value, status + start)) return -EFAULT; start++; } return 0; } static int do_move_pages_to_node(struct list_head *pagelist, int node) { int err; struct migration_target_control mtc = { .nid = node, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, .reason = MR_SYSCALL, }; err = migrate_pages(pagelist, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL); if (err) putback_movable_pages(pagelist); return err; } static int __add_folio_for_migration(struct folio *folio, int node, struct list_head *pagelist, bool migrate_all) { if (is_zero_folio(folio) || is_huge_zero_folio(folio)) return -EFAULT; if (folio_is_zone_device(folio)) return -ENOENT; if (folio_nid(folio) == node) return 0; if (folio_maybe_mapped_shared(folio) && !migrate_all) return -EACCES; if (folio_test_hugetlb(folio)) { if (folio_isolate_hugetlb(folio, pagelist)) return 1; } else if (folio_isolate_lru(folio)) { list_add_tail(&folio->lru, pagelist); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); return 1; } return -EBUSY; } /* * Resolves the given address to a struct folio, isolates it from the LRU and * puts it to the given pagelist. * Returns: * errno - if the folio cannot be found/isolated * 0 - when it doesn't have to be migrated because it is already on the * target node * 1 - when it has been queued */ static int add_folio_for_migration(struct mm_struct *mm, const void __user *p, int node, struct list_head *pagelist, bool migrate_all) { struct vm_area_struct *vma; struct folio_walk fw; struct folio *folio; unsigned long addr; int err = -EFAULT; mmap_read_lock(mm); addr = (unsigned long)untagged_addr_remote(mm, p); vma = vma_lookup(mm, addr); if (vma && vma_migratable(vma)) { folio = folio_walk_start(&fw, vma, addr, FW_ZEROPAGE); if (folio) { err = __add_folio_for_migration(folio, node, pagelist, migrate_all); folio_walk_end(&fw, vma); } else { err = -ENOENT; } } mmap_read_unlock(mm); return err; } static int move_pages_and_store_status(int node, struct list_head *pagelist, int __user *status, int start, int i, unsigned long nr_pages) { int err; if (list_empty(pagelist)) return 0; err = do_move_pages_to_node(pagelist, node); if (err) { /* * Positive err means the number of failed * pages to migrate. Since we are going to * abort and return the number of non-migrated * pages, so need to include the rest of the * nr_pages that have not been attempted as * well. */ if (err > 0) err += nr_pages - i; return err; } return store_status(status, start, node, i - start); } /* * Migrate an array of page address onto an array of nodes and fill * the corresponding array of status. */ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, unsigned long nr_pages, const void __user * __user *pages, const int __user *nodes, int __user *status, int flags) { compat_uptr_t __user *compat_pages = (void __user *)pages; int current_node = NUMA_NO_NODE; LIST_HEAD(pagelist); int start, i; int err = 0, err1; lru_cache_disable(); for (i = start = 0; i < nr_pages; i++) { const void __user *p; int node; err = -EFAULT; if (in_compat_syscall()) { compat_uptr_t cp; if (get_user(cp, compat_pages + i)) goto out_flush; p = compat_ptr(cp); } else { if (get_user(p, pages + i)) goto out_flush; } if (get_user(node, nodes + i)) goto out_flush; err = -ENODEV; if (node < 0 || node >= MAX_NUMNODES) goto out_flush; if (!node_state(node, N_MEMORY)) goto out_flush; err = -EACCES; if (!node_isset(node, task_nodes)) goto out_flush; if (current_node == NUMA_NO_NODE) { current_node = node; start = i; } else if (node != current_node) { err = move_pages_and_store_status(current_node, &pagelist, status, start, i, nr_pages); if (err) goto out; start = i; current_node = node; } /* * Errors in the page lookup or isolation are not fatal and we simply * report them via status */ err = add_folio_for_migration(mm, p, current_node, &pagelist, flags & MPOL_MF_MOVE_ALL); if (err > 0) { /* The page is successfully queued for migration */ continue; } /* * The move_pages() man page does not have an -EEXIST choice, so * use -EFAULT instead. */ if (err == -EEXIST) err = -EFAULT; /* * If the page is already on the target node (!err), store the * node, otherwise, store the err. */ err = store_status(status, i, err ? : current_node, 1); if (err) goto out_flush; err = move_pages_and_store_status(current_node, &pagelist, status, start, i, nr_pages); if (err) { /* We have accounted for page i */ if (err > 0) err--; goto out; } current_node = NUMA_NO_NODE; } out_flush: /* Make sure we do not overwrite the existing error */ err1 = move_pages_and_store_status(current_node, &pagelist, status, start, i, nr_pages); if (err >= 0) err = err1; out: lru_cache_enable(); return err; } /* * Determine the nodes of an array of pages and store it in an array of status. */ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages, const void __user **pages, int *status) { unsigned long i; mmap_read_lock(mm); for (i = 0; i < nr_pages; i++) { unsigned long addr = (unsigned long)(*pages); struct vm_area_struct *vma; struct folio_walk fw; struct folio *folio; int err = -EFAULT; vma = vma_lookup(mm, addr); if (!vma) goto set_status; folio = folio_walk_start(&fw, vma, addr, FW_ZEROPAGE); if (folio) { if (is_zero_folio(folio) || is_huge_zero_folio(folio)) err = -EFAULT; else if (folio_is_zone_device(folio)) err = -ENOENT; else err = folio_nid(folio); folio_walk_end(&fw, vma); } else { err = -ENOENT; } set_status: *status = err; pages++; status++; } mmap_read_unlock(mm); } static int get_compat_pages_array(const void __user *chunk_pages[], const void __user * __user *pages, unsigned long chunk_nr) { compat_uptr_t __user *pages32 = (compat_uptr_t __user *)pages; compat_uptr_t p; int i; for (i = 0; i < chunk_nr; i++) { if (get_user(p, pages32 + i)) return -EFAULT; chunk_pages[i] = compat_ptr(p); } return 0; } /* * Determine the nodes of a user array of pages and store it in * a user array of status. */ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages, const void __user * __user *pages, int __user *status) { #define DO_PAGES_STAT_CHUNK_NR 16UL const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR]; int chunk_status[DO_PAGES_STAT_CHUNK_NR]; while (nr_pages) { unsigned long chunk_nr = min(nr_pages, DO_PAGES_STAT_CHUNK_NR); if (in_compat_syscall()) { if (get_compat_pages_array(chunk_pages, pages, chunk_nr)) break; } else { if (copy_from_user(chunk_pages, pages, chunk_nr * sizeof(*chunk_pages))) break; } do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status); if (copy_to_user(status, chunk_status, chunk_nr * sizeof(*status))) break; pages += chunk_nr; status += chunk_nr; nr_pages -= chunk_nr; } return nr_pages ? -EFAULT : 0; } static struct mm_struct *find_mm_struct(pid_t pid, nodemask_t *mem_nodes) { struct task_struct *task; struct mm_struct *mm; /* * There is no need to check if current process has the right to modify * the specified process when they are same. */ if (!pid) { mmget(current->mm); *mem_nodes = cpuset_mems_allowed(current); return current->mm; } task = find_get_task_by_vpid(pid); if (!task) { return ERR_PTR(-ESRCH); } /* * Check if this process has the right to modify the specified * process. Use the regular "ptrace_may_access()" checks. */ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { mm = ERR_PTR(-EPERM); goto out; } mm = ERR_PTR(security_task_movememory(task)); if (IS_ERR(mm)) goto out; *mem_nodes = cpuset_mems_allowed(task); mm = get_task_mm(task); out: put_task_struct(task); if (!mm) mm = ERR_PTR(-EINVAL); return mm; } /* * Move a list of pages in the address space of the currently executing * process. */ static int kernel_move_pages(pid_t pid, unsigned long nr_pages, const void __user * __user *pages, const int __user *nodes, int __user *status, int flags) { struct mm_struct *mm; int err; nodemask_t task_nodes; /* Check flags */ if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL)) return -EINVAL; if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) return -EPERM; mm = find_mm_struct(pid, &task_nodes); if (IS_ERR(mm)) return PTR_ERR(mm); if (nodes) err = do_pages_move(mm, task_nodes, nr_pages, pages, nodes, status, flags); else err = do_pages_stat(mm, nr_pages, pages, status); mmput(mm); return err; } SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, const void __user * __user *, pages, const int __user *, nodes, int __user *, status, int, flags) { return kernel_move_pages(pid, nr_pages, pages, nodes, status, flags); } #ifdef CONFIG_NUMA_BALANCING /* * Returns true if this is a safe migration target node for misplaced NUMA * pages. Currently it only checks the watermarks which is crude. */ static bool migrate_balanced_pgdat(struct pglist_data *pgdat, unsigned long nr_migrate_pages) { int z; for (z = pgdat->nr_zones - 1; z >= 0; z--) { struct zone *zone = pgdat->node_zones + z; if (!managed_zone(zone)) continue; /* Avoid waking kswapd by allocating pages_to_migrate pages. */ if (!zone_watermark_ok(zone, 0, high_wmark_pages(zone) + nr_migrate_pages, ZONE_MOVABLE, ALLOC_CMA)) continue; return true; } return false; } static struct folio *alloc_misplaced_dst_folio(struct folio *src, unsigned long data) { int nid = (int) data; int order = folio_order(src); gfp_t gfp = __GFP_THISNODE; if (order > 0) gfp |= GFP_TRANSHUGE_LIGHT; else { gfp |= GFP_HIGHUSER_MOVABLE | __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN; gfp &= ~__GFP_RECLAIM; } return __folio_alloc_node(gfp, order, nid); } /* * Prepare for calling migrate_misplaced_folio() by isolating the folio if * permitted. Must be called with the PTL still held. */ int migrate_misplaced_folio_prepare(struct folio *folio, struct vm_area_struct *vma, int node) { int nr_pages = folio_nr_pages(folio); pg_data_t *pgdat = NODE_DATA(node); if (folio_is_file_lru(folio)) { /* * Do not migrate file folios that are mapped in multiple * processes with execute permissions as they are probably * shared libraries. * * See folio_maybe_mapped_shared() on possible imprecision * when we cannot easily detect if a folio is shared. */ if ((vma->vm_flags & VM_EXEC) && folio_maybe_mapped_shared(folio)) return -EACCES; /* * Do not migrate dirty folios as not all filesystems can move * dirty folios in MIGRATE_ASYNC mode which is a waste of * cycles. */ if (folio_test_dirty(folio)) return -EAGAIN; } /* Avoid migrating to a node that is nearly full */ if (!migrate_balanced_pgdat(pgdat, nr_pages)) { int z; if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)) return -EAGAIN; for (z = pgdat->nr_zones - 1; z >= 0; z--) { if (managed_zone(pgdat->node_zones + z)) break; } /* * If there are no managed zones, it should not proceed * further. */ if (z < 0) return -EAGAIN; wakeup_kswapd(pgdat->node_zones + z, 0, folio_order(folio), ZONE_MOVABLE); return -EAGAIN; } if (!folio_isolate_lru(folio)) return -EAGAIN; node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), nr_pages); return 0; } /* * Attempt to migrate a misplaced folio to the specified destination * node. Caller is expected to have isolated the folio by calling * migrate_misplaced_folio_prepare(), which will result in an * elevated reference count on the folio. This function will un-isolate the * folio, dereferencing the folio before returning. */ int migrate_misplaced_folio(struct folio *folio, int node) { pg_data_t *pgdat = NODE_DATA(node); int nr_remaining; unsigned int nr_succeeded; LIST_HEAD(migratepages); struct mem_cgroup *memcg = get_mem_cgroup_from_folio(folio); struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); list_add(&folio->lru, &migratepages); nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_folio, NULL, node, MIGRATE_ASYNC, MR_NUMA_MISPLACED, &nr_succeeded); if (nr_remaining && !list_empty(&migratepages)) putback_movable_pages(&migratepages); if (nr_succeeded) { count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_succeeded); count_memcg_events(memcg, NUMA_PAGE_MIGRATE, nr_succeeded); if ((sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) && !node_is_toptier(folio_nid(folio)) && node_is_toptier(node)) mod_lruvec_state(lruvec, PGPROMOTE_SUCCESS, nr_succeeded); } mem_cgroup_put(memcg); BUG_ON(!list_empty(&migratepages)); return nr_remaining ? -EAGAIN : 0; } #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_NUMA */ |
| 21 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) 2011 Instituto Nokia de Tecnologia * Copyright (C) 2014 Marvell International Ltd. * * Authors: * Lauro Ramos Venancio <lauro.venancio@openbossa.org> * Aloisio Almeida Jr <aloisio.almeida@openbossa.org> */ #ifndef __NET_NFC_H #define __NET_NFC_H #include <linux/nfc.h> #include <linux/device.h> #include <linux/skbuff.h> #define nfc_dbg(dev, fmt, ...) dev_dbg((dev), "NFC: " fmt, ##__VA_ARGS__) #define nfc_info(dev, fmt, ...) dev_info((dev), "NFC: " fmt, ##__VA_ARGS__) #define nfc_err(dev, fmt, ...) dev_err((dev), "NFC: " fmt, ##__VA_ARGS__) struct nfc_phy_ops { int (*write)(void *dev_id, struct sk_buff *skb); int (*enable)(void *dev_id); void (*disable)(void *dev_id); }; struct nfc_dev; /** * data_exchange_cb_t - Definition of nfc_data_exchange callback * * @context: nfc_data_exchange cb_context parameter * @skb: response data * @err: If an error has occurred during data exchange, it is the * error number. Zero means no error. * * When a rx or tx package is lost or corrupted or the target gets out * of the operating field, err is -EIO. */ typedef void (*data_exchange_cb_t)(void *context, struct sk_buff *skb, int err); typedef void (*se_io_cb_t)(void *context, u8 *apdu, size_t apdu_len, int err); struct nfc_target; struct nfc_ops { int (*dev_up)(struct nfc_dev *dev); int (*dev_down)(struct nfc_dev *dev); int (*start_poll)(struct nfc_dev *dev, u32 im_protocols, u32 tm_protocols); void (*stop_poll)(struct nfc_dev *dev); int (*dep_link_up)(struct nfc_dev *dev, struct nfc_target *target, u8 comm_mode, u8 *gb, size_t gb_len); int (*dep_link_down)(struct nfc_dev *dev); int (*activate_target)(struct nfc_dev *dev, struct nfc_target *target, u32 protocol); void (*deactivate_target)(struct nfc_dev *dev, struct nfc_target *target, u8 mode); int (*im_transceive)(struct nfc_dev *dev, struct nfc_target *target, struct sk_buff *skb, data_exchange_cb_t cb, void *cb_context); int (*tm_send)(struct nfc_dev *dev, struct sk_buff *skb); int (*check_presence)(struct nfc_dev *dev, struct nfc_target *target); int (*fw_download)(struct nfc_dev *dev, const char *firmware_name); /* Secure Element API */ int (*discover_se)(struct nfc_dev *dev); int (*enable_se)(struct nfc_dev *dev, u32 se_idx); int (*disable_se)(struct nfc_dev *dev, u32 se_idx); int (*se_io) (struct nfc_dev *dev, u32 se_idx, u8 *apdu, size_t apdu_length, se_io_cb_t cb, void *cb_context); }; #define NFC_TARGET_IDX_ANY -1 #define NFC_MAX_GT_LEN 48 #define NFC_ATR_RES_GT_OFFSET 15 #define NFC_ATR_REQ_GT_OFFSET 14 /** * struct nfc_target - NFC target description * * @sens_res: 2 bytes describing the target SENS_RES response, if the target * is a type A one. The %sens_res most significant byte must be byte 2 * as described by the NFC Forum digital specification (i.e. the platform * configuration one) while %sens_res least significant byte is byte 1. * @ats_len: length of Answer To Select in bytes * @ats: Answer To Select returned by an ISO 14443 Type A target upon activation */ struct nfc_target { u32 idx; u32 supported_protocols; u16 sens_res; u8 sel_res; u8 nfcid1_len; u8 nfcid1[NFC_NFCID1_MAXSIZE]; u8 nfcid2_len; u8 nfcid2[NFC_NFCID2_MAXSIZE]; u8 sensb_res_len; u8 sensb_res[NFC_SENSB_RES_MAXSIZE]; u8 sensf_res_len; u8 sensf_res[NFC_SENSF_RES_MAXSIZE]; u8 hci_reader_gate; u8 logical_idx; u8 is_iso15693; u8 iso15693_dsfid; u8 iso15693_uid[NFC_ISO15693_UID_MAXSIZE]; u8 ats_len; u8 ats[NFC_ATS_MAXSIZE]; }; /** * nfc_se - A structure for NFC accessible secure elements. * * @idx: The secure element index. User space will enable or * disable a secure element by its index. * @type: The secure element type. It can be SE_UICC or * SE_EMBEDDED. * @state: The secure element state, either enabled or disabled. * */ struct nfc_se { struct list_head list; u32 idx; u16 type; u16 state; }; /** * nfc_evt_transaction - A struct for NFC secure element event transaction. * * @aid: The application identifier triggering the event * * @aid_len: The application identifier length [5:16] * * @params: The application parameters transmitted during the transaction * * @params_len: The applications parameters length [0:255] * */ #define NFC_MIN_AID_LENGTH 5 #define NFC_MAX_AID_LENGTH 16 #define NFC_MAX_PARAMS_LENGTH 255 #define NFC_EVT_TRANSACTION_AID_TAG 0x81 #define NFC_EVT_TRANSACTION_PARAMS_TAG 0x82 struct nfc_evt_transaction { u32 aid_len; u8 aid[NFC_MAX_AID_LENGTH]; u8 params_len; u8 params[]; } __packed; struct nfc_genl_data { u32 poll_req_portid; struct mutex genl_data_mutex; }; struct nfc_vendor_cmd { __u32 vendor_id; __u32 subcmd; int (*doit)(struct nfc_dev *dev, void *data, size_t data_len); }; struct nfc_dev { int idx; u32 target_next_idx; struct nfc_target *targets; int n_targets; int targets_generation; struct device dev; bool dev_up; bool fw_download_in_progress; u8 rf_mode; bool polling; struct nfc_target *active_target; bool dep_link_up; struct nfc_genl_data genl_data; u32 supported_protocols; struct list_head secure_elements; int tx_headroom; int tx_tailroom; struct timer_list check_pres_timer; struct work_struct check_pres_work; bool shutting_down; struct rfkill *rfkill; const struct nfc_vendor_cmd *vendor_cmds; int n_vendor_cmds; const struct nfc_ops *ops; struct genl_info *cur_cmd_info; }; #define to_nfc_dev(_dev) container_of(_dev, struct nfc_dev, dev) extern const struct class nfc_class; struct nfc_dev *nfc_allocate_device(const struct nfc_ops *ops, u32 supported_protocols, int tx_headroom, int tx_tailroom); /** * nfc_free_device - free nfc device * * @dev: The nfc device to free */ static inline void nfc_free_device(struct nfc_dev *dev) { put_device(&dev->dev); } int nfc_register_device(struct nfc_dev *dev); void nfc_unregister_device(struct nfc_dev *dev); /** * nfc_set_parent_dev - set the parent device * * @nfc_dev: The nfc device whose parent is being set * @dev: The parent device */ static inline void nfc_set_parent_dev(struct nfc_dev *nfc_dev, struct device *dev) { nfc_dev->dev.parent = dev; } /** * nfc_set_drvdata - set driver specific data * * @dev: The nfc device * @data: Pointer to driver specific data */ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data) { dev_set_drvdata(&dev->dev, data); } /** * nfc_get_drvdata - get driver specific data * * @dev: The nfc device */ static inline void *nfc_get_drvdata(const struct nfc_dev *dev) { return dev_get_drvdata(&dev->dev); } /** * nfc_device_name - get the nfc device name * * @dev: The nfc device whose name to return */ static inline const char *nfc_device_name(const struct nfc_dev *dev) { return dev_name(&dev->dev); } struct sk_buff *nfc_alloc_send_skb(struct nfc_dev *dev, struct sock *sk, unsigned int flags, unsigned int size, unsigned int *err); struct sk_buff *nfc_alloc_recv_skb(unsigned int size, gfp_t gfp); int nfc_set_remote_general_bytes(struct nfc_dev *dev, const u8 *gt, u8 gt_len); u8 *nfc_get_local_general_bytes(struct nfc_dev *dev, size_t *gb_len); int nfc_fw_download_done(struct nfc_dev *dev, const char *firmware_name, u32 result); int nfc_targets_found(struct nfc_dev *dev, struct nfc_target *targets, int ntargets); int nfc_target_lost(struct nfc_dev *dev, u32 target_idx); int nfc_dep_link_is_up(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode); int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode, const u8 *gb, size_t gb_len); int nfc_tm_deactivated(struct nfc_dev *dev); int nfc_tm_data_received(struct nfc_dev *dev, struct sk_buff *skb); void nfc_driver_failure(struct nfc_dev *dev, int err); int nfc_se_transaction(struct nfc_dev *dev, u8 se_idx, struct nfc_evt_transaction *evt_transaction); int nfc_se_connectivity(struct nfc_dev *dev, u8 se_idx); int nfc_add_se(struct nfc_dev *dev, u32 se_idx, u16 type); int nfc_remove_se(struct nfc_dev *dev, u32 se_idx); struct nfc_se *nfc_find_se(struct nfc_dev *dev, u32 se_idx); void nfc_send_to_raw_sock(struct nfc_dev *dev, struct sk_buff *skb, u8 payload_type, u8 direction); static inline int nfc_set_vendor_cmds(struct nfc_dev *dev, const struct nfc_vendor_cmd *cmds, int n_cmds) { if (dev->vendor_cmds || dev->n_vendor_cmds) return -EINVAL; dev->vendor_cmds = cmds; dev->n_vendor_cmds = n_cmds; return 0; } struct sk_buff *__nfc_alloc_vendor_cmd_reply_skb(struct nfc_dev *dev, enum nfc_attrs attr, u32 oui, u32 subcmd, int approxlen); int nfc_vendor_cmd_reply(struct sk_buff *skb); /** * nfc_vendor_cmd_alloc_reply_skb - allocate vendor command reply * @dev: nfc device * @oui: vendor oui * @approxlen: an upper bound of the length of the data that will * be put into the skb * * This function allocates and pre-fills an skb for a reply to * a vendor command. Since it is intended for a reply, calling * it outside of a vendor command's doit() operation is invalid. * * The returned skb is pre-filled with some identifying data in * a way that any data that is put into the skb (with skb_put(), * nla_put() or similar) will end up being within the * %NFC_ATTR_VENDOR_DATA attribute, so all that needs to be done * with the skb is adding data for the corresponding userspace tool * which can then read that data out of the vendor data attribute. * You must not modify the skb in any other way. * * When done, call nfc_vendor_cmd_reply() with the skb and return * its error code as the result of the doit() operation. * * Return: An allocated and pre-filled skb. %NULL if any errors happen. */ static inline struct sk_buff * nfc_vendor_cmd_alloc_reply_skb(struct nfc_dev *dev, u32 oui, u32 subcmd, int approxlen) { return __nfc_alloc_vendor_cmd_reply_skb(dev, NFC_ATTR_VENDOR_DATA, oui, subcmd, approxlen); } #endif /* __NET_NFC_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_NOSPEC_BRANCH_H_ #define _ASM_X86_NOSPEC_BRANCH_H_ #include <linux/static_key.h> #include <linux/objtool.h> #include <linux/linkage.h> #include <asm/alternative.h> #include <asm/cpufeatures.h> #include <asm/msr-index.h> #include <asm/unwind_hints.h> #include <asm/percpu.h> /* * Call depth tracking for Intel SKL CPUs to address the RSB underflow * issue in software. * * The tracking does not use a counter. It uses uses arithmetic shift * right on call entry and logical shift left on return. * * The depth tracking variable is initialized to 0x8000.... when the call * depth is zero. The arithmetic shift right sign extends the MSB and * saturates after the 12th call. The shift count is 5 for both directions * so the tracking covers 12 nested calls. * * Call * 0: 0x8000000000000000 0x0000000000000000 * 1: 0xfc00000000000000 0xf000000000000000 * ... * 11: 0xfffffffffffffff8 0xfffffffffffffc00 * 12: 0xffffffffffffffff 0xffffffffffffffe0 * * After a return buffer fill the depth is credited 12 calls before the * next stuffing has to take place. * * There is a inaccuracy for situations like this: * * 10 calls * 5 returns * 3 calls * 4 returns * 3 calls * .... * * The shift count might cause this to be off by one in either direction, * but there is still a cushion vs. the RSB depth. The algorithm does not * claim to be perfect and it can be speculated around by the CPU, but it * is considered that it obfuscates the problem enough to make exploitation * extremely difficult. */ #define RET_DEPTH_SHIFT 5 #define RSB_RET_STUFF_LOOPS 16 #define RET_DEPTH_INIT 0x8000000000000000ULL #define RET_DEPTH_INIT_FROM_CALL 0xfc00000000000000ULL #define RET_DEPTH_CREDIT 0xffffffffffffffffULL #ifdef CONFIG_CALL_THUNKS_DEBUG # define CALL_THUNKS_DEBUG_INC_CALLS \ incq PER_CPU_VAR(__x86_call_count); # define CALL_THUNKS_DEBUG_INC_RETS \ incq PER_CPU_VAR(__x86_ret_count); # define CALL_THUNKS_DEBUG_INC_STUFFS \ incq PER_CPU_VAR(__x86_stuffs_count); # define CALL_THUNKS_DEBUG_INC_CTXSW \ incq PER_CPU_VAR(__x86_ctxsw_count); #else # define CALL_THUNKS_DEBUG_INC_CALLS # define CALL_THUNKS_DEBUG_INC_RETS # define CALL_THUNKS_DEBUG_INC_STUFFS # define CALL_THUNKS_DEBUG_INC_CTXSW #endif #if defined(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) && !defined(COMPILE_OFFSETS) #include <asm/asm-offsets.h> #define CREDIT_CALL_DEPTH \ movq $-1, PER_CPU_VAR(__x86_call_depth); #define RESET_CALL_DEPTH \ xor %eax, %eax; \ bts $63, %rax; \ movq %rax, PER_CPU_VAR(__x86_call_depth); #define RESET_CALL_DEPTH_FROM_CALL \ movb $0xfc, %al; \ shl $56, %rax; \ movq %rax, PER_CPU_VAR(__x86_call_depth); \ CALL_THUNKS_DEBUG_INC_CALLS #define INCREMENT_CALL_DEPTH \ sarq $5, PER_CPU_VAR(__x86_call_depth); \ CALL_THUNKS_DEBUG_INC_CALLS #else #define CREDIT_CALL_DEPTH #define RESET_CALL_DEPTH #define RESET_CALL_DEPTH_FROM_CALL #define INCREMENT_CALL_DEPTH #endif /* * Fill the CPU return stack buffer. * * Each entry in the RSB, if used for a speculative 'ret', contains an * infinite 'pause; lfence; jmp' loop to capture speculative execution. * * This is required in various cases for retpoline and IBRS-based * mitigations for the Spectre variant 2 vulnerability. Sometimes to * eliminate potentially bogus entries from the RSB, and sometimes * purely to ensure that it doesn't get empty, which on some CPUs would * allow predictions from other (unwanted!) sources to be used. * * We define a CPP macro such that it can be used from both .S files and * inline assembly. It's possible to do a .macro and then include that * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. */ #define RETPOLINE_THUNK_SIZE 32 #define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ /* * Common helper for __FILL_RETURN_BUFFER and __FILL_ONE_RETURN. */ #define __FILL_RETURN_SLOT \ ANNOTATE_INTRA_FUNCTION_CALL; \ call 772f; \ int3; \ 772: /* * Stuff the entire RSB. * * Google experimented with loop-unrolling and this turned out to be * the optimal version - two calls, each with their own speculation * trap should their return address end up getting used, in a loop. */ #ifdef CONFIG_X86_64 #define __FILL_RETURN_BUFFER(reg, nr) \ mov $(nr/2), reg; \ 771: \ __FILL_RETURN_SLOT \ __FILL_RETURN_SLOT \ add $(BITS_PER_LONG/8) * 2, %_ASM_SP; \ dec reg; \ jnz 771b; \ /* barrier for jnz misprediction */ \ lfence; \ CREDIT_CALL_DEPTH \ CALL_THUNKS_DEBUG_INC_CTXSW #else /* * i386 doesn't unconditionally have LFENCE, as such it can't * do a loop. */ #define __FILL_RETURN_BUFFER(reg, nr) \ .rept nr; \ __FILL_RETURN_SLOT; \ .endr; \ add $(BITS_PER_LONG/8) * nr, %_ASM_SP; #endif /* * Stuff a single RSB slot. * * To mitigate Post-Barrier RSB speculation, one CALL instruction must be * forced to retire before letting a RET instruction execute. * * On PBRSB-vulnerable CPUs, it is not safe for a RET to be executed * before this point. */ #define __FILL_ONE_RETURN \ __FILL_RETURN_SLOT \ add $(BITS_PER_LONG/8), %_ASM_SP; \ lfence; #ifdef __ASSEMBLER__ /* * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions * vs RETBleed validation. */ #define ANNOTATE_UNRET_SAFE ANNOTATE_RETPOLINE_SAFE /* * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should * eventually turn into its own annotation. */ .macro VALIDATE_UNRET_END #if defined(CONFIG_NOINSTR_VALIDATION) && \ (defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)) ANNOTATE_RETPOLINE_SAFE nop #endif .endm /* * Emits a conditional CS prefix that is compatible with * -mindirect-branch-cs-prefix. */ .macro __CS_PREFIX reg:req .irp rs,r8,r9,r10,r11,r12,r13,r14,r15 .ifc \reg,\rs .byte 0x2e .endif .endr .endm /* * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple * indirect jmp/call which may be susceptible to the Spectre variant 2 * attack. * * NOTE: these do not take kCFI into account and are thus not comparable to C * indirect calls, take care when using. The target of these should be an ENDBR * instruction irrespective of kCFI. */ .macro JMP_NOSPEC reg:req #ifdef CONFIG_MITIGATION_RETPOLINE __CS_PREFIX \reg jmp __x86_indirect_thunk_\reg #else jmp *%\reg int3 #endif .endm .macro CALL_NOSPEC reg:req #ifdef CONFIG_MITIGATION_RETPOLINE __CS_PREFIX \reg call __x86_indirect_thunk_\reg #else call *%\reg #endif .endm /* * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP * monstrosity above, manually. */ .macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2=ALT_NOT(X86_FEATURE_ALWAYS) ALTERNATIVE_2 "jmp .Lskip_rsb_\@", \ __stringify(__FILL_RETURN_BUFFER(\reg,\nr)), \ftr, \ __stringify(nop;nop;__FILL_ONE_RETURN), \ftr2 .Lskip_rsb_\@: .endm /* * The CALL to srso_alias_untrain_ret() must be patched in directly at * the spot where untraining must be done, ie., srso_alias_untrain_ret() * must be the target of a CALL instruction instead of indirectly * jumping to a wrapper which then calls it. Therefore, this macro is * called outside of __UNTRAIN_RET below, for the time being, before the * kernel can support nested alternatives with arbitrary nesting. */ .macro CALL_UNTRAIN_RET #if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO) ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \ "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS #endif .endm /* * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the * return thunk isn't mapped into the userspace tables (then again, AMD * typically has NO_MELTDOWN). * * While retbleed_untrain_ret() doesn't clobber anything but requires stack, * write_ibpb() will clobber AX, CX, DX. * * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point * where we have a stack but before any RET instruction. */ .macro __UNTRAIN_RET ibpb_feature, call_depth_insns #if defined(CONFIG_MITIGATION_RETHUNK) || defined(CONFIG_MITIGATION_IBPB_ENTRY) VALIDATE_UNRET_END CALL_UNTRAIN_RET ALTERNATIVE_2 "", \ "call write_ibpb", \ibpb_feature, \ __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH #endif .endm #define UNTRAIN_RET \ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH) #define UNTRAIN_RET_VM \ __UNTRAIN_RET X86_FEATURE_IBPB_ON_VMEXIT, __stringify(RESET_CALL_DEPTH) #define UNTRAIN_RET_FROM_CALL \ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH_FROM_CALL) .macro CALL_DEPTH_ACCOUNT #ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING ALTERNATIVE "", \ __stringify(INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH #endif .endm /* * Macro to execute VERW instruction that mitigate transient data sampling * attacks such as MDS. On affected systems a microcode update overloaded VERW * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF. * * Note: Only the memory operand variant of VERW clears the CPU buffers. */ .macro CLEAR_CPU_BUFFERS #ifdef CONFIG_X86_64 ALTERNATIVE "", "verw mds_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF #else /* * In 32bit mode, the memory operand must be a %cs reference. The data * segments may not be usable (vm86 mode), and the stack segment may not * be flat (ESPFIX32). */ ALTERNATIVE "", "verw %cs:mds_verw_sel", X86_FEATURE_CLEAR_CPU_BUF #endif .endm #ifdef CONFIG_X86_64 .macro CLEAR_BRANCH_HISTORY ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP .endm .macro CLEAR_BRANCH_HISTORY_VMEXIT ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT .endm #else #define CLEAR_BRANCH_HISTORY #define CLEAR_BRANCH_HISTORY_VMEXIT #endif #else /* __ASSEMBLER__ */ typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; extern retpoline_thunk_t __x86_indirect_thunk_array[]; extern retpoline_thunk_t __x86_indirect_call_thunk_array[]; extern retpoline_thunk_t __x86_indirect_jump_thunk_array[]; #ifdef CONFIG_MITIGATION_RETHUNK extern void __x86_return_thunk(void); #else static inline void __x86_return_thunk(void) {} #endif #ifdef CONFIG_MITIGATION_UNRET_ENTRY extern void retbleed_return_thunk(void); #else static inline void retbleed_return_thunk(void) {} #endif extern void srso_alias_untrain_ret(void); #ifdef CONFIG_MITIGATION_SRSO extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); #else static inline void srso_return_thunk(void) {} static inline void srso_alias_return_thunk(void) {} #endif extern void retbleed_return_thunk(void); extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); extern void entry_untrain_ret(void); extern void write_ibpb(void); #ifdef CONFIG_X86_64 extern void clear_bhb_loop(void); #endif extern void (*x86_return_thunk)(void); extern void __warn_thunk(void); #ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING extern void call_depth_return_thunk(void); #define CALL_DEPTH_ACCOUNT \ ALTERNATIVE("", \ __stringify(INCREMENT_CALL_DEPTH), \ X86_FEATURE_CALL_DEPTH) DECLARE_PER_CPU_CACHE_HOT(u64, __x86_call_depth); #ifdef CONFIG_CALL_THUNKS_DEBUG DECLARE_PER_CPU(u64, __x86_call_count); DECLARE_PER_CPU(u64, __x86_ret_count); DECLARE_PER_CPU(u64, __x86_stuffs_count); DECLARE_PER_CPU(u64, __x86_ctxsw_count); #endif #else /* !CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ static inline void call_depth_return_thunk(void) {} #define CALL_DEPTH_ACCOUNT "" #endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ #ifdef CONFIG_MITIGATION_RETPOLINE #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_thunk_ ## reg; #include <asm/GEN-for-each-reg.h> #undef GEN #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_call_thunk_ ## reg; #include <asm/GEN-for-each-reg.h> #undef GEN #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_jump_thunk_ ## reg; #include <asm/GEN-for-each-reg.h> #undef GEN #ifdef CONFIG_X86_64 /* * Emits a conditional CS prefix that is compatible with * -mindirect-branch-cs-prefix. */ #define __CS_PREFIX(reg) \ ".irp rs,r8,r9,r10,r11,r12,r13,r14,r15\n" \ ".ifc \\rs," reg "\n" \ ".byte 0x2e\n" \ ".endif\n" \ ".endr\n" /* * Inline asm uses the %V modifier which is only in newer GCC * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined. */ #define CALL_NOSPEC __CS_PREFIX("%V[thunk_target]") \ "call __x86_indirect_thunk_%V[thunk_target]\n" # define THUNK_TARGET(addr) [thunk_target] "r" (addr) #else /* CONFIG_X86_32 */ /* * For i386 we use the original ret-equivalent retpoline, because * otherwise we'll run out of registers. We don't care about CET * here, anyway. */ # define CALL_NOSPEC \ ALTERNATIVE_2( \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ " jmp 904f;\n" \ " .align 16\n" \ "901: call 903f;\n" \ "902: pause;\n" \ " lfence;\n" \ " jmp 902b;\n" \ " .align 16\n" \ "903: lea 4(%%esp), %%esp;\n" \ " pushl %[thunk_target];\n" \ " ret;\n" \ " .align 16\n" \ "904: call 901b;\n", \ X86_FEATURE_RETPOLINE, \ "lfence;\n" \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ X86_FEATURE_RETPOLINE_LFENCE) # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif #else /* No retpoline for C / inline asm */ # define CALL_NOSPEC "call *%[thunk_target]\n" # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif /* The Spectre V2 mitigation variants */ enum spectre_v2_mitigation { SPECTRE_V2_NONE, SPECTRE_V2_RETPOLINE, SPECTRE_V2_LFENCE, SPECTRE_V2_EIBRS, SPECTRE_V2_EIBRS_RETPOLINE, SPECTRE_V2_EIBRS_LFENCE, SPECTRE_V2_IBRS, }; /* The indirect branch speculation control variants */ enum spectre_v2_user_mitigation { SPECTRE_V2_USER_NONE, SPECTRE_V2_USER_STRICT, SPECTRE_V2_USER_STRICT_PREFERRED, SPECTRE_V2_USER_PRCTL, SPECTRE_V2_USER_SECCOMP, }; /* The Speculative Store Bypass disable variants */ enum ssb_mitigation { SPEC_STORE_BYPASS_NONE, SPEC_STORE_BYPASS_DISABLE, SPEC_STORE_BYPASS_PRCTL, SPEC_STORE_BYPASS_SECCOMP, }; static __always_inline void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) { asm volatile(ALTERNATIVE("", "wrmsr", %c[feature]) : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32)), [feature] "i" (feature) : "memory"); } static inline void indirect_branch_prediction_barrier(void) { asm_inline volatile(ALTERNATIVE("", "call write_ibpb", X86_FEATURE_IBPB) : ASM_CALL_CONSTRAINT :: "rax", "rcx", "rdx", "memory"); } /* The Intel SPEC CTRL MSR base value cache */ extern u64 x86_spec_ctrl_base; DECLARE_PER_CPU(u64, x86_spec_ctrl_current); extern void update_spec_ctrl_cond(u64 val); extern u64 spec_ctrl_current(void); /* * With retpoline, we must use IBRS to restrict branch prediction * before calling into firmware. * * (Implemented as CPP macros due to header hell.) */ #define firmware_restrict_branch_speculation_start() \ do { \ preempt_disable(); \ alternative_msr_write(MSR_IA32_SPEC_CTRL, \ spec_ctrl_current() | SPEC_CTRL_IBRS, \ X86_FEATURE_USE_IBRS_FW); \ alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, \ X86_FEATURE_USE_IBPB_FW); \ } while (0) #define firmware_restrict_branch_speculation_end() \ do { \ alternative_msr_write(MSR_IA32_SPEC_CTRL, \ spec_ctrl_current(), \ X86_FEATURE_USE_IBRS_FW); \ preempt_enable(); \ } while (0) DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); DECLARE_STATIC_KEY_FALSE(switch_vcpu_ibpb); DECLARE_STATIC_KEY_FALSE(mds_idle_clear); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); extern u16 mds_verw_sel; #include <asm/segment.h> /** * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * This uses the otherwise unused and obsolete VERW instruction in * combination with microcode which triggers a CPU buffer flush when the * instruction is executed. */ static __always_inline void mds_clear_cpu_buffers(void) { static const u16 ds = __KERNEL_DS; /* * Has to be the memory-operand variant because only that * guarantees the CPU buffer flush functionality according to * documentation. The register-operand variant does not. * Works with any segment selector, but a valid writable * data segment is the fastest variant. * * "cc" clobber is required because VERW modifies ZF. */ asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc"); } /** * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability * * Clear CPU buffers if the corresponding static key is enabled */ static __always_inline void mds_idle_clear_cpu_buffers(void) { if (static_branch_likely(&mds_idle_clear)) mds_clear_cpu_buffers(); } #endif /* __ASSEMBLER__ */ #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ |
| 14 1 1 2 2 2 2 2 20 1 19 20 11 2 7 16 9 2 13 5 2 6 4 1 1 1 1 18 11 18 5 2 20 16 16 11 2 9 1 11 11 1 10 5 6 1 2 16 3 2 3 2 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017 Red Hat, Inc. */ #include "fuse_i.h" #include <linux/uio.h> #include <linux/compat.h> #include <linux/fileattr.h> #include <linux/fsverity.h> #define FUSE_VERITY_ENABLE_ARG_MAX_PAGES 256 static ssize_t fuse_send_ioctl(struct fuse_mount *fm, struct fuse_args *args, struct fuse_ioctl_out *outarg) { ssize_t ret; args->out_args[0].size = sizeof(*outarg); args->out_args[0].value = outarg; ret = fuse_simple_request(fm, args); /* Translate ENOSYS, which shouldn't be returned from fs */ if (ret == -ENOSYS) ret = -ENOTTY; if (ret >= 0 && outarg->result == -ENOSYS) outarg->result = -ENOTTY; return ret; } /* * CUSE servers compiled on 32bit broke on 64bit kernels because the * ABI was defined to be 'struct iovec' which is different on 32bit * and 64bit. Fortunately we can determine which structure the server * used from the size of the reply. */ static int fuse_copy_ioctl_iovec_old(struct iovec *dst, void *src, size_t transferred, unsigned count, bool is_compat) { #ifdef CONFIG_COMPAT if (count * sizeof(struct compat_iovec) == transferred) { struct compat_iovec *ciov = src; unsigned i; /* * With this interface a 32bit server cannot support * non-compat (i.e. ones coming from 64bit apps) ioctl * requests */ if (!is_compat) return -EINVAL; for (i = 0; i < count; i++) { dst[i].iov_base = compat_ptr(ciov[i].iov_base); dst[i].iov_len = ciov[i].iov_len; } return 0; } #endif if (count * sizeof(struct iovec) != transferred) return -EIO; memcpy(dst, src, transferred); return 0; } /* Make sure iov_length() won't overflow */ static int fuse_verify_ioctl_iov(struct fuse_conn *fc, struct iovec *iov, size_t count) { size_t n; u32 max = fc->max_pages << PAGE_SHIFT; for (n = 0; n < count; n++, iov++) { if (iov->iov_len > (size_t) max) return -ENOMEM; max -= iov->iov_len; } return 0; } static int fuse_copy_ioctl_iovec(struct fuse_conn *fc, struct iovec *dst, void *src, size_t transferred, unsigned count, bool is_compat) { unsigned i; struct fuse_ioctl_iovec *fiov = src; if (fc->minor < 16) { return fuse_copy_ioctl_iovec_old(dst, src, transferred, count, is_compat); } if (count * sizeof(struct fuse_ioctl_iovec) != transferred) return -EIO; for (i = 0; i < count; i++) { /* Did the server supply an inappropriate value? */ if (fiov[i].base != (unsigned long) fiov[i].base || fiov[i].len != (unsigned long) fiov[i].len) return -EIO; dst[i].iov_base = (void __user *) (unsigned long) fiov[i].base; dst[i].iov_len = (size_t) fiov[i].len; #ifdef CONFIG_COMPAT if (is_compat && (ptr_to_compat(dst[i].iov_base) != fiov[i].base || (compat_size_t) dst[i].iov_len != fiov[i].len)) return -EIO; #endif } return 0; } /* For fs-verity, determine iov lengths from input */ static int fuse_setup_measure_verity(unsigned long arg, struct iovec *iov) { __u16 digest_size; struct fsverity_digest __user *uarg = (void __user *)arg; if (copy_from_user(&digest_size, &uarg->digest_size, sizeof(digest_size))) return -EFAULT; if (digest_size > SIZE_MAX - sizeof(struct fsverity_digest)) return -EINVAL; iov->iov_len = sizeof(struct fsverity_digest) + digest_size; return 0; } static int fuse_setup_enable_verity(unsigned long arg, struct iovec *iov, unsigned int *in_iovs) { struct fsverity_enable_arg enable; struct fsverity_enable_arg __user *uarg = (void __user *)arg; const __u32 max_buffer_len = FUSE_VERITY_ENABLE_ARG_MAX_PAGES * PAGE_SIZE; if (copy_from_user(&enable, uarg, sizeof(enable))) return -EFAULT; if (enable.salt_size > max_buffer_len || enable.sig_size > max_buffer_len) return -ENOMEM; if (enable.salt_size > 0) { iov++; (*in_iovs)++; iov->iov_base = u64_to_user_ptr(enable.salt_ptr); iov->iov_len = enable.salt_size; } if (enable.sig_size > 0) { iov++; (*in_iovs)++; iov->iov_base = u64_to_user_ptr(enable.sig_ptr); iov->iov_len = enable.sig_size; } return 0; } /* * For ioctls, there is no generic way to determine how much memory * needs to be read and/or written. Furthermore, ioctls are allowed * to dereference the passed pointer, so the parameter requires deep * copying but FUSE has no idea whatsoever about what to copy in or * out. * * This is solved by allowing FUSE server to retry ioctl with * necessary in/out iovecs. Let's assume the ioctl implementation * needs to read in the following structure. * * struct a { * char *buf; * size_t buflen; * } * * On the first callout to FUSE server, inarg->in_size and * inarg->out_size will be NULL; then, the server completes the ioctl * with FUSE_IOCTL_RETRY set in out->flags, out->in_iovs set to 1 and * the actual iov array to * * { { .iov_base = inarg.arg, .iov_len = sizeof(struct a) } } * * which tells FUSE to copy in the requested area and retry the ioctl. * On the second round, the server has access to the structure and * from that it can tell what to look for next, so on the invocation, * it sets FUSE_IOCTL_RETRY, out->in_iovs to 2 and iov array to * * { { .iov_base = inarg.arg, .iov_len = sizeof(struct a) }, * { .iov_base = a.buf, .iov_len = a.buflen } } * * FUSE will copy both struct a and the pointed buffer from the * process doing the ioctl and retry ioctl with both struct a and the * buffer. * * This time, FUSE server has everything it needs and completes ioctl * without FUSE_IOCTL_RETRY which finishes the ioctl call. * * Copying data out works the same way. * * Note that if FUSE_IOCTL_UNRESTRICTED is clear, the kernel * automatically initializes in and out iovs by decoding @cmd with * _IOC_* macros and the server is not allowed to request RETRY. This * limits ioctl data transfers to well-formed ioctls and is the forced * behavior for all FUSE servers. */ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg, unsigned int flags) { struct fuse_file *ff = file->private_data; struct fuse_mount *fm = ff->fm; struct fuse_ioctl_in inarg = { .fh = ff->fh, .cmd = cmd, .arg = arg, .flags = flags }; struct fuse_ioctl_out outarg; struct iovec *iov_page = NULL; struct iovec *in_iov = NULL, *out_iov = NULL; unsigned int in_iovs = 0, out_iovs = 0, max_pages; size_t in_size, out_size, c; ssize_t transferred; int err, i; struct iov_iter ii; struct fuse_args_pages ap = {}; #if BITS_PER_LONG == 32 inarg.flags |= FUSE_IOCTL_32BIT; #else if (flags & FUSE_IOCTL_COMPAT) { inarg.flags |= FUSE_IOCTL_32BIT; #ifdef CONFIG_X86_X32_ABI if (in_x32_syscall()) inarg.flags |= FUSE_IOCTL_COMPAT_X32; #endif } #endif /* assume all the iovs returned by client always fits in a page */ BUILD_BUG_ON(sizeof(struct fuse_ioctl_iovec) * FUSE_IOCTL_MAX_IOV > PAGE_SIZE); err = -ENOMEM; ap.folios = fuse_folios_alloc(fm->fc->max_pages, GFP_KERNEL, &ap.descs); iov_page = (struct iovec *) __get_free_page(GFP_KERNEL); if (!ap.folios || !iov_page) goto out; fuse_folio_descs_length_init(ap.descs, 0, fm->fc->max_pages); /* * If restricted, initialize IO parameters as encoded in @cmd. * RETRY from server is not allowed. */ if (!(flags & FUSE_IOCTL_UNRESTRICTED)) { struct iovec *iov = iov_page; iov->iov_base = (void __user *)arg; iov->iov_len = _IOC_SIZE(cmd); if (_IOC_DIR(cmd) & _IOC_WRITE) { in_iov = iov; in_iovs = 1; } if (_IOC_DIR(cmd) & _IOC_READ) { out_iov = iov; out_iovs = 1; } err = 0; switch (cmd) { case FS_IOC_MEASURE_VERITY: err = fuse_setup_measure_verity(arg, iov); break; case FS_IOC_ENABLE_VERITY: err = fuse_setup_enable_verity(arg, iov, &in_iovs); break; } if (err) goto out; } retry: inarg.in_size = in_size = iov_length(in_iov, in_iovs); inarg.out_size = out_size = iov_length(out_iov, out_iovs); /* * Out data can be used either for actual out data or iovs, * make sure there always is at least one page. */ out_size = max_t(size_t, out_size, PAGE_SIZE); max_pages = DIV_ROUND_UP(max(in_size, out_size), PAGE_SIZE); /* make sure there are enough buffer pages and init request with them */ err = -ENOMEM; if (max_pages > fm->fc->max_pages) goto out; while (ap.num_folios < max_pages) { ap.folios[ap.num_folios] = folio_alloc(GFP_KERNEL | __GFP_HIGHMEM, 0); if (!ap.folios[ap.num_folios]) goto out; ap.num_folios++; } /* okay, let's send it to the client */ ap.args.opcode = FUSE_IOCTL; ap.args.nodeid = ff->nodeid; ap.args.in_numargs = 1; ap.args.in_args[0].size = sizeof(inarg); ap.args.in_args[0].value = &inarg; if (in_size) { ap.args.in_numargs++; ap.args.in_args[1].size = in_size; ap.args.in_pages = true; err = -EFAULT; iov_iter_init(&ii, ITER_SOURCE, in_iov, in_iovs, in_size); for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= ap.num_folios); i++) { c = copy_folio_from_iter(ap.folios[i], 0, PAGE_SIZE, &ii); if (c != PAGE_SIZE && iov_iter_count(&ii)) goto out; } } ap.args.out_numargs = 2; ap.args.out_args[1].size = out_size; ap.args.out_pages = true; ap.args.out_argvar = true; transferred = fuse_send_ioctl(fm, &ap.args, &outarg); err = transferred; if (transferred < 0) goto out; /* did it ask for retry? */ if (outarg.flags & FUSE_IOCTL_RETRY) { void *vaddr; /* no retry if in restricted mode */ err = -EIO; if (!(flags & FUSE_IOCTL_UNRESTRICTED)) goto out; in_iovs = outarg.in_iovs; out_iovs = outarg.out_iovs; /* * Make sure things are in boundary, separate checks * are to protect against overflow. */ err = -ENOMEM; if (in_iovs > FUSE_IOCTL_MAX_IOV || out_iovs > FUSE_IOCTL_MAX_IOV || in_iovs + out_iovs > FUSE_IOCTL_MAX_IOV) goto out; vaddr = kmap_local_folio(ap.folios[0], 0); err = fuse_copy_ioctl_iovec(fm->fc, iov_page, vaddr, transferred, in_iovs + out_iovs, (flags & FUSE_IOCTL_COMPAT) != 0); kunmap_local(vaddr); if (err) goto out; in_iov = iov_page; out_iov = in_iov + in_iovs; err = fuse_verify_ioctl_iov(fm->fc, in_iov, in_iovs); if (err) goto out; err = fuse_verify_ioctl_iov(fm->fc, out_iov, out_iovs); if (err) goto out; goto retry; } err = -EIO; if (transferred > inarg.out_size) goto out; err = -EFAULT; iov_iter_init(&ii, ITER_DEST, out_iov, out_iovs, transferred); for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= ap.num_folios); i++) { c = copy_folio_to_iter(ap.folios[i], 0, PAGE_SIZE, &ii); if (c != PAGE_SIZE && iov_iter_count(&ii)) goto out; } err = 0; out: free_page((unsigned long) iov_page); while (ap.num_folios) folio_put(ap.folios[--ap.num_folios]); kfree(ap.folios); return err ? err : outarg.result; } EXPORT_SYMBOL_GPL(fuse_do_ioctl); long fuse_ioctl_common(struct file *file, unsigned int cmd, unsigned long arg, unsigned int flags) { struct inode *inode = file_inode(file); struct fuse_conn *fc = get_fuse_conn(inode); if (!fuse_allow_current_process(fc)) return -EACCES; if (fuse_is_bad(inode)) return -EIO; return fuse_do_ioctl(file, cmd, arg, flags); } long fuse_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return fuse_ioctl_common(file, cmd, arg, 0); } long fuse_file_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return fuse_ioctl_common(file, cmd, arg, FUSE_IOCTL_COMPAT); } static int fuse_priv_ioctl(struct inode *inode, struct fuse_file *ff, unsigned int cmd, void *ptr, size_t size) { struct fuse_mount *fm = ff->fm; struct fuse_ioctl_in inarg; struct fuse_ioctl_out outarg; FUSE_ARGS(args); int err; memset(&inarg, 0, sizeof(inarg)); inarg.fh = ff->fh; inarg.cmd = cmd; #if BITS_PER_LONG == 32 inarg.flags |= FUSE_IOCTL_32BIT; #endif if (S_ISDIR(inode->i_mode)) inarg.flags |= FUSE_IOCTL_DIR; if (_IOC_DIR(cmd) & _IOC_READ) inarg.out_size = size; if (_IOC_DIR(cmd) & _IOC_WRITE) inarg.in_size = size; args.opcode = FUSE_IOCTL; args.nodeid = ff->nodeid; args.in_numargs = 2; args.in_args[0].size = sizeof(inarg); args.in_args[0].value = &inarg; args.in_args[1].size = inarg.in_size; args.in_args[1].value = ptr; args.out_numargs = 2; args.out_args[1].size = inarg.out_size; args.out_args[1].value = ptr; err = fuse_send_ioctl(fm, &args, &outarg); if (!err) { if (outarg.result < 0) err = outarg.result; else if (outarg.flags & FUSE_IOCTL_RETRY) err = -EIO; } return err; } static struct fuse_file *fuse_priv_ioctl_prepare(struct inode *inode) { struct fuse_mount *fm = get_fuse_mount(inode); bool isdir = S_ISDIR(inode->i_mode); if (!fuse_allow_current_process(fm->fc)) return ERR_PTR(-EACCES); if (fuse_is_bad(inode)) return ERR_PTR(-EIO); if (!S_ISREG(inode->i_mode) && !isdir) return ERR_PTR(-ENOTTY); return fuse_file_open(fm, get_node_id(inode), O_RDONLY, isdir); } static void fuse_priv_ioctl_cleanup(struct inode *inode, struct fuse_file *ff) { fuse_file_release(inode, ff, O_RDONLY, NULL, S_ISDIR(inode->i_mode)); } int fuse_fileattr_get(struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); struct fuse_file *ff; unsigned int flags; struct fsxattr xfa; int err; ff = fuse_priv_ioctl_prepare(inode); if (IS_ERR(ff)) return PTR_ERR(ff); if (fa->flags_valid) { err = fuse_priv_ioctl(inode, ff, FS_IOC_GETFLAGS, &flags, sizeof(flags)); if (err) goto cleanup; fileattr_fill_flags(fa, flags); } else { err = fuse_priv_ioctl(inode, ff, FS_IOC_FSGETXATTR, &xfa, sizeof(xfa)); if (err) goto cleanup; fileattr_fill_xflags(fa, xfa.fsx_xflags); fa->fsx_extsize = xfa.fsx_extsize; fa->fsx_nextents = xfa.fsx_nextents; fa->fsx_projid = xfa.fsx_projid; fa->fsx_cowextsize = xfa.fsx_cowextsize; } cleanup: fuse_priv_ioctl_cleanup(inode, ff); return err; } int fuse_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); struct fuse_file *ff; unsigned int flags = fa->flags; struct fsxattr xfa; int err; ff = fuse_priv_ioctl_prepare(inode); if (IS_ERR(ff)) return PTR_ERR(ff); if (fa->flags_valid) { err = fuse_priv_ioctl(inode, ff, FS_IOC_SETFLAGS, &flags, sizeof(flags)); if (err) goto cleanup; } else { memset(&xfa, 0, sizeof(xfa)); xfa.fsx_xflags = fa->fsx_xflags; xfa.fsx_extsize = fa->fsx_extsize; xfa.fsx_nextents = fa->fsx_nextents; xfa.fsx_projid = fa->fsx_projid; xfa.fsx_cowextsize = fa->fsx_cowextsize; err = fuse_priv_ioctl(inode, ff, FS_IOC_FSSETXATTR, &xfa, sizeof(xfa)); } cleanup: fuse_priv_ioctl_cleanup(inode, ff); return err; } |
| 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 | // SPDX-License-Identifier: GPL-2.0 // // Register cache access API // // Copyright 2011 Wolfson Microelectronics plc // // Author: Dimitris Papastamos <dp@opensource.wolfsonmicro.com> #include <linux/bsearch.h> #include <linux/device.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/sort.h> #include "trace.h" #include "internal.h" static const struct regcache_ops *cache_types[] = { ®cache_rbtree_ops, ®cache_maple_ops, ®cache_flat_ops, }; static int regcache_defaults_cmp(const void *a, const void *b) { const struct reg_default *x = a; const struct reg_default *y = b; if (x->reg > y->reg) return 1; else if (x->reg < y->reg) return -1; else return 0; } static void regcache_defaults_swap(void *a, void *b, int size) { struct reg_default *x = a; struct reg_default *y = b; struct reg_default tmp; tmp = *x; *x = *y; *y = tmp; } void regcache_sort_defaults(struct reg_default *defaults, unsigned int ndefaults) { sort(defaults, ndefaults, sizeof(*defaults), regcache_defaults_cmp, regcache_defaults_swap); } EXPORT_SYMBOL_GPL(regcache_sort_defaults); static int regcache_hw_init(struct regmap *map) { int i, j; int ret; int count; unsigned int reg, val; void *tmp_buf; if (!map->num_reg_defaults_raw) return -EINVAL; /* calculate the size of reg_defaults */ for (count = 0, i = 0; i < map->num_reg_defaults_raw; i++) if (regmap_readable(map, i * map->reg_stride) && !regmap_volatile(map, i * map->reg_stride)) count++; /* all registers are unreadable or volatile, so just bypass */ if (!count) { map->cache_bypass = true; return 0; } map->num_reg_defaults = count; map->reg_defaults = kmalloc_array(count, sizeof(struct reg_default), GFP_KERNEL); if (!map->reg_defaults) return -ENOMEM; if (!map->reg_defaults_raw) { bool cache_bypass = map->cache_bypass; dev_warn(map->dev, "No cache defaults, reading back from HW\n"); /* Bypass the cache access till data read from HW */ map->cache_bypass = true; tmp_buf = kmalloc(map->cache_size_raw, GFP_KERNEL); if (!tmp_buf) { ret = -ENOMEM; goto err_free; } ret = regmap_raw_read(map, 0, tmp_buf, map->cache_size_raw); map->cache_bypass = cache_bypass; if (ret == 0) { map->reg_defaults_raw = tmp_buf; map->cache_free = true; } else { kfree(tmp_buf); } } /* fill the reg_defaults */ for (i = 0, j = 0; i < map->num_reg_defaults_raw; i++) { reg = i * map->reg_stride; if (!regmap_readable(map, reg)) continue; if (regmap_volatile(map, reg)) continue; if (map->reg_defaults_raw) { val = regcache_get_val(map, map->reg_defaults_raw, i); } else { bool cache_bypass = map->cache_bypass; map->cache_bypass = true; ret = regmap_read(map, reg, &val); map->cache_bypass = cache_bypass; if (ret != 0) { dev_err(map->dev, "Failed to read %d: %d\n", reg, ret); goto err_free; } } map->reg_defaults[j].reg = reg; map->reg_defaults[j].def = val; j++; } return 0; err_free: kfree(map->reg_defaults); return ret; } int regcache_init(struct regmap *map, const struct regmap_config *config) { int ret; int i; void *tmp_buf; if (map->cache_type == REGCACHE_NONE) { if (config->reg_defaults || config->num_reg_defaults_raw) dev_warn(map->dev, "No cache used with register defaults set!\n"); map->cache_bypass = true; return 0; } if (config->reg_defaults && !config->num_reg_defaults) { dev_err(map->dev, "Register defaults are set without the number!\n"); return -EINVAL; } if (config->num_reg_defaults && !config->reg_defaults) { dev_err(map->dev, "Register defaults number are set without the reg!\n"); return -EINVAL; } for (i = 0; i < config->num_reg_defaults; i++) if (config->reg_defaults[i].reg % map->reg_stride) return -EINVAL; for (i = 0; i < ARRAY_SIZE(cache_types); i++) if (cache_types[i]->type == map->cache_type) break; if (i == ARRAY_SIZE(cache_types)) { dev_err(map->dev, "Could not match cache type: %d\n", map->cache_type); return -EINVAL; } map->num_reg_defaults = config->num_reg_defaults; map->num_reg_defaults_raw = config->num_reg_defaults_raw; map->reg_defaults_raw = config->reg_defaults_raw; map->cache_word_size = BITS_TO_BYTES(config->val_bits); map->cache_size_raw = map->cache_word_size * config->num_reg_defaults_raw; map->cache = NULL; map->cache_ops = cache_types[i]; if (!map->cache_ops->read || !map->cache_ops->write || !map->cache_ops->name) return -EINVAL; /* We still need to ensure that the reg_defaults * won't vanish from under us. We'll need to make * a copy of it. */ if (config->reg_defaults) { tmp_buf = kmemdup_array(config->reg_defaults, map->num_reg_defaults, sizeof(*map->reg_defaults), GFP_KERNEL); if (!tmp_buf) return -ENOMEM; map->reg_defaults = tmp_buf; } else if (map->num_reg_defaults_raw) { /* Some devices such as PMICs don't have cache defaults, * we cope with this by reading back the HW registers and * crafting the cache defaults by hand. */ ret = regcache_hw_init(map); if (ret < 0) return ret; if (map->cache_bypass) return 0; } if (!map->max_register_is_set && map->num_reg_defaults_raw) { map->max_register = (map->num_reg_defaults_raw - 1) * map->reg_stride; map->max_register_is_set = true; } if (map->cache_ops->init) { dev_dbg(map->dev, "Initializing %s cache\n", map->cache_ops->name); map->lock(map->lock_arg); ret = map->cache_ops->init(map); map->unlock(map->lock_arg); if (ret) goto err_free; } return 0; err_free: kfree(map->reg_defaults); if (map->cache_free) kfree(map->reg_defaults_raw); return ret; } void regcache_exit(struct regmap *map) { if (map->cache_type == REGCACHE_NONE) return; BUG_ON(!map->cache_ops); kfree(map->reg_defaults); if (map->cache_free) kfree(map->reg_defaults_raw); if (map->cache_ops->exit) { dev_dbg(map->dev, "Destroying %s cache\n", map->cache_ops->name); map->lock(map->lock_arg); map->cache_ops->exit(map); map->unlock(map->lock_arg); } } /** * regcache_read - Fetch the value of a given register from the cache. * * @map: map to configure. * @reg: The register index. * @value: The value to be returned. * * Return a negative value on failure, 0 on success. */ int regcache_read(struct regmap *map, unsigned int reg, unsigned int *value) { int ret; if (map->cache_type == REGCACHE_NONE) return -EINVAL; BUG_ON(!map->cache_ops); if (!regmap_volatile(map, reg)) { ret = map->cache_ops->read(map, reg, value); if (ret == 0) trace_regmap_reg_read_cache(map, reg, *value); return ret; } return -EINVAL; } /** * regcache_write - Set the value of a given register in the cache. * * @map: map to configure. * @reg: The register index. * @value: The new register value. * * Return a negative value on failure, 0 on success. */ int regcache_write(struct regmap *map, unsigned int reg, unsigned int value) { if (map->cache_type == REGCACHE_NONE) return 0; BUG_ON(!map->cache_ops); if (!regmap_volatile(map, reg)) return map->cache_ops->write(map, reg, value); return 0; } bool regcache_reg_needs_sync(struct regmap *map, unsigned int reg, unsigned int val) { int ret; if (!regmap_writeable(map, reg)) return false; /* If we don't know the chip just got reset, then sync everything. */ if (!map->no_sync_defaults) return true; /* Is this the hardware default? If so skip. */ ret = regcache_lookup_reg(map, reg); if (ret >= 0 && val == map->reg_defaults[ret].def) return false; return true; } static int regcache_default_sync(struct regmap *map, unsigned int min, unsigned int max) { unsigned int reg; for (reg = min; reg <= max; reg += map->reg_stride) { unsigned int val; int ret; if (regmap_volatile(map, reg) || !regmap_writeable(map, reg)) continue; ret = regcache_read(map, reg, &val); if (ret == -ENOENT) continue; if (ret) return ret; if (!regcache_reg_needs_sync(map, reg, val)) continue; map->cache_bypass = true; ret = _regmap_write(map, reg, val); map->cache_bypass = false; if (ret) { dev_err(map->dev, "Unable to sync register %#x. %d\n", reg, ret); return ret; } dev_dbg(map->dev, "Synced register %#x, value %#x\n", reg, val); } return 0; } static int rbtree_all(const void *key, const struct rb_node *node) { return 0; } /** * regcache_sync - Sync the register cache with the hardware. * * @map: map to configure. * * Any registers that should not be synced should be marked as * volatile. In general drivers can choose not to use the provided * syncing functionality if they so require. * * Return a negative value on failure, 0 on success. */ int regcache_sync(struct regmap *map) { int ret = 0; unsigned int i; const char *name; bool bypass; struct rb_node *node; if (WARN_ON(map->cache_type == REGCACHE_NONE)) return -EINVAL; BUG_ON(!map->cache_ops); map->lock(map->lock_arg); /* Remember the initial bypass state */ bypass = map->cache_bypass; dev_dbg(map->dev, "Syncing %s cache\n", map->cache_ops->name); name = map->cache_ops->name; trace_regcache_sync(map, name, "start"); if (!map->cache_dirty) goto out; /* Apply any patch first */ map->cache_bypass = true; for (i = 0; i < map->patch_regs; i++) { ret = _regmap_write(map, map->patch[i].reg, map->patch[i].def); if (ret != 0) { dev_err(map->dev, "Failed to write %x = %x: %d\n", map->patch[i].reg, map->patch[i].def, ret); goto out; } } map->cache_bypass = false; if (map->cache_ops->sync) ret = map->cache_ops->sync(map, 0, map->max_register); else ret = regcache_default_sync(map, 0, map->max_register); if (ret == 0) map->cache_dirty = false; out: /* Restore the bypass state */ map->cache_bypass = bypass; map->no_sync_defaults = false; /* * If we did any paging with cache bypassed and a cached * paging register then the register and cache state might * have gone out of sync, force writes of all the paging * registers. */ rb_for_each(node, NULL, &map->range_tree, rbtree_all) { struct regmap_range_node *this = rb_entry(node, struct regmap_range_node, node); /* If there's nothing in the cache there's nothing to sync */ if (regcache_read(map, this->selector_reg, &i) != 0) continue; ret = _regmap_write(map, this->selector_reg, i); if (ret != 0) { dev_err(map->dev, "Failed to write %x = %x: %d\n", this->selector_reg, i, ret); break; } } map->unlock(map->lock_arg); regmap_async_complete(map); trace_regcache_sync(map, name, "stop"); return ret; } EXPORT_SYMBOL_GPL(regcache_sync); /** * regcache_sync_region - Sync part of the register cache with the hardware. * * @map: map to sync. * @min: first register to sync * @max: last register to sync * * Write all non-default register values in the specified region to * the hardware. * * Return a negative value on failure, 0 on success. */ int regcache_sync_region(struct regmap *map, unsigned int min, unsigned int max) { int ret = 0; const char *name; bool bypass; if (WARN_ON(map->cache_type == REGCACHE_NONE)) return -EINVAL; BUG_ON(!map->cache_ops); map->lock(map->lock_arg); /* Remember the initial bypass state */ bypass = map->cache_bypass; name = map->cache_ops->name; dev_dbg(map->dev, "Syncing %s cache from %d-%d\n", name, min, max); trace_regcache_sync(map, name, "start region"); if (!map->cache_dirty) goto out; map->async = true; if (map->cache_ops->sync) ret = map->cache_ops->sync(map, min, max); else ret = regcache_default_sync(map, min, max); out: /* Restore the bypass state */ map->cache_bypass = bypass; map->async = false; map->no_sync_defaults = false; map->unlock(map->lock_arg); regmap_async_complete(map); trace_regcache_sync(map, name, "stop region"); return ret; } EXPORT_SYMBOL_GPL(regcache_sync_region); /** * regcache_drop_region - Discard part of the register cache * * @map: map to operate on * @min: first register to discard * @max: last register to discard * * Discard part of the register cache. * * Return a negative value on failure, 0 on success. */ int regcache_drop_region(struct regmap *map, unsigned int min, unsigned int max) { int ret = 0; if (!map->cache_ops || !map->cache_ops->drop) return -EINVAL; map->lock(map->lock_arg); trace_regcache_drop_region(map, min, max); ret = map->cache_ops->drop(map, min, max); map->unlock(map->lock_arg); return ret; } EXPORT_SYMBOL_GPL(regcache_drop_region); /** * regcache_cache_only - Put a register map into cache only mode * * @map: map to configure * @enable: flag if changes should be written to the hardware * * When a register map is marked as cache only writes to the register * map API will only update the register cache, they will not cause * any hardware changes. This is useful for allowing portions of * drivers to act as though the device were functioning as normal when * it is disabled for power saving reasons. */ void regcache_cache_only(struct regmap *map, bool enable) { map->lock(map->lock_arg); WARN_ON(map->cache_type != REGCACHE_NONE && map->cache_bypass && enable); map->cache_only = enable; trace_regmap_cache_only(map, enable); map->unlock(map->lock_arg); } EXPORT_SYMBOL_GPL(regcache_cache_only); /** * regcache_mark_dirty - Indicate that HW registers were reset to default values * * @map: map to mark * * Inform regcache that the device has been powered down or reset, so that * on resume, regcache_sync() knows to write out all non-default values * stored in the cache. * * If this function is not called, regcache_sync() will assume that * the hardware state still matches the cache state, modulo any writes that * happened when cache_only was true. */ void regcache_mark_dirty(struct regmap *map) { map->lock(map->lock_arg); map->cache_dirty = true; map->no_sync_defaults = true; map->unlock(map->lock_arg); } EXPORT_SYMBOL_GPL(regcache_mark_dirty); /** * regcache_cache_bypass - Put a register map into cache bypass mode * * @map: map to configure * @enable: flag if changes should not be written to the cache * * When a register map is marked with the cache bypass option, writes * to the register map API will only update the hardware and not * the cache directly. This is useful when syncing the cache back to * the hardware. */ void regcache_cache_bypass(struct regmap *map, bool enable) { map->lock(map->lock_arg); WARN_ON(map->cache_only && enable); map->cache_bypass = enable; trace_regmap_cache_bypass(map, enable); map->unlock(map->lock_arg); } EXPORT_SYMBOL_GPL(regcache_cache_bypass); /** * regcache_reg_cached - Check if a register is cached * * @map: map to check * @reg: register to check * * Reports if a register is cached. */ bool regcache_reg_cached(struct regmap *map, unsigned int reg) { unsigned int val; int ret; map->lock(map->lock_arg); ret = regcache_read(map, reg, &val); map->unlock(map->lock_arg); return ret == 0; } EXPORT_SYMBOL_GPL(regcache_reg_cached); void regcache_set_val(struct regmap *map, void *base, unsigned int idx, unsigned int val) { /* Use device native format if possible */ if (map->format.format_val) { map->format.format_val(base + (map->cache_word_size * idx), val, 0); return; } switch (map->cache_word_size) { case 1: { u8 *cache = base; cache[idx] = val; break; } case 2: { u16 *cache = base; cache[idx] = val; break; } case 4: { u32 *cache = base; cache[idx] = val; break; } default: BUG(); } } unsigned int regcache_get_val(struct regmap *map, const void *base, unsigned int idx) { if (!base) return -EINVAL; /* Use device native format if possible */ if (map->format.parse_val) return map->format.parse_val(regcache_get_val_addr(map, base, idx)); switch (map->cache_word_size) { case 1: { const u8 *cache = base; return cache[idx]; } case 2: { const u16 *cache = base; return cache[idx]; } case 4: { const u32 *cache = base; return cache[idx]; } default: BUG(); } /* unreachable */ return -1; } static int regcache_default_cmp(const void *a, const void *b) { const struct reg_default *_a = a; const struct reg_default *_b = b; return _a->reg - _b->reg; } int regcache_lookup_reg(struct regmap *map, unsigned int reg) { struct reg_default key; struct reg_default *r; key.reg = reg; key.def = 0; r = bsearch(&key, map->reg_defaults, map->num_reg_defaults, sizeof(struct reg_default), regcache_default_cmp); if (r) return r - map->reg_defaults; else return -ENOENT; } static bool regcache_reg_present(unsigned long *cache_present, unsigned int idx) { if (!cache_present) return true; return test_bit(idx, cache_present); } int regcache_sync_val(struct regmap *map, unsigned int reg, unsigned int val) { int ret; if (!regcache_reg_needs_sync(map, reg, val)) return 0; map->cache_bypass = true; ret = _regmap_write(map, reg, val); map->cache_bypass = false; if (ret != 0) { dev_err(map->dev, "Unable to sync register %#x. %d\n", reg, ret); return ret; } dev_dbg(map->dev, "Synced register %#x, value %#x\n", reg, val); return 0; } static int regcache_sync_block_single(struct regmap *map, void *block, unsigned long *cache_present, unsigned int block_base, unsigned int start, unsigned int end) { unsigned int i, regtmp, val; int ret; for (i = start; i < end; i++) { regtmp = block_base + (i * map->reg_stride); if (!regcache_reg_present(cache_present, i) || !regmap_writeable(map, regtmp)) continue; val = regcache_get_val(map, block, i); ret = regcache_sync_val(map, regtmp, val); if (ret != 0) return ret; } return 0; } static int regcache_sync_block_raw_flush(struct regmap *map, const void **data, unsigned int base, unsigned int cur) { size_t val_bytes = map->format.val_bytes; int ret, count; if (*data == NULL) return 0; count = (cur - base) / map->reg_stride; dev_dbg(map->dev, "Writing %zu bytes for %d registers from 0x%x-0x%x\n", count * val_bytes, count, base, cur - map->reg_stride); map->cache_bypass = true; ret = _regmap_raw_write(map, base, *data, count * val_bytes, false); if (ret) dev_err(map->dev, "Unable to sync registers %#x-%#x. %d\n", base, cur - map->reg_stride, ret); map->cache_bypass = false; *data = NULL; return ret; } static int regcache_sync_block_raw(struct regmap *map, void *block, unsigned long *cache_present, unsigned int block_base, unsigned int start, unsigned int end) { unsigned int i, val; unsigned int regtmp = 0; unsigned int base = 0; const void *data = NULL; int ret; for (i = start; i < end; i++) { regtmp = block_base + (i * map->reg_stride); if (!regcache_reg_present(cache_present, i) || !regmap_writeable(map, regtmp)) { ret = regcache_sync_block_raw_flush(map, &data, base, regtmp); if (ret != 0) return ret; continue; } val = regcache_get_val(map, block, i); if (!regcache_reg_needs_sync(map, regtmp, val)) { ret = regcache_sync_block_raw_flush(map, &data, base, regtmp); if (ret != 0) return ret; continue; } if (!data) { data = regcache_get_val_addr(map, block, i); base = regtmp; } } return regcache_sync_block_raw_flush(map, &data, base, regtmp + map->reg_stride); } int regcache_sync_block(struct regmap *map, void *block, unsigned long *cache_present, unsigned int block_base, unsigned int start, unsigned int end) { if (regmap_can_raw_write(map) && !map->use_single_write) return regcache_sync_block_raw(map, block, cache_present, block_base, start, end); else return regcache_sync_block_single(map, block, cache_present, block_base, start, end); } |
| 3 10 1 2 2 2 1 1 14 21 1 15 5 20 12 6 18 18 15 5 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 | // SPDX-License-Identifier: GPL-2.0 /* * Framework for userspace DMA-BUF allocations * * Copyright (C) 2011 Google, Inc. * Copyright (C) 2019 Linaro Ltd. */ #include <linux/cdev.h> #include <linux/device.h> #include <linux/dma-buf.h> #include <linux/dma-heap.h> #include <linux/err.h> #include <linux/list.h> #include <linux/nospec.h> #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/xarray.h> #include <uapi/linux/dma-heap.h> #define DEVNAME "dma_heap" #define NUM_HEAP_MINORS 128 /** * struct dma_heap - represents a dmabuf heap in the system * @name: used for debugging/device-node name * @ops: ops struct for this heap * @priv: private data for this heap * @heap_devt: heap device node * @list: list head connecting to list of heaps * @heap_cdev: heap char device * * Represents a heap of memory from which buffers can be made. */ struct dma_heap { const char *name; const struct dma_heap_ops *ops; void *priv; dev_t heap_devt; struct list_head list; struct cdev heap_cdev; }; static LIST_HEAD(heap_list); static DEFINE_MUTEX(heap_list_lock); static dev_t dma_heap_devt; static struct class *dma_heap_class; static DEFINE_XARRAY_ALLOC(dma_heap_minors); static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len, u32 fd_flags, u64 heap_flags) { struct dma_buf *dmabuf; int fd; /* * Allocations from all heaps have to begin * and end on page boundaries. */ len = PAGE_ALIGN(len); if (!len) return -EINVAL; dmabuf = heap->ops->allocate(heap, len, fd_flags, heap_flags); if (IS_ERR(dmabuf)) return PTR_ERR(dmabuf); fd = dma_buf_fd(dmabuf, fd_flags); if (fd < 0) { dma_buf_put(dmabuf); /* just return, as put will call release and that will free */ } return fd; } static int dma_heap_open(struct inode *inode, struct file *file) { struct dma_heap *heap; heap = xa_load(&dma_heap_minors, iminor(inode)); if (!heap) { pr_err("dma_heap: minor %d unknown.\n", iminor(inode)); return -ENODEV; } /* instance data as context */ file->private_data = heap; nonseekable_open(inode, file); return 0; } static long dma_heap_ioctl_allocate(struct file *file, void *data) { struct dma_heap_allocation_data *heap_allocation = data; struct dma_heap *heap = file->private_data; int fd; if (heap_allocation->fd) return -EINVAL; if (heap_allocation->fd_flags & ~DMA_HEAP_VALID_FD_FLAGS) return -EINVAL; if (heap_allocation->heap_flags & ~DMA_HEAP_VALID_HEAP_FLAGS) return -EINVAL; fd = dma_heap_buffer_alloc(heap, heap_allocation->len, heap_allocation->fd_flags, heap_allocation->heap_flags); if (fd < 0) return fd; heap_allocation->fd = fd; return 0; } static unsigned int dma_heap_ioctl_cmds[] = { DMA_HEAP_IOCTL_ALLOC, }; static long dma_heap_ioctl(struct file *file, unsigned int ucmd, unsigned long arg) { char stack_kdata[128]; char *kdata = stack_kdata; unsigned int kcmd; unsigned int in_size, out_size, drv_size, ksize; int nr = _IOC_NR(ucmd); int ret = 0; if (nr >= ARRAY_SIZE(dma_heap_ioctl_cmds)) return -EINVAL; nr = array_index_nospec(nr, ARRAY_SIZE(dma_heap_ioctl_cmds)); /* Get the kernel ioctl cmd that matches */ kcmd = dma_heap_ioctl_cmds[nr]; /* Figure out the delta between user cmd size and kernel cmd size */ drv_size = _IOC_SIZE(kcmd); out_size = _IOC_SIZE(ucmd); in_size = out_size; if ((ucmd & kcmd & IOC_IN) == 0) in_size = 0; if ((ucmd & kcmd & IOC_OUT) == 0) out_size = 0; ksize = max(max(in_size, out_size), drv_size); /* If necessary, allocate buffer for ioctl argument */ if (ksize > sizeof(stack_kdata)) { kdata = kmalloc(ksize, GFP_KERNEL); if (!kdata) return -ENOMEM; } if (copy_from_user(kdata, (void __user *)arg, in_size) != 0) { ret = -EFAULT; goto err; } /* zero out any difference between the kernel/user structure size */ if (ksize > in_size) memset(kdata + in_size, 0, ksize - in_size); switch (kcmd) { case DMA_HEAP_IOCTL_ALLOC: ret = dma_heap_ioctl_allocate(file, kdata); break; default: ret = -ENOTTY; goto err; } if (copy_to_user((void __user *)arg, kdata, out_size) != 0) ret = -EFAULT; err: if (kdata != stack_kdata) kfree(kdata); return ret; } static const struct file_operations dma_heap_fops = { .owner = THIS_MODULE, .open = dma_heap_open, .unlocked_ioctl = dma_heap_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = dma_heap_ioctl, #endif }; /** * dma_heap_get_drvdata - get per-heap driver data * @heap: DMA-Heap to retrieve private data for * * Returns: * The per-heap data for the heap. */ void *dma_heap_get_drvdata(struct dma_heap *heap) { return heap->priv; } /** * dma_heap_get_name - get heap name * @heap: DMA-Heap to retrieve the name of * * Returns: * The char* for the heap name. */ const char *dma_heap_get_name(struct dma_heap *heap) { return heap->name; } /** * dma_heap_add - adds a heap to dmabuf heaps * @exp_info: information needed to register this heap */ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) { struct dma_heap *heap, *h, *err_ret; struct device *dev_ret; unsigned int minor; int ret; if (!exp_info->name || !strcmp(exp_info->name, "")) { pr_err("dma_heap: Cannot add heap without a name\n"); return ERR_PTR(-EINVAL); } if (!exp_info->ops || !exp_info->ops->allocate) { pr_err("dma_heap: Cannot add heap with invalid ops struct\n"); return ERR_PTR(-EINVAL); } heap = kzalloc(sizeof(*heap), GFP_KERNEL); if (!heap) return ERR_PTR(-ENOMEM); heap->name = exp_info->name; heap->ops = exp_info->ops; heap->priv = exp_info->priv; /* Find unused minor number */ ret = xa_alloc(&dma_heap_minors, &minor, heap, XA_LIMIT(0, NUM_HEAP_MINORS - 1), GFP_KERNEL); if (ret < 0) { pr_err("dma_heap: Unable to get minor number for heap\n"); err_ret = ERR_PTR(ret); goto err0; } /* Create device */ heap->heap_devt = MKDEV(MAJOR(dma_heap_devt), minor); cdev_init(&heap->heap_cdev, &dma_heap_fops); ret = cdev_add(&heap->heap_cdev, heap->heap_devt, 1); if (ret < 0) { pr_err("dma_heap: Unable to add char device\n"); err_ret = ERR_PTR(ret); goto err1; } dev_ret = device_create(dma_heap_class, NULL, heap->heap_devt, NULL, heap->name); if (IS_ERR(dev_ret)) { pr_err("dma_heap: Unable to create device\n"); err_ret = ERR_CAST(dev_ret); goto err2; } mutex_lock(&heap_list_lock); /* check the name is unique */ list_for_each_entry(h, &heap_list, list) { if (!strcmp(h->name, exp_info->name)) { mutex_unlock(&heap_list_lock); pr_err("dma_heap: Already registered heap named %s\n", exp_info->name); err_ret = ERR_PTR(-EINVAL); goto err3; } } /* Add heap to the list */ list_add(&heap->list, &heap_list); mutex_unlock(&heap_list_lock); return heap; err3: device_destroy(dma_heap_class, heap->heap_devt); err2: cdev_del(&heap->heap_cdev); err1: xa_erase(&dma_heap_minors, minor); err0: kfree(heap); return err_ret; } static char *dma_heap_devnode(const struct device *dev, umode_t *mode) { return kasprintf(GFP_KERNEL, "dma_heap/%s", dev_name(dev)); } static int dma_heap_init(void) { int ret; ret = alloc_chrdev_region(&dma_heap_devt, 0, NUM_HEAP_MINORS, DEVNAME); if (ret) return ret; dma_heap_class = class_create(DEVNAME); if (IS_ERR(dma_heap_class)) { unregister_chrdev_region(dma_heap_devt, NUM_HEAP_MINORS); return PTR_ERR(dma_heap_class); } dma_heap_class->devnode = dma_heap_devnode; return 0; } subsys_initcall(dma_heap_init); |
| 2 2 2 2 2 1 2 1 1 2 1 1 3 5 2 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 | // SPDX-License-Identifier: GPL-2.0 /* * Driver for Phoenix RC Flight Controller Adapter * * Copyright (C) 2018 Marcus Folkesson <marcus.folkesson@gmail.com> */ #include <linux/cleanup.h> #include <linux/errno.h> #include <linux/input.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/usb.h> #include <linux/usb/input.h> #define PXRC_VENDOR_ID 0x1781 #define PXRC_PRODUCT_ID 0x0898 struct pxrc { struct input_dev *input; struct usb_interface *intf; struct urb *urb; struct mutex pm_mutex; bool is_open; char phys[64]; }; static void pxrc_usb_irq(struct urb *urb) { struct pxrc *pxrc = urb->context; u8 *data = urb->transfer_buffer; int error; switch (urb->status) { case 0: /* success */ break; case -ETIME: /* this urb is timing out */ dev_dbg(&pxrc->intf->dev, "%s - urb timed out - was the device unplugged?\n", __func__); return; case -ECONNRESET: case -ENOENT: case -ESHUTDOWN: case -EPIPE: /* this urb is terminated, clean up */ dev_dbg(&pxrc->intf->dev, "%s - urb shutting down with status: %d\n", __func__, urb->status); return; default: dev_dbg(&pxrc->intf->dev, "%s - nonzero urb status received: %d\n", __func__, urb->status); goto exit; } if (urb->actual_length == 8) { input_report_abs(pxrc->input, ABS_X, data[0]); input_report_abs(pxrc->input, ABS_Y, data[2]); input_report_abs(pxrc->input, ABS_RX, data[3]); input_report_abs(pxrc->input, ABS_RY, data[4]); input_report_abs(pxrc->input, ABS_RUDDER, data[5]); input_report_abs(pxrc->input, ABS_THROTTLE, data[6]); input_report_abs(pxrc->input, ABS_MISC, data[7]); input_report_key(pxrc->input, BTN_A, data[1]); } exit: /* Resubmit to fetch new fresh URBs */ error = usb_submit_urb(urb, GFP_ATOMIC); if (error && error != -EPERM) dev_err(&pxrc->intf->dev, "%s - usb_submit_urb failed with result: %d", __func__, error); } static int pxrc_open(struct input_dev *input) { struct pxrc *pxrc = input_get_drvdata(input); int error; guard(mutex)(&pxrc->pm_mutex); error = usb_submit_urb(pxrc->urb, GFP_KERNEL); if (error) { dev_err(&pxrc->intf->dev, "%s - usb_submit_urb failed, error: %d\n", __func__, error); return -EIO; } pxrc->is_open = true; return 0; } static void pxrc_close(struct input_dev *input) { struct pxrc *pxrc = input_get_drvdata(input); guard(mutex)(&pxrc->pm_mutex); usb_kill_urb(pxrc->urb); pxrc->is_open = false; } static void pxrc_free_urb(void *_pxrc) { struct pxrc *pxrc = _pxrc; usb_free_urb(pxrc->urb); } static int pxrc_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct usb_device *udev = interface_to_usbdev(intf); struct pxrc *pxrc; struct usb_endpoint_descriptor *epirq; size_t xfer_size; void *xfer_buf; int error; /* * Locate the endpoint information. This device only has an * interrupt endpoint. */ error = usb_find_common_endpoints(intf->cur_altsetting, NULL, NULL, &epirq, NULL); if (error) { dev_err(&intf->dev, "Could not find endpoint\n"); return error; } pxrc = devm_kzalloc(&intf->dev, sizeof(*pxrc), GFP_KERNEL); if (!pxrc) return -ENOMEM; mutex_init(&pxrc->pm_mutex); pxrc->intf = intf; usb_set_intfdata(pxrc->intf, pxrc); xfer_size = usb_endpoint_maxp(epirq); xfer_buf = devm_kmalloc(&intf->dev, xfer_size, GFP_KERNEL); if (!xfer_buf) return -ENOMEM; pxrc->urb = usb_alloc_urb(0, GFP_KERNEL); if (!pxrc->urb) return -ENOMEM; error = devm_add_action_or_reset(&intf->dev, pxrc_free_urb, pxrc); if (error) return error; usb_fill_int_urb(pxrc->urb, udev, usb_rcvintpipe(udev, epirq->bEndpointAddress), xfer_buf, xfer_size, pxrc_usb_irq, pxrc, 1); pxrc->input = devm_input_allocate_device(&intf->dev); if (!pxrc->input) { dev_err(&intf->dev, "couldn't allocate input device\n"); return -ENOMEM; } pxrc->input->name = "PXRC Flight Controller Adapter"; usb_make_path(udev, pxrc->phys, sizeof(pxrc->phys)); strlcat(pxrc->phys, "/input0", sizeof(pxrc->phys)); pxrc->input->phys = pxrc->phys; usb_to_input_id(udev, &pxrc->input->id); pxrc->input->open = pxrc_open; pxrc->input->close = pxrc_close; input_set_capability(pxrc->input, EV_KEY, BTN_A); input_set_abs_params(pxrc->input, ABS_X, 0, 255, 0, 0); input_set_abs_params(pxrc->input, ABS_Y, 0, 255, 0, 0); input_set_abs_params(pxrc->input, ABS_RX, 0, 255, 0, 0); input_set_abs_params(pxrc->input, ABS_RY, 0, 255, 0, 0); input_set_abs_params(pxrc->input, ABS_RUDDER, 0, 255, 0, 0); input_set_abs_params(pxrc->input, ABS_THROTTLE, 0, 255, 0, 0); input_set_abs_params(pxrc->input, ABS_MISC, 0, 255, 0, 0); input_set_drvdata(pxrc->input, pxrc); error = input_register_device(pxrc->input); if (error) return error; return 0; } static void pxrc_disconnect(struct usb_interface *intf) { /* All driver resources are devm-managed. */ } static int pxrc_suspend(struct usb_interface *intf, pm_message_t message) { struct pxrc *pxrc = usb_get_intfdata(intf); guard(mutex)(&pxrc->pm_mutex); if (pxrc->is_open) usb_kill_urb(pxrc->urb); return 0; } static int pxrc_resume(struct usb_interface *intf) { struct pxrc *pxrc = usb_get_intfdata(intf); guard(mutex)(&pxrc->pm_mutex); if (pxrc->is_open && usb_submit_urb(pxrc->urb, GFP_KERNEL) < 0) return -EIO; return 0; } static int pxrc_pre_reset(struct usb_interface *intf) { struct pxrc *pxrc = usb_get_intfdata(intf); mutex_lock(&pxrc->pm_mutex); usb_kill_urb(pxrc->urb); return 0; } static int pxrc_post_reset(struct usb_interface *intf) { struct pxrc *pxrc = usb_get_intfdata(intf); int retval = 0; if (pxrc->is_open && usb_submit_urb(pxrc->urb, GFP_KERNEL) < 0) retval = -EIO; mutex_unlock(&pxrc->pm_mutex); return retval; } static int pxrc_reset_resume(struct usb_interface *intf) { return pxrc_resume(intf); } static const struct usb_device_id pxrc_table[] = { { USB_DEVICE(PXRC_VENDOR_ID, PXRC_PRODUCT_ID) }, { } }; MODULE_DEVICE_TABLE(usb, pxrc_table); static struct usb_driver pxrc_driver = { .name = "pxrc", .probe = pxrc_probe, .disconnect = pxrc_disconnect, .id_table = pxrc_table, .suspend = pxrc_suspend, .resume = pxrc_resume, .pre_reset = pxrc_pre_reset, .post_reset = pxrc_post_reset, .reset_resume = pxrc_reset_resume, }; module_usb_driver(pxrc_driver); MODULE_AUTHOR("Marcus Folkesson <marcus.folkesson@gmail.com>"); MODULE_DESCRIPTION("PhoenixRC Flight Controller Adapter"); MODULE_LICENSE("GPL v2"); |
| 1 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * HID driver for ELO usb touchscreen 4000/4500 * * Copyright (c) 2013 Jiri Slaby * * Data parsing taken from elousb driver by Vojtech Pavlik. */ #include <linux/hid.h> #include <linux/input.h> #include <linux/module.h> #include <linux/usb.h> #include <linux/workqueue.h> #include "hid-ids.h" #define ELO_PERIODIC_READ_INTERVAL HZ #define ELO_SMARTSET_CMD_TIMEOUT 2000 /* msec */ /* Elo SmartSet commands */ #define ELO_FLUSH_SMARTSET_RESPONSES 0x02 /* Flush all pending smartset responses */ #define ELO_SEND_SMARTSET_COMMAND 0x05 /* Send a smartset command */ #define ELO_GET_SMARTSET_RESPONSE 0x06 /* Get a smartset response */ #define ELO_DIAG 0x64 /* Diagnostics command */ #define ELO_SMARTSET_PACKET_SIZE 8 struct elo_priv { struct usb_device *usbdev; struct delayed_work work; unsigned char buffer[ELO_SMARTSET_PACKET_SIZE]; }; static struct workqueue_struct *wq; static bool use_fw_quirk = true; module_param(use_fw_quirk, bool, S_IRUGO); MODULE_PARM_DESC(use_fw_quirk, "Do periodic pokes for broken M firmwares (default = true)"); static int elo_input_configured(struct hid_device *hdev, struct hid_input *hidinput) { struct input_dev *input = hidinput->input; /* * ELO devices have one Button usage in GenDesk field, which makes * hid-input map it to BTN_LEFT; that confuses userspace, which then * considers the device to be a mouse/touchpad instead of touchscreen. */ clear_bit(BTN_LEFT, input->keybit); set_bit(BTN_TOUCH, input->keybit); set_bit(ABS_PRESSURE, input->absbit); input_set_abs_params(input, ABS_PRESSURE, 0, 256, 0, 0); return 0; } static void elo_process_data(struct input_dev *input, const u8 *data, int size) { int press; input_report_abs(input, ABS_X, (data[3] << 8) | data[2]); input_report_abs(input, ABS_Y, (data[5] << 8) | data[4]); press = 0; if (data[1] & 0x80) press = (data[7] << 8) | data[6]; input_report_abs(input, ABS_PRESSURE, press); if (data[1] & 0x03) { input_report_key(input, BTN_TOUCH, 1); input_sync(input); } if (data[1] & 0x04) input_report_key(input, BTN_TOUCH, 0); input_sync(input); } static int elo_raw_event(struct hid_device *hdev, struct hid_report *report, u8 *data, int size) { struct hid_input *hidinput; if (!(hdev->claimed & HID_CLAIMED_INPUT) || list_empty(&hdev->inputs)) return 0; hidinput = list_first_entry(&hdev->inputs, struct hid_input, list); switch (report->id) { case 0: if (data[0] == 'T') { /* Mandatory ELO packet marker */ elo_process_data(hidinput->input, data, size); return 1; } break; default: /* unknown report */ /* Unknown report type; pass upstream */ hid_info(hdev, "unknown report type %d\n", report->id); break; } return 0; } static int elo_smartset_send_get(struct usb_device *dev, u8 command, void *data) { unsigned int pipe; u8 dir; if (command == ELO_SEND_SMARTSET_COMMAND) { pipe = usb_sndctrlpipe(dev, 0); dir = USB_DIR_OUT; } else if (command == ELO_GET_SMARTSET_RESPONSE) { pipe = usb_rcvctrlpipe(dev, 0); dir = USB_DIR_IN; } else return -EINVAL; return usb_control_msg(dev, pipe, command, dir | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, 0, data, ELO_SMARTSET_PACKET_SIZE, ELO_SMARTSET_CMD_TIMEOUT); } static int elo_flush_smartset_responses(struct usb_device *dev) { return usb_control_msg(dev, usb_sndctrlpipe(dev, 0), ELO_FLUSH_SMARTSET_RESPONSES, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, 0, NULL, 0, USB_CTRL_SET_TIMEOUT); } static void elo_work(struct work_struct *work) { struct elo_priv *priv = container_of(work, struct elo_priv, work.work); struct usb_device *dev = priv->usbdev; unsigned char *buffer = priv->buffer; int ret; ret = elo_flush_smartset_responses(dev); if (ret < 0) { dev_err(&dev->dev, "initial FLUSH_SMARTSET_RESPONSES failed, error %d\n", ret); goto fail; } /* send Diagnostics command */ *buffer = ELO_DIAG; ret = elo_smartset_send_get(dev, ELO_SEND_SMARTSET_COMMAND, buffer); if (ret < 0) { dev_err(&dev->dev, "send Diagnostics Command failed, error %d\n", ret); goto fail; } /* get the result */ ret = elo_smartset_send_get(dev, ELO_GET_SMARTSET_RESPONSE, buffer); if (ret < 0) { dev_err(&dev->dev, "get Diagnostics Command response failed, error %d\n", ret); goto fail; } /* read the ack */ if (*buffer != 'A') { ret = elo_smartset_send_get(dev, ELO_GET_SMARTSET_RESPONSE, buffer); if (ret < 0) { dev_err(&dev->dev, "get acknowledge response failed, error %d\n", ret); goto fail; } } fail: ret = elo_flush_smartset_responses(dev); if (ret < 0) dev_err(&dev->dev, "final FLUSH_SMARTSET_RESPONSES failed, error %d\n", ret); queue_delayed_work(wq, &priv->work, ELO_PERIODIC_READ_INTERVAL); } /* * Not all Elo devices need the periodic HID descriptor reads. * Only firmware version M needs this. */ static bool elo_broken_firmware(struct usb_device *dev) { struct usb_device *hub = dev->parent; struct usb_device *child = NULL; u16 fw_lvl = le16_to_cpu(dev->descriptor.bcdDevice); u16 child_vid, child_pid; int i; if (!use_fw_quirk) return false; if (fw_lvl != 0x10d) return false; /* iterate sibling devices of the touch controller */ usb_hub_for_each_child(hub, i, child) { child_vid = le16_to_cpu(child->descriptor.idVendor); child_pid = le16_to_cpu(child->descriptor.idProduct); /* * If one of the devices below is present attached as a sibling of * the touch controller then this is a newer IBM 4820 monitor that * does not need the IBM-requested workaround if fw level is * 0x010d - aka 'M'. * No other HW can have this combination. */ if (child_vid==0x04b3) { switch (child_pid) { case 0x4676: /* 4820 21x Video */ case 0x4677: /* 4820 51x Video */ case 0x4678: /* 4820 2Lx Video */ case 0x4679: /* 4820 5Lx Video */ return false; } } } return true; } static int elo_probe(struct hid_device *hdev, const struct hid_device_id *id) { struct elo_priv *priv; int ret; if (!hid_is_usb(hdev)) return -EINVAL; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; INIT_DELAYED_WORK(&priv->work, elo_work); priv->usbdev = interface_to_usbdev(to_usb_interface(hdev->dev.parent)); hid_set_drvdata(hdev, priv); ret = hid_parse(hdev); if (ret) { hid_err(hdev, "parse failed\n"); goto err_free; } ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT); if (ret) { hid_err(hdev, "hw start failed\n"); goto err_free; } if (elo_broken_firmware(priv->usbdev)) { hid_info(hdev, "broken firmware found, installing workaround\n"); queue_delayed_work(wq, &priv->work, ELO_PERIODIC_READ_INTERVAL); } return 0; err_free: kfree(priv); return ret; } static void elo_remove(struct hid_device *hdev) { struct elo_priv *priv = hid_get_drvdata(hdev); hid_hw_stop(hdev); cancel_delayed_work_sync(&priv->work); kfree(priv); } static const struct hid_device_id elo_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ELO, 0x0009), }, { HID_USB_DEVICE(USB_VENDOR_ID_ELO, 0x0030), }, { } }; MODULE_DEVICE_TABLE(hid, elo_devices); static struct hid_driver elo_driver = { .name = "elo", .id_table = elo_devices, .probe = elo_probe, .remove = elo_remove, .raw_event = elo_raw_event, .input_configured = elo_input_configured, }; static int __init elo_driver_init(void) { int ret; wq = create_singlethread_workqueue("elousb"); if (!wq) return -ENOMEM; ret = hid_register_driver(&elo_driver); if (ret) destroy_workqueue(wq); return ret; } module_init(elo_driver_init); static void __exit elo_driver_exit(void) { hid_unregister_driver(&elo_driver); destroy_workqueue(wq); } module_exit(elo_driver_exit); MODULE_AUTHOR("Jiri Slaby <jslaby@suse.cz>"); MODULE_DESCRIPTION("HID driver for ELO usb touchscreen 4000/4500"); MODULE_LICENSE("GPL"); |
| 379 | 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 */ /* * Because linux/module.h has tracepoints in the header, and ftrace.h * used to include this file, define_trace.h includes linux/module.h * But we do not want the module.h to override the TRACE_SYSTEM macro * variable that define_trace.h is processing, so we only set it * when module events are being processed, which would happen when * CREATE_TRACE_POINTS is defined. */ #ifdef CREATE_TRACE_POINTS #undef TRACE_SYSTEM #define TRACE_SYSTEM module #endif #if !defined(_TRACE_MODULE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MODULE_H #include <linux/tracepoint.h> #ifdef CONFIG_MODULES struct module; #define show_module_flags(flags) __print_flags(flags, "", \ { (1UL << TAINT_PROPRIETARY_MODULE), "P" }, \ { (1UL << TAINT_OOT_MODULE), "O" }, \ { (1UL << TAINT_FORCED_MODULE), "F" }, \ { (1UL << TAINT_CRAP), "C" }, \ { (1UL << TAINT_UNSIGNED_MODULE), "E" }) TRACE_EVENT(module_load, TP_PROTO(struct module *mod), TP_ARGS(mod), TP_STRUCT__entry( __field( unsigned int, taints ) __string( name, mod->name ) ), TP_fast_assign( __entry->taints = mod->taints; __assign_str(name); ), TP_printk("%s %s", __get_str(name), show_module_flags(__entry->taints)) ); TRACE_EVENT(module_free, TP_PROTO(struct module *mod), TP_ARGS(mod), TP_STRUCT__entry( __string( name, mod->name ) ), TP_fast_assign( __assign_str(name); ), TP_printk("%s", __get_str(name)) ); #ifdef CONFIG_MODULE_UNLOAD /* trace_module_get/put are only used if CONFIG_MODULE_UNLOAD is defined */ DECLARE_EVENT_CLASS(module_refcnt, TP_PROTO(struct module *mod, unsigned long ip), TP_ARGS(mod, ip), TP_STRUCT__entry( __field( unsigned long, ip ) __field( int, refcnt ) __string( name, mod->name ) ), TP_fast_assign( __entry->ip = ip; __entry->refcnt = atomic_read(&mod->refcnt); __assign_str(name); ), TP_printk("%s call_site=%ps refcnt=%d", __get_str(name), (void *)__entry->ip, __entry->refcnt) ); DEFINE_EVENT(module_refcnt, module_get, TP_PROTO(struct module *mod, unsigned long ip), TP_ARGS(mod, ip) ); DEFINE_EVENT(module_refcnt, module_put, TP_PROTO(struct module *mod, unsigned long ip), TP_ARGS(mod, ip) ); #endif /* CONFIG_MODULE_UNLOAD */ TRACE_EVENT(module_request, TP_PROTO(char *name, bool wait, unsigned long ip), TP_ARGS(name, wait, ip), TP_STRUCT__entry( __field( unsigned long, ip ) __field( bool, wait ) __string( name, name ) ), TP_fast_assign( __entry->ip = ip; __entry->wait = wait; __assign_str(name); ), TP_printk("%s wait=%d call_site=%ps", __get_str(name), (int)__entry->wait, (void *)__entry->ip) ); #endif /* CONFIG_MODULES */ #endif /* _TRACE_MODULE_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 4 24 58 58 14 1 5 3 1 11 36 36 32 66 13 9 90 19 40 278 55 244 50 52 36 52 23 23 23 90 90 90 90 90 90 90 53 98 99 9 25 25 16 16 242 126 128 51 75 1114 1106 42 42 43 8 24 43 30 30 43 43 40 1 1115 1115 1116 43 40 40 40 40 12 1075 1115 1114 65 65 63 17 17 17 17 17 17 17 17 1 17 16 2 16 9 15 2 18 18 18 51 52 52 44 22 44 45 45 45 44 45 45 44 7 45 52 52 52 18 45 45 45 44 45 40 10 27 6 24 46 21 20 20 20 20 20 7 56 56 56 27 27 69 60 60 58 58 19 58 66 67 137 60 88 135 133 60 89 27 114 137 16 16 18 7 2 8 16 66 16 21 31 58 46 20 20 20 2 2 10 27 27 27 27 27 27 27 53 11 1 10 11 11 11 11 11 1 10 11 11 11 11 11 13 41 13 41 44 42 10 43 43 6 40 29 40 29 40 40 40 39 40 50 14 40 35 18 49 40 40 40 14 40 29 35 50 50 40 40 28 32 48 50 50 41 50 41 44 44 44 23 44 43 44 44 44 44 50 50 50 44 6 6 6 40 3 41 41 41 10 27 36 36 36 10 27 35 36 35 46 6 40 40 41 12 30 11 28 37 3 39 37 38 37 38 38 4 4 2 2 4 3 3 1 16 16 11 16 16 9 16 29 29 29 29 1 1 16 16 16 66 67 67 67 67 67 66 67 36 34 67 67 67 67 16 58 58 66 7 67 16 16 16 16 16 16 6 15 7 16 16 15 16 16 6 4 3 5 23 22 3 21 21 1 13 9 19 6 11 19 6 7 7 12 12 11 7 1 1 5 2 5 5 5 3 1 2 2 8 2 7 1 1 5 2 2 2 2 1 1 6 3 2 2 1 2 2 2 2 2 2 2 2 2 4 4 4 4 1 3 4 4 2 2 2 2 2 2 11 11 2 11 6 5 5 2 4 4 5 1 11 3 1 7 4 4 1 3 4 4 4 7 2 1 4 29 29 29 18 7 12 18 178 177 1 175 158 18 18 2 7 1 6 2 7 4 3 25 20 25 9 16 87 69 14 2 2 58 58 69 69 69 69 69 68 69 69 58 16 14 11 27 8 43 114 94 95 28 95 31 95 25 33 33 33 33 33 33 18 24 10 10 10 4 10 43 42 5 41 21 5 1 5 42 42 43 27 2 27 1 26 27 1 1 1 43 43 41 28 23 26 23 26 28 40 2 5 21 42 8 34 43 41 28 43 41 28 41 16 26 37 5 37 4 7 3 4 7 6 9 7 3 2 3 3 7 32 32 16 32 33 32 33 33 25 8 29 5 5 23 21 6 10 58 58 58 58 58 32 58 58 58 31 56 58 58 58 58 58 32 21 52 1 53 53 52 1 52 1 35 19 53 21 32 53 45 1 53 1 53 53 53 16 16 16 16 11 11 1 4 10 10 10 10 1 10 10 2 8 11 5 10 2 2 2 2 2 2 2 2 2 2 2 2 1222 7 40 11 2 1 1069 12 1083 1082 1083 1081 1069 1 11 8 8 4 4 4 12 1079 1077 7 1071 8 1082 1083 12 1079 7 7 7 7 1074 7 1069 1076 1075 1 1077 1063 13 13 1076 2 36 36 36 8 8 8 46 7 38 40 39 39 7 7 2 5 5 5 5 5 36 32 38 41 5 29 2 1418 1419 1416 1414 1421 1 1 680 682 | 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 | /* * Generic process-grouping system. * * Based originally on the cpuset system, extracted by Paul Menage * Copyright (C) 2006 Google, Inc * * Notifications support * Copyright (C) 2009 Nokia Corporation * Author: Kirill A. Shutemov * * Copyright notices from the original cpuset code: * -------------------------------------------------- * Copyright (C) 2003 BULL SA. * Copyright (C) 2004-2006 Silicon Graphics, Inc. * * Portions derived from Patrick Mochel's sysfs code. * sysfs is Copyright (c) 2001-3 Patrick Mochel * * 2003-10-10 Written by Simon Derr. * 2003-10-22 Updates by Stephen Hemminger. * 2004 May-July Rework by Paul Jackson. * --------------------------------------------------- * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of the Linux * distribution for more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "cgroup-internal.h" #include <linux/bpf-cgroup.h> #include <linux/cred.h> #include <linux/errno.h> #include <linux/init_task.h> #include <linux/kernel.h> #include <linux/magic.h> #include <linux/mutex.h> #include <linux/mount.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/percpu-rwsem.h> #include <linux/string.h> #include <linux/hashtable.h> #include <linux/idr.h> #include <linux/kthread.h> #include <linux/atomic.h> #include <linux/cpuset.h> #include <linux/proc_ns.h> #include <linux/nsproxy.h> #include <linux/file.h> #include <linux/fs_parser.h> #include <linux/sched/cputime.h> #include <linux/sched/deadline.h> #include <linux/psi.h> #include <net/sock.h> #define CREATE_TRACE_POINTS #include <trace/events/cgroup.h> #define CGROUP_FILE_NAME_MAX (MAX_CGROUP_TYPE_NAMELEN + \ MAX_CFTYPE_NAME + 2) /* let's not notify more than 100 times per second */ #define CGROUP_FILE_NOTIFY_MIN_INTV DIV_ROUND_UP(HZ, 100) /* * To avoid confusing the compiler (and generating warnings) with code * that attempts to access what would be a 0-element array (i.e. sized * to a potentially empty array when CGROUP_SUBSYS_COUNT == 0), this * constant expression can be added. */ #define CGROUP_HAS_SUBSYS_CONFIG (CGROUP_SUBSYS_COUNT > 0) /* * cgroup_mutex is the master lock. Any modification to cgroup or its * hierarchy must be performed while holding it. * * css_set_lock protects task->cgroups pointer, the list of css_set * objects, and the chain of tasks off each css_set. * * These locks are exported if CONFIG_PROVE_RCU so that accessors in * cgroup.h can use them for lockdep annotations. */ DEFINE_MUTEX(cgroup_mutex); DEFINE_SPINLOCK(css_set_lock); #ifdef CONFIG_PROVE_RCU EXPORT_SYMBOL_GPL(cgroup_mutex); EXPORT_SYMBOL_GPL(css_set_lock); #endif DEFINE_SPINLOCK(trace_cgroup_path_lock); char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; static bool cgroup_debug __read_mostly; /* * Protects cgroup_idr and css_idr so that IDs can be released without * grabbing cgroup_mutex. */ static DEFINE_SPINLOCK(cgroup_idr_lock); /* * Protects cgroup_file->kn for !self csses. It synchronizes notifications * against file removal/re-creation across css hiding. */ static DEFINE_SPINLOCK(cgroup_file_kn_lock); DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem); #define cgroup_assert_mutex_or_rcu_locked() \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&cgroup_mutex), \ "cgroup_mutex or RCU read lock required"); /* * cgroup destruction makes heavy use of work items and there can be a lot * of concurrent destructions. Use a separate workqueue so that cgroup * destruction work items don't end up filling up max_active of system_wq * which may lead to deadlock. */ static struct workqueue_struct *cgroup_destroy_wq; /* generate an array of cgroup subsystem pointers */ #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys, struct cgroup_subsys *cgroup_subsys[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS /* array of cgroup subsystem names */ #define SUBSYS(_x) [_x ## _cgrp_id] = #_x, static const char *cgroup_subsys_name[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS /* array of static_keys for cgroup_subsys_enabled() and cgroup_subsys_on_dfl() */ #define SUBSYS(_x) \ DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_enabled_key); \ DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_on_dfl_key); \ EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_enabled_key); \ EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_on_dfl_key); #include <linux/cgroup_subsys.h> #undef SUBSYS #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_enabled_key, static struct static_key_true *cgroup_subsys_enabled_key[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_on_dfl_key, static struct static_key_true *cgroup_subsys_on_dfl_key[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS static DEFINE_PER_CPU(struct cgroup_rstat_cpu, cgrp_dfl_root_rstat_cpu); /* the default hierarchy */ struct cgroup_root cgrp_dfl_root = { .cgrp.rstat_cpu = &cgrp_dfl_root_rstat_cpu }; EXPORT_SYMBOL_GPL(cgrp_dfl_root); /* * The default hierarchy always exists but is hidden until mounted for the * first time. This is for backward compatibility. */ bool cgrp_dfl_visible; /* some controllers are not supported in the default hierarchy */ static u16 cgrp_dfl_inhibit_ss_mask; /* some controllers are implicitly enabled on the default hierarchy */ static u16 cgrp_dfl_implicit_ss_mask; /* some controllers can be threaded on the default hierarchy */ static u16 cgrp_dfl_threaded_ss_mask; /* The list of hierarchy roots */ LIST_HEAD(cgroup_roots); static int cgroup_root_count; /* hierarchy ID allocation and mapping, protected by cgroup_mutex */ static DEFINE_IDR(cgroup_hierarchy_idr); /* * Assign a monotonically increasing serial number to csses. It guarantees * cgroups with bigger numbers are newer than those with smaller numbers. * Also, as csses are always appended to the parent's ->children list, it * guarantees that sibling csses are always sorted in the ascending serial * number order on the list. Protected by cgroup_mutex. */ static u64 css_serial_nr_next = 1; /* * These bitmasks identify subsystems with specific features to avoid * having to do iterative checks repeatedly. */ static u16 have_fork_callback __read_mostly; static u16 have_exit_callback __read_mostly; static u16 have_release_callback __read_mostly; static u16 have_canfork_callback __read_mostly; static bool have_favordynmods __ro_after_init = IS_ENABLED(CONFIG_CGROUP_FAVOR_DYNMODS); /* cgroup namespace for init task */ struct cgroup_namespace init_cgroup_ns = { .ns.count = REFCOUNT_INIT(2), .user_ns = &init_user_ns, .ns.ops = &cgroupns_operations, .ns.inum = PROC_CGROUP_INIT_INO, .root_cset = &init_css_set, }; static struct file_system_type cgroup2_fs_type; static struct cftype cgroup_base_files[]; static struct cftype cgroup_psi_files[]; /* cgroup optional features */ enum cgroup_opt_features { #ifdef CONFIG_PSI OPT_FEATURE_PRESSURE, #endif OPT_FEATURE_COUNT }; static const char *cgroup_opt_feature_names[OPT_FEATURE_COUNT] = { #ifdef CONFIG_PSI "pressure", #endif }; static u16 cgroup_feature_disable_mask __read_mostly; static int cgroup_apply_control(struct cgroup *cgrp); static void cgroup_finalize_control(struct cgroup *cgrp, int ret); static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task); static int cgroup_destroy_locked(struct cgroup *cgrp); static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss); static void css_release(struct percpu_ref *ref); static void kill_css(struct cgroup_subsys_state *css); static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add); #ifdef CONFIG_DEBUG_CGROUP_REF #define CGROUP_REF_FN_ATTRS noinline #define CGROUP_REF_EXPORT(fn) EXPORT_SYMBOL_GPL(fn); #include <linux/cgroup_refcnt.h> #endif /** * cgroup_ssid_enabled - cgroup subsys enabled test by subsys ID * @ssid: subsys ID of interest * * cgroup_subsys_enabled() can only be used with literal subsys names which * is fine for individual subsystems but unsuitable for cgroup core. This * is slower static_key_enabled() based test indexed by @ssid. */ bool cgroup_ssid_enabled(int ssid) { if (!CGROUP_HAS_SUBSYS_CONFIG) return false; return static_key_enabled(cgroup_subsys_enabled_key[ssid]); } /** * cgroup_on_dfl - test whether a cgroup is on the default hierarchy * @cgrp: the cgroup of interest * * The default hierarchy is the v2 interface of cgroup and this function * can be used to test whether a cgroup is on the default hierarchy for * cases where a subsystem should behave differently depending on the * interface version. * * List of changed behaviors: * * - Mount options "noprefix", "xattr", "clone_children", "release_agent" * and "name" are disallowed. * * - When mounting an existing superblock, mount options should match. * * - rename(2) is disallowed. * * - "tasks" is removed. Everything should be at process granularity. Use * "cgroup.procs" instead. * * - "cgroup.procs" is not sorted. pids will be unique unless they got * recycled in-between reads. * * - "release_agent" and "notify_on_release" are removed. Replacement * notification mechanism will be implemented. * * - "cgroup.clone_children" is removed. * * - "cgroup.subtree_populated" is available. Its value is 0 if the cgroup * and its descendants contain no task; otherwise, 1. The file also * generates kernfs notification which can be monitored through poll and * [di]notify when the value of the file changes. * * - cpuset: tasks will be kept in empty cpusets when hotplug happens and * take masks of ancestors with non-empty cpus/mems, instead of being * moved to an ancestor. * * - cpuset: a task can be moved into an empty cpuset, and again it takes * masks of ancestors. * * - blkcg: blk-throttle becomes properly hierarchical. */ bool cgroup_on_dfl(const struct cgroup *cgrp) { return cgrp->root == &cgrp_dfl_root; } /* IDR wrappers which synchronize using cgroup_idr_lock */ static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask) { int ret; idr_preload(gfp_mask); spin_lock_bh(&cgroup_idr_lock); ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_DIRECT_RECLAIM); spin_unlock_bh(&cgroup_idr_lock); idr_preload_end(); return ret; } static void *cgroup_idr_replace(struct idr *idr, void *ptr, int id) { void *ret; spin_lock_bh(&cgroup_idr_lock); ret = idr_replace(idr, ptr, id); spin_unlock_bh(&cgroup_idr_lock); return ret; } static void cgroup_idr_remove(struct idr *idr, int id) { spin_lock_bh(&cgroup_idr_lock); idr_remove(idr, id); spin_unlock_bh(&cgroup_idr_lock); } static bool cgroup_has_tasks(struct cgroup *cgrp) { return cgrp->nr_populated_csets; } static bool cgroup_is_threaded(struct cgroup *cgrp) { return cgrp->dom_cgrp != cgrp; } /* can @cgrp host both domain and threaded children? */ static bool cgroup_is_mixable(struct cgroup *cgrp) { /* * Root isn't under domain level resource control exempting it from * the no-internal-process constraint, so it can serve as a thread * root and a parent of resource domains at the same time. */ return !cgroup_parent(cgrp); } /* can @cgrp become a thread root? Should always be true for a thread root */ static bool cgroup_can_be_thread_root(struct cgroup *cgrp) { /* mixables don't care */ if (cgroup_is_mixable(cgrp)) return true; /* domain roots can't be nested under threaded */ if (cgroup_is_threaded(cgrp)) return false; /* can only have either domain or threaded children */ if (cgrp->nr_populated_domain_children) return false; /* and no domain controllers can be enabled */ if (cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) return false; return true; } /* is @cgrp root of a threaded subtree? */ static bool cgroup_is_thread_root(struct cgroup *cgrp) { /* thread root should be a domain */ if (cgroup_is_threaded(cgrp)) return false; /* a domain w/ threaded children is a thread root */ if (cgrp->nr_threaded_children) return true; /* * A domain which has tasks and explicit threaded controllers * enabled is a thread root. */ if (cgroup_has_tasks(cgrp) && (cgrp->subtree_control & cgrp_dfl_threaded_ss_mask)) return true; return false; } /* a domain which isn't connected to the root w/o brekage can't be used */ static bool cgroup_is_valid_domain(struct cgroup *cgrp) { /* the cgroup itself can be a thread root */ if (cgroup_is_threaded(cgrp)) return false; /* but the ancestors can't be unless mixable */ while ((cgrp = cgroup_parent(cgrp))) { if (!cgroup_is_mixable(cgrp) && cgroup_is_thread_root(cgrp)) return false; if (cgroup_is_threaded(cgrp)) return false; } return true; } /* subsystems visibly enabled on a cgroup */ static u16 cgroup_control(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); u16 root_ss_mask = cgrp->root->subsys_mask; if (parent) { u16 ss_mask = parent->subtree_control; /* threaded cgroups can only have threaded controllers */ if (cgroup_is_threaded(cgrp)) ss_mask &= cgrp_dfl_threaded_ss_mask; return ss_mask; } if (cgroup_on_dfl(cgrp)) root_ss_mask &= ~(cgrp_dfl_inhibit_ss_mask | cgrp_dfl_implicit_ss_mask); return root_ss_mask; } /* subsystems enabled on a cgroup */ static u16 cgroup_ss_mask(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); if (parent) { u16 ss_mask = parent->subtree_ss_mask; /* threaded cgroups can only have threaded controllers */ if (cgroup_is_threaded(cgrp)) ss_mask &= cgrp_dfl_threaded_ss_mask; return ss_mask; } return cgrp->root->subsys_mask; } /** * cgroup_css - obtain a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * * Return @cgrp's css (cgroup_subsys_state) associated with @ss. This * function must be called either under cgroup_mutex or rcu_read_lock() and * the caller is responsible for pinning the returned css if it wants to * keep accessing it outside the said locks. This function may return * %NULL if @cgrp doesn't have @subsys_id enabled. */ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { if (CGROUP_HAS_SUBSYS_CONFIG && ss) return rcu_dereference_check(cgrp->subsys[ss->id], lockdep_is_held(&cgroup_mutex)); else return &cgrp->self; } /** * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * * Similar to cgroup_css() but returns the effective css, which is defined * as the matching css of the nearest ancestor including self which has @ss * enabled. If @ss is associated with the hierarchy @cgrp is on, this * function is guaranteed to return non-NULL css. */ static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, struct cgroup_subsys *ss) { lockdep_assert_held(&cgroup_mutex); if (!ss) return &cgrp->self; /* * This function is used while updating css associations and thus * can't test the csses directly. Test ss_mask. */ while (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) { cgrp = cgroup_parent(cgrp); if (!cgrp) return NULL; } return cgroup_css(cgrp, ss); } /** * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get the effective css of @cgrp for @ss. The effective css is * defined as the matching css of the nearest ancestor including self which * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, * the root css is returned, so this function always returns a valid css. * * The returned css is not guaranteed to be online, and therefore it is the * callers responsibility to try get a reference for it. */ struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; if (!CGROUP_HAS_SUBSYS_CONFIG) return NULL; do { css = cgroup_css(cgrp, ss); if (css) return css; cgrp = cgroup_parent(cgrp); } while (cgrp); return init_css_set.subsys[ss->id]; } /** * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get the effective css of @cgrp for @ss. The effective css is * defined as the matching css of the nearest ancestor including self which * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, * the root css is returned, so this function always returns a valid css. * The returned css must be put using css_put(). */ struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; if (!CGROUP_HAS_SUBSYS_CONFIG) return NULL; rcu_read_lock(); do { css = cgroup_css(cgrp, ss); if (css && css_tryget_online(css)) goto out_unlock; cgrp = cgroup_parent(cgrp); } while (cgrp); css = init_css_set.subsys[ss->id]; css_get(css); out_unlock: rcu_read_unlock(); return css; } EXPORT_SYMBOL_GPL(cgroup_get_e_css); static void cgroup_get_live(struct cgroup *cgrp) { WARN_ON_ONCE(cgroup_is_dead(cgrp)); cgroup_get(cgrp); } /** * __cgroup_task_count - count the number of tasks in a cgroup. The caller * is responsible for taking the css_set_lock. * @cgrp: the cgroup in question */ int __cgroup_task_count(const struct cgroup *cgrp) { int count = 0; struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) count += link->cset->nr_tasks; return count; } /** * cgroup_task_count - count the number of tasks in a cgroup. * @cgrp: the cgroup in question */ int cgroup_task_count(const struct cgroup *cgrp) { int count; spin_lock_irq(&css_set_lock); count = __cgroup_task_count(cgrp); spin_unlock_irq(&css_set_lock); return count; } static struct cgroup *kn_priv(struct kernfs_node *kn) { struct kernfs_node *parent; /* * The parent can not be replaced due to KERNFS_ROOT_INVARIANT_PARENT. * Therefore it is always safe to dereference this pointer outside of a * RCU section. */ parent = rcu_dereference_check(kn->__parent, kernfs_root_flags(kn) & KERNFS_ROOT_INVARIANT_PARENT); return parent->priv; } struct cgroup_subsys_state *of_css(struct kernfs_open_file *of) { struct cgroup *cgrp = kn_priv(of->kn); struct cftype *cft = of_cft(of); /* * This is open and unprotected implementation of cgroup_css(). * seq_css() is only called from a kernfs file operation which has * an active reference on the file. Because all the subsystem * files are drained before a css is disassociated with a cgroup, * the matching css from the cgroup's subsys table is guaranteed to * be and stay valid until the enclosing operation is complete. */ if (CGROUP_HAS_SUBSYS_CONFIG && cft->ss) return rcu_dereference_raw(cgrp->subsys[cft->ss->id]); else return &cgrp->self; } EXPORT_SYMBOL_GPL(of_css); /** * for_each_css - iterate all css's of a cgroup * @css: the iteration cursor * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end * @cgrp: the target cgroup to iterate css's of * * Should be called under cgroup_mutex. */ #define for_each_css(css, ssid, cgrp) \ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ if (!((css) = rcu_dereference_check( \ (cgrp)->subsys[(ssid)], \ lockdep_is_held(&cgroup_mutex)))) { } \ else /** * do_each_subsys_mask - filter for_each_subsys with a bitmask * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end * @ss_mask: the bitmask * * The block will only run for cases where the ssid-th bit (1 << ssid) of * @ss_mask is set. */ #define do_each_subsys_mask(ss, ssid, ss_mask) do { \ unsigned long __ss_mask = (ss_mask); \ if (!CGROUP_HAS_SUBSYS_CONFIG) { \ (ssid) = 0; \ break; \ } \ for_each_set_bit(ssid, &__ss_mask, CGROUP_SUBSYS_COUNT) { \ (ss) = cgroup_subsys[ssid]; \ { #define while_each_subsys_mask() \ } \ } \ } while (false) /* iterate over child cgrps, lock should be held throughout iteration */ #define cgroup_for_each_live_child(child, cgrp) \ list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \ if (({ lockdep_assert_held(&cgroup_mutex); \ cgroup_is_dead(child); })) \ ; \ else /* walk live descendants in pre order */ #define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) \ css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL)) \ if (({ lockdep_assert_held(&cgroup_mutex); \ (dsct) = (d_css)->cgroup; \ cgroup_is_dead(dsct); })) \ ; \ else /* walk live descendants in postorder */ #define cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) \ css_for_each_descendant_post((d_css), cgroup_css((cgrp), NULL)) \ if (({ lockdep_assert_held(&cgroup_mutex); \ (dsct) = (d_css)->cgroup; \ cgroup_is_dead(dsct); })) \ ; \ else /* * The default css_set - used by init and its children prior to any * hierarchies being mounted. It contains a pointer to the root state * for each subsystem. Also used to anchor the list of css_sets. Not * reference-counted, to improve performance when child cgroups * haven't been created. */ struct css_set init_css_set = { .refcount = REFCOUNT_INIT(1), .dom_cset = &init_css_set, .tasks = LIST_HEAD_INIT(init_css_set.tasks), .mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks), .dying_tasks = LIST_HEAD_INIT(init_css_set.dying_tasks), .task_iters = LIST_HEAD_INIT(init_css_set.task_iters), .threaded_csets = LIST_HEAD_INIT(init_css_set.threaded_csets), .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), .mg_src_preload_node = LIST_HEAD_INIT(init_css_set.mg_src_preload_node), .mg_dst_preload_node = LIST_HEAD_INIT(init_css_set.mg_dst_preload_node), .mg_node = LIST_HEAD_INIT(init_css_set.mg_node), /* * The following field is re-initialized when this cset gets linked * in cgroup_init(). However, let's initialize the field * statically too so that the default cgroup can be accessed safely * early during boot. */ .dfl_cgrp = &cgrp_dfl_root.cgrp, }; static int css_set_count = 1; /* 1 for init_css_set */ static bool css_set_threaded(struct css_set *cset) { return cset->dom_cset != cset; } /** * css_set_populated - does a css_set contain any tasks? * @cset: target css_set * * css_set_populated() should be the same as !!cset->nr_tasks at steady * state. However, css_set_populated() can be called while a task is being * added to or removed from the linked list before the nr_tasks is * properly updated. Hence, we can't just look at ->nr_tasks here. */ static bool css_set_populated(struct css_set *cset) { lockdep_assert_held(&css_set_lock); return !list_empty(&cset->tasks) || !list_empty(&cset->mg_tasks); } /** * cgroup_update_populated - update the populated count of a cgroup * @cgrp: the target cgroup * @populated: inc or dec populated count * * One of the css_sets associated with @cgrp is either getting its first * task or losing the last. Update @cgrp->nr_populated_* accordingly. The * count is propagated towards root so that a given cgroup's * nr_populated_children is zero iff none of its descendants contain any * tasks. * * @cgrp's interface file "cgroup.populated" is zero if both * @cgrp->nr_populated_csets and @cgrp->nr_populated_children are zero and * 1 otherwise. When the sum changes from or to zero, userland is notified * that the content of the interface file has changed. This can be used to * detect when @cgrp and its descendants become populated or empty. */ static void cgroup_update_populated(struct cgroup *cgrp, bool populated) { struct cgroup *child = NULL; int adj = populated ? 1 : -1; lockdep_assert_held(&css_set_lock); do { bool was_populated = cgroup_is_populated(cgrp); if (!child) { cgrp->nr_populated_csets += adj; } else { if (cgroup_is_threaded(child)) cgrp->nr_populated_threaded_children += adj; else cgrp->nr_populated_domain_children += adj; } if (was_populated == cgroup_is_populated(cgrp)) break; cgroup1_check_for_release(cgrp); TRACE_CGROUP_PATH(notify_populated, cgrp, cgroup_is_populated(cgrp)); cgroup_file_notify(&cgrp->events_file); child = cgrp; cgrp = cgroup_parent(cgrp); } while (cgrp); } /** * css_set_update_populated - update populated state of a css_set * @cset: target css_set * @populated: whether @cset is populated or depopulated * * @cset is either getting the first task or losing the last. Update the * populated counters of all associated cgroups accordingly. */ static void css_set_update_populated(struct css_set *cset, bool populated) { struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) cgroup_update_populated(link->cgrp, populated); } /* * @task is leaving, advance task iterators which are pointing to it so * that they can resume at the next position. Advancing an iterator might * remove it from the list, use safe walk. See css_task_iter_skip() for * details. */ static void css_set_skip_task_iters(struct css_set *cset, struct task_struct *task) { struct css_task_iter *it, *pos; list_for_each_entry_safe(it, pos, &cset->task_iters, iters_node) css_task_iter_skip(it, task); } /** * css_set_move_task - move a task from one css_set to another * @task: task being moved * @from_cset: css_set @task currently belongs to (may be NULL) * @to_cset: new css_set @task is being moved to (may be NULL) * @use_mg_tasks: move to @to_cset->mg_tasks instead of ->tasks * * Move @task from @from_cset to @to_cset. If @task didn't belong to any * css_set, @from_cset can be NULL. If @task is being disassociated * instead of moved, @to_cset can be NULL. * * This function automatically handles populated counter updates and * css_task_iter adjustments but the caller is responsible for managing * @from_cset and @to_cset's reference counts. */ static void css_set_move_task(struct task_struct *task, struct css_set *from_cset, struct css_set *to_cset, bool use_mg_tasks) { lockdep_assert_held(&css_set_lock); if (to_cset && !css_set_populated(to_cset)) css_set_update_populated(to_cset, true); if (from_cset) { WARN_ON_ONCE(list_empty(&task->cg_list)); css_set_skip_task_iters(from_cset, task); list_del_init(&task->cg_list); if (!css_set_populated(from_cset)) css_set_update_populated(from_cset, false); } else { WARN_ON_ONCE(!list_empty(&task->cg_list)); } if (to_cset) { /* * We are synchronized through cgroup_threadgroup_rwsem * against PF_EXITING setting such that we can't race * against cgroup_exit()/cgroup_free() dropping the css_set. */ WARN_ON_ONCE(task->flags & PF_EXITING); cgroup_move_task(task, to_cset); list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks : &to_cset->tasks); } } /* * hash table for cgroup groups. This improves the performance to find * an existing css_set. This hash doesn't (currently) take into * account cgroups in empty hierarchies. */ #define CSS_SET_HASH_BITS 7 static DEFINE_HASHTABLE(css_set_table, CSS_SET_HASH_BITS); static unsigned long css_set_hash(struct cgroup_subsys_state **css) { unsigned long key = 0UL; struct cgroup_subsys *ss; int i; for_each_subsys(ss, i) key += (unsigned long)css[i]; key = (key >> 16) ^ key; return key; } void put_css_set_locked(struct css_set *cset) { struct cgrp_cset_link *link, *tmp_link; struct cgroup_subsys *ss; int ssid; lockdep_assert_held(&css_set_lock); if (!refcount_dec_and_test(&cset->refcount)) return; WARN_ON_ONCE(!list_empty(&cset->threaded_csets)); /* This css_set is dead. Unlink it and release cgroup and css refs */ for_each_subsys(ss, ssid) { list_del(&cset->e_cset_node[ssid]); css_put(cset->subsys[ssid]); } hash_del(&cset->hlist); css_set_count--; list_for_each_entry_safe(link, tmp_link, &cset->cgrp_links, cgrp_link) { list_del(&link->cset_link); list_del(&link->cgrp_link); if (cgroup_parent(link->cgrp)) cgroup_put(link->cgrp); kfree(link); } if (css_set_threaded(cset)) { list_del(&cset->threaded_csets_node); put_css_set_locked(cset->dom_cset); } kfree_rcu(cset, rcu_head); } /** * compare_css_sets - helper function for find_existing_css_set(). * @cset: candidate css_set being tested * @old_cset: existing css_set for a task * @new_cgrp: cgroup that's being entered by the task * @template: desired set of css pointers in css_set (pre-calculated) * * Returns true if "cset" matches "old_cset" except for the hierarchy * which "new_cgrp" belongs to, for which it should match "new_cgrp". */ static bool compare_css_sets(struct css_set *cset, struct css_set *old_cset, struct cgroup *new_cgrp, struct cgroup_subsys_state *template[]) { struct cgroup *new_dfl_cgrp; struct list_head *l1, *l2; /* * On the default hierarchy, there can be csets which are * associated with the same set of cgroups but different csses. * Let's first ensure that csses match. */ if (memcmp(template, cset->subsys, sizeof(cset->subsys))) return false; /* @cset's domain should match the default cgroup's */ if (cgroup_on_dfl(new_cgrp)) new_dfl_cgrp = new_cgrp; else new_dfl_cgrp = old_cset->dfl_cgrp; if (new_dfl_cgrp->dom_cgrp != cset->dom_cset->dfl_cgrp) return false; /* * Compare cgroup pointers in order to distinguish between * different cgroups in hierarchies. As different cgroups may * share the same effective css, this comparison is always * necessary. */ l1 = &cset->cgrp_links; l2 = &old_cset->cgrp_links; while (1) { struct cgrp_cset_link *link1, *link2; struct cgroup *cgrp1, *cgrp2; l1 = l1->next; l2 = l2->next; /* See if we reached the end - both lists are equal length. */ if (l1 == &cset->cgrp_links) { BUG_ON(l2 != &old_cset->cgrp_links); break; } else { BUG_ON(l2 == &old_cset->cgrp_links); } /* Locate the cgroups associated with these links. */ link1 = list_entry(l1, struct cgrp_cset_link, cgrp_link); link2 = list_entry(l2, struct cgrp_cset_link, cgrp_link); cgrp1 = link1->cgrp; cgrp2 = link2->cgrp; /* Hierarchies should be linked in the same order. */ BUG_ON(cgrp1->root != cgrp2->root); /* * If this hierarchy is the hierarchy of the cgroup * that's changing, then we need to check that this * css_set points to the new cgroup; if it's any other * hierarchy, then this css_set should point to the * same cgroup as the old css_set. */ if (cgrp1->root == new_cgrp->root) { if (cgrp1 != new_cgrp) return false; } else { if (cgrp1 != cgrp2) return false; } } return true; } /** * find_existing_css_set - init css array and find the matching css_set * @old_cset: the css_set that we're using before the cgroup transition * @cgrp: the cgroup that we're moving into * @template: out param for the new set of csses, should be clear on entry */ static struct css_set *find_existing_css_set(struct css_set *old_cset, struct cgroup *cgrp, struct cgroup_subsys_state **template) { struct cgroup_root *root = cgrp->root; struct cgroup_subsys *ss; struct css_set *cset; unsigned long key; int i; /* * Build the set of subsystem state objects that we want to see in the * new css_set. While subsystems can change globally, the entries here * won't change, so no need for locking. */ for_each_subsys(ss, i) { if (root->subsys_mask & (1UL << i)) { /* * @ss is in this hierarchy, so we want the * effective css from @cgrp. */ template[i] = cgroup_e_css_by_mask(cgrp, ss); } else { /* * @ss is not in this hierarchy, so we don't want * to change the css. */ template[i] = old_cset->subsys[i]; } } key = css_set_hash(template); hash_for_each_possible(css_set_table, cset, hlist, key) { if (!compare_css_sets(cset, old_cset, cgrp, template)) continue; /* This css_set matches what we need */ return cset; } /* No existing cgroup group matched */ return NULL; } static void free_cgrp_cset_links(struct list_head *links_to_free) { struct cgrp_cset_link *link, *tmp_link; list_for_each_entry_safe(link, tmp_link, links_to_free, cset_link) { list_del(&link->cset_link); kfree(link); } } /** * allocate_cgrp_cset_links - allocate cgrp_cset_links * @count: the number of links to allocate * @tmp_links: list_head the allocated links are put on * * Allocate @count cgrp_cset_link structures and chain them on @tmp_links * through ->cset_link. Returns 0 on success or -errno. */ static int allocate_cgrp_cset_links(int count, struct list_head *tmp_links) { struct cgrp_cset_link *link; int i; INIT_LIST_HEAD(tmp_links); for (i = 0; i < count; i++) { link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) { free_cgrp_cset_links(tmp_links); return -ENOMEM; } list_add(&link->cset_link, tmp_links); } return 0; } /** * link_css_set - a helper function to link a css_set to a cgroup * @tmp_links: cgrp_cset_link objects allocated by allocate_cgrp_cset_links() * @cset: the css_set to be linked * @cgrp: the destination cgroup */ static void link_css_set(struct list_head *tmp_links, struct css_set *cset, struct cgroup *cgrp) { struct cgrp_cset_link *link; BUG_ON(list_empty(tmp_links)); if (cgroup_on_dfl(cgrp)) cset->dfl_cgrp = cgrp; link = list_first_entry(tmp_links, struct cgrp_cset_link, cset_link); link->cset = cset; link->cgrp = cgrp; /* * Always add links to the tail of the lists so that the lists are * in chronological order. */ list_move_tail(&link->cset_link, &cgrp->cset_links); list_add_tail(&link->cgrp_link, &cset->cgrp_links); if (cgroup_parent(cgrp)) cgroup_get_live(cgrp); } /** * find_css_set - return a new css_set with one cgroup updated * @old_cset: the baseline css_set * @cgrp: the cgroup to be updated * * Return a new css_set that's equivalent to @old_cset, but with @cgrp * substituted into the appropriate hierarchy. */ static struct css_set *find_css_set(struct css_set *old_cset, struct cgroup *cgrp) { struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT] = { }; struct css_set *cset; struct list_head tmp_links; struct cgrp_cset_link *link; struct cgroup_subsys *ss; unsigned long key; int ssid; lockdep_assert_held(&cgroup_mutex); /* First see if we already have a cgroup group that matches * the desired set */ spin_lock_irq(&css_set_lock); cset = find_existing_css_set(old_cset, cgrp, template); if (cset) get_css_set(cset); spin_unlock_irq(&css_set_lock); if (cset) return cset; cset = kzalloc(sizeof(*cset), GFP_KERNEL); if (!cset) return NULL; /* Allocate all the cgrp_cset_link objects that we'll need */ if (allocate_cgrp_cset_links(cgroup_root_count, &tmp_links) < 0) { kfree(cset); return NULL; } refcount_set(&cset->refcount, 1); cset->dom_cset = cset; INIT_LIST_HEAD(&cset->tasks); INIT_LIST_HEAD(&cset->mg_tasks); INIT_LIST_HEAD(&cset->dying_tasks); INIT_LIST_HEAD(&cset->task_iters); INIT_LIST_HEAD(&cset->threaded_csets); INIT_HLIST_NODE(&cset->hlist); INIT_LIST_HEAD(&cset->cgrp_links); INIT_LIST_HEAD(&cset->mg_src_preload_node); INIT_LIST_HEAD(&cset->mg_dst_preload_node); INIT_LIST_HEAD(&cset->mg_node); /* Copy the set of subsystem state objects generated in * find_existing_css_set() */ memcpy(cset->subsys, template, sizeof(cset->subsys)); spin_lock_irq(&css_set_lock); /* Add reference counts and links from the new css_set. */ list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; if (c->root == cgrp->root) c = cgrp; link_css_set(&tmp_links, cset, c); } BUG_ON(!list_empty(&tmp_links)); css_set_count++; /* Add @cset to the hash table */ key = css_set_hash(cset->subsys); hash_add(css_set_table, &cset->hlist, key); for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cset->subsys[ssid]; list_add_tail(&cset->e_cset_node[ssid], &css->cgroup->e_csets[ssid]); css_get(css); } spin_unlock_irq(&css_set_lock); /* * If @cset should be threaded, look up the matching dom_cset and * link them up. We first fully initialize @cset then look for the * dom_cset. It's simpler this way and safe as @cset is guaranteed * to stay empty until we return. */ if (cgroup_is_threaded(cset->dfl_cgrp)) { struct css_set *dcset; dcset = find_css_set(cset, cset->dfl_cgrp->dom_cgrp); if (!dcset) { put_css_set(cset); return NULL; } spin_lock_irq(&css_set_lock); cset->dom_cset = dcset; list_add_tail(&cset->threaded_csets_node, &dcset->threaded_csets); spin_unlock_irq(&css_set_lock); } return cset; } struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root) { struct cgroup *root_cgrp = kernfs_root_to_node(kf_root)->priv; return root_cgrp->root; } void cgroup_favor_dynmods(struct cgroup_root *root, bool favor) { bool favoring = root->flags & CGRP_ROOT_FAVOR_DYNMODS; /* see the comment above CGRP_ROOT_FAVOR_DYNMODS definition */ if (favor && !favoring) { rcu_sync_enter(&cgroup_threadgroup_rwsem.rss); root->flags |= CGRP_ROOT_FAVOR_DYNMODS; } else if (!favor && favoring) { rcu_sync_exit(&cgroup_threadgroup_rwsem.rss); root->flags &= ~CGRP_ROOT_FAVOR_DYNMODS; } } static int cgroup_init_root_id(struct cgroup_root *root) { int id; lockdep_assert_held(&cgroup_mutex); id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, 0, 0, GFP_KERNEL); if (id < 0) return id; root->hierarchy_id = id; return 0; } static void cgroup_exit_root_id(struct cgroup_root *root) { lockdep_assert_held(&cgroup_mutex); idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id); } void cgroup_free_root(struct cgroup_root *root) { kfree_rcu(root, rcu); } static void cgroup_destroy_root(struct cgroup_root *root) { struct cgroup *cgrp = &root->cgrp; struct cgrp_cset_link *link, *tmp_link; trace_cgroup_destroy_root(root); cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); BUG_ON(atomic_read(&root->nr_cgrps)); BUG_ON(!list_empty(&cgrp->self.children)); /* Rebind all subsystems back to the default hierarchy */ WARN_ON(rebind_subsystems(&cgrp_dfl_root, root->subsys_mask)); /* * Release all the links from cset_links to this hierarchy's * root cgroup */ spin_lock_irq(&css_set_lock); list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) { list_del(&link->cset_link); list_del(&link->cgrp_link); kfree(link); } spin_unlock_irq(&css_set_lock); WARN_ON_ONCE(list_empty(&root->root_list)); list_del_rcu(&root->root_list); cgroup_root_count--; if (!have_favordynmods) cgroup_favor_dynmods(root, false); cgroup_exit_root_id(root); cgroup_unlock(); cgroup_rstat_exit(cgrp); kernfs_destroy_root(root->kf_root); cgroup_free_root(root); } /* * Returned cgroup is without refcount but it's valid as long as cset pins it. */ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { struct cgroup *res_cgroup = NULL; if (cset == &init_css_set) { res_cgroup = &root->cgrp; } else if (root == &cgrp_dfl_root) { res_cgroup = cset->dfl_cgrp; } else { struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; if (c->root == root) { res_cgroup = c; break; } } } /* * If cgroup_mutex is not held, the cgrp_cset_link will be freed * before we remove the cgroup root from the root_list. Consequently, * when accessing a cgroup root, the cset_link may have already been * freed, resulting in a NULL res_cgroup. However, by holding the * cgroup_mutex, we ensure that res_cgroup can't be NULL. * If we don't hold cgroup_mutex in the caller, we must do the NULL * check. */ return res_cgroup; } /* * look up cgroup associated with current task's cgroup namespace on the * specified hierarchy */ static struct cgroup * current_cgns_cgroup_from_root(struct cgroup_root *root) { struct cgroup *res = NULL; struct css_set *cset; lockdep_assert_held(&css_set_lock); rcu_read_lock(); cset = current->nsproxy->cgroup_ns->root_cset; res = __cset_cgroup_from_root(cset, root); rcu_read_unlock(); /* * The namespace_sem is held by current, so the root cgroup can't * be umounted. Therefore, we can ensure that the res is non-NULL. */ WARN_ON_ONCE(!res); return res; } /* * Look up cgroup associated with current task's cgroup namespace on the default * hierarchy. * * Unlike current_cgns_cgroup_from_root(), this doesn't need locks: * - Internal rcu_read_lock is unnecessary because we don't dereference any rcu * pointers. * - css_set_lock is not needed because we just read cset->dfl_cgrp. * - As a bonus returned cgrp is pinned with the current because it cannot * switch cgroup_ns asynchronously. */ static struct cgroup *current_cgns_cgroup_dfl(void) { struct css_set *cset; if (current->nsproxy) { cset = current->nsproxy->cgroup_ns->root_cset; return __cset_cgroup_from_root(cset, &cgrp_dfl_root); } else { /* * NOTE: This function may be called from bpf_cgroup_from_id() * on a task which has already passed exit_task_namespaces() and * nsproxy == NULL. Fall back to cgrp_dfl_root which will make all * cgroups visible for lookups. */ return &cgrp_dfl_root.cgrp; } } /* look up cgroup associated with given css_set on the specified hierarchy */ static struct cgroup *cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { lockdep_assert_held(&css_set_lock); return __cset_cgroup_from_root(cset, root); } /* * Return the cgroup for "task" from the given hierarchy. Must be * called with css_set_lock held to prevent task's groups from being modified. * Must be called with either cgroup_mutex or rcu read lock to prevent the * cgroup root from being destroyed. */ struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroup_root *root) { /* * No need to lock the task - since we hold css_set_lock the * task can't change groups. */ return cset_cgroup_from_root(task_css_set(task), root); } /* * A task must hold cgroup_mutex to modify cgroups. * * Any task can increment and decrement the count field without lock. * So in general, code holding cgroup_mutex can't rely on the count * field not changing. However, if the count goes to zero, then only * cgroup_attach_task() can increment it again. Because a count of zero * means that no tasks are currently attached, therefore there is no * way a task attached to that cgroup can fork (the other way to * increment the count). So code holding cgroup_mutex can safely * assume that if the count is zero, it will stay zero. Similarly, if * a task holds cgroup_mutex on a cgroup with zero count, it * knows that the cgroup won't be removed, as cgroup_rmdir() * needs that mutex. * * A cgroup can only be deleted if both its 'count' of using tasks * is zero, and its list of 'children' cgroups is empty. Since all * tasks in the system use _some_ cgroup, and since there is always at * least one task in the system (init, pid == 1), therefore, root cgroup * always has either children cgroups and/or using tasks. So we don't * need a special hack to ensure that root cgroup cannot be deleted. * * P.S. One more locking exception. RCU is used to guard the * update of a tasks cgroup pointer by cgroup_attach_task() */ static struct kernfs_syscall_ops cgroup_kf_syscall_ops; static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft, char *buf) { struct cgroup_subsys *ss = cft->ss; if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) && !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) { const char *dbg = (cft->flags & CFTYPE_DEBUG) ? ".__DEBUG__." : ""; snprintf(buf, CGROUP_FILE_NAME_MAX, "%s%s.%s", dbg, cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name, cft->name); } else { strscpy(buf, cft->name, CGROUP_FILE_NAME_MAX); } return buf; } /** * cgroup_file_mode - deduce file mode of a control file * @cft: the control file in question * * S_IRUGO for read, S_IWUSR for write. */ static umode_t cgroup_file_mode(const struct cftype *cft) { umode_t mode = 0; if (cft->read_u64 || cft->read_s64 || cft->seq_show) mode |= S_IRUGO; if (cft->write_u64 || cft->write_s64 || cft->write) { if (cft->flags & CFTYPE_WORLD_WRITABLE) mode |= S_IWUGO; else mode |= S_IWUSR; } return mode; } /** * cgroup_calc_subtree_ss_mask - calculate subtree_ss_mask * @subtree_control: the new subtree_control mask to consider * @this_ss_mask: available subsystems * * On the default hierarchy, a subsystem may request other subsystems to be * enabled together through its ->depends_on mask. In such cases, more * subsystems than specified in "cgroup.subtree_control" may be enabled. * * This function calculates which subsystems need to be enabled if * @subtree_control is to be applied while restricted to @this_ss_mask. */ static u16 cgroup_calc_subtree_ss_mask(u16 subtree_control, u16 this_ss_mask) { u16 cur_ss_mask = subtree_control; struct cgroup_subsys *ss; int ssid; lockdep_assert_held(&cgroup_mutex); cur_ss_mask |= cgrp_dfl_implicit_ss_mask; while (true) { u16 new_ss_mask = cur_ss_mask; do_each_subsys_mask(ss, ssid, cur_ss_mask) { new_ss_mask |= ss->depends_on; } while_each_subsys_mask(); /* * Mask out subsystems which aren't available. This can * happen only if some depended-upon subsystems were bound * to non-default hierarchies. */ new_ss_mask &= this_ss_mask; if (new_ss_mask == cur_ss_mask) break; cur_ss_mask = new_ss_mask; } return cur_ss_mask; } /** * cgroup_kn_unlock - unlocking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced * * This helper undoes cgroup_kn_lock_live() and should be invoked before * the method finishes if locking succeeded. Note that once this function * returns the cgroup returned by cgroup_kn_lock_live() may become * inaccessible any time. If the caller intends to continue to access the * cgroup, it should pin it before invoking this function. */ void cgroup_kn_unlock(struct kernfs_node *kn) { struct cgroup *cgrp; if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else cgrp = kn_priv(kn); cgroup_unlock(); kernfs_unbreak_active_protection(kn); cgroup_put(cgrp); } /** * cgroup_kn_lock_live - locking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced * @drain_offline: perform offline draining on the cgroup * * This helper is to be used by a cgroup kernfs method currently servicing * @kn. It breaks the active protection, performs cgroup locking and * verifies that the associated cgroup is alive. Returns the cgroup if * alive; otherwise, %NULL. A successful return should be undone by a * matching cgroup_kn_unlock() invocation. If @drain_offline is %true, the * cgroup is drained of offlining csses before return. * * Any cgroup kernfs method implementation which requires locking the * associated cgroup should use this helper. It avoids nesting cgroup * locking under kernfs active protection and allows all kernfs operations * including self-removal. */ struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline) { struct cgroup *cgrp; if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else cgrp = kn_priv(kn); /* * We're gonna grab cgroup_mutex which nests outside kernfs * active_ref. cgroup liveliness check alone provides enough * protection against removal. Ensure @cgrp stays accessible and * break the active_ref protection. */ if (!cgroup_tryget(cgrp)) return NULL; kernfs_break_active_protection(kn); if (drain_offline) cgroup_lock_and_drain_offline(cgrp); else cgroup_lock(); if (!cgroup_is_dead(cgrp)) return cgrp; cgroup_kn_unlock(kn); return NULL; } static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) { char name[CGROUP_FILE_NAME_MAX]; lockdep_assert_held(&cgroup_mutex); if (cft->file_offset) { struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss); struct cgroup_file *cfile = (void *)css + cft->file_offset; spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = NULL; spin_unlock_irq(&cgroup_file_kn_lock); timer_delete_sync(&cfile->notify_timer); } kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name)); } /** * css_clear_dir - remove subsys files in a cgroup directory * @css: target css */ static void css_clear_dir(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; struct cftype *cfts; if (!(css->flags & CSS_VISIBLE)) return; css->flags &= ~CSS_VISIBLE; if (!css->ss) { if (cgroup_on_dfl(cgrp)) { cgroup_addrm_files(css, cgrp, cgroup_base_files, false); if (cgroup_psi_enabled()) cgroup_addrm_files(css, cgrp, cgroup_psi_files, false); } else { cgroup_addrm_files(css, cgrp, cgroup1_base_files, false); } } else { list_for_each_entry(cfts, &css->ss->cfts, node) cgroup_addrm_files(css, cgrp, cfts, false); } } /** * css_populate_dir - create subsys files in a cgroup directory * @css: target css * * On failure, no file is added. */ static int css_populate_dir(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; struct cftype *cfts, *failed_cfts; int ret; if (css->flags & CSS_VISIBLE) return 0; if (!css->ss) { if (cgroup_on_dfl(cgrp)) { ret = cgroup_addrm_files(css, cgrp, cgroup_base_files, true); if (ret < 0) return ret; if (cgroup_psi_enabled()) { ret = cgroup_addrm_files(css, cgrp, cgroup_psi_files, true); if (ret < 0) { cgroup_addrm_files(css, cgrp, cgroup_base_files, false); return ret; } } } else { ret = cgroup_addrm_files(css, cgrp, cgroup1_base_files, true); if (ret < 0) return ret; } } else { list_for_each_entry(cfts, &css->ss->cfts, node) { ret = cgroup_addrm_files(css, cgrp, cfts, true); if (ret < 0) { failed_cfts = cfts; goto err; } } } css->flags |= CSS_VISIBLE; return 0; err: list_for_each_entry(cfts, &css->ss->cfts, node) { if (cfts == failed_cfts) break; cgroup_addrm_files(css, cgrp, cfts, false); } return ret; } int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) { struct cgroup *dcgrp = &dst_root->cgrp; struct cgroup_subsys *ss; int ssid, ret; u16 dfl_disable_ss_mask = 0; lockdep_assert_held(&cgroup_mutex); do_each_subsys_mask(ss, ssid, ss_mask) { /* * If @ss has non-root csses attached to it, can't move. * If @ss is an implicit controller, it is exempt from this * rule and can be stolen. */ if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss)) && !ss->implicit_on_dfl) return -EBUSY; /* can't move between two non-dummy roots either */ if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root) return -EBUSY; /* * Collect ssid's that need to be disabled from default * hierarchy. */ if (ss->root == &cgrp_dfl_root) dfl_disable_ss_mask |= 1 << ssid; } while_each_subsys_mask(); if (dfl_disable_ss_mask) { struct cgroup *scgrp = &cgrp_dfl_root.cgrp; /* * Controllers from default hierarchy that need to be rebound * are all disabled together in one go. */ cgrp_dfl_root.subsys_mask &= ~dfl_disable_ss_mask; WARN_ON(cgroup_apply_control(scgrp)); cgroup_finalize_control(scgrp, 0); } do_each_subsys_mask(ss, ssid, ss_mask) { struct cgroup_root *src_root = ss->root; struct cgroup *scgrp = &src_root->cgrp; struct cgroup_subsys_state *css = cgroup_css(scgrp, ss); struct css_set *cset, *cset_pos; struct css_task_iter *it; WARN_ON(!css || cgroup_css(dcgrp, ss)); if (src_root != &cgrp_dfl_root) { /* disable from the source */ src_root->subsys_mask &= ~(1 << ssid); WARN_ON(cgroup_apply_control(scgrp)); cgroup_finalize_control(scgrp, 0); } /* rebind */ RCU_INIT_POINTER(scgrp->subsys[ssid], NULL); rcu_assign_pointer(dcgrp->subsys[ssid], css); ss->root = dst_root; spin_lock_irq(&css_set_lock); css->cgroup = dcgrp; WARN_ON(!list_empty(&dcgrp->e_csets[ss->id])); list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id], e_cset_node[ss->id]) { list_move_tail(&cset->e_cset_node[ss->id], &dcgrp->e_csets[ss->id]); /* * all css_sets of scgrp together in same order to dcgrp, * patch in-flight iterators to preserve correct iteration. * since the iterator is always advanced right away and * finished when it->cset_pos meets it->cset_head, so only * update it->cset_head is enough here. */ list_for_each_entry(it, &cset->task_iters, iters_node) if (it->cset_head == &scgrp->e_csets[ss->id]) it->cset_head = &dcgrp->e_csets[ss->id]; } spin_unlock_irq(&css_set_lock); if (ss->css_rstat_flush) { list_del_rcu(&css->rstat_css_node); synchronize_rcu(); list_add_rcu(&css->rstat_css_node, &dcgrp->rstat_css_list); } /* default hierarchy doesn't enable controllers by default */ dst_root->subsys_mask |= 1 << ssid; if (dst_root == &cgrp_dfl_root) { static_branch_enable(cgroup_subsys_on_dfl_key[ssid]); } else { dcgrp->subtree_control |= 1 << ssid; static_branch_disable(cgroup_subsys_on_dfl_key[ssid]); } ret = cgroup_apply_control(dcgrp); if (ret) pr_warn("partial failure to rebind %s controller (err=%d)\n", ss->name, ret); if (ss->bind) ss->bind(css); } while_each_subsys_mask(); kernfs_activate(dcgrp->kn); return 0; } int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, struct kernfs_root *kf_root) { int len = 0; char *buf = NULL; struct cgroup_root *kf_cgroot = cgroup_root_from_kf(kf_root); struct cgroup *ns_cgroup; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) return -ENOMEM; spin_lock_irq(&css_set_lock); ns_cgroup = current_cgns_cgroup_from_root(kf_cgroot); len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX); spin_unlock_irq(&css_set_lock); if (len == -E2BIG) len = -ERANGE; else if (len > 0) { seq_escape(sf, buf, " \t\n\\"); len = 0; } kfree(buf); return len; } enum cgroup2_param { Opt_nsdelegate, Opt_favordynmods, Opt_memory_localevents, Opt_memory_recursiveprot, Opt_memory_hugetlb_accounting, Opt_pids_localevents, nr__cgroup2_params }; static const struct fs_parameter_spec cgroup2_fs_parameters[] = { fsparam_flag("nsdelegate", Opt_nsdelegate), fsparam_flag("favordynmods", Opt_favordynmods), fsparam_flag("memory_localevents", Opt_memory_localevents), fsparam_flag("memory_recursiveprot", Opt_memory_recursiveprot), fsparam_flag("memory_hugetlb_accounting", Opt_memory_hugetlb_accounting), fsparam_flag("pids_localevents", Opt_pids_localevents), {} }; static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct fs_parse_result result; int opt; opt = fs_parse(fc, cgroup2_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_nsdelegate: ctx->flags |= CGRP_ROOT_NS_DELEGATE; return 0; case Opt_favordynmods: ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS; return 0; case Opt_memory_localevents: ctx->flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS; return 0; case Opt_memory_recursiveprot: ctx->flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT; return 0; case Opt_memory_hugetlb_accounting: ctx->flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING; return 0; case Opt_pids_localevents: ctx->flags |= CGRP_ROOT_PIDS_LOCAL_EVENTS; return 0; } return -EINVAL; } struct cgroup_of_peak *of_peak(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; return &ctx->peak; } static void apply_cgroup_root_flags(unsigned int root_flags) { if (current->nsproxy->cgroup_ns == &init_cgroup_ns) { if (root_flags & CGRP_ROOT_NS_DELEGATE) cgrp_dfl_root.flags |= CGRP_ROOT_NS_DELEGATE; else cgrp_dfl_root.flags &= ~CGRP_ROOT_NS_DELEGATE; cgroup_favor_dynmods(&cgrp_dfl_root, root_flags & CGRP_ROOT_FAVOR_DYNMODS); if (root_flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_LOCAL_EVENTS; if (root_flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_RECURSIVE_PROT; if (root_flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING; if (root_flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) cgrp_dfl_root.flags |= CGRP_ROOT_PIDS_LOCAL_EVENTS; else cgrp_dfl_root.flags &= ~CGRP_ROOT_PIDS_LOCAL_EVENTS; } } static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root) { if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) seq_puts(seq, ",nsdelegate"); if (cgrp_dfl_root.flags & CGRP_ROOT_FAVOR_DYNMODS) seq_puts(seq, ",favordynmods"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) seq_puts(seq, ",memory_localevents"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT) seq_puts(seq, ",memory_recursiveprot"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING) seq_puts(seq, ",memory_hugetlb_accounting"); if (cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) seq_puts(seq, ",pids_localevents"); return 0; } static int cgroup_reconfigure(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); apply_cgroup_root_flags(ctx->flags); return 0; } static void init_cgroup_housekeeping(struct cgroup *cgrp) { struct cgroup_subsys *ss; int ssid; INIT_LIST_HEAD(&cgrp->self.sibling); INIT_LIST_HEAD(&cgrp->self.children); INIT_LIST_HEAD(&cgrp->cset_links); INIT_LIST_HEAD(&cgrp->pidlists); mutex_init(&cgrp->pidlist_mutex); cgrp->self.cgroup = cgrp; cgrp->self.flags |= CSS_ONLINE; cgrp->dom_cgrp = cgrp; cgrp->max_descendants = INT_MAX; cgrp->max_depth = INT_MAX; INIT_LIST_HEAD(&cgrp->rstat_css_list); prev_cputime_init(&cgrp->prev_cputime); for_each_subsys(ss, ssid) INIT_LIST_HEAD(&cgrp->e_csets[ssid]); init_waitqueue_head(&cgrp->offline_waitq); INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent); } void init_cgroup_root(struct cgroup_fs_context *ctx) { struct cgroup_root *root = ctx->root; struct cgroup *cgrp = &root->cgrp; INIT_LIST_HEAD_RCU(&root->root_list); atomic_set(&root->nr_cgrps, 1); cgrp->root = root; init_cgroup_housekeeping(cgrp); /* DYNMODS must be modified through cgroup_favor_dynmods() */ root->flags = ctx->flags & ~CGRP_ROOT_FAVOR_DYNMODS; if (ctx->release_agent) strscpy(root->release_agent_path, ctx->release_agent, PATH_MAX); if (ctx->name) strscpy(root->name, ctx->name, MAX_CGROUP_ROOT_NAMELEN); if (ctx->cpuset_clone_children) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags); } int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) { LIST_HEAD(tmp_links); struct cgroup *root_cgrp = &root->cgrp; struct kernfs_syscall_ops *kf_sops; struct css_set *cset; int i, ret; lockdep_assert_held(&cgroup_mutex); ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) goto out; /* * We're accessing css_set_count without locking css_set_lock here, * but that's OK - it can only be increased by someone holding * cgroup_lock, and that's us. Later rebinding may disable * controllers on the default hierarchy and thus create new csets, * which can't be more than the existing ones. Allocate 2x. */ ret = allocate_cgrp_cset_links(2 * css_set_count, &tmp_links); if (ret) goto cancel_ref; ret = cgroup_init_root_id(root); if (ret) goto cancel_ref; kf_sops = root == &cgrp_dfl_root ? &cgroup_kf_syscall_ops : &cgroup1_kf_syscall_ops; root->kf_root = kernfs_create_root(kf_sops, KERNFS_ROOT_CREATE_DEACTIVATED | KERNFS_ROOT_SUPPORT_EXPORTOP | KERNFS_ROOT_SUPPORT_USER_XATTR | KERNFS_ROOT_INVARIANT_PARENT, root_cgrp); if (IS_ERR(root->kf_root)) { ret = PTR_ERR(root->kf_root); goto exit_root_id; } root_cgrp->kn = kernfs_root_to_node(root->kf_root); WARN_ON_ONCE(cgroup_ino(root_cgrp) != 1); root_cgrp->ancestors[0] = root_cgrp; ret = css_populate_dir(&root_cgrp->self); if (ret) goto destroy_root; ret = cgroup_rstat_init(root_cgrp); if (ret) goto destroy_root; ret = rebind_subsystems(root, ss_mask); if (ret) goto exit_stats; if (root == &cgrp_dfl_root) { ret = cgroup_bpf_inherit(root_cgrp); WARN_ON_ONCE(ret); } trace_cgroup_setup_root(root); /* * There must be no failure case after here, since rebinding takes * care of subsystems' refcounts, which are explicitly dropped in * the failure exit path. */ list_add_rcu(&root->root_list, &cgroup_roots); cgroup_root_count++; /* * Link the root cgroup in this hierarchy into all the css_set * objects. */ spin_lock_irq(&css_set_lock); hash_for_each(css_set_table, i, cset, hlist) { link_css_set(&tmp_links, cset, root_cgrp); if (css_set_populated(cset)) cgroup_update_populated(root_cgrp, true); } spin_unlock_irq(&css_set_lock); BUG_ON(!list_empty(&root_cgrp->self.children)); BUG_ON(atomic_read(&root->nr_cgrps) != 1); ret = 0; goto out; exit_stats: cgroup_rstat_exit(root_cgrp); destroy_root: kernfs_destroy_root(root->kf_root); root->kf_root = NULL; exit_root_id: cgroup_exit_root_id(root); cancel_ref: percpu_ref_exit(&root_cgrp->self.refcnt); out: free_cgrp_cset_links(&tmp_links); return ret; } int cgroup_do_get_tree(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret; ctx->kfc.root = ctx->root->kf_root; if (fc->fs_type == &cgroup2_fs_type) ctx->kfc.magic = CGROUP2_SUPER_MAGIC; else ctx->kfc.magic = CGROUP_SUPER_MAGIC; ret = kernfs_get_tree(fc); /* * In non-init cgroup namespace, instead of root cgroup's dentry, * we return the dentry corresponding to the cgroupns->root_cgrp. */ if (!ret && ctx->ns != &init_cgroup_ns) { struct dentry *nsdentry; struct super_block *sb = fc->root->d_sb; struct cgroup *cgrp; cgroup_lock(); spin_lock_irq(&css_set_lock); cgrp = cset_cgroup_from_root(ctx->ns->root_cset, ctx->root); spin_unlock_irq(&css_set_lock); cgroup_unlock(); nsdentry = kernfs_node_dentry(cgrp->kn, sb); dput(fc->root); if (IS_ERR(nsdentry)) { deactivate_locked_super(sb); ret = PTR_ERR(nsdentry); nsdentry = NULL; } fc->root = nsdentry; } if (!ctx->kfc.new_sb_created) cgroup_put(&ctx->root->cgrp); return ret; } /* * Destroy a cgroup filesystem context. */ static void cgroup_fs_context_free(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); kfree(ctx->name); kfree(ctx->release_agent); put_cgroup_ns(ctx->ns); kernfs_free_fs_context(fc); kfree(ctx); } static int cgroup_get_tree(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret; WRITE_ONCE(cgrp_dfl_visible, true); cgroup_get_live(&cgrp_dfl_root.cgrp); ctx->root = &cgrp_dfl_root; ret = cgroup_do_get_tree(fc); if (!ret) apply_cgroup_root_flags(ctx->flags); return ret; } static const struct fs_context_operations cgroup_fs_context_ops = { .free = cgroup_fs_context_free, .parse_param = cgroup2_parse_param, .get_tree = cgroup_get_tree, .reconfigure = cgroup_reconfigure, }; static const struct fs_context_operations cgroup1_fs_context_ops = { .free = cgroup_fs_context_free, .parse_param = cgroup1_parse_param, .get_tree = cgroup1_get_tree, .reconfigure = cgroup1_reconfigure, }; /* * Initialise the cgroup filesystem creation/reconfiguration context. Notably, * we select the namespace we're going to use. */ static int cgroup_init_fs_context(struct fs_context *fc) { struct cgroup_fs_context *ctx; ctx = kzalloc(sizeof(struct cgroup_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->ns = current->nsproxy->cgroup_ns; get_cgroup_ns(ctx->ns); fc->fs_private = &ctx->kfc; if (fc->fs_type == &cgroup2_fs_type) fc->ops = &cgroup_fs_context_ops; else fc->ops = &cgroup1_fs_context_ops; put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(ctx->ns->user_ns); fc->global = true; if (have_favordynmods) ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS; return 0; } static void cgroup_kill_sb(struct super_block *sb) { struct kernfs_root *kf_root = kernfs_root_from_sb(sb); struct cgroup_root *root = cgroup_root_from_kf(kf_root); /* * If @root doesn't have any children, start killing it. * This prevents new mounts by disabling percpu_ref_tryget_live(). * * And don't kill the default root. */ if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root && !percpu_ref_is_dying(&root->cgrp.self.refcnt)) percpu_ref_kill(&root->cgrp.self.refcnt); cgroup_put(&root->cgrp); kernfs_kill_sb(sb); } struct file_system_type cgroup_fs_type = { .name = "cgroup", .init_fs_context = cgroup_init_fs_context, .parameters = cgroup1_fs_parameters, .kill_sb = cgroup_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; static struct file_system_type cgroup2_fs_type = { .name = "cgroup2", .init_fs_context = cgroup_init_fs_context, .parameters = cgroup2_fs_parameters, .kill_sb = cgroup_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; #ifdef CONFIG_CPUSETS_V1 static const struct fs_context_operations cpuset_fs_context_ops = { .get_tree = cgroup1_get_tree, .free = cgroup_fs_context_free, }; /* * This is ugly, but preserves the userspace API for existing cpuset * users. If someone tries to mount the "cpuset" filesystem, we * silently switch it to mount "cgroup" instead */ static int cpuset_init_fs_context(struct fs_context *fc) { char *agent = kstrdup("/sbin/cpuset_release_agent", GFP_USER); struct cgroup_fs_context *ctx; int err; err = cgroup_init_fs_context(fc); if (err) { kfree(agent); return err; } fc->ops = &cpuset_fs_context_ops; ctx = cgroup_fc2context(fc); ctx->subsys_mask = 1 << cpuset_cgrp_id; ctx->flags |= CGRP_ROOT_NOPREFIX; ctx->release_agent = agent; get_filesystem(&cgroup_fs_type); put_filesystem(fc->fs_type); fc->fs_type = &cgroup_fs_type; return 0; } static struct file_system_type cpuset_fs_type = { .name = "cpuset", .init_fs_context = cpuset_init_fs_context, .fs_flags = FS_USERNS_MOUNT, }; #endif int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns) { struct cgroup *root = cset_cgroup_from_root(ns->root_cset, cgrp->root); return kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen); } int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns) { int ret; cgroup_lock(); spin_lock_irq(&css_set_lock); ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns); spin_unlock_irq(&css_set_lock); cgroup_unlock(); return ret; } EXPORT_SYMBOL_GPL(cgroup_path_ns); /** * cgroup_attach_lock - Lock for ->attach() * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem * * cgroup migration sometimes needs to stabilize threadgroups against forks and * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach() * implementations (e.g. cpuset), also need to disable CPU hotplug. * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can * lead to deadlocks. * * Bringing up a CPU may involve creating and destroying tasks which requires * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while * write-locking threadgroup_rwsem, the locking order is reversed and we end up * waiting for an on-going CPU hotplug operation which in turn is waiting for * the threadgroup_rwsem to be released to create new tasks. For more details: * * http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu * * Resolve the situation by always acquiring cpus_read_lock() before optionally * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that * CPU hotplug is disabled on entry. */ void cgroup_attach_lock(bool lock_threadgroup) { cpus_read_lock(); if (lock_threadgroup) percpu_down_write(&cgroup_threadgroup_rwsem); } /** * cgroup_attach_unlock - Undo cgroup_attach_lock() * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem */ void cgroup_attach_unlock(bool lock_threadgroup) { if (lock_threadgroup) percpu_up_write(&cgroup_threadgroup_rwsem); cpus_read_unlock(); } /** * cgroup_migrate_add_task - add a migration target task to a migration context * @task: target task * @mgctx: target migration context * * Add @task, which is a migration target, to @mgctx->tset. This function * becomes noop if @task doesn't need to be migrated. @task's css_set * should have been added as a migration source and @task->cg_list will be * moved from the css_set's tasks list to mg_tasks one. */ static void cgroup_migrate_add_task(struct task_struct *task, struct cgroup_mgctx *mgctx) { struct css_set *cset; lockdep_assert_held(&css_set_lock); /* @task either already exited or can't exit until the end */ if (task->flags & PF_EXITING) return; /* cgroup_threadgroup_rwsem protects racing against forks */ WARN_ON_ONCE(list_empty(&task->cg_list)); cset = task_css_set(task); if (!cset->mg_src_cgrp) return; mgctx->tset.nr_tasks++; list_move_tail(&task->cg_list, &cset->mg_tasks); if (list_empty(&cset->mg_node)) list_add_tail(&cset->mg_node, &mgctx->tset.src_csets); if (list_empty(&cset->mg_dst_cset->mg_node)) list_add_tail(&cset->mg_dst_cset->mg_node, &mgctx->tset.dst_csets); } /** * cgroup_taskset_first - reset taskset and return the first task * @tset: taskset of interest * @dst_cssp: output variable for the destination css * * @tset iteration is initialized and the first task is returned. */ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp) { tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node); tset->cur_task = NULL; return cgroup_taskset_next(tset, dst_cssp); } /** * cgroup_taskset_next - iterate to the next task in taskset * @tset: taskset of interest * @dst_cssp: output variable for the destination css * * Return the next task in @tset. Iteration must have been initialized * with cgroup_taskset_first(). */ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp) { struct css_set *cset = tset->cur_cset; struct task_struct *task = tset->cur_task; while (CGROUP_HAS_SUBSYS_CONFIG && &cset->mg_node != tset->csets) { if (!task) task = list_first_entry(&cset->mg_tasks, struct task_struct, cg_list); else task = list_next_entry(task, cg_list); if (&task->cg_list != &cset->mg_tasks) { tset->cur_cset = cset; tset->cur_task = task; /* * This function may be called both before and * after cgroup_migrate_execute(). The two cases * can be distinguished by looking at whether @cset * has its ->mg_dst_cset set. */ if (cset->mg_dst_cset) *dst_cssp = cset->mg_dst_cset->subsys[tset->ssid]; else *dst_cssp = cset->subsys[tset->ssid]; return task; } cset = list_next_entry(cset, mg_node); task = NULL; } return NULL; } /** * cgroup_migrate_execute - migrate a taskset * @mgctx: migration context * * Migrate tasks in @mgctx as setup by migration preparation functions. * This function fails iff one of the ->can_attach callbacks fails and * guarantees that either all or none of the tasks in @mgctx are migrated. * @mgctx is consumed regardless of success. */ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx) { struct cgroup_taskset *tset = &mgctx->tset; struct cgroup_subsys *ss; struct task_struct *task, *tmp_task; struct css_set *cset, *tmp_cset; int ssid, failed_ssid, ret; /* check that we can legitimately attach to the cgroup */ if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ss->can_attach) { tset->ssid = ssid; ret = ss->can_attach(tset); if (ret) { failed_ssid = ssid; goto out_cancel_attach; } } } while_each_subsys_mask(); } /* * Now that we're guaranteed success, proceed to move all tasks to * the new cgroup. There are no failure cases after here, so this * is the commit point. */ spin_lock_irq(&css_set_lock); list_for_each_entry(cset, &tset->src_csets, mg_node) { list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) { struct css_set *from_cset = task_css_set(task); struct css_set *to_cset = cset->mg_dst_cset; get_css_set(to_cset); to_cset->nr_tasks++; css_set_move_task(task, from_cset, to_cset, true); from_cset->nr_tasks--; /* * If the source or destination cgroup is frozen, * the task might require to change its state. */ cgroup_freezer_migrate_task(task, from_cset->dfl_cgrp, to_cset->dfl_cgrp); put_css_set_locked(from_cset); } } spin_unlock_irq(&css_set_lock); /* * Migration is committed, all target tasks are now on dst_csets. * Nothing is sensitive to fork() after this point. Notify * controllers that migration is complete. */ tset->csets = &tset->dst_csets; if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ss->attach) { tset->ssid = ssid; ss->attach(tset); } } while_each_subsys_mask(); } ret = 0; goto out_release_tset; out_cancel_attach: if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ssid == failed_ssid) break; if (ss->cancel_attach) { tset->ssid = ssid; ss->cancel_attach(tset); } } while_each_subsys_mask(); } out_release_tset: spin_lock_irq(&css_set_lock); list_splice_init(&tset->dst_csets, &tset->src_csets); list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) { list_splice_tail_init(&cset->mg_tasks, &cset->tasks); list_del_init(&cset->mg_node); } spin_unlock_irq(&css_set_lock); /* * Re-initialize the cgroup_taskset structure in case it is reused * again in another cgroup_migrate_add_task()/cgroup_migrate_execute() * iteration. */ tset->nr_tasks = 0; tset->csets = &tset->src_csets; return ret; } /** * cgroup_migrate_vet_dst - verify whether a cgroup can be migration destination * @dst_cgrp: destination cgroup to test * * On the default hierarchy, except for the mixable, (possible) thread root * and threaded cgroups, subtree_control must be zero for migration * destination cgroups with tasks so that child cgroups don't compete * against tasks. */ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp) { /* v1 doesn't have any restriction */ if (!cgroup_on_dfl(dst_cgrp)) return 0; /* verify @dst_cgrp can host resources */ if (!cgroup_is_valid_domain(dst_cgrp->dom_cgrp)) return -EOPNOTSUPP; /* * If @dst_cgrp is already or can become a thread root or is * threaded, it doesn't matter. */ if (cgroup_can_be_thread_root(dst_cgrp) || cgroup_is_threaded(dst_cgrp)) return 0; /* apply no-internal-process constraint */ if (dst_cgrp->subtree_control) return -EBUSY; return 0; } /** * cgroup_migrate_finish - cleanup after attach * @mgctx: migration context * * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst(). See * those functions for details. */ void cgroup_migrate_finish(struct cgroup_mgctx *mgctx) { struct css_set *cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets, mg_src_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; list_del_init(&cset->mg_src_preload_node); put_css_set_locked(cset); } list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets, mg_dst_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; list_del_init(&cset->mg_dst_preload_node); put_css_set_locked(cset); } spin_unlock_irq(&css_set_lock); } /** * cgroup_migrate_add_src - add a migration source css_set * @src_cset: the source css_set to add * @dst_cgrp: the destination cgroup * @mgctx: migration context * * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp. Pin * @src_cset and add it to @mgctx->src_csets, which should later be cleaned * up by cgroup_migrate_finish(). * * This function may be called without holding cgroup_threadgroup_rwsem * even if the target is a process. Threads may be created and destroyed * but as long as cgroup_mutex is not dropped, no new css_set can be put * into play and the preloaded css_sets are guaranteed to cover all * migrations. */ void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, struct cgroup_mgctx *mgctx) { struct cgroup *src_cgrp; lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock); /* * If ->dead, @src_set is associated with one or more dead cgroups * and doesn't contain any migratable tasks. Ignore it early so * that the rest of migration path doesn't get confused by it. */ if (src_cset->dead) return; if (!list_empty(&src_cset->mg_src_preload_node)) return; src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root); WARN_ON(src_cset->mg_src_cgrp); WARN_ON(src_cset->mg_dst_cgrp); WARN_ON(!list_empty(&src_cset->mg_tasks)); WARN_ON(!list_empty(&src_cset->mg_node)); src_cset->mg_src_cgrp = src_cgrp; src_cset->mg_dst_cgrp = dst_cgrp; get_css_set(src_cset); list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets); } /** * cgroup_migrate_prepare_dst - prepare destination css_sets for migration * @mgctx: migration context * * Tasks are about to be moved and all the source css_sets have been * preloaded to @mgctx->preloaded_src_csets. This function looks up and * pins all destination css_sets, links each to its source, and append them * to @mgctx->preloaded_dst_csets. * * This function must be called after cgroup_migrate_add_src() has been * called on each migration source css_set. After migration is performed * using cgroup_migrate(), cgroup_migrate_finish() must be called on * @mgctx. */ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx) { struct css_set *src_cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); /* look up the dst cset for each src cset and link it to src */ list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets, mg_src_preload_node) { struct css_set *dst_cset; struct cgroup_subsys *ss; int ssid; dst_cset = find_css_set(src_cset, src_cset->mg_dst_cgrp); if (!dst_cset) return -ENOMEM; WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset); /* * If src cset equals dst, it's noop. Drop the src. * cgroup_migrate() will skip the cset too. Note that we * can't handle src == dst as some nodes are used by both. */ if (src_cset == dst_cset) { src_cset->mg_src_cgrp = NULL; src_cset->mg_dst_cgrp = NULL; list_del_init(&src_cset->mg_src_preload_node); put_css_set(src_cset); put_css_set(dst_cset); continue; } src_cset->mg_dst_cset = dst_cset; if (list_empty(&dst_cset->mg_dst_preload_node)) list_add_tail(&dst_cset->mg_dst_preload_node, &mgctx->preloaded_dst_csets); else put_css_set(dst_cset); for_each_subsys(ss, ssid) if (src_cset->subsys[ssid] != dst_cset->subsys[ssid]) mgctx->ss_mask |= 1 << ssid; } return 0; } /** * cgroup_migrate - migrate a process or task to a cgroup * @leader: the leader of the process or the task to migrate * @threadgroup: whether @leader points to the whole process or a single task * @mgctx: migration context * * Migrate a process or task denoted by @leader. If migrating a process, * the caller must be holding cgroup_threadgroup_rwsem. The caller is also * responsible for invoking cgroup_migrate_add_src() and * cgroup_migrate_prepare_dst() on the targets before invoking this * function and following up with cgroup_migrate_finish(). * * As long as a controller's ->can_attach() doesn't fail, this function is * guaranteed to succeed. This means that, excluding ->can_attach() * failure, when migrating multiple targets, the success or failure can be * decided for all targets by invoking group_migrate_prepare_dst() before * actually starting migrating. */ int cgroup_migrate(struct task_struct *leader, bool threadgroup, struct cgroup_mgctx *mgctx) { struct task_struct *task; /* * The following thread iteration should be inside an RCU critical * section to prevent tasks from being freed while taking the snapshot. * spin_lock_irq() implies RCU critical section here. */ spin_lock_irq(&css_set_lock); task = leader; do { cgroup_migrate_add_task(task, mgctx); if (!threadgroup) break; } while_each_thread(leader, task); spin_unlock_irq(&css_set_lock); return cgroup_migrate_execute(mgctx); } /** * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup * @dst_cgrp: the cgroup to attach to * @leader: the task or the leader of the threadgroup to be attached * @threadgroup: attach the whole threadgroup? * * Call holding cgroup_mutex and cgroup_threadgroup_rwsem. */ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup) { DEFINE_CGROUP_MGCTX(mgctx); struct task_struct *task; int ret = 0; /* look up all src csets */ spin_lock_irq(&css_set_lock); rcu_read_lock(); task = leader; do { cgroup_migrate_add_src(task_css_set(task), dst_cgrp, &mgctx); if (!threadgroup) break; } while_each_thread(leader, task); rcu_read_unlock(); spin_unlock_irq(&css_set_lock); /* prepare dst csets and commit */ ret = cgroup_migrate_prepare_dst(&mgctx); if (!ret) ret = cgroup_migrate(leader, threadgroup, &mgctx); cgroup_migrate_finish(&mgctx); if (!ret) TRACE_CGROUP_PATH(attach_task, dst_cgrp, leader, threadgroup); return ret; } struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, bool *threadgroup_locked) { struct task_struct *tsk; pid_t pid; if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return ERR_PTR(-EINVAL); /* * If we migrate a single thread, we don't care about threadgroup * stability. If the thread is `current`, it won't exit(2) under our * hands or change PID through exec(2). We exclude * cgroup_update_dfl_csses and other cgroup_{proc,thread}s_write * callers by cgroup_mutex. * Therefore, we can skip the global lock. */ lockdep_assert_held(&cgroup_mutex); *threadgroup_locked = pid || threadgroup; cgroup_attach_lock(*threadgroup_locked); rcu_read_lock(); if (pid) { tsk = find_task_by_vpid(pid); if (!tsk) { tsk = ERR_PTR(-ESRCH); goto out_unlock_threadgroup; } } else { tsk = current; } if (threadgroup) tsk = tsk->group_leader; /* * kthreads may acquire PF_NO_SETAFFINITY during initialization. * If userland migrates such a kthread to a non-root cgroup, it can * become trapped in a cpuset, or RT kthread may be born in a * cgroup with no rt_runtime allocated. Just say no. */ if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) { tsk = ERR_PTR(-EINVAL); goto out_unlock_threadgroup; } get_task_struct(tsk); goto out_unlock_rcu; out_unlock_threadgroup: cgroup_attach_unlock(*threadgroup_locked); *threadgroup_locked = false; out_unlock_rcu: rcu_read_unlock(); return tsk; } void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked) { struct cgroup_subsys *ss; int ssid; /* release reference from cgroup_procs_write_start() */ put_task_struct(task); cgroup_attach_unlock(threadgroup_locked); for_each_subsys(ss, ssid) if (ss->post_attach) ss->post_attach(); } static void cgroup_print_ss_mask(struct seq_file *seq, u16 ss_mask) { struct cgroup_subsys *ss; bool printed = false; int ssid; do_each_subsys_mask(ss, ssid, ss_mask) { if (printed) seq_putc(seq, ' '); seq_puts(seq, ss->name); printed = true; } while_each_subsys_mask(); if (printed) seq_putc(seq, '\n'); } /* show controllers which are enabled from the parent */ static int cgroup_controllers_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; cgroup_print_ss_mask(seq, cgroup_control(cgrp)); return 0; } /* show controllers which are enabled for a given cgroup's children */ static int cgroup_subtree_control_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; cgroup_print_ss_mask(seq, cgrp->subtree_control); return 0; } /** * cgroup_update_dfl_csses - update css assoc of a subtree in default hierarchy * @cgrp: root of the subtree to update csses for * * @cgrp's control masks have changed and its subtree's css associations * need to be updated accordingly. This function looks up all css_sets * which are attached to the subtree, creates the matching updated css_sets * and migrates the tasks to the new ones. */ static int cgroup_update_dfl_csses(struct cgroup *cgrp) { DEFINE_CGROUP_MGCTX(mgctx); struct cgroup_subsys_state *d_css; struct cgroup *dsct; struct css_set *src_cset; bool has_tasks; int ret; lockdep_assert_held(&cgroup_mutex); /* look up all csses currently attached to @cgrp's subtree */ spin_lock_irq(&css_set_lock); cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { struct cgrp_cset_link *link; /* * As cgroup_update_dfl_csses() is only called by * cgroup_apply_control(). The csses associated with the * given cgrp will not be affected by changes made to * its subtree_control file. We can skip them. */ if (dsct == cgrp) continue; list_for_each_entry(link, &dsct->cset_links, cset_link) cgroup_migrate_add_src(link->cset, dsct, &mgctx); } spin_unlock_irq(&css_set_lock); /* * We need to write-lock threadgroup_rwsem while migrating tasks. * However, if there are no source csets for @cgrp, changing its * controllers isn't gonna produce any task migrations and the * write-locking can be skipped safely. */ has_tasks = !list_empty(&mgctx.preloaded_src_csets); cgroup_attach_lock(has_tasks); /* NULL dst indicates self on default hierarchy */ ret = cgroup_migrate_prepare_dst(&mgctx); if (ret) goto out_finish; spin_lock_irq(&css_set_lock); list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_src_preload_node) { struct task_struct *task, *ntask; /* all tasks in src_csets need to be migrated */ list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list) cgroup_migrate_add_task(task, &mgctx); } spin_unlock_irq(&css_set_lock); ret = cgroup_migrate_execute(&mgctx); out_finish: cgroup_migrate_finish(&mgctx); cgroup_attach_unlock(has_tasks); return ret; } /** * cgroup_lock_and_drain_offline - lock cgroup_mutex and drain offlined csses * @cgrp: root of the target subtree * * Because css offlining is asynchronous, userland may try to re-enable a * controller while the previous css is still around. This function grabs * cgroup_mutex and drains the previous css instances of @cgrp's subtree. */ void cgroup_lock_and_drain_offline(struct cgroup *cgrp) __acquires(&cgroup_mutex) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid; restart: cgroup_lock(); cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); DEFINE_WAIT(wait); if (!css || !percpu_ref_is_dying(&css->refcnt)) continue; cgroup_get_live(dsct); prepare_to_wait(&dsct->offline_waitq, &wait, TASK_UNINTERRUPTIBLE); cgroup_unlock(); schedule(); finish_wait(&dsct->offline_waitq, &wait); cgroup_put(dsct); goto restart; } } } /** * cgroup_save_control - save control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * * Save ->subtree_control, ->subtree_ss_mask and ->dom_cgrp to the * respective old_ prefixed fields for @cgrp's subtree including @cgrp * itself. */ static void cgroup_save_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->old_subtree_control = dsct->subtree_control; dsct->old_subtree_ss_mask = dsct->subtree_ss_mask; dsct->old_dom_cgrp = dsct->dom_cgrp; } } /** * cgroup_propagate_control - refresh control masks of a subtree * @cgrp: root of the target subtree * * For @cgrp and its subtree, ensure ->subtree_ss_mask matches * ->subtree_control and propagate controller availability through the * subtree so that descendants don't have unavailable controllers enabled. */ static void cgroup_propagate_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->subtree_control &= cgroup_control(dsct); dsct->subtree_ss_mask = cgroup_calc_subtree_ss_mask(dsct->subtree_control, cgroup_ss_mask(dsct)); } } /** * cgroup_restore_control - restore control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * * Restore ->subtree_control, ->subtree_ss_mask and ->dom_cgrp from the * respective old_ prefixed fields for @cgrp's subtree including @cgrp * itself. */ static void cgroup_restore_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { dsct->subtree_control = dsct->old_subtree_control; dsct->subtree_ss_mask = dsct->old_subtree_ss_mask; dsct->dom_cgrp = dsct->old_dom_cgrp; } } static bool css_visible(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; if (cgroup_control(cgrp) & (1 << ss->id)) return true; if (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) return false; return cgroup_on_dfl(cgrp) && ss->implicit_on_dfl; } /** * cgroup_apply_control_enable - enable or show csses according to control * @cgrp: root of the target subtree * * Walk @cgrp's subtree and create new csses or make the existing ones * visible. A css is created invisible if it's being implicitly enabled * through dependency. An invisible css is made visible when the userland * explicitly enables it. * * Returns 0 on success, -errno on failure. On failure, csses which have * been processed already aren't cleaned up. The caller is responsible for * cleaning up with cgroup_apply_control_disable(). */ static int cgroup_apply_control_enable(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid, ret; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); if (!(cgroup_ss_mask(dsct) & (1 << ss->id))) continue; if (!css) { css = css_create(dsct, ss); if (IS_ERR(css)) return PTR_ERR(css); } WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt)); if (css_visible(css)) { ret = css_populate_dir(css); if (ret) return ret; } } } return 0; } /** * cgroup_apply_control_disable - kill or hide csses according to control * @cgrp: root of the target subtree * * Walk @cgrp's subtree and kill and hide csses so that they match * cgroup_ss_mask() and cgroup_visible_mask(). * * A css is hidden when the userland requests it to be disabled while other * subsystems are still depending on it. The css must not actively control * resources and be in the vanilla state if it's made visible again later. * Controllers which may be depended upon should provide ->css_reset() for * this purpose. */ static void cgroup_apply_control_disable(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid; cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); if (!css) continue; WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt)); if (css->parent && !(cgroup_ss_mask(dsct) & (1 << ss->id))) { kill_css(css); } else if (!css_visible(css)) { css_clear_dir(css); if (ss->css_reset) ss->css_reset(css); } } } } /** * cgroup_apply_control - apply control mask updates to the subtree * @cgrp: root of the target subtree * * subsystems can be enabled and disabled in a subtree using the following * steps. * * 1. Call cgroup_save_control() to stash the current state. * 2. Update ->subtree_control masks in the subtree as desired. * 3. Call cgroup_apply_control() to apply the changes. * 4. Optionally perform other related operations. * 5. Call cgroup_finalize_control() to finish up. * * This function implements step 3 and propagates the mask changes * throughout @cgrp's subtree, updates csses accordingly and perform * process migrations. */ static int cgroup_apply_control(struct cgroup *cgrp) { int ret; cgroup_propagate_control(cgrp); ret = cgroup_apply_control_enable(cgrp); if (ret) return ret; /* * At this point, cgroup_e_css_by_mask() results reflect the new csses * making the following cgroup_update_dfl_csses() properly update * css associations of all tasks in the subtree. */ return cgroup_update_dfl_csses(cgrp); } /** * cgroup_finalize_control - finalize control mask update * @cgrp: root of the target subtree * @ret: the result of the update * * Finalize control mask update. See cgroup_apply_control() for more info. */ static void cgroup_finalize_control(struct cgroup *cgrp, int ret) { if (ret) { cgroup_restore_control(cgrp); cgroup_propagate_control(cgrp); } cgroup_apply_control_disable(cgrp); } static int cgroup_vet_subtree_control_enable(struct cgroup *cgrp, u16 enable) { u16 domain_enable = enable & ~cgrp_dfl_threaded_ss_mask; /* if nothing is getting enabled, nothing to worry about */ if (!enable) return 0; /* can @cgrp host any resources? */ if (!cgroup_is_valid_domain(cgrp->dom_cgrp)) return -EOPNOTSUPP; /* mixables don't care */ if (cgroup_is_mixable(cgrp)) return 0; if (domain_enable) { /* can't enable domain controllers inside a thread subtree */ if (cgroup_is_thread_root(cgrp) || cgroup_is_threaded(cgrp)) return -EOPNOTSUPP; } else { /* * Threaded controllers can handle internal competitions * and are always allowed inside a (prospective) thread * subtree. */ if (cgroup_can_be_thread_root(cgrp) || cgroup_is_threaded(cgrp)) return 0; } /* * Controllers can't be enabled for a cgroup with tasks to avoid * child cgroups competing against tasks. */ if (cgroup_has_tasks(cgrp)) return -EBUSY; return 0; } /* change the enabled child controllers for a cgroup in the default hierarchy */ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { u16 enable = 0, disable = 0; struct cgroup *cgrp, *child; struct cgroup_subsys *ss; char *tok; int ssid, ret; /* * Parse input - space separated list of subsystem names prefixed * with either + or -. */ buf = strstrip(buf); while ((tok = strsep(&buf, " "))) { if (tok[0] == '\0') continue; do_each_subsys_mask(ss, ssid, ~cgrp_dfl_inhibit_ss_mask) { if (!cgroup_ssid_enabled(ssid) || strcmp(tok + 1, ss->name)) continue; if (*tok == '+') { enable |= 1 << ssid; disable &= ~(1 << ssid); } else if (*tok == '-') { disable |= 1 << ssid; enable &= ~(1 << ssid); } else { return -EINVAL; } break; } while_each_subsys_mask(); if (ssid == CGROUP_SUBSYS_COUNT) return -EINVAL; } cgrp = cgroup_kn_lock_live(of->kn, true); if (!cgrp) return -ENODEV; for_each_subsys(ss, ssid) { if (enable & (1 << ssid)) { if (cgrp->subtree_control & (1 << ssid)) { enable &= ~(1 << ssid); continue; } if (!(cgroup_control(cgrp) & (1 << ssid))) { ret = -ENOENT; goto out_unlock; } } else if (disable & (1 << ssid)) { if (!(cgrp->subtree_control & (1 << ssid))) { disable &= ~(1 << ssid); continue; } /* a child has it enabled? */ cgroup_for_each_live_child(child, cgrp) { if (child->subtree_control & (1 << ssid)) { ret = -EBUSY; goto out_unlock; } } } } if (!enable && !disable) { ret = 0; goto out_unlock; } ret = cgroup_vet_subtree_control_enable(cgrp, enable); if (ret) goto out_unlock; /* save and update control masks and prepare csses */ cgroup_save_control(cgrp); cgrp->subtree_control |= enable; cgrp->subtree_control &= ~disable; ret = cgroup_apply_control(cgrp); cgroup_finalize_control(cgrp, ret); if (ret) goto out_unlock; kernfs_activate(cgrp->kn); out_unlock: cgroup_kn_unlock(of->kn); return ret ?: nbytes; } /** * cgroup_enable_threaded - make @cgrp threaded * @cgrp: the target cgroup * * Called when "threaded" is written to the cgroup.type interface file and * tries to make @cgrp threaded and join the parent's resource domain. * This function is never called on the root cgroup as cgroup.type doesn't * exist on it. */ static int cgroup_enable_threaded(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup *dom_cgrp = parent->dom_cgrp; struct cgroup *dsct; struct cgroup_subsys_state *d_css; int ret; lockdep_assert_held(&cgroup_mutex); /* noop if already threaded */ if (cgroup_is_threaded(cgrp)) return 0; /* * If @cgroup is populated or has domain controllers enabled, it * can't be switched. While the below cgroup_can_be_thread_root() * test can catch the same conditions, that's only when @parent is * not mixable, so let's check it explicitly. */ if (cgroup_is_populated(cgrp) || cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) return -EOPNOTSUPP; /* we're joining the parent's domain, ensure its validity */ if (!cgroup_is_valid_domain(dom_cgrp) || !cgroup_can_be_thread_root(dom_cgrp)) return -EOPNOTSUPP; /* * The following shouldn't cause actual migrations and should * always succeed. */ cgroup_save_control(cgrp); cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) if (dsct == cgrp || cgroup_is_threaded(dsct)) dsct->dom_cgrp = dom_cgrp; ret = cgroup_apply_control(cgrp); if (!ret) parent->nr_threaded_children++; cgroup_finalize_control(cgrp, ret); return ret; } static int cgroup_type_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; if (cgroup_is_threaded(cgrp)) seq_puts(seq, "threaded\n"); else if (!cgroup_is_valid_domain(cgrp)) seq_puts(seq, "domain invalid\n"); else if (cgroup_is_thread_root(cgrp)) seq_puts(seq, "domain threaded\n"); else seq_puts(seq, "domain\n"); return 0; } static ssize_t cgroup_type_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; int ret; /* only switching to threaded mode is supported */ if (strcmp(strstrip(buf), "threaded")) return -EINVAL; /* drain dying csses before we re-apply (threaded) subtree control */ cgrp = cgroup_kn_lock_live(of->kn, true); if (!cgrp) return -ENOENT; /* threaded can only be enabled */ ret = cgroup_enable_threaded(cgrp); cgroup_kn_unlock(of->kn); return ret ?: nbytes; } static int cgroup_max_descendants_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; int descendants = READ_ONCE(cgrp->max_descendants); if (descendants == INT_MAX) seq_puts(seq, "max\n"); else seq_printf(seq, "%d\n", descendants); return 0; } static ssize_t cgroup_max_descendants_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; int descendants; ssize_t ret; buf = strstrip(buf); if (!strcmp(buf, "max")) { descendants = INT_MAX; } else { ret = kstrtoint(buf, 0, &descendants); if (ret) return ret; } if (descendants < 0) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; cgrp->max_descendants = descendants; cgroup_kn_unlock(of->kn); return nbytes; } static int cgroup_max_depth_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; int depth = READ_ONCE(cgrp->max_depth); if (depth == INT_MAX) seq_puts(seq, "max\n"); else seq_printf(seq, "%d\n", depth); return 0; } static ssize_t cgroup_max_depth_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; ssize_t ret; int depth; buf = strstrip(buf); if (!strcmp(buf, "max")) { depth = INT_MAX; } else { ret = kstrtoint(buf, 0, &depth); if (ret) return ret; } if (depth < 0) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; cgrp->max_depth = depth; cgroup_kn_unlock(of->kn); return nbytes; } static int cgroup_events_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; seq_printf(seq, "populated %d\n", cgroup_is_populated(cgrp)); seq_printf(seq, "frozen %d\n", test_bit(CGRP_FROZEN, &cgrp->flags)); return 0; } static int cgroup_stat_show(struct seq_file *seq, void *v) { struct cgroup *cgroup = seq_css(seq)->cgroup; struct cgroup_subsys_state *css; int dying_cnt[CGROUP_SUBSYS_COUNT]; int ssid; seq_printf(seq, "nr_descendants %d\n", cgroup->nr_descendants); /* * Show the number of live and dying csses associated with each of * non-inhibited cgroup subsystems that is bound to cgroup v2. * * Without proper lock protection, racing is possible. So the * numbers may not be consistent when that happens. */ rcu_read_lock(); for (ssid = 0; ssid < CGROUP_SUBSYS_COUNT; ssid++) { dying_cnt[ssid] = -1; if ((BIT(ssid) & cgrp_dfl_inhibit_ss_mask) || (cgroup_subsys[ssid]->root != &cgrp_dfl_root)) continue; css = rcu_dereference_raw(cgroup->subsys[ssid]); dying_cnt[ssid] = cgroup->nr_dying_subsys[ssid]; seq_printf(seq, "nr_subsys_%s %d\n", cgroup_subsys[ssid]->name, css ? (css->nr_descendants + 1) : 0); } seq_printf(seq, "nr_dying_descendants %d\n", cgroup->nr_dying_descendants); for (ssid = 0; ssid < CGROUP_SUBSYS_COUNT; ssid++) { if (dying_cnt[ssid] >= 0) seq_printf(seq, "nr_dying_subsys_%s %d\n", cgroup_subsys[ssid]->name, dying_cnt[ssid]); } rcu_read_unlock(); return 0; } #ifdef CONFIG_CGROUP_SCHED /** * cgroup_tryget_css - try to get a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get @cgrp's css associated with @ss. If the css doesn't exist * or is offline, %NULL is returned. */ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; rcu_read_lock(); css = cgroup_css(cgrp, ss); if (css && !css_tryget_online(css)) css = NULL; rcu_read_unlock(); return css; } static int cgroup_extra_stat_show(struct seq_file *seq, int ssid) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct cgroup_subsys *ss = cgroup_subsys[ssid]; struct cgroup_subsys_state *css; int ret; if (!ss->css_extra_stat_show) return 0; css = cgroup_tryget_css(cgrp, ss); if (!css) return 0; ret = ss->css_extra_stat_show(seq, css); css_put(css); return ret; } static int cgroup_local_stat_show(struct seq_file *seq, struct cgroup *cgrp, int ssid) { struct cgroup_subsys *ss = cgroup_subsys[ssid]; struct cgroup_subsys_state *css; int ret; if (!ss->css_local_stat_show) return 0; css = cgroup_tryget_css(cgrp, ss); if (!css) return 0; ret = ss->css_local_stat_show(seq, css); css_put(css); return ret; } #endif static int cpu_stat_show(struct seq_file *seq, void *v) { int ret = 0; cgroup_base_stat_cputime_show(seq); #ifdef CONFIG_CGROUP_SCHED ret = cgroup_extra_stat_show(seq, cpu_cgrp_id); #endif return ret; } static int cpu_local_stat_show(struct seq_file *seq, void *v) { struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup; int ret = 0; #ifdef CONFIG_CGROUP_SCHED ret = cgroup_local_stat_show(seq, cgrp, cpu_cgrp_id); #endif return ret; } #ifdef CONFIG_PSI static int cgroup_io_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_IO); } static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_MEM); } static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_CPU); } static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, enum psi_res res) { struct cgroup_file_ctx *ctx = of->priv; struct psi_trigger *new; struct cgroup *cgrp; struct psi_group *psi; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; cgroup_get(cgrp); cgroup_kn_unlock(of->kn); /* Allow only one trigger per file descriptor */ if (ctx->psi.trigger) { cgroup_put(cgrp); return -EBUSY; } psi = cgroup_psi(cgrp); new = psi_trigger_create(psi, buf, res, of->file, of); if (IS_ERR(new)) { cgroup_put(cgrp); return PTR_ERR(new); } smp_store_release(&ctx->psi.trigger, new); cgroup_put(cgrp); return nbytes; } static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_IO); } static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_MEM); } static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_CPU); } #ifdef CONFIG_IRQ_TIME_ACCOUNTING static int cgroup_irq_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_IRQ); } static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_IRQ); } #endif static int cgroup_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); seq_printf(seq, "%d\n", psi->enabled); return 0; } static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { ssize_t ret; int enable; struct cgroup *cgrp; struct psi_group *psi; ret = kstrtoint(strstrip(buf), 0, &enable); if (ret) return ret; if (enable < 0 || enable > 1) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; psi = cgroup_psi(cgrp); if (psi->enabled != enable) { int i; /* show or hide {cpu,memory,io,irq}.pressure files */ for (i = 0; i < NR_PSI_RESOURCES; i++) cgroup_file_show(&cgrp->psi_files[i], enable); psi->enabled = enable; if (enable) psi_cgroup_restart(psi); } cgroup_kn_unlock(of->kn); return nbytes; } static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, poll_table *pt) { struct cgroup_file_ctx *ctx = of->priv; return psi_trigger_poll(&ctx->psi.trigger, of->file, pt); } static void cgroup_pressure_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; psi_trigger_destroy(ctx->psi.trigger); } bool cgroup_psi_enabled(void) { if (static_branch_likely(&psi_disabled)) return false; return (cgroup_feature_disable_mask & (1 << OPT_FEATURE_PRESSURE)) == 0; } #else /* CONFIG_PSI */ bool cgroup_psi_enabled(void) { return false; } #endif /* CONFIG_PSI */ static int cgroup_freeze_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; seq_printf(seq, "%d\n", cgrp->freezer.freeze); return 0; } static ssize_t cgroup_freeze_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; ssize_t ret; int freeze; ret = kstrtoint(strstrip(buf), 0, &freeze); if (ret) return ret; if (freeze < 0 || freeze > 1) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; cgroup_freeze(cgrp, freeze); cgroup_kn_unlock(of->kn); return nbytes; } static void __cgroup_kill(struct cgroup *cgrp) { struct css_task_iter it; struct task_struct *task; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); cgrp->kill_seq++; spin_unlock_irq(&css_set_lock); css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED, &it); while ((task = css_task_iter_next(&it))) { /* Ignore kernel threads here. */ if (task->flags & PF_KTHREAD) continue; /* Skip tasks that are already dying. */ if (__fatal_signal_pending(task)) continue; send_sig(SIGKILL, task, 0); } css_task_iter_end(&it); } static void cgroup_kill(struct cgroup *cgrp) { struct cgroup_subsys_state *css; struct cgroup *dsct; lockdep_assert_held(&cgroup_mutex); cgroup_for_each_live_descendant_pre(dsct, css, cgrp) __cgroup_kill(dsct); } static ssize_t cgroup_kill_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { ssize_t ret = 0; int kill; struct cgroup *cgrp; ret = kstrtoint(strstrip(buf), 0, &kill); if (ret) return ret; if (kill != 1) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; /* * Killing is a process directed operation, i.e. the whole thread-group * is taken down so act like we do for cgroup.procs and only make this * writable in non-threaded cgroups. */ if (cgroup_is_threaded(cgrp)) ret = -EOPNOTSUPP; else cgroup_kill(cgrp); cgroup_kn_unlock(of->kn); return ret ?: nbytes; } static int cgroup_file_open(struct kernfs_open_file *of) { struct cftype *cft = of_cft(of); struct cgroup_file_ctx *ctx; int ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->ns = current->nsproxy->cgroup_ns; get_cgroup_ns(ctx->ns); of->priv = ctx; if (!cft->open) return 0; ret = cft->open(of); if (ret) { put_cgroup_ns(ctx->ns); kfree(ctx); } return ret; } static void cgroup_file_release(struct kernfs_open_file *of) { struct cftype *cft = of_cft(of); struct cgroup_file_ctx *ctx = of->priv; if (cft->release) cft->release(of); put_cgroup_ns(ctx->ns); kfree(ctx); } static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = kn_priv(of->kn); struct cftype *cft = of_cft(of); struct cgroup_subsys_state *css; int ret; if (!nbytes) return 0; /* * If namespaces are delegation boundaries, disallow writes to * files in an non-init namespace root from inside the namespace * except for the files explicitly marked delegatable - * eg. cgroup.procs, cgroup.threads and cgroup.subtree_control. */ if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) && !(cft->flags & CFTYPE_NS_DELEGATABLE) && ctx->ns != &init_cgroup_ns && ctx->ns->root_cset->dfl_cgrp == cgrp) return -EPERM; if (cft->write) return cft->write(of, buf, nbytes, off); /* * kernfs guarantees that a file isn't deleted with operations in * flight, which means that the matching css is and stays alive and * doesn't need to be pinned. The RCU locking is not necessary * either. It's just for the convenience of using cgroup_css(). */ rcu_read_lock(); css = cgroup_css(cgrp, cft->ss); rcu_read_unlock(); if (cft->write_u64) { unsigned long long v; ret = kstrtoull(buf, 0, &v); if (!ret) ret = cft->write_u64(css, cft, v); } else if (cft->write_s64) { long long v; ret = kstrtoll(buf, 0, &v); if (!ret) ret = cft->write_s64(css, cft, v); } else { ret = -EINVAL; } return ret ?: nbytes; } static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt) { struct cftype *cft = of_cft(of); if (cft->poll) return cft->poll(of, pt); return kernfs_generic_poll(of, pt); } static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos) { return seq_cft(seq)->seq_start(seq, ppos); } static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos) { return seq_cft(seq)->seq_next(seq, v, ppos); } static void cgroup_seqfile_stop(struct seq_file *seq, void *v) { if (seq_cft(seq)->seq_stop) seq_cft(seq)->seq_stop(seq, v); } static int cgroup_seqfile_show(struct seq_file *m, void *arg) { struct cftype *cft = seq_cft(m); struct cgroup_subsys_state *css = seq_css(m); if (cft->seq_show) return cft->seq_show(m, arg); if (cft->read_u64) seq_printf(m, "%llu\n", cft->read_u64(css, cft)); else if (cft->read_s64) seq_printf(m, "%lld\n", cft->read_s64(css, cft)); else return -EINVAL; return 0; } static struct kernfs_ops cgroup_kf_single_ops = { .atomic_write_len = PAGE_SIZE, .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, .poll = cgroup_file_poll, .seq_show = cgroup_seqfile_show, }; static struct kernfs_ops cgroup_kf_ops = { .atomic_write_len = PAGE_SIZE, .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, .poll = cgroup_file_poll, .seq_start = cgroup_seqfile_start, .seq_next = cgroup_seqfile_next, .seq_stop = cgroup_seqfile_stop, .seq_show = cgroup_seqfile_show, }; static void cgroup_file_notify_timer(struct timer_list *timer) { cgroup_file_notify(container_of(timer, struct cgroup_file, notify_timer)); } static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype *cft) { char name[CGROUP_FILE_NAME_MAX]; struct kernfs_node *kn; struct lock_class_key *key = NULL; #ifdef CONFIG_DEBUG_LOCK_ALLOC key = &cft->lockdep_key; #endif kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name), cgroup_file_mode(cft), current_fsuid(), current_fsgid(), 0, cft->kf_ops, cft, NULL, key); if (IS_ERR(kn)) return PTR_ERR(kn); if (cft->file_offset) { struct cgroup_file *cfile = (void *)css + cft->file_offset; timer_setup(&cfile->notify_timer, cgroup_file_notify_timer, 0); spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = kn; spin_unlock_irq(&cgroup_file_kn_lock); } return 0; } /** * cgroup_addrm_files - add or remove files to a cgroup directory * @css: the target css * @cgrp: the target cgroup (usually css->cgroup) * @cfts: array of cftypes to be added * @is_add: whether to add or remove * * Depending on @is_add, add or remove files defined by @cfts on @cgrp. * For removals, this function never fails. */ static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add) { struct cftype *cft, *cft_end = NULL; int ret = 0; lockdep_assert_held(&cgroup_mutex); restart: for (cft = cfts; cft != cft_end && cft->name[0] != '\0'; cft++) { /* does cft->flags tell us to skip this file on @cgrp? */ if ((cft->flags & __CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp)) continue; if ((cft->flags & __CFTYPE_NOT_ON_DFL) && cgroup_on_dfl(cgrp)) continue; if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgroup_parent(cgrp)) continue; if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgroup_parent(cgrp)) continue; if ((cft->flags & CFTYPE_DEBUG) && !cgroup_debug) continue; if (is_add) { ret = cgroup_add_file(css, cgrp, cft); if (ret) { pr_warn("%s: failed to add %s, err=%d\n", __func__, cft->name, ret); cft_end = cft; is_add = false; goto restart; } } else { cgroup_rm_file(cgrp, cft); } } return ret; } static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add) { struct cgroup_subsys *ss = cfts[0].ss; struct cgroup *root = &ss->root->cgrp; struct cgroup_subsys_state *css; int ret = 0; lockdep_assert_held(&cgroup_mutex); /* add/rm files for all cgroups created before */ css_for_each_descendant_pre(css, cgroup_css(root, ss)) { struct cgroup *cgrp = css->cgroup; if (!(css->flags & CSS_VISIBLE)) continue; ret = cgroup_addrm_files(css, cgrp, cfts, is_add); if (ret) break; } if (is_add && !ret) kernfs_activate(root->kn); return ret; } static void cgroup_exit_cftypes(struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft->name[0] != '\0'; cft++) { /* free copy for custom atomic_write_len, see init_cftypes() */ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) kfree(cft->kf_ops); cft->kf_ops = NULL; cft->ss = NULL; /* revert flags set by cgroup core while adding @cfts */ cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL | __CFTYPE_ADDED); } } static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; int ret = 0; for (cft = cfts; cft->name[0] != '\0'; cft++) { struct kernfs_ops *kf_ops; WARN_ON(cft->ss || cft->kf_ops); if (cft->flags & __CFTYPE_ADDED) { ret = -EBUSY; break; } if (cft->seq_start) kf_ops = &cgroup_kf_ops; else kf_ops = &cgroup_kf_single_ops; /* * Ugh... if @cft wants a custom max_write_len, we need to * make a copy of kf_ops to set its atomic_write_len. */ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) { kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL); if (!kf_ops) { ret = -ENOMEM; break; } kf_ops->atomic_write_len = cft->max_write_len; } cft->kf_ops = kf_ops; cft->ss = ss; cft->flags |= __CFTYPE_ADDED; } if (ret) cgroup_exit_cftypes(cfts); return ret; } static void cgroup_rm_cftypes_locked(struct cftype *cfts) { lockdep_assert_held(&cgroup_mutex); list_del(&cfts->node); cgroup_apply_cftypes(cfts, false); cgroup_exit_cftypes(cfts); } /** * cgroup_rm_cftypes - remove an array of cftypes from a subsystem * @cfts: zero-length name terminated array of cftypes * * Unregister @cfts. Files described by @cfts are removed from all * existing cgroups and all future cgroups won't have them either. This * function can be called anytime whether @cfts' subsys is attached or not. * * Returns 0 on successful unregistration, -ENOENT if @cfts is not * registered. */ int cgroup_rm_cftypes(struct cftype *cfts) { if (!cfts || cfts[0].name[0] == '\0') return 0; if (!(cfts[0].flags & __CFTYPE_ADDED)) return -ENOENT; cgroup_lock(); cgroup_rm_cftypes_locked(cfts); cgroup_unlock(); return 0; } /** * cgroup_add_cftypes - add an array of cftypes to a subsystem * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Register @cfts to @ss. Files described by @cfts are created for all * existing cgroups to which @ss is attached and all future cgroups will * have them too. This function can be called anytime whether @ss is * attached or not. * * Returns 0 on successful registration, -errno on failure. Note that this * function currently returns 0 as long as @cfts registration is successful * even if some file creation attempts on existing cgroups fail. */ int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { int ret; if (!cgroup_ssid_enabled(ss->id)) return 0; if (!cfts || cfts[0].name[0] == '\0') return 0; ret = cgroup_init_cftypes(ss, cfts); if (ret) return ret; cgroup_lock(); list_add_tail(&cfts->node, &ss->cfts); ret = cgroup_apply_cftypes(cfts, true); if (ret) cgroup_rm_cftypes_locked(cfts); cgroup_unlock(); return ret; } /** * cgroup_add_dfl_cftypes - add an array of cftypes for default hierarchy * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Similar to cgroup_add_cftypes() but the added files are only used for * the default hierarchy. */ int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft && cft->name[0] != '\0'; cft++) cft->flags |= __CFTYPE_ONLY_ON_DFL; return cgroup_add_cftypes(ss, cfts); } /** * cgroup_add_legacy_cftypes - add an array of cftypes for legacy hierarchies * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Similar to cgroup_add_cftypes() but the added files are only used for * the legacy hierarchies. */ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft && cft->name[0] != '\0'; cft++) cft->flags |= __CFTYPE_NOT_ON_DFL; return cgroup_add_cftypes(ss, cfts); } /** * cgroup_file_notify - generate a file modified event for a cgroup_file * @cfile: target cgroup_file * * @cfile must have been obtained by setting cftype->file_offset. */ void cgroup_file_notify(struct cgroup_file *cfile) { unsigned long flags; spin_lock_irqsave(&cgroup_file_kn_lock, flags); if (cfile->kn) { unsigned long last = cfile->notified_at; unsigned long next = last + CGROUP_FILE_NOTIFY_MIN_INTV; if (time_in_range(jiffies, last, next)) { timer_reduce(&cfile->notify_timer, next); } else { kernfs_notify(cfile->kn); cfile->notified_at = jiffies; } } spin_unlock_irqrestore(&cgroup_file_kn_lock, flags); } /** * cgroup_file_show - show or hide a hidden cgroup file * @cfile: target cgroup_file obtained by setting cftype->file_offset * @show: whether to show or hide */ void cgroup_file_show(struct cgroup_file *cfile, bool show) { struct kernfs_node *kn; spin_lock_irq(&cgroup_file_kn_lock); kn = cfile->kn; kernfs_get(kn); spin_unlock_irq(&cgroup_file_kn_lock); if (kn) kernfs_show(kn, show); kernfs_put(kn); } /** * css_next_child - find the next child of a given css * @pos: the current position (%NULL to initiate traversal) * @parent: css whose children to walk * * This function returns the next child of @parent and should be called * under either cgroup_mutex or RCU read lock. The only requirement is * that @parent and @pos are accessible. The next sibling is guaranteed to * be returned regardless of their states. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* * @pos could already have been unlinked from the sibling list. * Once a cgroup is removed, its ->sibling.next is no longer * updated when its next sibling changes. CSS_RELEASED is set when * @pos is taken off list, at which time its next pointer is valid, * and, as releases are serialized, the one pointed to by the next * pointer is guaranteed to not have started release yet. This * implies that if we observe !CSS_RELEASED on @pos in this RCU * critical section, the one pointed to by its next pointer is * guaranteed to not have finished its RCU grace period even if we * have dropped rcu_read_lock() in-between iterations. * * If @pos has CSS_RELEASED set, its next pointer can't be * dereferenced; however, as each css is given a monotonically * increasing unique serial number and always appended to the * sibling list, the next one can be found by walking the parent's * children until the first css with higher serial number than * @pos's. While this path can be slower, it happens iff iteration * races against release and the race window is very small. */ if (!pos) { next = list_entry_rcu(parent->children.next, struct cgroup_subsys_state, sibling); } else if (likely(!(pos->flags & CSS_RELEASED))) { next = list_entry_rcu(pos->sibling.next, struct cgroup_subsys_state, sibling); } else { list_for_each_entry_rcu(next, &parent->children, sibling, lockdep_is_held(&cgroup_mutex)) if (next->serial_nr > pos->serial_nr) break; } /* * @next, if not pointing to the head, can be dereferenced and is * the next sibling. */ if (&next->sibling != &parent->children) return next; return NULL; } /** * css_next_descendant_pre - find the next descendant for pre-order walk * @pos: the current position (%NULL to initiate traversal) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_pre(). Find the next descendant * to visit for pre-order traversal of @root's descendants. @root is * included in the iteration and the first node to be visited. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. Additionally, it isn't necessary to hold onto a reference to @pos. * This function will return the correct next descendant as long as both @pos * and @root are accessible and @pos is a descendant of @root. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state * css_next_descendant_pre(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *root) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* if first iteration, visit @root */ if (!pos) return root; /* visit the first child if exists */ next = css_next_child(NULL, pos); if (next) return next; /* no child, visit my or the closest ancestor's next sibling */ while (pos != root) { next = css_next_child(pos, pos->parent); if (next) return next; pos = pos->parent; } return NULL; } EXPORT_SYMBOL_GPL(css_next_descendant_pre); /** * css_rightmost_descendant - return the rightmost descendant of a css * @pos: css of interest * * Return the rightmost descendant of @pos. If there's no descendant, @pos * is returned. This can be used during pre-order traversal to skip * subtree of @pos. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. Additionally, it isn't necessary to hold onto a reference to @pos. * This function will return the correct rightmost descendant as long as @pos * is accessible. */ struct cgroup_subsys_state * css_rightmost_descendant(struct cgroup_subsys_state *pos) { struct cgroup_subsys_state *last, *tmp; cgroup_assert_mutex_or_rcu_locked(); do { last = pos; /* ->prev isn't RCU safe, walk ->next till the end */ pos = NULL; css_for_each_child(tmp, last) pos = tmp; } while (pos); return last; } static struct cgroup_subsys_state * css_leftmost_descendant(struct cgroup_subsys_state *pos) { struct cgroup_subsys_state *last; do { last = pos; pos = css_next_child(NULL, pos); } while (pos); return last; } /** * css_next_descendant_post - find the next descendant for post-order walk * @pos: the current position (%NULL to initiate traversal) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_post(). Find the next descendant * to visit for post-order traversal of @root's descendants. @root is * included in the iteration and the last node to be visited. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. Additionally, it isn't necessary to hold onto a reference to @pos. * This function will return the correct next descendant as long as both @pos * and @cgroup are accessible and @pos is a descendant of @cgroup. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state * css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *root) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* if first iteration, visit leftmost descendant which may be @root */ if (!pos) return css_leftmost_descendant(root); /* if we visited @root, we're done */ if (pos == root) return NULL; /* if there's an unvisited sibling, visit its leftmost descendant */ next = css_next_child(pos, pos->parent); if (next) return css_leftmost_descendant(next); /* no sibling left, visit parent */ return pos->parent; } /** * css_has_online_children - does a css have online children * @css: the target css * * Returns %true if @css has any online children; otherwise, %false. This * function can be called from any context but the caller is responsible * for synchronizing against on/offlining as necessary. */ bool css_has_online_children(struct cgroup_subsys_state *css) { struct cgroup_subsys_state *child; bool ret = false; rcu_read_lock(); css_for_each_child(child, css) { if (child->flags & CSS_ONLINE) { ret = true; break; } } rcu_read_unlock(); return ret; } static struct css_set *css_task_iter_next_css_set(struct css_task_iter *it) { struct list_head *l; struct cgrp_cset_link *link; struct css_set *cset; lockdep_assert_held(&css_set_lock); /* find the next threaded cset */ if (it->tcset_pos) { l = it->tcset_pos->next; if (l != it->tcset_head) { it->tcset_pos = l; return container_of(l, struct css_set, threaded_csets_node); } it->tcset_pos = NULL; } /* find the next cset */ l = it->cset_pos; l = l->next; if (l == it->cset_head) { it->cset_pos = NULL; return NULL; } if (it->ss) { cset = container_of(l, struct css_set, e_cset_node[it->ss->id]); } else { link = list_entry(l, struct cgrp_cset_link, cset_link); cset = link->cset; } it->cset_pos = l; /* initialize threaded css_set walking */ if (it->flags & CSS_TASK_ITER_THREADED) { if (it->cur_dcset) put_css_set_locked(it->cur_dcset); it->cur_dcset = cset; get_css_set(cset); it->tcset_head = &cset->threaded_csets; it->tcset_pos = &cset->threaded_csets; } return cset; } /** * css_task_iter_advance_css_set - advance a task iterator to the next css_set * @it: the iterator to advance * * Advance @it to the next css_set to walk. */ static void css_task_iter_advance_css_set(struct css_task_iter *it) { struct css_set *cset; lockdep_assert_held(&css_set_lock); /* Advance to the next non-empty css_set and find first non-empty tasks list*/ while ((cset = css_task_iter_next_css_set(it))) { if (!list_empty(&cset->tasks)) { it->cur_tasks_head = &cset->tasks; break; } else if (!list_empty(&cset->mg_tasks)) { it->cur_tasks_head = &cset->mg_tasks; break; } else if (!list_empty(&cset->dying_tasks)) { it->cur_tasks_head = &cset->dying_tasks; break; } } if (!cset) { it->task_pos = NULL; return; } it->task_pos = it->cur_tasks_head->next; /* * We don't keep css_sets locked across iteration steps and thus * need to take steps to ensure that iteration can be resumed after * the lock is re-acquired. Iteration is performed at two levels - * css_sets and tasks in them. * * Once created, a css_set never leaves its cgroup lists, so a * pinned css_set is guaranteed to stay put and we can resume * iteration afterwards. * * Tasks may leave @cset across iteration steps. This is resolved * by registering each iterator with the css_set currently being * walked and making css_set_move_task() advance iterators whose * next task is leaving. */ if (it->cur_cset) { list_del(&it->iters_node); put_css_set_locked(it->cur_cset); } get_css_set(cset); it->cur_cset = cset; list_add(&it->iters_node, &cset->task_iters); } static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task) { lockdep_assert_held(&css_set_lock); if (it->task_pos == &task->cg_list) { it->task_pos = it->task_pos->next; it->flags |= CSS_TASK_ITER_SKIPPED; } } static void css_task_iter_advance(struct css_task_iter *it) { struct task_struct *task; lockdep_assert_held(&css_set_lock); repeat: if (it->task_pos) { /* * Advance iterator to find next entry. We go through cset * tasks, mg_tasks and dying_tasks, when consumed we move onto * the next cset. */ if (it->flags & CSS_TASK_ITER_SKIPPED) it->flags &= ~CSS_TASK_ITER_SKIPPED; else it->task_pos = it->task_pos->next; if (it->task_pos == &it->cur_cset->tasks) { it->cur_tasks_head = &it->cur_cset->mg_tasks; it->task_pos = it->cur_tasks_head->next; } if (it->task_pos == &it->cur_cset->mg_tasks) { it->cur_tasks_head = &it->cur_cset->dying_tasks; it->task_pos = it->cur_tasks_head->next; } if (it->task_pos == &it->cur_cset->dying_tasks) css_task_iter_advance_css_set(it); } else { /* called from start, proceed to the first cset */ css_task_iter_advance_css_set(it); } if (!it->task_pos) return; task = list_entry(it->task_pos, struct task_struct, cg_list); if (it->flags & CSS_TASK_ITER_PROCS) { /* if PROCS, skip over tasks which aren't group leaders */ if (!thread_group_leader(task)) goto repeat; /* and dying leaders w/o live member threads */ if (it->cur_tasks_head == &it->cur_cset->dying_tasks && !atomic_read(&task->signal->live)) goto repeat; } else { /* skip all dying ones */ if (it->cur_tasks_head == &it->cur_cset->dying_tasks) goto repeat; } } /** * css_task_iter_start - initiate task iteration * @css: the css to walk tasks of * @flags: CSS_TASK_ITER_* flags * @it: the task iterator to use * * Initiate iteration through the tasks of @css. The caller can call * css_task_iter_next() to walk through the tasks until the function * returns NULL. On completion of iteration, css_task_iter_end() must be * called. */ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it) { unsigned long irqflags; memset(it, 0, sizeof(*it)); spin_lock_irqsave(&css_set_lock, irqflags); it->ss = css->ss; it->flags = flags; if (CGROUP_HAS_SUBSYS_CONFIG && it->ss) it->cset_pos = &css->cgroup->e_csets[css->ss->id]; else it->cset_pos = &css->cgroup->cset_links; it->cset_head = it->cset_pos; css_task_iter_advance(it); spin_unlock_irqrestore(&css_set_lock, irqflags); } /** * css_task_iter_next - return the next task for the iterator * @it: the task iterator being iterated * * The "next" function for task iteration. @it should have been * initialized via css_task_iter_start(). Returns NULL when the iteration * reaches the end. */ struct task_struct *css_task_iter_next(struct css_task_iter *it) { unsigned long irqflags; if (it->cur_task) { put_task_struct(it->cur_task); it->cur_task = NULL; } spin_lock_irqsave(&css_set_lock, irqflags); /* @it may be half-advanced by skips, finish advancing */ if (it->flags & CSS_TASK_ITER_SKIPPED) css_task_iter_advance(it); if (it->task_pos) { it->cur_task = list_entry(it->task_pos, struct task_struct, cg_list); get_task_struct(it->cur_task); css_task_iter_advance(it); } spin_unlock_irqrestore(&css_set_lock, irqflags); return it->cur_task; } /** * css_task_iter_end - finish task iteration * @it: the task iterator to finish * * Finish task iteration started by css_task_iter_start(). */ void css_task_iter_end(struct css_task_iter *it) { unsigned long irqflags; if (it->cur_cset) { spin_lock_irqsave(&css_set_lock, irqflags); list_del(&it->iters_node); put_css_set_locked(it->cur_cset); spin_unlock_irqrestore(&css_set_lock, irqflags); } if (it->cur_dcset) put_css_set(it->cur_dcset); if (it->cur_task) put_task_struct(it->cur_task); } static void cgroup_procs_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; if (ctx->procs.started) css_task_iter_end(&ctx->procs.iter); } static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; if (pos) (*pos)++; return css_task_iter_next(&ctx->procs.iter); } static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, unsigned int iter_flags) { struct kernfs_open_file *of = s->private; struct cgroup *cgrp = seq_css(s)->cgroup; struct cgroup_file_ctx *ctx = of->priv; struct css_task_iter *it = &ctx->procs.iter; /* * When a seq_file is seeked, it's always traversed sequentially * from position 0, so we can simply keep iterating on !0 *pos. */ if (!ctx->procs.started) { if (WARN_ON_ONCE((*pos))) return ERR_PTR(-EINVAL); css_task_iter_start(&cgrp->self, iter_flags, it); ctx->procs.started = true; } else if (!(*pos)) { css_task_iter_end(it); css_task_iter_start(&cgrp->self, iter_flags, it); } else return it->cur_task; return cgroup_procs_next(s, NULL, NULL); } static void *cgroup_procs_start(struct seq_file *s, loff_t *pos) { struct cgroup *cgrp = seq_css(s)->cgroup; /* * All processes of a threaded subtree belong to the domain cgroup * of the subtree. Only threads can be distributed across the * subtree. Reject reads on cgroup.procs in the subtree proper. * They're always empty anyway. */ if (cgroup_is_threaded(cgrp)) return ERR_PTR(-EOPNOTSUPP); return __cgroup_procs_start(s, pos, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED); } static int cgroup_procs_show(struct seq_file *s, void *v) { seq_printf(s, "%d\n", task_pid_vnr(v)); return 0; } static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb) { int ret; struct inode *inode; lockdep_assert_held(&cgroup_mutex); inode = kernfs_get_inode(sb, cgrp->procs_file.kn); if (!inode) return -ENOMEM; ret = inode_permission(&nop_mnt_idmap, inode, MAY_WRITE); iput(inode); return ret; } static int cgroup_procs_write_permission(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, struct super_block *sb, struct cgroup_namespace *ns) { struct cgroup *com_cgrp = src_cgrp; int ret; lockdep_assert_held(&cgroup_mutex); /* find the common ancestor */ while (!cgroup_is_descendant(dst_cgrp, com_cgrp)) com_cgrp = cgroup_parent(com_cgrp); /* %current should be authorized to migrate to the common ancestor */ ret = cgroup_may_write(com_cgrp, sb); if (ret) return ret; /* * If namespaces are delegation boundaries, %current must be able * to see both source and destination cgroups from its namespace. */ if ((cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) && (!cgroup_is_descendant(src_cgrp, ns->root_cset->dfl_cgrp) || !cgroup_is_descendant(dst_cgrp, ns->root_cset->dfl_cgrp))) return -ENOENT; return 0; } static int cgroup_attach_permissions(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, struct super_block *sb, bool threadgroup, struct cgroup_namespace *ns) { int ret = 0; ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb, ns); if (ret) return ret; ret = cgroup_migrate_vet_dst(dst_cgrp); if (ret) return ret; if (!threadgroup && (src_cgrp->dom_cgrp != dst_cgrp->dom_cgrp)) ret = -EOPNOTSUPP; return ret; } static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, bool threadgroup) { struct cgroup_file_ctx *ctx = of->priv; struct cgroup *src_cgrp, *dst_cgrp; struct task_struct *task; const struct cred *saved_cred; ssize_t ret; bool threadgroup_locked; dst_cgrp = cgroup_kn_lock_live(of->kn, false); if (!dst_cgrp) return -ENODEV; task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked); ret = PTR_ERR_OR_ZERO(task); if (ret) goto out_unlock; /* find the source cgroup */ spin_lock_irq(&css_set_lock); src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); spin_unlock_irq(&css_set_lock); /* * Process and thread migrations follow same delegation rule. Check * permissions using the credentials from file open to protect against * inherited fd attacks. */ saved_cred = override_creds(of->file->f_cred); ret = cgroup_attach_permissions(src_cgrp, dst_cgrp, of->file->f_path.dentry->d_sb, threadgroup, ctx->ns); revert_creds(saved_cred); if (ret) goto out_finish; ret = cgroup_attach_task(dst_cgrp, task, threadgroup); out_finish: cgroup_procs_write_finish(task, threadgroup_locked); out_unlock: cgroup_kn_unlock(of->kn); return ret; } static ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup_procs_write(of, buf, true) ?: nbytes; } static void *cgroup_threads_start(struct seq_file *s, loff_t *pos) { return __cgroup_procs_start(s, pos, 0); } static ssize_t cgroup_threads_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup_procs_write(of, buf, false) ?: nbytes; } /* cgroup core interface files for the default hierarchy */ static struct cftype cgroup_base_files[] = { { .name = "cgroup.type", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_type_show, .write = cgroup_type_write, }, { .name = "cgroup.procs", .flags = CFTYPE_NS_DELEGATABLE, .file_offset = offsetof(struct cgroup, procs_file), .release = cgroup_procs_release, .seq_start = cgroup_procs_start, .seq_next = cgroup_procs_next, .seq_show = cgroup_procs_show, .write = cgroup_procs_write, }, { .name = "cgroup.threads", .flags = CFTYPE_NS_DELEGATABLE, .release = cgroup_procs_release, .seq_start = cgroup_threads_start, .seq_next = cgroup_procs_next, .seq_show = cgroup_procs_show, .write = cgroup_threads_write, }, { .name = "cgroup.controllers", .seq_show = cgroup_controllers_show, }, { .name = "cgroup.subtree_control", .flags = CFTYPE_NS_DELEGATABLE, .seq_show = cgroup_subtree_control_show, .write = cgroup_subtree_control_write, }, { .name = "cgroup.events", .flags = CFTYPE_NOT_ON_ROOT, .file_offset = offsetof(struct cgroup, events_file), .seq_show = cgroup_events_show, }, { .name = "cgroup.max.descendants", .seq_show = cgroup_max_descendants_show, .write = cgroup_max_descendants_write, }, { .name = "cgroup.max.depth", .seq_show = cgroup_max_depth_show, .write = cgroup_max_depth_write, }, { .name = "cgroup.stat", .seq_show = cgroup_stat_show, }, { .name = "cgroup.freeze", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_freeze_show, .write = cgroup_freeze_write, }, { .name = "cgroup.kill", .flags = CFTYPE_NOT_ON_ROOT, .write = cgroup_kill_write, }, { .name = "cpu.stat", .seq_show = cpu_stat_show, }, { .name = "cpu.stat.local", .seq_show = cpu_local_stat_show, }, { } /* terminate */ }; static struct cftype cgroup_psi_files[] = { #ifdef CONFIG_PSI { .name = "io.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IO]), .seq_show = cgroup_io_pressure_show, .write = cgroup_io_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, { .name = "memory.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]), .seq_show = cgroup_memory_pressure_show, .write = cgroup_memory_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, { .name = "cpu.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]), .seq_show = cgroup_cpu_pressure_show, .write = cgroup_cpu_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, #ifdef CONFIG_IRQ_TIME_ACCOUNTING { .name = "irq.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]), .seq_show = cgroup_irq_pressure_show, .write = cgroup_irq_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, #endif { .name = "cgroup.pressure", .seq_show = cgroup_pressure_show, .write = cgroup_pressure_write, }, #endif /* CONFIG_PSI */ { } /* terminate */ }; /* * css destruction is four-stage process. * * 1. Destruction starts. Killing of the percpu_ref is initiated. * Implemented in kill_css(). * * 2. When the percpu_ref is confirmed to be visible as killed on all CPUs * and thus css_tryget_online() is guaranteed to fail, the css can be * offlined by invoking offline_css(). After offlining, the base ref is * put. Implemented in css_killed_work_fn(). * * 3. When the percpu_ref reaches zero, the only possible remaining * accessors are inside RCU read sections. css_release() schedules the * RCU callback. * * 4. After the grace period, the css can be freed. Implemented in * css_free_rwork_fn(). * * It is actually hairier because both step 2 and 4 require process context * and thus involve punting to css->destroy_work adding two additional * steps to the already complex sequence. */ static void css_free_rwork_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(to_rcu_work(work), struct cgroup_subsys_state, destroy_rwork); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; percpu_ref_exit(&css->refcnt); if (ss) { /* css free path */ struct cgroup_subsys_state *parent = css->parent; int id = css->id; ss->css_free(css); cgroup_idr_remove(&ss->css_idr, id); cgroup_put(cgrp); if (parent) css_put(parent); } else { /* cgroup free path */ atomic_dec(&cgrp->root->nr_cgrps); if (!cgroup_on_dfl(cgrp)) cgroup1_pidlist_destroy_all(cgrp); cancel_work_sync(&cgrp->release_agent_work); bpf_cgrp_storage_free(cgrp); if (cgroup_parent(cgrp)) { /* * We get a ref to the parent, and put the ref when * this cgroup is being freed, so it's guaranteed * that the parent won't be destroyed before its * children. */ cgroup_put(cgroup_parent(cgrp)); kernfs_put(cgrp->kn); psi_cgroup_free(cgrp); cgroup_rstat_exit(cgrp); kfree(cgrp); } else { /* * This is root cgroup's refcnt reaching zero, * which indicates that the root should be * released. */ cgroup_destroy_root(cgrp->root); } } } static void css_release_work_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; cgroup_lock(); css->flags |= CSS_RELEASED; list_del_rcu(&css->sibling); if (ss) { struct cgroup *parent_cgrp; /* css release path */ if (!list_empty(&css->rstat_css_node)) { cgroup_rstat_flush(cgrp); list_del_rcu(&css->rstat_css_node); } cgroup_idr_replace(&ss->css_idr, NULL, css->id); if (ss->css_released) ss->css_released(css); cgrp->nr_dying_subsys[ss->id]--; /* * When a css is released and ready to be freed, its * nr_descendants must be zero. However, the corresponding * cgrp->nr_dying_subsys[ss->id] may not be 0 if a subsystem * is activated and deactivated multiple times with one or * more of its previous activation leaving behind dying csses. */ WARN_ON_ONCE(css->nr_descendants); parent_cgrp = cgroup_parent(cgrp); while (parent_cgrp) { parent_cgrp->nr_dying_subsys[ss->id]--; parent_cgrp = cgroup_parent(parent_cgrp); } } else { struct cgroup *tcgrp; /* cgroup release path */ TRACE_CGROUP_PATH(release, cgrp); cgroup_rstat_flush(cgrp); spin_lock_irq(&css_set_lock); for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) tcgrp->nr_dying_descendants--; spin_unlock_irq(&css_set_lock); /* * There are two control paths which try to determine * cgroup from dentry without going through kernfs - * cgroupstats_build() and css_tryget_online_from_dir(). * Those are supported by RCU protecting clearing of * cgrp->kn->priv backpointer. */ if (cgrp->kn) RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL); } cgroup_unlock(); INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); } static void css_release(struct percpu_ref *ref) { struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); INIT_WORK(&css->destroy_work, css_release_work_fn); queue_work(cgroup_destroy_wq, &css->destroy_work); } static void init_and_link_css(struct cgroup_subsys_state *css, struct cgroup_subsys *ss, struct cgroup *cgrp) { lockdep_assert_held(&cgroup_mutex); cgroup_get_live(cgrp); memset(css, 0, sizeof(*css)); css->cgroup = cgrp; css->ss = ss; css->id = -1; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); INIT_LIST_HEAD(&css->rstat_css_node); css->serial_nr = css_serial_nr_next++; atomic_set(&css->online_cnt, 0); if (cgroup_parent(cgrp)) { css->parent = cgroup_css(cgroup_parent(cgrp), ss); css_get(css->parent); } if (ss->css_rstat_flush) list_add_rcu(&css->rstat_css_node, &cgrp->rstat_css_list); BUG_ON(cgroup_css(cgrp, ss)); } /* invoke ->css_online() on a new CSS and mark it online if successful */ static int online_css(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; int ret = 0; lockdep_assert_held(&cgroup_mutex); if (ss->css_online) ret = ss->css_online(css); if (!ret) { css->flags |= CSS_ONLINE; rcu_assign_pointer(css->cgroup->subsys[ss->id], css); atomic_inc(&css->online_cnt); if (css->parent) { atomic_inc(&css->parent->online_cnt); while ((css = css->parent)) css->nr_descendants++; } } return ret; } /* if the CSS is online, invoke ->css_offline() on it and mark it offline */ static void offline_css(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; lockdep_assert_held(&cgroup_mutex); if (!(css->flags & CSS_ONLINE)) return; if (ss->css_offline) ss->css_offline(css); css->flags &= ~CSS_ONLINE; RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL); wake_up_all(&css->cgroup->offline_waitq); css->cgroup->nr_dying_subsys[ss->id]++; /* * Parent css and cgroup cannot be freed until after the freeing * of child css, see css_free_rwork_fn(). */ while ((css = css->parent)) { css->nr_descendants--; css->cgroup->nr_dying_subsys[ss->id]++; } } /** * css_create - create a cgroup_subsys_state * @cgrp: the cgroup new css will be associated with * @ss: the subsys of new css * * Create a new css associated with @cgrp - @ss pair. On success, the new * css is online and installed in @cgrp. This function doesn't create the * interface files. Returns 0 on success, -errno on failure. */ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *parent_css = cgroup_css(parent, ss); struct cgroup_subsys_state *css; int err; lockdep_assert_held(&cgroup_mutex); css = ss->css_alloc(parent_css); if (!css) css = ERR_PTR(-ENOMEM); if (IS_ERR(css)) return css; init_and_link_css(css, ss, cgrp); err = percpu_ref_init(&css->refcnt, css_release, 0, GFP_KERNEL); if (err) goto err_free_css; err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL); if (err < 0) goto err_free_css; css->id = err; /* @css is ready to be brought online now, make it visible */ list_add_tail_rcu(&css->sibling, &parent_css->children); cgroup_idr_replace(&ss->css_idr, css, css->id); err = online_css(css); if (err) goto err_list_del; return css; err_list_del: list_del_rcu(&css->sibling); err_free_css: list_del_rcu(&css->rstat_css_node); INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); return ERR_PTR(err); } /* * The returned cgroup is fully initialized including its control mask, but * it doesn't have the control mask applied. */ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name, umode_t mode) { struct cgroup_root *root = parent->root; struct cgroup *cgrp, *tcgrp; struct kernfs_node *kn; int level = parent->level + 1; int ret; /* allocate the cgroup and its ID, 0 is reserved for the root */ cgrp = kzalloc(struct_size(cgrp, ancestors, (level + 1)), GFP_KERNEL); if (!cgrp) return ERR_PTR(-ENOMEM); ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) goto out_free_cgrp; ret = cgroup_rstat_init(cgrp); if (ret) goto out_cancel_ref; /* create the directory */ kn = kernfs_create_dir_ns(parent->kn, name, mode, current_fsuid(), current_fsgid(), cgrp, NULL); if (IS_ERR(kn)) { ret = PTR_ERR(kn); goto out_stat_exit; } cgrp->kn = kn; init_cgroup_housekeeping(cgrp); cgrp->self.parent = &parent->self; cgrp->root = root; cgrp->level = level; ret = psi_cgroup_alloc(cgrp); if (ret) goto out_kernfs_remove; if (cgrp->root == &cgrp_dfl_root) { ret = cgroup_bpf_inherit(cgrp); if (ret) goto out_psi_free; } /* * New cgroup inherits effective freeze counter, and * if the parent has to be frozen, the child has too. */ cgrp->freezer.e_freeze = parent->freezer.e_freeze; if (cgrp->freezer.e_freeze) { /* * Set the CGRP_FREEZE flag, so when a process will be * attached to the child cgroup, it will become frozen. * At this point the new cgroup is unpopulated, so we can * consider it frozen immediately. */ set_bit(CGRP_FREEZE, &cgrp->flags); set_bit(CGRP_FROZEN, &cgrp->flags); } spin_lock_irq(&css_set_lock); for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { cgrp->ancestors[tcgrp->level] = tcgrp; if (tcgrp != cgrp) { tcgrp->nr_descendants++; /* * If the new cgroup is frozen, all ancestor cgroups * get a new frozen descendant, but their state can't * change because of this. */ if (cgrp->freezer.e_freeze) tcgrp->freezer.nr_frozen_descendants++; } } spin_unlock_irq(&css_set_lock); if (notify_on_release(parent)) set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags)) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags); cgrp->self.serial_nr = css_serial_nr_next++; /* allocation complete, commit to creation */ list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children); atomic_inc(&root->nr_cgrps); cgroup_get_live(parent); /* * On the default hierarchy, a child doesn't automatically inherit * subtree_control from the parent. Each is configured manually. */ if (!cgroup_on_dfl(cgrp)) cgrp->subtree_control = cgroup_control(cgrp); cgroup_propagate_control(cgrp); return cgrp; out_psi_free: psi_cgroup_free(cgrp); out_kernfs_remove: kernfs_remove(cgrp->kn); out_stat_exit: cgroup_rstat_exit(cgrp); out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt); out_free_cgrp: kfree(cgrp); return ERR_PTR(ret); } static bool cgroup_check_hierarchy_limits(struct cgroup *parent) { struct cgroup *cgroup; int ret = false; int level = 0; lockdep_assert_held(&cgroup_mutex); for (cgroup = parent; cgroup; cgroup = cgroup_parent(cgroup)) { if (cgroup->nr_descendants >= cgroup->max_descendants) goto fail; if (level >= cgroup->max_depth) goto fail; level++; } ret = true; fail: return ret; } int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) { struct cgroup *parent, *cgrp; int ret; /* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */ if (strchr(name, '\n')) return -EINVAL; parent = cgroup_kn_lock_live(parent_kn, false); if (!parent) return -ENODEV; if (!cgroup_check_hierarchy_limits(parent)) { ret = -EAGAIN; goto out_unlock; } cgrp = cgroup_create(parent, name, mode); if (IS_ERR(cgrp)) { ret = PTR_ERR(cgrp); goto out_unlock; } /* * This extra ref will be put in css_free_rwork_fn() and guarantees * that @cgrp->kn is always accessible. */ kernfs_get(cgrp->kn); ret = css_populate_dir(&cgrp->self); if (ret) goto out_destroy; ret = cgroup_apply_control_enable(cgrp); if (ret) goto out_destroy; TRACE_CGROUP_PATH(mkdir, cgrp); /* let's create and online css's */ kernfs_activate(cgrp->kn); ret = 0; goto out_unlock; out_destroy: cgroup_destroy_locked(cgrp); out_unlock: cgroup_kn_unlock(parent_kn); return ret; } /* * This is called when the refcnt of a css is confirmed to be killed. * css_tryget_online() is now guaranteed to fail. Tell the subsystem to * initiate destruction and put the css ref from kill_css(). */ static void css_killed_work_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); cgroup_lock(); do { offline_css(css); css_put(css); /* @css can't go away while we're holding cgroup_mutex */ css = css->parent; } while (css && atomic_dec_and_test(&css->online_cnt)); cgroup_unlock(); } /* css kill confirmation processing requires process context, bounce */ static void css_killed_ref_fn(struct percpu_ref *ref) { struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); if (atomic_dec_and_test(&css->online_cnt)) { INIT_WORK(&css->destroy_work, css_killed_work_fn); queue_work(cgroup_destroy_wq, &css->destroy_work); } } /** * kill_css - destroy a css * @css: css to destroy * * This function initiates destruction of @css by removing cgroup interface * files and putting its base reference. ->css_offline() will be invoked * asynchronously once css_tryget_online() is guaranteed to fail and when * the reference count reaches zero, @css will be released. */ static void kill_css(struct cgroup_subsys_state *css) { lockdep_assert_held(&cgroup_mutex); if (css->flags & CSS_DYING) return; /* * Call css_killed(), if defined, before setting the CSS_DYING flag */ if (css->ss->css_killed) css->ss->css_killed(css); css->flags |= CSS_DYING; /* * This must happen before css is disassociated with its cgroup. * See seq_css() for details. */ css_clear_dir(css); /* * Killing would put the base ref, but we need to keep it alive * until after ->css_offline(). */ css_get(css); /* * cgroup core guarantees that, by the time ->css_offline() is * invoked, no new css reference will be given out via * css_tryget_online(). We can't simply call percpu_ref_kill() and * proceed to offlining css's because percpu_ref_kill() doesn't * guarantee that the ref is seen as killed on all CPUs on return. * * Use percpu_ref_kill_and_confirm() to get notifications as each * css is confirmed to be seen as killed on all CPUs. */ percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn); } /** * cgroup_destroy_locked - the first stage of cgroup destruction * @cgrp: cgroup to be destroyed * * css's make use of percpu refcnts whose killing latency shouldn't be * exposed to userland and are RCU protected. Also, cgroup core needs to * guarantee that css_tryget_online() won't succeed by the time * ->css_offline() is invoked. To satisfy all the requirements, * destruction is implemented in the following two steps. * * s1. Verify @cgrp can be destroyed and mark it dying. Remove all * userland visible parts and start killing the percpu refcnts of * css's. Set up so that the next stage will be kicked off once all * the percpu refcnts are confirmed to be killed. * * s2. Invoke ->css_offline(), mark the cgroup dead and proceed with the * rest of destruction. Once all cgroup references are gone, the * cgroup is RCU-freed. * * This function implements s1. After this step, @cgrp is gone as far as * the userland is concerned and a new cgroup with the same name may be * created. As cgroup doesn't care about the names internally, this * doesn't cause any problem. */ static int cgroup_destroy_locked(struct cgroup *cgrp) __releases(&cgroup_mutex) __acquires(&cgroup_mutex) { struct cgroup *tcgrp, *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *css; struct cgrp_cset_link *link; int ssid; lockdep_assert_held(&cgroup_mutex); /* * Only migration can raise populated from zero and we're already * holding cgroup_mutex. */ if (cgroup_is_populated(cgrp)) return -EBUSY; /* * Make sure there's no live children. We can't test emptiness of * ->self.children as dead children linger on it while being * drained; otherwise, "rmdir parent/child parent" may fail. */ if (css_has_online_children(&cgrp->self)) return -EBUSY; /* * Mark @cgrp and the associated csets dead. The former prevents * further task migration and child creation by disabling * cgroup_kn_lock_live(). The latter makes the csets ignored by * the migration path. */ cgrp->self.flags &= ~CSS_ONLINE; spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) link->cset->dead = true; spin_unlock_irq(&css_set_lock); /* initiate massacre of all css's */ for_each_css(css, ssid, cgrp) kill_css(css); /* clear and remove @cgrp dir, @cgrp has an extra ref on its kn */ css_clear_dir(&cgrp->self); kernfs_remove(cgrp->kn); if (cgroup_is_threaded(cgrp)) parent->nr_threaded_children--; spin_lock_irq(&css_set_lock); for (tcgrp = parent; tcgrp; tcgrp = cgroup_parent(tcgrp)) { tcgrp->nr_descendants--; tcgrp->nr_dying_descendants++; /* * If the dying cgroup is frozen, decrease frozen descendants * counters of ancestor cgroups. */ if (test_bit(CGRP_FROZEN, &cgrp->flags)) tcgrp->freezer.nr_frozen_descendants--; } spin_unlock_irq(&css_set_lock); cgroup1_check_for_release(parent); if (cgrp->root == &cgrp_dfl_root) cgroup_bpf_offline(cgrp); /* put the base reference */ percpu_ref_kill(&cgrp->self.refcnt); return 0; }; int cgroup_rmdir(struct kernfs_node *kn) { struct cgroup *cgrp; int ret = 0; cgrp = cgroup_kn_lock_live(kn, false); if (!cgrp) return 0; ret = cgroup_destroy_locked(cgrp); if (!ret) TRACE_CGROUP_PATH(rmdir, cgrp); cgroup_kn_unlock(kn); return ret; } static struct kernfs_syscall_ops cgroup_kf_syscall_ops = { .show_options = cgroup_show_options, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .show_path = cgroup_show_path, }; static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early) { struct cgroup_subsys_state *css; pr_debug("Initializing cgroup subsys %s\n", ss->name); cgroup_lock(); idr_init(&ss->css_idr); INIT_LIST_HEAD(&ss->cfts); /* Create the root cgroup state for this subsystem */ ss->root = &cgrp_dfl_root; css = ss->css_alloc(NULL); /* We don't handle early failures gracefully */ BUG_ON(IS_ERR(css)); init_and_link_css(css, ss, &cgrp_dfl_root.cgrp); /* * Root csses are never destroyed and we can't initialize * percpu_ref during early init. Disable refcnting. */ css->flags |= CSS_NO_REF; if (early) { /* allocation can't be done safely during early init */ css->id = 1; } else { css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL); BUG_ON(css->id < 0); } /* Update the init_css_set to contain a subsys * pointer to this state - since the subsystem is * newly registered, all tasks and hence the * init_css_set is in the subsystem's root cgroup. */ init_css_set.subsys[ss->id] = css; have_fork_callback |= (bool)ss->fork << ss->id; have_exit_callback |= (bool)ss->exit << ss->id; have_release_callback |= (bool)ss->release << ss->id; have_canfork_callback |= (bool)ss->can_fork << ss->id; /* At system boot, before all subsystems have been * registered, no tasks have been forked, so we don't * need to invoke fork callbacks here. */ BUG_ON(!list_empty(&init_task.tasks)); BUG_ON(online_css(css)); cgroup_unlock(); } /** * cgroup_init_early - cgroup initialization at system boot * * Initialize cgroups at system boot, and initialize any * subsystems that request early init. */ int __init cgroup_init_early(void) { static struct cgroup_fs_context __initdata ctx; struct cgroup_subsys *ss; int i; ctx.root = &cgrp_dfl_root; init_cgroup_root(&ctx); cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF; RCU_INIT_POINTER(init_task.cgroups, &init_css_set); for_each_subsys(ss, i) { WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id, "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p id:name=%d:%s\n", i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free, ss->id, ss->name); WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN, "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]); ss->id = i; ss->name = cgroup_subsys_name[i]; if (!ss->legacy_name) ss->legacy_name = cgroup_subsys_name[i]; if (ss->early_init) cgroup_init_subsys(ss, true); } return 0; } /** * cgroup_init - cgroup initialization * * Register cgroup filesystem and /proc file, and initialize * any subsystems that didn't request early init. */ int __init cgroup_init(void) { struct cgroup_subsys *ss; int ssid; BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16); BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_psi_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files)); cgroup_rstat_boot(); get_user_ns(init_cgroup_ns.user_ns); cgroup_lock(); /* * Add init_css_set to the hash table so that dfl_root can link to * it during init. */ hash_add(css_set_table, &init_css_set.hlist, css_set_hash(init_css_set.subsys)); BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0)); cgroup_unlock(); for_each_subsys(ss, ssid) { if (ss->early_init) { struct cgroup_subsys_state *css = init_css_set.subsys[ss->id]; css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL); BUG_ON(css->id < 0); } else { cgroup_init_subsys(ss, false); } list_add_tail(&init_css_set.e_cset_node[ssid], &cgrp_dfl_root.cgrp.e_csets[ssid]); /* * Setting dfl_root subsys_mask needs to consider the * disabled flag and cftype registration needs kmalloc, * both of which aren't available during early_init. */ if (!cgroup_ssid_enabled(ssid)) continue; if (cgroup1_ssid_disabled(ssid)) pr_info("Disabling %s control group subsystem in v1 mounts\n", ss->legacy_name); cgrp_dfl_root.subsys_mask |= 1 << ss->id; /* implicit controllers must be threaded too */ WARN_ON(ss->implicit_on_dfl && !ss->threaded); if (ss->implicit_on_dfl) cgrp_dfl_implicit_ss_mask |= 1 << ss->id; else if (!ss->dfl_cftypes) cgrp_dfl_inhibit_ss_mask |= 1 << ss->id; if (ss->threaded) cgrp_dfl_threaded_ss_mask |= 1 << ss->id; if (ss->dfl_cftypes == ss->legacy_cftypes) { WARN_ON(cgroup_add_cftypes(ss, ss->dfl_cftypes)); } else { WARN_ON(cgroup_add_dfl_cftypes(ss, ss->dfl_cftypes)); WARN_ON(cgroup_add_legacy_cftypes(ss, ss->legacy_cftypes)); } if (ss->bind) ss->bind(init_css_set.subsys[ssid]); cgroup_lock(); css_populate_dir(init_css_set.subsys[ssid]); cgroup_unlock(); } /* init_css_set.subsys[] has been updated, re-hash */ hash_del(&init_css_set.hlist); hash_add(css_set_table, &init_css_set.hlist, css_set_hash(init_css_set.subsys)); WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup")); WARN_ON(register_filesystem(&cgroup_fs_type)); WARN_ON(register_filesystem(&cgroup2_fs_type)); WARN_ON(!proc_create_single("cgroups", 0, NULL, proc_cgroupstats_show)); #ifdef CONFIG_CPUSETS_V1 WARN_ON(register_filesystem(&cpuset_fs_type)); #endif return 0; } static int __init cgroup_wq_init(void) { /* * There isn't much point in executing destruction path in * parallel. Good chunk is serialized with cgroup_mutex anyway. * Use 1 for @max_active. * * We would prefer to do this in cgroup_init() above, but that * is called before init_workqueues(): so leave this until after. */ cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); BUG_ON(!cgroup_destroy_wq); return 0; } core_initcall(cgroup_wq_init); void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) { struct kernfs_node *kn; kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id); if (!kn) return; kernfs_path(kn, buf, buflen); kernfs_put(kn); } /* * cgroup_get_from_id : get the cgroup associated with cgroup id * @id: cgroup id * On success return the cgrp or ERR_PTR on failure * Only cgroups within current task's cgroup NS are valid. */ struct cgroup *cgroup_get_from_id(u64 id) { struct kernfs_node *kn; struct cgroup *cgrp, *root_cgrp; kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id); if (!kn) return ERR_PTR(-ENOENT); if (kernfs_type(kn) != KERNFS_DIR) { kernfs_put(kn); return ERR_PTR(-ENOENT); } rcu_read_lock(); cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (cgrp && !cgroup_tryget(cgrp)) cgrp = NULL; rcu_read_unlock(); kernfs_put(kn); if (!cgrp) return ERR_PTR(-ENOENT); root_cgrp = current_cgns_cgroup_dfl(); if (!cgroup_is_descendant(cgrp, root_cgrp)) { cgroup_put(cgrp); return ERR_PTR(-ENOENT); } return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_id); /* * proc_cgroup_show() * - Print task's cgroup paths into seq_file, one line for each hierarchy * - Used for /proc/<pid>/cgroup. */ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk) { char *buf; int retval; struct cgroup_root *root; retval = -ENOMEM; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) goto out; rcu_read_lock(); spin_lock_irq(&css_set_lock); for_each_root(root) { struct cgroup_subsys *ss; struct cgroup *cgrp; int ssid, count = 0; if (root == &cgrp_dfl_root && !READ_ONCE(cgrp_dfl_visible)) continue; cgrp = task_cgroup_from_root(tsk, root); /* The root has already been unmounted. */ if (!cgrp) continue; seq_printf(m, "%d:", root->hierarchy_id); if (root != &cgrp_dfl_root) for_each_subsys(ss, ssid) if (root->subsys_mask & (1 << ssid)) seq_printf(m, "%s%s", count++ ? "," : "", ss->legacy_name); if (strlen(root->name)) seq_printf(m, "%sname=%s", count ? "," : "", root->name); seq_putc(m, ':'); /* * On traditional hierarchies, all zombie tasks show up as * belonging to the root cgroup. On the default hierarchy, * while a zombie doesn't show up in "cgroup.procs" and * thus can't be migrated, its /proc/PID/cgroup keeps * reporting the cgroup it belonged to before exiting. If * the cgroup is removed before the zombie is reaped, * " (deleted)" is appended to the cgroup path. */ if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) { retval = cgroup_path_ns_locked(cgrp, buf, PATH_MAX, current->nsproxy->cgroup_ns); if (retval == -E2BIG) retval = -ENAMETOOLONG; if (retval < 0) goto out_unlock; seq_puts(m, buf); } else { seq_puts(m, "/"); } if (cgroup_on_dfl(cgrp) && cgroup_is_dead(cgrp)) seq_puts(m, " (deleted)\n"); else seq_putc(m, '\n'); } retval = 0; out_unlock: spin_unlock_irq(&css_set_lock); rcu_read_unlock(); kfree(buf); out: return retval; } /** * cgroup_fork - initialize cgroup related fields during copy_process() * @child: pointer to task_struct of forking parent process. * * A task is associated with the init_css_set until cgroup_post_fork() * attaches it to the target css_set. */ void cgroup_fork(struct task_struct *child) { RCU_INIT_POINTER(child->cgroups, &init_css_set); INIT_LIST_HEAD(&child->cg_list); } /** * cgroup_v1v2_get_from_file - get a cgroup pointer from a file pointer * @f: file corresponding to cgroup_dir * * Find the cgroup from a file pointer associated with a cgroup directory. * Returns a pointer to the cgroup on success. ERR_PTR is returned if the * cgroup cannot be found. */ static struct cgroup *cgroup_v1v2_get_from_file(struct file *f) { struct cgroup_subsys_state *css; css = css_tryget_online_from_dir(f->f_path.dentry, NULL); if (IS_ERR(css)) return ERR_CAST(css); return css->cgroup; } /** * cgroup_get_from_file - same as cgroup_v1v2_get_from_file, but only supports * cgroup2. * @f: file corresponding to cgroup2_dir */ static struct cgroup *cgroup_get_from_file(struct file *f) { struct cgroup *cgrp = cgroup_v1v2_get_from_file(f); if (IS_ERR(cgrp)) return ERR_CAST(cgrp); if (!cgroup_on_dfl(cgrp)) { cgroup_put(cgrp); return ERR_PTR(-EBADF); } return cgrp; } /** * cgroup_css_set_fork - find or create a css_set for a child process * @kargs: the arguments passed to create the child process * * This functions finds or creates a new css_set which the child * process will be attached to in cgroup_post_fork(). By default, * the child process will be given the same css_set as its parent. * * If CLONE_INTO_CGROUP is specified this function will try to find an * existing css_set which includes the requested cgroup and if not create * a new css_set that the child will be attached to later. If this function * succeeds it will hold cgroup_threadgroup_rwsem on return. If * CLONE_INTO_CGROUP is requested this function will grab cgroup mutex * before grabbing cgroup_threadgroup_rwsem and will hold a reference * to the target cgroup. */ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) __acquires(&cgroup_mutex) __acquires(&cgroup_threadgroup_rwsem) { int ret; struct cgroup *dst_cgrp = NULL; struct css_set *cset; struct super_block *sb; if (kargs->flags & CLONE_INTO_CGROUP) cgroup_lock(); cgroup_threadgroup_change_begin(current); spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); if (kargs->cgrp) kargs->kill_seq = kargs->cgrp->kill_seq; else kargs->kill_seq = cset->dfl_cgrp->kill_seq; spin_unlock_irq(&css_set_lock); if (!(kargs->flags & CLONE_INTO_CGROUP)) { kargs->cset = cset; return 0; } CLASS(fd_raw, f)(kargs->cgroup); if (fd_empty(f)) { ret = -EBADF; goto err; } sb = fd_file(f)->f_path.dentry->d_sb; dst_cgrp = cgroup_get_from_file(fd_file(f)); if (IS_ERR(dst_cgrp)) { ret = PTR_ERR(dst_cgrp); dst_cgrp = NULL; goto err; } if (cgroup_is_dead(dst_cgrp)) { ret = -ENODEV; goto err; } /* * Verify that we the target cgroup is writable for us. This is * usually done by the vfs layer but since we're not going through * the vfs layer here we need to do it "manually". */ ret = cgroup_may_write(dst_cgrp, sb); if (ret) goto err; /* * Spawning a task directly into a cgroup works by passing a file * descriptor to the target cgroup directory. This can even be an O_PATH * file descriptor. But it can never be a cgroup.procs file descriptor. * This was done on purpose so spawning into a cgroup could be * conceptualized as an atomic * * fd = openat(dfd_cgroup, "cgroup.procs", ...); * write(fd, <child-pid>, ...); * * sequence, i.e. it's a shorthand for the caller opening and writing * cgroup.procs of the cgroup indicated by @dfd_cgroup. This allows us * to always use the caller's credentials. */ ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb, !(kargs->flags & CLONE_THREAD), current->nsproxy->cgroup_ns); if (ret) goto err; kargs->cset = find_css_set(cset, dst_cgrp); if (!kargs->cset) { ret = -ENOMEM; goto err; } put_css_set(cset); kargs->cgrp = dst_cgrp; return ret; err: cgroup_threadgroup_change_end(current); cgroup_unlock(); if (dst_cgrp) cgroup_put(dst_cgrp); put_css_set(cset); if (kargs->cset) put_css_set(kargs->cset); return ret; } /** * cgroup_css_set_put_fork - drop references we took during fork * @kargs: the arguments passed to create the child process * * Drop references to the prepared css_set and target cgroup if * CLONE_INTO_CGROUP was requested. */ static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { struct cgroup *cgrp = kargs->cgrp; struct css_set *cset = kargs->cset; cgroup_threadgroup_change_end(current); if (cset) { put_css_set(cset); kargs->cset = NULL; } if (kargs->flags & CLONE_INTO_CGROUP) { cgroup_unlock(); if (cgrp) { cgroup_put(cgrp); kargs->cgrp = NULL; } } } /** * cgroup_can_fork - called on a new task before the process is exposed * @child: the child process * @kargs: the arguments passed to create the child process * * This prepares a new css_set for the child process which the child will * be attached to in cgroup_post_fork(). * This calls the subsystem can_fork() callbacks. If the cgroup_can_fork() * callback returns an error, the fork aborts with that error code. This * allows for a cgroup subsystem to conditionally allow or deny new forks. */ int cgroup_can_fork(struct task_struct *child, struct kernel_clone_args *kargs) { struct cgroup_subsys *ss; int i, j, ret; ret = cgroup_css_set_fork(kargs); if (ret) return ret; do_each_subsys_mask(ss, i, have_canfork_callback) { ret = ss->can_fork(child, kargs->cset); if (ret) goto out_revert; } while_each_subsys_mask(); return 0; out_revert: for_each_subsys(ss, j) { if (j >= i) break; if (ss->cancel_fork) ss->cancel_fork(child, kargs->cset); } cgroup_css_set_put_fork(kargs); return ret; } /** * cgroup_cancel_fork - called if a fork failed after cgroup_can_fork() * @child: the child process * @kargs: the arguments passed to create the child process * * This calls the cancel_fork() callbacks if a fork failed *after* * cgroup_can_fork() succeeded and cleans up references we took to * prepare a new css_set for the child process in cgroup_can_fork(). */ void cgroup_cancel_fork(struct task_struct *child, struct kernel_clone_args *kargs) { struct cgroup_subsys *ss; int i; for_each_subsys(ss, i) if (ss->cancel_fork) ss->cancel_fork(child, kargs->cset); cgroup_css_set_put_fork(kargs); } /** * cgroup_post_fork - finalize cgroup setup for the child process * @child: the child process * @kargs: the arguments passed to create the child process * * Attach the child process to its css_set calling the subsystem fork() * callbacks. */ void cgroup_post_fork(struct task_struct *child, struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { unsigned int cgrp_kill_seq = 0; unsigned long cgrp_flags = 0; bool kill = false; struct cgroup_subsys *ss; struct css_set *cset; int i; cset = kargs->cset; kargs->cset = NULL; spin_lock_irq(&css_set_lock); /* init tasks are special, only link regular threads */ if (likely(child->pid)) { if (kargs->cgrp) { cgrp_flags = kargs->cgrp->flags; cgrp_kill_seq = kargs->cgrp->kill_seq; } else { cgrp_flags = cset->dfl_cgrp->flags; cgrp_kill_seq = cset->dfl_cgrp->kill_seq; } WARN_ON_ONCE(!list_empty(&child->cg_list)); cset->nr_tasks++; css_set_move_task(child, NULL, cset, false); } else { put_css_set(cset); cset = NULL; } if (!(child->flags & PF_KTHREAD)) { if (unlikely(test_bit(CGRP_FREEZE, &cgrp_flags))) { /* * If the cgroup has to be frozen, the new task has * too. Let's set the JOBCTL_TRAP_FREEZE jobctl bit to * get the task into the frozen state. */ spin_lock(&child->sighand->siglock); WARN_ON_ONCE(child->frozen); child->jobctl |= JOBCTL_TRAP_FREEZE; spin_unlock(&child->sighand->siglock); /* * Calling cgroup_update_frozen() isn't required here, * because it will be called anyway a bit later from * do_freezer_trap(). So we avoid cgroup's transient * switch from the frozen state and back. */ } /* * If the cgroup is to be killed notice it now and take the * child down right after we finished preparing it for * userspace. */ kill = kargs->kill_seq != cgrp_kill_seq; } spin_unlock_irq(&css_set_lock); /* * Call ss->fork(). This must happen after @child is linked on * css_set; otherwise, @child might change state between ->fork() * and addition to css_set. */ do_each_subsys_mask(ss, i, have_fork_callback) { ss->fork(child); } while_each_subsys_mask(); /* Make the new cset the root_cset of the new cgroup namespace. */ if (kargs->flags & CLONE_NEWCGROUP) { struct css_set *rcset = child->nsproxy->cgroup_ns->root_cset; get_css_set(cset); child->nsproxy->cgroup_ns->root_cset = cset; put_css_set(rcset); } /* Cgroup has to be killed so take down child immediately. */ if (unlikely(kill)) do_send_sig_info(SIGKILL, SEND_SIG_NOINFO, child, PIDTYPE_TGID); cgroup_css_set_put_fork(kargs); } /** * cgroup_exit - detach cgroup from exiting task * @tsk: pointer to task_struct of exiting process * * Description: Detach cgroup from @tsk. * */ void cgroup_exit(struct task_struct *tsk) { struct cgroup_subsys *ss; struct css_set *cset; int i; spin_lock_irq(&css_set_lock); WARN_ON_ONCE(list_empty(&tsk->cg_list)); cset = task_css_set(tsk); css_set_move_task(tsk, cset, NULL, false); cset->nr_tasks--; /* matches the signal->live check in css_task_iter_advance() */ if (thread_group_leader(tsk) && atomic_read(&tsk->signal->live)) list_add_tail(&tsk->cg_list, &cset->dying_tasks); if (dl_task(tsk)) dec_dl_tasks_cs(tsk); WARN_ON_ONCE(cgroup_task_frozen(tsk)); if (unlikely(!(tsk->flags & PF_KTHREAD) && test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags))) cgroup_update_frozen(task_dfl_cgroup(tsk)); spin_unlock_irq(&css_set_lock); /* see cgroup_post_fork() for details */ do_each_subsys_mask(ss, i, have_exit_callback) { ss->exit(tsk); } while_each_subsys_mask(); } void cgroup_release(struct task_struct *task) { struct cgroup_subsys *ss; int ssid; do_each_subsys_mask(ss, ssid, have_release_callback) { ss->release(task); } while_each_subsys_mask(); if (!list_empty(&task->cg_list)) { spin_lock_irq(&css_set_lock); css_set_skip_task_iters(task_css_set(task), task); list_del_init(&task->cg_list); spin_unlock_irq(&css_set_lock); } } void cgroup_free(struct task_struct *task) { struct css_set *cset = task_css_set(task); put_css_set(cset); } static int __init cgroup_disable(char *str) { struct cgroup_subsys *ss; char *token; int i; while ((token = strsep(&str, ",")) != NULL) { if (!*token) continue; for_each_subsys(ss, i) { if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue; static_branch_disable(cgroup_subsys_enabled_key[i]); pr_info("Disabling %s control group subsystem\n", ss->name); } for (i = 0; i < OPT_FEATURE_COUNT; i++) { if (strcmp(token, cgroup_opt_feature_names[i])) continue; cgroup_feature_disable_mask |= 1 << i; pr_info("Disabling %s control group feature\n", cgroup_opt_feature_names[i]); break; } } return 1; } __setup("cgroup_disable=", cgroup_disable); void __init __weak enable_debug_cgroup(void) { } static int __init enable_cgroup_debug(char *str) { cgroup_debug = true; enable_debug_cgroup(); return 1; } __setup("cgroup_debug", enable_cgroup_debug); static int __init cgroup_favordynmods_setup(char *str) { return (kstrtobool(str, &have_favordynmods) == 0); } __setup("cgroup_favordynmods=", cgroup_favordynmods_setup); /** * css_tryget_online_from_dir - get corresponding css from a cgroup dentry * @dentry: directory dentry of interest * @ss: subsystem of interest * * If @dentry is a directory for a cgroup which has @ss enabled on it, try * to get the corresponding css and return it. If such css doesn't exist * or can't be pinned, an ERR_PTR value is returned. */ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss) { struct kernfs_node *kn = kernfs_node_from_dentry(dentry); struct file_system_type *s_type = dentry->d_sb->s_type; struct cgroup_subsys_state *css = NULL; struct cgroup *cgrp; /* is @dentry a cgroup dir? */ if ((s_type != &cgroup_fs_type && s_type != &cgroup2_fs_type) || !kn || kernfs_type(kn) != KERNFS_DIR) return ERR_PTR(-EBADF); rcu_read_lock(); /* * This path doesn't originate from kernfs and @kn could already * have been or be removed at any point. @kn->priv is RCU * protected for this access. See css_release_work_fn() for details. */ cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (cgrp) css = cgroup_css(cgrp, ss); if (!css || !css_tryget_online(css)) css = ERR_PTR(-ENOENT); rcu_read_unlock(); return css; } /** * css_from_id - lookup css by id * @id: the cgroup id * @ss: cgroup subsys to be looked into * * Returns the css if there's valid one with @id, otherwise returns NULL. * Should be called under rcu_read_lock(). */ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss) { WARN_ON_ONCE(!rcu_read_lock_held()); return idr_find(&ss->css_idr, id); } /** * cgroup_get_from_path - lookup and get a cgroup from its default hierarchy path * @path: path on the default hierarchy * * Find the cgroup at @path on the default hierarchy, increment its * reference count and return it. Returns pointer to the found cgroup on * success, ERR_PTR(-ENOENT) if @path doesn't exist or if the cgroup has already * been released and ERR_PTR(-ENOTDIR) if @path points to a non-directory. */ struct cgroup *cgroup_get_from_path(const char *path) { struct kernfs_node *kn; struct cgroup *cgrp = ERR_PTR(-ENOENT); struct cgroup *root_cgrp; root_cgrp = current_cgns_cgroup_dfl(); kn = kernfs_walk_and_get(root_cgrp->kn, path); if (!kn) goto out; if (kernfs_type(kn) != KERNFS_DIR) { cgrp = ERR_PTR(-ENOTDIR); goto out_kernfs; } rcu_read_lock(); cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (!cgrp || !cgroup_tryget(cgrp)) cgrp = ERR_PTR(-ENOENT); rcu_read_unlock(); out_kernfs: kernfs_put(kn); out: return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_path); /** * cgroup_v1v2_get_from_fd - get a cgroup pointer from a fd * @fd: fd obtained by open(cgroup_dir) * * Find the cgroup from a fd which should be obtained * by opening a cgroup directory. Returns a pointer to the * cgroup on success. ERR_PTR is returned if the cgroup * cannot be found. */ struct cgroup *cgroup_v1v2_get_from_fd(int fd) { CLASS(fd_raw, f)(fd); if (fd_empty(f)) return ERR_PTR(-EBADF); return cgroup_v1v2_get_from_file(fd_file(f)); } /** * cgroup_get_from_fd - same as cgroup_v1v2_get_from_fd, but only supports * cgroup2. * @fd: fd obtained by open(cgroup2_dir) */ struct cgroup *cgroup_get_from_fd(int fd) { struct cgroup *cgrp = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgrp)) return ERR_CAST(cgrp); if (!cgroup_on_dfl(cgrp)) { cgroup_put(cgrp); return ERR_PTR(-EBADF); } return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_fd); static u64 power_of_ten(int power) { u64 v = 1; while (power--) v *= 10; return v; } /** * cgroup_parse_float - parse a floating number * @input: input string * @dec_shift: number of decimal digits to shift * @v: output * * Parse a decimal floating point number in @input and store the result in * @v with decimal point right shifted @dec_shift times. For example, if * @input is "12.3456" and @dec_shift is 3, *@v will be set to 12345. * Returns 0 on success, -errno otherwise. * * There's nothing cgroup specific about this function except that it's * currently the only user. */ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v) { s64 whole, frac = 0; int fstart = 0, fend = 0, flen; if (!sscanf(input, "%lld.%n%lld%n", &whole, &fstart, &frac, &fend)) return -EINVAL; if (frac < 0) return -EINVAL; flen = fend > fstart ? fend - fstart : 0; if (flen < dec_shift) frac *= power_of_ten(dec_shift - flen); else frac = DIV_ROUND_CLOSEST_ULL(frac, power_of_ten(flen - dec_shift)); *v = whole * power_of_ten(dec_shift) + frac; return 0; } /* * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data * definition in cgroup-defs.h. */ #ifdef CONFIG_SOCK_CGROUP_DATA void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { struct cgroup *cgroup; rcu_read_lock(); /* Don't associate the sock with unrelated interrupted task's cgroup. */ if (in_interrupt()) { cgroup = &cgrp_dfl_root.cgrp; cgroup_get(cgroup); goto out; } while (true) { struct css_set *cset; cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { cgroup = cset->dfl_cgrp; break; } cpu_relax(); } out: skcd->cgroup = cgroup; cgroup_bpf_get(cgroup); rcu_read_unlock(); } void cgroup_sk_clone(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); /* * We might be cloning a socket which is left in an empty * cgroup and the cgroup might have already been rmdir'd. * Don't use cgroup_get_live(). */ cgroup_get(cgrp); cgroup_bpf_get(cgrp); } void cgroup_sk_free(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); cgroup_bpf_put(cgrp); cgroup_put(cgrp); } #endif /* CONFIG_SOCK_CGROUP_DATA */ #ifdef CONFIG_SYSFS static ssize_t show_delegatable_files(struct cftype *files, char *buf, ssize_t size, const char *prefix) { struct cftype *cft; ssize_t ret = 0; for (cft = files; cft && cft->name[0] != '\0'; cft++) { if (!(cft->flags & CFTYPE_NS_DELEGATABLE)) continue; if (prefix) ret += snprintf(buf + ret, size - ret, "%s.", prefix); ret += snprintf(buf + ret, size - ret, "%s\n", cft->name); if (WARN_ON(ret >= size)) break; } return ret; } static ssize_t delegate_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct cgroup_subsys *ss; int ssid; ssize_t ret = 0; ret = show_delegatable_files(cgroup_base_files, buf + ret, PAGE_SIZE - ret, NULL); if (cgroup_psi_enabled()) ret += show_delegatable_files(cgroup_psi_files, buf + ret, PAGE_SIZE - ret, NULL); for_each_subsys(ss, ssid) ret += show_delegatable_files(ss->dfl_cftypes, buf + ret, PAGE_SIZE - ret, cgroup_subsys_name[ssid]); return ret; } static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate); static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE, "nsdelegate\n" "favordynmods\n" "memory_localevents\n" "memory_recursiveprot\n" "memory_hugetlb_accounting\n" "pids_localevents\n"); } static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features); static struct attribute *cgroup_sysfs_attrs[] = { &cgroup_delegate_attr.attr, &cgroup_features_attr.attr, NULL, }; static const struct attribute_group cgroup_sysfs_attr_group = { .attrs = cgroup_sysfs_attrs, .name = "cgroup", }; static int __init cgroup_sysfs_init(void) { return sysfs_create_group(kernel_kobj, &cgroup_sysfs_attr_group); } subsys_initcall(cgroup_sysfs_init); #endif /* CONFIG_SYSFS */ |
| 4 3 3 2 2 11 4 1 34 34 6 8 8 6 1 5 5 4 1 10 10 5 2 2 1 1 10 17 3 21 24 3 21 20 15 21 21 21 21 21 26 21 28 26 11 24 24 25 28 16 12 10 26 18 17 18 22 22 22 22 5 22 22 30 30 1 25 1 24 24 13 19 19 19 3 16 19 8 1 7 7 6 3 3 3 3 32 33 8 25 33 22 2 19 8 23 22 1 1 1 1 1 1 47 71 65 1 4 2 1 56 10 1 59 6 1 62 2 1 36 27 20 20 1 2 2 42 42 6 36 33 35 5 1 29 31 3 33 63 56 2 5 2 2 40 18 1 2 14 45 9 4 2 44 2 45 6 46 6 45 5 1 1 48 1 1 43 6 6 2 39 1 2 6 41 2 4 43 4 8 35 2 7 22 11 10 7 17 29 47 47 5 20 33 5 3 5 5 3 3 5 2 16 11 5 5 5 7 7 87 121 3 29 95 85 7 1 1 4 122 1 4 122 121 1954 1957 1 165 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * GENEVE: Generic Network Virtualization Encapsulation * * Copyright (c) 2015 Red Hat, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/ethtool.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/etherdevice.h> #include <linux/hash.h> #include <net/ipv6_stubs.h> #include <net/dst_metadata.h> #include <net/gro_cells.h> #include <net/rtnetlink.h> #include <net/geneve.h> #include <net/gro.h> #include <net/netdev_lock.h> #include <net/protocol.h> #define GENEVE_NETDEV_VER "0.6" #define GENEVE_N_VID (1u << 24) #define GENEVE_VID_MASK (GENEVE_N_VID - 1) #define VNI_HASH_BITS 10 #define VNI_HASH_SIZE (1<<VNI_HASH_BITS) 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"); #define GENEVE_VER 0 #define GENEVE_BASE_HLEN (sizeof(struct udphdr) + sizeof(struct genevehdr)) #define GENEVE_IPV4_HLEN (ETH_HLEN + sizeof(struct iphdr) + GENEVE_BASE_HLEN) #define GENEVE_IPV6_HLEN (ETH_HLEN + sizeof(struct ipv6hdr) + GENEVE_BASE_HLEN) /* per-network namespace private data for this module */ struct geneve_net { struct list_head geneve_list; struct list_head sock_list; }; static unsigned int geneve_net_id; struct geneve_dev_node { struct hlist_node hlist; struct geneve_dev *geneve; }; struct geneve_config { struct ip_tunnel_info info; bool collect_md; bool use_udp6_rx_checksums; bool ttl_inherit; enum ifla_geneve_df df; bool inner_proto_inherit; u16 port_min; u16 port_max; }; /* Pseudo network device */ struct geneve_dev { struct geneve_dev_node hlist4; /* vni hash table for IPv4 socket */ #if IS_ENABLED(CONFIG_IPV6) struct geneve_dev_node hlist6; /* vni hash table for IPv6 socket */ #endif struct net *net; /* netns for packet i/o */ struct net_device *dev; /* netdev for geneve tunnel */ struct geneve_sock __rcu *sock4; /* IPv4 socket used for geneve tunnel */ #if IS_ENABLED(CONFIG_IPV6) struct geneve_sock __rcu *sock6; /* IPv6 socket used for geneve tunnel */ #endif struct list_head next; /* geneve's per namespace list */ struct gro_cells gro_cells; struct geneve_config cfg; }; struct geneve_sock { bool collect_md; struct list_head list; struct socket *sock; struct rcu_head rcu; int refcnt; struct hlist_head vni_list[VNI_HASH_SIZE]; }; static inline __u32 geneve_net_vni_hash(u8 vni[3]) { __u32 vnid; vnid = (vni[0] << 16) | (vni[1] << 8) | vni[2]; return hash_32(vnid, VNI_HASH_BITS); } static __be64 vni_to_tunnel_id(const __u8 *vni) { #ifdef __BIG_ENDIAN return (vni[0] << 16) | (vni[1] << 8) | vni[2]; #else return (__force __be64)(((__force u64)vni[0] << 40) | ((__force u64)vni[1] << 48) | ((__force u64)vni[2] << 56)); #endif } /* Convert 64 bit tunnel ID to 24 bit VNI. */ static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni) { #ifdef __BIG_ENDIAN vni[0] = (__force __u8)(tun_id >> 16); vni[1] = (__force __u8)(tun_id >> 8); vni[2] = (__force __u8)tun_id; #else vni[0] = (__force __u8)((__force u64)tun_id >> 40); vni[1] = (__force __u8)((__force u64)tun_id >> 48); vni[2] = (__force __u8)((__force u64)tun_id >> 56); #endif } static bool eq_tun_id_and_vni(u8 *tun_id, u8 *vni) { return !memcmp(vni, &tun_id[5], 3); } static sa_family_t geneve_get_sk_family(struct geneve_sock *gs) { return gs->sock->sk->sk_family; } static struct geneve_dev *geneve_lookup(struct geneve_sock *gs, __be32 addr, u8 vni[]) { struct hlist_head *vni_list_head; struct geneve_dev_node *node; __u32 hash; /* Find the device for this VNI */ hash = geneve_net_vni_hash(vni); vni_list_head = &gs->vni_list[hash]; hlist_for_each_entry_rcu(node, vni_list_head, hlist) { if (eq_tun_id_and_vni((u8 *)&node->geneve->cfg.info.key.tun_id, vni) && addr == node->geneve->cfg.info.key.u.ipv4.dst) return node->geneve; } return NULL; } #if IS_ENABLED(CONFIG_IPV6) static struct geneve_dev *geneve6_lookup(struct geneve_sock *gs, struct in6_addr addr6, u8 vni[]) { struct hlist_head *vni_list_head; struct geneve_dev_node *node; __u32 hash; /* Find the device for this VNI */ hash = geneve_net_vni_hash(vni); vni_list_head = &gs->vni_list[hash]; hlist_for_each_entry_rcu(node, vni_list_head, hlist) { if (eq_tun_id_and_vni((u8 *)&node->geneve->cfg.info.key.tun_id, vni) && ipv6_addr_equal(&addr6, &node->geneve->cfg.info.key.u.ipv6.dst)) return node->geneve; } return NULL; } #endif static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb) { return (struct genevehdr *)(udp_hdr(skb) + 1); } static struct geneve_dev *geneve_lookup_skb(struct geneve_sock *gs, struct sk_buff *skb) { static u8 zero_vni[3]; u8 *vni; if (geneve_get_sk_family(gs) == AF_INET) { struct iphdr *iph; __be32 addr; iph = ip_hdr(skb); /* outer IP header... */ if (gs->collect_md) { vni = zero_vni; addr = 0; } else { vni = geneve_hdr(skb)->vni; addr = iph->saddr; } return geneve_lookup(gs, addr, vni); #if IS_ENABLED(CONFIG_IPV6) } else if (geneve_get_sk_family(gs) == AF_INET6) { static struct in6_addr zero_addr6; struct ipv6hdr *ip6h; struct in6_addr addr6; ip6h = ipv6_hdr(skb); /* outer IPv6 header... */ if (gs->collect_md) { vni = zero_vni; addr6 = zero_addr6; } else { vni = geneve_hdr(skb)->vni; addr6 = ip6h->saddr; } return geneve6_lookup(gs, addr6, vni); #endif } return NULL; } /* geneve receive/decap routine */ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, struct sk_buff *skb) { struct genevehdr *gnvh = geneve_hdr(skb); struct metadata_dst *tun_dst = NULL; unsigned int len; int nh, err = 0; void *oiph; if (ip_tunnel_collect_metadata() || gs->collect_md) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __set_bit(IP_TUNNEL_KEY_BIT, flags); __assign_bit(IP_TUNNEL_OAM_BIT, flags, gnvh->oam); __assign_bit(IP_TUNNEL_CRIT_OPT_BIT, flags, gnvh->critical); tun_dst = udp_tun_rx_dst(skb, geneve_get_sk_family(gs), flags, vni_to_tunnel_id(gnvh->vni), gnvh->opt_len * 4); if (!tun_dst) { dev_dstats_rx_dropped(geneve->dev); goto drop; } /* Update tunnel dst according to Geneve options. */ ip_tunnel_flags_zero(flags); __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, flags); ip_tunnel_info_opts_set(&tun_dst->u.tun_info, gnvh->options, gnvh->opt_len * 4, flags); } else { /* Drop packets w/ critical options, * since we don't support any... */ if (gnvh->critical) { DEV_STATS_INC(geneve->dev, rx_frame_errors); DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } } if (tun_dst) skb_dst_set(skb, &tun_dst->dst); if (gnvh->proto_type == htons(ETH_P_TEB)) { skb_reset_mac_header(skb); skb->protocol = eth_type_trans(skb, geneve->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); /* Ignore packet loops (and multicast echo) */ if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr)) { DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } } else { skb_reset_mac_header(skb); skb->dev = geneve->dev; skb->pkt_type = PACKET_HOST; } /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_reset_network_header(skb); if (!pskb_inet_may_pull(skb)) { DEV_STATS_INC(geneve->dev, rx_length_errors); DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } /* Get the outer header. */ oiph = skb->head + nh; if (geneve_get_sk_family(gs) == AF_INET) err = IP_ECN_decapsulate(oiph, skb); #if IS_ENABLED(CONFIG_IPV6) else err = IP6_ECN_decapsulate(oiph, skb); #endif if (unlikely(err)) { if (log_ecn_error) { if (geneve_get_sk_family(gs) == AF_INET) net_info_ratelimited("non-ECT from %pI4 " "with TOS=%#x\n", &((struct iphdr *)oiph)->saddr, ((struct iphdr *)oiph)->tos); #if IS_ENABLED(CONFIG_IPV6) else net_info_ratelimited("non-ECT from %pI6\n", &((struct ipv6hdr *)oiph)->saddr); #endif } if (err > 1) { DEV_STATS_INC(geneve->dev, rx_frame_errors); DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } } len = skb->len; err = gro_cells_receive(&geneve->gro_cells, skb); if (likely(err == NET_RX_SUCCESS)) dev_dstats_rx_add(geneve->dev, len); return; drop: /* Consume bad packet */ kfree_skb(skb); } /* Setup stats when device is created */ static int geneve_init(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); int err; err = gro_cells_init(&geneve->gro_cells, dev); if (err) return err; err = dst_cache_init(&geneve->cfg.info.dst_cache, GFP_KERNEL); if (err) { gro_cells_destroy(&geneve->gro_cells); return err; } netdev_lockdep_set_classes(dev); return 0; } static void geneve_uninit(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); dst_cache_destroy(&geneve->cfg.info.dst_cache); gro_cells_destroy(&geneve->gro_cells); } /* Callback from net/ipv4/udp.c to receive packets */ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct genevehdr *geneveh; struct geneve_dev *geneve; struct geneve_sock *gs; __be16 inner_proto; int opts_len; /* Need UDP and Geneve header to be present */ if (unlikely(!pskb_may_pull(skb, GENEVE_BASE_HLEN))) goto drop; /* Return packets with reserved bits set */ geneveh = geneve_hdr(skb); if (unlikely(geneveh->ver != GENEVE_VER)) goto drop; gs = rcu_dereference_sk_user_data(sk); if (!gs) goto drop; geneve = geneve_lookup_skb(gs, skb); if (!geneve) goto drop; inner_proto = geneveh->proto_type; if (unlikely((!geneve->cfg.inner_proto_inherit && inner_proto != htons(ETH_P_TEB)))) { dev_dstats_rx_dropped(geneve->dev); goto drop; } opts_len = geneveh->opt_len * 4; if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len, inner_proto, !net_eq(geneve->net, dev_net(geneve->dev)))) { dev_dstats_rx_dropped(geneve->dev); goto drop; } geneve_rx(geneve, gs, skb); return 0; drop: /* Consume bad packet */ kfree_skb(skb); return 0; } /* Callback from net/ipv{4,6}/udp.c to check that we have a tunnel for errors */ static int geneve_udp_encap_err_lookup(struct sock *sk, struct sk_buff *skb) { struct genevehdr *geneveh; struct geneve_sock *gs; u8 zero_vni[3] = { 0 }; u8 *vni = zero_vni; if (!pskb_may_pull(skb, skb_transport_offset(skb) + GENEVE_BASE_HLEN)) return -EINVAL; geneveh = geneve_hdr(skb); if (geneveh->ver != GENEVE_VER) return -EINVAL; if (geneveh->proto_type != htons(ETH_P_TEB)) return -EINVAL; gs = rcu_dereference_sk_user_data(sk); if (!gs) return -ENOENT; if (geneve_get_sk_family(gs) == AF_INET) { struct iphdr *iph = ip_hdr(skb); __be32 addr4 = 0; if (!gs->collect_md) { vni = geneve_hdr(skb)->vni; addr4 = iph->daddr; } return geneve_lookup(gs, addr4, vni) ? 0 : -ENOENT; } #if IS_ENABLED(CONFIG_IPV6) if (geneve_get_sk_family(gs) == AF_INET6) { struct ipv6hdr *ip6h = ipv6_hdr(skb); struct in6_addr addr6; memset(&addr6, 0, sizeof(struct in6_addr)); if (!gs->collect_md) { vni = geneve_hdr(skb)->vni; addr6 = ip6h->daddr; } return geneve6_lookup(gs, addr6, vni) ? 0 : -ENOENT; } #endif return -EPFNOSUPPORT; } static struct socket *geneve_create_sock(struct net *net, bool ipv6, __be16 port, bool ipv6_rx_csum) { struct socket *sock; struct udp_port_cfg udp_conf; int err; memset(&udp_conf, 0, sizeof(udp_conf)); if (ipv6) { udp_conf.family = AF_INET6; udp_conf.ipv6_v6only = 1; udp_conf.use_udp6_rx_checksums = ipv6_rx_csum; } else { udp_conf.family = AF_INET; udp_conf.local_ip.s_addr = htonl(INADDR_ANY); } udp_conf.local_udp_port = port; /* Open UDP socket */ err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) return ERR_PTR(err); udp_allow_gso(sock->sk); return sock; } static int geneve_hlen(struct genevehdr *gh) { return sizeof(*gh) + gh->opt_len * 4; } static struct sk_buff *geneve_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { struct sk_buff *pp = NULL; struct sk_buff *p; struct genevehdr *gh, *gh2; unsigned int hlen, gh_len, off_gnv; const struct packet_offload *ptype; __be16 type; int flush = 1; off_gnv = skb_gro_offset(skb); hlen = off_gnv + sizeof(*gh); gh = skb_gro_header(skb, hlen, off_gnv); if (unlikely(!gh)) goto out; if (gh->ver != GENEVE_VER || gh->oam) goto out; gh_len = geneve_hlen(gh); hlen = off_gnv + gh_len; if (!skb_gro_may_pull(skb, hlen)) { gh = skb_gro_header_slow(skb, hlen, off_gnv); if (unlikely(!gh)) goto out; } list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; gh2 = (struct genevehdr *)(p->data + off_gnv); if (gh->opt_len != gh2->opt_len || memcmp(gh, gh2, gh_len)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } skb_gro_pull(skb, gh_len); skb_gro_postpull_rcsum(skb, gh, gh_len); type = gh->proto_type; if (likely(type == htons(ETH_P_TEB))) return call_gro_receive(eth_gro_receive, head, skb); ptype = gro_find_receive_by_type(type); if (!ptype) goto out; pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); flush = 0; out: skb_gro_flush_final(skb, pp, flush); return pp; } static int geneve_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { struct genevehdr *gh; struct packet_offload *ptype; __be16 type; int gh_len; int err = -ENOSYS; gh = (struct genevehdr *)(skb->data + nhoff); gh_len = geneve_hlen(gh); type = gh->proto_type; /* since skb->encapsulation is set, eth_gro_complete() sets the inner mac header */ if (likely(type == htons(ETH_P_TEB))) return eth_gro_complete(skb, nhoff + gh_len); ptype = gro_find_complete_by_type(type); if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + gh_len); skb_set_inner_mac_header(skb, nhoff + gh_len); return err; } /* Create new listen socket if needed */ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, bool ipv6, bool ipv6_rx_csum) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_sock *gs; struct socket *sock; struct udp_tunnel_sock_cfg tunnel_cfg; int h; gs = kzalloc(sizeof(*gs), GFP_KERNEL); if (!gs) return ERR_PTR(-ENOMEM); sock = geneve_create_sock(net, ipv6, port, ipv6_rx_csum); if (IS_ERR(sock)) { kfree(gs); return ERR_CAST(sock); } gs->sock = sock; gs->refcnt = 1; for (h = 0; h < VNI_HASH_SIZE; ++h) INIT_HLIST_HEAD(&gs->vni_list[h]); /* Initialize the geneve udp offloads structure */ udp_tunnel_notify_add_rx_port(gs->sock, UDP_TUNNEL_TYPE_GENEVE); /* Mark socket as an encapsulation socket */ memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); tunnel_cfg.sk_user_data = gs; tunnel_cfg.encap_type = 1; tunnel_cfg.gro_receive = geneve_gro_receive; tunnel_cfg.gro_complete = geneve_gro_complete; tunnel_cfg.encap_rcv = geneve_udp_encap_recv; tunnel_cfg.encap_err_lookup = geneve_udp_encap_err_lookup; tunnel_cfg.encap_destroy = NULL; setup_udp_tunnel_sock(net, sock, &tunnel_cfg); list_add(&gs->list, &gn->sock_list); return gs; } static void __geneve_sock_release(struct geneve_sock *gs) { if (!gs || --gs->refcnt) return; list_del(&gs->list); udp_tunnel_notify_del_rx_port(gs->sock, UDP_TUNNEL_TYPE_GENEVE); udp_tunnel_sock_release(gs->sock); kfree_rcu(gs, rcu); } static void geneve_sock_release(struct geneve_dev *geneve) { struct geneve_sock *gs4 = rtnl_dereference(geneve->sock4); #if IS_ENABLED(CONFIG_IPV6) struct geneve_sock *gs6 = rtnl_dereference(geneve->sock6); rcu_assign_pointer(geneve->sock6, NULL); #endif rcu_assign_pointer(geneve->sock4, NULL); synchronize_net(); __geneve_sock_release(gs4); #if IS_ENABLED(CONFIG_IPV6) __geneve_sock_release(gs6); #endif } static struct geneve_sock *geneve_find_sock(struct geneve_net *gn, sa_family_t family, __be16 dst_port) { struct geneve_sock *gs; list_for_each_entry(gs, &gn->sock_list, list) { if (inet_sk(gs->sock->sk)->inet_sport == dst_port && geneve_get_sk_family(gs) == family) { return gs; } } return NULL; } static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6) { struct net *net = geneve->net; struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev_node *node; struct geneve_sock *gs; __u8 vni[3]; __u32 hash; gs = geneve_find_sock(gn, ipv6 ? AF_INET6 : AF_INET, geneve->cfg.info.key.tp_dst); if (gs) { gs->refcnt++; goto out; } gs = geneve_socket_create(net, geneve->cfg.info.key.tp_dst, ipv6, geneve->cfg.use_udp6_rx_checksums); if (IS_ERR(gs)) return PTR_ERR(gs); out: gs->collect_md = geneve->cfg.collect_md; #if IS_ENABLED(CONFIG_IPV6) if (ipv6) { rcu_assign_pointer(geneve->sock6, gs); node = &geneve->hlist6; } else #endif { rcu_assign_pointer(geneve->sock4, gs); node = &geneve->hlist4; } node->geneve = geneve; tunnel_id_to_vni(geneve->cfg.info.key.tun_id, vni); hash = geneve_net_vni_hash(vni); hlist_add_head_rcu(&node->hlist, &gs->vni_list[hash]); return 0; } static int geneve_open(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); bool metadata = geneve->cfg.collect_md; bool ipv4, ipv6; int ret = 0; ipv6 = geneve->cfg.info.mode & IP_TUNNEL_INFO_IPV6 || metadata; ipv4 = !ipv6 || metadata; #if IS_ENABLED(CONFIG_IPV6) if (ipv6) { ret = geneve_sock_add(geneve, true); if (ret < 0 && ret != -EAFNOSUPPORT) ipv4 = false; } #endif if (ipv4) ret = geneve_sock_add(geneve, false); if (ret < 0) geneve_sock_release(geneve); return ret; } static int geneve_stop(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); hlist_del_init_rcu(&geneve->hlist4.hlist); #if IS_ENABLED(CONFIG_IPV6) hlist_del_init_rcu(&geneve->hlist6.hlist); #endif geneve_sock_release(geneve); return 0; } static void geneve_build_header(struct genevehdr *geneveh, const struct ip_tunnel_info *info, __be16 inner_proto) { geneveh->ver = GENEVE_VER; geneveh->opt_len = info->options_len / 4; geneveh->oam = test_bit(IP_TUNNEL_OAM_BIT, info->key.tun_flags); geneveh->critical = test_bit(IP_TUNNEL_CRIT_OPT_BIT, info->key.tun_flags); geneveh->rsvd1 = 0; tunnel_id_to_vni(info->key.tun_id, geneveh->vni); geneveh->proto_type = inner_proto; geneveh->rsvd2 = 0; if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) ip_tunnel_info_opts_get(geneveh->options, info); } static int geneve_build_skb(struct dst_entry *dst, struct sk_buff *skb, const struct ip_tunnel_info *info, bool xnet, int ip_hdr_len, bool inner_proto_inherit) { bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); struct genevehdr *gnvh; __be16 inner_proto; int min_headroom; int err; skb_reset_mac_header(skb); skb_scrub_packet(skb, xnet); min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + GENEVE_BASE_HLEN + info->options_len + ip_hdr_len; err = skb_cow_head(skb, min_headroom); if (unlikely(err)) goto free_dst; err = udp_tunnel_handle_offloads(skb, udp_sum); if (err) goto free_dst; gnvh = __skb_push(skb, sizeof(*gnvh) + info->options_len); inner_proto = inner_proto_inherit ? skb->protocol : htons(ETH_P_TEB); geneve_build_header(gnvh, info, inner_proto); skb_set_inner_protocol(skb, inner_proto); return 0; free_dst: dst_release(dst); return err; } static u8 geneve_get_dsfield(struct sk_buff *skb, struct net_device *dev, const struct ip_tunnel_info *info, bool *use_cache) { struct geneve_dev *geneve = netdev_priv(dev); u8 dsfield; dsfield = info->key.tos; if (dsfield == 1 && !geneve->cfg.collect_md) { dsfield = ip_tunnel_get_dsfield(ip_hdr(skb), skb); *use_cache = false; } return dsfield; } static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve, const struct ip_tunnel_info *info) { bool inner_proto_inherit = geneve->cfg.inner_proto_inherit; bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); struct geneve_sock *gs4 = rcu_dereference(geneve->sock4); const struct ip_tunnel_key *key = &info->key; struct rtable *rt; bool use_cache; __u8 tos, ttl; __be16 df = 0; __be32 saddr; __be16 sport; int err; if (skb_vlan_inet_prepare(skb, inner_proto_inherit)) return -EINVAL; if (!gs4) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); tos = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, geneve->cfg.port_min, geneve->cfg.port_max, true); rt = udp_tunnel_dst_lookup(skb, dev, geneve->net, 0, &saddr, &info->key, sport, geneve->cfg.info.key.tp_dst, tos, use_cache ? (struct dst_cache *)&info->dst_cache : NULL); if (IS_ERR(rt)) return PTR_ERR(rt); err = skb_tunnel_check_pmtu(skb, &rt->dst, GENEVE_IPV4_HLEN + info->options_len, netif_is_any_bridge_port(dev)); if (err < 0) { dst_release(&rt->dst); return err; } else if (err) { struct ip_tunnel_info *info; info = skb_tunnel_info(skb); if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) { dst_release(&rt->dst); return -ENOMEM; } unclone->key.u.ipv4.dst = saddr; unclone->key.u.ipv4.src = info->key.u.ipv4.dst; } if (!pskb_may_pull(skb, ETH_HLEN)) { dst_release(&rt->dst); return -EINVAL; } skb->protocol = eth_type_trans(skb, geneve->dev); __netif_rx(skb); dst_release(&rt->dst); return -EMSGSIZE; } tos = ip_tunnel_ecn_encap(tos, ip_hdr(skb), skb); if (geneve->cfg.collect_md) { ttl = key->ttl; df = test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) ? htons(IP_DF) : 0; } else { if (geneve->cfg.ttl_inherit) ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); else ttl = key->ttl; ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); if (geneve->cfg.df == GENEVE_DF_SET) { df = htons(IP_DF); } else if (geneve->cfg.df == GENEVE_DF_INHERIT) { struct ethhdr *eth = skb_eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_IPV6) { df = htons(IP_DF); } else if (ntohs(eth->h_proto) == ETH_P_IP) { struct iphdr *iph = ip_hdr(skb); if (iph->frag_off & htons(IP_DF)) df = htons(IP_DF); } } } err = geneve_build_skb(&rt->dst, skb, info, xnet, sizeof(struct iphdr), inner_proto_inherit); if (unlikely(err)) return err; udp_tunnel_xmit_skb(rt, gs4->sock->sk, skb, saddr, info->key.u.ipv4.dst, tos, ttl, df, sport, geneve->cfg.info.key.tp_dst, !net_eq(geneve->net, dev_net(geneve->dev)), !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)); return 0; } #if IS_ENABLED(CONFIG_IPV6) static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve, const struct ip_tunnel_info *info) { bool inner_proto_inherit = geneve->cfg.inner_proto_inherit; bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); struct geneve_sock *gs6 = rcu_dereference(geneve->sock6); const struct ip_tunnel_key *key = &info->key; struct dst_entry *dst = NULL; struct in6_addr saddr; bool use_cache; __u8 prio, ttl; __be16 sport; int err; if (skb_vlan_inet_prepare(skb, inner_proto_inherit)) return -EINVAL; if (!gs6) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); prio = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, geneve->cfg.port_min, geneve->cfg.port_max, true); dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sock, 0, &saddr, key, sport, geneve->cfg.info.key.tp_dst, prio, use_cache ? (struct dst_cache *)&info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); err = skb_tunnel_check_pmtu(skb, dst, GENEVE_IPV6_HLEN + info->options_len, netif_is_any_bridge_port(dev)); if (err < 0) { dst_release(dst); return err; } else if (err) { struct ip_tunnel_info *info = skb_tunnel_info(skb); if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) { dst_release(dst); return -ENOMEM; } unclone->key.u.ipv6.dst = saddr; unclone->key.u.ipv6.src = info->key.u.ipv6.dst; } if (!pskb_may_pull(skb, ETH_HLEN)) { dst_release(dst); return -EINVAL; } skb->protocol = eth_type_trans(skb, geneve->dev); __netif_rx(skb); dst_release(dst); return -EMSGSIZE; } prio = ip_tunnel_ecn_encap(prio, ip_hdr(skb), skb); if (geneve->cfg.collect_md) { ttl = key->ttl; } else { if (geneve->cfg.ttl_inherit) ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); else ttl = key->ttl; ttl = ttl ? : ip6_dst_hoplimit(dst); } err = geneve_build_skb(dst, skb, info, xnet, sizeof(struct ipv6hdr), inner_proto_inherit); if (unlikely(err)) return err; udp_tunnel6_xmit_skb(dst, gs6->sock->sk, skb, dev, &saddr, &key->u.ipv6.dst, prio, ttl, info->key.label, sport, geneve->cfg.info.key.tp_dst, !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)); return 0; } #endif static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); struct ip_tunnel_info *info = NULL; int err; if (geneve->cfg.collect_md) { info = skb_tunnel_info(skb); if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { netdev_dbg(dev, "no tunnel metadata\n"); dev_kfree_skb(skb); dev_dstats_tx_dropped(dev); return NETDEV_TX_OK; } } else { info = &geneve->cfg.info; } rcu_read_lock(); #if IS_ENABLED(CONFIG_IPV6) if (info->mode & IP_TUNNEL_INFO_IPV6) err = geneve6_xmit_skb(skb, dev, geneve, info); else #endif err = geneve_xmit_skb(skb, dev, geneve, info); rcu_read_unlock(); if (likely(!err)) return NETDEV_TX_OK; if (err != -EMSGSIZE) dev_kfree_skb(skb); if (err == -ELOOP) DEV_STATS_INC(dev, collisions); else if (err == -ENETUNREACH) DEV_STATS_INC(dev, tx_carrier_errors); DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK; } static int geneve_change_mtu(struct net_device *dev, int new_mtu) { if (new_mtu > dev->max_mtu) new_mtu = dev->max_mtu; else if (new_mtu < dev->min_mtu) new_mtu = dev->min_mtu; WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); struct geneve_dev *geneve = netdev_priv(dev); __be16 sport; if (ip_tunnel_info_af(info) == AF_INET) { struct rtable *rt; struct geneve_sock *gs4 = rcu_dereference(geneve->sock4); bool use_cache; __be32 saddr; u8 tos; if (!gs4) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); tos = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, geneve->cfg.port_min, geneve->cfg.port_max, true); rt = udp_tunnel_dst_lookup(skb, dev, geneve->net, 0, &saddr, &info->key, sport, geneve->cfg.info.key.tp_dst, tos, use_cache ? &info->dst_cache : NULL); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); info->key.u.ipv4.src = saddr; #if IS_ENABLED(CONFIG_IPV6) } else if (ip_tunnel_info_af(info) == AF_INET6) { struct dst_entry *dst; struct geneve_sock *gs6 = rcu_dereference(geneve->sock6); struct in6_addr saddr; bool use_cache; u8 prio; if (!gs6) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); prio = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, geneve->cfg.port_min, geneve->cfg.port_max, true); dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sock, 0, &saddr, &info->key, sport, geneve->cfg.info.key.tp_dst, prio, use_cache ? &info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); dst_release(dst); info->key.u.ipv6.src = saddr; #endif } else { return -EINVAL; } info->key.tp_src = sport; info->key.tp_dst = geneve->cfg.info.key.tp_dst; return 0; } static const struct net_device_ops geneve_netdev_ops = { .ndo_init = geneve_init, .ndo_uninit = geneve_uninit, .ndo_open = geneve_open, .ndo_stop = geneve_stop, .ndo_start_xmit = geneve_xmit, .ndo_change_mtu = geneve_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_fill_metadata_dst = geneve_fill_metadata_dst, }; static void geneve_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->version, GENEVE_NETDEV_VER, sizeof(drvinfo->version)); strscpy(drvinfo->driver, "geneve", sizeof(drvinfo->driver)); } static const struct ethtool_ops geneve_ethtool_ops = { .get_drvinfo = geneve_get_drvinfo, .get_link = ethtool_op_get_link, }; /* Info for udev, that this is a virtual tunnel endpoint */ static const struct device_type geneve_type = { .name = "geneve", }; /* Calls the ndo_udp_tunnel_add of the caller in order to * supply the listening GENEVE udp ports. Callers are expected * to implement the ndo_udp_tunnel_add. */ static void geneve_offload_rx_ports(struct net_device *dev, bool push) { struct net *net = dev_net(dev); struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_sock *gs; rcu_read_lock(); list_for_each_entry_rcu(gs, &gn->sock_list, list) { if (push) { udp_tunnel_push_rx_port(dev, gs->sock, UDP_TUNNEL_TYPE_GENEVE); } else { udp_tunnel_drop_rx_port(dev, gs->sock, UDP_TUNNEL_TYPE_GENEVE); } } rcu_read_unlock(); } /* Initialize the device structure. */ static void geneve_setup(struct net_device *dev) { ether_setup(dev); dev->netdev_ops = &geneve_netdev_ops; dev->ethtool_ops = &geneve_ethtool_ops; dev->needs_free_netdev = true; SET_NETDEV_DEVTYPE(dev, &geneve_type); dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->features |= NETIF_F_RXCSUM; dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->hw_features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; /* MTU range: 68 - (something less than 65535) */ dev->min_mtu = ETH_MIN_MTU; /* The max_mtu calculation does not take account of GENEVE * options, to avoid excluding potentially valid * configurations. This will be further reduced by IPvX hdr size. */ dev->max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - dev->hard_header_len; netif_keep_dst(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; dev->lltx = true; eth_hw_addr_random(dev); } static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_UNSPEC] = { .strict_start_type = IFLA_GENEVE_INNER_PROTO_INHERIT }, [IFLA_GENEVE_ID] = { .type = NLA_U32 }, [IFLA_GENEVE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GENEVE_REMOTE6] = { .len = sizeof(struct in6_addr) }, [IFLA_GENEVE_TTL] = { .type = NLA_U8 }, [IFLA_GENEVE_TOS] = { .type = NLA_U8 }, [IFLA_GENEVE_LABEL] = { .type = NLA_U32 }, [IFLA_GENEVE_PORT] = { .type = NLA_U16 }, [IFLA_GENEVE_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_GENEVE_UDP_CSUM] = { .type = NLA_U8 }, [IFLA_GENEVE_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 }, [IFLA_GENEVE_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 }, [IFLA_GENEVE_TTL_INHERIT] = { .type = NLA_U8 }, [IFLA_GENEVE_DF] = { .type = NLA_U8 }, [IFLA_GENEVE_INNER_PROTO_INHERIT] = { .type = NLA_FLAG }, [IFLA_GENEVE_PORT_RANGE] = NLA_POLICY_EXACT_LEN(sizeof(struct ifla_geneve_port_range)), }; static int geneve_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided link layer address is not Ethernet"); return -EINVAL; } if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided Ethernet address is not unicast"); return -EADDRNOTAVAIL; } } if (!data) { NL_SET_ERR_MSG(extack, "Not enough attributes provided to perform the operation"); return -EINVAL; } if (data[IFLA_GENEVE_ID]) { __u32 vni = nla_get_u32(data[IFLA_GENEVE_ID]); if (vni >= GENEVE_N_VID) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_ID], "Geneve ID must be lower than 16777216"); return -ERANGE; } } if (data[IFLA_GENEVE_DF]) { enum ifla_geneve_df df = nla_get_u8(data[IFLA_GENEVE_DF]); if (df < 0 || df > GENEVE_DF_MAX) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_DF], "Invalid DF attribute"); return -EINVAL; } } if (data[IFLA_GENEVE_PORT_RANGE]) { const struct ifla_geneve_port_range *p; p = nla_data(data[IFLA_GENEVE_PORT_RANGE]); if (ntohs(p->high) < ntohs(p->low)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_PORT_RANGE], "Invalid source port range"); return -EINVAL; } } return 0; } static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, const struct ip_tunnel_info *info, bool *tun_on_same_port, bool *tun_collect_md) { struct geneve_dev *geneve, *t = NULL; *tun_on_same_port = false; *tun_collect_md = false; list_for_each_entry(geneve, &gn->geneve_list, next) { if (info->key.tp_dst == geneve->cfg.info.key.tp_dst) { *tun_collect_md = geneve->cfg.collect_md; *tun_on_same_port = true; } if (info->key.tun_id == geneve->cfg.info.key.tun_id && info->key.tp_dst == geneve->cfg.info.key.tp_dst && !memcmp(&info->key.u, &geneve->cfg.info.key.u, sizeof(info->key.u))) t = geneve; } return t; } static bool is_tnl_info_zero(const struct ip_tunnel_info *info) { return !(info->key.tun_id || info->key.tos || !ip_tunnel_flags_empty(info->key.tun_flags) || info->key.ttl || info->key.label || info->key.tp_src || memchr_inv(&info->key.u, 0, sizeof(info->key.u))); } static bool geneve_dst_addr_equal(struct ip_tunnel_info *a, struct ip_tunnel_info *b) { if (ip_tunnel_info_af(a) == AF_INET) return a->key.u.ipv4.dst == b->key.u.ipv4.dst; else return ipv6_addr_equal(&a->key.u.ipv6.dst, &b->key.u.ipv6.dst); } static int geneve_configure(struct net *net, struct net_device *dev, struct netlink_ext_ack *extack, const struct geneve_config *cfg) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *t, *geneve = netdev_priv(dev); const struct ip_tunnel_info *info = &cfg->info; bool tun_collect_md, tun_on_same_port; int err, encap_len; if (cfg->collect_md && !is_tnl_info_zero(info)) { NL_SET_ERR_MSG(extack, "Device is externally controlled, so attributes (VNI, Port, and so on) must not be specified"); return -EINVAL; } geneve->net = net; geneve->dev = dev; t = geneve_find_dev(gn, info, &tun_on_same_port, &tun_collect_md); if (t) return -EBUSY; /* make enough headroom for basic scenario */ encap_len = GENEVE_BASE_HLEN + ETH_HLEN; if (!cfg->collect_md && ip_tunnel_info_af(info) == AF_INET) { encap_len += sizeof(struct iphdr); dev->max_mtu -= sizeof(struct iphdr); } else { encap_len += sizeof(struct ipv6hdr); dev->max_mtu -= sizeof(struct ipv6hdr); } dev->needed_headroom = encap_len + ETH_HLEN; if (cfg->collect_md) { if (tun_on_same_port) { NL_SET_ERR_MSG(extack, "There can be only one externally controlled device on a destination port"); return -EPERM; } } else { if (tun_collect_md) { NL_SET_ERR_MSG(extack, "There already exists an externally controlled device on this destination port"); return -EPERM; } } dst_cache_reset(&geneve->cfg.info.dst_cache); memcpy(&geneve->cfg, cfg, sizeof(*cfg)); if (geneve->cfg.inner_proto_inherit) { dev->header_ops = NULL; dev->type = ARPHRD_NONE; dev->hard_header_len = 0; dev->addr_len = 0; dev->flags = IFF_POINTOPOINT | IFF_NOARP; } err = register_netdevice(dev); if (err) return err; list_add(&geneve->next, &gn->geneve_list); return 0; } static void init_tnl_info(struct ip_tunnel_info *info, __u16 dst_port) { memset(info, 0, sizeof(*info)); info->key.tp_dst = htons(dst_port); } static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack, struct geneve_config *cfg, bool changelink) { struct ip_tunnel_info *info = &cfg->info; int attrtype; if (data[IFLA_GENEVE_REMOTE] && data[IFLA_GENEVE_REMOTE6]) { NL_SET_ERR_MSG(extack, "Cannot specify both IPv4 and IPv6 Remote addresses"); return -EINVAL; } if (data[IFLA_GENEVE_REMOTE]) { if (changelink && (ip_tunnel_info_af(info) == AF_INET6)) { attrtype = IFLA_GENEVE_REMOTE; goto change_notsup; } info->key.u.ipv4.dst = nla_get_in_addr(data[IFLA_GENEVE_REMOTE]); if (ipv4_is_multicast(info->key.u.ipv4.dst)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE], "Remote IPv4 address cannot be Multicast"); return -EINVAL; } } if (data[IFLA_GENEVE_REMOTE6]) { #if IS_ENABLED(CONFIG_IPV6) if (changelink && (ip_tunnel_info_af(info) == AF_INET)) { attrtype = IFLA_GENEVE_REMOTE6; goto change_notsup; } info->mode = IP_TUNNEL_INFO_IPV6; info->key.u.ipv6.dst = nla_get_in6_addr(data[IFLA_GENEVE_REMOTE6]); if (ipv6_addr_type(&info->key.u.ipv6.dst) & IPV6_ADDR_LINKLOCAL) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], "Remote IPv6 address cannot be link-local"); return -EINVAL; } if (ipv6_addr_is_multicast(&info->key.u.ipv6.dst)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], "Remote IPv6 address cannot be Multicast"); return -EINVAL; } __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); cfg->use_udp6_rx_checksums = true; #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; #endif } if (data[IFLA_GENEVE_ID]) { __u32 vni; __u8 tvni[3]; __be64 tunid; vni = nla_get_u32(data[IFLA_GENEVE_ID]); tvni[0] = (vni & 0x00ff0000) >> 16; tvni[1] = (vni & 0x0000ff00) >> 8; tvni[2] = vni & 0x000000ff; tunid = vni_to_tunnel_id(tvni); if (changelink && (tunid != info->key.tun_id)) { attrtype = IFLA_GENEVE_ID; goto change_notsup; } info->key.tun_id = tunid; } if (data[IFLA_GENEVE_TTL_INHERIT]) { if (nla_get_u8(data[IFLA_GENEVE_TTL_INHERIT])) cfg->ttl_inherit = true; else cfg->ttl_inherit = false; } else if (data[IFLA_GENEVE_TTL]) { info->key.ttl = nla_get_u8(data[IFLA_GENEVE_TTL]); cfg->ttl_inherit = false; } if (data[IFLA_GENEVE_TOS]) info->key.tos = nla_get_u8(data[IFLA_GENEVE_TOS]); if (data[IFLA_GENEVE_DF]) cfg->df = nla_get_u8(data[IFLA_GENEVE_DF]); if (data[IFLA_GENEVE_LABEL]) { info->key.label = nla_get_be32(data[IFLA_GENEVE_LABEL]) & IPV6_FLOWLABEL_MASK; if (info->key.label && (!(info->mode & IP_TUNNEL_INFO_IPV6))) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_LABEL], "Label attribute only applies for IPv6 Geneve devices"); return -EINVAL; } } if (data[IFLA_GENEVE_PORT]) { if (changelink) { attrtype = IFLA_GENEVE_PORT; goto change_notsup; } info->key.tp_dst = nla_get_be16(data[IFLA_GENEVE_PORT]); } if (data[IFLA_GENEVE_PORT_RANGE]) { const struct ifla_geneve_port_range *p; if (changelink) { attrtype = IFLA_GENEVE_PORT_RANGE; goto change_notsup; } p = nla_data(data[IFLA_GENEVE_PORT_RANGE]); cfg->port_min = ntohs(p->low); cfg->port_max = ntohs(p->high); } if (data[IFLA_GENEVE_COLLECT_METADATA]) { if (changelink) { attrtype = IFLA_GENEVE_COLLECT_METADATA; goto change_notsup; } cfg->collect_md = true; } if (data[IFLA_GENEVE_UDP_CSUM]) { if (changelink) { attrtype = IFLA_GENEVE_UDP_CSUM; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_CSUM])) __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); } if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX]) { #if IS_ENABLED(CONFIG_IPV6) if (changelink) { attrtype = IFLA_GENEVE_UDP_ZERO_CSUM6_TX; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX])) __clear_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; #endif } if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX]) { #if IS_ENABLED(CONFIG_IPV6) if (changelink) { attrtype = IFLA_GENEVE_UDP_ZERO_CSUM6_RX; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX])) cfg->use_udp6_rx_checksums = false; #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; #endif } if (data[IFLA_GENEVE_INNER_PROTO_INHERIT]) { if (changelink) { attrtype = IFLA_GENEVE_INNER_PROTO_INHERIT; goto change_notsup; } cfg->inner_proto_inherit = true; } return 0; change_notsup: NL_SET_ERR_MSG_ATTR(extack, data[attrtype], "Changing VNI, Port, endpoint IP address family, external, inner_proto_inherit, and UDP checksum attributes are not supported"); return -EOPNOTSUPP; } static void geneve_link_config(struct net_device *dev, struct ip_tunnel_info *info, struct nlattr *tb[]) { struct geneve_dev *geneve = netdev_priv(dev); int ldev_mtu = 0; if (tb[IFLA_MTU]) { geneve_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); return; } switch (ip_tunnel_info_af(info)) { case AF_INET: { struct flowi4 fl4 = { .daddr = info->key.u.ipv4.dst }; struct rtable *rt = ip_route_output_key(geneve->net, &fl4); if (!IS_ERR(rt) && rt->dst.dev) { ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV4_HLEN; ip_rt_put(rt); } break; } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { struct rt6_info *rt; if (!__in6_dev_get(dev)) break; rt = rt6_lookup(geneve->net, &info->key.u.ipv6.dst, NULL, 0, NULL, 0); if (rt && rt->dst.dev) ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV6_HLEN; ip6_rt_put(rt); break; } #endif } if (ldev_mtu <= 0) return; geneve_change_mtu(dev, ldev_mtu - info->options_len); } static int geneve_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net *link_net = rtnl_newlink_link_net(params); struct nlattr **data = params->data; struct nlattr **tb = params->tb; struct geneve_config cfg = { .df = GENEVE_DF_UNSET, .use_udp6_rx_checksums = false, .ttl_inherit = false, .collect_md = false, .port_min = 1, .port_max = USHRT_MAX, }; int err; init_tnl_info(&cfg.info, GENEVE_UDP_PORT); err = geneve_nl2info(tb, data, extack, &cfg, false); if (err) return err; err = geneve_configure(link_net, dev, extack, &cfg); if (err) return err; geneve_link_config(dev, &cfg.info, tb); return 0; } /* Quiesces the geneve device data path for both TX and RX. * * On transmit geneve checks for non-NULL geneve_sock before it proceeds. * So, if we set that socket to NULL under RCU and wait for synchronize_net() * to complete for the existing set of in-flight packets to be transmitted, * then we would have quiesced the transmit data path. All the future packets * will get dropped until we unquiesce the data path. * * On receive geneve dereference the geneve_sock stashed in the socket. So, * if we set that to NULL under RCU and wait for synchronize_net() to * complete, then we would have quiesced the receive data path. */ static void geneve_quiesce(struct geneve_dev *geneve, struct geneve_sock **gs4, struct geneve_sock **gs6) { *gs4 = rtnl_dereference(geneve->sock4); rcu_assign_pointer(geneve->sock4, NULL); if (*gs4) rcu_assign_sk_user_data((*gs4)->sock->sk, NULL); #if IS_ENABLED(CONFIG_IPV6) *gs6 = rtnl_dereference(geneve->sock6); rcu_assign_pointer(geneve->sock6, NULL); if (*gs6) rcu_assign_sk_user_data((*gs6)->sock->sk, NULL); #else *gs6 = NULL; #endif synchronize_net(); } /* Resumes the geneve device data path for both TX and RX. */ static void geneve_unquiesce(struct geneve_dev *geneve, struct geneve_sock *gs4, struct geneve_sock __maybe_unused *gs6) { rcu_assign_pointer(geneve->sock4, gs4); if (gs4) rcu_assign_sk_user_data(gs4->sock->sk, gs4); #if IS_ENABLED(CONFIG_IPV6) rcu_assign_pointer(geneve->sock6, gs6); if (gs6) rcu_assign_sk_user_data(gs6->sock->sk, gs6); #endif synchronize_net(); } static int geneve_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct geneve_dev *geneve = netdev_priv(dev); struct geneve_sock *gs4, *gs6; struct geneve_config cfg; int err; /* If the geneve device is configured for metadata (or externally * controlled, for example, OVS), then nothing can be changed. */ if (geneve->cfg.collect_md) return -EOPNOTSUPP; /* Start with the existing info. */ memcpy(&cfg, &geneve->cfg, sizeof(cfg)); err = geneve_nl2info(tb, data, extack, &cfg, true); if (err) return err; if (!geneve_dst_addr_equal(&geneve->cfg.info, &cfg.info)) { dst_cache_reset(&cfg.info.dst_cache); geneve_link_config(dev, &cfg.info, tb); } geneve_quiesce(geneve, &gs4, &gs6); memcpy(&geneve->cfg, &cfg, sizeof(cfg)); geneve_unquiesce(geneve, gs4, gs6); return 0; } static void geneve_dellink(struct net_device *dev, struct list_head *head) { struct geneve_dev *geneve = netdev_priv(dev); list_del(&geneve->next); unregister_netdevice_queue(dev, head); } static size_t geneve_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_GENEVE_ID */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GENEVE_REMOTE{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TOS */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_DF */ nla_total_size(sizeof(__be32)) + /* IFLA_GENEVE_LABEL */ nla_total_size(sizeof(__be16)) + /* IFLA_GENEVE_PORT */ nla_total_size(0) + /* IFLA_GENEVE_COLLECT_METADATA */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_CSUM */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL_INHERIT */ nla_total_size(0) + /* IFLA_GENEVE_INNER_PROTO_INHERIT */ nla_total_size(sizeof(struct ifla_geneve_port_range)) + /* IFLA_GENEVE_PORT_RANGE */ 0; } static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); struct ip_tunnel_info *info = &geneve->cfg.info; bool ttl_inherit = geneve->cfg.ttl_inherit; bool metadata = geneve->cfg.collect_md; struct ifla_geneve_port_range ports = { .low = htons(geneve->cfg.port_min), .high = htons(geneve->cfg.port_max), }; __u8 tmp_vni[3]; __u32 vni; tunnel_id_to_vni(info->key.tun_id, tmp_vni); vni = (tmp_vni[0] << 16) | (tmp_vni[1] << 8) | tmp_vni[2]; if (nla_put_u32(skb, IFLA_GENEVE_ID, vni)) goto nla_put_failure; if (!metadata && ip_tunnel_info_af(info) == AF_INET) { if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE, info->key.u.ipv4.dst)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_UDP_CSUM, test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags))) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else if (!metadata) { if (nla_put_in6_addr(skb, IFLA_GENEVE_REMOTE6, &info->key.u.ipv6.dst)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_TX, !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags))) goto nla_put_failure; #endif } if (nla_put_u8(skb, IFLA_GENEVE_TTL, info->key.ttl) || nla_put_u8(skb, IFLA_GENEVE_TOS, info->key.tos) || nla_put_be32(skb, IFLA_GENEVE_LABEL, info->key.label)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_DF, geneve->cfg.df)) goto nla_put_failure; if (nla_put_be16(skb, IFLA_GENEVE_PORT, info->key.tp_dst)) goto nla_put_failure; if (metadata && nla_put_flag(skb, IFLA_GENEVE_COLLECT_METADATA)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_RX, !geneve->cfg.use_udp6_rx_checksums)) goto nla_put_failure; #endif if (nla_put_u8(skb, IFLA_GENEVE_TTL_INHERIT, ttl_inherit)) goto nla_put_failure; if (geneve->cfg.inner_proto_inherit && nla_put_flag(skb, IFLA_GENEVE_INNER_PROTO_INHERIT)) goto nla_put_failure; if (nla_put(skb, IFLA_GENEVE_PORT_RANGE, sizeof(ports), &ports)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static struct rtnl_link_ops geneve_link_ops __read_mostly = { .kind = "geneve", .maxtype = IFLA_GENEVE_MAX, .policy = geneve_policy, .priv_size = sizeof(struct geneve_dev), .setup = geneve_setup, .validate = geneve_validate, .newlink = geneve_newlink, .changelink = geneve_changelink, .dellink = geneve_dellink, .get_size = geneve_get_size, .fill_info = geneve_fill_info, }; struct net_device *geneve_dev_create_fb(struct net *net, const char *name, u8 name_assign_type, u16 dst_port) { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; LIST_HEAD(list_kill); int err; struct geneve_config cfg = { .df = GENEVE_DF_UNSET, .use_udp6_rx_checksums = true, .ttl_inherit = false, .collect_md = true, .port_min = 1, .port_max = USHRT_MAX, }; memset(tb, 0, sizeof(tb)); dev = rtnl_create_link(net, name, name_assign_type, &geneve_link_ops, tb, NULL); if (IS_ERR(dev)) return dev; init_tnl_info(&cfg.info, dst_port); err = geneve_configure(net, dev, NULL, &cfg); if (err) { free_netdev(dev); return ERR_PTR(err); } /* openvswitch users expect packet sizes to be unrestricted, * so set the largest MTU we can. */ err = geneve_change_mtu(dev, IP_MAX_MTU); if (err) goto err; err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto err; return dev; err: geneve_dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(geneve_dev_create_fb); static int geneve_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (event == NETDEV_UDP_TUNNEL_PUSH_INFO) geneve_offload_rx_ports(dev, true); else if (event == NETDEV_UDP_TUNNEL_DROP_INFO) geneve_offload_rx_ports(dev, false); return NOTIFY_DONE; } static struct notifier_block geneve_notifier_block __read_mostly = { .notifier_call = geneve_netdevice_event, }; static __net_init int geneve_init_net(struct net *net) { struct geneve_net *gn = net_generic(net, geneve_net_id); INIT_LIST_HEAD(&gn->geneve_list); INIT_LIST_HEAD(&gn->sock_list); return 0; } static void geneve_destroy_tunnels(struct net *net, struct list_head *head) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *geneve, *next; list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) geneve_dellink(geneve->dev, head); } static void __net_exit geneve_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_to_kill) { struct net *net; list_for_each_entry(net, net_list, exit_list) geneve_destroy_tunnels(net, dev_to_kill); } static void __net_exit geneve_exit_net(struct net *net) { const struct geneve_net *gn = net_generic(net, geneve_net_id); WARN_ON_ONCE(!list_empty(&gn->sock_list)); } static struct pernet_operations geneve_net_ops = { .init = geneve_init_net, .exit_batch_rtnl = geneve_exit_batch_rtnl, .exit = geneve_exit_net, .id = &geneve_net_id, .size = sizeof(struct geneve_net), }; static int __init geneve_init_module(void) { int rc; rc = register_pernet_subsys(&geneve_net_ops); if (rc) goto out1; rc = register_netdevice_notifier(&geneve_notifier_block); if (rc) goto out2; rc = rtnl_link_register(&geneve_link_ops); if (rc) goto out3; return 0; out3: unregister_netdevice_notifier(&geneve_notifier_block); out2: unregister_pernet_subsys(&geneve_net_ops); out1: return rc; } late_initcall(geneve_init_module); static void __exit geneve_cleanup_module(void) { rtnl_link_unregister(&geneve_link_ops); unregister_netdevice_notifier(&geneve_notifier_block); unregister_pernet_subsys(&geneve_net_ops); } module_exit(geneve_cleanup_module); MODULE_LICENSE("GPL"); MODULE_VERSION(GENEVE_NETDEV_VER); MODULE_AUTHOR("John W. Linville <linville@tuxdriver.com>"); MODULE_DESCRIPTION("Interface driver for GENEVE encapsulated traffic"); MODULE_ALIAS_RTNL_LINK("geneve"); |
| 6 336 135 143 482 138 138 | 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 */ #ifndef _NF_CONNTRACK_ZONES_H #define _NF_CONNTRACK_ZONES_H #include <linux/netfilter/nf_conntrack_zones_common.h> #include <net/netfilter/nf_conntrack.h> static inline const struct nf_conntrack_zone * nf_ct_zone(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_ZONES return &ct->zone; #else return &nf_ct_zone_dflt; #endif } static inline const struct nf_conntrack_zone * nf_ct_zone_init(struct nf_conntrack_zone *zone, u16 id, u8 dir, u8 flags) { zone->id = id; zone->flags = flags; zone->dir = dir; return zone; } static inline const struct nf_conntrack_zone * nf_ct_zone_tmpl(const struct nf_conn *tmpl, const struct sk_buff *skb, struct nf_conntrack_zone *tmp) { #ifdef CONFIG_NF_CONNTRACK_ZONES if (!tmpl) return &nf_ct_zone_dflt; if (tmpl->zone.flags & NF_CT_FLAG_MARK) return nf_ct_zone_init(tmp, skb->mark, tmpl->zone.dir, 0); #endif return nf_ct_zone(tmpl); } static inline void nf_ct_zone_add(struct nf_conn *ct, const struct nf_conntrack_zone *zone) { #ifdef CONFIG_NF_CONNTRACK_ZONES ct->zone = *zone; #endif } static inline bool nf_ct_zone_matches_dir(const struct nf_conntrack_zone *zone, enum ip_conntrack_dir dir) { return zone->dir & (1 << dir); } static inline u16 nf_ct_zone_id(const struct nf_conntrack_zone *zone, enum ip_conntrack_dir dir) { #ifdef CONFIG_NF_CONNTRACK_ZONES return nf_ct_zone_matches_dir(zone, dir) ? zone->id : NF_CT_DEFAULT_ZONE_ID; #else return NF_CT_DEFAULT_ZONE_ID; #endif } static inline bool nf_ct_zone_equal(const struct nf_conn *a, const struct nf_conntrack_zone *b, enum ip_conntrack_dir dir) { #ifdef CONFIG_NF_CONNTRACK_ZONES return nf_ct_zone_id(nf_ct_zone(a), dir) == nf_ct_zone_id(b, dir); #else return true; #endif } static inline bool nf_ct_zone_equal_any(const struct nf_conn *a, const struct nf_conntrack_zone *b) { #ifdef CONFIG_NF_CONNTRACK_ZONES return nf_ct_zone(a)->id == b->id; #else return true; #endif } #endif /* _NF_CONNTRACK_ZONES_H */ |
| 38 38 3 1 1 1 3 1 1 1 1 1 1 1 165 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Management Component Transport Protocol (MCTP) - routing * implementation. * * This is currently based on a simple routing table, with no dst cache. The * number of routes should stay fairly small, so the lookup cost is small. * * Copyright (c) 2021 Code Construct * Copyright (c) 2021 Google */ #include <linux/idr.h> #include <linux/mctp.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <net/mctp.h> #include <net/mctpdevice.h> #include <net/netlink.h> #include <net/sock.h> static int mctp_neigh_add(struct mctp_dev *mdev, mctp_eid_t eid, enum mctp_neigh_source source, size_t lladdr_len, const void *lladdr) { struct net *net = dev_net(mdev->dev); struct mctp_neigh *neigh; int rc; mutex_lock(&net->mctp.neigh_lock); if (mctp_neigh_lookup(mdev, eid, NULL) == 0) { rc = -EEXIST; goto out; } if (lladdr_len > sizeof(neigh->ha)) { rc = -EINVAL; goto out; } neigh = kzalloc(sizeof(*neigh), GFP_KERNEL); if (!neigh) { rc = -ENOMEM; goto out; } INIT_LIST_HEAD(&neigh->list); neigh->dev = mdev; mctp_dev_hold(neigh->dev); neigh->eid = eid; neigh->source = source; memcpy(neigh->ha, lladdr, lladdr_len); list_add_rcu(&neigh->list, &net->mctp.neighbours); rc = 0; out: mutex_unlock(&net->mctp.neigh_lock); return rc; } static void __mctp_neigh_free(struct rcu_head *rcu) { struct mctp_neigh *neigh = container_of(rcu, struct mctp_neigh, rcu); mctp_dev_put(neigh->dev); kfree(neigh); } /* Removes all neighbour entries referring to a device */ void mctp_neigh_remove_dev(struct mctp_dev *mdev) { struct net *net = dev_net(mdev->dev); struct mctp_neigh *neigh, *tmp; mutex_lock(&net->mctp.neigh_lock); list_for_each_entry_safe(neigh, tmp, &net->mctp.neighbours, list) { if (neigh->dev == mdev) { list_del_rcu(&neigh->list); /* TODO: immediate RTM_DELNEIGH */ call_rcu(&neigh->rcu, __mctp_neigh_free); } } mutex_unlock(&net->mctp.neigh_lock); } static int mctp_neigh_remove(struct mctp_dev *mdev, mctp_eid_t eid, enum mctp_neigh_source source) { struct net *net = dev_net(mdev->dev); struct mctp_neigh *neigh, *tmp; bool dropped = false; mutex_lock(&net->mctp.neigh_lock); list_for_each_entry_safe(neigh, tmp, &net->mctp.neighbours, list) { if (neigh->dev == mdev && neigh->eid == eid && neigh->source == source) { list_del_rcu(&neigh->list); /* TODO: immediate RTM_DELNEIGH */ call_rcu(&neigh->rcu, __mctp_neigh_free); dropped = true; } } mutex_unlock(&net->mctp.neigh_lock); return dropped ? 0 : -ENOENT; } static const struct nla_policy nd_mctp_policy[NDA_MAX + 1] = { [NDA_DST] = { .type = NLA_U8 }, [NDA_LLADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, }; static int mctp_rtm_newneigh(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct net_device *dev; struct mctp_dev *mdev; struct ndmsg *ndm; struct nlattr *tb[NDA_MAX + 1]; int rc; mctp_eid_t eid; void *lladdr; int lladdr_len; rc = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, nd_mctp_policy, extack); if (rc < 0) { NL_SET_ERR_MSG(extack, "lladdr too large?"); return rc; } if (!tb[NDA_DST]) { NL_SET_ERR_MSG(extack, "Neighbour EID must be specified"); return -EINVAL; } if (!tb[NDA_LLADDR]) { NL_SET_ERR_MSG(extack, "Neighbour lladdr must be specified"); return -EINVAL; } eid = nla_get_u8(tb[NDA_DST]); if (!mctp_address_unicast(eid)) { NL_SET_ERR_MSG(extack, "Invalid neighbour EID"); return -EINVAL; } lladdr = nla_data(tb[NDA_LLADDR]); lladdr_len = nla_len(tb[NDA_LLADDR]); ndm = nlmsg_data(nlh); dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (!dev) return -ENODEV; mdev = mctp_dev_get_rtnl(dev); if (!mdev) return -ENODEV; if (lladdr_len != dev->addr_len) { NL_SET_ERR_MSG(extack, "Wrong lladdr length"); return -EINVAL; } return mctp_neigh_add(mdev, eid, MCTP_NEIGH_STATIC, lladdr_len, lladdr); } static int mctp_rtm_delneigh(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[NDA_MAX + 1]; struct net_device *dev; struct mctp_dev *mdev; struct ndmsg *ndm; int rc; mctp_eid_t eid; rc = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, nd_mctp_policy, extack); if (rc < 0) { NL_SET_ERR_MSG(extack, "incorrect format"); return rc; } if (!tb[NDA_DST]) { NL_SET_ERR_MSG(extack, "Neighbour EID must be specified"); return -EINVAL; } eid = nla_get_u8(tb[NDA_DST]); ndm = nlmsg_data(nlh); dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (!dev) return -ENODEV; mdev = mctp_dev_get_rtnl(dev); if (!mdev) return -ENODEV; return mctp_neigh_remove(mdev, eid, MCTP_NEIGH_STATIC); } static int mctp_fill_neigh(struct sk_buff *skb, u32 portid, u32 seq, int event, unsigned int flags, struct mctp_neigh *neigh) { struct net_device *dev = neigh->dev->dev; struct nlmsghdr *nlh; struct ndmsg *hdr; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags); if (!nlh) return -EMSGSIZE; hdr = nlmsg_data(nlh); hdr->ndm_family = AF_MCTP; hdr->ndm_ifindex = dev->ifindex; hdr->ndm_state = 0; // TODO other state bits? if (neigh->source == MCTP_NEIGH_STATIC) hdr->ndm_state |= NUD_PERMANENT; hdr->ndm_flags = 0; hdr->ndm_type = RTN_UNICAST; // TODO: is loopback RTN_LOCAL? if (nla_put_u8(skb, NDA_DST, neigh->eid)) goto cancel; if (nla_put(skb, NDA_LLADDR, dev->addr_len, neigh->ha)) goto cancel; nlmsg_end(skb, nlh); return 0; cancel: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int mctp_rtm_getneigh(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int rc, idx, req_ifindex; struct mctp_neigh *neigh; struct ndmsg *ndmsg; struct { int idx; } *cbctx = (void *)cb->ctx; ndmsg = nlmsg_data(cb->nlh); req_ifindex = ndmsg->ndm_ifindex; idx = 0; rcu_read_lock(); list_for_each_entry_rcu(neigh, &net->mctp.neighbours, list) { if (idx < cbctx->idx) goto cont; rc = 0; if (req_ifindex == 0 || req_ifindex == neigh->dev->dev->ifindex) rc = mctp_fill_neigh(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, neigh); if (rc) break; cont: idx++; } rcu_read_unlock(); cbctx->idx = idx; return skb->len; } int mctp_neigh_lookup(struct mctp_dev *mdev, mctp_eid_t eid, void *ret_hwaddr) { struct net *net = dev_net(mdev->dev); struct mctp_neigh *neigh; int rc = -EHOSTUNREACH; // TODO: or ENOENT? rcu_read_lock(); list_for_each_entry_rcu(neigh, &net->mctp.neighbours, list) { if (mdev == neigh->dev && eid == neigh->eid) { if (ret_hwaddr) memcpy(ret_hwaddr, neigh->ha, sizeof(neigh->ha)); rc = 0; break; } } rcu_read_unlock(); return rc; } /* namespace registration */ static int __net_init mctp_neigh_net_init(struct net *net) { struct netns_mctp *ns = &net->mctp; INIT_LIST_HEAD(&ns->neighbours); mutex_init(&ns->neigh_lock); return 0; } static void __net_exit mctp_neigh_net_exit(struct net *net) { struct netns_mctp *ns = &net->mctp; struct mctp_neigh *neigh; list_for_each_entry(neigh, &ns->neighbours, list) call_rcu(&neigh->rcu, __mctp_neigh_free); } /* net namespace implementation */ static struct pernet_operations mctp_net_ops = { .init = mctp_neigh_net_init, .exit = mctp_neigh_net_exit, }; static const struct rtnl_msg_handler mctp_neigh_rtnl_msg_handlers[] = { {THIS_MODULE, PF_MCTP, RTM_NEWNEIGH, mctp_rtm_newneigh, NULL, 0}, {THIS_MODULE, PF_MCTP, RTM_DELNEIGH, mctp_rtm_delneigh, NULL, 0}, {THIS_MODULE, PF_MCTP, RTM_GETNEIGH, NULL, mctp_rtm_getneigh, 0}, }; int __init mctp_neigh_init(void) { int err; err = register_pernet_subsys(&mctp_net_ops); if (err) return err; err = rtnl_register_many(mctp_neigh_rtnl_msg_handlers); if (err) unregister_pernet_subsys(&mctp_net_ops); return err; } void mctp_neigh_exit(void) { rtnl_unregister_many(mctp_neigh_rtnl_msg_handlers); unregister_pernet_subsys(&mctp_net_ops); } |
| 2 2 2 2 3 3 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * Alarmtimer interface * * This interface provides a timer which is similar to hrtimers, * but triggers a RTC alarm if the box is suspend. * * This interface is influenced by the Android RTC Alarm timer * interface. * * Copyright (C) 2010 IBM Corporation * * Author: John Stultz <john.stultz@linaro.org> */ #include <linux/time.h> #include <linux/hrtimer.h> #include <linux/timerqueue.h> #include <linux/rtc.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> #include <linux/alarmtimer.h> #include <linux/mutex.h> #include <linux/platform_device.h> #include <linux/posix-timers.h> #include <linux/workqueue.h> #include <linux/freezer.h> #include <linux/compat.h> #include <linux/module.h> #include <linux/time_namespace.h> #include "posix-timers.h" #define CREATE_TRACE_POINTS #include <trace/events/alarmtimer.h> /** * struct alarm_base - Alarm timer bases * @lock: Lock for syncrhonized access to the base * @timerqueue: Timerqueue head managing the list of events * @get_ktime: Function to read the time correlating to the base * @get_timespec: Function to read the namespace time correlating to the base * @base_clockid: clockid for the base */ static struct alarm_base { spinlock_t lock; struct timerqueue_head timerqueue; ktime_t (*get_ktime)(void); void (*get_timespec)(struct timespec64 *tp); clockid_t base_clockid; } alarm_bases[ALARM_NUMTYPE]; #if defined(CONFIG_POSIX_TIMERS) || defined(CONFIG_RTC_CLASS) /* freezer information to handle clock_nanosleep triggered wakeups */ static enum alarmtimer_type freezer_alarmtype; static ktime_t freezer_expires; static ktime_t freezer_delta; static DEFINE_SPINLOCK(freezer_delta_lock); #endif #ifdef CONFIG_RTC_CLASS /* rtc timer and device for setting alarm wakeups at suspend */ static struct rtc_timer rtctimer; static struct rtc_device *rtcdev; static DEFINE_SPINLOCK(rtcdev_lock); /** * alarmtimer_get_rtcdev - Return selected rtcdevice * * This function returns the rtc device to use for wakealarms. */ struct rtc_device *alarmtimer_get_rtcdev(void) { unsigned long flags; struct rtc_device *ret; spin_lock_irqsave(&rtcdev_lock, flags); ret = rtcdev; spin_unlock_irqrestore(&rtcdev_lock, flags); return ret; } EXPORT_SYMBOL_GPL(alarmtimer_get_rtcdev); static int alarmtimer_rtc_add_device(struct device *dev) { unsigned long flags; struct rtc_device *rtc = to_rtc_device(dev); struct platform_device *pdev; int ret = 0; if (rtcdev) return -EBUSY; if (!test_bit(RTC_FEATURE_ALARM, rtc->features)) return -1; if (!device_may_wakeup(rtc->dev.parent)) return -1; pdev = platform_device_register_data(dev, "alarmtimer", PLATFORM_DEVID_AUTO, NULL, 0); if (!IS_ERR(pdev)) device_init_wakeup(&pdev->dev, true); spin_lock_irqsave(&rtcdev_lock, flags); if (!IS_ERR(pdev) && !rtcdev) { if (!try_module_get(rtc->owner)) { ret = -1; goto unlock; } rtcdev = rtc; /* hold a reference so it doesn't go away */ get_device(dev); pdev = NULL; } else { ret = -1; } unlock: spin_unlock_irqrestore(&rtcdev_lock, flags); platform_device_unregister(pdev); return ret; } static inline void alarmtimer_rtc_timer_init(void) { rtc_timer_init(&rtctimer, NULL, NULL); } static struct class_interface alarmtimer_rtc_interface = { .add_dev = &alarmtimer_rtc_add_device, }; static int alarmtimer_rtc_interface_setup(void) { alarmtimer_rtc_interface.class = &rtc_class; return class_interface_register(&alarmtimer_rtc_interface); } static void alarmtimer_rtc_interface_remove(void) { class_interface_unregister(&alarmtimer_rtc_interface); } #else static inline int alarmtimer_rtc_interface_setup(void) { return 0; } static inline void alarmtimer_rtc_interface_remove(void) { } static inline void alarmtimer_rtc_timer_init(void) { } #endif /** * alarmtimer_enqueue - Adds an alarm timer to an alarm_base timerqueue * @base: pointer to the base where the timer is being run * @alarm: pointer to alarm being enqueued. * * Adds alarm to a alarm_base timerqueue * * Must hold base->lock when calling. */ static void alarmtimer_enqueue(struct alarm_base *base, struct alarm *alarm) { if (alarm->state & ALARMTIMER_STATE_ENQUEUED) timerqueue_del(&base->timerqueue, &alarm->node); timerqueue_add(&base->timerqueue, &alarm->node); alarm->state |= ALARMTIMER_STATE_ENQUEUED; } /** * alarmtimer_dequeue - Removes an alarm timer from an alarm_base timerqueue * @base: pointer to the base where the timer is running * @alarm: pointer to alarm being removed * * Removes alarm to a alarm_base timerqueue * * Must hold base->lock when calling. */ static void alarmtimer_dequeue(struct alarm_base *base, struct alarm *alarm) { if (!(alarm->state & ALARMTIMER_STATE_ENQUEUED)) return; timerqueue_del(&base->timerqueue, &alarm->node); alarm->state &= ~ALARMTIMER_STATE_ENQUEUED; } /** * alarmtimer_fired - Handles alarm hrtimer being fired. * @timer: pointer to hrtimer being run * * When a alarm timer fires, this runs through the timerqueue to * see which alarms expired, and runs those. If there are more alarm * timers queued for the future, we set the hrtimer to fire when * the next future alarm timer expires. */ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) { struct alarm *alarm = container_of(timer, struct alarm, timer); struct alarm_base *base = &alarm_bases[alarm->type]; scoped_guard (spinlock_irqsave, &base->lock) alarmtimer_dequeue(base, alarm); if (alarm->function) alarm->function(alarm, base->get_ktime()); trace_alarmtimer_fired(alarm, base->get_ktime()); return HRTIMER_NORESTART; } ktime_t alarm_expires_remaining(const struct alarm *alarm) { struct alarm_base *base = &alarm_bases[alarm->type]; return ktime_sub(alarm->node.expires, base->get_ktime()); } EXPORT_SYMBOL_GPL(alarm_expires_remaining); #ifdef CONFIG_RTC_CLASS /** * alarmtimer_suspend - Suspend time callback * @dev: unused * * When we are going into suspend, we look through the bases * to see which is the soonest timer to expire. We then * set an rtc timer to fire that far into the future, which * will wake us from suspend. */ static int alarmtimer_suspend(struct device *dev) { ktime_t min, now, expires; int i, ret, type; struct rtc_device *rtc; unsigned long flags; struct rtc_time tm; spin_lock_irqsave(&freezer_delta_lock, flags); min = freezer_delta; expires = freezer_expires; type = freezer_alarmtype; freezer_delta = 0; spin_unlock_irqrestore(&freezer_delta_lock, flags); rtc = alarmtimer_get_rtcdev(); /* If we have no rtcdev, just return */ if (!rtc) return 0; /* Find the soonest timer to expire*/ for (i = 0; i < ALARM_NUMTYPE; i++) { struct alarm_base *base = &alarm_bases[i]; struct timerqueue_node *next; ktime_t delta; spin_lock_irqsave(&base->lock, flags); next = timerqueue_getnext(&base->timerqueue); spin_unlock_irqrestore(&base->lock, flags); if (!next) continue; delta = ktime_sub(next->expires, base->get_ktime()); if (!min || (delta < min)) { expires = next->expires; min = delta; type = i; } } if (min == 0) return 0; if (ktime_to_ns(min) < 2 * NSEC_PER_SEC) { pm_wakeup_event(dev, 2 * MSEC_PER_SEC); return -EBUSY; } trace_alarmtimer_suspend(expires, type); /* Setup an rtc timer to fire that far in the future */ rtc_timer_cancel(rtc, &rtctimer); rtc_read_time(rtc, &tm); now = rtc_tm_to_ktime(tm); /* * If the RTC alarm timer only supports a limited time offset, set the * alarm time to the maximum supported value. * The system may wake up earlier (possibly much earlier) than expected * when the alarmtimer runs. This is the best the kernel can do if * the alarmtimer exceeds the time that the rtc device can be programmed * for. */ min = rtc_bound_alarmtime(rtc, min); now = ktime_add(now, min); /* Set alarm, if in the past reject suspend briefly to handle */ ret = rtc_timer_start(rtc, &rtctimer, now, 0); if (ret < 0) pm_wakeup_event(dev, MSEC_PER_SEC); return ret; } static int alarmtimer_resume(struct device *dev) { struct rtc_device *rtc; rtc = alarmtimer_get_rtcdev(); if (rtc) rtc_timer_cancel(rtc, &rtctimer); return 0; } #else static int alarmtimer_suspend(struct device *dev) { return 0; } static int alarmtimer_resume(struct device *dev) { return 0; } #endif static void __alarm_init(struct alarm *alarm, enum alarmtimer_type type, void (*function)(struct alarm *, ktime_t)) { timerqueue_init(&alarm->node); alarm->function = function; alarm->type = type; alarm->state = ALARMTIMER_STATE_INACTIVE; } /** * alarm_init - Initialize an alarm structure * @alarm: ptr to alarm to be initialized * @type: the type of the alarm * @function: callback that is run when the alarm fires */ void alarm_init(struct alarm *alarm, enum alarmtimer_type type, void (*function)(struct alarm *, ktime_t)) { hrtimer_setup(&alarm->timer, alarmtimer_fired, alarm_bases[type].base_clockid, HRTIMER_MODE_ABS); __alarm_init(alarm, type, function); } EXPORT_SYMBOL_GPL(alarm_init); /** * alarm_start - Sets an absolute alarm to fire * @alarm: ptr to alarm to set * @start: time to run the alarm */ void alarm_start(struct alarm *alarm, ktime_t start) { struct alarm_base *base = &alarm_bases[alarm->type]; unsigned long flags; spin_lock_irqsave(&base->lock, flags); alarm->node.expires = start; alarmtimer_enqueue(base, alarm); hrtimer_start(&alarm->timer, alarm->node.expires, HRTIMER_MODE_ABS); spin_unlock_irqrestore(&base->lock, flags); trace_alarmtimer_start(alarm, base->get_ktime()); } EXPORT_SYMBOL_GPL(alarm_start); /** * alarm_start_relative - Sets a relative alarm to fire * @alarm: ptr to alarm to set * @start: time relative to now to run the alarm */ void alarm_start_relative(struct alarm *alarm, ktime_t start) { struct alarm_base *base = &alarm_bases[alarm->type]; start = ktime_add_safe(start, base->get_ktime()); alarm_start(alarm, start); } EXPORT_SYMBOL_GPL(alarm_start_relative); void alarm_restart(struct alarm *alarm) { struct alarm_base *base = &alarm_bases[alarm->type]; unsigned long flags; spin_lock_irqsave(&base->lock, flags); hrtimer_set_expires(&alarm->timer, alarm->node.expires); hrtimer_restart(&alarm->timer); alarmtimer_enqueue(base, alarm); spin_unlock_irqrestore(&base->lock, flags); } EXPORT_SYMBOL_GPL(alarm_restart); /** * alarm_try_to_cancel - Tries to cancel an alarm timer * @alarm: ptr to alarm to be canceled * * Returns 1 if the timer was canceled, 0 if it was not running, * and -1 if the callback was running */ int alarm_try_to_cancel(struct alarm *alarm) { struct alarm_base *base = &alarm_bases[alarm->type]; unsigned long flags; int ret; spin_lock_irqsave(&base->lock, flags); ret = hrtimer_try_to_cancel(&alarm->timer); if (ret >= 0) alarmtimer_dequeue(base, alarm); spin_unlock_irqrestore(&base->lock, flags); trace_alarmtimer_cancel(alarm, base->get_ktime()); return ret; } EXPORT_SYMBOL_GPL(alarm_try_to_cancel); /** * alarm_cancel - Spins trying to cancel an alarm timer until it is done * @alarm: ptr to alarm to be canceled * * Returns 1 if the timer was canceled, 0 if it was not active. */ int alarm_cancel(struct alarm *alarm) { for (;;) { int ret = alarm_try_to_cancel(alarm); if (ret >= 0) return ret; hrtimer_cancel_wait_running(&alarm->timer); } } EXPORT_SYMBOL_GPL(alarm_cancel); u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) { u64 overrun = 1; ktime_t delta; delta = ktime_sub(now, alarm->node.expires); if (delta < 0) return 0; if (unlikely(delta >= interval)) { s64 incr = ktime_to_ns(interval); overrun = ktime_divns(delta, incr); alarm->node.expires = ktime_add_ns(alarm->node.expires, incr*overrun); if (alarm->node.expires > now) return overrun; /* * This (and the ktime_add() below) is the * correction for exact: */ overrun++; } alarm->node.expires = ktime_add_safe(alarm->node.expires, interval); return overrun; } EXPORT_SYMBOL_GPL(alarm_forward); u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) { struct alarm_base *base = &alarm_bases[alarm->type]; return alarm_forward(alarm, base->get_ktime(), interval); } EXPORT_SYMBOL_GPL(alarm_forward_now); #ifdef CONFIG_POSIX_TIMERS static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type) { struct alarm_base *base; unsigned long flags; ktime_t delta; switch(type) { case ALARM_REALTIME: base = &alarm_bases[ALARM_REALTIME]; type = ALARM_REALTIME_FREEZER; break; case ALARM_BOOTTIME: base = &alarm_bases[ALARM_BOOTTIME]; type = ALARM_BOOTTIME_FREEZER; break; default: WARN_ONCE(1, "Invalid alarm type: %d\n", type); return; } delta = ktime_sub(absexp, base->get_ktime()); spin_lock_irqsave(&freezer_delta_lock, flags); if (!freezer_delta || (delta < freezer_delta)) { freezer_delta = delta; freezer_expires = absexp; freezer_alarmtype = type; } spin_unlock_irqrestore(&freezer_delta_lock, flags); } /** * clock2alarm - helper that converts from clockid to alarmtypes * @clockid: clockid. */ static enum alarmtimer_type clock2alarm(clockid_t clockid) { if (clockid == CLOCK_REALTIME_ALARM) return ALARM_REALTIME; if (clockid == CLOCK_BOOTTIME_ALARM) return ALARM_BOOTTIME; return -1; } /** * alarm_handle_timer - Callback for posix timers * @alarm: alarm that fired * @now: time at the timer expiration * * Posix timer callback for expired alarm timers. * * Return: whether the timer is to be restarted */ static void alarm_handle_timer(struct alarm *alarm, ktime_t now) { struct k_itimer *ptr = container_of(alarm, struct k_itimer, it.alarm.alarmtimer); guard(spinlock_irqsave)(&ptr->it_lock); posix_timer_queue_signal(ptr); } /** * alarm_timer_rearm - Posix timer callback for rearming timer * @timr: Pointer to the posixtimer data struct */ static void alarm_timer_rearm(struct k_itimer *timr) { struct alarm *alarm = &timr->it.alarm.alarmtimer; timr->it_overrun += alarm_forward_now(alarm, timr->it_interval); alarm_start(alarm, alarm->node.expires); } /** * alarm_timer_forward - Posix timer callback for forwarding timer * @timr: Pointer to the posixtimer data struct * @now: Current time to forward the timer against */ static s64 alarm_timer_forward(struct k_itimer *timr, ktime_t now) { struct alarm *alarm = &timr->it.alarm.alarmtimer; return alarm_forward(alarm, timr->it_interval, now); } /** * alarm_timer_remaining - Posix timer callback to retrieve remaining time * @timr: Pointer to the posixtimer data struct * @now: Current time to calculate against */ static ktime_t alarm_timer_remaining(struct k_itimer *timr, ktime_t now) { struct alarm *alarm = &timr->it.alarm.alarmtimer; return ktime_sub(alarm->node.expires, now); } /** * alarm_timer_try_to_cancel - Posix timer callback to cancel a timer * @timr: Pointer to the posixtimer data struct */ static int alarm_timer_try_to_cancel(struct k_itimer *timr) { return alarm_try_to_cancel(&timr->it.alarm.alarmtimer); } /** * alarm_timer_wait_running - Posix timer callback to wait for a timer * @timr: Pointer to the posixtimer data struct * * Called from the core code when timer cancel detected that the callback * is running. @timr is unlocked and rcu read lock is held to prevent it * from being freed. */ static void alarm_timer_wait_running(struct k_itimer *timr) { hrtimer_cancel_wait_running(&timr->it.alarm.alarmtimer.timer); } /** * alarm_timer_arm - Posix timer callback to arm a timer * @timr: Pointer to the posixtimer data struct * @expires: The new expiry time * @absolute: Expiry value is absolute time * @sigev_none: Posix timer does not deliver signals */ static void alarm_timer_arm(struct k_itimer *timr, ktime_t expires, bool absolute, bool sigev_none) { struct alarm *alarm = &timr->it.alarm.alarmtimer; struct alarm_base *base = &alarm_bases[alarm->type]; if (!absolute) expires = ktime_add_safe(expires, base->get_ktime()); if (sigev_none) alarm->node.expires = expires; else alarm_start(&timr->it.alarm.alarmtimer, expires); } /** * alarm_clock_getres - posix getres interface * @which_clock: clockid * @tp: timespec to fill * * Returns the granularity of underlying alarm base clock */ static int alarm_clock_getres(const clockid_t which_clock, struct timespec64 *tp) { if (!alarmtimer_get_rtcdev()) return -EINVAL; tp->tv_sec = 0; tp->tv_nsec = hrtimer_resolution; return 0; } /** * alarm_clock_get_timespec - posix clock_get_timespec interface * @which_clock: clockid * @tp: timespec to fill. * * Provides the underlying alarm base time in a tasks time namespace. */ static int alarm_clock_get_timespec(clockid_t which_clock, struct timespec64 *tp) { struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)]; if (!alarmtimer_get_rtcdev()) return -EINVAL; base->get_timespec(tp); return 0; } /** * alarm_clock_get_ktime - posix clock_get_ktime interface * @which_clock: clockid * * Provides the underlying alarm base time in the root namespace. */ static ktime_t alarm_clock_get_ktime(clockid_t which_clock) { struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)]; if (!alarmtimer_get_rtcdev()) return -EINVAL; return base->get_ktime(); } /** * alarm_timer_create - posix timer_create interface * @new_timer: k_itimer pointer to manage * * Initializes the k_itimer structure. */ static int alarm_timer_create(struct k_itimer *new_timer) { enum alarmtimer_type type; if (!alarmtimer_get_rtcdev()) return -EOPNOTSUPP; if (!capable(CAP_WAKE_ALARM)) return -EPERM; type = clock2alarm(new_timer->it_clock); alarm_init(&new_timer->it.alarm.alarmtimer, type, alarm_handle_timer); return 0; } /** * alarmtimer_nsleep_wakeup - Wakeup function for alarm_timer_nsleep * @alarm: ptr to alarm that fired * @now: time at the timer expiration * * Wakes up the task that set the alarmtimer */ static void alarmtimer_nsleep_wakeup(struct alarm *alarm, ktime_t now) { struct task_struct *task = alarm->data; alarm->data = NULL; if (task) wake_up_process(task); } /** * alarmtimer_do_nsleep - Internal alarmtimer nsleep implementation * @alarm: ptr to alarmtimer * @absexp: absolute expiration time * @type: alarm type (BOOTTIME/REALTIME). * * Sets the alarm timer and sleeps until it is fired or interrupted. */ static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp, enum alarmtimer_type type) { struct restart_block *restart; alarm->data = (void *)current; do { set_current_state(TASK_INTERRUPTIBLE); alarm_start(alarm, absexp); if (likely(alarm->data)) schedule(); alarm_cancel(alarm); } while (alarm->data && !signal_pending(current)); __set_current_state(TASK_RUNNING); destroy_hrtimer_on_stack(&alarm->timer); if (!alarm->data) return 0; if (freezing(current)) alarmtimer_freezerset(absexp, type); restart = ¤t->restart_block; if (restart->nanosleep.type != TT_NONE) { struct timespec64 rmt; ktime_t rem; rem = ktime_sub(absexp, alarm_bases[type].get_ktime()); if (rem <= 0) return 0; rmt = ktime_to_timespec64(rem); return nanosleep_copyout(restart, &rmt); } return -ERESTART_RESTARTBLOCK; } static void alarm_init_on_stack(struct alarm *alarm, enum alarmtimer_type type, void (*function)(struct alarm *, ktime_t)) { hrtimer_setup_on_stack(&alarm->timer, alarmtimer_fired, alarm_bases[type].base_clockid, HRTIMER_MODE_ABS); __alarm_init(alarm, type, function); } /** * alarm_timer_nsleep_restart - restartblock alarmtimer nsleep * @restart: ptr to restart block * * Handles restarted clock_nanosleep calls */ static long __sched alarm_timer_nsleep_restart(struct restart_block *restart) { enum alarmtimer_type type = restart->nanosleep.clockid; ktime_t exp = restart->nanosleep.expires; struct alarm alarm; alarm_init_on_stack(&alarm, type, alarmtimer_nsleep_wakeup); return alarmtimer_do_nsleep(&alarm, exp, type); } /** * alarm_timer_nsleep - alarmtimer nanosleep * @which_clock: clockid * @flags: determines abstime or relative * @tsreq: requested sleep time (abs or rel) * * Handles clock_nanosleep calls against _ALARM clockids */ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, const struct timespec64 *tsreq) { enum alarmtimer_type type = clock2alarm(which_clock); struct restart_block *restart = ¤t->restart_block; struct alarm alarm; ktime_t exp; int ret; if (!alarmtimer_get_rtcdev()) return -EOPNOTSUPP; if (flags & ~TIMER_ABSTIME) return -EINVAL; if (!capable(CAP_WAKE_ALARM)) return -EPERM; alarm_init_on_stack(&alarm, type, alarmtimer_nsleep_wakeup); exp = timespec64_to_ktime(*tsreq); /* Convert (if necessary) to absolute time */ if (flags != TIMER_ABSTIME) { ktime_t now = alarm_bases[type].get_ktime(); exp = ktime_add_safe(now, exp); } else { exp = timens_ktime_to_host(which_clock, exp); } ret = alarmtimer_do_nsleep(&alarm, exp, type); if (ret != -ERESTART_RESTARTBLOCK) return ret; /* abs timers don't set remaining time or restart */ if (flags == TIMER_ABSTIME) return -ERESTARTNOHAND; restart->nanosleep.clockid = type; restart->nanosleep.expires = exp; set_restart_fn(restart, alarm_timer_nsleep_restart); return ret; } const struct k_clock alarm_clock = { .clock_getres = alarm_clock_getres, .clock_get_ktime = alarm_clock_get_ktime, .clock_get_timespec = alarm_clock_get_timespec, .timer_create = alarm_timer_create, .timer_set = common_timer_set, .timer_del = common_timer_del, .timer_get = common_timer_get, .timer_arm = alarm_timer_arm, .timer_rearm = alarm_timer_rearm, .timer_forward = alarm_timer_forward, .timer_remaining = alarm_timer_remaining, .timer_try_to_cancel = alarm_timer_try_to_cancel, .timer_wait_running = alarm_timer_wait_running, .nsleep = alarm_timer_nsleep, }; #endif /* CONFIG_POSIX_TIMERS */ /* Suspend hook structures */ static const struct dev_pm_ops alarmtimer_pm_ops = { .suspend = alarmtimer_suspend, .resume = alarmtimer_resume, }; static struct platform_driver alarmtimer_driver = { .driver = { .name = "alarmtimer", .pm = &alarmtimer_pm_ops, } }; static void get_boottime_timespec(struct timespec64 *tp) { ktime_get_boottime_ts64(tp); timens_add_boottime(tp); } /** * alarmtimer_init - Initialize alarm timer code * * This function initializes the alarm bases and registers * the posix clock ids. */ static int __init alarmtimer_init(void) { int error; int i; alarmtimer_rtc_timer_init(); /* Initialize alarm bases */ alarm_bases[ALARM_REALTIME].base_clockid = CLOCK_REALTIME; alarm_bases[ALARM_REALTIME].get_ktime = &ktime_get_real; alarm_bases[ALARM_REALTIME].get_timespec = ktime_get_real_ts64; alarm_bases[ALARM_BOOTTIME].base_clockid = CLOCK_BOOTTIME; alarm_bases[ALARM_BOOTTIME].get_ktime = &ktime_get_boottime; alarm_bases[ALARM_BOOTTIME].get_timespec = get_boottime_timespec; for (i = 0; i < ALARM_NUMTYPE; i++) { timerqueue_init_head(&alarm_bases[i].timerqueue); spin_lock_init(&alarm_bases[i].lock); } error = alarmtimer_rtc_interface_setup(); if (error) return error; error = platform_driver_register(&alarmtimer_driver); if (error) goto out_if; return 0; out_if: alarmtimer_rtc_interface_remove(); return error; } device_initcall(alarmtimer_init); |
| 72 72 53 3 3 2 2 84 14 69 2 1 3 69 84 12 69 3 3 3 87 90 3 87 87 87 87 90 3 87 81 6 6 5 6 6 84 54 30 30 30 30 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 1996-2000 Russell King. * * Scan ADFS partitions on hard disk drives. Unfortunately, there * isn't a standard for partitioning drives on Acorn machines, so * every single manufacturer of SCSI and IDE cards created their own * method. */ #include <linux/buffer_head.h> #include <linux/adfs_fs.h> #include "check.h" /* * Partition types. (Oh for reusability) */ #define PARTITION_RISCIX_MFM 1 #define PARTITION_RISCIX_SCSI 2 #define PARTITION_LINUX 9 #if defined(CONFIG_ACORN_PARTITION_CUMANA) || \ defined(CONFIG_ACORN_PARTITION_ADFS) static struct adfs_discrecord * adfs_partition(struct parsed_partitions *state, char *name, char *data, unsigned long first_sector, int slot) { struct adfs_discrecord *dr; unsigned int nr_sects; if (adfs_checkbblk(data)) return NULL; dr = (struct adfs_discrecord *)(data + 0x1c0); if (dr->disc_size == 0 && dr->disc_size_high == 0) return NULL; nr_sects = (le32_to_cpu(dr->disc_size_high) << 23) | (le32_to_cpu(dr->disc_size) >> 9); if (name) { strlcat(state->pp_buf, " [", PAGE_SIZE); strlcat(state->pp_buf, name, PAGE_SIZE); strlcat(state->pp_buf, "]", PAGE_SIZE); } put_partition(state, slot, first_sector, nr_sects); return dr; } #endif #ifdef CONFIG_ACORN_PARTITION_RISCIX struct riscix_part { __le32 start; __le32 length; __le32 one; char name[16]; }; struct riscix_record { __le32 magic; #define RISCIX_MAGIC cpu_to_le32(0x4a657320) __le32 date; struct riscix_part part[8]; }; #if defined(CONFIG_ACORN_PARTITION_CUMANA) || \ defined(CONFIG_ACORN_PARTITION_ADFS) static int riscix_partition(struct parsed_partitions *state, unsigned long first_sect, int slot, unsigned long nr_sects) { Sector sect; struct riscix_record *rr; rr = read_part_sector(state, first_sect, §); if (!rr) return -1; strlcat(state->pp_buf, " [RISCiX]", PAGE_SIZE); if (rr->magic == RISCIX_MAGIC) { unsigned long size = nr_sects > 2 ? 2 : nr_sects; int part; strlcat(state->pp_buf, " <", PAGE_SIZE); put_partition(state, slot++, first_sect, size); for (part = 0; part < 8; part++) { if (rr->part[part].one && memcmp(rr->part[part].name, "All\0", 4)) { put_partition(state, slot++, le32_to_cpu(rr->part[part].start), le32_to_cpu(rr->part[part].length)); strlcat(state->pp_buf, "(", PAGE_SIZE); strlcat(state->pp_buf, rr->part[part].name, PAGE_SIZE); strlcat(state->pp_buf, ")", PAGE_SIZE); } } strlcat(state->pp_buf, " >\n", PAGE_SIZE); } else { put_partition(state, slot++, first_sect, nr_sects); } put_dev_sector(sect); return slot; } #endif #endif #define LINUX_NATIVE_MAGIC 0xdeafa1de #define LINUX_SWAP_MAGIC 0xdeafab1e struct linux_part { __le32 magic; __le32 start_sect; __le32 nr_sects; }; #if defined(CONFIG_ACORN_PARTITION_CUMANA) || \ defined(CONFIG_ACORN_PARTITION_ADFS) static int linux_partition(struct parsed_partitions *state, unsigned long first_sect, int slot, unsigned long nr_sects) { Sector sect; struct linux_part *linuxp; unsigned long size = nr_sects > 2 ? 2 : nr_sects; strlcat(state->pp_buf, " [Linux]", PAGE_SIZE); put_partition(state, slot++, first_sect, size); linuxp = read_part_sector(state, first_sect, §); if (!linuxp) return -1; strlcat(state->pp_buf, " <", PAGE_SIZE); while (linuxp->magic == cpu_to_le32(LINUX_NATIVE_MAGIC) || linuxp->magic == cpu_to_le32(LINUX_SWAP_MAGIC)) { if (slot == state->limit) break; put_partition(state, slot++, first_sect + le32_to_cpu(linuxp->start_sect), le32_to_cpu(linuxp->nr_sects)); linuxp ++; } strlcat(state->pp_buf, " >", PAGE_SIZE); put_dev_sector(sect); return slot; } #endif #ifdef CONFIG_ACORN_PARTITION_CUMANA int adfspart_check_CUMANA(struct parsed_partitions *state) { unsigned long first_sector = 0; unsigned int start_blk = 0; Sector sect; unsigned char *data; char *name = "CUMANA/ADFS"; int first = 1; int slot = 1; /* * Try Cumana style partitions - sector 6 contains ADFS boot block * with pointer to next 'drive'. * * There are unknowns in this code - is the 'cylinder number' of the * next partition relative to the start of this one - I'm assuming * it is. * * Also, which ID did Cumana use? * * This is totally unfinished, and will require more work to get it * going. Hence it is totally untested. */ do { struct adfs_discrecord *dr; unsigned int nr_sects; data = read_part_sector(state, start_blk * 2 + 6, §); if (!data) return -1; if (slot == state->limit) break; dr = adfs_partition(state, name, data, first_sector, slot++); if (!dr) break; name = NULL; nr_sects = (data[0x1fd] + (data[0x1fe] << 8)) * (dr->heads + (dr->lowsector & 0x40 ? 1 : 0)) * dr->secspertrack; if (!nr_sects) break; first = 0; first_sector += nr_sects; start_blk += nr_sects >> (BLOCK_SIZE_BITS - 9); nr_sects = 0; /* hmm - should be partition size */ switch (data[0x1fc] & 15) { case 0: /* No partition / ADFS? */ break; #ifdef CONFIG_ACORN_PARTITION_RISCIX case PARTITION_RISCIX_SCSI: /* RISCiX - we don't know how to find the next one. */ slot = riscix_partition(state, first_sector, slot, nr_sects); break; #endif case PARTITION_LINUX: slot = linux_partition(state, first_sector, slot, nr_sects); break; } put_dev_sector(sect); if (slot == -1) return -1; } while (1); put_dev_sector(sect); return first ? 0 : 1; } #endif #ifdef CONFIG_ACORN_PARTITION_ADFS /* * Purpose: allocate ADFS partitions. * * Params : hd - pointer to gendisk structure to store partition info. * dev - device number to access. * * Returns: -1 on error, 0 for no ADFS boot sector, 1 for ok. * * Alloc : hda = whole drive * hda1 = ADFS partition on first drive. * hda2 = non-ADFS partition. */ int adfspart_check_ADFS(struct parsed_partitions *state) { unsigned long start_sect, nr_sects, sectscyl, heads; Sector sect; unsigned char *data; struct adfs_discrecord *dr; unsigned char id; int slot = 1; data = read_part_sector(state, 6, §); if (!data) return -1; dr = adfs_partition(state, "ADFS", data, 0, slot++); if (!dr) { put_dev_sector(sect); return 0; } heads = dr->heads + ((dr->lowsector >> 6) & 1); sectscyl = dr->secspertrack * heads; start_sect = ((data[0x1fe] << 8) + data[0x1fd]) * sectscyl; id = data[0x1fc] & 15; put_dev_sector(sect); /* * Work out start of non-adfs partition. */ nr_sects = get_capacity(state->disk) - start_sect; if (start_sect) { switch (id) { #ifdef CONFIG_ACORN_PARTITION_RISCIX case PARTITION_RISCIX_SCSI: case PARTITION_RISCIX_MFM: riscix_partition(state, start_sect, slot, nr_sects); break; #endif case PARTITION_LINUX: linux_partition(state, start_sect, slot, nr_sects); break; } } strlcat(state->pp_buf, "\n", PAGE_SIZE); return 1; } #endif #ifdef CONFIG_ACORN_PARTITION_ICS struct ics_part { __le32 start; __le32 size; }; static int adfspart_check_ICSLinux(struct parsed_partitions *state, unsigned long block) { Sector sect; unsigned char *data = read_part_sector(state, block, §); int result = 0; if (data) { if (memcmp(data, "LinuxPart", 9) == 0) result = 1; put_dev_sector(sect); } return result; } /* * Check for a valid ICS partition using the checksum. */ static inline int valid_ics_sector(const unsigned char *data) { unsigned long sum; int i; for (i = 0, sum = 0x50617274; i < 508; i++) sum += data[i]; sum -= le32_to_cpu(*(__le32 *)(&data[508])); return sum == 0; } /* * Purpose: allocate ICS partitions. * Params : hd - pointer to gendisk structure to store partition info. * dev - device number to access. * Returns: -1 on error, 0 for no ICS table, 1 for partitions ok. * Alloc : hda = whole drive * hda1 = ADFS partition 0 on first drive. * hda2 = ADFS partition 1 on first drive. * ..etc.. */ int adfspart_check_ICS(struct parsed_partitions *state) { const unsigned char *data; const struct ics_part *p; int slot; Sector sect; /* * Try ICS style partitions - sector 0 contains partition info. */ data = read_part_sector(state, 0, §); if (!data) return -1; if (!valid_ics_sector(data)) { put_dev_sector(sect); return 0; } strlcat(state->pp_buf, " [ICS]", PAGE_SIZE); for (slot = 1, p = (const struct ics_part *)data; p->size; p++) { u32 start = le32_to_cpu(p->start); s32 size = le32_to_cpu(p->size); /* yes, it's signed. */ if (slot == state->limit) break; /* * Negative sizes tell the RISC OS ICS driver to ignore * this partition - in effect it says that this does not * contain an ADFS filesystem. */ if (size < 0) { size = -size; /* * Our own extension - We use the first sector * of the partition to identify what type this * partition is. We must not make this visible * to the filesystem. */ if (size > 1 && adfspart_check_ICSLinux(state, start)) { start += 1; size -= 1; } } if (size) put_partition(state, slot++, start, size); } put_dev_sector(sect); strlcat(state->pp_buf, "\n", PAGE_SIZE); return 1; } #endif #ifdef CONFIG_ACORN_PARTITION_POWERTEC struct ptec_part { __le32 unused1; __le32 unused2; __le32 start; __le32 size; __le32 unused5; char type[8]; }; static inline int valid_ptec_sector(const unsigned char *data) { unsigned char checksum = 0x2a; int i; /* * If it looks like a PC/BIOS partition, then it * probably isn't PowerTec. */ if (data[510] == 0x55 && data[511] == 0xaa) return 0; for (i = 0; i < 511; i++) checksum += data[i]; return checksum == data[511]; } /* * Purpose: allocate ICS partitions. * Params : hd - pointer to gendisk structure to store partition info. * dev - device number to access. * Returns: -1 on error, 0 for no ICS table, 1 for partitions ok. * Alloc : hda = whole drive * hda1 = ADFS partition 0 on first drive. * hda2 = ADFS partition 1 on first drive. * ..etc.. */ int adfspart_check_POWERTEC(struct parsed_partitions *state) { Sector sect; const unsigned char *data; const struct ptec_part *p; int slot = 1; int i; data = read_part_sector(state, 0, §); if (!data) return -1; if (!valid_ptec_sector(data)) { put_dev_sector(sect); return 0; } strlcat(state->pp_buf, " [POWERTEC]", PAGE_SIZE); for (i = 0, p = (const struct ptec_part *)data; i < 12; i++, p++) { u32 start = le32_to_cpu(p->start); u32 size = le32_to_cpu(p->size); if (size) put_partition(state, slot++, start, size); } put_dev_sector(sect); strlcat(state->pp_buf, "\n", PAGE_SIZE); return 1; } #endif #ifdef CONFIG_ACORN_PARTITION_EESOX struct eesox_part { char magic[6]; char name[10]; __le32 start; __le32 unused6; __le32 unused7; __le32 unused8; }; /* * Guess who created this format? */ static const char eesox_name[] = { 'N', 'e', 'i', 'l', ' ', 'C', 'r', 'i', 't', 'c', 'h', 'e', 'l', 'l', ' ', ' ' }; /* * EESOX SCSI partition format. * * This is a goddamned awful partition format. We don't seem to store * the size of the partition in this table, only the start addresses. * * There are two possibilities where the size comes from: * 1. The individual ADFS boot block entries that are placed on the disk. * 2. The start address of the next entry. */ int adfspart_check_EESOX(struct parsed_partitions *state) { Sector sect; const unsigned char *data; unsigned char buffer[256]; struct eesox_part *p; sector_t start = 0; int i, slot = 1; data = read_part_sector(state, 7, §); if (!data) return -1; /* * "Decrypt" the partition table. God knows why... */ for (i = 0; i < 256; i++) buffer[i] = data[i] ^ eesox_name[i & 15]; put_dev_sector(sect); for (i = 0, p = (struct eesox_part *)buffer; i < 8; i++, p++) { sector_t next; if (memcmp(p->magic, "Eesox", 6)) break; next = le32_to_cpu(p->start); if (i) put_partition(state, slot++, start, next - start); start = next; } if (i != 0) { sector_t size; size = get_capacity(state->disk); put_partition(state, slot++, start, size - start); strlcat(state->pp_buf, "\n", PAGE_SIZE); } return i ? 1 : 0; } #endif |
| 2 4 4 2 14 14 19 19 19 19 5 5 5 14 17 8 3 7 7 7 2 8 8 5 14 7 8 7 2 5 7 8 3 5 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 | // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2010-2011 EIA Electronics, // Kurt Van Dijck <kurt.van.dijck@eia.be> // Copyright (c) 2017-2019 Pengutronix, // Marc Kleine-Budde <kernel@pengutronix.de> // Copyright (c) 2017-2019 Pengutronix, // Oleksij Rempel <kernel@pengutronix.de> /* bus for j1939 remote devices * Since rtnetlink, no real bus is used. */ #include <net/sock.h> #include "j1939-priv.h" static void __j1939_ecu_release(struct kref *kref) { struct j1939_ecu *ecu = container_of(kref, struct j1939_ecu, kref); struct j1939_priv *priv = ecu->priv; list_del(&ecu->list); kfree(ecu); j1939_priv_put(priv); } void j1939_ecu_put(struct j1939_ecu *ecu) { kref_put(&ecu->kref, __j1939_ecu_release); } static void j1939_ecu_get(struct j1939_ecu *ecu) { kref_get(&ecu->kref); } static bool j1939_ecu_is_mapped_locked(struct j1939_ecu *ecu) { struct j1939_priv *priv = ecu->priv; lockdep_assert_held(&priv->lock); return j1939_ecu_find_by_addr_locked(priv, ecu->addr) == ecu; } /* ECU device interface */ /* map ECU to a bus address space */ static void j1939_ecu_map_locked(struct j1939_ecu *ecu) { struct j1939_priv *priv = ecu->priv; struct j1939_addr_ent *ent; lockdep_assert_held(&priv->lock); if (!j1939_address_is_unicast(ecu->addr)) return; ent = &priv->ents[ecu->addr]; if (ent->ecu) { netdev_warn(priv->ndev, "Trying to map already mapped ECU, addr: 0x%02x, name: 0x%016llx. Skip it.\n", ecu->addr, ecu->name); return; } j1939_ecu_get(ecu); ent->ecu = ecu; ent->nusers += ecu->nusers; } /* unmap ECU from a bus address space */ void j1939_ecu_unmap_locked(struct j1939_ecu *ecu) { struct j1939_priv *priv = ecu->priv; struct j1939_addr_ent *ent; lockdep_assert_held(&priv->lock); if (!j1939_address_is_unicast(ecu->addr)) return; if (!j1939_ecu_is_mapped_locked(ecu)) return; ent = &priv->ents[ecu->addr]; ent->ecu = NULL; ent->nusers -= ecu->nusers; j1939_ecu_put(ecu); } void j1939_ecu_unmap(struct j1939_ecu *ecu) { write_lock_bh(&ecu->priv->lock); j1939_ecu_unmap_locked(ecu); write_unlock_bh(&ecu->priv->lock); } void j1939_ecu_unmap_all(struct j1939_priv *priv) { int i; write_lock_bh(&priv->lock); for (i = 0; i < ARRAY_SIZE(priv->ents); i++) if (priv->ents[i].ecu) j1939_ecu_unmap_locked(priv->ents[i].ecu); write_unlock_bh(&priv->lock); } void j1939_ecu_timer_start(struct j1939_ecu *ecu) { /* The ECU is held here and released in the * j1939_ecu_timer_handler() or j1939_ecu_timer_cancel(). */ j1939_ecu_get(ecu); /* Schedule timer in 250 msec to commit address change. */ hrtimer_start(&ecu->ac_timer, ms_to_ktime(250), HRTIMER_MODE_REL_SOFT); } void j1939_ecu_timer_cancel(struct j1939_ecu *ecu) { if (hrtimer_cancel(&ecu->ac_timer)) j1939_ecu_put(ecu); } static enum hrtimer_restart j1939_ecu_timer_handler(struct hrtimer *hrtimer) { struct j1939_ecu *ecu = container_of(hrtimer, struct j1939_ecu, ac_timer); struct j1939_priv *priv = ecu->priv; write_lock_bh(&priv->lock); /* TODO: can we test if ecu->addr is unicast before starting * the timer? */ j1939_ecu_map_locked(ecu); /* The corresponding j1939_ecu_get() is in * j1939_ecu_timer_start(). */ j1939_ecu_put(ecu); write_unlock_bh(&priv->lock); return HRTIMER_NORESTART; } struct j1939_ecu *j1939_ecu_create_locked(struct j1939_priv *priv, name_t name) { struct j1939_ecu *ecu; lockdep_assert_held(&priv->lock); ecu = kzalloc(sizeof(*ecu), gfp_any()); if (!ecu) return ERR_PTR(-ENOMEM); kref_init(&ecu->kref); ecu->addr = J1939_IDLE_ADDR; ecu->name = name; hrtimer_setup(&ecu->ac_timer, j1939_ecu_timer_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); INIT_LIST_HEAD(&ecu->list); j1939_priv_get(priv); ecu->priv = priv; list_add_tail(&ecu->list, &priv->ecus); return ecu; } struct j1939_ecu *j1939_ecu_find_by_addr_locked(struct j1939_priv *priv, u8 addr) { lockdep_assert_held(&priv->lock); return priv->ents[addr].ecu; } struct j1939_ecu *j1939_ecu_get_by_addr_locked(struct j1939_priv *priv, u8 addr) { struct j1939_ecu *ecu; lockdep_assert_held(&priv->lock); if (!j1939_address_is_unicast(addr)) return NULL; ecu = j1939_ecu_find_by_addr_locked(priv, addr); if (ecu) j1939_ecu_get(ecu); return ecu; } struct j1939_ecu *j1939_ecu_get_by_addr(struct j1939_priv *priv, u8 addr) { struct j1939_ecu *ecu; read_lock_bh(&priv->lock); ecu = j1939_ecu_get_by_addr_locked(priv, addr); read_unlock_bh(&priv->lock); return ecu; } /* get pointer to ecu without increasing ref counter */ static struct j1939_ecu *j1939_ecu_find_by_name_locked(struct j1939_priv *priv, name_t name) { struct j1939_ecu *ecu; lockdep_assert_held(&priv->lock); list_for_each_entry(ecu, &priv->ecus, list) { if (ecu->name == name) return ecu; } return NULL; } struct j1939_ecu *j1939_ecu_get_by_name_locked(struct j1939_priv *priv, name_t name) { struct j1939_ecu *ecu; lockdep_assert_held(&priv->lock); if (!name) return NULL; ecu = j1939_ecu_find_by_name_locked(priv, name); if (ecu) j1939_ecu_get(ecu); return ecu; } struct j1939_ecu *j1939_ecu_get_by_name(struct j1939_priv *priv, name_t name) { struct j1939_ecu *ecu; read_lock_bh(&priv->lock); ecu = j1939_ecu_get_by_name_locked(priv, name); read_unlock_bh(&priv->lock); return ecu; } u8 j1939_name_to_addr(struct j1939_priv *priv, name_t name) { struct j1939_ecu *ecu; int addr = J1939_IDLE_ADDR; if (!name) return J1939_NO_ADDR; read_lock_bh(&priv->lock); ecu = j1939_ecu_find_by_name_locked(priv, name); if (ecu && j1939_ecu_is_mapped_locked(ecu)) /* ecu's SA is registered */ addr = ecu->addr; read_unlock_bh(&priv->lock); return addr; } /* TX addr/name accounting * Transport protocol needs to know if a SA is local or not * These functions originate from userspace manipulating sockets, * so locking is straigforward */ int j1939_local_ecu_get(struct j1939_priv *priv, name_t name, u8 sa) { struct j1939_ecu *ecu; int err = 0; write_lock_bh(&priv->lock); if (j1939_address_is_unicast(sa)) priv->ents[sa].nusers++; if (!name) goto done; ecu = j1939_ecu_get_by_name_locked(priv, name); if (!ecu) ecu = j1939_ecu_create_locked(priv, name); err = PTR_ERR_OR_ZERO(ecu); if (err) goto done; ecu->nusers++; /* TODO: do we care if ecu->addr != sa? */ if (j1939_ecu_is_mapped_locked(ecu)) /* ecu's sa is active already */ priv->ents[ecu->addr].nusers++; done: write_unlock_bh(&priv->lock); return err; } void j1939_local_ecu_put(struct j1939_priv *priv, name_t name, u8 sa) { struct j1939_ecu *ecu; write_lock_bh(&priv->lock); if (j1939_address_is_unicast(sa)) priv->ents[sa].nusers--; if (!name) goto done; ecu = j1939_ecu_find_by_name_locked(priv, name); if (WARN_ON_ONCE(!ecu)) goto done; ecu->nusers--; /* TODO: do we care if ecu->addr != sa? */ if (j1939_ecu_is_mapped_locked(ecu)) /* ecu's sa is active already */ priv->ents[ecu->addr].nusers--; j1939_ecu_put(ecu); done: write_unlock_bh(&priv->lock); } |
| 12 14 12 12 12 12 10 10 10 10 10 10 10 10 10 10 10 63 63 63 62 63 11 52 52 11 62 62 62 62 2 2 64 14 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * hosts.c Copyright (C) 1992 Drew Eckhardt * Copyright (C) 1993, 1994, 1995 Eric Youngdale * Copyright (C) 2002-2003 Christoph Hellwig * * mid to lowlevel SCSI driver interface * Initial versions: Drew Eckhardt * Subsequent revisions: Eric Youngdale * * <drew@colorado.edu> * * Jiffies wrap fixes (host->resetting), 3 Dec 1998 Andrea Arcangeli * Added QLOGIC QLA1280 SCSI controller kernel host support. * August 4, 1999 Fred Lewis, Intel DuPont * * Updated to reflect the new initialization scheme for the higher * level of scsi drivers (sd/sr/st) * September 17, 2000 Torben Mathiasen <tmm@image.dk> * * Restructured scsi_host lists and associated functions. * September 04, 2002 Mike Anderson (andmike@us.ibm.com) */ #include <linux/module.h> #include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/kthread.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/completion.h> #include <linux/transport_class.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/idr.h> #include <scsi/scsi_device.h> #include <scsi/scsi_host.h> #include <scsi/scsi_transport.h> #include <scsi/scsi_cmnd.h> #include "scsi_priv.h" #include "scsi_logging.h" static int shost_eh_deadline = -1; module_param_named(eh_deadline, shost_eh_deadline, int, S_IRUGO|S_IWUSR); MODULE_PARM_DESC(eh_deadline, "SCSI EH timeout in seconds (should be between 0 and 2^31-1)"); static DEFINE_IDA(host_index_ida); static void scsi_host_cls_release(struct device *dev) { put_device(&class_to_shost(dev)->shost_gendev); } static struct class shost_class = { .name = "scsi_host", .dev_release = scsi_host_cls_release, .dev_groups = scsi_shost_groups, }; /** * scsi_host_set_state - Take the given host through the host state model. * @shost: scsi host to change the state of. * @state: state to change to. * * Returns zero if unsuccessful or an error if the requested * transition is illegal. **/ int scsi_host_set_state(struct Scsi_Host *shost, enum scsi_host_state state) { enum scsi_host_state oldstate = shost->shost_state; if (state == oldstate) return 0; switch (state) { case SHOST_CREATED: /* There are no legal states that come back to * created. This is the manually initialised start * state */ goto illegal; case SHOST_RUNNING: switch (oldstate) { case SHOST_CREATED: case SHOST_RECOVERY: break; default: goto illegal; } break; case SHOST_RECOVERY: switch (oldstate) { case SHOST_RUNNING: break; default: goto illegal; } break; case SHOST_CANCEL: switch (oldstate) { case SHOST_CREATED: case SHOST_RUNNING: case SHOST_CANCEL_RECOVERY: break; default: goto illegal; } break; case SHOST_DEL: switch (oldstate) { case SHOST_CANCEL: case SHOST_DEL_RECOVERY: break; default: goto illegal; } break; case SHOST_CANCEL_RECOVERY: switch (oldstate) { case SHOST_CANCEL: case SHOST_RECOVERY: break; default: goto illegal; } break; case SHOST_DEL_RECOVERY: switch (oldstate) { case SHOST_CANCEL_RECOVERY: break; default: goto illegal; } break; } shost->shost_state = state; return 0; illegal: SCSI_LOG_ERROR_RECOVERY(1, shost_printk(KERN_ERR, shost, "Illegal host state transition" "%s->%s\n", scsi_host_state_name(oldstate), scsi_host_state_name(state))); return -EINVAL; } /** * scsi_remove_host - remove a scsi host * @shost: a pointer to a scsi host to remove **/ void scsi_remove_host(struct Scsi_Host *shost) { unsigned long flags; mutex_lock(&shost->scan_mutex); spin_lock_irqsave(shost->host_lock, flags); if (scsi_host_set_state(shost, SHOST_CANCEL)) if (scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY)) { spin_unlock_irqrestore(shost->host_lock, flags); mutex_unlock(&shost->scan_mutex); return; } spin_unlock_irqrestore(shost->host_lock, flags); scsi_autopm_get_host(shost); flush_workqueue(shost->tmf_work_q); scsi_forget_host(shost); mutex_unlock(&shost->scan_mutex); scsi_proc_host_rm(shost); scsi_proc_hostdir_rm(shost->hostt); /* * New SCSI devices cannot be attached anymore because of the SCSI host * state so drop the tag set refcnt. Wait until the tag set refcnt drops * to zero because .exit_cmd_priv implementations may need the host * pointer. */ kref_put(&shost->tagset_refcnt, scsi_mq_free_tags); wait_for_completion(&shost->tagset_freed); spin_lock_irqsave(shost->host_lock, flags); if (scsi_host_set_state(shost, SHOST_DEL)) BUG_ON(scsi_host_set_state(shost, SHOST_DEL_RECOVERY)); spin_unlock_irqrestore(shost->host_lock, flags); transport_unregister_device(&shost->shost_gendev); device_unregister(&shost->shost_dev); device_del(&shost->shost_gendev); } EXPORT_SYMBOL(scsi_remove_host); /** * scsi_add_host_with_dma - add a scsi host with dma device * @shost: scsi host pointer to add * @dev: a struct device of type scsi class * @dma_dev: dma device for the host * * Note: You rarely need to worry about this unless you're in a * virtualised host environments, so use the simpler scsi_add_host() * function instead. * * Return value: * 0 on success / != 0 for error **/ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev, struct device *dma_dev) { const struct scsi_host_template *sht = shost->hostt; int error = -EINVAL; shost_printk(KERN_INFO, shost, "%s\n", sht->info ? sht->info(shost) : sht->name); if (!shost->can_queue) { shost_printk(KERN_ERR, shost, "can_queue = 0 no longer supported\n"); goto fail; } /* Use min_t(int, ...) in case shost->can_queue exceeds SHRT_MAX */ shost->cmd_per_lun = min_t(int, shost->cmd_per_lun, shost->can_queue); error = scsi_init_sense_cache(shost); if (error) goto fail; if (!shost->shost_gendev.parent) shost->shost_gendev.parent = dev ? dev : &platform_bus; if (!dma_dev) dma_dev = shost->shost_gendev.parent; shost->dma_dev = dma_dev; if (dma_dev->dma_mask) { shost->max_sectors = min_t(unsigned int, shost->max_sectors, dma_max_mapping_size(dma_dev) >> SECTOR_SHIFT); } error = scsi_mq_setup_tags(shost); if (error) goto fail; kref_init(&shost->tagset_refcnt); init_completion(&shost->tagset_freed); /* * Increase usage count temporarily here so that calling * scsi_autopm_put_host() will trigger runtime idle if there is * nothing else preventing suspending the device. */ pm_runtime_get_noresume(&shost->shost_gendev); pm_runtime_set_active(&shost->shost_gendev); pm_runtime_enable(&shost->shost_gendev); device_enable_async_suspend(&shost->shost_gendev); error = device_add(&shost->shost_gendev); if (error) goto out_disable_runtime_pm; scsi_host_set_state(shost, SHOST_RUNNING); get_device(shost->shost_gendev.parent); device_enable_async_suspend(&shost->shost_dev); get_device(&shost->shost_gendev); error = device_add(&shost->shost_dev); if (error) goto out_del_gendev; if (shost->transportt->host_size) { shost->shost_data = kzalloc(shost->transportt->host_size, GFP_KERNEL); if (shost->shost_data == NULL) { error = -ENOMEM; goto out_del_dev; } } if (shost->transportt->create_work_queue) { shost->work_q = alloc_workqueue( "scsi_wq_%d", WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_UNBOUND, 1, shost->host_no); if (!shost->work_q) { error = -EINVAL; goto out_del_dev; } } error = scsi_sysfs_add_host(shost); if (error) goto out_del_dev; scsi_proc_host_add(shost); scsi_autopm_put_host(shost); return error; /* * Any host allocation in this function will be freed in * scsi_host_dev_release(). */ out_del_dev: device_del(&shost->shost_dev); out_del_gendev: /* * Host state is SHOST_RUNNING so we have to explicitly release * ->shost_dev. */ put_device(&shost->shost_dev); device_del(&shost->shost_gendev); out_disable_runtime_pm: device_disable_async_suspend(&shost->shost_gendev); pm_runtime_disable(&shost->shost_gendev); pm_runtime_set_suspended(&shost->shost_gendev); pm_runtime_put_noidle(&shost->shost_gendev); kref_put(&shost->tagset_refcnt, scsi_mq_free_tags); fail: return error; } EXPORT_SYMBOL(scsi_add_host_with_dma); static void scsi_host_dev_release(struct device *dev) { struct Scsi_Host *shost = dev_to_shost(dev); struct device *parent = dev->parent; /* Wait for functions invoked through call_rcu(&scmd->rcu, ...) */ rcu_barrier(); if (shost->tmf_work_q) destroy_workqueue(shost->tmf_work_q); if (shost->ehandler) kthread_stop(shost->ehandler); if (shost->work_q) destroy_workqueue(shost->work_q); if (shost->shost_state == SHOST_CREATED) { /* * Free the shost_dev device name and remove the proc host dir * here if scsi_host_{alloc,put}() have been called but neither * scsi_host_add() nor scsi_remove_host() has been called. * This avoids that the memory allocated for the shost_dev * name as well as the proc dir structure are leaked. */ scsi_proc_hostdir_rm(shost->hostt); kfree(dev_name(&shost->shost_dev)); } kfree(shost->shost_data); ida_free(&host_index_ida, shost->host_no); if (shost->shost_state != SHOST_CREATED) put_device(parent); kfree(shost); } static const struct device_type scsi_host_type = { .name = "scsi_host", .release = scsi_host_dev_release, }; /** * scsi_host_alloc - register a scsi host adapter instance. * @sht: pointer to scsi host template * @privsize: extra bytes to allocate for driver * * Note: * Allocate a new Scsi_Host and perform basic initialization. * The host is not published to the scsi midlayer until scsi_add_host * is called. * * Return value: * Pointer to a new Scsi_Host **/ struct Scsi_Host *scsi_host_alloc(const struct scsi_host_template *sht, int privsize) { struct Scsi_Host *shost; int index; shost = kzalloc(sizeof(struct Scsi_Host) + privsize, GFP_KERNEL); if (!shost) return NULL; shost->host_lock = &shost->default_lock; spin_lock_init(shost->host_lock); shost->shost_state = SHOST_CREATED; INIT_LIST_HEAD(&shost->__devices); INIT_LIST_HEAD(&shost->__targets); INIT_LIST_HEAD(&shost->eh_abort_list); INIT_LIST_HEAD(&shost->eh_cmd_q); INIT_LIST_HEAD(&shost->starved_list); init_waitqueue_head(&shost->host_wait); mutex_init(&shost->scan_mutex); index = ida_alloc(&host_index_ida, GFP_KERNEL); if (index < 0) { kfree(shost); return NULL; } shost->host_no = index; shost->dma_channel = 0xff; /* These three are default values which can be overridden */ shost->max_channel = 0; shost->max_id = 8; shost->max_lun = 8; /* Give each shost a default transportt */ shost->transportt = &blank_transport_template; /* * All drivers right now should be able to handle 12 byte * commands. Every so often there are requests for 16 byte * commands, but individual low-level drivers need to certify that * they actually do something sensible with such commands. */ shost->max_cmd_len = 12; shost->hostt = sht; shost->this_id = sht->this_id; shost->can_queue = sht->can_queue; shost->sg_tablesize = sht->sg_tablesize; shost->sg_prot_tablesize = sht->sg_prot_tablesize; shost->cmd_per_lun = sht->cmd_per_lun; shost->no_write_same = sht->no_write_same; shost->host_tagset = sht->host_tagset; shost->queuecommand_may_block = sht->queuecommand_may_block; if (shost_eh_deadline == -1 || !sht->eh_host_reset_handler) shost->eh_deadline = -1; else if ((ulong) shost_eh_deadline * HZ > INT_MAX) { shost_printk(KERN_WARNING, shost, "eh_deadline %u too large, setting to %u\n", shost_eh_deadline, INT_MAX / HZ); shost->eh_deadline = INT_MAX; } else shost->eh_deadline = shost_eh_deadline * HZ; if (sht->supported_mode == MODE_UNKNOWN) /* means we didn't set it ... default to INITIATOR */ shost->active_mode = MODE_INITIATOR; else shost->active_mode = sht->supported_mode; if (sht->max_host_blocked) shost->max_host_blocked = sht->max_host_blocked; else shost->max_host_blocked = SCSI_DEFAULT_HOST_BLOCKED; /* * If the driver imposes no hard sector transfer limit, start at * machine infinity initially. */ if (sht->max_sectors) shost->max_sectors = sht->max_sectors; else shost->max_sectors = SCSI_DEFAULT_MAX_SECTORS; if (sht->max_segment_size) shost->max_segment_size = sht->max_segment_size; else shost->max_segment_size = BLK_MAX_SEGMENT_SIZE; /* 32-byte (dword) is a common minimum for HBAs. */ if (sht->dma_alignment) shost->dma_alignment = sht->dma_alignment; else shost->dma_alignment = 3; /* * assume a 4GB boundary, if not set */ if (sht->dma_boundary) shost->dma_boundary = sht->dma_boundary; else shost->dma_boundary = 0xffffffff; if (sht->virt_boundary_mask) shost->virt_boundary_mask = sht->virt_boundary_mask; device_initialize(&shost->shost_gendev); dev_set_name(&shost->shost_gendev, "host%d", shost->host_no); shost->shost_gendev.bus = &scsi_bus_type; shost->shost_gendev.type = &scsi_host_type; scsi_enable_async_suspend(&shost->shost_gendev); device_initialize(&shost->shost_dev); shost->shost_dev.parent = &shost->shost_gendev; shost->shost_dev.class = &shost_class; dev_set_name(&shost->shost_dev, "host%d", shost->host_no); shost->shost_dev.groups = sht->shost_groups; shost->ehandler = kthread_run(scsi_error_handler, shost, "scsi_eh_%d", shost->host_no); if (IS_ERR(shost->ehandler)) { shost_printk(KERN_WARNING, shost, "error handler thread failed to spawn, error = %ld\n", PTR_ERR(shost->ehandler)); shost->ehandler = NULL; goto fail; } shost->tmf_work_q = alloc_workqueue("scsi_tmf_%d", WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 1, shost->host_no); if (!shost->tmf_work_q) { shost_printk(KERN_WARNING, shost, "failed to create tmf workq\n"); goto fail; } if (scsi_proc_hostdir_add(shost->hostt) < 0) goto fail; return shost; fail: /* * Host state is still SHOST_CREATED and that is enough to release * ->shost_gendev. scsi_host_dev_release() will free * dev_name(&shost->shost_dev). */ put_device(&shost->shost_gendev); return NULL; } EXPORT_SYMBOL(scsi_host_alloc); static int __scsi_host_match(struct device *dev, const void *data) { struct Scsi_Host *p; const unsigned int *hostnum = data; p = class_to_shost(dev); return p->host_no == *hostnum; } /** * scsi_host_lookup - get a reference to a Scsi_Host by host no * @hostnum: host number to locate * * Return value: * A pointer to located Scsi_Host or NULL. * * The caller must do a scsi_host_put() to drop the reference * that scsi_host_get() took. The put_device() below dropped * the reference from class_find_device(). **/ struct Scsi_Host *scsi_host_lookup(unsigned int hostnum) { struct device *cdev; struct Scsi_Host *shost = NULL; cdev = class_find_device(&shost_class, NULL, &hostnum, __scsi_host_match); if (cdev) { shost = scsi_host_get(class_to_shost(cdev)); put_device(cdev); } return shost; } EXPORT_SYMBOL(scsi_host_lookup); /** * scsi_host_get - inc a Scsi_Host ref count * @shost: Pointer to Scsi_Host to inc. **/ struct Scsi_Host *scsi_host_get(struct Scsi_Host *shost) { if ((shost->shost_state == SHOST_DEL) || !get_device(&shost->shost_gendev)) return NULL; return shost; } EXPORT_SYMBOL(scsi_host_get); static bool scsi_host_check_in_flight(struct request *rq, void *data) { int *count = data; struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq); if (test_bit(SCMD_STATE_INFLIGHT, &cmd->state)) (*count)++; return true; } /** * scsi_host_busy - Return the host busy counter * @shost: Pointer to Scsi_Host to inc. **/ int scsi_host_busy(struct Scsi_Host *shost) { int cnt = 0; blk_mq_tagset_busy_iter(&shost->tag_set, scsi_host_check_in_flight, &cnt); return cnt; } EXPORT_SYMBOL(scsi_host_busy); /** * scsi_host_put - dec a Scsi_Host ref count * @shost: Pointer to Scsi_Host to dec. **/ void scsi_host_put(struct Scsi_Host *shost) { put_device(&shost->shost_gendev); } EXPORT_SYMBOL(scsi_host_put); int scsi_init_hosts(void) { return class_register(&shost_class); } void scsi_exit_hosts(void) { class_unregister(&shost_class); ida_destroy(&host_index_ida); } int scsi_is_host_device(const struct device *dev) { return dev->type == &scsi_host_type; } EXPORT_SYMBOL(scsi_is_host_device); /** * scsi_queue_work - Queue work to the Scsi_Host workqueue. * @shost: Pointer to Scsi_Host. * @work: Work to queue for execution. * * Return value: * 1 - work queued for execution * 0 - work is already queued * -EINVAL - work queue doesn't exist **/ int scsi_queue_work(struct Scsi_Host *shost, struct work_struct *work) { if (unlikely(!shost->work_q)) { shost_printk(KERN_ERR, shost, "ERROR: Scsi host '%s' attempted to queue scsi-work, " "when no workqueue created.\n", shost->hostt->name); dump_stack(); return -EINVAL; } return queue_work(shost->work_q, work); } EXPORT_SYMBOL_GPL(scsi_queue_work); /** * scsi_flush_work - Flush a Scsi_Host's workqueue. * @shost: Pointer to Scsi_Host. **/ void scsi_flush_work(struct Scsi_Host *shost) { if (!shost->work_q) { shost_printk(KERN_ERR, shost, "ERROR: Scsi host '%s' attempted to flush scsi-work, " "when no workqueue created.\n", shost->hostt->name); dump_stack(); return; } flush_workqueue(shost->work_q); } EXPORT_SYMBOL_GPL(scsi_flush_work); static bool complete_all_cmds_iter(struct request *rq, void *data) { struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(rq); enum scsi_host_status status = *(enum scsi_host_status *)data; scsi_dma_unmap(scmd); scmd->result = 0; set_host_byte(scmd, status); scsi_done(scmd); return true; } /** * scsi_host_complete_all_commands - Terminate all running commands * @shost: Scsi Host on which commands should be terminated * @status: Status to be set for the terminated commands * * There is no protection against modification of the number * of outstanding commands. It is the responsibility of the * caller to ensure that concurrent I/O submission and/or * completion is stopped when calling this function. */ void scsi_host_complete_all_commands(struct Scsi_Host *shost, enum scsi_host_status status) { blk_mq_tagset_busy_iter(&shost->tag_set, complete_all_cmds_iter, &status); } EXPORT_SYMBOL_GPL(scsi_host_complete_all_commands); struct scsi_host_busy_iter_data { bool (*fn)(struct scsi_cmnd *, void *); void *priv; }; static bool __scsi_host_busy_iter_fn(struct request *req, void *priv) { struct scsi_host_busy_iter_data *iter_data = priv; struct scsi_cmnd *sc = blk_mq_rq_to_pdu(req); return iter_data->fn(sc, iter_data->priv); } /** * scsi_host_busy_iter - Iterate over all busy commands * @shost: Pointer to Scsi_Host. * @fn: Function to call on each busy command * @priv: Data pointer passed to @fn * * If locking against concurrent command completions is required * ithas to be provided by the caller **/ void scsi_host_busy_iter(struct Scsi_Host *shost, bool (*fn)(struct scsi_cmnd *, void *), void *priv) { struct scsi_host_busy_iter_data iter_data = { .fn = fn, .priv = priv, }; blk_mq_tagset_busy_iter(&shost->tag_set, __scsi_host_busy_iter_fn, &iter_data); } EXPORT_SYMBOL_GPL(scsi_host_busy_iter); |
| 276 277 276 125 121 10 9 9 121 4 3 85 26 103 2 115 114 88 9 79 5 115 114 15 98 16 1 15 38 37 36 1 1 37 37 37 37 37 153 38 126 180 180 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 | // 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 INET6 transport hashtables * * Authors: Lotsa people, from code originally in tcp, generalised here * by Arnaldo Carvalho de Melo <acme@mandriva.com> */ #include <linux/module.h> #include <linux/random.h> #include <net/addrconf.h> #include <net/hotdata.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> #include <net/secure_seq.h> #include <net/ip.h> #include <net/sock_reuseport.h> #include <net/tcp.h> u32 inet6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, const struct in6_addr *faddr, const __be16 fport) { u32 lhash, fhash; net_get_random_once(&inet6_ehash_secret, sizeof(inet6_ehash_secret)); net_get_random_once(&tcp_ipv6_hash_secret, sizeof(tcp_ipv6_hash_secret)); lhash = (__force u32)laddr->s6_addr32[3]; fhash = __ipv6_addr_jhash(faddr, tcp_ipv6_hash_secret); return lport + __inet6_ehashfn(lhash, 0, fhash, fport, inet6_ehash_secret + net_hash_mix(net)); } EXPORT_SYMBOL_GPL(inet6_ehashfn); /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM * * The sockhash lock must be held as a reader here. */ struct sock *__inet6_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, const int sdif) { struct sock *sk; const struct hlist_nulls_node *node; const __portpair ports = INET_COMBINED_PORTS(sport, hnum); /* Optimize here for direct hit, only listening connections can * have wildcards anyways. */ unsigned int hash = inet6_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 (!inet6_match(net, sk, saddr, daddr, ports, dif, sdif)) continue; if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) goto out; if (unlikely(!inet6_match(net, sk, saddr, daddr, ports, dif, sdif))) { sock_gen_put(sk); goto begin; } goto found; } if (get_nulls_value(node) != slot) goto begin; out: sk = NULL; found: return sk; } EXPORT_SYMBOL(__inet6_lookup_established); static inline int compute_score(struct sock *sk, const struct net *net, const unsigned short hnum, const struct in6_addr *daddr, const int dif, const int sdif) { int score = -1; if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum && sk->sk_family == PF_INET6) { if (!ipv6_addr_equal(&sk->sk_v6_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 (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; } return score; } /** * inet6_lookup_reuseport() - execute reuseport logic on AF_INET6 socket if necessary. * @net: network namespace. * @sk: AF_INET6 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 *inet6_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned short hnum, inet6_ehashfn_t *ehashfn) { struct sock *reuse_sk = NULL; u32 phash; if (sk->sk_reuseport) { phash = INDIRECT_CALL_INET(ehashfn, udp6_ehashfn, inet6_ehashfn, net, daddr, hnum, saddr, sport); reuse_sk = reuseport_select_sock(sk, phash, skb, doff); } return reuse_sk; } EXPORT_SYMBOL_GPL(inet6_lookup_reuseport); /* called with rcu_read_lock() */ static struct sock *inet6_lhash2_lookup(const struct net *net, struct inet_listen_hashbucket *ilb2, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *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 = inet6_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum, inet6_ehashfn); if (result) return result; result = sk; hiscore = score; } } return result; } struct sock *inet6_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, inet6_ehashfn_t *ehashfn) { struct sock *sk, *reuse_sk; bool no_reuseport; no_reuseport = bpf_sk_lookup_run_v6(net, protocol, saddr, sport, daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum, ehashfn); if (reuse_sk) sk = reuse_sk; return sk; } EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup); struct sock *inet6_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *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 = inet6_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff, saddr, sport, daddr, hnum, dif, inet6_ehashfn); if (result) goto done; } hash2 = ipv6_portaddr_hash(net, daddr, hnum); ilb2 = inet_lhash2_bucket(hashinfo, hash2); result = inet6_lhash2_lookup(net, ilb2, skb, doff, saddr, sport, daddr, hnum, dif, sdif); if (result) goto done; /* Lookup lhash2 with in6addr_any */ hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum); ilb2 = inet_lhash2_bucket(hashinfo, hash2); result = inet6_lhash2_lookup(net, ilb2, skb, doff, saddr, sport, &in6addr_any, hnum, dif, sdif); done: if (IS_ERR(result)) return NULL; return result; } EXPORT_SYMBOL_GPL(inet6_lookup_listener); struct sock *inet6_lookup(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, const int dif) { struct sock *sk; bool refcounted; sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr, ntohs(dport), dif, 0, &refcounted); if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } EXPORT_SYMBOL_GPL(inet6_lookup); static int __inet6_check_established(struct inet_timewait_death_row *death_row, struct sock *sk, const __u16 lport, struct inet_timewait_sock **twp, bool rcu_lookup, u32 hash) { struct inet_hashinfo *hinfo = death_row->hashinfo; struct inet_sock *inet = inet_sk(sk); const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr; const struct in6_addr *saddr = &sk->sk_v6_daddr; const int dif = sk->sk_bound_dev_if; struct net *net = sock_net(sk); const int sdif = l3mdev_master_ifindex_by_index(net, dif); const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); struct inet_timewait_sock *tw = NULL; const struct hlist_nulls_node *node; struct sock *sk2; spinlock_t *lock; if (rcu_lookup) { sk_nulls_for_each(sk2, node, &head->chain) { if (sk2->sk_hash != hash || !inet6_match(net, sk2, saddr, daddr, ports, dif, sdif)) continue; if (sk2->sk_state == TCP_TIME_WAIT) break; return -EADDRNOTAVAIL; } return 0; } lock = inet_ehash_lockp(hinfo, hash); spin_lock(lock); sk_nulls_for_each(sk2, node, &head->chain) { if (sk2->sk_hash != hash) continue; if (likely(inet6_match(net, sk2, saddr, daddr, 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 inet6_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); return secure_ipv6_port_ephemeral(sk->sk_v6_rcv_saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32, inet->inet_dport); } int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr; const struct in6_addr *saddr = &sk->sk_v6_daddr; const struct inet_sock *inet = inet_sk(sk); const struct net *net = sock_net(sk); u64 port_offset = 0; u32 hash_port0; if (!inet_sk(sk)->inet_num) port_offset = inet6_sk_port_offset(sk); hash_port0 = inet6_ehashfn(net, daddr, 0, saddr, inet->inet_dport); return __inet_hash_connect(death_row, sk, port_offset, hash_port0, __inet6_check_established); } EXPORT_SYMBOL_GPL(inet6_hash_connect); int inet6_hash(struct sock *sk) { int err = 0; if (sk->sk_state != TCP_CLOSE) err = __inet_hash(sk, NULL); return err; } EXPORT_SYMBOL_GPL(inet6_hash); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __KVM_FPU_H_ #define __KVM_FPU_H_ #include <asm/fpu/api.h> typedef u32 __attribute__((vector_size(16))) sse128_t; #define __sse128_u union { sse128_t vec; u64 as_u64[2]; u32 as_u32[4]; } #define sse128_lo(x) ({ __sse128_u t; t.vec = x; t.as_u64[0]; }) #define sse128_hi(x) ({ __sse128_u t; t.vec = x; t.as_u64[1]; }) #define sse128_l0(x) ({ __sse128_u t; t.vec = x; t.as_u32[0]; }) #define sse128_l1(x) ({ __sse128_u t; t.vec = x; t.as_u32[1]; }) #define sse128_l2(x) ({ __sse128_u t; t.vec = x; t.as_u32[2]; }) #define sse128_l3(x) ({ __sse128_u t; t.vec = x; t.as_u32[3]; }) #define sse128(lo, hi) ({ __sse128_u t; t.as_u64[0] = lo; t.as_u64[1] = hi; t.vec; }) static inline void _kvm_read_sse_reg(int reg, sse128_t *data) { switch (reg) { case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break; case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break; case 2: asm("movdqa %%xmm2, %0" : "=m"(*data)); break; case 3: asm("movdqa %%xmm3, %0" : "=m"(*data)); break; case 4: asm("movdqa %%xmm4, %0" : "=m"(*data)); break; case 5: asm("movdqa %%xmm5, %0" : "=m"(*data)); break; case 6: asm("movdqa %%xmm6, %0" : "=m"(*data)); break; case 7: asm("movdqa %%xmm7, %0" : "=m"(*data)); break; #ifdef CONFIG_X86_64 case 8: asm("movdqa %%xmm8, %0" : "=m"(*data)); break; case 9: asm("movdqa %%xmm9, %0" : "=m"(*data)); break; case 10: asm("movdqa %%xmm10, %0" : "=m"(*data)); break; case 11: asm("movdqa %%xmm11, %0" : "=m"(*data)); break; case 12: asm("movdqa %%xmm12, %0" : "=m"(*data)); break; case 13: asm("movdqa %%xmm13, %0" : "=m"(*data)); break; case 14: asm("movdqa %%xmm14, %0" : "=m"(*data)); break; case 15: asm("movdqa %%xmm15, %0" : "=m"(*data)); break; #endif default: BUG(); } } static inline void _kvm_write_sse_reg(int reg, const sse128_t *data) { switch (reg) { case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break; case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break; case 2: asm("movdqa %0, %%xmm2" : : "m"(*data)); break; case 3: asm("movdqa %0, %%xmm3" : : "m"(*data)); break; case 4: asm("movdqa %0, %%xmm4" : : "m"(*data)); break; case 5: asm("movdqa %0, %%xmm5" : : "m"(*data)); break; case 6: asm("movdqa %0, %%xmm6" : : "m"(*data)); break; case 7: asm("movdqa %0, %%xmm7" : : "m"(*data)); break; #ifdef CONFIG_X86_64 case 8: asm("movdqa %0, %%xmm8" : : "m"(*data)); break; case 9: asm("movdqa %0, %%xmm9" : : "m"(*data)); break; case 10: asm("movdqa %0, %%xmm10" : : "m"(*data)); break; case 11: asm("movdqa %0, %%xmm11" : : "m"(*data)); break; case 12: asm("movdqa %0, %%xmm12" : : "m"(*data)); break; case 13: asm("movdqa %0, %%xmm13" : : "m"(*data)); break; case 14: asm("movdqa %0, %%xmm14" : : "m"(*data)); break; case 15: asm("movdqa %0, %%xmm15" : : "m"(*data)); break; #endif default: BUG(); } } static inline void _kvm_read_mmx_reg(int reg, u64 *data) { switch (reg) { case 0: asm("movq %%mm0, %0" : "=m"(*data)); break; case 1: asm("movq %%mm1, %0" : "=m"(*data)); break; case 2: asm("movq %%mm2, %0" : "=m"(*data)); break; case 3: asm("movq %%mm3, %0" : "=m"(*data)); break; case 4: asm("movq %%mm4, %0" : "=m"(*data)); break; case 5: asm("movq %%mm5, %0" : "=m"(*data)); break; case 6: asm("movq %%mm6, %0" : "=m"(*data)); break; case 7: asm("movq %%mm7, %0" : "=m"(*data)); break; default: BUG(); } } static inline void _kvm_write_mmx_reg(int reg, const u64 *data) { switch (reg) { case 0: asm("movq %0, %%mm0" : : "m"(*data)); break; case 1: asm("movq %0, %%mm1" : : "m"(*data)); break; case 2: asm("movq %0, %%mm2" : : "m"(*data)); break; case 3: asm("movq %0, %%mm3" : : "m"(*data)); break; case 4: asm("movq %0, %%mm4" : : "m"(*data)); break; case 5: asm("movq %0, %%mm5" : : "m"(*data)); break; case 6: asm("movq %0, %%mm6" : : "m"(*data)); break; case 7: asm("movq %0, %%mm7" : : "m"(*data)); break; default: BUG(); } } static inline void kvm_fpu_get(void) { fpregs_lock(); fpregs_assert_state_consistent(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) switch_fpu_return(); } static inline void kvm_fpu_put(void) { fpregs_unlock(); } static inline void kvm_read_sse_reg(int reg, sse128_t *data) { kvm_fpu_get(); _kvm_read_sse_reg(reg, data); kvm_fpu_put(); } static inline void kvm_write_sse_reg(int reg, const sse128_t *data) { kvm_fpu_get(); _kvm_write_sse_reg(reg, data); kvm_fpu_put(); } static inline void kvm_read_mmx_reg(int reg, u64 *data) { kvm_fpu_get(); _kvm_read_mmx_reg(reg, data); kvm_fpu_put(); } static inline void kvm_write_mmx_reg(int reg, const u64 *data) { kvm_fpu_get(); _kvm_write_mmx_reg(reg, data); kvm_fpu_put(); } #endif |
| 8 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 | // SPDX-License-Identifier: GPL-2.0 /* * queue_stack_maps.c: BPF queue and stack maps * * Copyright (c) 2018 Politecnico di Torino */ #include <linux/bpf.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/btf_ids.h> #include "percpu_freelist.h" #include <asm/rqspinlock.h> #define QUEUE_STACK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK) struct bpf_queue_stack { struct bpf_map map; rqspinlock_t lock; u32 head, tail; u32 size; /* max_entries + 1 */ char elements[] __aligned(8); }; static struct bpf_queue_stack *bpf_queue_stack(struct bpf_map *map) { return container_of(map, struct bpf_queue_stack, map); } static bool queue_stack_map_is_empty(struct bpf_queue_stack *qs) { return qs->head == qs->tail; } static bool queue_stack_map_is_full(struct bpf_queue_stack *qs) { u32 head = qs->head + 1; if (unlikely(head >= qs->size)) head = 0; return head == qs->tail; } /* Called from syscall */ static int queue_stack_map_alloc_check(union bpf_attr *attr) { /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 0 || attr->value_size == 0 || attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK || !bpf_map_flags_access_ok(attr->map_flags)) return -EINVAL; if (attr->value_size > KMALLOC_MAX_SIZE) /* if value_size is bigger, the user space won't be able to * access the elements. */ return -E2BIG; return 0; } static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); struct bpf_queue_stack *qs; u64 size, queue_size; size = (u64) attr->max_entries + 1; queue_size = sizeof(*qs) + size * attr->value_size; qs = bpf_map_area_alloc(queue_size, numa_node); if (!qs) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&qs->map, attr); qs->size = size; raw_res_spin_lock_init(&qs->lock); return &qs->map; } /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ static void queue_stack_map_free(struct bpf_map *map) { struct bpf_queue_stack *qs = bpf_queue_stack(map); bpf_map_area_free(qs); } static long __queue_map_get(struct bpf_map *map, void *value, bool delete) { struct bpf_queue_stack *qs = bpf_queue_stack(map); unsigned long flags; int err = 0; void *ptr; if (raw_res_spin_lock_irqsave(&qs->lock, flags)) return -EBUSY; if (queue_stack_map_is_empty(qs)) { memset(value, 0, qs->map.value_size); err = -ENOENT; goto out; } ptr = &qs->elements[qs->tail * qs->map.value_size]; memcpy(value, ptr, qs->map.value_size); if (delete) { if (unlikely(++qs->tail >= qs->size)) qs->tail = 0; } out: raw_res_spin_unlock_irqrestore(&qs->lock, flags); return err; } static long __stack_map_get(struct bpf_map *map, void *value, bool delete) { struct bpf_queue_stack *qs = bpf_queue_stack(map); unsigned long flags; int err = 0; void *ptr; u32 index; if (raw_res_spin_lock_irqsave(&qs->lock, flags)) return -EBUSY; if (queue_stack_map_is_empty(qs)) { memset(value, 0, qs->map.value_size); err = -ENOENT; goto out; } index = qs->head - 1; if (unlikely(index >= qs->size)) index = qs->size - 1; ptr = &qs->elements[index * qs->map.value_size]; memcpy(value, ptr, qs->map.value_size); if (delete) qs->head = index; out: raw_res_spin_unlock_irqrestore(&qs->lock, flags); return err; } /* Called from syscall or from eBPF program */ static long queue_map_peek_elem(struct bpf_map *map, void *value) { return __queue_map_get(map, value, false); } /* Called from syscall or from eBPF program */ static long stack_map_peek_elem(struct bpf_map *map, void *value) { return __stack_map_get(map, value, false); } /* Called from syscall or from eBPF program */ static long queue_map_pop_elem(struct bpf_map *map, void *value) { return __queue_map_get(map, value, true); } /* Called from syscall or from eBPF program */ static long stack_map_pop_elem(struct bpf_map *map, void *value) { return __stack_map_get(map, value, true); } /* Called from syscall or from eBPF program */ static long queue_stack_map_push_elem(struct bpf_map *map, void *value, u64 flags) { struct bpf_queue_stack *qs = bpf_queue_stack(map); unsigned long irq_flags; int err = 0; void *dst; /* BPF_EXIST is used to force making room for a new element in case the * map is full */ bool replace = (flags & BPF_EXIST); /* Check supported flags for queue and stack maps */ if (flags & BPF_NOEXIST || flags > BPF_EXIST) return -EINVAL; if (raw_res_spin_lock_irqsave(&qs->lock, irq_flags)) return -EBUSY; if (queue_stack_map_is_full(qs)) { if (!replace) { err = -E2BIG; goto out; } /* advance tail pointer to overwrite oldest element */ if (unlikely(++qs->tail >= qs->size)) qs->tail = 0; } dst = &qs->elements[qs->head * qs->map.value_size]; memcpy(dst, value, qs->map.value_size); if (unlikely(++qs->head >= qs->size)) qs->head = 0; out: raw_res_spin_unlock_irqrestore(&qs->lock, irq_flags); return err; } /* Called from syscall or from eBPF program */ static void *queue_stack_map_lookup_elem(struct bpf_map *map, void *key) { return NULL; } /* Called from syscall or from eBPF program */ static long queue_stack_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { return -EINVAL; } /* Called from syscall or from eBPF program */ static long queue_stack_map_delete_elem(struct bpf_map *map, void *key) { return -EINVAL; } /* Called from syscall */ static int queue_stack_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -EINVAL; } static u64 queue_stack_map_mem_usage(const struct bpf_map *map) { u64 usage = sizeof(struct bpf_queue_stack); usage += ((u64)map->max_entries + 1) * map->value_size; return usage; } BTF_ID_LIST_SINGLE(queue_map_btf_ids, struct, bpf_queue_stack) const struct bpf_map_ops queue_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = queue_stack_map_alloc_check, .map_alloc = queue_stack_map_alloc, .map_free = queue_stack_map_free, .map_lookup_elem = queue_stack_map_lookup_elem, .map_update_elem = queue_stack_map_update_elem, .map_delete_elem = queue_stack_map_delete_elem, .map_push_elem = queue_stack_map_push_elem, .map_pop_elem = queue_map_pop_elem, .map_peek_elem = queue_map_peek_elem, .map_get_next_key = queue_stack_map_get_next_key, .map_mem_usage = queue_stack_map_mem_usage, .map_btf_id = &queue_map_btf_ids[0], }; const struct bpf_map_ops stack_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = queue_stack_map_alloc_check, .map_alloc = queue_stack_map_alloc, .map_free = queue_stack_map_free, .map_lookup_elem = queue_stack_map_lookup_elem, .map_update_elem = queue_stack_map_update_elem, .map_delete_elem = queue_stack_map_delete_elem, .map_push_elem = queue_stack_map_push_elem, .map_pop_elem = stack_map_pop_elem, .map_peek_elem = stack_map_peek_elem, .map_get_next_key = queue_stack_map_get_next_key, .map_mem_usage = queue_stack_map_mem_usage, .map_btf_id = &queue_map_btf_ids[0], }; |
| 2 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * NILFS module and super block management. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * * Written by Ryusuke Konishi. */ /* * linux/fs/ext2/super.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/inode.c * * Copyright (C) 1991, 1992 Linus Torvalds * * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 */ #include <linux/module.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/blkdev.h> #include <linux/crc32.h> #include <linux/vfs.h> #include <linux/writeback.h> #include <linux/seq_file.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include "nilfs.h" #include "export.h" #include "mdt.h" #include "alloc.h" #include "btree.h" #include "btnode.h" #include "page.h" #include "cpfile.h" #include "sufile.h" /* nilfs_sufile_resize(), nilfs_sufile_set_alloc_range() */ #include "ifile.h" #include "dat.h" #include "segment.h" #include "segbuf.h" MODULE_AUTHOR("NTT Corp."); MODULE_DESCRIPTION("A New Implementation of the Log-structured Filesystem " "(NILFS)"); MODULE_LICENSE("GPL"); static struct kmem_cache *nilfs_inode_cachep; struct kmem_cache *nilfs_transaction_cachep; struct kmem_cache *nilfs_segbuf_cachep; struct kmem_cache *nilfs_btree_path_cache; static int nilfs_setup_super(struct super_block *sb, int is_mount); void __nilfs_msg(struct super_block *sb, const char *fmt, ...) { struct va_format vaf; va_list args; int level; va_start(args, fmt); level = printk_get_level(fmt); vaf.fmt = printk_skip_level(fmt); vaf.va = &args; if (sb) printk("%c%cNILFS (%s): %pV\n", KERN_SOH_ASCII, level, sb->s_id, &vaf); else printk("%c%cNILFS: %pV\n", KERN_SOH_ASCII, level, &vaf); va_end(args); } static void nilfs_set_error(struct super_block *sb) { struct the_nilfs *nilfs = sb->s_fs_info; struct nilfs_super_block **sbp; down_write(&nilfs->ns_sem); if (!(nilfs->ns_mount_state & NILFS_ERROR_FS)) { nilfs->ns_mount_state |= NILFS_ERROR_FS; sbp = nilfs_prepare_super(sb, 0); if (likely(sbp)) { sbp[0]->s_state |= cpu_to_le16(NILFS_ERROR_FS); if (sbp[1]) sbp[1]->s_state |= cpu_to_le16(NILFS_ERROR_FS); nilfs_commit_super(sb, NILFS_SB_COMMIT_ALL); } } up_write(&nilfs->ns_sem); } /** * __nilfs_error() - report failure condition on a filesystem * @sb: super block instance * @function: name of calling function * @fmt: format string for message to be output * @...: optional arguments to @fmt * * __nilfs_error() sets an ERROR_FS flag on the superblock as well as * reporting an error message. This function should be called when * NILFS detects incoherences or defects of meta data on disk. * * This implements the body of nilfs_error() macro. Normally, * nilfs_error() should be used. As for sustainable errors such as a * single-shot I/O error, nilfs_err() should be used instead. * * Callers should not add a trailing newline since this will do it. */ void __nilfs_error(struct super_block *sb, const char *function, const char *fmt, ...) { struct the_nilfs *nilfs = sb->s_fs_info; struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_CRIT "NILFS error (device %s): %s: %pV\n", sb->s_id, function, &vaf); va_end(args); if (!sb_rdonly(sb)) { nilfs_set_error(sb); if (nilfs_test_opt(nilfs, ERRORS_RO)) { printk(KERN_CRIT "Remounting filesystem read-only\n"); sb->s_flags |= SB_RDONLY; } } if (nilfs_test_opt(nilfs, ERRORS_PANIC)) panic("NILFS (device %s): panic forced after error\n", sb->s_id); } struct inode *nilfs_alloc_inode(struct super_block *sb) { struct nilfs_inode_info *ii; ii = alloc_inode_sb(sb, nilfs_inode_cachep, GFP_NOFS); if (!ii) return NULL; ii->i_bh = NULL; ii->i_state = 0; ii->i_type = 0; ii->i_cno = 0; ii->i_assoc_inode = NULL; ii->i_bmap = &ii->i_bmap_data; return &ii->vfs_inode; } static void nilfs_free_inode(struct inode *inode) { if (nilfs_is_metadata_file_inode(inode)) nilfs_mdt_destroy(inode); kmem_cache_free(nilfs_inode_cachep, NILFS_I(inode)); } static int nilfs_sync_super(struct super_block *sb, int flag) { struct the_nilfs *nilfs = sb->s_fs_info; int err; retry: set_buffer_dirty(nilfs->ns_sbh[0]); if (nilfs_test_opt(nilfs, BARRIER)) { err = __sync_dirty_buffer(nilfs->ns_sbh[0], REQ_SYNC | REQ_PREFLUSH | REQ_FUA); } else { err = sync_dirty_buffer(nilfs->ns_sbh[0]); } if (unlikely(err)) { nilfs_err(sb, "unable to write superblock: err=%d", err); if (err == -EIO && nilfs->ns_sbh[1]) { /* * sbp[0] points to newer log than sbp[1], * so copy sbp[0] to sbp[1] to take over sbp[0]. */ memcpy(nilfs->ns_sbp[1], nilfs->ns_sbp[0], nilfs->ns_sbsize); nilfs_fall_back_super_block(nilfs); goto retry; } } else { struct nilfs_super_block *sbp = nilfs->ns_sbp[0]; nilfs->ns_sbwcount++; /* * The latest segment becomes trailable from the position * written in superblock. */ clear_nilfs_discontinued(nilfs); /* update GC protection for recent segments */ if (nilfs->ns_sbh[1]) { if (flag == NILFS_SB_COMMIT_ALL) { set_buffer_dirty(nilfs->ns_sbh[1]); if (sync_dirty_buffer(nilfs->ns_sbh[1]) < 0) goto out; } if (le64_to_cpu(nilfs->ns_sbp[1]->s_last_cno) < le64_to_cpu(nilfs->ns_sbp[0]->s_last_cno)) sbp = nilfs->ns_sbp[1]; } spin_lock(&nilfs->ns_last_segment_lock); nilfs->ns_prot_seq = le64_to_cpu(sbp->s_last_seq); spin_unlock(&nilfs->ns_last_segment_lock); } out: return err; } void nilfs_set_log_cursor(struct nilfs_super_block *sbp, struct the_nilfs *nilfs) { sector_t nfreeblocks; /* nilfs->ns_sem must be locked by the caller. */ nilfs_count_free_blocks(nilfs, &nfreeblocks); sbp->s_free_blocks_count = cpu_to_le64(nfreeblocks); spin_lock(&nilfs->ns_last_segment_lock); sbp->s_last_seq = cpu_to_le64(nilfs->ns_last_seq); sbp->s_last_pseg = cpu_to_le64(nilfs->ns_last_pseg); sbp->s_last_cno = cpu_to_le64(nilfs->ns_last_cno); spin_unlock(&nilfs->ns_last_segment_lock); } struct nilfs_super_block **nilfs_prepare_super(struct super_block *sb, int flip) { struct the_nilfs *nilfs = sb->s_fs_info; struct nilfs_super_block **sbp = nilfs->ns_sbp; /* nilfs->ns_sem must be locked by the caller. */ if (sbp[0]->s_magic != cpu_to_le16(NILFS_SUPER_MAGIC)) { if (sbp[1] && sbp[1]->s_magic == cpu_to_le16(NILFS_SUPER_MAGIC)) { memcpy(sbp[0], sbp[1], nilfs->ns_sbsize); } else { nilfs_crit(sb, "superblock broke"); return NULL; } } else if (sbp[1] && sbp[1]->s_magic != cpu_to_le16(NILFS_SUPER_MAGIC)) { memcpy(sbp[1], sbp[0], nilfs->ns_sbsize); } if (flip && sbp[1]) nilfs_swap_super_block(nilfs); return sbp; } int nilfs_commit_super(struct super_block *sb, int flag) { struct the_nilfs *nilfs = sb->s_fs_info; struct nilfs_super_block **sbp = nilfs->ns_sbp; time64_t t; /* nilfs->ns_sem must be locked by the caller. */ t = ktime_get_real_seconds(); nilfs->ns_sbwtime = t; sbp[0]->s_wtime = cpu_to_le64(t); sbp[0]->s_sum = 0; sbp[0]->s_sum = cpu_to_le32(crc32_le(nilfs->ns_crc_seed, (unsigned char *)sbp[0], nilfs->ns_sbsize)); if (flag == NILFS_SB_COMMIT_ALL && sbp[1]) { sbp[1]->s_wtime = sbp[0]->s_wtime; sbp[1]->s_sum = 0; sbp[1]->s_sum = cpu_to_le32(crc32_le(nilfs->ns_crc_seed, (unsigned char *)sbp[1], nilfs->ns_sbsize)); } clear_nilfs_sb_dirty(nilfs); nilfs->ns_flushed_device = 1; /* make sure store to ns_flushed_device cannot be reordered */ smp_wmb(); return nilfs_sync_super(sb, flag); } /** * nilfs_cleanup_super() - write filesystem state for cleanup * @sb: super block instance to be unmounted or degraded to read-only * * This function restores state flags in the on-disk super block. * This will set "clean" flag (i.e. NILFS_VALID_FS) unless the * filesystem was not clean previously. * * Return: 0 on success, %-EIO if I/O error or superblock is corrupted. */ int nilfs_cleanup_super(struct super_block *sb) { struct the_nilfs *nilfs = sb->s_fs_info; struct nilfs_super_block **sbp; int flag = NILFS_SB_COMMIT; int ret = -EIO; sbp = nilfs_prepare_super(sb, 0); if (sbp) { sbp[0]->s_state = cpu_to_le16(nilfs->ns_mount_state); nilfs_set_log_cursor(sbp[0], nilfs); if (sbp[1] && sbp[0]->s_last_cno == sbp[1]->s_last_cno) { /* * make the "clean" flag also to the opposite * super block if both super blocks point to * the same checkpoint. */ sbp[1]->s_state = sbp[0]->s_state; flag = NILFS_SB_COMMIT_ALL; } ret = nilfs_commit_super(sb, flag); } return ret; } /** * nilfs_move_2nd_super - relocate secondary super block * @sb: super block instance * @sb2off: new offset of the secondary super block (in bytes) * * Return: 0 on success, or a negative error code on failure. */ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off) { struct the_nilfs *nilfs = sb->s_fs_info; struct buffer_head *nsbh; struct nilfs_super_block *nsbp; sector_t blocknr, newblocknr; unsigned long offset; int sb2i; /* array index of the secondary superblock */ int ret = 0; /* nilfs->ns_sem must be locked by the caller. */ if (nilfs->ns_sbh[1] && nilfs->ns_sbh[1]->b_blocknr > nilfs->ns_first_data_block) { sb2i = 1; blocknr = nilfs->ns_sbh[1]->b_blocknr; } else if (nilfs->ns_sbh[0]->b_blocknr > nilfs->ns_first_data_block) { sb2i = 0; blocknr = nilfs->ns_sbh[0]->b_blocknr; } else { sb2i = -1; blocknr = 0; } if (sb2i >= 0 && (u64)blocknr << nilfs->ns_blocksize_bits == sb2off) goto out; /* super block location is unchanged */ /* Get new super block buffer */ newblocknr = sb2off >> nilfs->ns_blocksize_bits; offset = sb2off & (nilfs->ns_blocksize - 1); nsbh = sb_getblk(sb, newblocknr); if (!nsbh) { nilfs_warn(sb, "unable to move secondary superblock to block %llu", (unsigned long long)newblocknr); ret = -EIO; goto out; } nsbp = (void *)nsbh->b_data + offset; lock_buffer(nsbh); if (sb2i >= 0) { /* * The position of the second superblock only changes by 4KiB, * which is larger than the maximum superblock data size * (= 1KiB), so there is no need to use memmove() to allow * overlap between source and destination. */ memcpy(nsbp, nilfs->ns_sbp[sb2i], nilfs->ns_sbsize); /* * Zero fill after copy to avoid overwriting in case of move * within the same block. */ memset(nsbh->b_data, 0, offset); memset((void *)nsbp + nilfs->ns_sbsize, 0, nsbh->b_size - offset - nilfs->ns_sbsize); } else { memset(nsbh->b_data, 0, nsbh->b_size); } set_buffer_uptodate(nsbh); unlock_buffer(nsbh); if (sb2i >= 0) { brelse(nilfs->ns_sbh[sb2i]); nilfs->ns_sbh[sb2i] = nsbh; nilfs->ns_sbp[sb2i] = nsbp; } else if (nilfs->ns_sbh[0]->b_blocknr < nilfs->ns_first_data_block) { /* secondary super block will be restored to index 1 */ nilfs->ns_sbh[1] = nsbh; nilfs->ns_sbp[1] = nsbp; } else { brelse(nsbh); } out: return ret; } /** * nilfs_resize_fs - resize the filesystem * @sb: super block instance * @newsize: new size of the filesystem (in bytes) * * Return: 0 on success, or a negative error code on failure. */ int nilfs_resize_fs(struct super_block *sb, __u64 newsize) { struct the_nilfs *nilfs = sb->s_fs_info; struct nilfs_super_block **sbp; __u64 devsize, newnsegs; loff_t sb2off; int ret; ret = -ERANGE; devsize = bdev_nr_bytes(sb->s_bdev); if (newsize > devsize) goto out; /* * Prevent underflow in second superblock position calculation. * The exact minimum size check is done in nilfs_sufile_resize(). */ if (newsize < 4096) { ret = -ENOSPC; goto out; } /* * Write lock is required to protect some functions depending * on the number of segments, the number of reserved segments, * and so forth. */ down_write(&nilfs->ns_segctor_sem); sb2off = NILFS_SB2_OFFSET_BYTES(newsize); newnsegs = sb2off >> nilfs->ns_blocksize_bits; newnsegs = div64_ul(newnsegs, nilfs->ns_blocks_per_segment); ret = nilfs_sufile_resize(nilfs->ns_sufile, newnsegs); up_write(&nilfs->ns_segctor_sem); if (ret < 0) goto out; ret = nilfs_construct_segment(sb); if (ret < 0) goto out; down_write(&nilfs->ns_sem); nilfs_move_2nd_super(sb, sb2off); ret = -EIO; sbp = nilfs_prepare_super(sb, 0); if (likely(sbp)) { nilfs_set_log_cursor(sbp[0], nilfs); /* * Drop NILFS_RESIZE_FS flag for compatibility with * mount-time resize which may be implemented in a * future release. */ sbp[0]->s_state = cpu_to_le16(le16_to_cpu(sbp[0]->s_state) & ~NILFS_RESIZE_FS); sbp[0]->s_dev_size = cpu_to_le64(newsize); sbp[0]->s_nsegments = cpu_to_le64(nilfs->ns_nsegments); if (sbp[1]) memcpy(sbp[1], sbp[0], nilfs->ns_sbsize); ret = nilfs_commit_super(sb, NILFS_SB_COMMIT_ALL); } up_write(&nilfs->ns_sem); /* * Reset the range of allocatable segments last. This order * is important in the case of expansion because the secondary * superblock must be protected from log write until migration * completes. */ if (!ret) nilfs_sufile_set_alloc_range(nilfs->ns_sufile, 0, newnsegs - 1); out: return ret; } static void nilfs_put_super(struct super_block *sb) { struct the_nilfs *nilfs = sb->s_fs_info; nilfs_detach_log_writer(sb); if (!sb_rdonly(sb)) { down_write(&nilfs->ns_sem); nilfs_cleanup_super(sb); up_write(&nilfs->ns_sem); } nilfs_sysfs_delete_device_group(nilfs); iput(nilfs->ns_sufile); iput(nilfs->ns_cpfile); iput(nilfs->ns_dat); destroy_nilfs(nilfs); sb->s_fs_info = NULL; } static int nilfs_sync_fs(struct super_block *sb, int wait) { struct the_nilfs *nilfs = sb->s_fs_info; struct nilfs_super_block **sbp; int err = 0; /* This function is called when super block should be written back */ if (wait) err = nilfs_construct_segment(sb); down_write(&nilfs->ns_sem); if (nilfs_sb_dirty(nilfs)) { sbp = nilfs_prepare_super(sb, nilfs_sb_will_flip(nilfs)); if (likely(sbp)) { nilfs_set_log_cursor(sbp[0], nilfs); nilfs_commit_super(sb, NILFS_SB_COMMIT); } } up_write(&nilfs->ns_sem); if (!err) err = nilfs_flush_device(nilfs); return err; } int nilfs_attach_checkpoint(struct super_block *sb, __u64 cno, int curr_mnt, struct nilfs_root **rootp) { struct the_nilfs *nilfs = sb->s_fs_info; struct nilfs_root *root; int err = -ENOMEM; root = nilfs_find_or_create_root( nilfs, curr_mnt ? NILFS_CPTREE_CURRENT_CNO : cno); if (!root) return err; if (root->ifile) goto reuse; /* already attached checkpoint */ down_read(&nilfs->ns_segctor_sem); err = nilfs_ifile_read(sb, root, cno, nilfs->ns_inode_size); up_read(&nilfs->ns_segctor_sem); if (unlikely(err)) goto failed; reuse: *rootp = root; return 0; failed: if (err == -EINVAL) nilfs_err(sb, "Invalid checkpoint (checkpoint number=%llu)", (unsigned long long)cno); nilfs_put_root(root); return err; } static int nilfs_freeze(struct super_block *sb) { struct the_nilfs *nilfs = sb->s_fs_info; int err; if (sb_rdonly(sb)) return 0; /* Mark super block clean */ down_write(&nilfs->ns_sem); err = nilfs_cleanup_super(sb); up_write(&nilfs->ns_sem); return err; } static int nilfs_unfreeze(struct super_block *sb) { struct the_nilfs *nilfs = sb->s_fs_info; if (sb_rdonly(sb)) return 0; down_write(&nilfs->ns_sem); nilfs_setup_super(sb, false); up_write(&nilfs->ns_sem); return 0; } static int nilfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct nilfs_root *root = NILFS_I(d_inode(dentry))->i_root; struct the_nilfs *nilfs = root->nilfs; u64 id = huge_encode_dev(sb->s_bdev->bd_dev); unsigned long long blocks; unsigned long overhead; unsigned long nrsvblocks; sector_t nfreeblocks; u64 nmaxinodes, nfreeinodes; int err; /* * Compute all of the segment blocks * * The blocks before first segment and after last segment * are excluded. */ blocks = nilfs->ns_blocks_per_segment * nilfs->ns_nsegments - nilfs->ns_first_data_block; nrsvblocks = nilfs->ns_nrsvsegs * nilfs->ns_blocks_per_segment; /* * Compute the overhead * * When distributing meta data blocks outside segment structure, * We must count them as the overhead. */ overhead = 0; err = nilfs_count_free_blocks(nilfs, &nfreeblocks); if (unlikely(err)) return err; err = nilfs_ifile_count_free_inodes(root->ifile, &nmaxinodes, &nfreeinodes); if (unlikely(err)) { nilfs_warn(sb, "failed to count free inodes: err=%d", err); if (err == -ERANGE) { /* * If nilfs_palloc_count_max_entries() returns * -ERANGE error code then we simply treat * curent inodes count as maximum possible and * zero as free inodes value. */ nmaxinodes = atomic64_read(&root->inodes_count); nfreeinodes = 0; err = 0; } else return err; } buf->f_type = NILFS_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_blocks = blocks - overhead; buf->f_bfree = nfreeblocks; buf->f_bavail = (buf->f_bfree >= nrsvblocks) ? (buf->f_bfree - nrsvblocks) : 0; buf->f_files = nmaxinodes; buf->f_ffree = nfreeinodes; buf->f_namelen = NILFS_NAME_LEN; buf->f_fsid = u64_to_fsid(id); return 0; } static int nilfs_show_options(struct seq_file *seq, struct dentry *dentry) { struct super_block *sb = dentry->d_sb; struct the_nilfs *nilfs = sb->s_fs_info; struct nilfs_root *root = NILFS_I(d_inode(dentry))->i_root; if (!nilfs_test_opt(nilfs, BARRIER)) seq_puts(seq, ",nobarrier"); if (root->cno != NILFS_CPTREE_CURRENT_CNO) seq_printf(seq, ",cp=%llu", (unsigned long long)root->cno); if (nilfs_test_opt(nilfs, ERRORS_PANIC)) seq_puts(seq, ",errors=panic"); if (nilfs_test_opt(nilfs, ERRORS_CONT)) seq_puts(seq, ",errors=continue"); if (nilfs_test_opt(nilfs, STRICT_ORDER)) seq_puts(seq, ",order=strict"); if (nilfs_test_opt(nilfs, NORECOVERY)) seq_puts(seq, ",norecovery"); if (nilfs_test_opt(nilfs, DISCARD)) seq_puts(seq, ",discard"); return 0; } static const struct super_operations nilfs_sops = { .alloc_inode = nilfs_alloc_inode, .free_inode = nilfs_free_inode, .dirty_inode = nilfs_dirty_inode, .evict_inode = nilfs_evict_inode, .put_super = nilfs_put_super, .sync_fs = nilfs_sync_fs, .freeze_fs = nilfs_freeze, .unfreeze_fs = nilfs_unfreeze, .statfs = nilfs_statfs, .show_options = nilfs_show_options }; enum { Opt_err, Opt_barrier, Opt_snapshot, Opt_order, Opt_norecovery, Opt_discard, }; static const struct constant_table nilfs_param_err[] = { {"continue", NILFS_MOUNT_ERRORS_CONT}, {"panic", NILFS_MOUNT_ERRORS_PANIC}, {"remount-ro", NILFS_MOUNT_ERRORS_RO}, {} }; static const struct fs_parameter_spec nilfs_param_spec[] = { fsparam_enum ("errors", Opt_err, nilfs_param_err), fsparam_flag_no ("barrier", Opt_barrier), fsparam_u64 ("cp", Opt_snapshot), fsparam_string ("order", Opt_order), fsparam_flag ("norecovery", Opt_norecovery), fsparam_flag_no ("discard", Opt_discard), {} }; struct nilfs_fs_context { unsigned long ns_mount_opt; __u64 cno; }; static int nilfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct nilfs_fs_context *nilfs = fc->fs_private; int is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE; struct fs_parse_result result; int opt; opt = fs_parse(fc, nilfs_param_spec, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_barrier: if (result.negated) nilfs_clear_opt(nilfs, BARRIER); else nilfs_set_opt(nilfs, BARRIER); break; case Opt_order: if (strcmp(param->string, "relaxed") == 0) /* Ordered data semantics */ nilfs_clear_opt(nilfs, STRICT_ORDER); else if (strcmp(param->string, "strict") == 0) /* Strict in-order semantics */ nilfs_set_opt(nilfs, STRICT_ORDER); else return -EINVAL; break; case Opt_err: nilfs->ns_mount_opt &= ~NILFS_MOUNT_ERROR_MODE; nilfs->ns_mount_opt |= result.uint_32; break; case Opt_snapshot: if (is_remount) { struct super_block *sb = fc->root->d_sb; nilfs_err(sb, "\"%s\" option is invalid for remount", param->key); return -EINVAL; } if (result.uint_64 == 0) { nilfs_err(NULL, "invalid option \"cp=0\": invalid checkpoint number 0"); return -EINVAL; } nilfs->cno = result.uint_64; break; case Opt_norecovery: nilfs_set_opt(nilfs, NORECOVERY); break; case Opt_discard: if (result.negated) nilfs_clear_opt(nilfs, DISCARD); else nilfs_set_opt(nilfs, DISCARD); break; default: return -EINVAL; } return 0; } static int nilfs_setup_super(struct super_block *sb, int is_mount) { struct the_nilfs *nilfs = sb->s_fs_info; struct nilfs_super_block **sbp; int max_mnt_count; int mnt_count; /* nilfs->ns_sem must be locked by the caller. */ sbp = nilfs_prepare_super(sb, 0); if (!sbp) return -EIO; if (!is_mount) goto skip_mount_setup; max_mnt_count = le16_to_cpu(sbp[0]->s_max_mnt_count); mnt_count = le16_to_cpu(sbp[0]->s_mnt_count); if (nilfs->ns_mount_state & NILFS_ERROR_FS) { nilfs_warn(sb, "mounting fs with errors"); #if 0 } else if (max_mnt_count >= 0 && mnt_count >= max_mnt_count) { nilfs_warn(sb, "maximal mount count reached"); #endif } if (!max_mnt_count) sbp[0]->s_max_mnt_count = cpu_to_le16(NILFS_DFL_MAX_MNT_COUNT); sbp[0]->s_mnt_count = cpu_to_le16(mnt_count + 1); sbp[0]->s_mtime = cpu_to_le64(ktime_get_real_seconds()); skip_mount_setup: sbp[0]->s_state = cpu_to_le16(le16_to_cpu(sbp[0]->s_state) & ~NILFS_VALID_FS); /* synchronize sbp[1] with sbp[0] */ if (sbp[1]) memcpy(sbp[1], sbp[0], nilfs->ns_sbsize); return nilfs_commit_super(sb, NILFS_SB_COMMIT_ALL); } struct nilfs_super_block *nilfs_read_super_block(struct super_block *sb, u64 pos, int blocksize, struct buffer_head **pbh) { unsigned long long sb_index = pos; unsigned long offset; offset = do_div(sb_index, blocksize); *pbh = sb_bread(sb, sb_index); if (!*pbh) return NULL; return (struct nilfs_super_block *)((char *)(*pbh)->b_data + offset); } int nilfs_store_magic(struct super_block *sb, struct nilfs_super_block *sbp) { struct the_nilfs *nilfs = sb->s_fs_info; sb->s_magic = le16_to_cpu(sbp->s_magic); /* FS independent flags */ #ifdef NILFS_ATIME_DISABLE sb->s_flags |= SB_NOATIME; #endif nilfs->ns_resuid = le16_to_cpu(sbp->s_def_resuid); nilfs->ns_resgid = le16_to_cpu(sbp->s_def_resgid); nilfs->ns_interval = le32_to_cpu(sbp->s_c_interval); nilfs->ns_watermark = le32_to_cpu(sbp->s_c_block_max); return 0; } int nilfs_check_feature_compatibility(struct super_block *sb, struct nilfs_super_block *sbp) { __u64 features; features = le64_to_cpu(sbp->s_feature_incompat) & ~NILFS_FEATURE_INCOMPAT_SUPP; if (features) { nilfs_err(sb, "couldn't mount because of unsupported optional features (%llx)", (unsigned long long)features); return -EINVAL; } features = le64_to_cpu(sbp->s_feature_compat_ro) & ~NILFS_FEATURE_COMPAT_RO_SUPP; if (!sb_rdonly(sb) && features) { nilfs_err(sb, "couldn't mount RDWR because of unsupported optional features (%llx)", (unsigned long long)features); return -EINVAL; } return 0; } static int nilfs_get_root_dentry(struct super_block *sb, struct nilfs_root *root, struct dentry **root_dentry) { struct inode *inode; struct dentry *dentry; int ret = 0; inode = nilfs_iget(sb, root, NILFS_ROOT_INO); if (IS_ERR(inode)) { ret = PTR_ERR(inode); nilfs_err(sb, "error %d getting root inode", ret); goto out; } if (!S_ISDIR(inode->i_mode) || !inode->i_blocks || !inode->i_size) { iput(inode); nilfs_err(sb, "corrupt root inode"); ret = -EINVAL; goto out; } if (root->cno == NILFS_CPTREE_CURRENT_CNO) { dentry = d_find_alias(inode); if (!dentry) { dentry = d_make_root(inode); if (!dentry) { ret = -ENOMEM; goto failed_dentry; } } else { iput(inode); } } else { dentry = d_obtain_root(inode); if (IS_ERR(dentry)) { ret = PTR_ERR(dentry); goto failed_dentry; } } *root_dentry = dentry; out: return ret; failed_dentry: nilfs_err(sb, "error %d getting root dentry", ret); goto out; } static int nilfs_attach_snapshot(struct super_block *s, __u64 cno, struct dentry **root_dentry) { struct the_nilfs *nilfs = s->s_fs_info; struct nilfs_root *root; int ret; mutex_lock(&nilfs->ns_snapshot_mount_mutex); down_read(&nilfs->ns_segctor_sem); ret = nilfs_cpfile_is_snapshot(nilfs->ns_cpfile, cno); up_read(&nilfs->ns_segctor_sem); if (ret < 0) { ret = (ret == -ENOENT) ? -EINVAL : ret; goto out; } else if (!ret) { nilfs_err(s, "The specified checkpoint is not a snapshot (checkpoint number=%llu)", (unsigned long long)cno); ret = -EINVAL; goto out; } ret = nilfs_attach_checkpoint(s, cno, false, &root); if (ret) { nilfs_err(s, "error %d while loading snapshot (checkpoint number=%llu)", ret, (unsigned long long)cno); goto out; } ret = nilfs_get_root_dentry(s, root, root_dentry); nilfs_put_root(root); out: mutex_unlock(&nilfs->ns_snapshot_mount_mutex); return ret; } /** * nilfs_tree_is_busy() - try to shrink dentries of a checkpoint * @root_dentry: root dentry of the tree to be shrunk * * Return: true if the tree was in-use, false otherwise. */ static bool nilfs_tree_is_busy(struct dentry *root_dentry) { shrink_dcache_parent(root_dentry); return d_count(root_dentry) > 1; } int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno) { struct the_nilfs *nilfs = sb->s_fs_info; struct nilfs_root *root; struct inode *inode; struct dentry *dentry; int ret; if (cno > nilfs->ns_cno) return false; if (cno >= nilfs_last_cno(nilfs)) return true; /* protect recent checkpoints */ ret = false; root = nilfs_lookup_root(nilfs, cno); if (root) { inode = nilfs_ilookup(sb, root, NILFS_ROOT_INO); if (inode) { dentry = d_find_alias(inode); if (dentry) { ret = nilfs_tree_is_busy(dentry); dput(dentry); } iput(inode); } nilfs_put_root(root); } return ret; } /** * nilfs_fill_super() - initialize a super block instance * @sb: super_block * @fc: filesystem context * * This function is called exclusively by nilfs->ns_mount_mutex. * So, the recovery process is protected from other simultaneous mounts. * * Return: 0 on success, or a negative error code on failure. */ static int nilfs_fill_super(struct super_block *sb, struct fs_context *fc) { struct the_nilfs *nilfs; struct nilfs_root *fsroot; struct nilfs_fs_context *ctx = fc->fs_private; __u64 cno; int err; nilfs = alloc_nilfs(sb); if (!nilfs) return -ENOMEM; sb->s_fs_info = nilfs; err = init_nilfs(nilfs, sb); if (err) goto failed_nilfs; /* Copy in parsed mount options */ nilfs->ns_mount_opt = ctx->ns_mount_opt; sb->s_op = &nilfs_sops; sb->s_export_op = &nilfs_export_ops; sb->s_root = NULL; sb->s_time_gran = 1; sb->s_max_links = NILFS_LINK_MAX; sb->s_bdi = bdi_get(sb->s_bdev->bd_disk->bdi); err = load_nilfs(nilfs, sb); if (err) goto failed_nilfs; super_set_uuid(sb, nilfs->ns_sbp[0]->s_uuid, sizeof(nilfs->ns_sbp[0]->s_uuid)); super_set_sysfs_name_bdev(sb); cno = nilfs_last_cno(nilfs); err = nilfs_attach_checkpoint(sb, cno, true, &fsroot); if (err) { nilfs_err(sb, "error %d while loading last checkpoint (checkpoint number=%llu)", err, (unsigned long long)cno); goto failed_unload; } if (!sb_rdonly(sb)) { err = nilfs_attach_log_writer(sb, fsroot); if (err) goto failed_checkpoint; } err = nilfs_get_root_dentry(sb, fsroot, &sb->s_root); if (err) goto failed_segctor; nilfs_put_root(fsroot); if (!sb_rdonly(sb)) { down_write(&nilfs->ns_sem); nilfs_setup_super(sb, true); up_write(&nilfs->ns_sem); } return 0; failed_segctor: nilfs_detach_log_writer(sb); failed_checkpoint: nilfs_put_root(fsroot); failed_unload: nilfs_sysfs_delete_device_group(nilfs); iput(nilfs->ns_sufile); iput(nilfs->ns_cpfile); iput(nilfs->ns_dat); failed_nilfs: destroy_nilfs(nilfs); return err; } static int nilfs_reconfigure(struct fs_context *fc) { struct nilfs_fs_context *ctx = fc->fs_private; struct super_block *sb = fc->root->d_sb; struct the_nilfs *nilfs = sb->s_fs_info; int err; sync_filesystem(sb); err = -EINVAL; if (!nilfs_valid_fs(nilfs)) { nilfs_warn(sb, "couldn't remount because the filesystem is in an incomplete recovery state"); goto ignore_opts; } if ((bool)(fc->sb_flags & SB_RDONLY) == sb_rdonly(sb)) goto out; if (fc->sb_flags & SB_RDONLY) { sb->s_flags |= SB_RDONLY; /* * Remounting a valid RW partition RDONLY, so set * the RDONLY flag and then mark the partition as valid again. */ down_write(&nilfs->ns_sem); nilfs_cleanup_super(sb); up_write(&nilfs->ns_sem); } else { __u64 features; struct nilfs_root *root; /* * Mounting a RDONLY partition read-write, so reread and * store the current valid flag. (It may have been changed * by fsck since we originally mounted the partition.) */ down_read(&nilfs->ns_sem); features = le64_to_cpu(nilfs->ns_sbp[0]->s_feature_compat_ro) & ~NILFS_FEATURE_COMPAT_RO_SUPP; up_read(&nilfs->ns_sem); if (features) { nilfs_warn(sb, "couldn't remount RDWR because of unsupported optional features (%llx)", (unsigned long long)features); err = -EROFS; goto ignore_opts; } sb->s_flags &= ~SB_RDONLY; root = NILFS_I(d_inode(sb->s_root))->i_root; err = nilfs_attach_log_writer(sb, root); if (err) { sb->s_flags |= SB_RDONLY; goto ignore_opts; } down_write(&nilfs->ns_sem); nilfs_setup_super(sb, true); up_write(&nilfs->ns_sem); } out: sb->s_flags = (sb->s_flags & ~SB_POSIXACL); /* Copy over parsed remount options */ nilfs->ns_mount_opt = ctx->ns_mount_opt; return 0; ignore_opts: return err; } static int nilfs_get_tree(struct fs_context *fc) { struct nilfs_fs_context *ctx = fc->fs_private; struct super_block *s; dev_t dev; int err; if (ctx->cno && !(fc->sb_flags & SB_RDONLY)) { nilfs_err(NULL, "invalid option \"cp=%llu\": read-only option is not specified", ctx->cno); return -EINVAL; } err = lookup_bdev(fc->source, &dev); if (err) return err; s = sget_dev(fc, dev); if (IS_ERR(s)) return PTR_ERR(s); if (!s->s_root) { err = setup_bdev_super(s, fc->sb_flags, fc); if (!err) err = nilfs_fill_super(s, fc); if (err) goto failed_super; s->s_flags |= SB_ACTIVE; } else if (!ctx->cno) { if (nilfs_tree_is_busy(s->s_root)) { if ((fc->sb_flags ^ s->s_flags) & SB_RDONLY) { nilfs_err(s, "the device already has a %s mount.", sb_rdonly(s) ? "read-only" : "read/write"); err = -EBUSY; goto failed_super; } } else { /* * Try reconfigure to setup mount states if the current * tree is not mounted and only snapshots use this sb. * * Since nilfs_reconfigure() requires fc->root to be * set, set it first and release it on failure. */ fc->root = dget(s->s_root); err = nilfs_reconfigure(fc); if (err) { dput(fc->root); fc->root = NULL; /* prevent double release */ goto failed_super; } return 0; } } if (ctx->cno) { struct dentry *root_dentry; err = nilfs_attach_snapshot(s, ctx->cno, &root_dentry); if (err) goto failed_super; fc->root = root_dentry; return 0; } fc->root = dget(s->s_root); return 0; failed_super: deactivate_locked_super(s); return err; } static void nilfs_free_fc(struct fs_context *fc) { kfree(fc->fs_private); } static const struct fs_context_operations nilfs_context_ops = { .parse_param = nilfs_parse_param, .get_tree = nilfs_get_tree, .reconfigure = nilfs_reconfigure, .free = nilfs_free_fc, }; static int nilfs_init_fs_context(struct fs_context *fc) { struct nilfs_fs_context *ctx; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->ns_mount_opt = NILFS_MOUNT_ERRORS_RO | NILFS_MOUNT_BARRIER; fc->fs_private = ctx; fc->ops = &nilfs_context_ops; return 0; } struct file_system_type nilfs_fs_type = { .owner = THIS_MODULE, .name = "nilfs2", .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, .init_fs_context = nilfs_init_fs_context, .parameters = nilfs_param_spec, }; MODULE_ALIAS_FS("nilfs2"); static void nilfs_inode_init_once(void *obj) { struct nilfs_inode_info *ii = obj; INIT_LIST_HEAD(&ii->i_dirty); #ifdef CONFIG_NILFS_XATTR init_rwsem(&ii->xattr_sem); #endif inode_init_once(&ii->vfs_inode); } static void nilfs_segbuf_init_once(void *obj) { memset(obj, 0, sizeof(struct nilfs_segment_buffer)); } static void nilfs_destroy_cachep(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(nilfs_inode_cachep); kmem_cache_destroy(nilfs_transaction_cachep); kmem_cache_destroy(nilfs_segbuf_cachep); kmem_cache_destroy(nilfs_btree_path_cache); } static int __init nilfs_init_cachep(void) { nilfs_inode_cachep = kmem_cache_create("nilfs2_inode_cache", sizeof(struct nilfs_inode_info), 0, SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, nilfs_inode_init_once); if (!nilfs_inode_cachep) goto fail; nilfs_transaction_cachep = kmem_cache_create("nilfs2_transaction_cache", sizeof(struct nilfs_transaction_info), 0, SLAB_RECLAIM_ACCOUNT, NULL); if (!nilfs_transaction_cachep) goto fail; nilfs_segbuf_cachep = kmem_cache_create("nilfs2_segbuf_cache", sizeof(struct nilfs_segment_buffer), 0, SLAB_RECLAIM_ACCOUNT, nilfs_segbuf_init_once); if (!nilfs_segbuf_cachep) goto fail; nilfs_btree_path_cache = kmem_cache_create("nilfs2_btree_path_cache", sizeof(struct nilfs_btree_path) * NILFS_BTREE_LEVEL_MAX, 0, 0, NULL); if (!nilfs_btree_path_cache) goto fail; return 0; fail: nilfs_destroy_cachep(); return -ENOMEM; } static int __init init_nilfs_fs(void) { int err; err = nilfs_init_cachep(); if (err) goto fail; err = nilfs_sysfs_init(); if (err) goto free_cachep; err = register_filesystem(&nilfs_fs_type); if (err) goto deinit_sysfs_entry; printk(KERN_INFO "NILFS version 2 loaded\n"); return 0; deinit_sysfs_entry: nilfs_sysfs_exit(); free_cachep: nilfs_destroy_cachep(); fail: return err; } static void __exit exit_nilfs_fs(void) { nilfs_destroy_cachep(); nilfs_sysfs_exit(); unregister_filesystem(&nilfs_fs_type); } module_init(init_nilfs_fs) module_exit(exit_nilfs_fs) |
| 5193 5191 119 118 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * ACPI device specific properties support. * * Copyright (C) 2014 - 2023, Intel Corporation * All rights reserved. * * Authors: Mika Westerberg <mika.westerberg@linux.intel.com> * Darren Hart <dvhart@linux.intel.com> * Rafael J. Wysocki <rafael.j.wysocki@intel.com> * Sakari Ailus <sakari.ailus@linux.intel.com> */ #define pr_fmt(fmt) "ACPI: " fmt #include <linux/acpi.h> #include <linux/device.h> #include <linux/export.h> #include "internal.h" static int acpi_data_get_property_array(const struct acpi_device_data *data, const char *name, acpi_object_type type, const union acpi_object **obj); /* * The GUIDs here are made equivalent to each other in order to avoid extra * complexity in the properties handling code, with the caveat that the * kernel will accept certain combinations of GUID and properties that are * not defined without a warning. For instance if any of the properties * from different GUID appear in a property list of another, it will be * accepted by the kernel. Firmware validation tools should catch these. * * References: * * [1] UEFI DSD Guide. * https://github.com/UEFI/DSD-Guide/blob/main/src/dsd-guide.adoc */ static const guid_t prp_guids[] = { /* ACPI _DSD device properties GUID [1]: daffd814-6eba-4d8c-8a91-bc9bbf4aa301 */ GUID_INIT(0xdaffd814, 0x6eba, 0x4d8c, 0x8a, 0x91, 0xbc, 0x9b, 0xbf, 0x4a, 0xa3, 0x01), /* Hotplug in D3 GUID: 6211e2c0-58a3-4af3-90e1-927a4e0c55a4 */ GUID_INIT(0x6211e2c0, 0x58a3, 0x4af3, 0x90, 0xe1, 0x92, 0x7a, 0x4e, 0x0c, 0x55, 0xa4), /* External facing port GUID: efcc06cc-73ac-4bc3-bff0-76143807c389 */ GUID_INIT(0xefcc06cc, 0x73ac, 0x4bc3, 0xbf, 0xf0, 0x76, 0x14, 0x38, 0x07, 0xc3, 0x89), /* Thunderbolt GUID for IMR_VALID: c44d002f-69f9-4e7d-a904-a7baabdf43f7 */ GUID_INIT(0xc44d002f, 0x69f9, 0x4e7d, 0xa9, 0x04, 0xa7, 0xba, 0xab, 0xdf, 0x43, 0xf7), /* Thunderbolt GUID for WAKE_SUPPORTED: 6c501103-c189-4296-ba72-9bf5a26ebe5d */ GUID_INIT(0x6c501103, 0xc189, 0x4296, 0xba, 0x72, 0x9b, 0xf5, 0xa2, 0x6e, 0xbe, 0x5d), /* Storage device needs D3 GUID: 5025030f-842f-4ab4-a561-99a5189762d0 */ GUID_INIT(0x5025030f, 0x842f, 0x4ab4, 0xa5, 0x61, 0x99, 0xa5, 0x18, 0x97, 0x62, 0xd0), }; /* ACPI _DSD data subnodes GUID [1]: dbb8e3e6-5886-4ba6-8795-1319f52a966b */ static const guid_t ads_guid = GUID_INIT(0xdbb8e3e6, 0x5886, 0x4ba6, 0x87, 0x95, 0x13, 0x19, 0xf5, 0x2a, 0x96, 0x6b); /* ACPI _DSD data buffer GUID [1]: edb12dd0-363d-4085-a3d2-49522ca160c4 */ static const guid_t buffer_prop_guid = GUID_INIT(0xedb12dd0, 0x363d, 0x4085, 0xa3, 0xd2, 0x49, 0x52, 0x2c, 0xa1, 0x60, 0xc4); static bool acpi_enumerate_nondev_subnodes(acpi_handle scope, union acpi_object *desc, struct acpi_device_data *data, struct fwnode_handle *parent); static bool acpi_extract_properties(acpi_handle handle, union acpi_object *desc, struct acpi_device_data *data); static bool acpi_nondev_subnode_extract(union acpi_object *desc, acpi_handle handle, const union acpi_object *link, struct list_head *list, struct fwnode_handle *parent) { struct acpi_data_node *dn; bool result; if (acpi_graph_ignore_port(handle)) return false; dn = kzalloc(sizeof(*dn), GFP_KERNEL); if (!dn) return false; dn->name = link->package.elements[0].string.pointer; fwnode_init(&dn->fwnode, &acpi_data_fwnode_ops); dn->parent = parent; INIT_LIST_HEAD(&dn->data.properties); INIT_LIST_HEAD(&dn->data.subnodes); result = acpi_extract_properties(handle, desc, &dn->data); if (handle) { acpi_handle scope; acpi_status status; /* * The scope for the subnode object lookup is the one of the * namespace node (device) containing the object that has * returned the package. That is, it's the scope of that * object's parent. */ status = acpi_get_parent(handle, &scope); if (ACPI_SUCCESS(status) && acpi_enumerate_nondev_subnodes(scope, desc, &dn->data, &dn->fwnode)) result = true; } else if (acpi_enumerate_nondev_subnodes(NULL, desc, &dn->data, &dn->fwnode)) { result = true; } if (result) { dn->handle = handle; dn->data.pointer = desc; list_add_tail(&dn->sibling, list); return true; } kfree(dn); acpi_handle_debug(handle, "Invalid properties/subnodes data, skipping\n"); return false; } static bool acpi_nondev_subnode_data_ok(acpi_handle handle, const union acpi_object *link, struct list_head *list, struct fwnode_handle *parent) { struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER }; acpi_status status; status = acpi_evaluate_object_typed(handle, NULL, NULL, &buf, ACPI_TYPE_PACKAGE); if (ACPI_FAILURE(status)) return false; if (acpi_nondev_subnode_extract(buf.pointer, handle, link, list, parent)) return true; ACPI_FREE(buf.pointer); return false; } static bool acpi_nondev_subnode_ok(acpi_handle scope, const union acpi_object *link, struct list_head *list, struct fwnode_handle *parent) { acpi_handle handle; acpi_status status; if (!scope) return false; status = acpi_get_handle(scope, link->package.elements[1].string.pointer, &handle); if (ACPI_FAILURE(status)) return false; return acpi_nondev_subnode_data_ok(handle, link, list, parent); } static bool acpi_add_nondev_subnodes(acpi_handle scope, union acpi_object *links, struct list_head *list, struct fwnode_handle *parent) { bool ret = false; int i; for (i = 0; i < links->package.count; i++) { union acpi_object *link, *desc; acpi_handle handle; bool result; link = &links->package.elements[i]; /* Only two elements allowed. */ if (link->package.count != 2) continue; /* The first one must be a string. */ if (link->package.elements[0].type != ACPI_TYPE_STRING) continue; /* The second one may be a string, a reference or a package. */ switch (link->package.elements[1].type) { case ACPI_TYPE_STRING: result = acpi_nondev_subnode_ok(scope, link, list, parent); break; case ACPI_TYPE_LOCAL_REFERENCE: handle = link->package.elements[1].reference.handle; result = acpi_nondev_subnode_data_ok(handle, link, list, parent); break; case ACPI_TYPE_PACKAGE: desc = &link->package.elements[1]; result = acpi_nondev_subnode_extract(desc, NULL, link, list, parent); break; default: result = false; break; } ret = ret || result; } return ret; } static bool acpi_enumerate_nondev_subnodes(acpi_handle scope, union acpi_object *desc, struct acpi_device_data *data, struct fwnode_handle *parent) { int i; /* Look for the ACPI data subnodes GUID. */ for (i = 0; i < desc->package.count; i += 2) { const union acpi_object *guid; union acpi_object *links; guid = &desc->package.elements[i]; links = &desc->package.elements[i + 1]; /* * The first element must be a GUID and the second one must be * a package. */ if (guid->type != ACPI_TYPE_BUFFER || guid->buffer.length != 16 || links->type != ACPI_TYPE_PACKAGE) break; if (!guid_equal((guid_t *)guid->buffer.pointer, &ads_guid)) continue; return acpi_add_nondev_subnodes(scope, links, &data->subnodes, parent); } return false; } static bool acpi_property_value_ok(const union acpi_object *value) { int j; /* * The value must be an integer, a string, a reference, or a package * whose every element must be an integer, a string, or a reference. */ switch (value->type) { case ACPI_TYPE_INTEGER: case ACPI_TYPE_STRING: case ACPI_TYPE_LOCAL_REFERENCE: return true; case ACPI_TYPE_PACKAGE: for (j = 0; j < value->package.count; j++) switch (value->package.elements[j].type) { case ACPI_TYPE_INTEGER: case ACPI_TYPE_STRING: case ACPI_TYPE_LOCAL_REFERENCE: continue; default: return false; } return true; } return false; } static bool acpi_properties_format_valid(const union acpi_object *properties) { int i; for (i = 0; i < properties->package.count; i++) { const union acpi_object *property; property = &properties->package.elements[i]; /* * Only two elements allowed, the first one must be a string and * the second one has to satisfy certain conditions. */ if (property->package.count != 2 || property->package.elements[0].type != ACPI_TYPE_STRING || !acpi_property_value_ok(&property->package.elements[1])) return false; } return true; } static void acpi_init_of_compatible(struct acpi_device *adev) { const union acpi_object *of_compatible; int ret; ret = acpi_data_get_property_array(&adev->data, "compatible", ACPI_TYPE_STRING, &of_compatible); if (ret) { ret = acpi_dev_get_property(adev, "compatible", ACPI_TYPE_STRING, &of_compatible); if (ret) { struct acpi_device *parent; parent = acpi_dev_parent(adev); if (parent && parent->flags.of_compatible_ok) goto out; return; } } adev->data.of_compatible = of_compatible; out: adev->flags.of_compatible_ok = 1; } static bool acpi_is_property_guid(const guid_t *guid) { int i; for (i = 0; i < ARRAY_SIZE(prp_guids); i++) { if (guid_equal(guid, &prp_guids[i])) return true; } return false; } struct acpi_device_properties * acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, union acpi_object *properties) { struct acpi_device_properties *props; props = kzalloc(sizeof(*props), GFP_KERNEL); if (props) { INIT_LIST_HEAD(&props->list); props->guid = guid; props->properties = properties; list_add_tail(&props->list, &data->properties); } return props; } static void acpi_nondev_subnode_tag(acpi_handle handle, void *context) { } static void acpi_untie_nondev_subnodes(struct acpi_device_data *data) { struct acpi_data_node *dn; list_for_each_entry(dn, &data->subnodes, sibling) { acpi_detach_data(dn->handle, acpi_nondev_subnode_tag); acpi_untie_nondev_subnodes(&dn->data); } } static bool acpi_tie_nondev_subnodes(struct acpi_device_data *data) { struct acpi_data_node *dn; list_for_each_entry(dn, &data->subnodes, sibling) { acpi_status status; bool ret; status = acpi_attach_data(dn->handle, acpi_nondev_subnode_tag, dn); if (ACPI_FAILURE(status) && status != AE_ALREADY_EXISTS) { acpi_handle_err(dn->handle, "Can't tag data node\n"); return false; } ret = acpi_tie_nondev_subnodes(&dn->data); if (!ret) return ret; } return true; } static void acpi_data_add_buffer_props(acpi_handle handle, struct acpi_device_data *data, union acpi_object *properties) { struct acpi_device_properties *props; union acpi_object *package; size_t alloc_size; unsigned int i; u32 *count; if (check_mul_overflow((size_t)properties->package.count, sizeof(*package) + sizeof(void *), &alloc_size) || check_add_overflow(sizeof(*props) + sizeof(*package), alloc_size, &alloc_size)) { acpi_handle_warn(handle, "can't allocate memory for %u buffer props", properties->package.count); return; } props = kvzalloc(alloc_size, GFP_KERNEL); if (!props) return; props->guid = &buffer_prop_guid; props->bufs = (void *)(props + 1); props->properties = (void *)(props->bufs + properties->package.count); /* Outer package */ package = props->properties; package->type = ACPI_TYPE_PACKAGE; package->package.elements = package + 1; count = &package->package.count; *count = 0; /* Inner packages */ package++; for (i = 0; i < properties->package.count; i++) { struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER }; union acpi_object *property = &properties->package.elements[i]; union acpi_object *prop, *obj, *buf_obj; acpi_status status; if (property->type != ACPI_TYPE_PACKAGE || property->package.count != 2) { acpi_handle_warn(handle, "buffer property %u has %u entries\n", i, property->package.count); continue; } prop = &property->package.elements[0]; obj = &property->package.elements[1]; if (prop->type != ACPI_TYPE_STRING || obj->type != ACPI_TYPE_STRING) { acpi_handle_warn(handle, "wrong object types %u and %u\n", prop->type, obj->type); continue; } status = acpi_evaluate_object_typed(handle, obj->string.pointer, NULL, &buf, ACPI_TYPE_BUFFER); if (ACPI_FAILURE(status)) { acpi_handle_warn(handle, "can't evaluate \"%*pE\" as buffer\n", obj->string.length, obj->string.pointer); continue; } package->type = ACPI_TYPE_PACKAGE; package->package.elements = prop; package->package.count = 2; buf_obj = buf.pointer; /* Replace the string object with a buffer object */ obj->type = ACPI_TYPE_BUFFER; obj->buffer.length = buf_obj->buffer.length; obj->buffer.pointer = buf_obj->buffer.pointer; props->bufs[i] = buf.pointer; package++; (*count)++; } if (*count) list_add(&props->list, &data->properties); else kvfree(props); } static bool acpi_extract_properties(acpi_handle scope, union acpi_object *desc, struct acpi_device_data *data) { int i; if (desc->package.count % 2) return false; /* Look for the device properties GUID. */ for (i = 0; i < desc->package.count; i += 2) { const union acpi_object *guid; union acpi_object *properties; guid = &desc->package.elements[i]; properties = &desc->package.elements[i + 1]; /* * The first element must be a GUID and the second one must be * a package. */ if (guid->type != ACPI_TYPE_BUFFER || guid->buffer.length != 16 || properties->type != ACPI_TYPE_PACKAGE) break; if (guid_equal((guid_t *)guid->buffer.pointer, &buffer_prop_guid)) { acpi_data_add_buffer_props(scope, data, properties); continue; } if (!acpi_is_property_guid((guid_t *)guid->buffer.pointer)) continue; /* * We found the matching GUID. Now validate the format of the * package immediately following it. */ if (!acpi_properties_format_valid(properties)) continue; acpi_data_add_props(data, (const guid_t *)guid->buffer.pointer, properties); } return !list_empty(&data->properties); } void acpi_init_properties(struct acpi_device *adev) { struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER }; struct acpi_hardware_id *hwid; acpi_status status; bool acpi_of = false; INIT_LIST_HEAD(&adev->data.properties); INIT_LIST_HEAD(&adev->data.subnodes); if (!adev->handle) return; /* * Check if ACPI_DT_NAMESPACE_HID is present and inthat case we fill in * Device Tree compatible properties for this device. */ list_for_each_entry(hwid, &adev->pnp.ids, list) { if (!strcmp(hwid->id, ACPI_DT_NAMESPACE_HID)) { acpi_of = true; break; } } status = acpi_evaluate_object_typed(adev->handle, "_DSD", NULL, &buf, ACPI_TYPE_PACKAGE); if (ACPI_FAILURE(status)) goto out; if (acpi_extract_properties(adev->handle, buf.pointer, &adev->data)) { adev->data.pointer = buf.pointer; if (acpi_of) acpi_init_of_compatible(adev); } if (acpi_enumerate_nondev_subnodes(adev->handle, buf.pointer, &adev->data, acpi_fwnode_handle(adev))) adev->data.pointer = buf.pointer; if (!adev->data.pointer) { acpi_handle_debug(adev->handle, "Invalid _DSD data, skipping\n"); ACPI_FREE(buf.pointer); } else { if (!acpi_tie_nondev_subnodes(&adev->data)) acpi_untie_nondev_subnodes(&adev->data); } out: if (acpi_of && !adev->flags.of_compatible_ok) acpi_handle_info(adev->handle, ACPI_DT_NAMESPACE_HID " requires 'compatible' property\n"); if (!adev->data.pointer) acpi_extract_apple_properties(adev); } static void acpi_free_device_properties(struct list_head *list) { struct acpi_device_properties *props, *tmp; list_for_each_entry_safe(props, tmp, list, list) { u32 i; list_del(&props->list); /* Buffer data properties were separately allocated */ if (props->bufs) for (i = 0; i < props->properties->package.count; i++) ACPI_FREE(props->bufs[i]); kvfree(props); } } static void acpi_destroy_nondev_subnodes(struct list_head *list) { struct acpi_data_node *dn, *next; if (list_empty(list)) return; list_for_each_entry_safe_reverse(dn, next, list, sibling) { acpi_destroy_nondev_subnodes(&dn->data.subnodes); wait_for_completion(&dn->kobj_done); list_del(&dn->sibling); ACPI_FREE((void *)dn->data.pointer); acpi_free_device_properties(&dn->data.properties); kfree(dn); } } void acpi_free_properties(struct acpi_device *adev) { acpi_untie_nondev_subnodes(&adev->data); acpi_destroy_nondev_subnodes(&adev->data.subnodes); ACPI_FREE((void *)adev->data.pointer); adev->data.of_compatible = NULL; adev->data.pointer = NULL; acpi_free_device_properties(&adev->data.properties); } /** * acpi_data_get_property - return an ACPI property with given name * @data: ACPI device deta object to get the property from * @name: Name of the property * @type: Expected property type * @obj: Location to store the property value (if not %NULL) * * Look up a property with @name and store a pointer to the resulting ACPI * object at the location pointed to by @obj if found. * * Callers must not attempt to free the returned objects. These objects will be * freed by the ACPI core automatically during the removal of @data. * * Return: %0 if property with @name has been found (success), * %-EINVAL if the arguments are invalid, * %-EINVAL if the property doesn't exist, * %-EPROTO if the property value type doesn't match @type. */ static int acpi_data_get_property(const struct acpi_device_data *data, const char *name, acpi_object_type type, const union acpi_object **obj) { const struct acpi_device_properties *props; if (!data || !name) return -EINVAL; if (!data->pointer || list_empty(&data->properties)) return -EINVAL; list_for_each_entry(props, &data->properties, list) { const union acpi_object *properties; unsigned int i; properties = props->properties; for (i = 0; i < properties->package.count; i++) { const union acpi_object *propname, *propvalue; const union acpi_object *property; property = &properties->package.elements[i]; propname = &property->package.elements[0]; propvalue = &property->package.elements[1]; if (!strcmp(name, propname->string.pointer)) { if (type != ACPI_TYPE_ANY && propvalue->type != type) return -EPROTO; if (obj) *obj = propvalue; return 0; } } } return -EINVAL; } /** * acpi_dev_get_property - return an ACPI property with given name. * @adev: ACPI device to get the property from. * @name: Name of the property. * @type: Expected property type. * @obj: Location to store the property value (if not %NULL). */ int acpi_dev_get_property(const struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj) { return adev ? acpi_data_get_property(&adev->data, name, type, obj) : -EINVAL; } EXPORT_SYMBOL_GPL(acpi_dev_get_property); static const struct acpi_device_data * acpi_device_data_of_node(const struct fwnode_handle *fwnode) { if (is_acpi_device_node(fwnode)) { const struct acpi_device *adev = to_acpi_device_node(fwnode); return &adev->data; } if (is_acpi_data_node(fwnode)) { const struct acpi_data_node *dn = to_acpi_data_node(fwnode); return &dn->data; } return NULL; } /** * acpi_node_prop_get - return an ACPI property with given name. * @fwnode: Firmware node to get the property from. * @propname: Name of the property. * @valptr: Location to store a pointer to the property value (if not %NULL). */ int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr) { return acpi_data_get_property(acpi_device_data_of_node(fwnode), propname, ACPI_TYPE_ANY, (const union acpi_object **)valptr); } /** * acpi_data_get_property_array - return an ACPI array property with given name * @data: ACPI data object to get the property from * @name: Name of the property * @type: Expected type of array elements * @obj: Location to store a pointer to the property value (if not NULL) * * Look up an array property with @name and store a pointer to the resulting * ACPI object at the location pointed to by @obj if found. * * Callers must not attempt to free the returned objects. Those objects will be * freed by the ACPI core automatically during the removal of @data. * * Return: %0 if array property (package) with @name has been found (success), * %-EINVAL if the arguments are invalid, * %-EINVAL if the property doesn't exist, * %-EPROTO if the property is not a package or the type of its elements * doesn't match @type. */ static int acpi_data_get_property_array(const struct acpi_device_data *data, const char *name, acpi_object_type type, const union acpi_object **obj) { const union acpi_object *prop; int ret, i; ret = acpi_data_get_property(data, name, ACPI_TYPE_PACKAGE, &prop); if (ret) return ret; if (type != ACPI_TYPE_ANY) { /* Check that all elements are of correct type. */ for (i = 0; i < prop->package.count; i++) if (prop->package.elements[i].type != type) return -EPROTO; } if (obj) *obj = prop; return 0; } static struct fwnode_handle * acpi_fwnode_get_named_child_node(const struct fwnode_handle *fwnode, const char *childname) { struct fwnode_handle *child; fwnode_for_each_child_node(fwnode, child) { if (is_acpi_data_node(child)) { if (acpi_data_node_match(child, childname)) return child; continue; } if (!strncmp(acpi_device_bid(to_acpi_device_node(child)), childname, ACPI_NAMESEG_SIZE)) return child; } return NULL; } static int acpi_get_ref_args(struct fwnode_reference_args *args, struct fwnode_handle *ref_fwnode, const union acpi_object **element, const union acpi_object *end, size_t num_args) { u32 nargs = 0, i; /* * Assume the following integer elements are all args. Stop counting on * the first reference (possibly represented as a string) or end of the * package arguments. In case of neither reference, nor integer, return * an error, we can't parse it. */ for (i = 0; (*element) + i < end && i < num_args; i++) { acpi_object_type type = (*element)[i].type; if (type == ACPI_TYPE_LOCAL_REFERENCE || type == ACPI_TYPE_STRING) break; if (type == ACPI_TYPE_INTEGER) nargs++; else return -EINVAL; } if (nargs > NR_FWNODE_REFERENCE_ARGS) return -EINVAL; if (args) { args->fwnode = ref_fwnode; args->nargs = nargs; for (i = 0; i < nargs; i++) args->args[i] = (*element)[i].integer.value; } (*element) += nargs; return 0; } static struct fwnode_handle *acpi_parse_string_ref(const struct fwnode_handle *fwnode, const char *refstring) { acpi_handle scope, handle; struct acpi_data_node *dn; struct acpi_device *device; acpi_status status; if (is_acpi_device_node(fwnode)) { scope = to_acpi_device_node(fwnode)->handle; } else if (is_acpi_data_node(fwnode)) { scope = to_acpi_data_node(fwnode)->handle; } else { pr_debug("Bad node type for node %pfw\n", fwnode); return NULL; } status = acpi_get_handle(scope, refstring, &handle); if (ACPI_FAILURE(status)) { acpi_handle_debug(scope, "Unable to get an ACPI handle for %s\n", refstring); return NULL; } device = acpi_fetch_acpi_dev(handle); if (device) return acpi_fwnode_handle(device); status = acpi_get_data_full(handle, acpi_nondev_subnode_tag, (void **)&dn, NULL); if (ACPI_FAILURE(status) || !dn) { acpi_handle_debug(handle, "Subnode not found\n"); return NULL; } return &dn->fwnode; } /** * __acpi_node_get_property_reference - returns handle to the referenced object * @fwnode: Firmware node to get the property from * @propname: Name of the property * @index: Index of the reference to return * @num_args: Maximum number of arguments after each reference * @args: Location to store the returned reference with optional arguments * (may be NULL) * * Find property with @name, verifify that it is a package containing at least * one object reference and if so, store the ACPI device object pointer to the * target object in @args->adev. If the reference includes arguments, store * them in the @args->args[] array. * * If there's more than one reference in the property value package, @index is * used to select the one to return. * * It is possible to leave holes in the property value set like in the * example below: * * Package () { * "cs-gpios", * Package () { * ^GPIO, 19, 0, 0, * ^GPIO, 20, 0, 0, * 0, * ^GPIO, 21, 0, 0, * } * } * * Calling this function with index %2 or index %3 return %-ENOENT. If the * property does not contain any more values %-ENOENT is returned. The NULL * entry must be single integer and preferably contain value %0. * * Return: %0 on success, negative error code on failure. */ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *propname, size_t index, size_t num_args, struct fwnode_reference_args *args) { const union acpi_object *element, *end; const union acpi_object *obj; const struct acpi_device_data *data; struct fwnode_handle *ref_fwnode; struct acpi_device *device; int ret, idx = 0; data = acpi_device_data_of_node(fwnode); if (!data) return -ENOENT; ret = acpi_data_get_property(data, propname, ACPI_TYPE_ANY, &obj); if (ret) return ret == -EINVAL ? -ENOENT : -EINVAL; switch (obj->type) { case ACPI_TYPE_LOCAL_REFERENCE: /* Plain single reference without arguments. */ if (index) return -ENOENT; device = acpi_fetch_acpi_dev(obj->reference.handle); if (!device) return -EINVAL; if (!args) return 0; args->fwnode = acpi_fwnode_handle(device); args->nargs = 0; return 0; case ACPI_TYPE_STRING: if (index) return -ENOENT; ref_fwnode = acpi_parse_string_ref(fwnode, obj->string.pointer); if (!ref_fwnode) return -EINVAL; args->fwnode = ref_fwnode; args->nargs = 0; return 0; case ACPI_TYPE_PACKAGE: /* * If it is not a single reference, then it is a package of * references, followed by number of ints as follows: * * Package () { REF, INT, REF, INT, INT } * * Here, REF may be either a local reference or a string. The * index argument is then used to determine which reference the * caller wants (along with the arguments). */ break; default: return -EINVAL; } if (index >= obj->package.count) return -ENOENT; element = obj->package.elements; end = element + obj->package.count; while (element < end) { switch (element->type) { case ACPI_TYPE_LOCAL_REFERENCE: device = acpi_fetch_acpi_dev(element->reference.handle); if (!device) return -EINVAL; element++; ret = acpi_get_ref_args(idx == index ? args : NULL, acpi_fwnode_handle(device), &element, end, num_args); if (ret < 0) return ret; if (idx == index) return 0; break; case ACPI_TYPE_STRING: ref_fwnode = acpi_parse_string_ref(fwnode, element->string.pointer); if (!ref_fwnode) return -EINVAL; element++; ret = acpi_get_ref_args(idx == index ? args : NULL, ref_fwnode, &element, end, num_args); if (ret < 0) return ret; if (idx == index) return 0; break; case ACPI_TYPE_INTEGER: if (idx == index) return -ENOENT; element++; break; default: return -EINVAL; } idx++; } return -ENOENT; } EXPORT_SYMBOL_GPL(__acpi_node_get_property_reference); static int acpi_data_prop_read_single(const struct acpi_device_data *data, const char *propname, enum dev_prop_type proptype, void *val) { const union acpi_object *obj; int ret = 0; if (proptype >= DEV_PROP_U8 && proptype <= DEV_PROP_U64) ret = acpi_data_get_property(data, propname, ACPI_TYPE_INTEGER, &obj); else if (proptype == DEV_PROP_STRING) ret = acpi_data_get_property(data, propname, ACPI_TYPE_STRING, &obj); if (ret) return ret; switch (proptype) { case DEV_PROP_U8: if (obj->integer.value > U8_MAX) return -EOVERFLOW; if (val) *(u8 *)val = obj->integer.value; break; case DEV_PROP_U16: if (obj->integer.value > U16_MAX) return -EOVERFLOW; if (val) *(u16 *)val = obj->integer.value; break; case DEV_PROP_U32: if (obj->integer.value > U32_MAX) return -EOVERFLOW; if (val) *(u32 *)val = obj->integer.value; break; case DEV_PROP_U64: if (val) *(u64 *)val = obj->integer.value; break; case DEV_PROP_STRING: if (val) *(char **)val = obj->string.pointer; return 1; default: return -EINVAL; } /* When no storage provided return number of available values */ return val ? 0 : 1; } #define acpi_copy_property_array_uint(items, val, nval) \ ({ \ typeof(items) __items = items; \ typeof(val) __val = val; \ typeof(nval) __nval = nval; \ size_t i; \ int ret = 0; \ \ for (i = 0; i < __nval; i++) { \ if (__items->type == ACPI_TYPE_BUFFER) { \ __val[i] = __items->buffer.pointer[i]; \ continue; \ } \ if (__items[i].type != ACPI_TYPE_INTEGER) { \ ret = -EPROTO; \ break; \ } \ if (__items[i].integer.value > _Generic(__val, \ u8 *: U8_MAX, \ u16 *: U16_MAX, \ u32 *: U32_MAX, \ u64 *: U64_MAX)) { \ ret = -EOVERFLOW; \ break; \ } \ \ __val[i] = __items[i].integer.value; \ } \ ret; \ }) static int acpi_copy_property_array_string(const union acpi_object *items, char **val, size_t nval) { int i; for (i = 0; i < nval; i++) { if (items[i].type != ACPI_TYPE_STRING) return -EPROTO; val[i] = items[i].string.pointer; } return nval; } static int acpi_data_prop_read(const struct acpi_device_data *data, const char *propname, enum dev_prop_type proptype, void *val, size_t nval) { const union acpi_object *obj; const union acpi_object *items; int ret; if (nval == 1 || !val) { ret = acpi_data_prop_read_single(data, propname, proptype, val); /* * The overflow error means that the property is there and it is * single-value, but its type does not match, so return. */ if (ret >= 0 || ret == -EOVERFLOW) return ret; /* * Reading this property as a single-value one failed, but its * value may still be represented as one-element array, so * continue. */ } ret = acpi_data_get_property_array(data, propname, ACPI_TYPE_ANY, &obj); if (ret && proptype >= DEV_PROP_U8 && proptype <= DEV_PROP_U64) ret = acpi_data_get_property(data, propname, ACPI_TYPE_BUFFER, &obj); if (ret) return ret; if (!val) { if (obj->type == ACPI_TYPE_BUFFER) return obj->buffer.length; return obj->package.count; } switch (proptype) { case DEV_PROP_STRING: break; default: if (obj->type == ACPI_TYPE_BUFFER) { if (nval > obj->buffer.length) return -EOVERFLOW; } else { if (nval > obj->package.count) return -EOVERFLOW; } break; } if (obj->type == ACPI_TYPE_BUFFER) { if (proptype != DEV_PROP_U8) return -EPROTO; items = obj; } else { items = obj->package.elements; } switch (proptype) { case DEV_PROP_U8: ret = acpi_copy_property_array_uint(items, (u8 *)val, nval); break; case DEV_PROP_U16: ret = acpi_copy_property_array_uint(items, (u16 *)val, nval); break; case DEV_PROP_U32: ret = acpi_copy_property_array_uint(items, (u32 *)val, nval); break; case DEV_PROP_U64: ret = acpi_copy_property_array_uint(items, (u64 *)val, nval); break; case DEV_PROP_STRING: nval = min_t(u32, nval, obj->package.count); if (nval == 0) return -ENODATA; ret = acpi_copy_property_array_string(items, (char **)val, nval); break; default: ret = -EINVAL; break; } return ret; } /** * acpi_node_prop_read - retrieve the value of an ACPI property with given name. * @fwnode: Firmware node to get the property from. * @propname: Name of the property. * @proptype: Expected property type. * @val: Location to store the property value (if not %NULL). * @nval: Size of the array pointed to by @val. * * If @val is %NULL, return the number of array elements comprising the value * of the property. Otherwise, read at most @nval values to the array at the * location pointed to by @val. */ static int acpi_node_prop_read(const struct fwnode_handle *fwnode, const char *propname, enum dev_prop_type proptype, void *val, size_t nval) { return acpi_data_prop_read(acpi_device_data_of_node(fwnode), propname, proptype, val, nval); } static int stop_on_next(struct acpi_device *adev, void *data) { struct acpi_device **ret_p = data; if (!*ret_p) { *ret_p = adev; return 1; } /* Skip until the "previous" object is found. */ if (*ret_p == adev) *ret_p = NULL; return 0; } /** * acpi_get_next_subnode - Return the next child node handle for a fwnode * @fwnode: Firmware node to find the next child node for. * @child: Handle to one of the device's child nodes or a null handle. */ struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { struct acpi_device *adev = to_acpi_device_node(fwnode); if ((!child || is_acpi_device_node(child)) && adev) { struct acpi_device *child_adev = to_acpi_device_node(child); acpi_dev_for_each_child(adev, stop_on_next, &child_adev); if (child_adev) return acpi_fwnode_handle(child_adev); child = NULL; } if (!child || is_acpi_data_node(child)) { const struct acpi_data_node *data = to_acpi_data_node(fwnode); const struct list_head *head; struct list_head *next; struct acpi_data_node *dn; /* * We can have a combination of device and data nodes, e.g. with * hierarchical _DSD properties. Make sure the adev pointer is * restored before going through data nodes, otherwise we will * be looking for data_nodes below the last device found instead * of the common fwnode shared by device_nodes and data_nodes. */ adev = to_acpi_device_node(fwnode); if (adev) head = &adev->data.subnodes; else if (data) head = &data->data.subnodes; else return NULL; if (list_empty(head)) return NULL; if (child) { dn = to_acpi_data_node(child); next = dn->sibling.next; if (next == head) return NULL; dn = list_entry(next, struct acpi_data_node, sibling); } else { dn = list_first_entry(head, struct acpi_data_node, sibling); } return &dn->fwnode; } return NULL; } /** * acpi_node_get_parent - Return parent fwnode of this fwnode * @fwnode: Firmware node whose parent to get * * Returns parent node of an ACPI device or data firmware node or %NULL if * not available. */ static struct fwnode_handle * acpi_node_get_parent(const struct fwnode_handle *fwnode) { if (is_acpi_data_node(fwnode)) { /* All data nodes have parent pointer so just return that */ return to_acpi_data_node(fwnode)->parent; } if (is_acpi_device_node(fwnode)) { struct acpi_device *parent; parent = acpi_dev_parent(to_acpi_device_node(fwnode)); if (parent) return acpi_fwnode_handle(parent); } return NULL; } /* * Return true if the node is an ACPI graph node. Called on either ports * or endpoints. */ static bool is_acpi_graph_node(struct fwnode_handle *fwnode, const char *str) { unsigned int len = strlen(str); const char *name; if (!len || !is_acpi_data_node(fwnode)) return false; name = to_acpi_data_node(fwnode)->name; return (fwnode_property_present(fwnode, "reg") && !strncmp(name, str, len) && name[len] == '@') || fwnode_property_present(fwnode, str); } /** * acpi_graph_get_next_endpoint - Get next endpoint ACPI firmware node * @fwnode: Pointer to the parent firmware node * @prev: Previous endpoint node or %NULL to get the first * * Looks up next endpoint ACPI firmware node below a given @fwnode. Returns * %NULL if there is no next endpoint or in case of error. In case of success * the next endpoint is returned. */ static struct fwnode_handle *acpi_graph_get_next_endpoint( const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { struct fwnode_handle *port = NULL; struct fwnode_handle *endpoint; if (!prev) { do { port = fwnode_get_next_child_node(fwnode, port); /* * The names of the port nodes begin with "port@" * followed by the number of the port node and they also * have a "reg" property that also has the number of the * port node. For compatibility reasons a node is also * recognised as a port node from the "port" property. */ if (is_acpi_graph_node(port, "port")) break; } while (port); } else { port = fwnode_get_parent(prev); } if (!port) return NULL; endpoint = fwnode_get_next_child_node(port, prev); while (!endpoint) { port = fwnode_get_next_child_node(fwnode, port); if (!port) break; if (is_acpi_graph_node(port, "port")) endpoint = fwnode_get_next_child_node(port, NULL); } /* * The names of the endpoint nodes begin with "endpoint@" followed by * the number of the endpoint node and they also have a "reg" property * that also has the number of the endpoint node. For compatibility * reasons a node is also recognised as an endpoint node from the * "endpoint" property. */ if (!is_acpi_graph_node(endpoint, "endpoint")) return NULL; return endpoint; } /** * acpi_graph_get_child_prop_value - Return a child with a given property value * @fwnode: device fwnode * @prop_name: The name of the property to look for * @val: the desired property value * * Return the port node corresponding to a given port number. Returns * the child node on success, NULL otherwise. */ static struct fwnode_handle *acpi_graph_get_child_prop_value( const struct fwnode_handle *fwnode, const char *prop_name, unsigned int val) { struct fwnode_handle *child; fwnode_for_each_child_node(fwnode, child) { u32 nr; if (fwnode_property_read_u32(child, prop_name, &nr)) continue; if (val == nr) return child; } return NULL; } /** * acpi_graph_get_remote_endpoint - Parses and returns remote end of an endpoint * @__fwnode: Endpoint firmware node pointing to a remote device * * Returns the remote endpoint corresponding to @__fwnode. NULL on error. */ static struct fwnode_handle * acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode) { struct fwnode_handle *fwnode; unsigned int port_nr, endpoint_nr; struct fwnode_reference_args args; int ret; memset(&args, 0, sizeof(args)); ret = acpi_node_get_property_reference(__fwnode, "remote-endpoint", 0, &args); if (ret) return NULL; /* Direct endpoint reference? */ if (!is_acpi_device_node(args.fwnode)) return args.nargs ? NULL : args.fwnode; /* * Always require two arguments with the reference: port and * endpoint indices. */ if (args.nargs != 2) return NULL; fwnode = args.fwnode; port_nr = args.args[0]; endpoint_nr = args.args[1]; fwnode = acpi_graph_get_child_prop_value(fwnode, "port", port_nr); return acpi_graph_get_child_prop_value(fwnode, "endpoint", endpoint_nr); } static bool acpi_fwnode_device_is_available(const struct fwnode_handle *fwnode) { if (!is_acpi_device_node(fwnode)) return true; return acpi_device_is_present(to_acpi_device_node(fwnode)); } static const void * acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode, const struct device *dev) { return acpi_device_get_match_data(dev); } static bool acpi_fwnode_device_dma_supported(const struct fwnode_handle *fwnode) { return acpi_dma_supported(to_acpi_device_node(fwnode)); } static enum dev_dma_attr acpi_fwnode_device_get_dma_attr(const struct fwnode_handle *fwnode) { return acpi_get_dma_attr(to_acpi_device_node(fwnode)); } static bool acpi_fwnode_property_present(const struct fwnode_handle *fwnode, const char *propname) { return !acpi_node_prop_get(fwnode, propname, NULL); } static int acpi_fwnode_property_read_int_array(const struct fwnode_handle *fwnode, const char *propname, unsigned int elem_size, void *val, size_t nval) { enum dev_prop_type type; switch (elem_size) { case sizeof(u8): type = DEV_PROP_U8; break; case sizeof(u16): type = DEV_PROP_U16; break; case sizeof(u32): type = DEV_PROP_U32; break; case sizeof(u64): type = DEV_PROP_U64; break; default: return -ENXIO; } return acpi_node_prop_read(fwnode, propname, type, val, nval); } static int acpi_fwnode_property_read_string_array(const struct fwnode_handle *fwnode, const char *propname, const char **val, size_t nval) { return acpi_node_prop_read(fwnode, propname, DEV_PROP_STRING, val, nval); } static int acpi_fwnode_get_reference_args(const struct fwnode_handle *fwnode, const char *prop, const char *nargs_prop, unsigned int args_count, unsigned int index, struct fwnode_reference_args *args) { return __acpi_node_get_property_reference(fwnode, prop, index, args_count, args); } static const char *acpi_fwnode_get_name(const struct fwnode_handle *fwnode) { const struct acpi_device *adev; struct fwnode_handle *parent; /* Is this the root node? */ parent = fwnode_get_parent(fwnode); if (!parent) return "\\"; fwnode_handle_put(parent); if (is_acpi_data_node(fwnode)) { const struct acpi_data_node *dn = to_acpi_data_node(fwnode); return dn->name; } adev = to_acpi_device_node(fwnode); if (WARN_ON(!adev)) return NULL; return acpi_device_bid(adev); } static const char * acpi_fwnode_get_name_prefix(const struct fwnode_handle *fwnode) { struct fwnode_handle *parent; /* Is this the root node? */ parent = fwnode_get_parent(fwnode); if (!parent) return ""; /* Is this 2nd node from the root? */ parent = fwnode_get_next_parent(parent); if (!parent) return ""; fwnode_handle_put(parent); /* ACPI device or data node. */ return "."; } static struct fwnode_handle * acpi_fwnode_get_parent(struct fwnode_handle *fwnode) { return acpi_node_get_parent(fwnode); } static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint) { struct fwnode_handle *port_fwnode = fwnode_get_parent(fwnode); endpoint->local_fwnode = fwnode; if (fwnode_property_read_u32(port_fwnode, "reg", &endpoint->port)) fwnode_property_read_u32(port_fwnode, "port", &endpoint->port); if (fwnode_property_read_u32(fwnode, "reg", &endpoint->id)) fwnode_property_read_u32(fwnode, "endpoint", &endpoint->id); return 0; } static int acpi_fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index) { struct resource res; int ret; ret = acpi_irq_get(ACPI_HANDLE_FWNODE(fwnode), index, &res); if (ret) return ret; return res.start; } #define DECLARE_ACPI_FWNODE_OPS(ops) \ const struct fwnode_operations ops = { \ .device_is_available = acpi_fwnode_device_is_available, \ .device_get_match_data = acpi_fwnode_device_get_match_data, \ .device_dma_supported = \ acpi_fwnode_device_dma_supported, \ .device_get_dma_attr = acpi_fwnode_device_get_dma_attr, \ .property_present = acpi_fwnode_property_present, \ .property_read_bool = acpi_fwnode_property_present, \ .property_read_int_array = \ acpi_fwnode_property_read_int_array, \ .property_read_string_array = \ acpi_fwnode_property_read_string_array, \ .get_parent = acpi_node_get_parent, \ .get_next_child_node = acpi_get_next_subnode, \ .get_named_child_node = acpi_fwnode_get_named_child_node, \ .get_name = acpi_fwnode_get_name, \ .get_name_prefix = acpi_fwnode_get_name_prefix, \ .get_reference_args = acpi_fwnode_get_reference_args, \ .graph_get_next_endpoint = \ acpi_graph_get_next_endpoint, \ .graph_get_remote_endpoint = \ acpi_graph_get_remote_endpoint, \ .graph_get_port_parent = acpi_fwnode_get_parent, \ .graph_parse_endpoint = acpi_fwnode_graph_parse_endpoint, \ .irq_get = acpi_fwnode_irq_get, \ }; \ EXPORT_SYMBOL_GPL(ops) DECLARE_ACPI_FWNODE_OPS(acpi_device_fwnode_ops); DECLARE_ACPI_FWNODE_OPS(acpi_data_fwnode_ops); const struct fwnode_operations acpi_static_fwnode_ops; bool is_acpi_device_node(const struct fwnode_handle *fwnode) { return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &acpi_device_fwnode_ops; } EXPORT_SYMBOL(is_acpi_device_node); bool is_acpi_data_node(const struct fwnode_handle *fwnode) { return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &acpi_data_fwnode_ops; } EXPORT_SYMBOL(is_acpi_data_node); |
| 3 11 10 10 1 5 3 2 2 3 1 2 4 1 3 10 1 9 3 2 2 3 1 2 2 1 1 2 2 9 1 4 2 1 1 3 5 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 | /* * Copyright (c) 2007, 2020 Oracle and/or its affiliates. * * 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/pagemap.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/dma-mapping.h> /* for DMA_*_DEVICE */ #include "rds.h" /* * XXX * - build with sparse * - should we detect duplicate keys on a socket? hmm. * - an rdma is an mlock, apply rlimit? */ /* * get the number of pages by looking at the page indices that the start and * end addresses fall in. * * Returns 0 if the vec is invalid. It is invalid if the number of bytes * causes the address to wrap or overflows an unsigned int. This comes * from being stored in the 'length' member of 'struct scatterlist'. */ static unsigned int rds_pages_in_vec(struct rds_iovec *vec) { if ((vec->addr + vec->bytes <= vec->addr) || (vec->bytes > (u64)UINT_MAX)) return 0; return ((vec->addr + vec->bytes + PAGE_SIZE - 1) >> PAGE_SHIFT) - (vec->addr >> PAGE_SHIFT); } static struct rds_mr *rds_mr_tree_walk(struct rb_root *root, u64 key, struct rds_mr *insert) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct rds_mr *mr; while (*p) { parent = *p; mr = rb_entry(parent, struct rds_mr, r_rb_node); if (key < mr->r_key) p = &(*p)->rb_left; else if (key > mr->r_key) p = &(*p)->rb_right; else return mr; } if (insert) { rb_link_node(&insert->r_rb_node, parent, p); rb_insert_color(&insert->r_rb_node, root); kref_get(&insert->r_kref); } return NULL; } /* * Destroy the transport-specific part of a MR. */ static void rds_destroy_mr(struct rds_mr *mr) { struct rds_sock *rs = mr->r_sock; void *trans_private = NULL; unsigned long flags; rdsdebug("RDS: destroy mr key is %x refcnt %u\n", mr->r_key, kref_read(&mr->r_kref)); spin_lock_irqsave(&rs->rs_rdma_lock, flags); if (!RB_EMPTY_NODE(&mr->r_rb_node)) rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); trans_private = mr->r_trans_private; mr->r_trans_private = NULL; spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (trans_private) mr->r_trans->free_mr(trans_private, mr->r_invalidate); } void __rds_put_mr_final(struct kref *kref) { struct rds_mr *mr = container_of(kref, struct rds_mr, r_kref); rds_destroy_mr(mr); kfree(mr); } /* * By the time this is called we can't have any more ioctls called on * the socket so we don't need to worry about racing with others. */ void rds_rdma_drop_keys(struct rds_sock *rs) { struct rds_mr *mr; struct rb_node *node; unsigned long flags; /* Release any MRs associated with this socket */ spin_lock_irqsave(&rs->rs_rdma_lock, flags); while ((node = rb_first(&rs->rs_rdma_keys))) { mr = rb_entry(node, struct rds_mr, r_rb_node); if (mr->r_trans == rs->rs_transport) mr->r_invalidate = 0; rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); RB_CLEAR_NODE(&mr->r_rb_node); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); kref_put(&mr->r_kref, __rds_put_mr_final); spin_lock_irqsave(&rs->rs_rdma_lock, flags); } spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (rs->rs_transport && rs->rs_transport->flush_mrs) rs->rs_transport->flush_mrs(); } /* * Helper function to pin user pages. */ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages, struct page **pages, int write) { unsigned int gup_flags = FOLL_LONGTERM; int ret; if (write) gup_flags |= FOLL_WRITE; ret = pin_user_pages_fast(user_addr, nr_pages, gup_flags, pages); if (ret >= 0 && ret < nr_pages) { unpin_user_pages(pages, ret); ret = -EFAULT; } return ret; } static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, u64 *cookie_ret, struct rds_mr **mr_ret, struct rds_conn_path *cp) { struct rds_mr *mr = NULL, *found; struct scatterlist *sg = NULL; unsigned int nr_pages; struct page **pages = NULL; void *trans_private; unsigned long flags; rds_rdma_cookie_t cookie; unsigned int nents = 0; int need_odp = 0; long i; int ret; if (ipv6_addr_any(&rs->rs_bound_addr) || !rs->rs_transport) { ret = -ENOTCONN; /* XXX not a great errno */ goto out; } if (!rs->rs_transport->get_mr) { ret = -EOPNOTSUPP; goto out; } /* If the combination of the addr and size requested for this memory * region causes an integer overflow, return error. */ if (((args->vec.addr + args->vec.bytes) < args->vec.addr) || PAGE_ALIGN(args->vec.addr + args->vec.bytes) < (args->vec.addr + args->vec.bytes)) { ret = -EINVAL; goto out; } if (!can_do_mlock()) { ret = -EPERM; goto out; } nr_pages = rds_pages_in_vec(&args->vec); if (nr_pages == 0) { ret = -EINVAL; goto out; } /* Restrict the size of mr irrespective of underlying transport * To account for unaligned mr regions, subtract one from nr_pages */ if ((nr_pages - 1) > (RDS_MAX_MSG_SIZE >> PAGE_SHIFT)) { ret = -EMSGSIZE; goto out; } rdsdebug("RDS: get_mr addr %llx len %llu nr_pages %u\n", args->vec.addr, args->vec.bytes, nr_pages); /* XXX clamp nr_pages to limit the size of this alloc? */ pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) { ret = -ENOMEM; goto out; } mr = kzalloc(sizeof(struct rds_mr), GFP_KERNEL); if (!mr) { ret = -ENOMEM; goto out; } kref_init(&mr->r_kref); RB_CLEAR_NODE(&mr->r_rb_node); mr->r_trans = rs->rs_transport; mr->r_sock = rs; if (args->flags & RDS_RDMA_USE_ONCE) mr->r_use_once = 1; if (args->flags & RDS_RDMA_INVALIDATE) mr->r_invalidate = 1; if (args->flags & RDS_RDMA_READWRITE) mr->r_write = 1; /* * Pin the pages that make up the user buffer and transfer the page * pointers to the mr's sg array. We check to see if we've mapped * the whole region after transferring the partial page references * to the sg array so that we can have one page ref cleanup path. * * For now we have no flag that tells us whether the mapping is * r/o or r/w. We need to assume r/w, or we'll do a lot of RDMA to * the zero page. */ ret = rds_pin_pages(args->vec.addr, nr_pages, pages, 1); if (ret == -EOPNOTSUPP) { need_odp = 1; } else if (ret <= 0) { goto out; } else { nents = ret; sg = kmalloc_array(nents, sizeof(*sg), GFP_KERNEL); if (!sg) { ret = -ENOMEM; goto out; } WARN_ON(!nents); sg_init_table(sg, nents); /* Stick all pages into the scatterlist */ for (i = 0 ; i < nents; i++) sg_set_page(&sg[i], pages[i], PAGE_SIZE, 0); rdsdebug("RDS: trans_private nents is %u\n", nents); } /* Obtain a transport specific MR. If this succeeds, the * s/g list is now owned by the MR. * Note that dma_map() implies that pending writes are * flushed to RAM, so no dma_sync is needed here. */ trans_private = rs->rs_transport->get_mr( sg, nents, rs, &mr->r_key, cp ? cp->cp_conn : NULL, args->vec.addr, args->vec.bytes, need_odp ? ODP_ZEROBASED : ODP_NOT_NEEDED); if (IS_ERR(trans_private)) { /* In ODP case, we don't GUP pages, so don't need * to release anything. */ if (!need_odp) { unpin_user_pages(pages, nr_pages); kfree(sg); } ret = PTR_ERR(trans_private); /* Trigger connection so that its ready for the next retry */ if (ret == -ENODEV && cp) rds_conn_connect_if_down(cp->cp_conn); goto out; } mr->r_trans_private = trans_private; rdsdebug("RDS: get_mr put_user key is %x cookie_addr %p\n", mr->r_key, (void *)(unsigned long) args->cookie_addr); /* The user may pass us an unaligned address, but we can only * map page aligned regions. So we keep the offset, and build * a 64bit cookie containing <R_Key, offset> and pass that * around. */ if (need_odp) cookie = rds_rdma_make_cookie(mr->r_key, 0); else cookie = rds_rdma_make_cookie(mr->r_key, args->vec.addr & ~PAGE_MASK); if (cookie_ret) *cookie_ret = cookie; if (args->cookie_addr && put_user(cookie, (u64 __user *)(unsigned long)args->cookie_addr)) { if (!need_odp) { unpin_user_pages(pages, nr_pages); kfree(sg); } ret = -EFAULT; goto out; } /* Inserting the new MR into the rbtree bumps its * reference count. */ spin_lock_irqsave(&rs->rs_rdma_lock, flags); found = rds_mr_tree_walk(&rs->rs_rdma_keys, mr->r_key, mr); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); BUG_ON(found && found != mr); rdsdebug("RDS: get_mr key is %x\n", mr->r_key); if (mr_ret) { kref_get(&mr->r_kref); *mr_ret = mr; } ret = 0; out: kfree(pages); if (mr) kref_put(&mr->r_kref, __rds_put_mr_final); return ret; } int rds_get_mr(struct rds_sock *rs, sockptr_t optval, int optlen) { struct rds_get_mr_args args; if (optlen != sizeof(struct rds_get_mr_args)) return -EINVAL; if (copy_from_sockptr(&args, optval, sizeof(struct rds_get_mr_args))) return -EFAULT; return __rds_rdma_map(rs, &args, NULL, NULL, NULL); } int rds_get_mr_for_dest(struct rds_sock *rs, sockptr_t optval, int optlen) { struct rds_get_mr_for_dest_args args; struct rds_get_mr_args new_args; if (optlen != sizeof(struct rds_get_mr_for_dest_args)) return -EINVAL; if (copy_from_sockptr(&args, optval, sizeof(struct rds_get_mr_for_dest_args))) return -EFAULT; /* * Initially, just behave like get_mr(). * TODO: Implement get_mr as wrapper around this * and deprecate it. */ new_args.vec = args.vec; new_args.cookie_addr = args.cookie_addr; new_args.flags = args.flags; return __rds_rdma_map(rs, &new_args, NULL, NULL, NULL); } /* * Free the MR indicated by the given R_Key */ int rds_free_mr(struct rds_sock *rs, sockptr_t optval, int optlen) { struct rds_free_mr_args args; struct rds_mr *mr; unsigned long flags; if (optlen != sizeof(struct rds_free_mr_args)) return -EINVAL; if (copy_from_sockptr(&args, optval, sizeof(struct rds_free_mr_args))) return -EFAULT; /* Special case - a null cookie means flush all unused MRs */ if (args.cookie == 0) { if (!rs->rs_transport || !rs->rs_transport->flush_mrs) return -EINVAL; rs->rs_transport->flush_mrs(); return 0; } /* Look up the MR given its R_key and remove it from the rbtree * so nobody else finds it. * This should also prevent races with rds_rdma_unuse. */ spin_lock_irqsave(&rs->rs_rdma_lock, flags); mr = rds_mr_tree_walk(&rs->rs_rdma_keys, rds_rdma_cookie_key(args.cookie), NULL); if (mr) { rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); RB_CLEAR_NODE(&mr->r_rb_node); if (args.flags & RDS_RDMA_INVALIDATE) mr->r_invalidate = 1; } spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (!mr) return -EINVAL; kref_put(&mr->r_kref, __rds_put_mr_final); return 0; } /* * This is called when we receive an extension header that * tells us this MR was used. It allows us to implement * use_once semantics */ void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force) { struct rds_mr *mr; unsigned long flags; int zot_me = 0; spin_lock_irqsave(&rs->rs_rdma_lock, flags); mr = rds_mr_tree_walk(&rs->rs_rdma_keys, r_key, NULL); if (!mr) { pr_debug("rds: trying to unuse MR with unknown r_key %u!\n", r_key); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); return; } /* Get a reference so that the MR won't go away before calling * sync_mr() below. */ kref_get(&mr->r_kref); /* If it is going to be freed, remove it from the tree now so * that no other thread can find it and free it. */ if (mr->r_use_once || force) { rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys); RB_CLEAR_NODE(&mr->r_rb_node); zot_me = 1; } spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); /* May have to issue a dma_sync on this memory region. * Note we could avoid this if the operation was a RDMA READ, * but at this point we can't tell. */ if (mr->r_trans->sync_mr) mr->r_trans->sync_mr(mr->r_trans_private, DMA_FROM_DEVICE); /* Release the reference held above. */ kref_put(&mr->r_kref, __rds_put_mr_final); /* If the MR was marked as invalidate, this will * trigger an async flush. */ if (zot_me) kref_put(&mr->r_kref, __rds_put_mr_final); } void rds_rdma_free_op(struct rm_rdma_op *ro) { unsigned int i; if (ro->op_odp_mr) { kref_put(&ro->op_odp_mr->r_kref, __rds_put_mr_final); } else { for (i = 0; i < ro->op_nents; i++) { struct page *page = sg_page(&ro->op_sg[i]); /* Mark page dirty if it was possibly modified, which * is the case for a RDMA_READ which copies from remote * to local memory */ unpin_user_pages_dirty_lock(&page, 1, !ro->op_write); } } kfree(ro->op_notifier); ro->op_notifier = NULL; ro->op_active = 0; ro->op_odp_mr = NULL; } void rds_atomic_free_op(struct rm_atomic_op *ao) { struct page *page = sg_page(ao->op_sg); /* Mark page dirty if it was possibly modified, which * is the case for a RDMA_READ which copies from remote * to local memory */ unpin_user_pages_dirty_lock(&page, 1, true); kfree(ao->op_notifier); ao->op_notifier = NULL; ao->op_active = 0; } /* * Count the number of pages needed to describe an incoming iovec array. */ static int rds_rdma_pages(struct rds_iovec iov[], int nr_iovecs) { int tot_pages = 0; unsigned int nr_pages; unsigned int i; /* figure out the number of pages in the vector */ for (i = 0; i < nr_iovecs; i++) { nr_pages = rds_pages_in_vec(&iov[i]); if (nr_pages == 0) return -EINVAL; tot_pages += nr_pages; /* * nr_pages for one entry is limited to (UINT_MAX>>PAGE_SHIFT)+1, * so tot_pages cannot overflow without first going negative. */ if (tot_pages < 0) return -EINVAL; } return tot_pages; } int rds_rdma_extra_size(struct rds_rdma_args *args, struct rds_iov_vector *iov) { struct rds_iovec *vec; struct rds_iovec __user *local_vec; int tot_pages = 0; unsigned int nr_pages; unsigned int i; local_vec = (struct rds_iovec __user *)(unsigned long) args->local_vec_addr; if (args->nr_local == 0) return -EINVAL; if (args->nr_local > UIO_MAXIOV) return -EMSGSIZE; iov->iov = kcalloc(args->nr_local, sizeof(struct rds_iovec), GFP_KERNEL); if (!iov->iov) return -ENOMEM; vec = &iov->iov[0]; if (copy_from_user(vec, local_vec, args->nr_local * sizeof(struct rds_iovec))) return -EFAULT; iov->len = args->nr_local; /* figure out the number of pages in the vector */ for (i = 0; i < args->nr_local; i++, vec++) { nr_pages = rds_pages_in_vec(vec); if (nr_pages == 0) return -EINVAL; tot_pages += nr_pages; /* * nr_pages for one entry is limited to (UINT_MAX>>PAGE_SHIFT)+1, * so tot_pages cannot overflow without first going negative. */ if (tot_pages < 0) return -EINVAL; } return tot_pages * sizeof(struct scatterlist); } /* * The application asks for a RDMA transfer. * Extract all arguments and set up the rdma_op */ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg, struct rds_iov_vector *vec) { struct rds_rdma_args *args; struct rm_rdma_op *op = &rm->rdma; int nr_pages; unsigned int nr_bytes; struct page **pages = NULL; struct rds_iovec *iovs; unsigned int i, j; int ret = 0; bool odp_supported = true; if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_rdma_args)) || rm->rdma.op_active) return -EINVAL; args = CMSG_DATA(cmsg); if (ipv6_addr_any(&rs->rs_bound_addr)) { ret = -ENOTCONN; /* XXX not a great errno */ goto out_ret; } if (args->nr_local > UIO_MAXIOV) { ret = -EMSGSIZE; goto out_ret; } if (vec->len != args->nr_local) { ret = -EINVAL; goto out_ret; } /* odp-mr is not supported for multiple requests within one message */ if (args->nr_local != 1) odp_supported = false; iovs = vec->iov; nr_pages = rds_rdma_pages(iovs, args->nr_local); if (nr_pages < 0) { ret = -EINVAL; goto out_ret; } pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!pages) { ret = -ENOMEM; goto out_ret; } op->op_write = !!(args->flags & RDS_RDMA_READWRITE); op->op_fence = !!(args->flags & RDS_RDMA_FENCE); op->op_notify = !!(args->flags & RDS_RDMA_NOTIFY_ME); op->op_silent = !!(args->flags & RDS_RDMA_SILENT); op->op_active = 1; op->op_recverr = rs->rs_recverr; op->op_odp_mr = NULL; WARN_ON(!nr_pages); op->op_sg = rds_message_alloc_sgs(rm, nr_pages); if (IS_ERR(op->op_sg)) { ret = PTR_ERR(op->op_sg); goto out_pages; } if (op->op_notify || op->op_recverr) { /* We allocate an uninitialized notifier here, because * we don't want to do that in the completion handler. We * would have to use GFP_ATOMIC there, and don't want to deal * with failed allocations. */ op->op_notifier = kmalloc(sizeof(struct rds_notifier), GFP_KERNEL); if (!op->op_notifier) { ret = -ENOMEM; goto out_pages; } op->op_notifier->n_user_token = args->user_token; op->op_notifier->n_status = RDS_RDMA_SUCCESS; } /* The cookie contains the R_Key of the remote memory region, and * optionally an offset into it. This is how we implement RDMA into * unaligned memory. * When setting up the RDMA, we need to add that offset to the * destination address (which is really an offset into the MR) * FIXME: We may want to move this into ib_rdma.c */ op->op_rkey = rds_rdma_cookie_key(args->cookie); op->op_remote_addr = args->remote_vec.addr + rds_rdma_cookie_offset(args->cookie); nr_bytes = 0; rdsdebug("RDS: rdma prepare nr_local %llu rva %llx rkey %x\n", (unsigned long long)args->nr_local, (unsigned long long)args->remote_vec.addr, op->op_rkey); for (i = 0; i < args->nr_local; i++) { struct rds_iovec *iov = &iovs[i]; /* don't need to check, rds_rdma_pages() verified nr will be +nonzero */ unsigned int nr = rds_pages_in_vec(iov); rs->rs_user_addr = iov->addr; rs->rs_user_bytes = iov->bytes; /* If it's a WRITE operation, we want to pin the pages for reading. * If it's a READ operation, we need to pin the pages for writing. */ ret = rds_pin_pages(iov->addr, nr, pages, !op->op_write); if ((!odp_supported && ret <= 0) || (odp_supported && ret <= 0 && ret != -EOPNOTSUPP)) goto out_pages; if (ret == -EOPNOTSUPP) { struct rds_mr *local_odp_mr; if (!rs->rs_transport->get_mr) { ret = -EOPNOTSUPP; goto out_pages; } local_odp_mr = kzalloc(sizeof(*local_odp_mr), GFP_KERNEL); if (!local_odp_mr) { ret = -ENOMEM; goto out_pages; } RB_CLEAR_NODE(&local_odp_mr->r_rb_node); kref_init(&local_odp_mr->r_kref); local_odp_mr->r_trans = rs->rs_transport; local_odp_mr->r_sock = rs; local_odp_mr->r_trans_private = rs->rs_transport->get_mr( NULL, 0, rs, &local_odp_mr->r_key, NULL, iov->addr, iov->bytes, ODP_VIRTUAL); if (IS_ERR(local_odp_mr->r_trans_private)) { ret = PTR_ERR(local_odp_mr->r_trans_private); rdsdebug("get_mr ret %d %p\"", ret, local_odp_mr->r_trans_private); kfree(local_odp_mr); ret = -EOPNOTSUPP; goto out_pages; } rdsdebug("Need odp; local_odp_mr %p trans_private %p\n", local_odp_mr, local_odp_mr->r_trans_private); op->op_odp_mr = local_odp_mr; op->op_odp_addr = iov->addr; } rdsdebug("RDS: nr_bytes %u nr %u iov->bytes %llu iov->addr %llx\n", nr_bytes, nr, iov->bytes, iov->addr); nr_bytes += iov->bytes; for (j = 0; j < nr; j++) { unsigned int offset = iov->addr & ~PAGE_MASK; struct scatterlist *sg; sg = &op->op_sg[op->op_nents + j]; sg_set_page(sg, pages[j], min_t(unsigned int, iov->bytes, PAGE_SIZE - offset), offset); sg_dma_len(sg) = sg->length; rdsdebug("RDS: sg->offset %x sg->len %x iov->addr %llx iov->bytes %llu\n", sg->offset, sg->length, iov->addr, iov->bytes); iov->addr += sg->length; iov->bytes -= sg->length; } op->op_nents += nr; } if (nr_bytes > args->remote_vec.bytes) { rdsdebug("RDS nr_bytes %u remote_bytes %u do not match\n", nr_bytes, (unsigned int) args->remote_vec.bytes); ret = -EINVAL; goto out_pages; } op->op_bytes = nr_bytes; ret = 0; out_pages: kfree(pages); out_ret: if (ret) rds_rdma_free_op(op); else rds_stats_inc(s_send_rdma); return ret; } /* * The application wants us to pass an RDMA destination (aka MR) * to the remote */ int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg) { unsigned long flags; struct rds_mr *mr; u32 r_key; int err = 0; if (cmsg->cmsg_len < CMSG_LEN(sizeof(rds_rdma_cookie_t)) || rm->m_rdma_cookie != 0) return -EINVAL; memcpy(&rm->m_rdma_cookie, CMSG_DATA(cmsg), sizeof(rm->m_rdma_cookie)); /* We are reusing a previously mapped MR here. Most likely, the * application has written to the buffer, so we need to explicitly * flush those writes to RAM. Otherwise the HCA may not see them * when doing a DMA from that buffer. */ r_key = rds_rdma_cookie_key(rm->m_rdma_cookie); spin_lock_irqsave(&rs->rs_rdma_lock, flags); mr = rds_mr_tree_walk(&rs->rs_rdma_keys, r_key, NULL); if (!mr) err = -EINVAL; /* invalid r_key */ else kref_get(&mr->r_kref); spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (mr) { mr->r_trans->sync_mr(mr->r_trans_private, DMA_TO_DEVICE); rm->rdma.op_rdma_mr = mr; } return err; } /* * The application passes us an address range it wants to enable RDMA * to/from. We map the area, and save the <R_Key,offset> pair * in rm->m_rdma_cookie. This causes it to be sent along to the peer * in an extension header. */ int rds_cmsg_rdma_map(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg) { if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_get_mr_args)) || rm->m_rdma_cookie != 0) return -EINVAL; return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie, &rm->rdma.op_rdma_mr, rm->m_conn_path); } /* * Fill in rds_message for an atomic request. */ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg) { struct page *page = NULL; struct rds_atomic_args *args; int ret = 0; if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_atomic_args)) || rm->atomic.op_active) return -EINVAL; args = CMSG_DATA(cmsg); /* Nonmasked & masked cmsg ops converted to masked hw ops */ switch (cmsg->cmsg_type) { case RDS_CMSG_ATOMIC_FADD: rm->atomic.op_type = RDS_ATOMIC_TYPE_FADD; rm->atomic.op_m_fadd.add = args->fadd.add; rm->atomic.op_m_fadd.nocarry_mask = 0; break; case RDS_CMSG_MASKED_ATOMIC_FADD: rm->atomic.op_type = RDS_ATOMIC_TYPE_FADD; rm->atomic.op_m_fadd.add = args->m_fadd.add; rm->atomic.op_m_fadd.nocarry_mask = args->m_fadd.nocarry_mask; break; case RDS_CMSG_ATOMIC_CSWP: rm->atomic.op_type = RDS_ATOMIC_TYPE_CSWP; rm->atomic.op_m_cswp.compare = args->cswp.compare; rm->atomic.op_m_cswp.swap = args->cswp.swap; rm->atomic.op_m_cswp.compare_mask = ~0; rm->atomic.op_m_cswp.swap_mask = ~0; break; case RDS_CMSG_MASKED_ATOMIC_CSWP: rm->atomic.op_type = RDS_ATOMIC_TYPE_CSWP; rm->atomic.op_m_cswp.compare = args->m_cswp.compare; rm->atomic.op_m_cswp.swap = args->m_cswp.swap; rm->atomic.op_m_cswp.compare_mask = args->m_cswp.compare_mask; rm->atomic.op_m_cswp.swap_mask = args->m_cswp.swap_mask; break; default: BUG(); /* should never happen */ } rm->atomic.op_notify = !!(args->flags & RDS_RDMA_NOTIFY_ME); rm->atomic.op_silent = !!(args->flags & RDS_RDMA_SILENT); rm->atomic.op_active = 1; rm->atomic.op_recverr = rs->rs_recverr; rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1); if (IS_ERR(rm->atomic.op_sg)) { ret = PTR_ERR(rm->atomic.op_sg); goto err; } /* verify 8 byte-aligned */ if (args->local_addr & 0x7) { ret = -EFAULT; goto err; } ret = rds_pin_pages(args->local_addr, 1, &page, 1); if (ret != 1) goto err; ret = 0; sg_set_page(rm->atomic.op_sg, page, 8, offset_in_page(args->local_addr)); if (rm->atomic.op_notify || rm->atomic.op_recverr) { /* We allocate an uninitialized notifier here, because * we don't want to do that in the completion handler. We * would have to use GFP_ATOMIC there, and don't want to deal * with failed allocations. */ rm->atomic.op_notifier = kmalloc(sizeof(*rm->atomic.op_notifier), GFP_KERNEL); if (!rm->atomic.op_notifier) { ret = -ENOMEM; goto err; } rm->atomic.op_notifier->n_user_token = args->user_token; rm->atomic.op_notifier->n_status = RDS_RDMA_SUCCESS; } rm->atomic.op_rkey = rds_rdma_cookie_key(args->cookie); rm->atomic.op_remote_addr = args->remote_addr + rds_rdma_cookie_offset(args->cookie); return ret; err: if (page) unpin_user_page(page); rm->atomic.op_active = 0; kfree(rm->atomic.op_notifier); return ret; } |
| 1804 1802 3 1805 17 1804 17 32746 32744 32725 1805 1800 1508 673 1797 1804 15 15 1 15 17 10 15 10 8 11 15 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 53 53 53 15 15 2 26940 26942 26937 26940 26942 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/sched/cputime.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <trace/events/cgroup.h> static DEFINE_SPINLOCK(cgroup_rstat_lock); static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock); static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu); static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu) { return per_cpu_ptr(cgrp->rstat_cpu, cpu); } /* * Helper functions for rstat per CPU lock (cgroup_rstat_cpu_lock). * * This makes it easier to diagnose locking issues and contention in * production environments. The parameter @fast_path determine the * tracepoints being added, allowing us to diagnose "flush" related * operations without handling high-frequency fast-path "update" events. */ static __always_inline unsigned long _cgroup_rstat_cpu_lock(raw_spinlock_t *cpu_lock, int cpu, struct cgroup *cgrp, const bool fast_path) { unsigned long flags; bool contended; /* * The _irqsave() is needed because cgroup_rstat_lock is * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring * this lock with the _irq() suffix only disables interrupts on * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables * interrupts on both configurations. The _irqsave() ensures * that interrupts are always disabled and later restored. */ contended = !raw_spin_trylock_irqsave(cpu_lock, flags); if (contended) { if (fast_path) trace_cgroup_rstat_cpu_lock_contended_fastpath(cgrp, cpu, contended); else trace_cgroup_rstat_cpu_lock_contended(cgrp, cpu, contended); raw_spin_lock_irqsave(cpu_lock, flags); } if (fast_path) trace_cgroup_rstat_cpu_locked_fastpath(cgrp, cpu, contended); else trace_cgroup_rstat_cpu_locked(cgrp, cpu, contended); return flags; } static __always_inline void _cgroup_rstat_cpu_unlock(raw_spinlock_t *cpu_lock, int cpu, struct cgroup *cgrp, unsigned long flags, const bool fast_path) { if (fast_path) trace_cgroup_rstat_cpu_unlock_fastpath(cgrp, cpu, false); else trace_cgroup_rstat_cpu_unlock(cgrp, cpu, false); raw_spin_unlock_irqrestore(cpu_lock, flags); } /** * cgroup_rstat_updated - keep track of updated rstat_cpu * @cgrp: target cgroup * @cpu: cpu on which rstat_cpu was updated * * @cgrp's rstat_cpu on @cpu was updated. Put it on the parent's matching * rstat_cpu->updated_children list. See the comment on top of * cgroup_rstat_cpu definition for details. */ __bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); unsigned long flags; /* * Speculative already-on-list test. This may race leading to * temporary inaccuracies, which is fine. * * Because @parent's updated_children is terminated with @parent * instead of NULL, we can tell whether @cgrp is on the list by * testing the next pointer for NULL. */ if (data_race(cgroup_rstat_cpu(cgrp, cpu)->updated_next)) return; flags = _cgroup_rstat_cpu_lock(cpu_lock, cpu, cgrp, true); /* put @cgrp and all ancestors on the corresponding updated lists */ while (true) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_cpu *prstatc; /* * Both additions and removals are bottom-up. If a cgroup * is already in the tree, all ancestors are. */ if (rstatc->updated_next) break; /* Root has no parent to link it to, but mark it busy */ if (!parent) { rstatc->updated_next = cgrp; break; } prstatc = cgroup_rstat_cpu(parent, cpu); rstatc->updated_next = prstatc->updated_children; prstatc->updated_children = cgrp; cgrp = parent; } _cgroup_rstat_cpu_unlock(cpu_lock, cpu, cgrp, flags, true); } /** * cgroup_rstat_push_children - push children cgroups into the given list * @head: current head of the list (= subtree root) * @child: first child of the root * @cpu: target cpu * Return: A new singly linked list of cgroups to be flush * * Iteratively traverse down the cgroup_rstat_cpu updated tree level by * level and push all the parents first before their next level children * into a singly linked list built from the tail backward like "pushing" * cgroups into a stack. The root is pushed by the caller. */ static struct cgroup *cgroup_rstat_push_children(struct cgroup *head, struct cgroup *child, int cpu) { struct cgroup *chead = child; /* Head of child cgroup level */ struct cgroup *ghead = NULL; /* Head of grandchild cgroup level */ struct cgroup *parent, *grandchild; struct cgroup_rstat_cpu *crstatc; child->rstat_flush_next = NULL; next_level: while (chead) { child = chead; chead = child->rstat_flush_next; parent = cgroup_parent(child); /* updated_next is parent cgroup terminated */ while (child != parent) { child->rstat_flush_next = head; head = child; crstatc = cgroup_rstat_cpu(child, cpu); grandchild = crstatc->updated_children; if (grandchild != child) { /* Push the grand child to the next level */ crstatc->updated_children = child; grandchild->rstat_flush_next = ghead; ghead = grandchild; } child = crstatc->updated_next; crstatc->updated_next = NULL; } } if (ghead) { chead = ghead; ghead = NULL; goto next_level; } return head; } /** * cgroup_rstat_updated_list - return a list of updated cgroups to be flushed * @root: root of the cgroup subtree to traverse * @cpu: target cpu * Return: A singly linked list of cgroups to be flushed * * Walks the updated rstat_cpu tree on @cpu from @root. During traversal, * each returned cgroup is unlinked from the updated tree. * * The only ordering guarantee is that, for a parent and a child pair * covered by a given traversal, the child is before its parent in * the list. * * Note that updated_children is self terminated and points to a list of * child cgroups if not empty. Whereas updated_next is like a sibling link * within the children list and terminated by the parent cgroup. An exception * here is the cgroup root whose updated_next can be self terminated. */ static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(root, cpu); struct cgroup *head = NULL, *parent, *child; unsigned long flags; flags = _cgroup_rstat_cpu_lock(cpu_lock, cpu, root, false); /* Return NULL if this subtree is not on-list */ if (!rstatc->updated_next) goto unlock_ret; /* * Unlink @root from its parent. As the updated_children list is * singly linked, we have to walk it to find the removal point. */ parent = cgroup_parent(root); if (parent) { struct cgroup_rstat_cpu *prstatc; struct cgroup **nextp; prstatc = cgroup_rstat_cpu(parent, cpu); nextp = &prstatc->updated_children; while (*nextp != root) { struct cgroup_rstat_cpu *nrstatc; nrstatc = cgroup_rstat_cpu(*nextp, cpu); WARN_ON_ONCE(*nextp == parent); nextp = &nrstatc->updated_next; } *nextp = rstatc->updated_next; } rstatc->updated_next = NULL; /* Push @root to the list first before pushing the children */ head = root; root->rstat_flush_next = NULL; child = rstatc->updated_children; rstatc->updated_children = root; if (child != root) head = cgroup_rstat_push_children(head, child, cpu); unlock_ret: _cgroup_rstat_cpu_unlock(cpu_lock, cpu, root, flags, false); return head; } /* * A hook for bpf stat collectors to attach to and flush their stats. * Together with providing bpf kfuncs for cgroup_rstat_updated() and * cgroup_rstat_flush(), this enables a complete workflow where bpf progs that * collect cgroup stats can integrate with rstat for efficient flushing. * * A static noinline declaration here could cause the compiler to optimize away * the function. A global noinline declaration will keep the definition, but may * optimize away the callsite. Therefore, __weak is needed to ensure that the * call is still emitted, by telling the compiler that we don't know what the * function might eventually be. */ __bpf_hook_start(); __weak noinline void bpf_rstat_flush(struct cgroup *cgrp, struct cgroup *parent, int cpu) { } __bpf_hook_end(); /* * Helper functions for locking cgroup_rstat_lock. * * This makes it easier to diagnose locking issues and contention in * production environments. The parameter @cpu_in_loop indicate lock * was released and re-taken when collection data from the CPUs. The * value -1 is used when obtaining the main lock else this is the CPU * number processed last. */ static inline void __cgroup_rstat_lock(struct cgroup *cgrp, int cpu_in_loop) __acquires(&cgroup_rstat_lock) { bool contended; contended = !spin_trylock_irq(&cgroup_rstat_lock); if (contended) { trace_cgroup_rstat_lock_contended(cgrp, cpu_in_loop, contended); spin_lock_irq(&cgroup_rstat_lock); } trace_cgroup_rstat_locked(cgrp, cpu_in_loop, contended); } static inline void __cgroup_rstat_unlock(struct cgroup *cgrp, int cpu_in_loop) __releases(&cgroup_rstat_lock) { trace_cgroup_rstat_unlock(cgrp, cpu_in_loop, false); spin_unlock_irq(&cgroup_rstat_lock); } /** * cgroup_rstat_flush - flush stats in @cgrp's subtree * @cgrp: target cgroup * * Collect all per-cpu stats in @cgrp's subtree into the global counters * and propagate them upwards. After this function returns, all cgroups in * the subtree have up-to-date ->stat. * * This also gets all cgroups in the subtree including @cgrp off the * ->updated_children lists. * * This function may block. */ __bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp) { int cpu; might_sleep(); for_each_possible_cpu(cpu) { struct cgroup *pos; /* Reacquire for each CPU to avoid disabling IRQs too long */ __cgroup_rstat_lock(cgrp, cpu); pos = cgroup_rstat_updated_list(cgrp, cpu); for (; pos; pos = pos->rstat_flush_next) { struct cgroup_subsys_state *css; cgroup_base_stat_flush(pos, cpu); bpf_rstat_flush(pos, cgroup_parent(pos), cpu); rcu_read_lock(); list_for_each_entry_rcu(css, &pos->rstat_css_list, rstat_css_node) css->ss->css_rstat_flush(css, cpu); rcu_read_unlock(); } __cgroup_rstat_unlock(cgrp, cpu); if (!cond_resched()) cpu_relax(); } } int cgroup_rstat_init(struct cgroup *cgrp) { int cpu; /* the root cgrp has rstat_cpu preallocated */ if (!cgrp->rstat_cpu) { cgrp->rstat_cpu = alloc_percpu(struct cgroup_rstat_cpu); if (!cgrp->rstat_cpu) return -ENOMEM; } /* ->updated_children list is self terminated */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); rstatc->updated_children = cgrp; u64_stats_init(&rstatc->bsync); } return 0; } void cgroup_rstat_exit(struct cgroup *cgrp) { int cpu; cgroup_rstat_flush(cgrp); /* sanity check */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); if (WARN_ON_ONCE(rstatc->updated_children != cgrp) || WARN_ON_ONCE(rstatc->updated_next)) return; } free_percpu(cgrp->rstat_cpu); cgrp->rstat_cpu = NULL; } void __init cgroup_rstat_boot(void) { int cpu; for_each_possible_cpu(cpu) raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu)); } /* * Functions for cgroup basic resource statistics implemented on top of * rstat. */ static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime += src_bstat->cputime.utime; dst_bstat->cputime.stime += src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum += src_bstat->forceidle_sum; #endif dst_bstat->ntime += src_bstat->ntime; } static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime -= src_bstat->cputime.utime; dst_bstat->cputime.stime -= src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum -= src_bstat->forceidle_sum; #endif dst_bstat->ntime -= src_bstat->ntime; } static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_cpu *prstatc; struct cgroup_base_stat delta; unsigned seq; /* Root-level stats are sourced from system-wide CPU stats */ if (!parent) return; /* fetch the current per-cpu values */ do { seq = __u64_stats_fetch_begin(&rstatc->bsync); delta = rstatc->bstat; } while (__u64_stats_fetch_retry(&rstatc->bsync, seq)); /* propagate per-cpu delta to cgroup and per-cpu global statistics */ cgroup_base_stat_sub(&delta, &rstatc->last_bstat); cgroup_base_stat_add(&cgrp->bstat, &delta); cgroup_base_stat_add(&rstatc->last_bstat, &delta); cgroup_base_stat_add(&rstatc->subtree_bstat, &delta); /* propagate cgroup and per-cpu global delta to parent (unless that's root) */ if (cgroup_parent(parent)) { delta = cgrp->bstat; cgroup_base_stat_sub(&delta, &cgrp->last_bstat); cgroup_base_stat_add(&parent->bstat, &delta); cgroup_base_stat_add(&cgrp->last_bstat, &delta); delta = rstatc->subtree_bstat; prstatc = cgroup_rstat_cpu(parent, cpu); cgroup_base_stat_sub(&delta, &rstatc->last_subtree_bstat); cgroup_base_stat_add(&prstatc->subtree_bstat, &delta); cgroup_base_stat_add(&rstatc->last_subtree_bstat, &delta); } } static struct cgroup_rstat_cpu * cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags) { struct cgroup_rstat_cpu *rstatc; rstatc = get_cpu_ptr(cgrp->rstat_cpu); *flags = u64_stats_update_begin_irqsave(&rstatc->bsync); return rstatc; } static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, struct cgroup_rstat_cpu *rstatc, unsigned long flags) { u64_stats_update_end_irqrestore(&rstatc->bsync, flags); cgroup_rstat_updated(cgrp, smp_processor_id()); put_cpu_ptr(rstatc); } void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; unsigned long flags; rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); rstatc->bstat.cputime.sum_exec_runtime += delta_exec; cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); } void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; unsigned long flags; rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); switch (index) { case CPUTIME_NICE: rstatc->bstat.ntime += delta_exec; fallthrough; case CPUTIME_USER: rstatc->bstat.cputime.utime += delta_exec; break; case CPUTIME_SYSTEM: case CPUTIME_IRQ: case CPUTIME_SOFTIRQ: rstatc->bstat.cputime.stime += delta_exec; break; #ifdef CONFIG_SCHED_CORE case CPUTIME_FORCEIDLE: rstatc->bstat.forceidle_sum += delta_exec; break; #endif default: break; } cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); } /* * compute the cputime for the root cgroup by getting the per cpu data * at a global level, then categorizing the fields in a manner consistent * with how it is done by __cgroup_account_cputime_field for each bit of * cpu time attributed to a cgroup. */ static void root_cgroup_cputime(struct cgroup_base_stat *bstat) { struct task_cputime *cputime = &bstat->cputime; int i; memset(bstat, 0, sizeof(*bstat)); for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; u64 user = 0; u64 sys = 0; kcpustat_cpu_fetch(&kcpustat, i); user += cpustat[CPUTIME_USER]; user += cpustat[CPUTIME_NICE]; cputime->utime += user; sys += cpustat[CPUTIME_SYSTEM]; sys += cpustat[CPUTIME_IRQ]; sys += cpustat[CPUTIME_SOFTIRQ]; cputime->stime += sys; cputime->sum_exec_runtime += user; cputime->sum_exec_runtime += sys; #ifdef CONFIG_SCHED_CORE bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE]; #endif bstat->ntime += cpustat[CPUTIME_NICE]; } } static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat *bstat) { #ifdef CONFIG_SCHED_CORE u64 forceidle_time = bstat->forceidle_sum; do_div(forceidle_time, NSEC_PER_USEC); seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time); #endif } void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct cgroup_base_stat bstat; if (cgroup_parent(cgrp)) { cgroup_rstat_flush(cgrp); __cgroup_rstat_lock(cgrp, -1); bstat = cgrp->bstat; cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &bstat.cputime.utime, &bstat.cputime.stime); __cgroup_rstat_unlock(cgrp, -1); } else { root_cgroup_cputime(&bstat); } do_div(bstat.cputime.sum_exec_runtime, NSEC_PER_USEC); do_div(bstat.cputime.utime, NSEC_PER_USEC); do_div(bstat.cputime.stime, NSEC_PER_USEC); do_div(bstat.ntime, NSEC_PER_USEC); seq_printf(seq, "usage_usec %llu\n" "user_usec %llu\n" "system_usec %llu\n" "nice_usec %llu\n", bstat.cputime.sum_exec_runtime, bstat.cputime.utime, bstat.cputime.stime, bstat.ntime); cgroup_force_idle_show(seq, &bstat); } /* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */ BTF_KFUNCS_START(bpf_rstat_kfunc_ids) BTF_ID_FLAGS(func, cgroup_rstat_updated) BTF_ID_FLAGS(func, cgroup_rstat_flush, KF_SLEEPABLE) BTF_KFUNCS_END(bpf_rstat_kfunc_ids) static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_rstat_kfunc_ids, }; static int __init bpf_rstat_kfunc_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_rstat_kfunc_set); } late_initcall(bpf_rstat_kfunc_init); |
| 351 308 340 340 340 339 339 11 340 1 1 1 324 323 325 318 8 162 162 162 162 339 334 6 4 2 4 1 1 5 29 21 2 21 1 5 19 3 6 15 15 13 8 6 8 8 8 6 5 5 2 5 5 4 1 2 2 2 2 2 2 2 2 35 2 297 293 1 4 3 2 20 20 8 1 2 1 53 4 6 41 43 10 13 11 3 3 3 1 1 2 1 1 1 1 8 3 67 15 17 5 9 3 8 3 28 9 20 2 30 296 294 2 292 4 33 33 8 11 60 60 27 33 3 57 57 24 22 10 9 1 1 8 26 28 3 26 26 15 20 73 14 38 9 6 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2002,2003 by Andreas Gruenbacher <a.gruenbacher@computer.org> * * Fixes from William Schumacher incorporated on 15 March 2001. * (Reported by Charles Bertsch, <CBertsch@microtest.com>). */ /* * This file contains generic functions for manipulating * POSIX 1003.1e draft standard 17 ACLs. */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/atomic.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/cred.h> #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include <linux/xattr.h> #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/namei.h> #include <linux/mnt_idmapping.h> #include <linux/iversion.h> #include <linux/security.h> #include <linux/fsnotify.h> #include <linux/filelock.h> #include "internal.h" static struct posix_acl **acl_by_type(struct inode *inode, int type) { switch (type) { case ACL_TYPE_ACCESS: return &inode->i_acl; case ACL_TYPE_DEFAULT: return &inode->i_default_acl; default: BUG(); } } struct posix_acl *get_cached_acl(struct inode *inode, int type) { struct posix_acl **p = acl_by_type(inode, type); struct posix_acl *acl; for (;;) { rcu_read_lock(); acl = rcu_dereference(*p); if (!acl || is_uncached_acl(acl) || refcount_inc_not_zero(&acl->a_refcount)) break; rcu_read_unlock(); cpu_relax(); } rcu_read_unlock(); return acl; } EXPORT_SYMBOL(get_cached_acl); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type) { struct posix_acl *acl = rcu_dereference(*acl_by_type(inode, type)); if (acl == ACL_DONT_CACHE) { struct posix_acl *ret; ret = inode->i_op->get_inode_acl(inode, type, LOOKUP_RCU); if (!IS_ERR(ret)) acl = ret; } return acl; } EXPORT_SYMBOL(get_cached_acl_rcu); void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl) { struct posix_acl **p = acl_by_type(inode, type); struct posix_acl *old; old = xchg(p, posix_acl_dup(acl)); if (!is_uncached_acl(old)) posix_acl_release(old); } EXPORT_SYMBOL(set_cached_acl); static void __forget_cached_acl(struct posix_acl **p) { struct posix_acl *old; old = xchg(p, ACL_NOT_CACHED); if (!is_uncached_acl(old)) posix_acl_release(old); } void forget_cached_acl(struct inode *inode, int type) { __forget_cached_acl(acl_by_type(inode, type)); } EXPORT_SYMBOL(forget_cached_acl); void forget_all_cached_acls(struct inode *inode) { __forget_cached_acl(&inode->i_acl); __forget_cached_acl(&inode->i_default_acl); } EXPORT_SYMBOL(forget_all_cached_acls); static struct posix_acl *__get_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, int type) { struct posix_acl *sentinel; struct posix_acl **p; struct posix_acl *acl; /* * The sentinel is used to detect when another operation like * set_cached_acl() or forget_cached_acl() races with get_inode_acl(). * It is guaranteed that is_uncached_acl(sentinel) is true. */ acl = get_cached_acl(inode, type); if (!is_uncached_acl(acl)) return acl; if (!IS_POSIXACL(inode)) return NULL; sentinel = uncached_acl_sentinel(current); p = acl_by_type(inode, type); /* * If the ACL isn't being read yet, set our sentinel. Otherwise, the * current value of the ACL will not be ACL_NOT_CACHED and so our own * sentinel will not be set; another task will update the cache. We * could wait for that other task to complete its job, but it's easier * to just call ->get_inode_acl to fetch the ACL ourself. (This is * going to be an unlikely race.) */ cmpxchg(p, ACL_NOT_CACHED, sentinel); /* * Normally, the ACL returned by ->get{_inode}_acl will be cached. * A filesystem can prevent that by calling * forget_cached_acl(inode, type) in ->get{_inode}_acl. * * If the filesystem doesn't have a get{_inode}_ acl() function at all, * we'll just create the negative cache entry. */ if (dentry && inode->i_op->get_acl) { acl = inode->i_op->get_acl(idmap, dentry, type); } else if (inode->i_op->get_inode_acl) { acl = inode->i_op->get_inode_acl(inode, type, false); } else { set_cached_acl(inode, type, NULL); return NULL; } if (IS_ERR(acl)) { /* * Remove our sentinel so that we don't block future attempts * to cache the ACL. */ cmpxchg(p, sentinel, ACL_NOT_CACHED); return acl; } /* * Cache the result, but only if our sentinel is still in place. */ posix_acl_dup(acl); if (unlikely(!try_cmpxchg(p, &sentinel, acl))) posix_acl_release(acl); return acl; } struct posix_acl *get_inode_acl(struct inode *inode, int type) { return __get_acl(&nop_mnt_idmap, NULL, inode, type); } EXPORT_SYMBOL(get_inode_acl); /* * Init a fresh posix_acl */ void posix_acl_init(struct posix_acl *acl, int count) { refcount_set(&acl->a_refcount, 1); acl->a_count = count; } EXPORT_SYMBOL(posix_acl_init); /* * Allocate a new ACL with the specified number of entries. */ struct posix_acl * posix_acl_alloc(unsigned int count, gfp_t flags) { struct posix_acl *acl; acl = kmalloc(struct_size(acl, a_entries, count), flags); if (acl) posix_acl_init(acl, count); return acl; } EXPORT_SYMBOL(posix_acl_alloc); /* * Clone an ACL. */ struct posix_acl * posix_acl_clone(const struct posix_acl *acl, gfp_t flags) { struct posix_acl *clone = NULL; if (acl) { clone = kmemdup(acl, struct_size(acl, a_entries, acl->a_count), flags); if (clone) refcount_set(&clone->a_refcount, 1); } return clone; } EXPORT_SYMBOL_GPL(posix_acl_clone); /* * Check if an acl is valid. Returns 0 if it is, or -E... otherwise. */ int posix_acl_valid(struct user_namespace *user_ns, const struct posix_acl *acl) { const struct posix_acl_entry *pa, *pe; int state = ACL_USER_OBJ; int needs_mask = 0; FOREACH_ACL_ENTRY(pa, acl, pe) { if (pa->e_perm & ~(ACL_READ|ACL_WRITE|ACL_EXECUTE)) return -EINVAL; switch (pa->e_tag) { case ACL_USER_OBJ: if (state == ACL_USER_OBJ) { state = ACL_USER; break; } return -EINVAL; case ACL_USER: if (state != ACL_USER) return -EINVAL; if (!kuid_has_mapping(user_ns, pa->e_uid)) return -EINVAL; needs_mask = 1; break; case ACL_GROUP_OBJ: if (state == ACL_USER) { state = ACL_GROUP; break; } return -EINVAL; case ACL_GROUP: if (state != ACL_GROUP) return -EINVAL; if (!kgid_has_mapping(user_ns, pa->e_gid)) return -EINVAL; needs_mask = 1; break; case ACL_MASK: if (state != ACL_GROUP) return -EINVAL; state = ACL_OTHER; break; case ACL_OTHER: if (state == ACL_OTHER || (state == ACL_GROUP && !needs_mask)) { state = 0; break; } return -EINVAL; default: return -EINVAL; } } if (state == 0) return 0; return -EINVAL; } EXPORT_SYMBOL(posix_acl_valid); /* * Returns 0 if the acl can be exactly represented in the traditional * file mode permission bits, or else 1. Returns -E... on error. */ int posix_acl_equiv_mode(const struct posix_acl *acl, umode_t *mode_p) { const struct posix_acl_entry *pa, *pe; umode_t mode = 0; int not_equiv = 0; /* * A null ACL can always be presented as mode bits. */ if (!acl) return 0; FOREACH_ACL_ENTRY(pa, acl, pe) { switch (pa->e_tag) { case ACL_USER_OBJ: mode |= (pa->e_perm & S_IRWXO) << 6; break; case ACL_GROUP_OBJ: mode |= (pa->e_perm & S_IRWXO) << 3; break; case ACL_OTHER: mode |= pa->e_perm & S_IRWXO; break; case ACL_MASK: mode = (mode & ~S_IRWXG) | ((pa->e_perm & S_IRWXO) << 3); not_equiv = 1; break; case ACL_USER: case ACL_GROUP: not_equiv = 1; break; default: return -EINVAL; } } if (mode_p) *mode_p = (*mode_p & ~S_IRWXUGO) | mode; return not_equiv; } EXPORT_SYMBOL(posix_acl_equiv_mode); /* * Create an ACL representing the file mode permission bits of an inode. */ struct posix_acl * posix_acl_from_mode(umode_t mode, gfp_t flags) { struct posix_acl *acl = posix_acl_alloc(3, flags); if (!acl) return ERR_PTR(-ENOMEM); acl->a_entries[0].e_tag = ACL_USER_OBJ; acl->a_entries[0].e_perm = (mode & S_IRWXU) >> 6; acl->a_entries[1].e_tag = ACL_GROUP_OBJ; acl->a_entries[1].e_perm = (mode & S_IRWXG) >> 3; acl->a_entries[2].e_tag = ACL_OTHER; acl->a_entries[2].e_perm = (mode & S_IRWXO); return acl; } EXPORT_SYMBOL(posix_acl_from_mode); /* * Return 0 if current is granted want access to the inode * by the acl. Returns -E... otherwise. */ int posix_acl_permission(struct mnt_idmap *idmap, struct inode *inode, const struct posix_acl *acl, int want) { const struct posix_acl_entry *pa, *pe, *mask_obj; struct user_namespace *fs_userns = i_user_ns(inode); int found = 0; vfsuid_t vfsuid; vfsgid_t vfsgid; want &= MAY_READ | MAY_WRITE | MAY_EXEC; FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: /* (May have been checked already) */ vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) goto check_perm; break; case ACL_USER: vfsuid = make_vfsuid(idmap, fs_userns, pa->e_uid); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) goto mask; break; case ACL_GROUP_OBJ: vfsgid = i_gid_into_vfsgid(idmap, inode); if (vfsgid_in_group_p(vfsgid)) { found = 1; if ((pa->e_perm & want) == want) goto mask; } break; case ACL_GROUP: vfsgid = make_vfsgid(idmap, fs_userns, pa->e_gid); if (vfsgid_in_group_p(vfsgid)) { found = 1; if ((pa->e_perm & want) == want) goto mask; } break; case ACL_MASK: break; case ACL_OTHER: if (found) return -EACCES; else goto check_perm; default: return -EIO; } } return -EIO; mask: for (mask_obj = pa+1; mask_obj != pe; mask_obj++) { if (mask_obj->e_tag == ACL_MASK) { if ((pa->e_perm & mask_obj->e_perm & want) == want) return 0; return -EACCES; } } check_perm: if ((pa->e_perm & want) == want) return 0; return -EACCES; } /* * Modify acl when creating a new inode. The caller must ensure the acl is * only referenced once. * * mode_p initially must contain the mode parameter to the open() / creat() * system calls. All permissions that are not granted by the acl are removed. * The permissions in the acl are changed to reflect the mode_p parameter. */ static int posix_acl_create_masq(struct posix_acl *acl, umode_t *mode_p) { struct posix_acl_entry *pa, *pe; struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; umode_t mode = *mode_p; int not_equiv = 0; /* assert(atomic_read(acl->a_refcount) == 1); */ FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: pa->e_perm &= (mode >> 6) | ~S_IRWXO; mode &= (pa->e_perm << 6) | ~S_IRWXU; break; case ACL_USER: case ACL_GROUP: not_equiv = 1; break; case ACL_GROUP_OBJ: group_obj = pa; break; case ACL_OTHER: pa->e_perm &= mode | ~S_IRWXO; mode &= pa->e_perm | ~S_IRWXO; break; case ACL_MASK: mask_obj = pa; not_equiv = 1; break; default: return -EIO; } } if (mask_obj) { mask_obj->e_perm &= (mode >> 3) | ~S_IRWXO; mode &= (mask_obj->e_perm << 3) | ~S_IRWXG; } else { if (!group_obj) return -EIO; group_obj->e_perm &= (mode >> 3) | ~S_IRWXO; mode &= (group_obj->e_perm << 3) | ~S_IRWXG; } *mode_p = (*mode_p & ~S_IRWXUGO) | mode; return not_equiv; } /* * Modify the ACL for the chmod syscall. */ static int __posix_acl_chmod_masq(struct posix_acl *acl, umode_t mode) { struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; struct posix_acl_entry *pa, *pe; /* assert(atomic_read(acl->a_refcount) == 1); */ FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: pa->e_perm = (mode & S_IRWXU) >> 6; break; case ACL_USER: case ACL_GROUP: break; case ACL_GROUP_OBJ: group_obj = pa; break; case ACL_MASK: mask_obj = pa; break; case ACL_OTHER: pa->e_perm = (mode & S_IRWXO); break; default: return -EIO; } } if (mask_obj) { mask_obj->e_perm = (mode & S_IRWXG) >> 3; } else { if (!group_obj) return -EIO; group_obj->e_perm = (mode & S_IRWXG) >> 3; } return 0; } int __posix_acl_create(struct posix_acl **acl, gfp_t gfp, umode_t *mode_p) { struct posix_acl *clone = posix_acl_clone(*acl, gfp); int err = -ENOMEM; if (clone) { err = posix_acl_create_masq(clone, mode_p); if (err < 0) { posix_acl_release(clone); clone = NULL; } } posix_acl_release(*acl); *acl = clone; return err; } EXPORT_SYMBOL(__posix_acl_create); int __posix_acl_chmod(struct posix_acl **acl, gfp_t gfp, umode_t mode) { struct posix_acl *clone = posix_acl_clone(*acl, gfp); int err = -ENOMEM; if (clone) { err = __posix_acl_chmod_masq(clone, mode); if (err) { posix_acl_release(clone); clone = NULL; } } posix_acl_release(*acl); *acl = clone; return err; } EXPORT_SYMBOL(__posix_acl_chmod); /** * posix_acl_chmod - chmod a posix acl * * @idmap: idmap of the mount @inode was found from * @dentry: dentry to check permissions on * @mode: the new mode of @inode * * If the dentry 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. */ int posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode) { struct inode *inode = d_inode(dentry); struct posix_acl *acl; int ret = 0; if (!IS_POSIXACL(inode)) return 0; if (!inode->i_op->set_acl) return -EOPNOTSUPP; acl = get_inode_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR_OR_NULL(acl)) { if (acl == ERR_PTR(-EOPNOTSUPP)) return 0; return PTR_ERR(acl); } ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode); if (ret) return ret; ret = inode->i_op->set_acl(idmap, dentry, acl, ACL_TYPE_ACCESS); posix_acl_release(acl); return ret; } EXPORT_SYMBOL(posix_acl_chmod); int posix_acl_create(struct inode *dir, umode_t *mode, struct posix_acl **default_acl, struct posix_acl **acl) { struct posix_acl *p; struct posix_acl *clone; int ret; *acl = NULL; *default_acl = NULL; if (S_ISLNK(*mode) || !IS_POSIXACL(dir)) return 0; p = get_inode_acl(dir, ACL_TYPE_DEFAULT); if (!p || p == ERR_PTR(-EOPNOTSUPP)) { *mode &= ~current_umask(); return 0; } if (IS_ERR(p)) return PTR_ERR(p); ret = -ENOMEM; clone = posix_acl_clone(p, GFP_NOFS); if (!clone) goto err_release; ret = posix_acl_create_masq(clone, mode); if (ret < 0) goto err_release_clone; if (ret == 0) posix_acl_release(clone); else *acl = clone; if (!S_ISDIR(*mode)) posix_acl_release(p); else *default_acl = p; return 0; err_release_clone: posix_acl_release(clone); err_release: posix_acl_release(p); return ret; } EXPORT_SYMBOL_GPL(posix_acl_create); /** * posix_acl_update_mode - update mode in set_acl * @idmap: idmap of the mount @inode was found from * @inode: target inode * @mode_p: mode (pointer) for update * @acl: acl pointer * * Update the file mode when setting an ACL: compute the new file permission * bits based on the ACL. In addition, if the ACL is equivalent to the new * file mode, set *@acl to NULL to indicate that no ACL should be set. * * As with chmod, clear the setgid bit if the caller is not in the owning group * or capable of CAP_FSETID (see inode_change_ok). * * 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. * * Called from set_acl inode operations. */ int posix_acl_update_mode(struct mnt_idmap *idmap, struct inode *inode, umode_t *mode_p, struct posix_acl **acl) { umode_t mode = inode->i_mode; int error; error = posix_acl_equiv_mode(*acl, &mode); if (error < 0) return error; if (error == 0) *acl = NULL; if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode))) mode &= ~S_ISGID; *mode_p = mode; return 0; } EXPORT_SYMBOL(posix_acl_update_mode); /* * Fix up the uids and gids in posix acl extended attributes in place. */ static int posix_acl_fix_xattr_common(const void *value, size_t size) { const struct posix_acl_xattr_header *header = value; int count; if (!header) return -EINVAL; if (size < sizeof(struct posix_acl_xattr_header)) return -EINVAL; if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION)) return -EOPNOTSUPP; count = posix_acl_xattr_count(size); if (count < 0) return -EINVAL; if (count == 0) return 0; return count; } /** * posix_acl_from_xattr - convert POSIX ACLs from backing store to VFS format * @userns: the filesystem's idmapping * @value: the uapi representation of POSIX ACLs * @size: the size of @void * * Filesystems that store POSIX ACLs in the unaltered uapi format should use * posix_acl_from_xattr() when reading them from the backing store and * converting them into the struct posix_acl VFS format. The helper is * specifically intended to be called from the acl inode operation. * * The posix_acl_from_xattr() function will map the raw {g,u}id values stored * in ACL_{GROUP,USER} entries into idmapping in @userns. * * Note that posix_acl_from_xattr() does not take idmapped mounts into account. * If it did it calling it from the get acl inode operation would return POSIX * ACLs mapped according to an idmapped mount which would mean that the value * couldn't be cached for the filesystem. Idmapped mounts are taken into * account on the fly during permission checking or right at the VFS - * userspace boundary before reporting them to the user. * * Return: Allocated struct posix_acl on success, NULL for a valid header but * without actual POSIX ACL entries, or ERR_PTR() encoded error code. */ struct posix_acl *posix_acl_from_xattr(struct user_namespace *userns, const void *value, size_t size) { const struct posix_acl_xattr_header *header = value; const struct posix_acl_xattr_entry *entry = (const void *)(header + 1), *end; int count; struct posix_acl *acl; struct posix_acl_entry *acl_e; count = posix_acl_fix_xattr_common(value, size); if (count < 0) return ERR_PTR(count); if (count == 0) return NULL; acl = posix_acl_alloc(count, GFP_NOFS); if (!acl) return ERR_PTR(-ENOMEM); acl_e = acl->a_entries; for (end = entry + count; entry != end; acl_e++, entry++) { acl_e->e_tag = le16_to_cpu(entry->e_tag); acl_e->e_perm = le16_to_cpu(entry->e_perm); switch(acl_e->e_tag) { case ACL_USER_OBJ: case ACL_GROUP_OBJ: case ACL_MASK: case ACL_OTHER: break; case ACL_USER: acl_e->e_uid = make_kuid(userns, le32_to_cpu(entry->e_id)); if (!uid_valid(acl_e->e_uid)) goto fail; break; case ACL_GROUP: acl_e->e_gid = make_kgid(userns, le32_to_cpu(entry->e_id)); if (!gid_valid(acl_e->e_gid)) goto fail; break; default: goto fail; } } return acl; fail: posix_acl_release(acl); return ERR_PTR(-EINVAL); } EXPORT_SYMBOL (posix_acl_from_xattr); /* * Convert from in-memory to extended attribute representation. */ int posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl, void *buffer, size_t size) { struct posix_acl_xattr_header *ext_acl = buffer; struct posix_acl_xattr_entry *ext_entry; int real_size, n; real_size = posix_acl_xattr_size(acl->a_count); if (!buffer) return real_size; if (real_size > size) return -ERANGE; ext_entry = (void *)(ext_acl + 1); ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION); for (n=0; n < acl->a_count; n++, ext_entry++) { const struct posix_acl_entry *acl_e = &acl->a_entries[n]; ext_entry->e_tag = cpu_to_le16(acl_e->e_tag); ext_entry->e_perm = cpu_to_le16(acl_e->e_perm); switch(acl_e->e_tag) { case ACL_USER: ext_entry->e_id = cpu_to_le32(from_kuid(user_ns, acl_e->e_uid)); break; case ACL_GROUP: ext_entry->e_id = cpu_to_le32(from_kgid(user_ns, acl_e->e_gid)); break; default: ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID); break; } } return real_size; } EXPORT_SYMBOL (posix_acl_to_xattr); /** * vfs_posix_acl_to_xattr - convert from kernel to userspace representation * @idmap: idmap of the mount * @inode: inode the posix acls are set on * @acl: the posix acls as represented by the vfs * @buffer: the buffer into which to convert @acl * @size: size of @buffer * * This converts @acl from the VFS representation in the filesystem idmapping * to the uapi form reportable to userspace. And mount and caller idmappings * are handled appropriately. * * Return: On success, the size of the stored uapi posix acls, on error a * negative errno. */ static ssize_t vfs_posix_acl_to_xattr(struct mnt_idmap *idmap, struct inode *inode, const struct posix_acl *acl, void *buffer, size_t size) { struct posix_acl_xattr_header *ext_acl = buffer; struct posix_acl_xattr_entry *ext_entry; struct user_namespace *fs_userns, *caller_userns; ssize_t real_size, n; vfsuid_t vfsuid; vfsgid_t vfsgid; real_size = posix_acl_xattr_size(acl->a_count); if (!buffer) return real_size; if (real_size > size) return -ERANGE; ext_entry = (void *)(ext_acl + 1); ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION); fs_userns = i_user_ns(inode); caller_userns = current_user_ns(); for (n=0; n < acl->a_count; n++, ext_entry++) { const struct posix_acl_entry *acl_e = &acl->a_entries[n]; ext_entry->e_tag = cpu_to_le16(acl_e->e_tag); ext_entry->e_perm = cpu_to_le16(acl_e->e_perm); switch(acl_e->e_tag) { case ACL_USER: vfsuid = make_vfsuid(idmap, fs_userns, acl_e->e_uid); ext_entry->e_id = cpu_to_le32(from_kuid( caller_userns, vfsuid_into_kuid(vfsuid))); break; case ACL_GROUP: vfsgid = make_vfsgid(idmap, fs_userns, acl_e->e_gid); ext_entry->e_id = cpu_to_le32(from_kgid( caller_userns, vfsgid_into_kgid(vfsgid))); break; default: ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID); break; } } return real_size; } int set_posix_acl(struct mnt_idmap *idmap, struct dentry *dentry, int type, struct posix_acl *acl) { struct inode *inode = d_inode(dentry); if (!IS_POSIXACL(inode)) return -EOPNOTSUPP; if (!inode->i_op->set_acl) return -EOPNOTSUPP; if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; if (acl) { int ret = posix_acl_valid(inode->i_sb->s_user_ns, acl); if (ret) return ret; } return inode->i_op->set_acl(idmap, dentry, acl, type); } EXPORT_SYMBOL(set_posix_acl); int posix_acl_listxattr(struct inode *inode, char **buffer, ssize_t *remaining_size) { int err; if (!IS_POSIXACL(inode)) return 0; if (inode->i_acl) { err = xattr_list_one(buffer, remaining_size, XATTR_NAME_POSIX_ACL_ACCESS); if (err) return err; } if (inode->i_default_acl) { err = xattr_list_one(buffer, remaining_size, XATTR_NAME_POSIX_ACL_DEFAULT); if (err) return err; } return 0; } static bool posix_acl_xattr_list(struct dentry *dentry) { return IS_POSIXACL(d_backing_inode(dentry)); } /* * nop_posix_acl_access - legacy xattr handler for access POSIX ACLs * * This is the legacy POSIX ACL access xattr handler. It is used by some * filesystems to implement their ->listxattr() inode operation. New code * should never use them. */ const struct xattr_handler nop_posix_acl_access = { .name = XATTR_NAME_POSIX_ACL_ACCESS, .list = posix_acl_xattr_list, }; EXPORT_SYMBOL_GPL(nop_posix_acl_access); /* * nop_posix_acl_default - legacy xattr handler for default POSIX ACLs * * This is the legacy POSIX ACL default xattr handler. It is used by some * filesystems to implement their ->listxattr() inode operation. New code * should never use them. */ const struct xattr_handler nop_posix_acl_default = { .name = XATTR_NAME_POSIX_ACL_DEFAULT, .list = posix_acl_xattr_list, }; EXPORT_SYMBOL_GPL(nop_posix_acl_default); int simple_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { int error; struct inode *inode = d_inode(dentry); if (type == ACL_TYPE_ACCESS) { error = posix_acl_update_mode(idmap, inode, &inode->i_mode, &acl); if (error) return error; } inode_set_ctime_current(inode); if (IS_I_VERSION(inode)) inode_inc_iversion(inode); set_cached_acl(inode, type, acl); return 0; } int simple_acl_create(struct inode *dir, struct inode *inode) { struct posix_acl *default_acl, *acl; int error; error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); if (error) return error; set_cached_acl(inode, ACL_TYPE_DEFAULT, default_acl); set_cached_acl(inode, ACL_TYPE_ACCESS, acl); if (default_acl) posix_acl_release(default_acl); if (acl) posix_acl_release(acl); return 0; } static int vfs_set_acl_idmapped_mnt(struct mnt_idmap *idmap, struct user_namespace *fs_userns, struct posix_acl *acl) { for (int n = 0; n < acl->a_count; n++) { struct posix_acl_entry *acl_e = &acl->a_entries[n]; switch (acl_e->e_tag) { case ACL_USER: acl_e->e_uid = from_vfsuid(idmap, fs_userns, VFSUIDT_INIT(acl_e->e_uid)); break; case ACL_GROUP: acl_e->e_gid = from_vfsgid(idmap, fs_userns, VFSGIDT_INIT(acl_e->e_gid)); break; } } return 0; } /** * vfs_set_acl - set posix acls * @idmap: idmap of the mount * @dentry: the dentry based on which to set the posix acls * @acl_name: the name of the posix acl * @kacl: the posix acls in the appropriate VFS format * * This function sets @kacl. The caller must all posix_acl_release() on @kacl * afterwards. * * Return: On success 0, on error negative errno. */ int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { int acl_type; int error; struct inode *inode = d_inode(dentry); struct inode *delegated_inode = NULL; acl_type = posix_acl_type(acl_name); if (acl_type < 0) return -EINVAL; if (kacl) { /* * If we're on an idmapped mount translate from mount specific * vfs{g,u}id_t into global filesystem k{g,u}id_t. * Afterwards we can cache the POSIX ACLs filesystem wide and - * if this is a filesystem with a backing store - ultimately * translate them to backing store values. */ error = vfs_set_acl_idmapped_mnt(idmap, i_user_ns(inode), kacl); if (error) return error; } retry_deleg: inode_lock(inode); /* * We only care about restrictions the inode struct itself places upon * us otherwise POSIX ACLs aren't subject to any VFS restrictions. */ error = may_write_xattr(idmap, inode); if (error) goto out_inode_unlock; error = security_inode_set_acl(idmap, dentry, acl_name, kacl); if (error) goto out_inode_unlock; error = try_break_deleg(inode, &delegated_inode); if (error) goto out_inode_unlock; if (likely(!is_bad_inode(inode))) error = set_posix_acl(idmap, dentry, acl_type, kacl); else error = -EIO; if (!error) { fsnotify_xattr(dentry); security_inode_post_set_acl(dentry, acl_name, kacl); } out_inode_unlock: inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_set_acl); /** * vfs_get_acl - get posix acls * @idmap: idmap of the mount * @dentry: the dentry based on which to retrieve the posix acls * @acl_name: the name of the posix acl * * This function retrieves @kacl from the filesystem. The caller must all * posix_acl_release() on @kacl. * * Return: On success POSIX ACLs in VFS format, on error negative errno. */ struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { struct inode *inode = d_inode(dentry); struct posix_acl *acl; int acl_type, error; acl_type = posix_acl_type(acl_name); if (acl_type < 0) return ERR_PTR(-EINVAL); /* * The VFS has no restrictions on reading POSIX ACLs so calling * something like xattr_permission() isn't needed. Only LSMs get a say. */ error = security_inode_get_acl(idmap, dentry, acl_name); if (error) return ERR_PTR(error); if (!IS_POSIXACL(inode)) return ERR_PTR(-EOPNOTSUPP); if (S_ISLNK(inode->i_mode)) return ERR_PTR(-EOPNOTSUPP); acl = __get_acl(idmap, dentry, inode, acl_type); if (IS_ERR(acl)) return acl; if (!acl) return ERR_PTR(-ENODATA); return acl; } EXPORT_SYMBOL_GPL(vfs_get_acl); /** * vfs_remove_acl - remove posix acls * @idmap: idmap of the mount * @dentry: the dentry based on which to retrieve the posix acls * @acl_name: the name of the posix acl * * This function removes posix acls. * * Return: On success 0, on error negative errno. */ int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { int acl_type; int error; struct inode *inode = d_inode(dentry); struct inode *delegated_inode = NULL; acl_type = posix_acl_type(acl_name); if (acl_type < 0) return -EINVAL; retry_deleg: inode_lock(inode); /* * We only care about restrictions the inode struct itself places upon * us otherwise POSIX ACLs aren't subject to any VFS restrictions. */ error = may_write_xattr(idmap, inode); if (error) goto out_inode_unlock; error = security_inode_remove_acl(idmap, dentry, acl_name); if (error) goto out_inode_unlock; error = try_break_deleg(inode, &delegated_inode); if (error) goto out_inode_unlock; if (likely(!is_bad_inode(inode))) error = set_posix_acl(idmap, dentry, acl_type, NULL); else error = -EIO; if (!error) { fsnotify_xattr(dentry); security_inode_post_remove_acl(idmap, dentry, acl_name); } out_inode_unlock: inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_remove_acl); int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, const void *kvalue, size_t size) { int error; struct posix_acl *acl = NULL; if (size) { /* * Note that posix_acl_from_xattr() uses GFP_NOFS when it * probably doesn't need to here. */ acl = posix_acl_from_xattr(current_user_ns(), kvalue, size); if (IS_ERR(acl)) return PTR_ERR(acl); } error = vfs_set_acl(idmap, dentry, acl_name, acl); posix_acl_release(acl); return error; } ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, void *kvalue, size_t size) { ssize_t error; struct posix_acl *acl; acl = vfs_get_acl(idmap, dentry, acl_name); if (IS_ERR(acl)) return PTR_ERR(acl); error = vfs_posix_acl_to_xattr(idmap, d_inode(dentry), acl, kvalue, size); posix_acl_release(acl); return error; } |
| 3476 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Provides code common for host and device side USB. * * If either host side (ie. CONFIG_USB=y) or device side USB stack * (ie. CONFIG_USB_GADGET=y) is compiled in the kernel, this module is * compiled-in as well. Otherwise, if either of the two stacks is * compiled as module, this file is compiled as module as well. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/of.h> #include <linux/platform_device.h> #include <linux/usb/ch9.h> #include <linux/usb/of.h> #include <linux/usb/otg.h> #include <linux/of_platform.h> #include <linux/debugfs.h> #include "common.h" static const char *const ep_type_names[] = { [USB_ENDPOINT_XFER_CONTROL] = "ctrl", [USB_ENDPOINT_XFER_ISOC] = "isoc", [USB_ENDPOINT_XFER_BULK] = "bulk", [USB_ENDPOINT_XFER_INT] = "intr", }; /** * usb_ep_type_string() - Returns human readable-name of the endpoint type. * @ep_type: The endpoint type to return human-readable name for. If it's not * any of the types: USB_ENDPOINT_XFER_{CONTROL, ISOC, BULK, INT}, * usually got by usb_endpoint_type(), the string 'unknown' will be returned. */ const char *usb_ep_type_string(int ep_type) { if (ep_type < 0 || ep_type >= ARRAY_SIZE(ep_type_names)) return "unknown"; return ep_type_names[ep_type]; } EXPORT_SYMBOL_GPL(usb_ep_type_string); /** * usb_otg_state_string() - returns human readable name of OTG state. * @state: the OTG state to return the human readable name of. If it's not * any of the states defined in usb_otg_state enum, 'UNDEFINED' will be * returned. */ const char *usb_otg_state_string(enum usb_otg_state state) { static const char *const names[] = { [OTG_STATE_A_IDLE] = "a_idle", [OTG_STATE_A_WAIT_VRISE] = "a_wait_vrise", [OTG_STATE_A_WAIT_BCON] = "a_wait_bcon", [OTG_STATE_A_HOST] = "a_host", [OTG_STATE_A_SUSPEND] = "a_suspend", [OTG_STATE_A_PERIPHERAL] = "a_peripheral", [OTG_STATE_A_WAIT_VFALL] = "a_wait_vfall", [OTG_STATE_A_VBUS_ERR] = "a_vbus_err", [OTG_STATE_B_IDLE] = "b_idle", [OTG_STATE_B_SRP_INIT] = "b_srp_init", [OTG_STATE_B_PERIPHERAL] = "b_peripheral", [OTG_STATE_B_WAIT_ACON] = "b_wait_acon", [OTG_STATE_B_HOST] = "b_host", }; if (state < 0 || state >= ARRAY_SIZE(names)) return "UNDEFINED"; return names[state]; } EXPORT_SYMBOL_GPL(usb_otg_state_string); static const char *const speed_names[] = { [USB_SPEED_UNKNOWN] = "UNKNOWN", [USB_SPEED_LOW] = "low-speed", [USB_SPEED_FULL] = "full-speed", [USB_SPEED_HIGH] = "high-speed", [USB_SPEED_WIRELESS] = "wireless", [USB_SPEED_SUPER] = "super-speed", [USB_SPEED_SUPER_PLUS] = "super-speed-plus", }; static const char *const ssp_rate[] = { [USB_SSP_GEN_UNKNOWN] = "UNKNOWN", [USB_SSP_GEN_2x1] = "super-speed-plus-gen2x1", [USB_SSP_GEN_1x2] = "super-speed-plus-gen1x2", [USB_SSP_GEN_2x2] = "super-speed-plus-gen2x2", }; /** * usb_speed_string() - Returns human readable-name of the speed. * @speed: The speed to return human-readable name for. If it's not * any of the speeds defined in usb_device_speed enum, string for * USB_SPEED_UNKNOWN will be returned. */ const char *usb_speed_string(enum usb_device_speed speed) { if (speed < 0 || speed >= ARRAY_SIZE(speed_names)) speed = USB_SPEED_UNKNOWN; return speed_names[speed]; } EXPORT_SYMBOL_GPL(usb_speed_string); /** * usb_get_maximum_speed - Get maximum requested speed for a given USB * controller. * @dev: Pointer to the given USB controller device * * The function gets the maximum speed string from property "maximum-speed", * and returns the corresponding enum usb_device_speed. */ enum usb_device_speed usb_get_maximum_speed(struct device *dev) { const char *p = "maximum-speed"; int ret; ret = device_property_match_property_string(dev, p, ssp_rate, ARRAY_SIZE(ssp_rate)); if (ret > 0) return USB_SPEED_SUPER_PLUS; ret = device_property_match_property_string(dev, p, speed_names, ARRAY_SIZE(speed_names)); if (ret > 0) return ret; return USB_SPEED_UNKNOWN; } EXPORT_SYMBOL_GPL(usb_get_maximum_speed); /** * usb_get_maximum_ssp_rate - Get the signaling rate generation and lane count * of a SuperSpeed Plus capable device. * @dev: Pointer to the given USB controller device * * If the string from "maximum-speed" property is super-speed-plus-genXxY where * 'X' is the generation number and 'Y' is the number of lanes, then this * function returns the corresponding enum usb_ssp_rate. */ enum usb_ssp_rate usb_get_maximum_ssp_rate(struct device *dev) { const char *maximum_speed; int ret; ret = device_property_read_string(dev, "maximum-speed", &maximum_speed); if (ret < 0) return USB_SSP_GEN_UNKNOWN; ret = match_string(ssp_rate, ARRAY_SIZE(ssp_rate), maximum_speed); return (ret < 0) ? USB_SSP_GEN_UNKNOWN : ret; } EXPORT_SYMBOL_GPL(usb_get_maximum_ssp_rate); /** * usb_state_string - Returns human readable name for the state. * @state: The state to return a human-readable name for. If it's not * any of the states devices in usb_device_state_string enum, * the string UNKNOWN will be returned. */ const char *usb_state_string(enum usb_device_state state) { static const char *const names[] = { [USB_STATE_NOTATTACHED] = "not attached", [USB_STATE_ATTACHED] = "attached", [USB_STATE_POWERED] = "powered", [USB_STATE_RECONNECTING] = "reconnecting", [USB_STATE_UNAUTHENTICATED] = "unauthenticated", [USB_STATE_DEFAULT] = "default", [USB_STATE_ADDRESS] = "addressed", [USB_STATE_CONFIGURED] = "configured", [USB_STATE_SUSPENDED] = "suspended", }; if (state < 0 || state >= ARRAY_SIZE(names)) return "UNKNOWN"; return names[state]; } EXPORT_SYMBOL_GPL(usb_state_string); static const char *const usb_dr_modes[] = { [USB_DR_MODE_UNKNOWN] = "", [USB_DR_MODE_HOST] = "host", [USB_DR_MODE_PERIPHERAL] = "peripheral", [USB_DR_MODE_OTG] = "otg", }; /** * usb_get_dr_mode_from_string() - Get dual role mode for given string * @str: String to find the corresponding dual role mode for * * This function performs a lookup for the given string and returns the * corresponding enum usb_dr_mode. If no match for the string could be found, * 'USB_DR_MODE_UNKNOWN' is returned. */ static enum usb_dr_mode usb_get_dr_mode_from_string(const char *str) { int ret; ret = match_string(usb_dr_modes, ARRAY_SIZE(usb_dr_modes), str); return (ret < 0) ? USB_DR_MODE_UNKNOWN : ret; } enum usb_dr_mode usb_get_dr_mode(struct device *dev) { const char *dr_mode; int err; err = device_property_read_string(dev, "dr_mode", &dr_mode); if (err < 0) return USB_DR_MODE_UNKNOWN; return usb_get_dr_mode_from_string(dr_mode); } EXPORT_SYMBOL_GPL(usb_get_dr_mode); /** * usb_get_role_switch_default_mode - Get default mode for given device * @dev: Pointer to the given device * * The function gets string from property 'role-switch-default-mode', * and returns the corresponding enum usb_dr_mode. */ enum usb_dr_mode usb_get_role_switch_default_mode(struct device *dev) { const char *str; int ret; ret = device_property_read_string(dev, "role-switch-default-mode", &str); if (ret < 0) return USB_DR_MODE_UNKNOWN; return usb_get_dr_mode_from_string(str); } EXPORT_SYMBOL_GPL(usb_get_role_switch_default_mode); /** * usb_decode_interval - Decode bInterval into the time expressed in 1us unit * @epd: The descriptor of the endpoint * @speed: The speed that the endpoint works as * * Function returns the interval expressed in 1us unit for servicing * endpoint for data transfers. */ unsigned int usb_decode_interval(const struct usb_endpoint_descriptor *epd, enum usb_device_speed speed) { unsigned int interval = 0; switch (usb_endpoint_type(epd)) { case USB_ENDPOINT_XFER_CONTROL: /* uframes per NAK */ if (speed == USB_SPEED_HIGH) interval = epd->bInterval; break; case USB_ENDPOINT_XFER_ISOC: interval = 1 << (epd->bInterval - 1); break; case USB_ENDPOINT_XFER_BULK: /* uframes per NAK */ if (speed == USB_SPEED_HIGH && usb_endpoint_dir_out(epd)) interval = epd->bInterval; break; case USB_ENDPOINT_XFER_INT: if (speed >= USB_SPEED_HIGH) interval = 1 << (epd->bInterval - 1); else interval = epd->bInterval; break; } interval *= (speed >= USB_SPEED_HIGH) ? 125 : 1000; return interval; } EXPORT_SYMBOL_GPL(usb_decode_interval); #ifdef CONFIG_OF /** * of_usb_get_dr_mode_by_phy - Get dual role mode for the controller device * which is associated with the given phy device_node * @np: Pointer to the given phy device_node * @arg0: phandle args[0] for phy's with #phy-cells >= 1, or -1 for * phys which do not have phy-cells * * In dts a usb controller associates with phy devices. The function gets * the string from property 'dr_mode' of the controller associated with the * given phy device node, and returns the correspondig enum usb_dr_mode. */ enum usb_dr_mode of_usb_get_dr_mode_by_phy(struct device_node *np, int arg0) { struct device_node *controller; struct of_phandle_args args; const char *dr_mode; int index; int err; for_each_node_with_property(controller, "phys") { if (!of_device_is_available(controller)) continue; index = 0; do { if (arg0 == -1) { args.np = of_parse_phandle(controller, "phys", index); args.args_count = 0; } else { err = of_parse_phandle_with_args(controller, "phys", "#phy-cells", index, &args); if (err) break; } of_node_put(args.np); if (args.np == np && (args.args_count == 0 || args.args[0] == arg0)) goto finish; index++; } while (args.np); } finish: err = of_property_read_string(controller, "dr_mode", &dr_mode); of_node_put(controller); if (err < 0) return USB_DR_MODE_UNKNOWN; return usb_get_dr_mode_from_string(dr_mode); } EXPORT_SYMBOL_GPL(of_usb_get_dr_mode_by_phy); /** * of_usb_host_tpl_support - to get if Targeted Peripheral List is supported * for given targeted hosts (non-PC hosts) * @np: Pointer to the given device_node * * The function gets if the targeted hosts support TPL or not */ bool of_usb_host_tpl_support(struct device_node *np) { return of_property_read_bool(np, "tpl-support"); } EXPORT_SYMBOL_GPL(of_usb_host_tpl_support); /** * of_usb_update_otg_caps - to update usb otg capabilities according to * the passed properties in DT. * @np: Pointer to the given device_node * @otg_caps: Pointer to the target usb_otg_caps to be set * * The function updates the otg capabilities */ int of_usb_update_otg_caps(struct device_node *np, struct usb_otg_caps *otg_caps) { u32 otg_rev; if (!otg_caps) return -EINVAL; if (!of_property_read_u32(np, "otg-rev", &otg_rev)) { switch (otg_rev) { case 0x0100: case 0x0120: case 0x0130: case 0x0200: /* Choose the lesser one if it's already been set */ if (otg_caps->otg_rev) otg_caps->otg_rev = min_t(u16, otg_rev, otg_caps->otg_rev); else otg_caps->otg_rev = otg_rev; break; default: pr_err("%pOF: unsupported otg-rev: 0x%x\n", np, otg_rev); return -EINVAL; } } else { /* * otg-rev is mandatory for otg properties, if not passed * we set it to be 0 and assume it's a legacy otg device. * Non-dt platform can set it afterwards. */ otg_caps->otg_rev = 0; } if (of_property_read_bool(np, "hnp-disable")) otg_caps->hnp_support = false; if (of_property_read_bool(np, "srp-disable")) otg_caps->srp_support = false; if (of_property_read_bool(np, "adp-disable") || (otg_caps->otg_rev < 0x0200)) otg_caps->adp_support = false; return 0; } EXPORT_SYMBOL_GPL(of_usb_update_otg_caps); /** * usb_of_get_companion_dev - Find the companion device * @dev: the device pointer to find a companion * * Find the companion device from platform bus. * * Takes a reference to the returned struct device which needs to be dropped * after use. * * Return: On success, a pointer to the companion device, %NULL on failure. */ struct device *usb_of_get_companion_dev(struct device *dev) { struct device_node *node; struct platform_device *pdev = NULL; node = of_parse_phandle(dev->of_node, "companion", 0); if (node) pdev = of_find_device_by_node(node); of_node_put(node); return pdev ? &pdev->dev : NULL; } EXPORT_SYMBOL_GPL(usb_of_get_companion_dev); #endif struct dentry *usb_debug_root; EXPORT_SYMBOL_GPL(usb_debug_root); DEFINE_MUTEX(usb_dynids_lock); EXPORT_SYMBOL_GPL(usb_dynids_lock); static int __init usb_common_init(void) { usb_debug_root = debugfs_create_dir("usb", NULL); ledtrig_usb_init(); return 0; } static void __exit usb_common_exit(void) { ledtrig_usb_exit(); debugfs_remove_recursive(usb_debug_root); } subsys_initcall(usb_common_init); module_exit(usb_common_exit); MODULE_DESCRIPTION("Common code for host and device side USB"); MODULE_LICENSE("GPL"); |
| 1158 1159 1158 670 1159 1157 1156 1155 1158 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * jump label x86 support * * Copyright (C) 2009 Jason Baron <jbaron@redhat.com> * */ #include <linux/jump_label.h> #include <linux/memory.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/list.h> #include <linux/jhash.h> #include <linux/cpu.h> #include <asm/kprobes.h> #include <asm/alternative.h> #include <asm/text-patching.h> #include <asm/insn.h> int arch_jump_entry_size(struct jump_entry *entry) { struct insn insn = {}; insn_decode_kernel(&insn, (void *)jump_entry_code(entry)); BUG_ON(insn.length != 2 && insn.length != 5); return insn.length; } struct jump_label_patch { const void *code; int size; }; static struct jump_label_patch __jump_label_patch(struct jump_entry *entry, enum jump_label_type type) { const void *expect, *code, *nop; const void *addr, *dest; int size; addr = (void *)jump_entry_code(entry); dest = (void *)jump_entry_target(entry); size = arch_jump_entry_size(entry); switch (size) { case JMP8_INSN_SIZE: code = text_gen_insn(JMP8_INSN_OPCODE, addr, dest); nop = x86_nops[size]; break; case JMP32_INSN_SIZE: code = text_gen_insn(JMP32_INSN_OPCODE, addr, dest); nop = x86_nops[size]; break; default: BUG(); } if (type == JUMP_LABEL_JMP) expect = nop; else expect = code; if (memcmp(addr, expect, size)) { /* * The location is not an op that we were expecting. * Something went wrong. Crash the box, as something could be * corrupting the kernel. */ pr_crit("jump_label: Fatal kernel bug, unexpected op at %pS [%p] (%5ph != %5ph)) size:%d type:%d\n", addr, addr, addr, expect, size, type); BUG(); } if (type == JUMP_LABEL_NOP) code = nop; return (struct jump_label_patch){.code = code, .size = size}; } static __always_inline void __jump_label_transform(struct jump_entry *entry, enum jump_label_type type, int init) { const struct jump_label_patch jlp = __jump_label_patch(entry, type); /* * As long as only a single processor is running and the code is still * not marked as RO, text_poke_early() can be used; Checking that * system_state is SYSTEM_BOOTING guarantees it. It will be set to * SYSTEM_SCHEDULING before other cores are awaken and before the * code is write-protected. * * At the time the change is being done, just ignore whether we * are doing nop -> jump or jump -> nop transition, and assume * always nop being the 'currently valid' instruction */ if (init || system_state == SYSTEM_BOOTING) { text_poke_early((void *)jump_entry_code(entry), jlp.code, jlp.size); return; } text_poke_bp((void *)jump_entry_code(entry), jlp.code, jlp.size, NULL); } static void __ref jump_label_transform(struct jump_entry *entry, enum jump_label_type type, int init) { mutex_lock(&text_mutex); __jump_label_transform(entry, type, init); mutex_unlock(&text_mutex); } void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type) { jump_label_transform(entry, type, 0); } bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type) { struct jump_label_patch jlp; if (system_state == SYSTEM_BOOTING) { /* * Fallback to the non-batching mode. */ arch_jump_label_transform(entry, type); return true; } mutex_lock(&text_mutex); jlp = __jump_label_patch(entry, type); text_poke_queue((void *)jump_entry_code(entry), jlp.code, jlp.size, NULL); mutex_unlock(&text_mutex); return true; } void arch_jump_label_transform_apply(void) { mutex_lock(&text_mutex); text_poke_finish(); mutex_unlock(&text_mutex); } |
| 3 2189 1072 2189 43 43 8 1072 1073 | 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-only */ /* A pointer that can point to either kernel or userspace memory. */ #ifndef _LINUX_BPFPTR_H #define _LINUX_BPFPTR_H #include <linux/mm.h> #include <linux/sockptr.h> typedef sockptr_t bpfptr_t; static inline bool bpfptr_is_kernel(bpfptr_t bpfptr) { return bpfptr.is_kernel; } static inline bpfptr_t KERNEL_BPFPTR(void *p) { return (bpfptr_t) { .kernel = p, .is_kernel = true }; } static inline bpfptr_t USER_BPFPTR(void __user *p) { return (bpfptr_t) { .user = p }; } static inline bpfptr_t make_bpfptr(u64 addr, bool is_kernel) { if (is_kernel) return KERNEL_BPFPTR((void*) (uintptr_t) addr); else return USER_BPFPTR(u64_to_user_ptr(addr)); } static inline bool bpfptr_is_null(bpfptr_t bpfptr) { if (bpfptr_is_kernel(bpfptr)) return !bpfptr.kernel; return !bpfptr.user; } static inline void bpfptr_add(bpfptr_t *bpfptr, size_t val) { if (bpfptr_is_kernel(*bpfptr)) bpfptr->kernel += val; else bpfptr->user += val; } static inline int copy_from_bpfptr_offset(void *dst, bpfptr_t src, size_t offset, size_t size) { if (!bpfptr_is_kernel(src)) return copy_from_user(dst, src.user + offset, size); return copy_from_kernel_nofault(dst, src.kernel + offset, size); } static inline int copy_from_bpfptr(void *dst, bpfptr_t src, size_t size) { return copy_from_bpfptr_offset(dst, src, 0, size); } static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset, const void *src, size_t size) { return copy_to_sockptr_offset((sockptr_t) dst, offset, src, size); } static inline void *kvmemdup_bpfptr_noprof(bpfptr_t src, size_t len) { void *p = kvmalloc_noprof(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_bpfptr(p, src, len)) { kvfree(p); return ERR_PTR(-EFAULT); } return p; } #define kvmemdup_bpfptr(...) alloc_hooks(kvmemdup_bpfptr_noprof(__VA_ARGS__)) static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count) { if (bpfptr_is_kernel(src)) return strncpy_from_kernel_nofault(dst, src.kernel, count); return strncpy_from_user(dst, src.user, count); } #endif /* _LINUX_BPFPTR_H */ |
| 4 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Greybus driver and device API * * Copyright 2015 Google Inc. * Copyright 2015 Linaro Ltd. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM greybus #if !defined(_TRACE_GREYBUS_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_GREYBUS_H #include <linux/tracepoint.h> struct gb_message; struct gb_operation; struct gb_connection; struct gb_bundle; struct gb_host_device; DECLARE_EVENT_CLASS(gb_message, TP_PROTO(struct gb_message *message), TP_ARGS(message), TP_STRUCT__entry( __field(u16, size) __field(u16, operation_id) __field(u8, type) __field(u8, result) ), TP_fast_assign( __entry->size = le16_to_cpu(message->header->size); __entry->operation_id = le16_to_cpu(message->header->operation_id); __entry->type = message->header->type; __entry->result = message->header->result; ), TP_printk("size=%u operation_id=0x%04x type=0x%02x result=0x%02x", __entry->size, __entry->operation_id, __entry->type, __entry->result) ); #define DEFINE_MESSAGE_EVENT(name) \ DEFINE_EVENT(gb_message, name, \ TP_PROTO(struct gb_message *message), \ TP_ARGS(message)) /* * Occurs immediately before calling a host device's message_send() * method. */ DEFINE_MESSAGE_EVENT(gb_message_send); /* * Occurs after an incoming request message has been received */ DEFINE_MESSAGE_EVENT(gb_message_recv_request); /* * Occurs after an incoming response message has been received, * after its matching request has been found. */ DEFINE_MESSAGE_EVENT(gb_message_recv_response); /* * Occurs after an operation has been canceled, possibly before the * cancellation is complete. */ DEFINE_MESSAGE_EVENT(gb_message_cancel_outgoing); /* * Occurs when an incoming request is cancelled; if the response has * been queued for sending, this occurs after it is sent. */ DEFINE_MESSAGE_EVENT(gb_message_cancel_incoming); /* * Occurs in the host driver message_send() function just prior to * handing off the data to be processed by hardware. */ DEFINE_MESSAGE_EVENT(gb_message_submit); #undef DEFINE_MESSAGE_EVENT DECLARE_EVENT_CLASS(gb_operation, TP_PROTO(struct gb_operation *operation), TP_ARGS(operation), TP_STRUCT__entry( __field(u16, cport_id) /* CPort of HD side of connection */ __field(u16, id) /* Operation ID */ __field(u8, type) __field(unsigned long, flags) __field(int, active) __field(int, waiters) __field(int, errno) ), TP_fast_assign( __entry->cport_id = operation->connection->hd_cport_id; __entry->id = operation->id; __entry->type = operation->type; __entry->flags = operation->flags; __entry->active = operation->active; __entry->waiters = atomic_read(&operation->waiters); __entry->errno = operation->errno; ), TP_printk("id=%04x type=0x%02x cport_id=%04x flags=0x%lx active=%d waiters=%d errno=%d", __entry->id, __entry->cport_id, __entry->type, __entry->flags, __entry->active, __entry->waiters, __entry->errno) ); #define DEFINE_OPERATION_EVENT(name) \ DEFINE_EVENT(gb_operation, name, \ TP_PROTO(struct gb_operation *operation), \ TP_ARGS(operation)) /* * Occurs after a new operation is created for an outgoing request * has been successfully created. */ DEFINE_OPERATION_EVENT(gb_operation_create); /* * Occurs after a new core operation has been created. */ DEFINE_OPERATION_EVENT(gb_operation_create_core); /* * Occurs after a new operation has been created for an incoming * request has been successfully created and initialized. */ DEFINE_OPERATION_EVENT(gb_operation_create_incoming); /* * Occurs when the last reference to an operation has been dropped, * prior to freeing resources. */ DEFINE_OPERATION_EVENT(gb_operation_destroy); /* * Occurs when an operation has been marked active, after updating * its active count. */ DEFINE_OPERATION_EVENT(gb_operation_get_active); /* * Occurs when an operation has been marked active, before updating * its active count. */ DEFINE_OPERATION_EVENT(gb_operation_put_active); #undef DEFINE_OPERATION_EVENT DECLARE_EVENT_CLASS(gb_connection, TP_PROTO(struct gb_connection *connection), TP_ARGS(connection), TP_STRUCT__entry( __field(int, hd_bus_id) __field(u8, bundle_id) /* name contains "hd_cport_id/intf_id:cport_id" */ __dynamic_array(char, name, sizeof(connection->name)) __field(enum gb_connection_state, state) __field(unsigned long, flags) ), TP_fast_assign( __entry->hd_bus_id = connection->hd->bus_id; __entry->bundle_id = connection->bundle ? connection->bundle->id : BUNDLE_ID_NONE; memcpy(__get_str(name), connection->name, sizeof(connection->name)); __entry->state = connection->state; __entry->flags = connection->flags; ), TP_printk("hd_bus_id=%d bundle_id=0x%02x name=\"%s\" state=%u flags=0x%lx", __entry->hd_bus_id, __entry->bundle_id, __get_str(name), (unsigned int)__entry->state, __entry->flags) ); #define DEFINE_CONNECTION_EVENT(name) \ DEFINE_EVENT(gb_connection, name, \ TP_PROTO(struct gb_connection *connection), \ TP_ARGS(connection)) /* * Occurs after a new connection is successfully created. */ DEFINE_CONNECTION_EVENT(gb_connection_create); /* * Occurs when the last reference to a connection has been dropped, * before its resources are freed. */ DEFINE_CONNECTION_EVENT(gb_connection_release); /* * Occurs when a new reference to connection is added, currently * only when a message over the connection is received. */ DEFINE_CONNECTION_EVENT(gb_connection_get); /* * Occurs when a new reference to connection is dropped, after a * a received message is handled, or when the connection is * destroyed. */ DEFINE_CONNECTION_EVENT(gb_connection_put); /* * Occurs when a request to enable a connection is made, either for * transmit only, or for both transmit and receive. */ DEFINE_CONNECTION_EVENT(gb_connection_enable); /* * Occurs when a request to disable a connection is made, either for * receive only, or for both transmit and receive. Also occurs when * a request to forcefully disable a connection is made. */ DEFINE_CONNECTION_EVENT(gb_connection_disable); #undef DEFINE_CONNECTION_EVENT DECLARE_EVENT_CLASS(gb_bundle, TP_PROTO(struct gb_bundle *bundle), TP_ARGS(bundle), TP_STRUCT__entry( __field(u8, intf_id) __field(u8, id) __field(u8, class) __field(size_t, num_cports) ), TP_fast_assign( __entry->intf_id = bundle->intf->interface_id; __entry->id = bundle->id; __entry->class = bundle->class; __entry->num_cports = bundle->num_cports; ), TP_printk("intf_id=0x%02x id=%02x class=0x%02x num_cports=%zu", __entry->intf_id, __entry->id, __entry->class, __entry->num_cports) ); #define DEFINE_BUNDLE_EVENT(name) \ DEFINE_EVENT(gb_bundle, name, \ TP_PROTO(struct gb_bundle *bundle), \ TP_ARGS(bundle)) /* * Occurs after a new bundle is successfully created. */ DEFINE_BUNDLE_EVENT(gb_bundle_create); /* * Occurs when the last reference to a bundle has been dropped, * before its resources are freed. */ DEFINE_BUNDLE_EVENT(gb_bundle_release); /* * Occurs when a bundle is added to an interface when the interface * is enabled. */ DEFINE_BUNDLE_EVENT(gb_bundle_add); /* * Occurs when a registered bundle gets destroyed, normally at the * time an interface is disabled. */ DEFINE_BUNDLE_EVENT(gb_bundle_destroy); #undef DEFINE_BUNDLE_EVENT DECLARE_EVENT_CLASS(gb_interface, TP_PROTO(struct gb_interface *intf), TP_ARGS(intf), TP_STRUCT__entry( __field(u8, module_id) __field(u8, id) /* Interface id */ __field(u8, device_id) __field(int, disconnected) /* bool */ __field(int, ejected) /* bool */ __field(int, active) /* bool */ __field(int, enabled) /* bool */ __field(int, mode_switch) /* bool */ ), TP_fast_assign( __entry->module_id = intf->module->module_id; __entry->id = intf->interface_id; __entry->device_id = intf->device_id; __entry->disconnected = intf->disconnected; __entry->ejected = intf->ejected; __entry->active = intf->active; __entry->enabled = intf->enabled; __entry->mode_switch = intf->mode_switch; ), TP_printk("intf_id=%u device_id=%u module_id=%u D=%d J=%d A=%d E=%d M=%d", __entry->id, __entry->device_id, __entry->module_id, __entry->disconnected, __entry->ejected, __entry->active, __entry->enabled, __entry->mode_switch) ); #define DEFINE_INTERFACE_EVENT(name) \ DEFINE_EVENT(gb_interface, name, \ TP_PROTO(struct gb_interface *intf), \ TP_ARGS(intf)) /* * Occurs after a new interface is successfully created. */ DEFINE_INTERFACE_EVENT(gb_interface_create); /* * Occurs after the last reference to an interface has been dropped. */ DEFINE_INTERFACE_EVENT(gb_interface_release); /* * Occurs after an interface been registerd. */ DEFINE_INTERFACE_EVENT(gb_interface_add); /* * Occurs when a registered interface gets deregisterd. */ DEFINE_INTERFACE_EVENT(gb_interface_del); /* * Occurs when a registered interface has been successfully * activated. */ DEFINE_INTERFACE_EVENT(gb_interface_activate); /* * Occurs when an activated interface is being deactivated. */ DEFINE_INTERFACE_EVENT(gb_interface_deactivate); /* * Occurs when an interface has been successfully enabled. */ DEFINE_INTERFACE_EVENT(gb_interface_enable); /* * Occurs when an enabled interface is being disabled. */ DEFINE_INTERFACE_EVENT(gb_interface_disable); #undef DEFINE_INTERFACE_EVENT DECLARE_EVENT_CLASS(gb_module, TP_PROTO(struct gb_module *module), TP_ARGS(module), TP_STRUCT__entry( __field(int, hd_bus_id) __field(u8, module_id) __field(size_t, num_interfaces) __field(int, disconnected) /* bool */ ), TP_fast_assign( __entry->hd_bus_id = module->hd->bus_id; __entry->module_id = module->module_id; __entry->num_interfaces = module->num_interfaces; __entry->disconnected = module->disconnected; ), TP_printk("hd_bus_id=%d module_id=%u num_interfaces=%zu disconnected=%d", __entry->hd_bus_id, __entry->module_id, __entry->num_interfaces, __entry->disconnected) ); #define DEFINE_MODULE_EVENT(name) \ DEFINE_EVENT(gb_module, name, \ TP_PROTO(struct gb_module *module), \ TP_ARGS(module)) /* * Occurs after a new module is successfully created, before * creating any of its interfaces. */ DEFINE_MODULE_EVENT(gb_module_create); /* * Occurs after the last reference to a module has been dropped. */ DEFINE_MODULE_EVENT(gb_module_release); /* * Occurs after a module is successfully created, before registering * any of its interfaces. */ DEFINE_MODULE_EVENT(gb_module_add); /* * Occurs when a module is deleted, before deregistering its * interfaces. */ DEFINE_MODULE_EVENT(gb_module_del); #undef DEFINE_MODULE_EVENT DECLARE_EVENT_CLASS(gb_host_device, TP_PROTO(struct gb_host_device *hd), TP_ARGS(hd), TP_STRUCT__entry( __field(int, bus_id) __field(size_t, num_cports) __field(size_t, buffer_size_max) ), TP_fast_assign( __entry->bus_id = hd->bus_id; __entry->num_cports = hd->num_cports; __entry->buffer_size_max = hd->buffer_size_max; ), TP_printk("bus_id=%d num_cports=%zu mtu=%zu", __entry->bus_id, __entry->num_cports, __entry->buffer_size_max) ); #define DEFINE_HD_EVENT(name) \ DEFINE_EVENT(gb_host_device, name, \ TP_PROTO(struct gb_host_device *hd), \ TP_ARGS(hd)) /* * Occurs after a new host device is successfully created, before * its SVC has been set up. */ DEFINE_HD_EVENT(gb_hd_create); /* * Occurs after the last reference to a host device has been * dropped. */ DEFINE_HD_EVENT(gb_hd_release); /* * Occurs after a new host device has been added, after the * connection to its SVC has been enabled. */ DEFINE_HD_EVENT(gb_hd_add); /* * Occurs when a host device is being disconnected from the AP USB * host controller. */ DEFINE_HD_EVENT(gb_hd_del); /* * Occurs when a host device has passed received data to the Greybus * core, after it has been determined it is destined for a valid * CPort. */ DEFINE_HD_EVENT(gb_hd_in); #undef DEFINE_HD_EVENT #endif /* _TRACE_GREYBUS_H */ /* This part must be outside protection */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . /* * TRACE_INCLUDE_FILE is not needed if the filename and TRACE_SYSTEM are equal */ #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE greybus_trace #include <trace/define_trace.h> |
| 14 14 14 | 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2003-2008 Takahiro Hirofuchi * Copyright (C) 2015 Nobuo Iwata */ #include <linux/kthread.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/workqueue.h> #include "usbip_common.h" struct usbip_event { struct list_head node; struct usbip_device *ud; }; static DEFINE_SPINLOCK(event_lock); static LIST_HEAD(event_list); static void set_event(struct usbip_device *ud, unsigned long event) { unsigned long flags; spin_lock_irqsave(&ud->lock, flags); ud->event |= event; spin_unlock_irqrestore(&ud->lock, flags); } static void unset_event(struct usbip_device *ud, unsigned long event) { unsigned long flags; spin_lock_irqsave(&ud->lock, flags); ud->event &= ~event; spin_unlock_irqrestore(&ud->lock, flags); } static struct usbip_device *get_event(void) { struct usbip_event *ue = NULL; struct usbip_device *ud = NULL; unsigned long flags; spin_lock_irqsave(&event_lock, flags); if (!list_empty(&event_list)) { ue = list_first_entry(&event_list, struct usbip_event, node); list_del(&ue->node); } spin_unlock_irqrestore(&event_lock, flags); if (ue) { ud = ue->ud; kfree(ue); } return ud; } static struct task_struct *worker_context; static void event_handler(struct work_struct *work) { struct usbip_device *ud; if (worker_context == NULL) { worker_context = current; } while ((ud = get_event()) != NULL) { usbip_dbg_eh("pending event %lx\n", ud->event); mutex_lock(&ud->sysfs_lock); /* * NOTE: shutdown must come first. * Shutdown the device. */ if (ud->event & USBIP_EH_SHUTDOWN) { ud->eh_ops.shutdown(ud); unset_event(ud, USBIP_EH_SHUTDOWN); } /* Reset the device. */ if (ud->event & USBIP_EH_RESET) { ud->eh_ops.reset(ud); unset_event(ud, USBIP_EH_RESET); } /* Mark the device as unusable. */ if (ud->event & USBIP_EH_UNUSABLE) { ud->eh_ops.unusable(ud); unset_event(ud, USBIP_EH_UNUSABLE); } mutex_unlock(&ud->sysfs_lock); wake_up(&ud->eh_waitq); } } int usbip_start_eh(struct usbip_device *ud) { init_waitqueue_head(&ud->eh_waitq); ud->event = 0; return 0; } EXPORT_SYMBOL_GPL(usbip_start_eh); void usbip_stop_eh(struct usbip_device *ud) { unsigned long pending = ud->event & ~USBIP_EH_BYE; if (!(ud->event & USBIP_EH_BYE)) usbip_dbg_eh("usbip_eh stopping but not removed\n"); if (pending) usbip_dbg_eh("usbip_eh waiting completion %lx\n", pending); wait_event_interruptible(ud->eh_waitq, !(ud->event & ~USBIP_EH_BYE)); usbip_dbg_eh("usbip_eh has stopped\n"); } EXPORT_SYMBOL_GPL(usbip_stop_eh); #define WORK_QUEUE_NAME "usbip_event" static struct workqueue_struct *usbip_queue; static DECLARE_WORK(usbip_work, event_handler); int usbip_init_eh(void) { usbip_queue = create_singlethread_workqueue(WORK_QUEUE_NAME); if (usbip_queue == NULL) { pr_err("failed to create usbip_event\n"); return -ENOMEM; } return 0; } void usbip_finish_eh(void) { destroy_workqueue(usbip_queue); usbip_queue = NULL; } void usbip_event_add(struct usbip_device *ud, unsigned long event) { struct usbip_event *ue; unsigned long flags; if (ud->event & USBIP_EH_BYE) return; set_event(ud, event); spin_lock_irqsave(&event_lock, flags); list_for_each_entry_reverse(ue, &event_list, node) { if (ue->ud == ud) goto out; } ue = kmalloc(sizeof(struct usbip_event), GFP_ATOMIC); if (ue == NULL) goto out; ue->ud = ud; list_add_tail(&ue->node, &event_list); queue_work(usbip_queue, &usbip_work); out: spin_unlock_irqrestore(&event_lock, flags); } EXPORT_SYMBOL_GPL(usbip_event_add); int usbip_event_happened(struct usbip_device *ud) { int happened = 0; unsigned long flags; spin_lock_irqsave(&ud->lock, flags); if (ud->event != 0) happened = 1; spin_unlock_irqrestore(&ud->lock, flags); return happened; } EXPORT_SYMBOL_GPL(usbip_event_happened); int usbip_in_eh(struct task_struct *task) { if (task == worker_context) return 1; return 0; } EXPORT_SYMBOL_GPL(usbip_in_eh); |
| 60 59 60 60 12 48 44 96 97 41 27 7 67 92 90 200 1 200 13 3 35 154 21 22 22 7 7 2 2 1 2 1 1 1 2 51 23 4 4 8 4 4 3 3 5 3 29 2 13 13 1 13 1 10 4 12 2 9 5 10 4 2 1 22 23 1 11 11 20 19 1 9 4 3 1 26 2 11 10 1 12 1 10 3 10 3 10 3 10 3 15 15 11 2 70 52 17 19 20 89 3 74 74 83 82 46 40 6 35 11 30 16 41 2 3 41 5 46 39 7 37 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 Nicira, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> #include <linux/netfilter_ipv4.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/static_key.h> #include <net/ip.h> #include <net/icmp.h> #include <net/protocol.h> #include <net/ip_tunnels.h> #include <net/ip6_tunnel.h> #include <net/ip6_checksum.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/dst_metadata.h> #include <net/geneve.h> #include <net/vxlan.h> #include <net/erspan.h> const struct ip_tunnel_encap_ops __rcu * iptun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly; EXPORT_SYMBOL(iptun_encaps); const struct ip6_tnl_encap_ops __rcu * ip6tun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly; EXPORT_SYMBOL(ip6tun_encaps); void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, __u8 proto, __u8 tos, __u8 ttl, __be16 df, bool xnet) { int pkt_len = skb->len - skb_inner_network_offset(skb); struct net *net = dev_net(rt->dst.dev); struct net_device *dev = skb->dev; struct iphdr *iph; int err; skb_scrub_packet(skb, xnet); skb_clear_hash_if_not_l4(skb); skb_dst_set(skb, &rt->dst); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); /* Push down and install the IP header. */ skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = 4; iph->ihl = sizeof(struct iphdr) >> 2; iph->frag_off = ip_mtu_locked(&rt->dst) ? 0 : df; iph->protocol = proto; iph->tos = tos; iph->daddr = dst; iph->saddr = src; iph->ttl = ttl; __ip_select_ident(net, iph, skb_shinfo(skb)->gso_segs ?: 1); err = ip_local_out(net, sk, skb); if (dev) { if (unlikely(net_xmit_eval(err))) pkt_len = 0; iptunnel_xmit_stats(dev, pkt_len); } } EXPORT_SYMBOL_GPL(iptunnel_xmit); int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto, bool raw_proto, bool xnet) { if (unlikely(!pskb_may_pull(skb, hdr_len))) return -ENOMEM; skb_pull_rcsum(skb, hdr_len); if (!raw_proto && inner_proto == htons(ETH_P_TEB)) { struct ethhdr *eh; if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) return -ENOMEM; eh = (struct ethhdr *)skb->data; if (likely(eth_proto_is_802_3(eh->h_proto))) skb->protocol = eh->h_proto; else skb->protocol = htons(ETH_P_802_2); } else { skb->protocol = inner_proto; } skb_clear_hash_if_not_l4(skb); __vlan_hwaccel_clear_tag(skb); skb_set_queue_mapping(skb, 0); skb_scrub_packet(skb, xnet); return iptunnel_pull_offloads(skb); } EXPORT_SYMBOL_GPL(__iptunnel_pull_header); struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags) { IP_TUNNEL_DECLARE_FLAGS(tun_flags) = { }; struct metadata_dst *res; struct ip_tunnel_info *dst, *src; if (!md || md->type != METADATA_IP_TUNNEL || md->u.tun_info.mode & IP_TUNNEL_INFO_TX) return NULL; src = &md->u.tun_info; res = metadata_dst_alloc(src->options_len, METADATA_IP_TUNNEL, flags); if (!res) return NULL; dst = &res->u.tun_info; dst->key.tun_id = src->key.tun_id; if (src->mode & IP_TUNNEL_INFO_IPV6) memcpy(&dst->key.u.ipv6.dst, &src->key.u.ipv6.src, sizeof(struct in6_addr)); else dst->key.u.ipv4.dst = src->key.u.ipv4.src; ip_tunnel_flags_copy(dst->key.tun_flags, src->key.tun_flags); dst->mode = src->mode | IP_TUNNEL_INFO_TX; ip_tunnel_info_opts_set(dst, ip_tunnel_info_opts(src), src->options_len, tun_flags); return res; } EXPORT_SYMBOL_GPL(iptunnel_metadata_reply); int iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask) { int err; if (likely(!skb->encapsulation)) { skb_reset_inner_headers(skb); skb->encapsulation = 1; } if (skb_is_gso(skb)) { err = skb_header_unclone(skb, GFP_ATOMIC); if (unlikely(err)) return err; skb_shinfo(skb)->gso_type |= gso_type_mask; return 0; } if (skb->ip_summed != CHECKSUM_PARTIAL) { skb->ip_summed = CHECKSUM_NONE; /* We clear encapsulation here to prevent badly-written * drivers potentially deciding to offload an inner checksum * if we set CHECKSUM_PARTIAL on the outer header. * This should go away when the drivers are all fixed. */ skb->encapsulation = 0; } return 0; } EXPORT_SYMBOL_GPL(iptunnel_handle_offloads); /** * iptunnel_pmtud_build_icmp() - Build ICMP error message for PMTUD * @skb: Original packet with L2 header * @mtu: MTU value for ICMP error * * Return: length on success, negative error code if message couldn't be built. */ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) { const struct iphdr *iph = ip_hdr(skb); struct icmphdr *icmph; struct iphdr *niph; struct ethhdr eh; int len, err; if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr))) return -EINVAL; skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN); pskb_pull(skb, ETH_HLEN); skb_reset_network_header(skb); err = pskb_trim(skb, 576 - sizeof(*niph) - sizeof(*icmph)); if (err) return err; len = skb->len + sizeof(*icmph); err = skb_cow(skb, sizeof(*niph) + sizeof(*icmph) + ETH_HLEN); if (err) return err; icmph = skb_push(skb, sizeof(*icmph)); *icmph = (struct icmphdr) { .type = ICMP_DEST_UNREACH, .code = ICMP_FRAG_NEEDED, .checksum = 0, .un.frag.__unused = 0, .un.frag.mtu = htons(mtu), }; icmph->checksum = csum_fold(skb_checksum(skb, 0, len, 0)); skb_reset_transport_header(skb); niph = skb_push(skb, sizeof(*niph)); *niph = (struct iphdr) { .ihl = sizeof(*niph) / 4u, .version = 4, .tos = 0, .tot_len = htons(len + sizeof(*niph)), .id = 0, .frag_off = htons(IP_DF), .ttl = iph->ttl, .protocol = IPPROTO_ICMP, .saddr = iph->daddr, .daddr = iph->saddr, }; ip_send_check(niph); skb_reset_network_header(skb); skb->ip_summed = CHECKSUM_NONE; eth_header(skb, skb->dev, ntohs(eh.h_proto), eh.h_source, eh.h_dest, 0); skb_reset_mac_header(skb); return skb->len; } /** * iptunnel_pmtud_check_icmp() - Trigger ICMP reply if needed and allowed * @skb: Buffer being sent by encapsulation, L2 headers expected * @mtu: Network MTU for path * * Return: 0 for no ICMP reply, length if built, negative value on error. */ static int iptunnel_pmtud_check_icmp(struct sk_buff *skb, int mtu) { const struct icmphdr *icmph = icmp_hdr(skb); const struct iphdr *iph = ip_hdr(skb); if (mtu < 576 || iph->frag_off != htons(IP_DF)) return 0; if (ipv4_is_lbcast(iph->daddr) || ipv4_is_multicast(iph->daddr) || ipv4_is_zeronet(iph->saddr) || ipv4_is_loopback(iph->saddr) || ipv4_is_lbcast(iph->saddr) || ipv4_is_multicast(iph->saddr)) return 0; if (iph->protocol == IPPROTO_ICMP && icmp_is_err(icmph->type)) return 0; return iptunnel_pmtud_build_icmp(skb, mtu); } #if IS_ENABLED(CONFIG_IPV6) /** * iptunnel_pmtud_build_icmpv6() - Build ICMPv6 error message for PMTUD * @skb: Original packet with L2 header * @mtu: MTU value for ICMPv6 error * * Return: length on success, negative error code if message couldn't be built. */ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct icmp6hdr *icmp6h; struct ipv6hdr *nip6h; struct ethhdr eh; int len, err; __wsum csum; if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr))) return -EINVAL; skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN); pskb_pull(skb, ETH_HLEN); skb_reset_network_header(skb); err = pskb_trim(skb, IPV6_MIN_MTU - sizeof(*nip6h) - sizeof(*icmp6h)); if (err) return err; len = skb->len + sizeof(*icmp6h); err = skb_cow(skb, sizeof(*nip6h) + sizeof(*icmp6h) + ETH_HLEN); if (err) return err; icmp6h = skb_push(skb, sizeof(*icmp6h)); *icmp6h = (struct icmp6hdr) { .icmp6_type = ICMPV6_PKT_TOOBIG, .icmp6_code = 0, .icmp6_cksum = 0, .icmp6_mtu = htonl(mtu), }; skb_reset_transport_header(skb); nip6h = skb_push(skb, sizeof(*nip6h)); *nip6h = (struct ipv6hdr) { .priority = 0, .version = 6, .flow_lbl = { 0 }, .payload_len = htons(len), .nexthdr = IPPROTO_ICMPV6, .hop_limit = ip6h->hop_limit, .saddr = ip6h->daddr, .daddr = ip6h->saddr, }; skb_reset_network_header(skb); csum = skb_checksum(skb, skb_transport_offset(skb), len, 0); icmp6h->icmp6_cksum = csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr, len, IPPROTO_ICMPV6, csum); skb->ip_summed = CHECKSUM_NONE; eth_header(skb, skb->dev, ntohs(eh.h_proto), eh.h_source, eh.h_dest, 0); skb_reset_mac_header(skb); return skb->len; } /** * iptunnel_pmtud_check_icmpv6() - Trigger ICMPv6 reply if needed and allowed * @skb: Buffer being sent by encapsulation, L2 headers expected * @mtu: Network MTU for path * * Return: 0 for no ICMPv6 reply, length if built, negative value on error. */ static int iptunnel_pmtud_check_icmpv6(struct sk_buff *skb, int mtu) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); int stype = ipv6_addr_type(&ip6h->saddr); u8 proto = ip6h->nexthdr; __be16 frag_off; int offset; if (mtu < IPV6_MIN_MTU) return 0; if (stype == IPV6_ADDR_ANY || stype == IPV6_ADDR_MULTICAST || stype == IPV6_ADDR_LOOPBACK) return 0; offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &proto, &frag_off); if (offset < 0 || (frag_off & htons(~0x7))) return 0; if (proto == IPPROTO_ICMPV6) { struct icmp6hdr *icmp6h; if (!pskb_may_pull(skb, skb_network_header(skb) + offset + 1 - skb->data)) return 0; icmp6h = (struct icmp6hdr *)(skb_network_header(skb) + offset); if (icmpv6_is_err(icmp6h->icmp6_type) || icmp6h->icmp6_type == NDISC_REDIRECT) return 0; } return iptunnel_pmtud_build_icmpv6(skb, mtu); } #endif /* IS_ENABLED(CONFIG_IPV6) */ /** * skb_tunnel_check_pmtu() - Check, update PMTU and trigger ICMP reply as needed * @skb: Buffer being sent by encapsulation, L2 headers expected * @encap_dst: Destination for tunnel encapsulation (outer IP) * @headroom: Encapsulation header size, bytes * @reply: Build matching ICMP or ICMPv6 message as a result * * L2 tunnel implementations that can carry IP and can be directly bridged * (currently UDP tunnels) can't always rely on IP forwarding paths to handle * PMTU discovery. In the bridged case, ICMP or ICMPv6 messages need to be built * based on payload and sent back by the encapsulation itself. * * For routable interfaces, we just need to update the PMTU for the destination. * * Return: 0 if ICMP error not needed, length if built, negative value on error */ int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst, int headroom, bool reply) { u32 mtu = dst_mtu(encap_dst) - headroom; if ((skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) || (!skb_is_gso(skb) && (skb->len - skb_network_offset(skb)) <= mtu)) return 0; skb_dst_update_pmtu_no_confirm(skb, mtu); if (!reply) return 0; if (skb->protocol == htons(ETH_P_IP)) return iptunnel_pmtud_check_icmp(skb, mtu); #if IS_ENABLED(CONFIG_IPV6) if (skb->protocol == htons(ETH_P_IPV6)) return iptunnel_pmtud_check_icmpv6(skb, mtu); #endif return 0; } EXPORT_SYMBOL(skb_tunnel_check_pmtu); static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = { [LWTUNNEL_IP_UNSPEC] = { .strict_start_type = LWTUNNEL_IP_OPTS }, [LWTUNNEL_IP_ID] = { .type = NLA_U64 }, [LWTUNNEL_IP_DST] = { .type = NLA_U32 }, [LWTUNNEL_IP_SRC] = { .type = NLA_U32 }, [LWTUNNEL_IP_TTL] = { .type = NLA_U8 }, [LWTUNNEL_IP_TOS] = { .type = NLA_U8 }, [LWTUNNEL_IP_FLAGS] = { .type = NLA_U16 }, [LWTUNNEL_IP_OPTS] = { .type = NLA_NESTED }, }; static const struct nla_policy ip_opts_policy[LWTUNNEL_IP_OPTS_MAX + 1] = { [LWTUNNEL_IP_OPTS_GENEVE] = { .type = NLA_NESTED }, [LWTUNNEL_IP_OPTS_VXLAN] = { .type = NLA_NESTED }, [LWTUNNEL_IP_OPTS_ERSPAN] = { .type = NLA_NESTED }, }; static const struct nla_policy geneve_opt_policy[LWTUNNEL_IP_OPT_GENEVE_MAX + 1] = { [LWTUNNEL_IP_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, [LWTUNNEL_IP_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, [LWTUNNEL_IP_OPT_GENEVE_DATA] = { .type = NLA_BINARY, .len = 127 }, }; static const struct nla_policy vxlan_opt_policy[LWTUNNEL_IP_OPT_VXLAN_MAX + 1] = { [LWTUNNEL_IP_OPT_VXLAN_GBP] = { .type = NLA_U32 }, }; static const struct nla_policy erspan_opt_policy[LWTUNNEL_IP_OPT_ERSPAN_MAX + 1] = { [LWTUNNEL_IP_OPT_ERSPAN_VER] = { .type = NLA_U8 }, [LWTUNNEL_IP_OPT_ERSPAN_INDEX] = { .type = NLA_U32 }, [LWTUNNEL_IP_OPT_ERSPAN_DIR] = { .type = NLA_U8 }, [LWTUNNEL_IP_OPT_ERSPAN_HWID] = { .type = NLA_U8 }, }; static int ip_tun_parse_opts_geneve(struct nlattr *attr, struct ip_tunnel_info *info, int opts_len, struct netlink_ext_ack *extack) { struct nlattr *tb[LWTUNNEL_IP_OPT_GENEVE_MAX + 1]; int data_len, err; err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_GENEVE_MAX, attr, geneve_opt_policy, extack); if (err) return err; if (!tb[LWTUNNEL_IP_OPT_GENEVE_CLASS] || !tb[LWTUNNEL_IP_OPT_GENEVE_TYPE] || !tb[LWTUNNEL_IP_OPT_GENEVE_DATA]) return -EINVAL; attr = tb[LWTUNNEL_IP_OPT_GENEVE_DATA]; data_len = nla_len(attr); if (data_len % 4) return -EINVAL; if (info) { struct geneve_opt *opt = ip_tunnel_info_opts(info) + opts_len; memcpy(opt->opt_data, nla_data(attr), data_len); opt->length = data_len / 4; attr = tb[LWTUNNEL_IP_OPT_GENEVE_CLASS]; opt->opt_class = nla_get_be16(attr); attr = tb[LWTUNNEL_IP_OPT_GENEVE_TYPE]; opt->type = nla_get_u8(attr); __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags); } return sizeof(struct geneve_opt) + data_len; } static int ip_tun_parse_opts_vxlan(struct nlattr *attr, struct ip_tunnel_info *info, int opts_len, struct netlink_ext_ack *extack) { struct nlattr *tb[LWTUNNEL_IP_OPT_VXLAN_MAX + 1]; int err; err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_VXLAN_MAX, attr, vxlan_opt_policy, extack); if (err) return err; if (!tb[LWTUNNEL_IP_OPT_VXLAN_GBP]) return -EINVAL; if (info) { struct vxlan_metadata *md = ip_tunnel_info_opts(info) + opts_len; attr = tb[LWTUNNEL_IP_OPT_VXLAN_GBP]; md->gbp = nla_get_u32(attr); md->gbp &= VXLAN_GBP_MASK; __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags); } return sizeof(struct vxlan_metadata); } static int ip_tun_parse_opts_erspan(struct nlattr *attr, struct ip_tunnel_info *info, int opts_len, struct netlink_ext_ack *extack) { struct nlattr *tb[LWTUNNEL_IP_OPT_ERSPAN_MAX + 1]; int err; u8 ver; err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_ERSPAN_MAX, attr, erspan_opt_policy, extack); if (err) return err; if (!tb[LWTUNNEL_IP_OPT_ERSPAN_VER]) return -EINVAL; ver = nla_get_u8(tb[LWTUNNEL_IP_OPT_ERSPAN_VER]); if (ver == 1) { if (!tb[LWTUNNEL_IP_OPT_ERSPAN_INDEX]) return -EINVAL; } else if (ver == 2) { if (!tb[LWTUNNEL_IP_OPT_ERSPAN_DIR] || !tb[LWTUNNEL_IP_OPT_ERSPAN_HWID]) return -EINVAL; } else { return -EINVAL; } if (info) { struct erspan_metadata *md = ip_tunnel_info_opts(info) + opts_len; md->version = ver; if (ver == 1) { attr = tb[LWTUNNEL_IP_OPT_ERSPAN_INDEX]; md->u.index = nla_get_be32(attr); } else { attr = tb[LWTUNNEL_IP_OPT_ERSPAN_DIR]; md->u.md2.dir = nla_get_u8(attr); attr = tb[LWTUNNEL_IP_OPT_ERSPAN_HWID]; set_hwid(&md->u.md2, nla_get_u8(attr)); } __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); } return sizeof(struct erspan_metadata); } static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, struct netlink_ext_ack *extack) { int err, rem, opt_len, opts_len = 0; struct nlattr *nla; u32 type = 0; if (!attr) return 0; err = nla_validate(nla_data(attr), nla_len(attr), LWTUNNEL_IP_OPTS_MAX, ip_opts_policy, extack); if (err) return err; nla_for_each_attr(nla, nla_data(attr), nla_len(attr), rem) { switch (nla_type(nla)) { case LWTUNNEL_IP_OPTS_GENEVE: if (type && type != IP_TUNNEL_GENEVE_OPT_BIT) return -EINVAL; opt_len = ip_tun_parse_opts_geneve(nla, info, opts_len, extack); if (opt_len < 0) return opt_len; opts_len += opt_len; if (opts_len > IP_TUNNEL_OPTS_MAX) return -EINVAL; type = IP_TUNNEL_GENEVE_OPT_BIT; break; case LWTUNNEL_IP_OPTS_VXLAN: if (type) return -EINVAL; opt_len = ip_tun_parse_opts_vxlan(nla, info, opts_len, extack); if (opt_len < 0) return opt_len; opts_len += opt_len; type = IP_TUNNEL_VXLAN_OPT_BIT; break; case LWTUNNEL_IP_OPTS_ERSPAN: if (type) return -EINVAL; opt_len = ip_tun_parse_opts_erspan(nla, info, opts_len, extack); if (opt_len < 0) return opt_len; opts_len += opt_len; type = IP_TUNNEL_ERSPAN_OPT_BIT; break; default: return -EINVAL; } } return opts_len; } static int ip_tun_get_optlen(struct nlattr *attr, struct netlink_ext_ack *extack) { return ip_tun_parse_opts(attr, NULL, extack); } static int ip_tun_set_opts(struct nlattr *attr, struct ip_tunnel_info *info, struct netlink_ext_ack *extack) { return ip_tun_parse_opts(attr, info, extack); } static int ip_tun_build_state(struct net *net, struct nlattr *attr, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack) { struct nlattr *tb[LWTUNNEL_IP_MAX + 1]; struct lwtunnel_state *new_state; struct ip_tunnel_info *tun_info; int err, opt_len; err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy, extack); if (err < 0) return err; opt_len = ip_tun_get_optlen(tb[LWTUNNEL_IP_OPTS], extack); if (opt_len < 0) return opt_len; new_state = lwtunnel_state_alloc(sizeof(*tun_info) + opt_len); if (!new_state) return -ENOMEM; new_state->type = LWTUNNEL_ENCAP_IP; tun_info = lwt_tun_info(new_state); err = ip_tun_set_opts(tb[LWTUNNEL_IP_OPTS], tun_info, extack); if (err < 0) { lwtstate_free(new_state); return err; } #ifdef CONFIG_DST_CACHE err = dst_cache_init(&tun_info->dst_cache, GFP_KERNEL); if (err) { lwtstate_free(new_state); return err; } #endif if (tb[LWTUNNEL_IP_ID]) tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP_ID]); if (tb[LWTUNNEL_IP_DST]) tun_info->key.u.ipv4.dst = nla_get_in_addr(tb[LWTUNNEL_IP_DST]); if (tb[LWTUNNEL_IP_SRC]) tun_info->key.u.ipv4.src = nla_get_in_addr(tb[LWTUNNEL_IP_SRC]); if (tb[LWTUNNEL_IP_TTL]) tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP_TTL]); if (tb[LWTUNNEL_IP_TOS]) tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]); if (tb[LWTUNNEL_IP_FLAGS]) { IP_TUNNEL_DECLARE_FLAGS(flags); ip_tunnel_flags_from_be16(flags, nla_get_be16(tb[LWTUNNEL_IP_FLAGS])); ip_tunnel_clear_options_present(flags); ip_tunnel_flags_or(tun_info->key.tun_flags, tun_info->key.tun_flags, flags); } tun_info->mode = IP_TUNNEL_INFO_TX; tun_info->options_len = opt_len; *ts = new_state; return 0; } static void ip_tun_destroy_state(struct lwtunnel_state *lwtstate) { #ifdef CONFIG_DST_CACHE struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate); dst_cache_destroy(&tun_info->dst_cache); #endif } static int ip_tun_fill_encap_opts_geneve(struct sk_buff *skb, struct ip_tunnel_info *tun_info) { struct geneve_opt *opt; struct nlattr *nest; int offset = 0; nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_GENEVE); if (!nest) return -ENOMEM; while (tun_info->options_len > offset) { opt = ip_tunnel_info_opts(tun_info) + offset; if (nla_put_be16(skb, LWTUNNEL_IP_OPT_GENEVE_CLASS, opt->opt_class) || nla_put_u8(skb, LWTUNNEL_IP_OPT_GENEVE_TYPE, opt->type) || nla_put(skb, LWTUNNEL_IP_OPT_GENEVE_DATA, opt->length * 4, opt->opt_data)) { nla_nest_cancel(skb, nest); return -ENOMEM; } offset += sizeof(*opt) + opt->length * 4; } nla_nest_end(skb, nest); return 0; } static int ip_tun_fill_encap_opts_vxlan(struct sk_buff *skb, struct ip_tunnel_info *tun_info) { struct vxlan_metadata *md; struct nlattr *nest; nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_VXLAN); if (!nest) return -ENOMEM; md = ip_tunnel_info_opts(tun_info); if (nla_put_u32(skb, LWTUNNEL_IP_OPT_VXLAN_GBP, md->gbp)) { nla_nest_cancel(skb, nest); return -ENOMEM; } nla_nest_end(skb, nest); return 0; } static int ip_tun_fill_encap_opts_erspan(struct sk_buff *skb, struct ip_tunnel_info *tun_info) { struct erspan_metadata *md; struct nlattr *nest; nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_ERSPAN); if (!nest) return -ENOMEM; md = ip_tunnel_info_opts(tun_info); if (nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_VER, md->version)) goto err; if (md->version == 1 && nla_put_be32(skb, LWTUNNEL_IP_OPT_ERSPAN_INDEX, md->u.index)) goto err; if (md->version == 2 && (nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_DIR, md->u.md2.dir) || nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_HWID, get_hwid(&md->u.md2)))) goto err; nla_nest_end(skb, nest); return 0; err: nla_nest_cancel(skb, nest); return -ENOMEM; } static int ip_tun_fill_encap_opts(struct sk_buff *skb, int type, struct ip_tunnel_info *tun_info) { struct nlattr *nest; int err = 0; if (!ip_tunnel_is_options_present(tun_info->key.tun_flags)) return 0; nest = nla_nest_start_noflag(skb, type); if (!nest) return -ENOMEM; if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_info->key.tun_flags)) err = ip_tun_fill_encap_opts_geneve(skb, tun_info); else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_info->key.tun_flags)) err = ip_tun_fill_encap_opts_vxlan(skb, tun_info); else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_info->key.tun_flags)) err = ip_tun_fill_encap_opts_erspan(skb, tun_info); if (err) { nla_nest_cancel(skb, nest); return err; } nla_nest_end(skb, nest); return 0; } static int ip_tun_fill_encap_info(struct sk_buff *skb, struct lwtunnel_state *lwtstate) { struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate); if (nla_put_be64(skb, LWTUNNEL_IP_ID, tun_info->key.tun_id, LWTUNNEL_IP_PAD) || nla_put_in_addr(skb, LWTUNNEL_IP_DST, tun_info->key.u.ipv4.dst) || nla_put_in_addr(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) || nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) || nla_put_be16(skb, LWTUNNEL_IP_FLAGS, ip_tunnel_flags_to_be16(tun_info->key.tun_flags)) || ip_tun_fill_encap_opts(skb, LWTUNNEL_IP_OPTS, tun_info)) return -ENOMEM; return 0; } static int ip_tun_opts_nlsize(struct ip_tunnel_info *info) { int opt_len; if (!ip_tunnel_is_options_present(info->key.tun_flags)) return 0; opt_len = nla_total_size(0); /* LWTUNNEL_IP_OPTS */ if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) { struct geneve_opt *opt; int offset = 0; opt_len += nla_total_size(0); /* LWTUNNEL_IP_OPTS_GENEVE */ while (info->options_len > offset) { opt = ip_tunnel_info_opts(info) + offset; opt_len += nla_total_size(2) /* OPT_GENEVE_CLASS */ + nla_total_size(1) /* OPT_GENEVE_TYPE */ + nla_total_size(opt->length * 4); /* OPT_GENEVE_DATA */ offset += sizeof(*opt) + opt->length * 4; } } else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { opt_len += nla_total_size(0) /* LWTUNNEL_IP_OPTS_VXLAN */ + nla_total_size(4); /* OPT_VXLAN_GBP */ } else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags)) { struct erspan_metadata *md = ip_tunnel_info_opts(info); opt_len += nla_total_size(0) /* LWTUNNEL_IP_OPTS_ERSPAN */ + nla_total_size(1) /* OPT_ERSPAN_VER */ + (md->version == 1 ? nla_total_size(4) /* OPT_ERSPAN_INDEX (v1) */ : nla_total_size(1) + nla_total_size(1)); /* OPT_ERSPAN_DIR + HWID (v2) */ } return opt_len; } static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate) { return nla_total_size_64bit(8) /* LWTUNNEL_IP_ID */ + nla_total_size(4) /* LWTUNNEL_IP_DST */ + nla_total_size(4) /* LWTUNNEL_IP_SRC */ + nla_total_size(1) /* LWTUNNEL_IP_TOS */ + nla_total_size(1) /* LWTUNNEL_IP_TTL */ + nla_total_size(2) /* LWTUNNEL_IP_FLAGS */ + ip_tun_opts_nlsize(lwt_tun_info(lwtstate)); /* LWTUNNEL_IP_OPTS */ } static int ip_tun_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) { struct ip_tunnel_info *info_a = lwt_tun_info(a); struct ip_tunnel_info *info_b = lwt_tun_info(b); return memcmp(info_a, info_b, sizeof(info_a->key)) || info_a->mode != info_b->mode || info_a->options_len != info_b->options_len || memcmp(ip_tunnel_info_opts(info_a), ip_tunnel_info_opts(info_b), info_a->options_len); } static const struct lwtunnel_encap_ops ip_tun_lwt_ops = { .build_state = ip_tun_build_state, .destroy_state = ip_tun_destroy_state, .fill_encap = ip_tun_fill_encap_info, .get_encap_size = ip_tun_encap_nlsize, .cmp_encap = ip_tun_cmp_encap, .owner = THIS_MODULE, }; static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = { [LWTUNNEL_IP6_UNSPEC] = { .strict_start_type = LWTUNNEL_IP6_OPTS }, [LWTUNNEL_IP6_ID] = { .type = NLA_U64 }, [LWTUNNEL_IP6_DST] = { .len = sizeof(struct in6_addr) }, [LWTUNNEL_IP6_SRC] = { .len = sizeof(struct in6_addr) }, [LWTUNNEL_IP6_HOPLIMIT] = { .type = NLA_U8 }, [LWTUNNEL_IP6_TC] = { .type = NLA_U8 }, [LWTUNNEL_IP6_FLAGS] = { .type = NLA_U16 }, [LWTUNNEL_IP6_OPTS] = { .type = NLA_NESTED }, }; static int ip6_tun_build_state(struct net *net, struct nlattr *attr, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack) { struct nlattr *tb[LWTUNNEL_IP6_MAX + 1]; struct lwtunnel_state *new_state; struct ip_tunnel_info *tun_info; int err, opt_len; err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP6_MAX, attr, ip6_tun_policy, extack); if (err < 0) return err; opt_len = ip_tun_get_optlen(tb[LWTUNNEL_IP6_OPTS], extack); if (opt_len < 0) return opt_len; new_state = lwtunnel_state_alloc(sizeof(*tun_info) + opt_len); if (!new_state) return -ENOMEM; new_state->type = LWTUNNEL_ENCAP_IP6; tun_info = lwt_tun_info(new_state); err = ip_tun_set_opts(tb[LWTUNNEL_IP6_OPTS], tun_info, extack); if (err < 0) { lwtstate_free(new_state); return err; } if (tb[LWTUNNEL_IP6_ID]) tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP6_ID]); if (tb[LWTUNNEL_IP6_DST]) tun_info->key.u.ipv6.dst = nla_get_in6_addr(tb[LWTUNNEL_IP6_DST]); if (tb[LWTUNNEL_IP6_SRC]) tun_info->key.u.ipv6.src = nla_get_in6_addr(tb[LWTUNNEL_IP6_SRC]); if (tb[LWTUNNEL_IP6_HOPLIMIT]) tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP6_HOPLIMIT]); if (tb[LWTUNNEL_IP6_TC]) tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]); if (tb[LWTUNNEL_IP6_FLAGS]) { IP_TUNNEL_DECLARE_FLAGS(flags); __be16 data; data = nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]); ip_tunnel_flags_from_be16(flags, data); ip_tunnel_clear_options_present(flags); ip_tunnel_flags_or(tun_info->key.tun_flags, tun_info->key.tun_flags, flags); } tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6; tun_info->options_len = opt_len; *ts = new_state; return 0; } static int ip6_tun_fill_encap_info(struct sk_buff *skb, struct lwtunnel_state *lwtstate) { struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate); if (nla_put_be64(skb, LWTUNNEL_IP6_ID, tun_info->key.tun_id, LWTUNNEL_IP6_PAD) || nla_put_in6_addr(skb, LWTUNNEL_IP6_DST, &tun_info->key.u.ipv6.dst) || nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) || nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) || nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, ip_tunnel_flags_to_be16(tun_info->key.tun_flags)) || ip_tun_fill_encap_opts(skb, LWTUNNEL_IP6_OPTS, tun_info)) return -ENOMEM; return 0; } static int ip6_tun_encap_nlsize(struct lwtunnel_state *lwtstate) { return nla_total_size_64bit(8) /* LWTUNNEL_IP6_ID */ + nla_total_size(16) /* LWTUNNEL_IP6_DST */ + nla_total_size(16) /* LWTUNNEL_IP6_SRC */ + nla_total_size(1) /* LWTUNNEL_IP6_HOPLIMIT */ + nla_total_size(1) /* LWTUNNEL_IP6_TC */ + nla_total_size(2) /* LWTUNNEL_IP6_FLAGS */ + ip_tun_opts_nlsize(lwt_tun_info(lwtstate)); /* LWTUNNEL_IP6_OPTS */ } static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = { .build_state = ip6_tun_build_state, .fill_encap = ip6_tun_fill_encap_info, .get_encap_size = ip6_tun_encap_nlsize, .cmp_encap = ip_tun_cmp_encap, .owner = THIS_MODULE, }; void __init ip_tunnel_core_init(void) { /* If you land here, make sure whether increasing ip_tunnel_info's * options_len is a reasonable choice with its usage in front ends * (f.e., it's part of flow keys, etc). */ BUILD_BUG_ON(IP_TUNNEL_OPTS_MAX != 255); lwtunnel_encap_add_ops(&ip_tun_lwt_ops, LWTUNNEL_ENCAP_IP); lwtunnel_encap_add_ops(&ip6_tun_lwt_ops, LWTUNNEL_ENCAP_IP6); } DEFINE_STATIC_KEY_FALSE(ip_tunnel_metadata_cnt); EXPORT_SYMBOL(ip_tunnel_metadata_cnt); void ip_tunnel_need_metadata(void) { static_branch_inc(&ip_tunnel_metadata_cnt); } EXPORT_SYMBOL_GPL(ip_tunnel_need_metadata); void ip_tunnel_unneed_metadata(void) { static_branch_dec(&ip_tunnel_metadata_cnt); } EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata); /* Returns either the correct skb->protocol value, or 0 if invalid. */ __be16 ip_tunnel_parse_protocol(const struct sk_buff *skb) { if (skb_network_header(skb) >= skb->head && (skb_network_header(skb) + sizeof(struct iphdr)) <= skb_tail_pointer(skb) && ip_hdr(skb)->version == 4) return htons(ETH_P_IP); if (skb_network_header(skb) >= skb->head && (skb_network_header(skb) + sizeof(struct ipv6hdr)) <= skb_tail_pointer(skb) && ipv6_hdr(skb)->version == 6) return htons(ETH_P_IPV6); return 0; } EXPORT_SYMBOL(ip_tunnel_parse_protocol); const struct header_ops ip_tunnel_header_ops = { .parse_protocol = ip_tunnel_parse_protocol }; EXPORT_SYMBOL(ip_tunnel_header_ops); /* This function returns true when ENCAP attributes are present in the nl msg */ bool ip_tunnel_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *encap) { bool ret = false; memset(encap, 0, sizeof(*encap)); if (!data) return ret; if (data[IFLA_IPTUN_ENCAP_TYPE]) { ret = true; encap->type = nla_get_u16(data[IFLA_IPTUN_ENCAP_TYPE]); } if (data[IFLA_IPTUN_ENCAP_FLAGS]) { ret = true; encap->flags = nla_get_u16(data[IFLA_IPTUN_ENCAP_FLAGS]); } if (data[IFLA_IPTUN_ENCAP_SPORT]) { ret = true; encap->sport = nla_get_be16(data[IFLA_IPTUN_ENCAP_SPORT]); } if (data[IFLA_IPTUN_ENCAP_DPORT]) { ret = true; encap->dport = nla_get_be16(data[IFLA_IPTUN_ENCAP_DPORT]); } return ret; } EXPORT_SYMBOL_GPL(ip_tunnel_netlink_encap_parms); void ip_tunnel_netlink_parms(struct nlattr *data[], struct ip_tunnel_parm_kern *parms) { if (data[IFLA_IPTUN_LINK]) parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); if (data[IFLA_IPTUN_LOCAL]) parms->iph.saddr = nla_get_be32(data[IFLA_IPTUN_LOCAL]); if (data[IFLA_IPTUN_REMOTE]) parms->iph.daddr = nla_get_be32(data[IFLA_IPTUN_REMOTE]); if (data[IFLA_IPTUN_TTL]) { parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]); if (parms->iph.ttl) parms->iph.frag_off = htons(IP_DF); } if (data[IFLA_IPTUN_TOS]) parms->iph.tos = nla_get_u8(data[IFLA_IPTUN_TOS]); if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) parms->iph.frag_off = htons(IP_DF); if (data[IFLA_IPTUN_FLAGS]) { __be16 flags; flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); ip_tunnel_flags_from_be16(parms->i_flags, flags); } if (data[IFLA_IPTUN_PROTO]) parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]); } EXPORT_SYMBOL_GPL(ip_tunnel_netlink_parms); |
| 6 6 8 8 2 6 9 9 9 21 21 21 21 21 21 21 21 21 21 9 9 9 9 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2011 Instituto Nokia de Tecnologia * * Authors: * Lauro Ramos Venancio <lauro.venancio@openbossa.org> * Aloisio Almeida Jr <aloisio.almeida@openbossa.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__ #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/rfkill.h> #include <linux/nfc.h> #include <net/genetlink.h> #include "nfc.h" #define VERSION "0.1" #define NFC_CHECK_PRES_FREQ_MS 2000 int nfc_devlist_generation; DEFINE_MUTEX(nfc_devlist_mutex); /* NFC device ID bitmap */ static DEFINE_IDA(nfc_index_ida); int nfc_fw_download(struct nfc_dev *dev, const char *firmware_name) { int rc = 0; pr_debug("%s do firmware %s\n", dev_name(&dev->dev), firmware_name); device_lock(&dev->dev); if (dev->shutting_down) { rc = -ENODEV; goto error; } if (dev->dev_up) { rc = -EBUSY; goto error; } if (!dev->ops->fw_download) { rc = -EOPNOTSUPP; goto error; } dev->fw_download_in_progress = true; rc = dev->ops->fw_download(dev, firmware_name); if (rc) dev->fw_download_in_progress = false; error: device_unlock(&dev->dev); return rc; } /** * nfc_fw_download_done - inform that a firmware download was completed * * @dev: The nfc device to which firmware was downloaded * @firmware_name: The firmware filename * @result: The positive value of a standard errno value */ int nfc_fw_download_done(struct nfc_dev *dev, const char *firmware_name, u32 result) { dev->fw_download_in_progress = false; return nfc_genl_fw_download_done(dev, firmware_name, result); } EXPORT_SYMBOL(nfc_fw_download_done); /** * nfc_dev_up - turn on the NFC device * * @dev: The nfc device to be turned on * * The device remains up until the nfc_dev_down function is called. */ int nfc_dev_up(struct nfc_dev *dev) { int rc = 0; pr_debug("dev_name=%s\n", dev_name(&dev->dev)); device_lock(&dev->dev); if (dev->shutting_down) { rc = -ENODEV; goto error; } if (dev->rfkill && rfkill_blocked(dev->rfkill)) { rc = -ERFKILL; goto error; } if (dev->fw_download_in_progress) { rc = -EBUSY; goto error; } if (dev->dev_up) { rc = -EALREADY; goto error; } if (dev->ops->dev_up) rc = dev->ops->dev_up(dev); if (!rc) dev->dev_up = true; /* We have to enable the device before discovering SEs */ if (dev->ops->discover_se && dev->ops->discover_se(dev)) pr_err("SE discovery failed\n"); error: device_unlock(&dev->dev); return rc; } /** * nfc_dev_down - turn off the NFC device * * @dev: The nfc device to be turned off */ int nfc_dev_down(struct nfc_dev *dev) { int rc = 0; pr_debug("dev_name=%s\n", dev_name(&dev->dev)); device_lock(&dev->dev); if (dev->shutting_down) { rc = -ENODEV; goto error; } if (!dev->dev_up) { rc = -EALREADY; goto error; } if (dev->polling || dev->active_target) { rc = -EBUSY; goto error; } if (dev->ops->dev_down) dev->ops->dev_down(dev); dev->dev_up = false; error: device_unlock(&dev->dev); return rc; } static int nfc_rfkill_set_block(void *data, bool blocked) { struct nfc_dev *dev = data; pr_debug("%s blocked %d", dev_name(&dev->dev), blocked); if (!blocked) return 0; nfc_dev_down(dev); return 0; } static const struct rfkill_ops nfc_rfkill_ops = { .set_block = nfc_rfkill_set_block, }; /** * nfc_start_poll - start polling for nfc targets * * @dev: The nfc device that must start polling * @im_protocols: bitset of nfc initiator protocols to be used for polling * @tm_protocols: bitset of nfc transport protocols to be used for polling * * The device remains polling for targets until a target is found or * the nfc_stop_poll function is called. */ int nfc_start_poll(struct nfc_dev *dev, u32 im_protocols, u32 tm_protocols) { int rc; pr_debug("dev_name %s initiator protocols 0x%x target protocols 0x%x\n", dev_name(&dev->dev), im_protocols, tm_protocols); if (!im_protocols && !tm_protocols) return -EINVAL; device_lock(&dev->dev); if (dev->shutting_down) { rc = -ENODEV; goto error; } if (!dev->dev_up) { rc = -ENODEV; goto error; } if (dev->polling) { rc = -EBUSY; goto error; } rc = dev->ops->start_poll(dev, im_protocols, tm_protocols); if (!rc) { dev->polling = true; dev->rf_mode = NFC_RF_NONE; } error: device_unlock(&dev->dev); return rc; } /** * nfc_stop_poll - stop polling for nfc targets * * @dev: The nfc device that must stop polling */ int nfc_stop_poll(struct nfc_dev *dev) { int rc = 0; pr_debug("dev_name=%s\n", dev_name(&dev->dev)); device_lock(&dev->dev); if (dev->shutting_down) { rc = -ENODEV; goto error; } if (!dev->polling) { rc = -EINVAL; goto error; } dev->ops->stop_poll(dev); dev->polling = false; dev->rf_mode = NFC_RF_NONE; error: device_unlock(&dev->dev); return rc; } static struct nfc_target *nfc_find_target(struct nfc_dev *dev, u32 target_idx) { int i; for (i = 0; i < dev->n_targets; i++) { if (dev->targets[i].idx == target_idx) return &dev->targets[i]; } return NULL; } int nfc_dep_link_up(struct nfc_dev *dev, int target_index, u8 comm_mode) { int rc = 0; u8 *gb; size_t gb_len; struct nfc_target *target; pr_debug("dev_name=%s comm %d\n", dev_name(&dev->dev), comm_mode); if (!dev->ops->dep_link_up) return -EOPNOTSUPP; device_lock(&dev->dev); if (dev->shutting_down) { rc = -ENODEV; goto error; } if (dev->dep_link_up == true) { rc = -EALREADY; goto error; } gb = nfc_llcp_general_bytes(dev, &gb_len); if (gb_len > NFC_MAX_GT_LEN) { rc = -EINVAL; goto error; } target = nfc_find_target(dev, target_index); if (target == NULL) { rc = -ENOTCONN; goto error; } rc = dev->ops->dep_link_up(dev, target, comm_mode, gb, gb_len); if (!rc) { dev->active_target = target; dev->rf_mode = NFC_RF_INITIATOR; } error: device_unlock(&dev->dev); return rc; } int nfc_dep_link_down(struct nfc_dev *dev) { int rc = 0; pr_debug("dev_name=%s\n", dev_name(&dev->dev)); if (!dev->ops->dep_link_down) return -EOPNOTSUPP; device_lock(&dev->dev); if (dev->shutting_down) { rc = -ENODEV; goto error; } if (dev->dep_link_up == false) { rc = -EALREADY; goto error; } rc = dev->ops->dep_link_down(dev); if (!rc) { dev->dep_link_up = false; dev->active_target = NULL; dev->rf_mode = NFC_RF_NONE; nfc_llcp_mac_is_down(dev); nfc_genl_dep_link_down_event(dev); } error: device_unlock(&dev->dev); return rc; } int nfc_dep_link_is_up(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode) { dev->dep_link_up = true; if (!dev->active_target && rf_mode == NFC_RF_INITIATOR) { struct nfc_target *target; target = nfc_find_target(dev, target_idx); if (target == NULL) return -ENOTCONN; dev->active_target = target; } dev->polling = false; dev->rf_mode = rf_mode; nfc_llcp_mac_is_up(dev, target_idx, comm_mode, rf_mode); return nfc_genl_dep_link_up_event(dev, target_idx, comm_mode, rf_mode); } EXPORT_SYMBOL(nfc_dep_link_is_up); /** * nfc_activate_target - prepare the target for data exchange * * @dev: The nfc device that found the target * @target_idx: index of the target that must be activated * @protocol: nfc protocol that will be used for data exchange */ int nfc_activate_target(struct nfc_dev *dev, u32 target_idx, u32 protocol) { int rc; struct nfc_target *target; pr_debug("dev_name=%s target_idx=%u protocol=%u\n", dev_name(&dev->dev), target_idx, protocol); device_lock(&dev->dev); if (dev->shutting_down) { rc = -ENODEV; goto error; } if (dev->active_target) { rc = -EBUSY; goto error; } target = nfc_find_target(dev, target_idx); if (target == NULL) { rc = -ENOTCONN; goto error; } rc = dev->ops->activate_target(dev, target, protocol); if (!rc) { dev->active_target = target; dev->rf_mode = NFC_RF_INITIATOR; if (dev->ops->check_presence && !dev->shutting_down) mod_timer(&dev->check_pres_timer, jiffies + msecs_to_jiffies(NFC_CHECK_PRES_FREQ_MS)); } error: device_unlock(&dev->dev); return rc; } /** * nfc_deactivate_target - deactivate a nfc target * * @dev: The nfc device that found the target * @target_idx: index of the target that must be deactivated * @mode: idle or sleep? */ int nfc_deactivate_target(struct nfc_dev *dev, u32 target_idx, u8 mode) { int rc = 0; pr_debug("dev_name=%s target_idx=%u\n", dev_name(&dev->dev), target_idx); device_lock(&dev->dev); if (dev->shutting_down) { rc = -ENODEV; goto error; } if (dev->active_target == NULL) { rc = -ENOTCONN; goto error; } if (dev->active_target->idx != target_idx) { rc = -ENOTCONN; goto error; } if (dev->ops->check_presence) timer_delete_sync(&dev->check_pres_timer); dev->ops->deactivate_target(dev, dev->active_target, mode); dev->active_target = NULL; error: device_unlock(&dev->dev); return rc; } /** * nfc_data_exchange - transceive data * * @dev: The nfc device that found the target * @target_idx: index of the target * @skb: data to be sent * @cb: callback called when the response is received * @cb_context: parameter for the callback function * * The user must wait for the callback before calling this function again. */ int nfc_data_exchange(struct nfc_dev *dev, u32 target_idx, struct sk_buff *skb, data_exchange_cb_t cb, void *cb_context) { int rc; pr_debug("dev_name=%s target_idx=%u skb->len=%u\n", dev_name(&dev->dev), target_idx, skb->len); device_lock(&dev->dev); if (dev->shutting_down) { rc = -ENODEV; kfree_skb(skb); goto error; } if (dev->rf_mode == NFC_RF_INITIATOR && dev->active_target != NULL) { if (dev->active_target->idx != target_idx) { rc = -EADDRNOTAVAIL; kfree_skb(skb); goto error; } if (dev->ops->check_presence) timer_delete_sync(&dev->check_pres_timer); rc = dev->ops->im_transceive(dev, dev->active_target, skb, cb, cb_context); if (!rc && dev->ops->check_presence && !dev->shutting_down) mod_timer(&dev->check_pres_timer, jiffies + msecs_to_jiffies(NFC_CHECK_PRES_FREQ_MS)); } else if (dev->rf_mode == NFC_RF_TARGET && dev->ops->tm_send != NULL) { rc = dev->ops->tm_send(dev, skb); } else { rc = -ENOTCONN; kfree_skb(skb); goto error; } error: device_unlock(&dev->dev); return rc; } struct nfc_se *nfc_find_se(struct nfc_dev *dev, u32 se_idx) { struct nfc_se *se; list_for_each_entry(se, &dev->secure_elements, list) if (se->idx == se_idx) return se; return NULL; } EXPORT_SYMBOL(nfc_find_se); int nfc_enable_se(struct nfc_dev *dev, u32 se_idx) { struct nfc_se *se; int rc; pr_debug("%s se index %d\n", dev_name(&dev->dev), se_idx); device_lock(&dev->dev); if (dev->shutting_down) { rc = -ENODEV; goto error; } if (!dev->dev_up) { rc = -ENODEV; goto error; } if (dev->polling) { rc = -EBUSY; goto error; } if (!dev->ops->enable_se || !dev->ops->disable_se) { rc = -EOPNOTSUPP; goto error; } se = nfc_find_se(dev, se_idx); if (!se) { rc = -EINVAL; goto error; } if (se->state == NFC_SE_ENABLED) { rc = -EALREADY; goto error; } rc = dev->ops->enable_se(dev, se_idx); if (rc >= 0) se->state = NFC_SE_ENABLED; error: device_unlock(&dev->dev); return rc; } int nfc_disable_se(struct nfc_dev *dev, u32 se_idx) { struct nfc_se *se; int rc; pr_debug("%s se index %d\n", dev_name(&dev->dev), se_idx); device_lock(&dev->dev); if (dev->shutting_down) { rc = -ENODEV; goto error; } if (!dev->dev_up) { rc = -ENODEV; goto error; } if (!dev->ops->enable_se || !dev->ops->disable_se) { rc = -EOPNOTSUPP; goto error; } se = nfc_find_se(dev, se_idx); if (!se) { rc = -EINVAL; goto error; } if (se->state == NFC_SE_DISABLED) { rc = -EALREADY; goto error; } rc = dev->ops->disable_se(dev, se_idx); if (rc >= 0) se->state = NFC_SE_DISABLED; error: device_unlock(&dev->dev); return rc; } int nfc_set_remote_general_bytes(struct nfc_dev *dev, const u8 *gb, u8 gb_len) { pr_debug("dev_name=%s gb_len=%d\n", dev_name(&dev->dev), gb_len); return nfc_llcp_set_remote_gb(dev, gb, gb_len); } EXPORT_SYMBOL(nfc_set_remote_general_bytes); u8 *nfc_get_local_general_bytes(struct nfc_dev *dev, size_t *gb_len) { pr_debug("dev_name=%s\n", dev_name(&dev->dev)); return nfc_llcp_general_bytes(dev, gb_len); } EXPORT_SYMBOL(nfc_get_local_general_bytes); int nfc_tm_data_received(struct nfc_dev *dev, struct sk_buff *skb) { /* Only LLCP target mode for now */ if (dev->dep_link_up == false) { kfree_skb(skb); return -ENOLINK; } return nfc_llcp_data_received(dev, skb); } EXPORT_SYMBOL(nfc_tm_data_received); int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode, const u8 *gb, size_t gb_len) { int rc; device_lock(&dev->dev); dev->polling = false; if (gb != NULL) { rc = nfc_set_remote_general_bytes(dev, gb, gb_len); if (rc < 0) goto out; } dev->rf_mode = NFC_RF_TARGET; if (protocol == NFC_PROTO_NFC_DEP_MASK) nfc_dep_link_is_up(dev, 0, comm_mode, NFC_RF_TARGET); rc = nfc_genl_tm_activated(dev, protocol); out: device_unlock(&dev->dev); return rc; } EXPORT_SYMBOL(nfc_tm_activated); int nfc_tm_deactivated(struct nfc_dev *dev) { dev->dep_link_up = false; dev->rf_mode = NFC_RF_NONE; return nfc_genl_tm_deactivated(dev); } EXPORT_SYMBOL(nfc_tm_deactivated); /** * nfc_alloc_send_skb - allocate a skb for data exchange responses * * @dev: device sending the response * @sk: socket sending the response * @flags: MSG_DONTWAIT flag * @size: size to allocate * @err: pointer to memory to store the error code */ struct sk_buff *nfc_alloc_send_skb(struct nfc_dev *dev, struct sock *sk, unsigned int flags, unsigned int size, unsigned int *err) { struct sk_buff *skb; unsigned int total_size; total_size = size + dev->tx_headroom + dev->tx_tailroom + NFC_HEADER_SIZE; skb = sock_alloc_send_skb(sk, total_size, flags & MSG_DONTWAIT, err); if (skb) skb_reserve(skb, dev->tx_headroom + NFC_HEADER_SIZE); return skb; } /** * nfc_alloc_recv_skb - allocate a skb for data exchange responses * * @size: size to allocate * @gfp: gfp flags */ struct sk_buff *nfc_alloc_recv_skb(unsigned int size, gfp_t gfp) { struct sk_buff *skb; unsigned int total_size; total_size = size + 1; skb = alloc_skb(total_size, gfp); if (skb) skb_reserve(skb, 1); return skb; } EXPORT_SYMBOL(nfc_alloc_recv_skb); /** * nfc_targets_found - inform that targets were found * * @dev: The nfc device that found the targets * @targets: array of nfc targets found * @n_targets: targets array size * * The device driver must call this function when one or many nfc targets * are found. After calling this function, the device driver must stop * polling for targets. * NOTE: This function can be called with targets=NULL and n_targets=0 to * notify a driver error, meaning that the polling operation cannot complete. * IMPORTANT: this function must not be called from an atomic context. * In addition, it must also not be called from a context that would prevent * the NFC Core to call other nfc ops entry point concurrently. */ int nfc_targets_found(struct nfc_dev *dev, struct nfc_target *targets, int n_targets) { int i; pr_debug("dev_name=%s n_targets=%d\n", dev_name(&dev->dev), n_targets); for (i = 0; i < n_targets; i++) targets[i].idx = dev->target_next_idx++; device_lock(&dev->dev); if (dev->polling == false) { device_unlock(&dev->dev); return 0; } dev->polling = false; dev->targets_generation++; kfree(dev->targets); dev->targets = NULL; if (targets) { dev->targets = kmemdup(targets, n_targets * sizeof(struct nfc_target), GFP_ATOMIC); if (!dev->targets) { dev->n_targets = 0; device_unlock(&dev->dev); return -ENOMEM; } } dev->n_targets = n_targets; device_unlock(&dev->dev); nfc_genl_targets_found(dev); return 0; } EXPORT_SYMBOL(nfc_targets_found); /** * nfc_target_lost - inform that an activated target went out of field * * @dev: The nfc device that had the activated target in field * @target_idx: the nfc index of the target * * The device driver must call this function when the activated target * goes out of the field. * IMPORTANT: this function must not be called from an atomic context. * In addition, it must also not be called from a context that would prevent * the NFC Core to call other nfc ops entry point concurrently. */ int nfc_target_lost(struct nfc_dev *dev, u32 target_idx) { const struct nfc_target *tg; int i; pr_debug("dev_name %s n_target %d\n", dev_name(&dev->dev), target_idx); device_lock(&dev->dev); for (i = 0; i < dev->n_targets; i++) { tg = &dev->targets[i]; if (tg->idx == target_idx) break; } if (i == dev->n_targets) { device_unlock(&dev->dev); return -EINVAL; } dev->targets_generation++; dev->n_targets--; dev->active_target = NULL; if (dev->n_targets) { memcpy(&dev->targets[i], &dev->targets[i + 1], (dev->n_targets - i) * sizeof(struct nfc_target)); } else { kfree(dev->targets); dev->targets = NULL; } device_unlock(&dev->dev); nfc_genl_target_lost(dev, target_idx); return 0; } EXPORT_SYMBOL(nfc_target_lost); inline void nfc_driver_failure(struct nfc_dev *dev, int err) { nfc_targets_found(dev, NULL, 0); } EXPORT_SYMBOL(nfc_driver_failure); int nfc_add_se(struct nfc_dev *dev, u32 se_idx, u16 type) { struct nfc_se *se; int rc; pr_debug("%s se index %d\n", dev_name(&dev->dev), se_idx); se = nfc_find_se(dev, se_idx); if (se) return -EALREADY; se = kzalloc(sizeof(struct nfc_se), GFP_KERNEL); if (!se) return -ENOMEM; se->idx = se_idx; se->type = type; se->state = NFC_SE_DISABLED; INIT_LIST_HEAD(&se->list); list_add(&se->list, &dev->secure_elements); rc = nfc_genl_se_added(dev, se_idx, type); if (rc < 0) { list_del(&se->list); kfree(se); return rc; } return 0; } EXPORT_SYMBOL(nfc_add_se); int nfc_remove_se(struct nfc_dev *dev, u32 se_idx) { struct nfc_se *se, *n; int rc; pr_debug("%s se index %d\n", dev_name(&dev->dev), se_idx); list_for_each_entry_safe(se, n, &dev->secure_elements, list) if (se->idx == se_idx) { rc = nfc_genl_se_removed(dev, se_idx); if (rc < 0) return rc; list_del(&se->list); kfree(se); return 0; } return -EINVAL; } EXPORT_SYMBOL(nfc_remove_se); int nfc_se_transaction(struct nfc_dev *dev, u8 se_idx, struct nfc_evt_transaction *evt_transaction) { int rc; pr_debug("transaction: %x\n", se_idx); device_lock(&dev->dev); if (!evt_transaction) { rc = -EPROTO; goto out; } rc = nfc_genl_se_transaction(dev, se_idx, evt_transaction); out: device_unlock(&dev->dev); return rc; } EXPORT_SYMBOL(nfc_se_transaction); int nfc_se_connectivity(struct nfc_dev *dev, u8 se_idx) { int rc; pr_debug("connectivity: %x\n", se_idx); device_lock(&dev->dev); rc = nfc_genl_se_connectivity(dev, se_idx); device_unlock(&dev->dev); return rc; } EXPORT_SYMBOL(nfc_se_connectivity); static void nfc_release(struct device *d) { struct nfc_dev *dev = to_nfc_dev(d); struct nfc_se *se, *n; pr_debug("dev_name=%s\n", dev_name(&dev->dev)); nfc_genl_data_exit(&dev->genl_data); kfree(dev->targets); list_for_each_entry_safe(se, n, &dev->secure_elements, list) { nfc_genl_se_removed(dev, se->idx); list_del(&se->list); kfree(se); } ida_free(&nfc_index_ida, dev->idx); kfree(dev); } static void nfc_check_pres_work(struct work_struct *work) { struct nfc_dev *dev = container_of(work, struct nfc_dev, check_pres_work); int rc; device_lock(&dev->dev); if (dev->active_target && timer_pending(&dev->check_pres_timer) == 0) { rc = dev->ops->check_presence(dev, dev->active_target); if (rc == -EOPNOTSUPP) goto exit; if (rc) { u32 active_target_idx = dev->active_target->idx; device_unlock(&dev->dev); nfc_target_lost(dev, active_target_idx); return; } if (!dev->shutting_down) mod_timer(&dev->check_pres_timer, jiffies + msecs_to_jiffies(NFC_CHECK_PRES_FREQ_MS)); } exit: device_unlock(&dev->dev); } static void nfc_check_pres_timeout(struct timer_list *t) { struct nfc_dev *dev = from_timer(dev, t, check_pres_timer); schedule_work(&dev->check_pres_work); } const struct class nfc_class = { .name = "nfc", .dev_release = nfc_release, }; EXPORT_SYMBOL(nfc_class); static int match_idx(struct device *d, const void *data) { struct nfc_dev *dev = to_nfc_dev(d); const unsigned int *idx = data; return dev->idx == *idx; } struct nfc_dev *nfc_get_device(unsigned int idx) { struct device *d; d = class_find_device(&nfc_class, NULL, &idx, match_idx); if (!d) return NULL; return to_nfc_dev(d); } /** * nfc_allocate_device - allocate a new nfc device * * @ops: device operations * @supported_protocols: NFC protocols supported by the device * @tx_headroom: reserved space at beginning of skb * @tx_tailroom: reserved space at end of skb */ struct nfc_dev *nfc_allocate_device(const struct nfc_ops *ops, u32 supported_protocols, int tx_headroom, int tx_tailroom) { struct nfc_dev *dev; int rc; if (!ops->start_poll || !ops->stop_poll || !ops->activate_target || !ops->deactivate_target || !ops->im_transceive) return NULL; if (!supported_protocols) return NULL; dev = kzalloc(sizeof(struct nfc_dev), GFP_KERNEL); if (!dev) return NULL; rc = ida_alloc(&nfc_index_ida, GFP_KERNEL); if (rc < 0) goto err_free_dev; dev->idx = rc; dev->dev.class = &nfc_class; dev_set_name(&dev->dev, "nfc%d", dev->idx); device_initialize(&dev->dev); dev->ops = ops; dev->supported_protocols = supported_protocols; dev->tx_headroom = tx_headroom; dev->tx_tailroom = tx_tailroom; INIT_LIST_HEAD(&dev->secure_elements); nfc_genl_data_init(&dev->genl_data); dev->rf_mode = NFC_RF_NONE; /* first generation must not be 0 */ dev->targets_generation = 1; if (ops->check_presence) { timer_setup(&dev->check_pres_timer, nfc_check_pres_timeout, 0); INIT_WORK(&dev->check_pres_work, nfc_check_pres_work); } return dev; err_free_dev: kfree(dev); return NULL; } EXPORT_SYMBOL(nfc_allocate_device); /** * nfc_register_device - register a nfc device in the nfc subsystem * * @dev: The nfc device to register */ int nfc_register_device(struct nfc_dev *dev) { int rc; pr_debug("dev_name=%s\n", dev_name(&dev->dev)); mutex_lock(&nfc_devlist_mutex); nfc_devlist_generation++; rc = device_add(&dev->dev); mutex_unlock(&nfc_devlist_mutex); if (rc < 0) return rc; rc = nfc_llcp_register_device(dev); if (rc) pr_err("Could not register llcp device\n"); device_lock(&dev->dev); dev->rfkill = rfkill_alloc(dev_name(&dev->dev), &dev->dev, RFKILL_TYPE_NFC, &nfc_rfkill_ops, dev); if (dev->rfkill) { if (rfkill_register(dev->rfkill) < 0) { rfkill_destroy(dev->rfkill); dev->rfkill = NULL; } } dev->shutting_down = false; device_unlock(&dev->dev); rc = nfc_genl_device_added(dev); if (rc) pr_debug("The userspace won't be notified that the device %s was added\n", dev_name(&dev->dev)); return 0; } EXPORT_SYMBOL(nfc_register_device); /** * nfc_unregister_device - unregister a nfc device in the nfc subsystem * * @dev: The nfc device to unregister */ void nfc_unregister_device(struct nfc_dev *dev) { int rc; pr_debug("dev_name=%s\n", dev_name(&dev->dev)); rc = nfc_genl_device_removed(dev); if (rc) pr_debug("The userspace won't be notified that the device %s " "was removed\n", dev_name(&dev->dev)); device_lock(&dev->dev); if (dev->rfkill) { rfkill_unregister(dev->rfkill); rfkill_destroy(dev->rfkill); dev->rfkill = NULL; } dev->shutting_down = true; device_unlock(&dev->dev); if (dev->ops->check_presence) { timer_delete_sync(&dev->check_pres_timer); cancel_work_sync(&dev->check_pres_work); } nfc_llcp_unregister_device(dev); mutex_lock(&nfc_devlist_mutex); nfc_devlist_generation++; device_del(&dev->dev); mutex_unlock(&nfc_devlist_mutex); } EXPORT_SYMBOL(nfc_unregister_device); static int __init nfc_init(void) { int rc; pr_info("NFC Core ver %s\n", VERSION); rc = class_register(&nfc_class); if (rc) return rc; rc = nfc_genl_init(); if (rc) goto err_genl; /* the first generation must not be 0 */ nfc_devlist_generation = 1; rc = rawsock_init(); if (rc) goto err_rawsock; rc = nfc_llcp_init(); if (rc) goto err_llcp_sock; rc = af_nfc_init(); if (rc) goto err_af_nfc; return 0; err_af_nfc: nfc_llcp_exit(); err_llcp_sock: rawsock_exit(); err_rawsock: nfc_genl_exit(); err_genl: class_unregister(&nfc_class); return rc; } static void __exit nfc_exit(void) { af_nfc_exit(); nfc_llcp_exit(); rawsock_exit(); nfc_genl_exit(); class_unregister(&nfc_class); } subsys_initcall(nfc_init); module_exit(nfc_exit); MODULE_AUTHOR("Lauro Ramos Venancio <lauro.venancio@openbossa.org>"); MODULE_DESCRIPTION("NFC Core ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_NFC); MODULE_ALIAS_GENL_FAMILY(NFC_GENL_NAME); |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/mmzone.h> #include <linux/memblock.h> #include <linux/proc_fs.h> #include <linux/percpu.h> #include <linux/seq_file.h> #include <linux/swap.h> #include <linux/vmstat.h> #include <linux/atomic.h> #include <linux/vmalloc.h> #ifdef CONFIG_CMA #include <linux/cma.h> #endif #include <linux/zswap.h> #include <asm/page.h> #include "internal.h" void __attribute__((weak)) arch_report_meminfo(struct seq_file *m) { } static void show_val_kb(struct seq_file *m, const char *s, unsigned long num) { seq_put_decimal_ull_width(m, s, num << (PAGE_SHIFT - 10), 8); seq_write(m, " kB\n", 4); } static int meminfo_proc_show(struct seq_file *m, void *v) { struct sysinfo i; unsigned long committed; long cached; long available; unsigned long pages[NR_LRU_LISTS]; unsigned long sreclaimable, sunreclaim; int lru; si_meminfo(&i); si_swapinfo(&i); committed = vm_memory_committed(); cached = global_node_page_state(NR_FILE_PAGES) - total_swapcache_pages() - i.bufferram; if (cached < 0) cached = 0; for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++) pages[lru] = global_node_page_state(NR_LRU_BASE + lru); available = si_mem_available(); sreclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B); sunreclaim = global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B); show_val_kb(m, "MemTotal: ", i.totalram); show_val_kb(m, "MemFree: ", i.freeram); show_val_kb(m, "MemAvailable: ", available); show_val_kb(m, "Buffers: ", i.bufferram); show_val_kb(m, "Cached: ", cached); show_val_kb(m, "SwapCached: ", total_swapcache_pages()); show_val_kb(m, "Active: ", pages[LRU_ACTIVE_ANON] + pages[LRU_ACTIVE_FILE]); show_val_kb(m, "Inactive: ", pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]); show_val_kb(m, "Active(anon): ", pages[LRU_ACTIVE_ANON]); show_val_kb(m, "Inactive(anon): ", pages[LRU_INACTIVE_ANON]); show_val_kb(m, "Active(file): ", pages[LRU_ACTIVE_FILE]); show_val_kb(m, "Inactive(file): ", pages[LRU_INACTIVE_FILE]); show_val_kb(m, "Unevictable: ", pages[LRU_UNEVICTABLE]); show_val_kb(m, "Mlocked: ", global_zone_page_state(NR_MLOCK)); #ifdef CONFIG_HIGHMEM show_val_kb(m, "HighTotal: ", i.totalhigh); show_val_kb(m, "HighFree: ", i.freehigh); show_val_kb(m, "LowTotal: ", i.totalram - i.totalhigh); show_val_kb(m, "LowFree: ", i.freeram - i.freehigh); #endif #ifndef CONFIG_MMU show_val_kb(m, "MmapCopy: ", (unsigned long)atomic_long_read(&mmap_pages_allocated)); #endif show_val_kb(m, "SwapTotal: ", i.totalswap); show_val_kb(m, "SwapFree: ", i.freeswap); #ifdef CONFIG_ZSWAP show_val_kb(m, "Zswap: ", zswap_total_pages()); seq_printf(m, "Zswapped: %8lu kB\n", (unsigned long)atomic_long_read(&zswap_stored_pages) << (PAGE_SHIFT - 10)); #endif show_val_kb(m, "Dirty: ", global_node_page_state(NR_FILE_DIRTY)); show_val_kb(m, "Writeback: ", global_node_page_state(NR_WRITEBACK)); show_val_kb(m, "AnonPages: ", global_node_page_state(NR_ANON_MAPPED)); show_val_kb(m, "Mapped: ", global_node_page_state(NR_FILE_MAPPED)); show_val_kb(m, "Shmem: ", i.sharedram); show_val_kb(m, "KReclaimable: ", sreclaimable + global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE)); show_val_kb(m, "Slab: ", sreclaimable + sunreclaim); show_val_kb(m, "SReclaimable: ", sreclaimable); show_val_kb(m, "SUnreclaim: ", sunreclaim); seq_printf(m, "KernelStack: %8lu kB\n", global_node_page_state(NR_KERNEL_STACK_KB)); #ifdef CONFIG_SHADOW_CALL_STACK seq_printf(m, "ShadowCallStack:%8lu kB\n", global_node_page_state(NR_KERNEL_SCS_KB)); #endif show_val_kb(m, "PageTables: ", global_node_page_state(NR_PAGETABLE)); show_val_kb(m, "SecPageTables: ", global_node_page_state(NR_SECONDARY_PAGETABLE)); show_val_kb(m, "NFS_Unstable: ", 0); show_val_kb(m, "Bounce: ", global_zone_page_state(NR_BOUNCE)); show_val_kb(m, "WritebackTmp: ", global_node_page_state(NR_WRITEBACK_TEMP)); show_val_kb(m, "CommitLimit: ", vm_commit_limit()); show_val_kb(m, "Committed_AS: ", committed); seq_printf(m, "VmallocTotal: %8lu kB\n", (unsigned long)VMALLOC_TOTAL >> 10); show_val_kb(m, "VmallocUsed: ", vmalloc_nr_pages()); show_val_kb(m, "VmallocChunk: ", 0ul); show_val_kb(m, "Percpu: ", pcpu_nr_pages()); memtest_report_meminfo(m); #ifdef CONFIG_MEMORY_FAILURE seq_printf(m, "HardwareCorrupted: %5lu kB\n", atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)); #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE show_val_kb(m, "AnonHugePages: ", global_node_page_state(NR_ANON_THPS)); show_val_kb(m, "ShmemHugePages: ", global_node_page_state(NR_SHMEM_THPS)); show_val_kb(m, "ShmemPmdMapped: ", global_node_page_state(NR_SHMEM_PMDMAPPED)); show_val_kb(m, "FileHugePages: ", global_node_page_state(NR_FILE_THPS)); show_val_kb(m, "FilePmdMapped: ", global_node_page_state(NR_FILE_PMDMAPPED)); #endif #ifdef CONFIG_CMA show_val_kb(m, "CmaTotal: ", totalcma_pages); show_val_kb(m, "CmaFree: ", global_zone_page_state(NR_FREE_CMA_PAGES)); #endif #ifdef CONFIG_UNACCEPTED_MEMORY show_val_kb(m, "Unaccepted: ", global_zone_page_state(NR_UNACCEPTED)); #endif show_val_kb(m, "Balloon: ", global_node_page_state(NR_BALLOON_PAGES)); hugetlb_report_meminfo(m); arch_report_meminfo(m); return 0; } static int __init proc_meminfo_init(void) { struct proc_dir_entry *pde; pde = proc_create_single("meminfo", 0, NULL, meminfo_proc_show); pde_make_permanent(pde); return 0; } fs_initcall(proc_meminfo_init); |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * DSA tagging protocol handling * * Copyright (c) 2008-2009 Marvell Semiconductor * Copyright (c) 2013 Florian Fainelli <florian@openwrt.org> * Copyright (c) 2016 Andrew Lunn <andrew@lunn.ch> */ #include <linux/netdevice.h> #include <linux/ptp_classify.h> #include <linux/skbuff.h> #include <net/dsa.h> #include <net/dst_metadata.h> #include "tag.h" #include "user.h" static LIST_HEAD(dsa_tag_drivers_list); static DEFINE_MUTEX(dsa_tag_drivers_lock); /* Determine if we should defer delivery of skb until we have a rx timestamp. * * Called from dsa_switch_rcv. For now, this will only work if tagging is * enabled on the switch. Normally the MAC driver would retrieve the hardware * timestamp when it reads the packet out of the hardware. However in a DSA * switch, the DSA driver owning the interface to which the packet is * delivered is never notified unless we do so here. */ static bool dsa_skb_defer_rx_timestamp(struct dsa_user_priv *p, struct sk_buff *skb) { struct dsa_switch *ds = p->dp->ds; unsigned int type; if (!ds->ops->port_rxtstamp) return false; if (skb_headroom(skb) < ETH_HLEN) return false; __skb_push(skb, ETH_HLEN); type = ptp_classify_raw(skb); __skb_pull(skb, ETH_HLEN); if (type == PTP_CLASS_NONE) return false; return ds->ops->port_rxtstamp(ds, p->dp->index, skb, type); } static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *unused) { struct metadata_dst *md_dst = skb_metadata_dst(skb); struct dsa_port *cpu_dp = dev->dsa_ptr; struct sk_buff *nskb = NULL; struct dsa_user_priv *p; if (unlikely(!cpu_dp)) { kfree_skb(skb); return 0; } skb = skb_unshare(skb, GFP_ATOMIC); if (!skb) return 0; if (md_dst && md_dst->type == METADATA_HW_PORT_MUX) { unsigned int port = md_dst->u.port_info.port_id; skb_dst_drop(skb); if (!skb_has_extensions(skb)) skb->slow_gro = 0; skb->dev = dsa_conduit_find_user(dev, 0, port); if (likely(skb->dev)) { dsa_default_offload_fwd_mark(skb); nskb = skb; } } else { nskb = cpu_dp->rcv(skb, dev); } if (!nskb) { kfree_skb(skb); return 0; } skb = nskb; skb_push(skb, ETH_HLEN); skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); if (unlikely(!dsa_user_dev_check(skb->dev))) { /* Packet is to be injected directly on an upper * device, e.g. a team/bond, so skip all DSA-port * specific actions. */ netif_rx(skb); return 0; } p = netdev_priv(skb->dev); if (unlikely(cpu_dp->ds->untag_bridge_pvid || cpu_dp->ds->untag_vlan_aware_bridge_pvid)) { nskb = dsa_software_vlan_untag(skb); if (!nskb) { kfree_skb(skb); return 0; } skb = nskb; } dev_sw_netstats_rx_add(skb->dev, skb->len + ETH_HLEN); if (dsa_skb_defer_rx_timestamp(p, skb)) return 0; gro_cells_receive(&p->gcells, skb); return 0; } struct packet_type dsa_pack_type __read_mostly = { .type = cpu_to_be16(ETH_P_XDSA), .func = dsa_switch_rcv, }; static void dsa_tag_driver_register(struct dsa_tag_driver *dsa_tag_driver, struct module *owner) { dsa_tag_driver->owner = owner; mutex_lock(&dsa_tag_drivers_lock); list_add_tail(&dsa_tag_driver->list, &dsa_tag_drivers_list); mutex_unlock(&dsa_tag_drivers_lock); } void dsa_tag_drivers_register(struct dsa_tag_driver *dsa_tag_driver_array[], unsigned int count, struct module *owner) { unsigned int i; for (i = 0; i < count; i++) dsa_tag_driver_register(dsa_tag_driver_array[i], owner); } static void dsa_tag_driver_unregister(struct dsa_tag_driver *dsa_tag_driver) { mutex_lock(&dsa_tag_drivers_lock); list_del(&dsa_tag_driver->list); mutex_unlock(&dsa_tag_drivers_lock); } EXPORT_SYMBOL_GPL(dsa_tag_drivers_register); void dsa_tag_drivers_unregister(struct dsa_tag_driver *dsa_tag_driver_array[], unsigned int count) { unsigned int i; for (i = 0; i < count; i++) dsa_tag_driver_unregister(dsa_tag_driver_array[i]); } EXPORT_SYMBOL_GPL(dsa_tag_drivers_unregister); const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops) { return ops->name; }; /* Function takes a reference on the module owning the tagger, * so dsa_tag_driver_put must be called afterwards. */ const struct dsa_device_ops *dsa_tag_driver_get_by_name(const char *name) { const struct dsa_device_ops *ops = ERR_PTR(-ENOPROTOOPT); struct dsa_tag_driver *dsa_tag_driver; request_module("%s%s", DSA_TAG_DRIVER_ALIAS, name); mutex_lock(&dsa_tag_drivers_lock); list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { const struct dsa_device_ops *tmp = dsa_tag_driver->ops; if (strcmp(name, tmp->name)) continue; if (!try_module_get(dsa_tag_driver->owner)) break; ops = tmp; break; } mutex_unlock(&dsa_tag_drivers_lock); return ops; } const struct dsa_device_ops *dsa_tag_driver_get_by_id(int tag_protocol) { struct dsa_tag_driver *dsa_tag_driver; const struct dsa_device_ops *ops; bool found = false; request_module("%sid-%d", DSA_TAG_DRIVER_ALIAS, tag_protocol); mutex_lock(&dsa_tag_drivers_lock); list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { ops = dsa_tag_driver->ops; if (ops->proto == tag_protocol) { found = true; break; } } if (found) { if (!try_module_get(dsa_tag_driver->owner)) ops = ERR_PTR(-ENOPROTOOPT); } else { ops = ERR_PTR(-ENOPROTOOPT); } mutex_unlock(&dsa_tag_drivers_lock); return ops; } void dsa_tag_driver_put(const struct dsa_device_ops *ops) { struct dsa_tag_driver *dsa_tag_driver; mutex_lock(&dsa_tag_drivers_lock); list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { if (dsa_tag_driver->ops == ops) { module_put(dsa_tag_driver->owner); break; } } mutex_unlock(&dsa_tag_drivers_lock); } |
| 38 1 1 37 35 1 1 36 22 1 34 31 4 31 3 1 34 6 6 6 5 4 4 50 50 50 5 5 7 7 7 6 5 4 4 4 4 40 40 15 37 42 2 40 1 39 1 38 14 24 10 13 4 1 9 23 19 2 3 3 3 3 3 3 176 176 165 165 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/dccp/ipv4.c * * An implementation of the DCCP protocol * Arnaldo Carvalho de Melo <acme@conectiva.com.br> */ #include <linux/dccp.h> #include <linux/icmp.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/random.h> #include <net/icmp.h> #include <net/inet_common.h> #include <net/inet_dscp.h> #include <net/inet_hashtables.h> #include <net/inet_sock.h> #include <net/protocol.h> #include <net/sock.h> #include <net/timewait_sock.h> #include <net/tcp_states.h> #include <net/xfrm.h> #include <net/secure_seq.h> #include <net/netns/generic.h> #include <net/rstreason.h> #include "ackvec.h" #include "ccid.h" #include "dccp.h" #include "feat.h" struct dccp_v4_pernet { struct sock *v4_ctl_sk; }; static unsigned int dccp_v4_pernet_id __read_mostly; /* * The per-net v4_ctl_sk socket is used for responding to * the Out-of-the-blue (OOTB) packets. A control sock will be created * for this socket at the initialization time. */ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_sock *inet = inet_sk(sk); struct dccp_sock *dp = dccp_sk(sk); __be16 orig_sport, orig_dport; __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; struct ip_options_rcu *inet_opt; dp->dccps_role = DCCP_ROLE_CLIENT; if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; if (usin->sin_family != AF_INET) return -EAFNOSUPPORT; nexthop = daddr = usin->sin_addr.s_addr; inet_opt = rcu_dereference_protected(inet->inet_opt, lockdep_sock_is_held(sk)); if (inet_opt != NULL && inet_opt->opt.srr) { if (daddr == 0) return -EINVAL; nexthop = inet_opt->opt.faddr; } orig_sport = inet->inet_sport; orig_dport = usin->sin_port; fl4 = &inet->cork.fl.u.ip4; rt = ip_route_connect(fl4, nexthop, inet->inet_saddr, sk->sk_bound_dev_if, IPPROTO_DCCP, orig_sport, orig_dport, sk); if (IS_ERR(rt)) return PTR_ERR(rt); if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) { ip_rt_put(rt); return -ENETUNREACH; } if (inet_opt == NULL || !inet_opt->opt.srr) daddr = fl4->daddr; if (inet->inet_saddr == 0) { err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET); if (err) { ip_rt_put(rt); return err; } } else { sk_rcv_saddr_set(sk, inet->inet_saddr); } inet->inet_dport = usin->sin_port; sk_daddr_set(sk, daddr); inet_csk(sk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen; /* * Socket identity is still unknown (sport may be zero). * However we set state to DCCP_REQUESTING and not releasing socket * lock select source port, enter ourselves into the hash tables and * complete initialization after this. */ dccp_set_state(sk, DCCP_REQUESTING); err = inet_hash_connect(&dccp_death_row, sk); if (err != 0) goto failure; rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; goto failure; } /* OK, now commit destination to socket. */ sk_setup_caps(sk, &rt->dst); dp->dccps_iss = secure_dccp_sequence_number(inet->inet_saddr, inet->inet_daddr, inet->inet_sport, inet->inet_dport); atomic_set(&inet->inet_id, get_random_u16()); err = dccp_connect(sk); rt = NULL; if (err != 0) goto failure; out: return err; failure: /* * This unhashes the socket and releases the local port, if necessary. */ dccp_set_state(sk, DCCP_CLOSED); inet_bhash2_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; goto out; } EXPORT_SYMBOL_GPL(dccp_v4_connect); /* * This routine does path mtu discovery as defined in RFC1191. */ static inline void dccp_do_pmtu_discovery(struct sock *sk, const struct iphdr *iph, u32 mtu) { struct dst_entry *dst; const struct inet_sock *inet = inet_sk(sk); const struct dccp_sock *dp = dccp_sk(sk); /* We are not interested in DCCP_LISTEN and request_socks (RESPONSEs * send out by Linux are always < 576bytes so they should go through * unfragmented). */ if (sk->sk_state == DCCP_LISTEN) return; dst = inet_csk_update_pmtu(sk, mtu); if (!dst) return; /* Something is about to be wrong... Remember soft error * for the case, if this connection will not able to recover. */ if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst)) WRITE_ONCE(sk->sk_err_soft, EMSGSIZE); mtu = dst_mtu(dst); if (inet->pmtudisc != IP_PMTUDISC_DONT && ip_sk_accept_pmtu(sk) && inet_csk(sk)->icsk_pmtu_cookie > mtu) { dccp_sync_mss(sk, mtu); /* * From RFC 4340, sec. 14.1: * * DCCP-Sync packets are the best choice for upward * probing, since DCCP-Sync probes do not risk application * data loss. */ dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC); } /* else let the usual retransmit timer handle it */ } static void dccp_do_redirect(struct sk_buff *skb, struct sock *sk) { struct dst_entry *dst = __sk_dst_check(sk, 0); if (dst) dst->ops->redirect(dst, sk, skb); } void dccp_req_err(struct sock *sk, u64 seq) { struct request_sock *req = inet_reqsk(sk); struct net *net = sock_net(sk); /* * ICMPs are not backlogged, hence we cannot get an established * socket here. */ if (!between48(seq, dccp_rsk(req)->dreq_iss, dccp_rsk(req)->dreq_gss)) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); } else { /* * Still in RESPOND, just remove it silently. * There is no good way to pass the error to the newly * created socket, and POSIX does not want network * errors returned from accept(). */ inet_csk_reqsk_queue_drop(req->rsk_listener, req); } reqsk_put(req); } EXPORT_SYMBOL(dccp_req_err); /* * This routine is called by the ICMP module when it gets some sort of error * condition. If err < 0 then the socket should be closed and the error * returned to the user. If err > 0 it's just the icmp type << 8 | icmp code. * After adjustment header points to the first 8 bytes of the tcp header. We * need to find the appropriate port. * * The locking strategy used here is very "optimistic". When someone else * accesses the socket the ICMP is just dropped and for some paths there is no * check at all. A more general error queue to queue errors for later handling * is probably better. */ static int dccp_v4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (struct iphdr *)skb->data; const u8 offset = iph->ihl << 2; const struct dccp_hdr *dh; struct dccp_sock *dp; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct sock *sk; __u64 seq; int err; struct net *net = dev_net(skb->dev); if (!pskb_may_pull(skb, offset + sizeof(*dh))) return -EINVAL; dh = (struct dccp_hdr *)(skb->data + offset); if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh))) return -EINVAL; iph = (struct iphdr *)skb->data; dh = (struct dccp_hdr *)(skb->data + offset); sk = __inet_lookup_established(net, &dccp_hashinfo, iph->daddr, dh->dccph_dport, iph->saddr, ntohs(dh->dccph_sport), inet_iif(skb), 0); if (!sk) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return -ENOENT; } if (sk->sk_state == DCCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); return 0; } seq = dccp_hdr_seq(dh); if (sk->sk_state == DCCP_NEW_SYN_RECV) { dccp_req_err(sk, seq); return 0; } bh_lock_sock(sk); /* If too many ICMPs get dropped on busy * servers this needs to be solved differently. */ if (sock_owned_by_user(sk)) __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == DCCP_CLOSED) goto out; dp = dccp_sk(sk); if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && !between48(seq, dp->dccps_awl, dp->dccps_awh)) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } switch (type) { case ICMP_REDIRECT: if (!sock_owned_by_user(sk)) dccp_do_redirect(skb, sk); goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ goto out; case ICMP_PARAMETERPROB: err = EPROTO; break; case ICMP_DEST_UNREACH: if (code > NR_ICMP_UNREACH) goto out; if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */ if (!sock_owned_by_user(sk)) dccp_do_pmtu_discovery(sk, iph, info); goto out; } err = icmp_err_convert[code].errno; break; case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; break; default: goto out; } switch (sk->sk_state) { case DCCP_REQUESTING: case DCCP_RESPOND: if (!sock_owned_by_user(sk)) { __DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; sk_error_report(sk); dccp_done(sk); } else { WRITE_ONCE(sk->sk_err_soft, err); } goto out; } /* If we've already connected we will keep trying * until we time out, or the user gives up. * * rfc1122 4.2.3.9 allows to consider as hard errors * only PROTO_UNREACH and PORT_UNREACH (well, FRAG_FAILED too, * but it is obsoleted by pmtu discovery). * * Note, that in modern internet, where routing is unreliable * and in each dark corner broken firewalls sit, sending random * errors ordered by their masters even this two messages finally lose * their original sense (even Linux sends invalid PORT_UNREACHs) * * Now we are in compliance with RFCs. * --ANK (980905) */ if (!sock_owned_by_user(sk) && inet_test_bit(RECVERR, sk)) { sk->sk_err = err; sk_error_report(sk); } else { /* Only an error on timeout */ WRITE_ONCE(sk->sk_err_soft, err); } out: bh_unlock_sock(sk); sock_put(sk); return 0; } static inline __sum16 dccp_v4_csum_finish(struct sk_buff *skb, __be32 src, __be32 dst) { return csum_tcpudp_magic(src, dst, skb->len, IPPROTO_DCCP, skb->csum); } void dccp_v4_send_check(struct sock *sk, struct sk_buff *skb) { const struct inet_sock *inet = inet_sk(sk); struct dccp_hdr *dh = dccp_hdr(skb); dccp_csum_outgoing(skb); dh->dccph_checksum = dccp_v4_csum_finish(skb, inet->inet_saddr, inet->inet_daddr); } EXPORT_SYMBOL_GPL(dccp_v4_send_check); static inline u64 dccp_v4_init_sequence(const struct sk_buff *skb) { return secure_dccp_sequence_number(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, dccp_hdr(skb)->dccph_dport, dccp_hdr(skb)->dccph_sport); } /* * The three way handshake has completed - we got a valid ACK or DATAACK - * now create the new socket. * * This is the equivalent of TCP's tcp_v4_syn_recv_sock */ struct sock *dccp_v4_request_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) { struct inet_request_sock *ireq; struct inet_sock *newinet; struct sock *newsk; if (sk_acceptq_is_full(sk)) goto exit_overflow; newsk = dccp_create_openreq_child(sk, req, skb); if (newsk == NULL) goto exit_nonewsk; newinet = inet_sk(newsk); ireq = inet_rsk(req); RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt)); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; atomic_set(&newinet->inet_id, get_random_u16()); if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) goto put_and_exit; sk_setup_caps(newsk, dst); dccp_sync_mss(newsk, dst_mtu(dst)); if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); if (*own_req) ireq->ireq_opt = NULL; else newinet->inet_opt = NULL; return newsk; exit_overflow: __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); exit_nonewsk: dst_release(dst); exit: __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; put_and_exit: newinet->inet_opt = NULL; inet_csk_prepare_forced_close(newsk); dccp_done(newsk); goto exit; } EXPORT_SYMBOL_GPL(dccp_v4_request_recv_sock); static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *rt; const struct iphdr *iph = ip_hdr(skb); struct flowi4 fl4 = { .flowi4_oif = inet_iif(skb), .daddr = iph->saddr, .saddr = iph->daddr, .flowi4_tos = inet_dscp_to_dsfield(inet_sk_dscp(inet_sk(sk))), .flowi4_scope = ip_sock_rt_scope(sk), .flowi4_proto = sk->sk_protocol, .fl4_sport = dccp_hdr(skb)->dccph_dport, .fl4_dport = dccp_hdr(skb)->dccph_sport, }; security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) { IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } return &rt->dst; } static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req) { int err = -1; struct sk_buff *skb; struct dst_entry *dst; struct flowi4 fl4; dst = inet_csk_route_req(sk, &fl4, req); if (dst == NULL) goto out; skb = dccp_make_response(sk, dst, req); if (skb != NULL) { const struct inet_request_sock *ireq = inet_rsk(req); struct dccp_hdr *dh = dccp_hdr(skb); dh->dccph_checksum = dccp_v4_csum_finish(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, rcu_dereference(ireq->ireq_opt), READ_ONCE(inet_sk(sk)->tos)); rcu_read_unlock(); err = net_xmit_eval(err); } out: dst_release(dst); return err; } static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb, enum sk_rst_reason reason) { int err; const struct iphdr *rxiph; struct sk_buff *skb; struct dst_entry *dst; struct net *net = dev_net(skb_dst(rxskb)->dev); struct dccp_v4_pernet *pn; struct sock *ctl_sk; /* Never send a reset in response to a reset. */ if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET) return; if (skb_rtable(rxskb)->rt_type != RTN_LOCAL) return; pn = net_generic(net, dccp_v4_pernet_id); ctl_sk = pn->v4_ctl_sk; dst = dccp_v4_route_skb(net, ctl_sk, rxskb); if (dst == NULL) return; skb = dccp_ctl_make_reset(ctl_sk, rxskb); if (skb == NULL) goto out; rxiph = ip_hdr(rxskb); dccp_hdr(skb)->dccph_checksum = dccp_v4_csum_finish(skb, rxiph->saddr, rxiph->daddr); skb_dst_set(skb, dst_clone(dst)); local_bh_disable(); bh_lock_sock(ctl_sk); err = ip_build_and_send_pkt(skb, ctl_sk, rxiph->daddr, rxiph->saddr, NULL, inet_sk(ctl_sk)->tos); bh_unlock_sock(ctl_sk); if (net_xmit_eval(err) == 0) { __DCCP_INC_STATS(DCCP_MIB_OUTSEGS); __DCCP_INC_STATS(DCCP_MIB_OUTRSTS); } local_bh_enable(); out: dst_release(dst); } static void dccp_v4_reqsk_destructor(struct request_sock *req) { dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg); kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1)); } void dccp_syn_ack_timeout(const struct request_sock *req) { } EXPORT_SYMBOL(dccp_syn_ack_timeout); static struct request_sock_ops dccp_request_sock_ops __read_mostly = { .family = PF_INET, .obj_size = sizeof(struct dccp_request_sock), .rtx_syn_ack = dccp_v4_send_response, .send_ack = dccp_reqsk_send_ack, .destructor = dccp_v4_reqsk_destructor, .send_reset = dccp_v4_ctl_send_reset, .syn_ack_timeout = dccp_syn_ack_timeout, }; int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { struct inet_request_sock *ireq; struct request_sock *req; struct dccp_request_sock *dreq; const __be32 service = dccp_hdr_request(skb)->dccph_req_service; struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); /* Never answer to DCCP_PKT_REQUESTs send to broadcast or multicast */ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) return 0; /* discard, don't send a reset here */ if (dccp_bad_service_code(sk, service)) { dcb->dccpd_reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE; goto drop; } /* * TW buckets are converted to open requests without * limitations, they conserve resources and peer is * evidently real one. */ dcb->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY; if (inet_csk_reqsk_queue_is_full(sk)) goto drop; if (sk_acceptq_is_full(sk)) goto drop; req = inet_reqsk_alloc(&dccp_request_sock_ops, sk, true); if (req == NULL) goto drop; if (dccp_reqsk_init(req, dccp_sk(sk), skb)) goto drop_and_free; dreq = dccp_rsk(req); if (dccp_parse_options(sk, dreq, skb)) goto drop_and_free; ireq = inet_rsk(req); sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); ireq->ir_mark = inet_request_mark(sk, skb); ireq->ireq_family = AF_INET; ireq->ir_iif = READ_ONCE(sk->sk_bound_dev_if); if (security_inet_conn_request(sk, skb, req)) goto drop_and_free; /* * Step 3: Process LISTEN state * * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie * * Setting S.SWL/S.SWH to is deferred to dccp_create_openreq_child(). */ dreq->dreq_isr = dcb->dccpd_seq; dreq->dreq_gsr = dreq->dreq_isr; dreq->dreq_iss = dccp_v4_init_sequence(skb); dreq->dreq_gss = dreq->dreq_iss; dreq->dreq_service = service; if (dccp_v4_send_response(sk, req)) goto drop_and_free; if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT))) reqsk_free(req); else reqsk_put(req); return 0; drop_and_free: reqsk_free(req); drop: __DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS); return -1; } EXPORT_SYMBOL_GPL(dccp_v4_conn_request); int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) { struct dccp_hdr *dh = dccp_hdr(skb); if (sk->sk_state == DCCP_OPEN) { /* Fast path */ if (dccp_rcv_established(sk, skb, dh, skb->len)) goto reset; return 0; } /* * Step 3: Process LISTEN state * If P.type == Request or P contains a valid Init Cookie option, * (* Must scan the packet's options to check for Init * Cookies. Only Init Cookies are processed here, * however; other options are processed in Step 8. This * scan need only be performed if the endpoint uses Init * Cookies *) * (* Generate a new socket and switch to that socket *) * Set S := new socket for this port pair * S.state = RESPOND * Choose S.ISS (initial seqno) or set from Init Cookies * Initialize S.GAR := S.ISS * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookies * Continue with S.state == RESPOND * (* A Response packet will be generated in Step 11 *) * Otherwise, * Generate Reset(No Connection) unless P.type == Reset * Drop packet and return * * NOTE: the check for the packet types is done in * dccp_rcv_state_process */ if (dccp_rcv_state_process(sk, skb, dh, skb->len)) goto reset; return 0; reset: dccp_v4_ctl_send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED); kfree_skb(skb); return 0; } EXPORT_SYMBOL_GPL(dccp_v4_do_rcv); /** * dccp_invalid_packet - check for malformed packets * @skb: Packet to validate * * Implements RFC 4340, 8.5: Step 1: Check header basics * Packets that fail these checks are ignored and do not receive Resets. */ int dccp_invalid_packet(struct sk_buff *skb) { const struct dccp_hdr *dh; unsigned int cscov; u8 dccph_doff; if (skb->pkt_type != PACKET_HOST) return 1; /* If the packet is shorter than 12 bytes, drop packet and return */ if (!pskb_may_pull(skb, sizeof(struct dccp_hdr))) { DCCP_WARN("pskb_may_pull failed\n"); return 1; } dh = dccp_hdr(skb); /* If P.type is not understood, drop packet and return */ if (dh->dccph_type >= DCCP_PKT_INVALID) { DCCP_WARN("invalid packet type\n"); return 1; } /* * If P.Data Offset is too small for packet type, drop packet and return */ dccph_doff = dh->dccph_doff; if (dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) { DCCP_WARN("P.Data Offset(%u) too small\n", dccph_doff); return 1; } /* * If P.Data Offset is too large for packet, drop packet and return */ if (!pskb_may_pull(skb, dccph_doff * sizeof(u32))) { DCCP_WARN("P.Data Offset(%u) too large\n", dccph_doff); return 1; } dh = dccp_hdr(skb); /* * If P.type is not Data, Ack, or DataAck and P.X == 0 (the packet * has short sequence numbers), drop packet and return */ if ((dh->dccph_type < DCCP_PKT_DATA || dh->dccph_type > DCCP_PKT_DATAACK) && dh->dccph_x == 0) { DCCP_WARN("P.type (%s) not Data || [Data]Ack, while P.X == 0\n", dccp_packet_name(dh->dccph_type)); return 1; } /* * If P.CsCov is too large for the packet size, drop packet and return. * This must come _before_ checksumming (not as RFC 4340 suggests). */ cscov = dccp_csum_coverage(skb); if (cscov > skb->len) { DCCP_WARN("P.CsCov %u exceeds packet length %d\n", dh->dccph_cscov, skb->len); return 1; } /* If header checksum is incorrect, drop packet and return. * (This step is completed in the AF-dependent functions.) */ skb->csum = skb_checksum(skb, 0, cscov, 0); return 0; } EXPORT_SYMBOL_GPL(dccp_invalid_packet); /* this is called when real data arrives */ static int dccp_v4_rcv(struct sk_buff *skb) { const struct dccp_hdr *dh; const struct iphdr *iph; bool refcounted; struct sock *sk; int min_cov; /* Step 1: Check header basics */ if (dccp_invalid_packet(skb)) goto discard_it; iph = ip_hdr(skb); /* Step 1: If header checksum is incorrect, drop packet and return */ if (dccp_v4_csum_finish(skb, iph->saddr, iph->daddr)) { DCCP_WARN("dropped packet with invalid checksum\n"); goto discard_it; } dh = dccp_hdr(skb); DCCP_SKB_CB(skb)->dccpd_seq = dccp_hdr_seq(dh); DCCP_SKB_CB(skb)->dccpd_type = dh->dccph_type; dccp_pr_debug("%8.8s src=%pI4@%-5d dst=%pI4@%-5d seq=%llu", dccp_packet_name(dh->dccph_type), &iph->saddr, ntohs(dh->dccph_sport), &iph->daddr, ntohs(dh->dccph_dport), (unsigned long long) DCCP_SKB_CB(skb)->dccpd_seq); if (dccp_packet_without_ack(skb)) { DCCP_SKB_CB(skb)->dccpd_ack_seq = DCCP_PKT_WITHOUT_ACK_SEQ; dccp_pr_debug_cat("\n"); } else { DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb); dccp_pr_debug_cat(", ack=%llu\n", (unsigned long long) DCCP_SKB_CB(skb)->dccpd_ack_seq); } lookup: sk = __inet_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh), dh->dccph_sport, dh->dccph_dport, 0, &refcounted); if (!sk) { dccp_pr_debug("failed to look up flow ID in table and " "get corresponding socket\n"); goto no_dccp_socket; } /* * Step 2: * ... or S.state == TIMEWAIT, * Generate Reset(No Connection) unless P.type == Reset * Drop packet and return */ if (sk->sk_state == DCCP_TIME_WAIT) { dccp_pr_debug("sk->sk_state == DCCP_TIME_WAIT: do_time_wait\n"); inet_twsk_put(inet_twsk(sk)); goto no_dccp_socket; } if (sk->sk_state == DCCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); struct sock *nsk; sk = req->rsk_listener; if (unlikely(sk->sk_state != DCCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } sock_hold(sk); refcounted = true; nsk = dccp_check_req(sk, skb, req); if (!nsk) { reqsk_put(req); goto discard_and_relse; } if (nsk == sk) { reqsk_put(req); } else if (dccp_child_process(sk, nsk, skb)) { dccp_v4_ctl_send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED); goto discard_and_relse; } else { sock_put(sk); return 0; } } /* * RFC 4340, sec. 9.2.1: Minimum Checksum Coverage * o if MinCsCov = 0, only packets with CsCov = 0 are accepted * o if MinCsCov > 0, also accept packets with CsCov >= MinCsCov */ min_cov = dccp_sk(sk)->dccps_pcrlen; if (dh->dccph_cscov && (min_cov == 0 || dh->dccph_cscov < min_cov)) { dccp_pr_debug("Packet CsCov %d does not satisfy MinCsCov %d\n", dh->dccph_cscov, min_cov); /* FIXME: "Such packets SHOULD be reported using Data Dropped * options (Section 11.7) with Drop Code 0, Protocol * Constraints." */ goto discard_and_relse; } if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; nf_reset_ct(skb); return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, refcounted); no_dccp_socket: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; /* * Step 2: * If no socket ... * Generate Reset(No Connection) unless P.type == Reset * Drop packet and return */ if (dh->dccph_type != DCCP_PKT_RESET) { DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; dccp_v4_ctl_send_reset(sk, skb, SK_RST_REASON_NOT_SPECIFIED); } discard_it: kfree_skb(skb); return 0; discard_and_relse: if (refcounted) sock_put(sk); goto discard_it; } static const struct inet_connection_sock_af_ops dccp_ipv4_af_ops = { .queue_xmit = ip_queue_xmit, .send_check = dccp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, .conn_request = dccp_v4_conn_request, .syn_recv_sock = dccp_v4_request_recv_sock, .net_header_len = sizeof(struct iphdr), .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, }; static int dccp_v4_init_sock(struct sock *sk) { static __u8 dccp_v4_ctl_sock_initialized; int err = dccp_init_sock(sk, dccp_v4_ctl_sock_initialized); if (err == 0) { if (unlikely(!dccp_v4_ctl_sock_initialized)) dccp_v4_ctl_sock_initialized = 1; inet_csk(sk)->icsk_af_ops = &dccp_ipv4_af_ops; } return err; } static struct timewait_sock_ops dccp_timewait_sock_ops = { .twsk_obj_size = sizeof(struct inet_timewait_sock), }; static struct proto dccp_v4_prot = { .name = "DCCP", .owner = THIS_MODULE, .close = dccp_close, .connect = dccp_v4_connect, .disconnect = dccp_disconnect, .ioctl = dccp_ioctl, .init = dccp_v4_init_sock, .setsockopt = dccp_setsockopt, .getsockopt = dccp_getsockopt, .sendmsg = dccp_sendmsg, .recvmsg = dccp_recvmsg, .backlog_rcv = dccp_v4_do_rcv, .hash = inet_hash, .unhash = inet_unhash, .accept = inet_csk_accept, .get_port = inet_csk_get_port, .shutdown = dccp_shutdown, .destroy = dccp_destroy_sock, .orphan_count = &dccp_orphan_count, .max_header = MAX_DCCP_HEADER, .obj_size = sizeof(struct dccp_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, .rsk_prot = &dccp_request_sock_ops, .twsk_prot = &dccp_timewait_sock_ops, .h.hashinfo = &dccp_hashinfo, }; static const struct net_protocol dccp_v4_protocol = { .handler = dccp_v4_rcv, .err_handler = dccp_v4_err, .no_policy = 1, .icmp_strict_tag_validation = 1, }; static const struct proto_ops inet_dccp_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = inet_accept, .getname = inet_getname, /* FIXME: work on tcp_poll to rename it to inet_csk_poll */ .poll = dccp_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, /* FIXME: work on inet_listen to rename it to sock_common_listen */ .listen = inet_dccp_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, }; static struct inet_protosw dccp_v4_protosw = { .type = SOCK_DCCP, .protocol = IPPROTO_DCCP, .prot = &dccp_v4_prot, .ops = &inet_dccp_ops, .flags = INET_PROTOSW_ICSK, }; static int __net_init dccp_v4_init_net(struct net *net) { struct dccp_v4_pernet *pn = net_generic(net, dccp_v4_pernet_id); if (dccp_hashinfo.bhash == NULL) return -ESOCKTNOSUPPORT; return inet_ctl_sock_create(&pn->v4_ctl_sk, PF_INET, SOCK_DCCP, IPPROTO_DCCP, net); } static void __net_exit dccp_v4_exit_net(struct net *net) { struct dccp_v4_pernet *pn = net_generic(net, dccp_v4_pernet_id); inet_ctl_sock_destroy(pn->v4_ctl_sk); } static void __net_exit dccp_v4_exit_batch(struct list_head *net_exit_list) { inet_twsk_purge(&dccp_hashinfo); } static struct pernet_operations dccp_v4_ops = { .init = dccp_v4_init_net, .exit = dccp_v4_exit_net, .exit_batch = dccp_v4_exit_batch, .id = &dccp_v4_pernet_id, .size = sizeof(struct dccp_v4_pernet), }; static int __init dccp_v4_init(void) { int err = proto_register(&dccp_v4_prot, 1); if (err) goto out; inet_register_protosw(&dccp_v4_protosw); err = register_pernet_subsys(&dccp_v4_ops); if (err) goto out_destroy_ctl_sock; err = inet_add_protocol(&dccp_v4_protocol, IPPROTO_DCCP); if (err) goto out_proto_unregister; out: return err; out_proto_unregister: unregister_pernet_subsys(&dccp_v4_ops); out_destroy_ctl_sock: inet_unregister_protosw(&dccp_v4_protosw); proto_unregister(&dccp_v4_prot); goto out; } static void __exit dccp_v4_exit(void) { inet_del_protocol(&dccp_v4_protocol, IPPROTO_DCCP); unregister_pernet_subsys(&dccp_v4_ops); inet_unregister_protosw(&dccp_v4_protosw); proto_unregister(&dccp_v4_prot); } module_init(dccp_v4_init); module_exit(dccp_v4_exit); /* * __stringify doesn't likes enums, so use SOCK_DCCP (6) and IPPROTO_DCCP (33) * values directly, Also cover the case where the protocol is not specified, * i.e. net-pf-PF_INET-proto-0-type-SOCK_DCCP */ MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 33, 6); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 0, 6); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>"); MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol"); |
| 88 10645 12042 50 7204 33 33 16 5 50 45 514 319 51 48 20 642 26 38 39 392 6 357 847 108 109 108 109 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PGTABLE_H #define _LINUX_PGTABLE_H #include <linux/pfn.h> #include <asm/pgtable.h> #define PMD_ORDER (PMD_SHIFT - PAGE_SHIFT) #define PUD_ORDER (PUD_SHIFT - PAGE_SHIFT) #ifndef __ASSEMBLY__ #ifdef CONFIG_MMU #include <linux/mm_types.h> #include <linux/bug.h> #include <linux/errno.h> #include <asm-generic/pgtable_uffd.h> #include <linux/page_table_check.h> #if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \ defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS #error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED #endif /* * On almost all architectures and configurations, 0 can be used as the * upper ceiling to free_pgtables(): on many architectures it has the same * effect as using TASK_SIZE. However, there is one configuration which * must impose a more careful limit, to avoid freeing kernel pgtables. */ #ifndef USER_PGTABLES_CEILING #define USER_PGTABLES_CEILING 0UL #endif /* * This defines the first usable user address. Platforms * can override its value with custom FIRST_USER_ADDRESS * defined in their respective <asm/pgtable.h>. */ #ifndef FIRST_USER_ADDRESS #define FIRST_USER_ADDRESS 0UL #endif /* * This defines the generic helper for accessing PMD page * table page. Although platforms can still override this * via their respective <asm/pgtable.h>. */ #ifndef pmd_pgtable #define pmd_pgtable(pmd) pmd_page(pmd) #endif #define pmd_folio(pmd) page_folio(pmd_page(pmd)) /* * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD] * * The pXx_index() functions return the index of the entry in the page * table page which would control the given virtual address * * As these functions may be used by the same code for different levels of * the page table folding, they are always available, regardless of * CONFIG_PGTABLE_LEVELS value. For the folded levels they simply return 0 * because in such cases PTRS_PER_PxD equals 1. */ static inline unsigned long pte_index(unsigned long address) { return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); } #ifndef pmd_index static inline unsigned long pmd_index(unsigned long address) { return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); } #define pmd_index pmd_index #endif #ifndef pud_index static inline unsigned long pud_index(unsigned long address) { return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); } #define pud_index pud_index #endif #ifndef pgd_index /* Must be a compile-time constant, so implement it as a macro */ #define pgd_index(a) (((a) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) #endif #ifndef kernel_pte_init static inline void kernel_pte_init(void *addr) { } #define kernel_pte_init kernel_pte_init #endif #ifndef pmd_init static inline void pmd_init(void *addr) { } #define pmd_init pmd_init #endif #ifndef pud_init static inline void pud_init(void *addr) { } #define pud_init pud_init #endif #ifndef pte_offset_kernel static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address) { return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address); } #define pte_offset_kernel pte_offset_kernel #endif #ifdef CONFIG_HIGHPTE #define __pte_map(pmd, address) \ ((pte_t *)kmap_local_page(pmd_page(*(pmd))) + pte_index((address))) #define pte_unmap(pte) do { \ kunmap_local((pte)); \ rcu_read_unlock(); \ } while (0) #else static inline pte_t *__pte_map(pmd_t *pmd, unsigned long address) { return pte_offset_kernel(pmd, address); } static inline void pte_unmap(pte_t *pte) { rcu_read_unlock(); } #endif void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable); /* Find an entry in the second-level page table.. */ #ifndef pmd_offset static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) { return pud_pgtable(*pud) + pmd_index(address); } #define pmd_offset pmd_offset #endif #ifndef pud_offset static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) { return p4d_pgtable(*p4d) + pud_index(address); } #define pud_offset pud_offset #endif static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) { return (pgd + pgd_index(address)); }; /* * a shortcut to get a pgd_t in a given mm */ #ifndef pgd_offset #define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address)) #endif /* * a shortcut which implies the use of the kernel's pgd, instead * of a process's */ #define pgd_offset_k(address) pgd_offset(&init_mm, (address)) /* * In many cases it is known that a virtual address is mapped at PMD or PTE * level, so instead of traversing all the page table levels, we can get a * pointer to the PMD entry in user or kernel page table or translate a virtual * address to the pointer in the PTE in the kernel page tables with simple * helpers. */ static inline pmd_t *pmd_off(struct mm_struct *mm, unsigned long va) { return pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, va), va), va), va); } static inline pmd_t *pmd_off_k(unsigned long va) { return pmd_offset(pud_offset(p4d_offset(pgd_offset_k(va), va), va), va); } static inline pte_t *virt_to_kpte(unsigned long vaddr) { pmd_t *pmd = pmd_off_k(vaddr); return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr); } #ifndef pmd_young static inline int pmd_young(pmd_t pmd) { return 0; } #endif #ifndef pmd_dirty static inline int pmd_dirty(pmd_t pmd) { return 0; } #endif /* * A facility to provide lazy MMU batching. This allows PTE updates and * page invalidations to be delayed until a call to leave lazy MMU mode * is issued. Some architectures may benefit from doing this, and it is * beneficial for both shadow and direct mode hypervisors, which may batch * the PTE updates which happen during this window. Note that using this * interface requires that read hazards be removed from the code. A read * hazard could result in the direct mode hypervisor case, since the actual * write to the page tables may not yet have taken place, so reads though * a raw PTE pointer after it has been modified are not guaranteed to be * up to date. * * In the general case, no lock is guaranteed to be held between entry and exit * of the lazy mode. So the implementation must assume preemption may be enabled * and cpu migration is possible; it must take steps to be robust against this. * (In practice, for user PTE updates, the appropriate page table lock(s) are * held, but for kernel PTE updates, no lock is held). Nesting is not permitted * and the mode cannot be used in interrupt context. */ #ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE #define arch_enter_lazy_mmu_mode() do {} while (0) #define arch_leave_lazy_mmu_mode() do {} while (0) #define arch_flush_lazy_mmu_mode() do {} while (0) #endif #ifndef pte_batch_hint /** * pte_batch_hint - Number of pages that can be added to batch without scanning. * @ptep: Page table pointer for the entry. * @pte: Page table entry. * * Some architectures know that a set of contiguous ptes all map the same * contiguous memory with the same permissions. In this case, it can provide a * hint to aid pte batching without the core code needing to scan every pte. * * An architecture implementation may ignore the PTE accessed state. Further, * the dirty state must apply atomically to all the PTEs described by the hint. * * May be overridden by the architecture, else pte_batch_hint is always 1. */ static inline unsigned int pte_batch_hint(pte_t *ptep, pte_t pte) { return 1; } #endif #ifndef pte_advance_pfn static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr) { return __pte(pte_val(pte) + (nr << PFN_PTE_SHIFT)); } #endif #define pte_next_pfn(pte) pte_advance_pfn(pte, 1) #ifndef set_ptes /** * set_ptes - Map consecutive pages to a contiguous range of addresses. * @mm: Address space to map the pages into. * @addr: Address to map the first page at. * @ptep: Page table pointer for the first entry. * @pte: Page table entry for the first page. * @nr: Number of pages to map. * * When nr==1, initial state of pte may be present or not present, and new state * may be present or not present. When nr>1, initial state of all ptes must be * not present, and new state must be present. * * May be overridden by the architecture, or the architecture can define * set_pte() and PFN_PTE_SHIFT. * * Context: The caller holds the page table lock. The pages all belong * to the same folio. The PTEs are all in the same PMD. */ static inline void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr) { page_table_check_ptes_set(mm, ptep, pte, nr); for (;;) { set_pte(ptep, pte); if (--nr == 0) break; ptep++; pte = pte_next_pfn(pte); } } #endif #define set_pte_at(mm, addr, ptep, pte) set_ptes(mm, addr, ptep, pte, 1) #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); #endif #ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); extern int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty); #else static inline int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { BUILD_BUG(); return 0; } static inline int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty) { BUILD_BUG(); return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef ptep_get static inline pte_t ptep_get(pte_t *ptep) { return READ_ONCE(*ptep); } #endif #ifndef pmdp_get static inline pmd_t pmdp_get(pmd_t *pmdp) { return READ_ONCE(*pmdp); } #endif #ifndef pudp_get static inline pud_t pudp_get(pud_t *pudp) { return READ_ONCE(*pudp); } #endif #ifndef p4dp_get static inline p4d_t p4dp_get(p4d_t *p4dp) { return READ_ONCE(*p4dp); } #endif #ifndef pgdp_get static inline pgd_t pgdp_get(pgd_t *pgdp) { return READ_ONCE(*pgdp); } #endif #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t pte = ptep_get(ptep); int r = 1; if (!pte_young(pte)) r = 0; else set_pte_at(vma->vm_mm, address, ptep, pte_mkold(pte)); return r; } #endif #ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { pmd_t pmd = *pmdp; int r = 1; if (!pmd_young(pmd)) r = 0; else set_pmd_at(vma->vm_mm, address, pmdp, pmd_mkold(pmd)); return r; } #else static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */ #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #endif #ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #else /* * Despite relevant to THP only, this API is called from generic rmap code * under PageTransHuge(), hence needs a dummy implementation for !THP */ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef arch_has_hw_nonleaf_pmd_young /* * Return whether the accessed bit in non-leaf PMD entries is supported on the * local CPU. */ static inline bool arch_has_hw_nonleaf_pmd_young(void) { return IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG); } #endif #ifndef arch_has_hw_pte_young /* * Return whether the accessed bit is supported on the local CPU. * * This stub assumes accessing through an old PTE triggers a page fault. * Architectures that automatically set the access bit should overwrite it. */ static inline bool arch_has_hw_pte_young(void) { return IS_ENABLED(CONFIG_ARCH_HAS_HW_PTE_YOUNG); } #endif #ifndef arch_check_zapped_pte static inline void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte) { } #endif #ifndef arch_check_zapped_pmd static inline void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd) { } #endif #ifndef arch_check_zapped_pud static inline void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud) { } #endif #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t pte = ptep_get(ptep); pte_clear(mm, address, ptep); page_table_check_pte_clear(mm, pte); return pte; } #endif #ifndef clear_young_dirty_ptes /** * clear_young_dirty_ptes - Mark PTEs that map consecutive pages of the * same folio as old/clean. * @mm: Address space the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to mark old/clean. * @flags: Flags to modify the PTE batch semantics. * * May be overridden by the architecture; otherwise, implemented by * get_and_clear/modify/set for each pte in the range. * * Note that PTE bits in the PTE range besides the PFN can differ. For example, * some PTEs might be write-protected. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. The PTEs are all in the same PMD. */ static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags) { pte_t pte; for (;;) { if (flags == CYDP_CLEAR_YOUNG) ptep_test_and_clear_young(vma, addr, ptep); else { pte = ptep_get_and_clear(vma->vm_mm, addr, ptep); if (flags & CYDP_CLEAR_YOUNG) pte = pte_mkold(pte); if (flags & CYDP_CLEAR_DIRTY) pte = pte_mkclean(pte); set_pte_at(vma->vm_mm, addr, ptep, pte); } if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } #endif static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t pte = ptep_get(ptep); pte_clear(mm, addr, ptep); /* * No need for ptep_get_and_clear(): page table check doesn't care about * any bits that could have been set by HW concurrently. */ page_table_check_pte_clear(mm, pte); } #ifdef CONFIG_GUP_GET_PXX_LOW_HIGH /* * For walking the pagetables without holding any locks. Some architectures * (eg x86-32 PAE) cannot load the entries atomically without using expensive * instructions. We are guaranteed that a PTE will only either go from not * present to present, or present to not present -- it will not switch to a * completely different present page without a TLB flush inbetween; which we * are blocking by holding interrupts off. * * Setting ptes from not present to present goes: * * ptep->pte_high = h; * smp_wmb(); * ptep->pte_low = l; * * And present to not present goes: * * ptep->pte_low = 0; * smp_wmb(); * ptep->pte_high = 0; * * We must ensure here that the load of pte_low sees 'l' IFF pte_high sees 'h'. * We load pte_high *after* loading pte_low, which ensures we don't see an older * value of pte_high. *Then* we recheck pte_low, which ensures that we haven't * picked up a changed pte high. We might have gotten rubbish values from * pte_low and pte_high, but we are guaranteed that pte_low will not have the * present bit set *unless* it is 'l'. Because get_user_pages_fast() only * operates on present ptes we're safe. */ static inline pte_t ptep_get_lockless(pte_t *ptep) { pte_t pte; do { pte.pte_low = ptep->pte_low; smp_rmb(); pte.pte_high = ptep->pte_high; smp_rmb(); } while (unlikely(pte.pte_low != ptep->pte_low)); return pte; } #define ptep_get_lockless ptep_get_lockless #if CONFIG_PGTABLE_LEVELS > 2 static inline pmd_t pmdp_get_lockless(pmd_t *pmdp) { pmd_t pmd; do { pmd.pmd_low = pmdp->pmd_low; smp_rmb(); pmd.pmd_high = pmdp->pmd_high; smp_rmb(); } while (unlikely(pmd.pmd_low != pmdp->pmd_low)); return pmd; } #define pmdp_get_lockless pmdp_get_lockless #define pmdp_get_lockless_sync() tlb_remove_table_sync_one() #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #endif /* CONFIG_GUP_GET_PXX_LOW_HIGH */ /* * We require that the PTE can be read atomically. */ #ifndef ptep_get_lockless static inline pte_t ptep_get_lockless(pte_t *ptep) { return ptep_get(ptep); } #endif #ifndef pmdp_get_lockless static inline pmd_t pmdp_get_lockless(pmd_t *pmdp) { return pmdp_get(pmdp); } static inline void pmdp_get_lockless_sync(void) { } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE #ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { pmd_t pmd = *pmdp; pmd_clear(pmdp); page_table_check_pmd_clear(mm, pmd); return pmd; } #endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */ #ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pud_t *pudp) { pud_t pud = *pudp; pud_clear(pudp); page_table_check_pud_clear(mm, pud); return pud; } #endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL static inline pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, int full) { return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); } #endif #ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL static inline pud_t pudp_huge_get_and_clear_full(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, int full) { return pudp_huge_get_and_clear(vma->vm_mm, address, pudp); } #endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long address, pte_t *ptep, int full) { return ptep_get_and_clear(mm, address, ptep); } #endif #ifndef get_and_clear_full_ptes /** * get_and_clear_full_ptes - Clear present PTEs that map consecutive pages of * the same folio, collecting dirty/accessed bits. * @mm: Address space the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to clear. * @full: Whether we are clearing a full mm. * * May be overridden by the architecture; otherwise, implemented as a simple * loop over ptep_get_and_clear_full(), merging dirty/accessed bits into the * returned PTE. * * Note that PTE bits in the PTE range besides the PFN can differ. For example, * some PTEs might be write-protected. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. The PTEs are all in the same PMD. */ static inline pte_t get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { pte_t pte, tmp_pte; pte = ptep_get_and_clear_full(mm, addr, ptep, full); while (--nr) { ptep++; addr += PAGE_SIZE; tmp_pte = ptep_get_and_clear_full(mm, addr, ptep, full); if (pte_dirty(tmp_pte)) pte = pte_mkdirty(pte); if (pte_young(tmp_pte)) pte = pte_mkyoung(pte); } return pte; } #endif #ifndef clear_full_ptes /** * clear_full_ptes - Clear present PTEs that map consecutive pages of the same * folio. * @mm: Address space the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to clear. * @full: Whether we are clearing a full mm. * * May be overridden by the architecture; otherwise, implemented as a simple * loop over ptep_get_and_clear_full(). * * Note that PTE bits in the PTE range besides the PFN can differ. For example, * some PTEs might be write-protected. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. The PTEs are all in the same PMD. */ static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { for (;;) { ptep_get_and_clear_full(mm, addr, ptep, full); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } #endif /* * If two threads concurrently fault at the same page, the thread that * won the race updates the PTE and its local TLB/Cache. The other thread * gives up, simply does nothing, and continues; on architectures where * software can update TLB, local TLB can be updated here to avoid next page * fault. This function updates TLB only, do nothing with cache or others. * It is the difference with function update_mmu_cache. */ #ifndef update_mmu_tlb_range static inline void update_mmu_tlb_range(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, unsigned int nr) { } #endif static inline void update_mmu_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { update_mmu_tlb_range(vma, address, ptep, 1); } /* * Some architectures may be able to avoid expensive synchronization * primitives when modifications are made to PTE's which are already * not present, or in the process of an address space destruction. */ #ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL static inline void pte_clear_not_present_full(struct mm_struct *mm, unsigned long address, pte_t *ptep, int full) { pte_clear(mm, address, ptep); } #endif #ifndef clear_not_present_full_ptes /** * clear_not_present_full_ptes - Clear multiple not present PTEs which are * consecutive in the pgtable. * @mm: Address space the ptes represent. * @addr: Address of the first pte. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to clear. * @full: Whether we are clearing a full mm. * * May be overridden by the architecture; otherwise, implemented as a simple * loop over pte_clear_not_present_full(). * * Context: The caller holds the page table lock. The PTEs are all not present. * The PTEs are all in the same PMD. */ static inline void clear_not_present_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { for (;;) { pte_clear_not_present_full(mm, addr, ptep, full); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH extern pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #endif #ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, pud_t *pudp); #endif #ifndef pte_mkwrite static inline pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma) { return pte_mkwrite_novma(pte); } #endif #if defined(CONFIG_ARCH_WANT_PMD_MKWRITE) && !defined(pmd_mkwrite) static inline pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) { return pmd_mkwrite_novma(pmd); } #endif #ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT struct mm_struct; static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t old_pte = ptep_get(ptep); set_pte_at(mm, address, ptep, pte_wrprotect(old_pte)); } #endif #ifndef wrprotect_ptes /** * wrprotect_ptes - Write-protect PTEs that map consecutive pages of the same * folio. * @mm: Address space the pages are mapped into. * @addr: Address the first page is mapped at. * @ptep: Page table pointer for the first entry. * @nr: Number of entries to write-protect. * * May be overridden by the architecture; otherwise, implemented as a simple * loop over ptep_set_wrprotect(). * * Note that PTE bits in the PTE range besides the PFN can differ. For example, * some PTEs might be write-protected. * * Context: The caller holds the page table lock. The PTEs map consecutive * pages that belong to the same folio. The PTEs are all in the same PMD. */ static inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) { for (;;) { ptep_set_wrprotect(mm, addr, ptep); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } #endif /* * On some architectures hardware does not set page access bit when accessing * memory page, it is responsibility of software setting this bit. It brings * out extra page fault penalty to track page access bit. For optimization page * access bit can be set during all page fault flow on these arches. * To be differentiate with macro pte_mkyoung, this macro is used on platforms * where software maintains page access bit. */ #ifndef pte_sw_mkyoung static inline pte_t pte_sw_mkyoung(pte_t pte) { return pte; } #define pte_sw_mkyoung pte_sw_mkyoung #endif #ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { pmd_t old_pmd = *pmdp; set_pmd_at(mm, address, pmdp, pmd_wrprotect(old_pmd)); } #else static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PUDP_SET_WRPROTECT #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void pudp_set_wrprotect(struct mm_struct *mm, unsigned long address, pud_t *pudp) { pud_t old_pud = *pudp; set_pud_at(mm, address, pudp, pud_wrprotect(old_pud)); } #else static inline void pudp_set_wrprotect(struct mm_struct *mm, unsigned long address, pud_t *pudp) { BUILD_BUG(); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ #endif #ifndef pmdp_collapse_flush #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #else static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); return *pmdp; } #define pmdp_collapse_flush pmdp_collapse_flush #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable); #endif #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); #endif #ifndef arch_needs_pgtable_deposit #define arch_needs_pgtable_deposit() (false) #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * This is an implementation of pmdp_establish() that is only suitable for an * architecture that doesn't have hardware dirty/accessed bits. In this case we * can't race with CPU which sets these bits and non-atomic approach is fine. */ static inline pmd_t generic_pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { pmd_t old_pmd = *pmdp; set_pmd_at(vma->vm_mm, address, pmdp, pmd); return old_pmd; } #endif #ifndef __HAVE_ARCH_PMDP_INVALIDATE extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #endif #ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD /* * pmdp_invalidate_ad() invalidates the PMD while changing a transparent * hugepage mapping in the page tables. This function is similar to * pmdp_invalidate(), but should only be used if the access and dirty bits would * not be cleared by the software in the new PMD value. The function ensures * that hardware changes of the access and dirty bits updates would not be lost. * * Doing so can allow in certain architectures to avoid a TLB flush in most * cases. Yet, another TLB flush might be necessary later if the PMD update * itself requires such flush (e.g., if protection was set to be stricter). Yet, * even when a TLB flush is needed because of the update, the caller may be able * to batch these TLB flushing operations, so fewer TLB flush operations are * needed. */ extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #endif #ifndef __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t pte_a, pte_t pte_b) { return pte_val(pte_a) == pte_val(pte_b); } #endif #ifndef __HAVE_ARCH_PTE_UNUSED /* * Some architectures provide facilities to virtualization guests * so that they can flag allocated pages as unused. This allows the * host to transparently reclaim unused pages. This function returns * whether the pte's page is unused. */ static inline int pte_unused(pte_t pte) { return 0; } #endif #ifndef pte_access_permitted #define pte_access_permitted(pte, write) \ (pte_present(pte) && (!(write) || pte_write(pte))) #endif #ifndef pmd_access_permitted #define pmd_access_permitted(pmd, write) \ (pmd_present(pmd) && (!(write) || pmd_write(pmd))) #endif #ifndef pud_access_permitted #define pud_access_permitted(pud, write) \ (pud_present(pud) && (!(write) || pud_write(pud))) #endif #ifndef p4d_access_permitted #define p4d_access_permitted(p4d, write) \ (p4d_present(p4d) && (!(write) || p4d_write(p4d))) #endif #ifndef pgd_access_permitted #define pgd_access_permitted(pgd, write) \ (pgd_present(pgd) && (!(write) || pgd_write(pgd))) #endif #ifndef __HAVE_ARCH_PMD_SAME static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) { return pmd_val(pmd_a) == pmd_val(pmd_b); } #endif #ifndef pud_same static inline int pud_same(pud_t pud_a, pud_t pud_b) { return pud_val(pud_a) == pud_val(pud_b); } #define pud_same pud_same #endif #ifndef __HAVE_ARCH_P4D_SAME static inline int p4d_same(p4d_t p4d_a, p4d_t p4d_b) { return p4d_val(p4d_a) == p4d_val(p4d_b); } #endif #ifndef __HAVE_ARCH_PGD_SAME static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b) { return pgd_val(pgd_a) == pgd_val(pgd_b); } #endif #ifndef __HAVE_ARCH_DO_SWAP_PAGE static inline void arch_do_swap_page_nr(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t pte, pte_t oldpte, int nr) { } #else /* * Some architectures support metadata associated with a page. When a * page is being swapped out, this metadata must be saved so it can be * restored when the page is swapped back in. SPARC M7 and newer * processors support an ADI (Application Data Integrity) tag for the * page as metadata for the page. arch_do_swap_page() can restore this * metadata when a page is swapped back in. */ static inline void arch_do_swap_page_nr(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t pte, pte_t oldpte, int nr) { for (int i = 0; i < nr; i++) { arch_do_swap_page(vma->vm_mm, vma, addr + i * PAGE_SIZE, pte_advance_pfn(pte, i), pte_advance_pfn(oldpte, i)); } } #endif #ifndef __HAVE_ARCH_UNMAP_ONE /* * Some architectures support metadata associated with a page. When a * page is being swapped out, this metadata must be saved so it can be * restored when the page is swapped back in. SPARC M7 and newer * processors support an ADI (Application Data Integrity) tag for the * page as metadata for the page. arch_unmap_one() can save this * metadata on a swap-out of a page. */ static inline int arch_unmap_one(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t orig_pte) { return 0; } #endif /* * Allow architectures to preserve additional metadata associated with * swapped-out pages. The corresponding __HAVE_ARCH_SWAP_* macros and function * prototypes must be defined in the arch-specific asm/pgtable.h file. */ #ifndef __HAVE_ARCH_PREPARE_TO_SWAP static inline int arch_prepare_to_swap(struct folio *folio) { return 0; } #endif #ifndef __HAVE_ARCH_SWAP_INVALIDATE static inline void arch_swap_invalidate_page(int type, pgoff_t offset) { } static inline void arch_swap_invalidate_area(int type) { } #endif #ifndef __HAVE_ARCH_SWAP_RESTORE static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) { } #endif #ifndef __HAVE_ARCH_PGD_OFFSET_GATE #define pgd_offset_gate(mm, addr) pgd_offset(mm, addr) #endif #ifndef __HAVE_ARCH_MOVE_PTE #define move_pte(pte, old_addr, new_addr) (pte) #endif #ifndef pte_accessible # define pte_accessible(mm, pte) ((void)(pte), 1) #endif #ifndef flush_tlb_fix_spurious_fault #define flush_tlb_fix_spurious_fault(vma, address, ptep) flush_tlb_page(vma, address) #endif /* * When walking page tables, get the address of the next boundary, * or the end address of the range if that comes earlier. Although no * vma end wraps to 0, rounded up __boundary may wrap to 0 throughout. */ #define pgd_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #ifndef p4d_addr_end #define p4d_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #endif #ifndef pud_addr_end #define pud_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #endif #ifndef pmd_addr_end #define pmd_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PMD_SIZE) & PMD_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #endif /* * When walking page tables, we usually want to skip any p?d_none entries; * and any p?d_bad entries - reporting the error before resetting to none. * Do the tests inline, but report and clear the bad entry in mm/memory.c. */ void pgd_clear_bad(pgd_t *); #ifndef __PAGETABLE_P4D_FOLDED void p4d_clear_bad(p4d_t *); #else #define p4d_clear_bad(p4d) do { } while (0) #endif #ifndef __PAGETABLE_PUD_FOLDED void pud_clear_bad(pud_t *); #else #define pud_clear_bad(p4d) do { } while (0) #endif void pmd_clear_bad(pmd_t *); static inline int pgd_none_or_clear_bad(pgd_t *pgd) { if (pgd_none(*pgd)) return 1; if (unlikely(pgd_bad(*pgd))) { pgd_clear_bad(pgd); return 1; } return 0; } static inline int p4d_none_or_clear_bad(p4d_t *p4d) { if (p4d_none(*p4d)) return 1; if (unlikely(p4d_bad(*p4d))) { p4d_clear_bad(p4d); return 1; } return 0; } static inline int pud_none_or_clear_bad(pud_t *pud) { if (pud_none(*pud)) return 1; if (unlikely(pud_bad(*pud))) { pud_clear_bad(pud); return 1; } return 0; } static inline int pmd_none_or_clear_bad(pmd_t *pmd) { if (pmd_none(*pmd)) return 1; if (unlikely(pmd_bad(*pmd))) { pmd_clear_bad(pmd); return 1; } return 0; } static inline pte_t __ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { /* * Get the current pte state, but zero it out to make it * non-present, preventing the hardware from asynchronously * updating it. */ return ptep_get_and_clear(vma->vm_mm, addr, ptep); } static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte) { /* * The pte is non-present, so there's no hardware state to * preserve. */ set_pte_at(vma->vm_mm, addr, ptep, pte); } #ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION /* * Start a pte protection read-modify-write transaction, which * protects against asynchronous hardware modifications to the pte. * The intention is not to prevent the hardware from making pte * updates, but to prevent any updates it may make from being lost. * * This does not protect against other software modifications of the * pte; the appropriate pte lock must be held over the transaction. * * Note that this interface is intended to be batchable, meaning that * ptep_modify_prot_commit may not actually update the pte, but merely * queue the update to be done at some later time. The update must be * actually committed before the pte lock is released, however. */ static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return __ptep_modify_prot_start(vma, addr, ptep); } /* * Commit an update to a pte, leaving any hardware-controlled bits in * the PTE unmodified. */ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { __ptep_modify_prot_commit(vma, addr, ptep, pte); } #endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */ #endif /* CONFIG_MMU */ /* * No-op macros that just return the current protection value. Defined here * because these macros can be used even if CONFIG_MMU is not defined. */ #ifndef pgprot_nx #define pgprot_nx(prot) (prot) #endif #ifndef pgprot_noncached #define pgprot_noncached(prot) (prot) #endif #ifndef pgprot_writecombine #define pgprot_writecombine pgprot_noncached #endif #ifndef pgprot_writethrough #define pgprot_writethrough pgprot_noncached #endif #ifndef pgprot_device #define pgprot_device pgprot_noncached #endif #ifndef pgprot_mhp #define pgprot_mhp(prot) (prot) #endif #ifdef CONFIG_MMU #ifndef pgprot_modify #define pgprot_modify pgprot_modify static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) { if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot))) newprot = pgprot_noncached(newprot); if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot))) newprot = pgprot_writecombine(newprot); if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot))) newprot = pgprot_device(newprot); return newprot; } #endif #endif /* CONFIG_MMU */ #ifndef pgprot_encrypted #define pgprot_encrypted(prot) (prot) #endif #ifndef pgprot_decrypted #define pgprot_decrypted(prot) (prot) #endif /* * A facility to provide batching of the reload of page tables and * other process state with the actual context switch code for * paravirtualized guests. By convention, only one of the batched * update (lazy) modes (CPU, MMU) should be active at any given time, * entry should never be nested, and entry and exits should always be * paired. This is for sanity of maintaining and reasoning about the * kernel code. In this case, the exit (end of the context switch) is * in architecture-specific code, and so doesn't need a generic * definition. */ #ifndef __HAVE_ARCH_START_CONTEXT_SWITCH #define arch_start_context_switch(prev) do {} while (0) #endif #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY #ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) { return pmd; } static inline int pmd_swp_soft_dirty(pmd_t pmd) { return 0; } static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) { return pmd; } #endif #else /* !CONFIG_HAVE_ARCH_SOFT_DIRTY */ static inline int pte_soft_dirty(pte_t pte) { return 0; } static inline int pmd_soft_dirty(pmd_t pmd) { return 0; } static inline pte_t pte_mksoft_dirty(pte_t pte) { return pte; } static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) { return pmd; } static inline pte_t pte_clear_soft_dirty(pte_t pte) { return pte; } static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) { return pmd; } static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { return pte; } static inline int pte_swp_soft_dirty(pte_t pte) { return 0; } static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { return pte; } static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) { return pmd; } static inline int pmd_swp_soft_dirty(pmd_t pmd) { return 0; } static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) { return pmd; } #endif #ifndef __HAVE_PFNMAP_TRACKING /* * Interfaces that can be used by architecture code to keep track of * memory type of pfn mappings specified by the remap_pfn_range, * vmf_insert_pfn. */ /* * track_pfn_remap is called when a _new_ pfn mapping is being established * by remap_pfn_range() for physical range indicated by pfn and size. */ static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long addr, unsigned long size) { return 0; } /* * track_pfn_insert is called when a _new_ single pfn is established * by vmf_insert_pfn(). */ static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn) { } /* * track_pfn_copy is called when a VM_PFNMAP VMA is about to get the page * tables copied during copy_page_range(). Will store the pfn to be * passed to untrack_pfn_copy() only if there is something to be untracked. * Callers should initialize the pfn to 0. */ static inline int track_pfn_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long *pfn) { return 0; } /* * untrack_pfn_copy is called when a VM_PFNMAP VMA failed to copy during * copy_page_range(), but after track_pfn_copy() was already called. Can * be called even if track_pfn_copy() did not actually track anything: * handled internally. */ static inline void untrack_pfn_copy(struct vm_area_struct *dst_vma, unsigned long pfn) { } /* * untrack_pfn is called while unmapping a pfnmap for a region. * untrack can be called for a specific region indicated by pfn and size or * can be for the entire vma (in which case pfn, size are zero). */ static inline void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size, bool mm_wr_locked) { } /* * untrack_pfn_clear is called in the following cases on a VM_PFNMAP VMA: * * 1) During mremap() on the src VMA after the page tables were moved. * 2) During fork() on the dst VMA, immediately after duplicating the src VMA. */ static inline void untrack_pfn_clear(struct vm_area_struct *vma) { } #else extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long addr, unsigned long size); extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn); extern int track_pfn_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long *pfn); extern void untrack_pfn_copy(struct vm_area_struct *dst_vma, unsigned long pfn); extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size, bool mm_wr_locked); extern void untrack_pfn_clear(struct vm_area_struct *vma); #endif #ifdef CONFIG_MMU #ifdef __HAVE_COLOR_ZERO_PAGE static inline int is_zero_pfn(unsigned long pfn) { extern unsigned long zero_pfn; unsigned long offset_from_zero_pfn = pfn - zero_pfn; return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT); } #define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr)) #else static inline int is_zero_pfn(unsigned long pfn) { extern unsigned long zero_pfn; return pfn == zero_pfn; } static inline unsigned long my_zero_pfn(unsigned long addr) { extern unsigned long zero_pfn; return zero_pfn; } #endif #else static inline int is_zero_pfn(unsigned long pfn) { return 0; } static inline unsigned long my_zero_pfn(unsigned long addr) { return 0; } #endif /* CONFIG_MMU */ #ifdef CONFIG_MMU #ifndef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_trans_huge(pmd_t pmd) { return 0; } #ifndef pmd_write static inline int pmd_write(pmd_t pmd) { BUG(); return 0; } #endif /* pmd_write */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifndef pud_write static inline int pud_write(pud_t pud) { BUG(); return 0; } #endif /* pud_write */ #if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) static inline int pmd_devmap(pmd_t pmd) { return 0; } static inline int pud_devmap(pud_t pud) { return 0; } static inline int pgd_devmap(pgd_t pgd) { return 0; } #endif #if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \ !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) static inline int pud_trans_huge(pud_t pud) { return 0; } #endif static inline int pud_trans_unstable(pud_t *pud) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) pud_t pudval = READ_ONCE(*pud); if (pud_none(pudval) || pud_trans_huge(pudval) || pud_devmap(pudval)) return 1; if (unlikely(pud_bad(pudval))) { pud_clear_bad(pud); return 1; } #endif return 0; } #ifndef CONFIG_NUMA_BALANCING /* * In an inaccessible (PROT_NONE) VMA, pte_protnone() may indicate "yes". It is * perfectly valid to indicate "no" in that case, which is why our default * implementation defaults to "always no". * * In an accessible VMA, however, pte_protnone() reliably indicates PROT_NONE * page protection due to NUMA hinting. NUMA hinting faults only apply in * accessible VMAs. * * So, to reliably identify PROT_NONE PTEs that require a NUMA hinting fault, * looking at the VMA accessibility is sufficient. */ static inline int pte_protnone(pte_t pte) { return 0; } static inline int pmd_protnone(pmd_t pmd) { return 0; } #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_MMU */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP #ifndef __PAGETABLE_P4D_FOLDED int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot); void p4d_clear_huge(p4d_t *p4d); #else static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } static inline void p4d_clear_huge(p4d_t *p4d) { } #endif /* !__PAGETABLE_P4D_FOLDED */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); int pmd_clear_huge(pmd_t *pmd); int p4d_free_pud_page(p4d_t *p4d, unsigned long addr); int pud_free_pmd_page(pud_t *pud, unsigned long addr); int pmd_free_pte_page(pmd_t *pmd, unsigned long addr); #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) { return 0; } static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { return 0; } static inline void p4d_clear_huge(p4d_t *p4d) { } static inline int pud_clear_huge(pud_t *pud) { return 0; } static inline int pmd_clear_huge(pmd_t *pmd) { return 0; } static inline int p4d_free_pud_page(p4d_t *p4d, unsigned long addr) { return 0; } static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr) { return 0; } static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return 0; } #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * ARCHes with special requirements for evicting THP backing TLB entries can * implement this. Otherwise also, it can help optimize normal TLB flush in * THP regime. Stock flush_tlb_range() typically has optimization to nuke the * entire TLB if flush span is greater than a threshold, which will * likely be true for a single huge page. Thus a single THP flush will * invalidate the entire TLB which is not desirable. * e.g. see arch/arc: flush_pmd_tlb_range */ #define flush_pmd_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #define flush_pud_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #else #define flush_pmd_tlb_range(vma, addr, end) BUILD_BUG() #define flush_pud_tlb_range(vma, addr, end) BUILD_BUG() #endif #endif struct file; int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot); #ifndef CONFIG_X86_ESPFIX64 static inline void init_espfix_bsp(void) { } #endif extern void __init pgtable_cache_init(void); #ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) { return true; } static inline bool arch_has_pfn_modify_check(void) { return false; } #endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */ /* * Architecture PAGE_KERNEL_* fallbacks * * Some architectures don't define certain PAGE_KERNEL_* flags. This is either * because they really don't support them, or the port needs to be updated to * reflect the required functionality. Below are a set of relatively safe * fallbacks, as best effort, which we can count on in lieu of the architectures * not defining them on their own yet. */ #ifndef PAGE_KERNEL_RO # define PAGE_KERNEL_RO PAGE_KERNEL #endif #ifndef PAGE_KERNEL_EXEC # define PAGE_KERNEL_EXEC PAGE_KERNEL #endif /* * Page Table Modification bits for pgtbl_mod_mask. * * These are used by the p?d_alloc_track*() set of functions an in the generic * vmalloc/ioremap code to track at which page-table levels entries have been * modified. Based on that the code can better decide when vmalloc and ioremap * mapping changes need to be synchronized to other page-tables in the system. */ #define __PGTBL_PGD_MODIFIED 0 #define __PGTBL_P4D_MODIFIED 1 #define __PGTBL_PUD_MODIFIED 2 #define __PGTBL_PMD_MODIFIED 3 #define __PGTBL_PTE_MODIFIED 4 #define PGTBL_PGD_MODIFIED BIT(__PGTBL_PGD_MODIFIED) #define PGTBL_P4D_MODIFIED BIT(__PGTBL_P4D_MODIFIED) #define PGTBL_PUD_MODIFIED BIT(__PGTBL_PUD_MODIFIED) #define PGTBL_PMD_MODIFIED BIT(__PGTBL_PMD_MODIFIED) #define PGTBL_PTE_MODIFIED BIT(__PGTBL_PTE_MODIFIED) /* Page-Table Modification Mask */ typedef unsigned int pgtbl_mod_mask; #endif /* !__ASSEMBLY__ */ #if !defined(MAX_POSSIBLE_PHYSMEM_BITS) && !defined(CONFIG_64BIT) #ifdef CONFIG_PHYS_ADDR_T_64BIT /* * ZSMALLOC needs to know the highest PFN on 32-bit architectures * with physical address space extension, but falls back to * BITS_PER_LONG otherwise. */ #error Missing MAX_POSSIBLE_PHYSMEM_BITS definition #else #define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif #endif #ifndef has_transparent_hugepage #define has_transparent_hugepage() IS_BUILTIN(CONFIG_TRANSPARENT_HUGEPAGE) #endif #ifndef has_transparent_pud_hugepage #define has_transparent_pud_hugepage() IS_BUILTIN(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) #endif /* * On some architectures it depends on the mm if the p4d/pud or pmd * layer of the page table hierarchy is folded or not. */ #ifndef mm_p4d_folded #define mm_p4d_folded(mm) __is_defined(__PAGETABLE_P4D_FOLDED) #endif #ifndef mm_pud_folded #define mm_pud_folded(mm) __is_defined(__PAGETABLE_PUD_FOLDED) #endif #ifndef mm_pmd_folded #define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) #endif #ifndef p4d_offset_lockless #define p4d_offset_lockless(pgdp, pgd, address) p4d_offset(&(pgd), address) #endif #ifndef pud_offset_lockless #define pud_offset_lockless(p4dp, p4d, address) pud_offset(&(p4d), address) #endif #ifndef pmd_offset_lockless #define pmd_offset_lockless(pudp, pud, address) pmd_offset(&(pud), address) #endif /* * pXd_leaf() is the API to check whether a pgtable entry is a huge page * mapping. It should work globally across all archs, without any * dependency on CONFIG_* options. For architectures that do not support * huge mappings on specific levels, below fallbacks will be used. * * A leaf pgtable entry should always imply the following: * * - It is a "present" entry. IOW, before using this API, please check it * with pXd_present() first. NOTE: it may not always mean the "present * bit" is set. For example, PROT_NONE entries are always "present". * * - It should _never_ be a swap entry of any type. Above "present" check * should have guarded this, but let's be crystal clear on this. * * - It should contain a huge PFN, which points to a huge page larger than * PAGE_SIZE of the platform. The PFN format isn't important here. * * - It should cover all kinds of huge mappings (e.g., pXd_trans_huge(), * pXd_devmap(), or hugetlb mappings). */ #ifndef pgd_leaf #define pgd_leaf(x) false #endif #ifndef p4d_leaf #define p4d_leaf(x) false #endif #ifndef pud_leaf #define pud_leaf(x) false #endif #ifndef pmd_leaf #define pmd_leaf(x) false #endif #ifndef pgd_leaf_size #define pgd_leaf_size(x) (1ULL << PGDIR_SHIFT) #endif #ifndef p4d_leaf_size #define p4d_leaf_size(x) P4D_SIZE #endif #ifndef pud_leaf_size #define pud_leaf_size(x) PUD_SIZE #endif #ifndef pmd_leaf_size #define pmd_leaf_size(x) PMD_SIZE #endif #ifndef __pte_leaf_size #ifndef pte_leaf_size #define pte_leaf_size(x) PAGE_SIZE #endif #define __pte_leaf_size(x,y) pte_leaf_size(y) #endif /* * We always define pmd_pfn for all archs as it's used in lots of generic * code. Now it happens too for pud_pfn (and can happen for larger * mappings too in the future; we're not there yet). Instead of defining * it for all archs (like pmd_pfn), provide a fallback. * * Note that returning 0 here means any arch that didn't define this can * get severely wrong when it hits a real pud leaf. It's arch's * responsibility to properly define it when a huge pud is possible. */ #ifndef pud_pfn #define pud_pfn(x) 0 #endif /* * Some architectures have MMUs that are configurable or selectable at boot * time. These lead to variable PTRS_PER_x. For statically allocated arrays it * helps to have a static maximum value. */ #ifndef MAX_PTRS_PER_PTE #define MAX_PTRS_PER_PTE PTRS_PER_PTE #endif #ifndef MAX_PTRS_PER_PMD #define MAX_PTRS_PER_PMD PTRS_PER_PMD #endif #ifndef MAX_PTRS_PER_PUD #define MAX_PTRS_PER_PUD PTRS_PER_PUD #endif #ifndef MAX_PTRS_PER_P4D #define MAX_PTRS_PER_P4D PTRS_PER_P4D #endif #ifndef pte_pgprot #define pte_pgprot(x) ((pgprot_t) {0}) #endif #ifndef pmd_pgprot #define pmd_pgprot(x) ((pgprot_t) {0}) #endif #ifndef pud_pgprot #define pud_pgprot(x) ((pgprot_t) {0}) #endif /* description of effects of mapping type and prot in current implementation. * this is due to the limited x86 page protection hardware. The expected * behavior is in parens: * * map_type prot * PROT_NONE PROT_READ PROT_WRITE PROT_EXEC * MAP_SHARED r: (no) no r: (yes) yes r: (no) yes r: (no) yes * w: (no) no w: (no) no w: (yes) yes w: (no) no * x: (no) no x: (no) yes x: (no) yes x: (yes) yes * * MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes * w: (no) no w: (no) no w: (copy) copy w: (no) no * x: (no) no x: (no) yes x: (no) yes x: (yes) yes * * On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and * MAP_PRIVATE (with Enhanced PAN supported): * r: (no) no * w: (no) no * x: (yes) yes */ #define DECLARE_VM_GET_PAGE_PROT \ pgprot_t vm_get_page_prot(unsigned long vm_flags) \ { \ return protection_map[vm_flags & \ (VM_READ | VM_WRITE | VM_EXEC | VM_SHARED)]; \ } \ EXPORT_SYMBOL(vm_get_page_prot); #endif /* _LINUX_PGTABLE_H */ |
| 127 30 22 31 3 20 8 30 29 11 11 14 1 12 13 13 2 2 16 18 18 5 5 6 6 2 2 5 6 6 6 6 6 2 2 1 1 2 2 2 2 2 2 2 2 2 2 10 9 10 6 2 3 2 4 1 7 8 3 5 10 6 3 3 6 1 5 5 1 4 1 2 2 1 24 23 3 1 8 3 5 5 8 8 5 4 9 7 2 6 6 6 5 1 1 1 1 1 10 12 14 9 4 3 1 2 1 1 1 2 2 8 50 1 43 5 8 5 3 51 67 1 1224 1157 68 68 166 31 135 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/ipc/sem.c * Copyright (C) 1992 Krishna Balasubramanian * Copyright (C) 1995 Eric Schenk, Bruno Haible * * /proc/sysvipc/sem support (c) 1999 Dragos Acostachioaie <dragos@iname.com> * * SMP-threaded, sysctl's added * (c) 1999 Manfred Spraul <manfred@colorfullife.com> * Enforced range limit on SEM_UNDO * (c) 2001 Red Hat Inc * Lockless wakeup * (c) 2003 Manfred Spraul <manfred@colorfullife.com> * (c) 2016 Davidlohr Bueso <dave@stgolabs.net> * Further wakeup optimizations, documentation * (c) 2010 Manfred Spraul <manfred@colorfullife.com> * * support for audit of ipc object properties and permission changes * Dustin Kirkland <dustin.kirkland@us.ibm.com> * * namespaces support * OpenVZ, SWsoft Inc. * Pavel Emelianov <xemul@openvz.org> * * Implementation notes: (May 2010) * This file implements System V semaphores. * * User space visible behavior: * - FIFO ordering for semop() operations (just FIFO, not starvation * protection) * - multiple semaphore operations that alter the same semaphore in * one semop() are handled. * - sem_ctime (time of last semctl()) is updated in the IPC_SET, SETVAL and * SETALL calls. * - two Linux specific semctl() commands: SEM_STAT, SEM_INFO. * - undo adjustments at process exit are limited to 0..SEMVMX. * - namespace are supported. * - SEMMSL, SEMMNS, SEMOPM and SEMMNI can be configured at runtime by writing * to /proc/sys/kernel/sem. * - statistics about the usage are reported in /proc/sysvipc/sem. * * Internals: * - scalability: * - all global variables are read-mostly. * - semop() calls and semctl(RMID) are synchronized by RCU. * - most operations do write operations (actually: spin_lock calls) to * the per-semaphore array structure. * Thus: Perfect SMP scaling between independent semaphore arrays. * If multiple semaphores in one array are used, then cache line * trashing on the semaphore array spinlock will limit the scaling. * - semncnt and semzcnt are calculated on demand in count_semcnt() * - the task that performs a successful semop() scans the list of all * sleeping tasks and completes any pending operations that can be fulfilled. * Semaphores are actively given to waiting tasks (necessary for FIFO). * (see update_queue()) * - To improve the scalability, the actual wake-up calls are performed after * dropping all locks. (see wake_up_sem_queue_prepare()) * - All work is done by the waker, the woken up task does not have to do * anything - not even acquiring a lock or dropping a refcount. * - A woken up task may not even touch the semaphore array anymore, it may * have been destroyed already by a semctl(RMID). * - UNDO values are stored in an array (one per process and per * semaphore array, lazily allocated). For backwards compatibility, multiple * modes for the UNDO variables are supported (per process, per thread) * (see copy_semundo, CLONE_SYSVSEM) * - There are two lists of the pending operations: a per-array list * and per-semaphore list (stored in the array). This allows to achieve FIFO * ordering without always scanning all pending operations. * The worst-case behavior is nevertheless O(N^2) for N wakeups. */ #include <linux/compat.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/time.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/audit.h> #include <linux/capability.h> #include <linux/seq_file.h> #include <linux/rwsem.h> #include <linux/nsproxy.h> #include <linux/ipc_namespace.h> #include <linux/sched/wake_q.h> #include <linux/nospec.h> #include <linux/rhashtable.h> #include <linux/uaccess.h> #include "util.h" /* One semaphore structure for each semaphore in the system. */ struct sem { int semval; /* current value */ /* * PID of the process that last modified the semaphore. For * Linux, specifically these are: * - semop * - semctl, via SETVAL and SETALL. * - at task exit when performing undo adjustments (see exit_sem). */ struct pid *sempid; spinlock_t lock; /* spinlock for fine-grained semtimedop */ struct list_head pending_alter; /* pending single-sop operations */ /* that alter the semaphore */ struct list_head pending_const; /* pending single-sop operations */ /* that do not alter the semaphore*/ time64_t sem_otime; /* candidate for sem_otime */ } ____cacheline_aligned_in_smp; /* One sem_array data structure for each set of semaphores in the system. */ struct sem_array { struct kern_ipc_perm sem_perm; /* permissions .. see ipc.h */ time64_t sem_ctime; /* create/last semctl() time */ struct list_head pending_alter; /* pending operations */ /* that alter the array */ struct list_head pending_const; /* pending complex operations */ /* that do not alter semvals */ struct list_head list_id; /* undo requests on this array */ int sem_nsems; /* no. of semaphores in array */ int complex_count; /* pending complex operations */ unsigned int use_global_lock;/* >0: global lock required */ struct sem sems[]; } __randomize_layout; /* One queue for each sleeping process in the system. */ struct sem_queue { struct list_head list; /* queue of pending operations */ struct task_struct *sleeper; /* this process */ struct sem_undo *undo; /* undo structure */ struct pid *pid; /* process id of requesting process */ int status; /* completion status of operation */ struct sembuf *sops; /* array of pending operations */ struct sembuf *blocking; /* the operation that blocked */ int nsops; /* number of operations */ bool alter; /* does *sops alter the array? */ bool dupsop; /* sops on more than one sem_num */ }; /* Each task has a list of undo requests. They are executed automatically * when the process exits. */ struct sem_undo { struct list_head list_proc; /* per-process list: * * all undos from one process * rcu protected */ struct rcu_head rcu; /* rcu struct for sem_undo */ struct sem_undo_list *ulp; /* back ptr to sem_undo_list */ struct list_head list_id; /* per semaphore array list: * all undos for one array */ int semid; /* semaphore set identifier */ short semadj[]; /* array of adjustments */ /* one per semaphore */ }; /* sem_undo_list controls shared access to the list of sem_undo structures * that may be shared among all a CLONE_SYSVSEM task group. */ struct sem_undo_list { refcount_t refcnt; spinlock_t lock; struct list_head list_proc; }; #define sem_ids(ns) ((ns)->ids[IPC_SEM_IDS]) static int newary(struct ipc_namespace *, struct ipc_params *); static void freeary(struct ipc_namespace *, struct kern_ipc_perm *); #ifdef CONFIG_PROC_FS static int sysvipc_sem_proc_show(struct seq_file *s, void *it); #endif #define SEMMSL_FAST 256 /* 512 bytes on stack */ #define SEMOPM_FAST 64 /* ~ 372 bytes on stack */ /* * Switching from the mode suitable for simple ops * to the mode for complex ops is costly. Therefore: * use some hysteresis */ #define USE_GLOBAL_LOCK_HYSTERESIS 10 /* * Locking: * a) global sem_lock() for read/write * sem_undo.id_next, * sem_array.complex_count, * sem_array.pending{_alter,_const}, * sem_array.sem_undo * * b) global or semaphore sem_lock() for read/write: * sem_array.sems[i].pending_{const,alter}: * * c) special: * sem_undo_list.list_proc: * * undo_list->lock for write * * rcu for read * use_global_lock: * * global sem_lock() for write * * either local or global sem_lock() for read. * * Memory ordering: * Most ordering is enforced by using spin_lock() and spin_unlock(). * * Exceptions: * 1) use_global_lock: (SEM_BARRIER_1) * Setting it from non-zero to 0 is a RELEASE, this is ensured by * using smp_store_release(): Immediately after setting it to 0, * a simple op can start. * Testing if it is non-zero is an ACQUIRE, this is ensured by using * smp_load_acquire(). * Setting it from 0 to non-zero must be ordered with regards to * this smp_load_acquire(), this is guaranteed because the smp_load_acquire() * is inside a spin_lock() and after a write from 0 to non-zero a * spin_lock()+spin_unlock() is done. * To prevent the compiler/cpu temporarily writing 0 to use_global_lock, * READ_ONCE()/WRITE_ONCE() is used. * * 2) queue.status: (SEM_BARRIER_2) * Initialization is done while holding sem_lock(), so no further barrier is * required. * Setting it to a result code is a RELEASE, this is ensured by both a * smp_store_release() (for case a) and while holding sem_lock() * (for case b). * The ACQUIRE when reading the result code without holding sem_lock() is * achieved by using READ_ONCE() + smp_acquire__after_ctrl_dep(). * (case a above). * Reading the result code while holding sem_lock() needs no further barriers, * the locks inside sem_lock() enforce ordering (case b above) * * 3) current->state: * current->state is set to TASK_INTERRUPTIBLE while holding sem_lock(). * The wakeup is handled using the wake_q infrastructure. wake_q wakeups may * happen immediately after calling wake_q_add. As wake_q_add_safe() is called * when holding sem_lock(), no further barriers are required. * * See also ipc/mqueue.c for more details on the covered races. */ #define sc_semmsl sem_ctls[0] #define sc_semmns sem_ctls[1] #define sc_semopm sem_ctls[2] #define sc_semmni sem_ctls[3] void sem_init_ns(struct ipc_namespace *ns) { ns->sc_semmsl = SEMMSL; ns->sc_semmns = SEMMNS; ns->sc_semopm = SEMOPM; ns->sc_semmni = SEMMNI; ns->used_sems = 0; ipc_init_ids(&ns->ids[IPC_SEM_IDS]); } #ifdef CONFIG_IPC_NS void sem_exit_ns(struct ipc_namespace *ns) { free_ipcs(ns, &sem_ids(ns), freeary); idr_destroy(&ns->ids[IPC_SEM_IDS].ipcs_idr); rhashtable_destroy(&ns->ids[IPC_SEM_IDS].key_ht); } #endif void __init sem_init(void) { sem_init_ns(&init_ipc_ns); ipc_init_proc_interface("sysvipc/sem", " key semid perms nsems uid gid cuid cgid otime ctime\n", IPC_SEM_IDS, sysvipc_sem_proc_show); } /** * unmerge_queues - unmerge queues, if possible. * @sma: semaphore array * * The function unmerges the wait queues if complex_count is 0. * It must be called prior to dropping the global semaphore array lock. */ static void unmerge_queues(struct sem_array *sma) { struct sem_queue *q, *tq; /* complex operations still around? */ if (sma->complex_count) return; /* * We will switch back to simple mode. * Move all pending operation back into the per-semaphore * queues. */ list_for_each_entry_safe(q, tq, &sma->pending_alter, list) { struct sem *curr; curr = &sma->sems[q->sops[0].sem_num]; list_add_tail(&q->list, &curr->pending_alter); } INIT_LIST_HEAD(&sma->pending_alter); } /** * merge_queues - merge single semop queues into global queue * @sma: semaphore array * * This function merges all per-semaphore queues into the global queue. * It is necessary to achieve FIFO ordering for the pending single-sop * operations when a multi-semop operation must sleep. * Only the alter operations must be moved, the const operations can stay. */ static void merge_queues(struct sem_array *sma) { int i; for (i = 0; i < sma->sem_nsems; i++) { struct sem *sem = &sma->sems[i]; list_splice_init(&sem->pending_alter, &sma->pending_alter); } } static void sem_rcu_free(struct rcu_head *head) { struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu); struct sem_array *sma = container_of(p, struct sem_array, sem_perm); security_sem_free(&sma->sem_perm); kvfree(sma); } /* * Enter the mode suitable for non-simple operations: * Caller must own sem_perm.lock. */ static void complexmode_enter(struct sem_array *sma) { int i; struct sem *sem; if (sma->use_global_lock > 0) { /* * We are already in global lock mode. * Nothing to do, just reset the * counter until we return to simple mode. */ WRITE_ONCE(sma->use_global_lock, USE_GLOBAL_LOCK_HYSTERESIS); return; } WRITE_ONCE(sma->use_global_lock, USE_GLOBAL_LOCK_HYSTERESIS); for (i = 0; i < sma->sem_nsems; i++) { sem = &sma->sems[i]; spin_lock(&sem->lock); spin_unlock(&sem->lock); } } /* * Try to leave the mode that disallows simple operations: * Caller must own sem_perm.lock. */ static void complexmode_tryleave(struct sem_array *sma) { if (sma->complex_count) { /* Complex ops are sleeping. * We must stay in complex mode */ return; } if (sma->use_global_lock == 1) { /* See SEM_BARRIER_1 for purpose/pairing */ smp_store_release(&sma->use_global_lock, 0); } else { WRITE_ONCE(sma->use_global_lock, sma->use_global_lock-1); } } #define SEM_GLOBAL_LOCK (-1) /* * If the request contains only one semaphore operation, and there are * no complex transactions pending, lock only the semaphore involved. * Otherwise, lock the entire semaphore array, since we either have * multiple semaphores in our own semops, or we need to look at * semaphores from other pending complex operations. */ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, int nsops) { struct sem *sem; int idx; if (nsops != 1) { /* Complex operation - acquire a full lock */ ipc_lock_object(&sma->sem_perm); /* Prevent parallel simple ops */ complexmode_enter(sma); return SEM_GLOBAL_LOCK; } /* * Only one semaphore affected - try to optimize locking. * Optimized locking is possible if no complex operation * is either enqueued or processed right now. * * Both facts are tracked by use_global_mode. */ idx = array_index_nospec(sops->sem_num, sma->sem_nsems); sem = &sma->sems[idx]; /* * Initial check for use_global_lock. Just an optimization, * no locking, no memory barrier. */ if (!READ_ONCE(sma->use_global_lock)) { /* * It appears that no complex operation is around. * Acquire the per-semaphore lock. */ spin_lock(&sem->lock); /* see SEM_BARRIER_1 for purpose/pairing */ if (!smp_load_acquire(&sma->use_global_lock)) { /* fast path successful! */ return sops->sem_num; } spin_unlock(&sem->lock); } /* slow path: acquire the full lock */ ipc_lock_object(&sma->sem_perm); if (sma->use_global_lock == 0) { /* * The use_global_lock mode ended while we waited for * sma->sem_perm.lock. Thus we must switch to locking * with sem->lock. * Unlike in the fast path, there is no need to recheck * sma->use_global_lock after we have acquired sem->lock: * We own sma->sem_perm.lock, thus use_global_lock cannot * change. */ spin_lock(&sem->lock); ipc_unlock_object(&sma->sem_perm); return sops->sem_num; } else { /* * Not a false alarm, thus continue to use the global lock * mode. No need for complexmode_enter(), this was done by * the caller that has set use_global_mode to non-zero. */ return SEM_GLOBAL_LOCK; } } static inline void sem_unlock(struct sem_array *sma, int locknum) { if (locknum == SEM_GLOBAL_LOCK) { unmerge_queues(sma); complexmode_tryleave(sma); ipc_unlock_object(&sma->sem_perm); } else { struct sem *sem = &sma->sems[locknum]; spin_unlock(&sem->lock); } } /* * sem_lock_(check_) routines are called in the paths where the rwsem * is not held. * * The caller holds the RCU read lock. */ static inline struct sem_array *sem_obtain_object(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&sem_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct sem_array, sem_perm); } static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&sem_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct sem_array, sem_perm); } static inline void sem_lock_and_putref(struct sem_array *sma) { sem_lock(sma, NULL, -1); ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); } static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) { ipc_rmid(&sem_ids(ns), &s->sem_perm); } static struct sem_array *sem_alloc(size_t nsems) { struct sem_array *sma; if (nsems > (INT_MAX - sizeof(*sma)) / sizeof(sma->sems[0])) return NULL; sma = kvzalloc(struct_size(sma, sems, nsems), GFP_KERNEL_ACCOUNT); if (unlikely(!sma)) return NULL; return sma; } /** * newary - Create a new semaphore set * @ns: namespace * @params: ptr to the structure that contains key, semflg and nsems * * Called with sem_ids.rwsem held (as a writer) */ static int newary(struct ipc_namespace *ns, struct ipc_params *params) { int retval; struct sem_array *sma; key_t key = params->key; int nsems = params->u.nsems; int semflg = params->flg; int i; if (!nsems) return -EINVAL; if (ns->used_sems + nsems > ns->sc_semmns) return -ENOSPC; sma = sem_alloc(nsems); if (!sma) return -ENOMEM; sma->sem_perm.mode = (semflg & S_IRWXUGO); sma->sem_perm.key = key; sma->sem_perm.security = NULL; retval = security_sem_alloc(&sma->sem_perm); if (retval) { kvfree(sma); return retval; } for (i = 0; i < nsems; i++) { INIT_LIST_HEAD(&sma->sems[i].pending_alter); INIT_LIST_HEAD(&sma->sems[i].pending_const); spin_lock_init(&sma->sems[i].lock); } sma->complex_count = 0; sma->use_global_lock = USE_GLOBAL_LOCK_HYSTERESIS; INIT_LIST_HEAD(&sma->pending_alter); INIT_LIST_HEAD(&sma->pending_const); INIT_LIST_HEAD(&sma->list_id); sma->sem_nsems = nsems; sma->sem_ctime = ktime_get_real_seconds(); /* ipc_addid() locks sma upon success. */ retval = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni); if (retval < 0) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return retval; } ns->used_sems += nsems; sem_unlock(sma, -1); rcu_read_unlock(); return sma->sem_perm.id; } /* * Called with sem_ids.rwsem and ipcp locked. */ static int sem_more_checks(struct kern_ipc_perm *ipcp, struct ipc_params *params) { struct sem_array *sma; sma = container_of(ipcp, struct sem_array, sem_perm); if (params->u.nsems > sma->sem_nsems) return -EINVAL; return 0; } long ksys_semget(key_t key, int nsems, int semflg) { struct ipc_namespace *ns; static const struct ipc_ops sem_ops = { .getnew = newary, .associate = security_sem_associate, .more_checks = sem_more_checks, }; struct ipc_params sem_params; ns = current->nsproxy->ipc_ns; if (nsems < 0 || nsems > ns->sc_semmsl) return -EINVAL; sem_params.key = key; sem_params.flg = semflg; sem_params.u.nsems = nsems; return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params); } SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg) { return ksys_semget(key, nsems, semflg); } /** * perform_atomic_semop[_slow] - Attempt to perform semaphore * operations on a given array. * @sma: semaphore array * @q: struct sem_queue that describes the operation * * Caller blocking are as follows, based the value * indicated by the semaphore operation (sem_op): * * (1) >0 never blocks. * (2) 0 (wait-for-zero operation): semval is non-zero. * (3) <0 attempting to decrement semval to a value smaller than zero. * * Returns 0 if the operation was possible. * Returns 1 if the operation is impossible, the caller must sleep. * Returns <0 for error codes. */ static int perform_atomic_semop_slow(struct sem_array *sma, struct sem_queue *q) { int result, sem_op, nsops; struct pid *pid; struct sembuf *sop; struct sem *curr; struct sembuf *sops; struct sem_undo *un; sops = q->sops; nsops = q->nsops; un = q->undo; for (sop = sops; sop < sops + nsops; sop++) { int idx = array_index_nospec(sop->sem_num, sma->sem_nsems); curr = &sma->sems[idx]; sem_op = sop->sem_op; result = curr->semval; if (!sem_op && result) goto would_block; result += sem_op; if (result < 0) goto would_block; if (result > SEMVMX) goto out_of_range; if (sop->sem_flg & SEM_UNDO) { int undo = un->semadj[sop->sem_num] - sem_op; /* Exceeding the undo range is an error. */ if (undo < (-SEMAEM - 1) || undo > SEMAEM) goto out_of_range; un->semadj[sop->sem_num] = undo; } curr->semval = result; } sop--; pid = q->pid; while (sop >= sops) { ipc_update_pid(&sma->sems[sop->sem_num].sempid, pid); sop--; } return 0; out_of_range: result = -ERANGE; goto undo; would_block: q->blocking = sop; if (sop->sem_flg & IPC_NOWAIT) result = -EAGAIN; else result = 1; undo: sop--; while (sop >= sops) { sem_op = sop->sem_op; sma->sems[sop->sem_num].semval -= sem_op; if (sop->sem_flg & SEM_UNDO) un->semadj[sop->sem_num] += sem_op; sop--; } return result; } static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q) { int result, sem_op, nsops; struct sembuf *sop; struct sem *curr; struct sembuf *sops; struct sem_undo *un; sops = q->sops; nsops = q->nsops; un = q->undo; if (unlikely(q->dupsop)) return perform_atomic_semop_slow(sma, q); /* * We scan the semaphore set twice, first to ensure that the entire * operation can succeed, therefore avoiding any pointless writes * to shared memory and having to undo such changes in order to block * until the operations can go through. */ for (sop = sops; sop < sops + nsops; sop++) { int idx = array_index_nospec(sop->sem_num, sma->sem_nsems); curr = &sma->sems[idx]; sem_op = sop->sem_op; result = curr->semval; if (!sem_op && result) goto would_block; /* wait-for-zero */ result += sem_op; if (result < 0) goto would_block; if (result > SEMVMX) return -ERANGE; if (sop->sem_flg & SEM_UNDO) { int undo = un->semadj[sop->sem_num] - sem_op; /* Exceeding the undo range is an error. */ if (undo < (-SEMAEM - 1) || undo > SEMAEM) return -ERANGE; } } for (sop = sops; sop < sops + nsops; sop++) { curr = &sma->sems[sop->sem_num]; sem_op = sop->sem_op; if (sop->sem_flg & SEM_UNDO) { int undo = un->semadj[sop->sem_num] - sem_op; un->semadj[sop->sem_num] = undo; } curr->semval += sem_op; ipc_update_pid(&curr->sempid, q->pid); } return 0; would_block: q->blocking = sop; return sop->sem_flg & IPC_NOWAIT ? -EAGAIN : 1; } static inline void wake_up_sem_queue_prepare(struct sem_queue *q, int error, struct wake_q_head *wake_q) { struct task_struct *sleeper; sleeper = get_task_struct(q->sleeper); /* see SEM_BARRIER_2 for purpose/pairing */ smp_store_release(&q->status, error); wake_q_add_safe(wake_q, sleeper); } static void unlink_queue(struct sem_array *sma, struct sem_queue *q) { list_del(&q->list); if (q->nsops > 1) sma->complex_count--; } /** check_restart(sma, q) * @sma: semaphore array * @q: the operation that just completed * * update_queue is O(N^2) when it restarts scanning the whole queue of * waiting operations. Therefore this function checks if the restart is * really necessary. It is called after a previously waiting operation * modified the array. * Note that wait-for-zero operations are handled without restart. */ static inline int check_restart(struct sem_array *sma, struct sem_queue *q) { /* pending complex alter operations are too difficult to analyse */ if (!list_empty(&sma->pending_alter)) return 1; /* we were a sleeping complex operation. Too difficult */ if (q->nsops > 1) return 1; /* It is impossible that someone waits for the new value: * - complex operations always restart. * - wait-for-zero are handled separately. * - q is a previously sleeping simple operation that * altered the array. It must be a decrement, because * simple increments never sleep. * - If there are older (higher priority) decrements * in the queue, then they have observed the original * semval value and couldn't proceed. The operation * decremented to value - thus they won't proceed either. */ return 0; } /** * wake_const_ops - wake up non-alter tasks * @sma: semaphore array. * @semnum: semaphore that was modified. * @wake_q: lockless wake-queue head. * * wake_const_ops must be called after a semaphore in a semaphore array * was set to 0. If complex const operations are pending, wake_const_ops must * be called with semnum = -1, as well as with the number of each modified * semaphore. * The tasks that must be woken up are added to @wake_q. The return code * is stored in q->pid. * The function returns 1 if at least one operation was completed successfully. */ static int wake_const_ops(struct sem_array *sma, int semnum, struct wake_q_head *wake_q) { struct sem_queue *q, *tmp; struct list_head *pending_list; int semop_completed = 0; if (semnum == -1) pending_list = &sma->pending_const; else pending_list = &sma->sems[semnum].pending_const; list_for_each_entry_safe(q, tmp, pending_list, list) { int error = perform_atomic_semop(sma, q); if (error > 0) continue; /* operation completed, remove from queue & wakeup */ unlink_queue(sma, q); wake_up_sem_queue_prepare(q, error, wake_q); if (error == 0) semop_completed = 1; } return semop_completed; } /** * do_smart_wakeup_zero - wakeup all wait for zero tasks * @sma: semaphore array * @sops: operations that were performed * @nsops: number of operations * @wake_q: lockless wake-queue head * * Checks all required queue for wait-for-zero operations, based * on the actual changes that were performed on the semaphore array. * The function returns 1 if at least one operation was completed successfully. */ static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops, int nsops, struct wake_q_head *wake_q) { int i; int semop_completed = 0; int got_zero = 0; /* first: the per-semaphore queues, if known */ if (sops) { for (i = 0; i < nsops; i++) { int num = sops[i].sem_num; if (sma->sems[num].semval == 0) { got_zero = 1; semop_completed |= wake_const_ops(sma, num, wake_q); } } } else { /* * No sops means modified semaphores not known. * Assume all were changed. */ for (i = 0; i < sma->sem_nsems; i++) { if (sma->sems[i].semval == 0) { got_zero = 1; semop_completed |= wake_const_ops(sma, i, wake_q); } } } /* * If one of the modified semaphores got 0, * then check the global queue, too. */ if (got_zero) semop_completed |= wake_const_ops(sma, -1, wake_q); return semop_completed; } /** * update_queue - look for tasks that can be completed. * @sma: semaphore array. * @semnum: semaphore that was modified. * @wake_q: lockless wake-queue head. * * update_queue must be called after a semaphore in a semaphore array * was modified. If multiple semaphores were modified, update_queue must * be called with semnum = -1, as well as with the number of each modified * semaphore. * The tasks that must be woken up are added to @wake_q. The return code * is stored in q->pid. * The function internally checks if const operations can now succeed. * * The function return 1 if at least one semop was completed successfully. */ static int update_queue(struct sem_array *sma, int semnum, struct wake_q_head *wake_q) { struct sem_queue *q, *tmp; struct list_head *pending_list; int semop_completed = 0; if (semnum == -1) pending_list = &sma->pending_alter; else pending_list = &sma->sems[semnum].pending_alter; again: list_for_each_entry_safe(q, tmp, pending_list, list) { int error, restart; /* If we are scanning the single sop, per-semaphore list of * one semaphore and that semaphore is 0, then it is not * necessary to scan further: simple increments * that affect only one entry succeed immediately and cannot * be in the per semaphore pending queue, and decrements * cannot be successful if the value is already 0. */ if (semnum != -1 && sma->sems[semnum].semval == 0) break; error = perform_atomic_semop(sma, q); /* Does q->sleeper still need to sleep? */ if (error > 0) continue; unlink_queue(sma, q); if (error) { restart = 0; } else { semop_completed = 1; do_smart_wakeup_zero(sma, q->sops, q->nsops, wake_q); restart = check_restart(sma, q); } wake_up_sem_queue_prepare(q, error, wake_q); if (restart) goto again; } return semop_completed; } /** * set_semotime - set sem_otime * @sma: semaphore array * @sops: operations that modified the array, may be NULL * * sem_otime is replicated to avoid cache line trashing. * This function sets one instance to the current time. */ static void set_semotime(struct sem_array *sma, struct sembuf *sops) { if (sops == NULL) { sma->sems[0].sem_otime = ktime_get_real_seconds(); } else { sma->sems[sops[0].sem_num].sem_otime = ktime_get_real_seconds(); } } /** * do_smart_update - optimized update_queue * @sma: semaphore array * @sops: operations that were performed * @nsops: number of operations * @otime: force setting otime * @wake_q: lockless wake-queue head * * do_smart_update() does the required calls to update_queue and wakeup_zero, * based on the actual changes that were performed on the semaphore array. * Note that the function does not do the actual wake-up: the caller is * responsible for calling wake_up_q(). * It is safe to perform this call after dropping all locks. */ static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsops, int otime, struct wake_q_head *wake_q) { int i; otime |= do_smart_wakeup_zero(sma, sops, nsops, wake_q); if (!list_empty(&sma->pending_alter)) { /* semaphore array uses the global queue - just process it. */ otime |= update_queue(sma, -1, wake_q); } else { if (!sops) { /* * No sops, thus the modified semaphores are not * known. Check all. */ for (i = 0; i < sma->sem_nsems; i++) otime |= update_queue(sma, i, wake_q); } else { /* * Check the semaphores that were increased: * - No complex ops, thus all sleeping ops are * decrease. * - if we decreased the value, then any sleeping * semaphore ops won't be able to run: If the * previous value was too small, then the new * value will be too small, too. */ for (i = 0; i < nsops; i++) { if (sops[i].sem_op > 0) { otime |= update_queue(sma, sops[i].sem_num, wake_q); } } } } if (otime) set_semotime(sma, sops); } /* * check_qop: Test if a queued operation sleeps on the semaphore semnum */ static int check_qop(struct sem_array *sma, int semnum, struct sem_queue *q, bool count_zero) { struct sembuf *sop = q->blocking; /* * Linux always (since 0.99.10) reported a task as sleeping on all * semaphores. This violates SUS, therefore it was changed to the * standard compliant behavior. * Give the administrators a chance to notice that an application * might misbehave because it relies on the Linux behavior. */ pr_info_once("semctl(GETNCNT/GETZCNT) is since 3.16 Single Unix Specification compliant.\n" "The task %s (%d) triggered the difference, watch for misbehavior.\n", current->comm, task_pid_nr(current)); if (sop->sem_num != semnum) return 0; if (count_zero && sop->sem_op == 0) return 1; if (!count_zero && sop->sem_op < 0) return 1; return 0; } /* The following counts are associated to each semaphore: * semncnt number of tasks waiting on semval being nonzero * semzcnt number of tasks waiting on semval being zero * * Per definition, a task waits only on the semaphore of the first semop * that cannot proceed, even if additional operation would block, too. */ static int count_semcnt(struct sem_array *sma, ushort semnum, bool count_zero) { struct list_head *l; struct sem_queue *q; int semcnt; semcnt = 0; /* First: check the simple operations. They are easy to evaluate */ if (count_zero) l = &sma->sems[semnum].pending_const; else l = &sma->sems[semnum].pending_alter; list_for_each_entry(q, l, list) { /* all task on a per-semaphore list sleep on exactly * that semaphore */ semcnt++; } /* Then: check the complex operations. */ list_for_each_entry(q, &sma->pending_alter, list) { semcnt += check_qop(sma, semnum, q, count_zero); } if (count_zero) { list_for_each_entry(q, &sma->pending_const, list) { semcnt += check_qop(sma, semnum, q, count_zero); } } return semcnt; } /* Free a semaphore set. freeary() is called with sem_ids.rwsem locked * as a writer and the spinlock for this semaphore set hold. sem_ids.rwsem * remains locked on exit. */ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) { struct sem_undo *un, *tu; struct sem_queue *q, *tq; struct sem_array *sma = container_of(ipcp, struct sem_array, sem_perm); int i; DEFINE_WAKE_Q(wake_q); /* Free the existing undo structures for this semaphore set. */ ipc_assert_locked_object(&sma->sem_perm); list_for_each_entry_safe(un, tu, &sma->list_id, list_id) { list_del(&un->list_id); spin_lock(&un->ulp->lock); un->semid = -1; list_del_rcu(&un->list_proc); spin_unlock(&un->ulp->lock); kvfree_rcu(un, rcu); } /* Wake up all pending processes and let them fail with EIDRM. */ list_for_each_entry_safe(q, tq, &sma->pending_const, list) { unlink_queue(sma, q); wake_up_sem_queue_prepare(q, -EIDRM, &wake_q); } list_for_each_entry_safe(q, tq, &sma->pending_alter, list) { unlink_queue(sma, q); wake_up_sem_queue_prepare(q, -EIDRM, &wake_q); } for (i = 0; i < sma->sem_nsems; i++) { struct sem *sem = &sma->sems[i]; list_for_each_entry_safe(q, tq, &sem->pending_const, list) { unlink_queue(sma, q); wake_up_sem_queue_prepare(q, -EIDRM, &wake_q); } list_for_each_entry_safe(q, tq, &sem->pending_alter, list) { unlink_queue(sma, q); wake_up_sem_queue_prepare(q, -EIDRM, &wake_q); } ipc_update_pid(&sem->sempid, NULL); } /* Remove the semaphore set from the IDR */ sem_rmid(ns, sma); sem_unlock(sma, -1); rcu_read_unlock(); wake_up_q(&wake_q); ns->used_sems -= sma->sem_nsems; ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); } static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version) { switch (version) { case IPC_64: return copy_to_user(buf, in, sizeof(*in)); case IPC_OLD: { struct semid_ds out; memset(&out, 0, sizeof(out)); ipc64_perm_to_ipc_perm(&in->sem_perm, &out.sem_perm); out.sem_otime = in->sem_otime; out.sem_ctime = in->sem_ctime; out.sem_nsems = in->sem_nsems; return copy_to_user(buf, &out, sizeof(out)); } default: return -EINVAL; } } static time64_t get_semotime(struct sem_array *sma) { int i; time64_t res; res = sma->sems[0].sem_otime; for (i = 1; i < sma->sem_nsems; i++) { time64_t to = sma->sems[i].sem_otime; if (to > res) res = to; } return res; } static int semctl_stat(struct ipc_namespace *ns, int semid, int cmd, struct semid64_ds *semid64) { struct sem_array *sma; time64_t semotime; int err; memset(semid64, 0, sizeof(*semid64)); rcu_read_lock(); if (cmd == SEM_STAT || cmd == SEM_STAT_ANY) { sma = sem_obtain_object(ns, semid); if (IS_ERR(sma)) { err = PTR_ERR(sma); goto out_unlock; } } else { /* IPC_STAT */ sma = sem_obtain_object_check(ns, semid); if (IS_ERR(sma)) { err = PTR_ERR(sma); goto out_unlock; } } /* see comment for SHM_STAT_ANY */ if (cmd == SEM_STAT_ANY) audit_ipc_obj(&sma->sem_perm); else { err = -EACCES; if (ipcperms(ns, &sma->sem_perm, S_IRUGO)) goto out_unlock; } err = security_sem_semctl(&sma->sem_perm, cmd); if (err) goto out_unlock; ipc_lock_object(&sma->sem_perm); if (!ipc_valid_object(&sma->sem_perm)) { ipc_unlock_object(&sma->sem_perm); err = -EIDRM; goto out_unlock; } kernel_to_ipc64_perm(&sma->sem_perm, &semid64->sem_perm); semotime = get_semotime(sma); semid64->sem_otime = semotime; semid64->sem_ctime = sma->sem_ctime; #ifndef CONFIG_64BIT semid64->sem_otime_high = semotime >> 32; semid64->sem_ctime_high = sma->sem_ctime >> 32; #endif semid64->sem_nsems = sma->sem_nsems; if (cmd == IPC_STAT) { /* * As defined in SUS: * Return 0 on success */ err = 0; } else { /* * SEM_STAT and SEM_STAT_ANY (both Linux specific) * Return the full id, including the sequence number */ err = sma->sem_perm.id; } ipc_unlock_object(&sma->sem_perm); out_unlock: rcu_read_unlock(); return err; } static int semctl_info(struct ipc_namespace *ns, int semid, int cmd, void __user *p) { struct seminfo seminfo; int max_idx; int err; err = security_sem_semctl(NULL, cmd); if (err) return err; memset(&seminfo, 0, sizeof(seminfo)); seminfo.semmni = ns->sc_semmni; seminfo.semmns = ns->sc_semmns; seminfo.semmsl = ns->sc_semmsl; seminfo.semopm = ns->sc_semopm; seminfo.semvmx = SEMVMX; seminfo.semmnu = SEMMNU; seminfo.semmap = SEMMAP; seminfo.semume = SEMUME; down_read(&sem_ids(ns).rwsem); if (cmd == SEM_INFO) { seminfo.semusz = sem_ids(ns).in_use; seminfo.semaem = ns->used_sems; } else { seminfo.semusz = SEMUSZ; seminfo.semaem = SEMAEM; } max_idx = ipc_get_maxidx(&sem_ids(ns)); up_read(&sem_ids(ns).rwsem); if (copy_to_user(p, &seminfo, sizeof(struct seminfo))) return -EFAULT; return (max_idx < 0) ? 0 : max_idx; } static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum, int val) { struct sem_undo *un; struct sem_array *sma; struct sem *curr; int err; DEFINE_WAKE_Q(wake_q); if (val > SEMVMX || val < 0) return -ERANGE; rcu_read_lock(); sma = sem_obtain_object_check(ns, semid); if (IS_ERR(sma)) { rcu_read_unlock(); return PTR_ERR(sma); } if (semnum < 0 || semnum >= sma->sem_nsems) { rcu_read_unlock(); return -EINVAL; } if (ipcperms(ns, &sma->sem_perm, S_IWUGO)) { rcu_read_unlock(); return -EACCES; } err = security_sem_semctl(&sma->sem_perm, SETVAL); if (err) { rcu_read_unlock(); return -EACCES; } sem_lock(sma, NULL, -1); if (!ipc_valid_object(&sma->sem_perm)) { sem_unlock(sma, -1); rcu_read_unlock(); return -EIDRM; } semnum = array_index_nospec(semnum, sma->sem_nsems); curr = &sma->sems[semnum]; ipc_assert_locked_object(&sma->sem_perm); list_for_each_entry(un, &sma->list_id, list_id) un->semadj[semnum] = 0; curr->semval = val; ipc_update_pid(&curr->sempid, task_tgid(current)); sma->sem_ctime = ktime_get_real_seconds(); /* maybe some queued-up processes were waiting for this */ do_smart_update(sma, NULL, 0, 0, &wake_q); sem_unlock(sma, -1); rcu_read_unlock(); wake_up_q(&wake_q); return 0; } static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, int cmd, void __user *p) { struct sem_array *sma; struct sem *curr; int err, nsems; ushort fast_sem_io[SEMMSL_FAST]; ushort *sem_io = fast_sem_io; DEFINE_WAKE_Q(wake_q); rcu_read_lock(); sma = sem_obtain_object_check(ns, semid); if (IS_ERR(sma)) { rcu_read_unlock(); return PTR_ERR(sma); } nsems = sma->sem_nsems; err = -EACCES; if (ipcperms(ns, &sma->sem_perm, cmd == SETALL ? S_IWUGO : S_IRUGO)) goto out_rcu_wakeup; err = security_sem_semctl(&sma->sem_perm, cmd); if (err) goto out_rcu_wakeup; switch (cmd) { case GETALL: { ushort __user *array = p; int i; sem_lock(sma, NULL, -1); if (!ipc_valid_object(&sma->sem_perm)) { err = -EIDRM; goto out_unlock; } if (nsems > SEMMSL_FAST) { if (!ipc_rcu_getref(&sma->sem_perm)) { err = -EIDRM; goto out_unlock; } sem_unlock(sma, -1); rcu_read_unlock(); sem_io = kvmalloc_array(nsems, sizeof(ushort), GFP_KERNEL); if (sem_io == NULL) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return -ENOMEM; } rcu_read_lock(); sem_lock_and_putref(sma); if (!ipc_valid_object(&sma->sem_perm)) { err = -EIDRM; goto out_unlock; } } for (i = 0; i < sma->sem_nsems; i++) sem_io[i] = sma->sems[i].semval; sem_unlock(sma, -1); rcu_read_unlock(); err = 0; if (copy_to_user(array, sem_io, nsems*sizeof(ushort))) err = -EFAULT; goto out_free; } case SETALL: { int i; struct sem_undo *un; if (!ipc_rcu_getref(&sma->sem_perm)) { err = -EIDRM; goto out_rcu_wakeup; } rcu_read_unlock(); if (nsems > SEMMSL_FAST) { sem_io = kvmalloc_array(nsems, sizeof(ushort), GFP_KERNEL); if (sem_io == NULL) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return -ENOMEM; } } if (copy_from_user(sem_io, p, nsems*sizeof(ushort))) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); err = -EFAULT; goto out_free; } for (i = 0; i < nsems; i++) { if (sem_io[i] > SEMVMX) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); err = -ERANGE; goto out_free; } } rcu_read_lock(); sem_lock_and_putref(sma); if (!ipc_valid_object(&sma->sem_perm)) { err = -EIDRM; goto out_unlock; } for (i = 0; i < nsems; i++) { sma->sems[i].semval = sem_io[i]; ipc_update_pid(&sma->sems[i].sempid, task_tgid(current)); } ipc_assert_locked_object(&sma->sem_perm); list_for_each_entry(un, &sma->list_id, list_id) { for (i = 0; i < nsems; i++) un->semadj[i] = 0; } sma->sem_ctime = ktime_get_real_seconds(); /* maybe some queued-up processes were waiting for this */ do_smart_update(sma, NULL, 0, 0, &wake_q); err = 0; goto out_unlock; } /* GETVAL, GETPID, GETNCTN, GETZCNT: fall-through */ } err = -EINVAL; if (semnum < 0 || semnum >= nsems) goto out_rcu_wakeup; sem_lock(sma, NULL, -1); if (!ipc_valid_object(&sma->sem_perm)) { err = -EIDRM; goto out_unlock; } semnum = array_index_nospec(semnum, nsems); curr = &sma->sems[semnum]; switch (cmd) { case GETVAL: err = curr->semval; goto out_unlock; case GETPID: err = pid_vnr(curr->sempid); goto out_unlock; case GETNCNT: err = count_semcnt(sma, semnum, 0); goto out_unlock; case GETZCNT: err = count_semcnt(sma, semnum, 1); goto out_unlock; } out_unlock: sem_unlock(sma, -1); out_rcu_wakeup: rcu_read_unlock(); wake_up_q(&wake_q); out_free: if (sem_io != fast_sem_io) kvfree(sem_io); return err; } static inline unsigned long copy_semid_from_user(struct semid64_ds *out, void __user *buf, int version) { switch (version) { case IPC_64: if (copy_from_user(out, buf, sizeof(*out))) return -EFAULT; return 0; case IPC_OLD: { struct semid_ds tbuf_old; if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) return -EFAULT; out->sem_perm.uid = tbuf_old.sem_perm.uid; out->sem_perm.gid = tbuf_old.sem_perm.gid; out->sem_perm.mode = tbuf_old.sem_perm.mode; return 0; } default: return -EINVAL; } } /* * This function handles some semctl commands which require the rwsem * to be held in write mode. * NOTE: no locks must be held, the rwsem is taken inside this function. */ static int semctl_down(struct ipc_namespace *ns, int semid, int cmd, struct semid64_ds *semid64) { struct sem_array *sma; int err; struct kern_ipc_perm *ipcp; down_write(&sem_ids(ns).rwsem); rcu_read_lock(); ipcp = ipcctl_obtain_check(ns, &sem_ids(ns), semid, cmd, &semid64->sem_perm, 0); if (IS_ERR(ipcp)) { err = PTR_ERR(ipcp); goto out_unlock1; } sma = container_of(ipcp, struct sem_array, sem_perm); err = security_sem_semctl(&sma->sem_perm, cmd); if (err) goto out_unlock1; switch (cmd) { case IPC_RMID: sem_lock(sma, NULL, -1); /* freeary unlocks the ipc object and rcu */ freeary(ns, ipcp); goto out_up; case IPC_SET: sem_lock(sma, NULL, -1); err = ipc_update_perm(&semid64->sem_perm, ipcp); if (err) goto out_unlock0; sma->sem_ctime = ktime_get_real_seconds(); break; default: err = -EINVAL; goto out_unlock1; } out_unlock0: sem_unlock(sma, -1); out_unlock1: rcu_read_unlock(); out_up: up_write(&sem_ids(ns).rwsem); return err; } static long ksys_semctl(int semid, int semnum, int cmd, unsigned long arg, int version) { struct ipc_namespace *ns; void __user *p = (void __user *)arg; struct semid64_ds semid64; int err; if (semid < 0) return -EINVAL; ns = current->nsproxy->ipc_ns; switch (cmd) { case IPC_INFO: case SEM_INFO: return semctl_info(ns, semid, cmd, p); case IPC_STAT: case SEM_STAT: case SEM_STAT_ANY: err = semctl_stat(ns, semid, cmd, &semid64); if (err < 0) return err; if (copy_semid_to_user(p, &semid64, version)) err = -EFAULT; return err; case GETALL: case GETVAL: case GETPID: case GETNCNT: case GETZCNT: case SETALL: return semctl_main(ns, semid, semnum, cmd, p); case SETVAL: { int val; #if defined(CONFIG_64BIT) && defined(__BIG_ENDIAN) /* big-endian 64bit */ val = arg >> 32; #else /* 32bit or little-endian 64bit */ val = arg; #endif return semctl_setval(ns, semid, semnum, val); } case IPC_SET: if (copy_semid_from_user(&semid64, p, version)) return -EFAULT; fallthrough; case IPC_RMID: return semctl_down(ns, semid, cmd, &semid64); default: return -EINVAL; } } SYSCALL_DEFINE4(semctl, int, semid, int, semnum, int, cmd, unsigned long, arg) { return ksys_semctl(semid, semnum, cmd, arg, IPC_64); } #ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION long ksys_old_semctl(int semid, int semnum, int cmd, unsigned long arg) { int version = ipc_parse_version(&cmd); return ksys_semctl(semid, semnum, cmd, arg, version); } SYSCALL_DEFINE4(old_semctl, int, semid, int, semnum, int, cmd, unsigned long, arg) { return ksys_old_semctl(semid, semnum, cmd, arg); } #endif #ifdef CONFIG_COMPAT struct compat_semid_ds { struct compat_ipc_perm sem_perm; old_time32_t sem_otime; old_time32_t sem_ctime; compat_uptr_t sem_base; compat_uptr_t sem_pending; compat_uptr_t sem_pending_last; compat_uptr_t undo; unsigned short sem_nsems; }; static int copy_compat_semid_from_user(struct semid64_ds *out, void __user *buf, int version) { memset(out, 0, sizeof(*out)); if (version == IPC_64) { struct compat_semid64_ds __user *p = buf; return get_compat_ipc64_perm(&out->sem_perm, &p->sem_perm); } else { struct compat_semid_ds __user *p = buf; return get_compat_ipc_perm(&out->sem_perm, &p->sem_perm); } } static int copy_compat_semid_to_user(void __user *buf, struct semid64_ds *in, int version) { if (version == IPC_64) { struct compat_semid64_ds v; memset(&v, 0, sizeof(v)); to_compat_ipc64_perm(&v.sem_perm, &in->sem_perm); v.sem_otime = lower_32_bits(in->sem_otime); v.sem_otime_high = upper_32_bits(in->sem_otime); v.sem_ctime = lower_32_bits(in->sem_ctime); v.sem_ctime_high = upper_32_bits(in->sem_ctime); v.sem_nsems = in->sem_nsems; return copy_to_user(buf, &v, sizeof(v)); } else { struct compat_semid_ds v; memset(&v, 0, sizeof(v)); to_compat_ipc_perm(&v.sem_perm, &in->sem_perm); v.sem_otime = in->sem_otime; v.sem_ctime = in->sem_ctime; v.sem_nsems = in->sem_nsems; return copy_to_user(buf, &v, sizeof(v)); } } static long compat_ksys_semctl(int semid, int semnum, int cmd, int arg, int version) { void __user *p = compat_ptr(arg); struct ipc_namespace *ns; struct semid64_ds semid64; int err; ns = current->nsproxy->ipc_ns; if (semid < 0) return -EINVAL; switch (cmd & (~IPC_64)) { case IPC_INFO: case SEM_INFO: return semctl_info(ns, semid, cmd, p); case IPC_STAT: case SEM_STAT: case SEM_STAT_ANY: err = semctl_stat(ns, semid, cmd, &semid64); if (err < 0) return err; if (copy_compat_semid_to_user(p, &semid64, version)) err = -EFAULT; return err; case GETVAL: case GETPID: case GETNCNT: case GETZCNT: case GETALL: case SETALL: return semctl_main(ns, semid, semnum, cmd, p); case SETVAL: return semctl_setval(ns, semid, semnum, arg); case IPC_SET: if (copy_compat_semid_from_user(&semid64, p, version)) return -EFAULT; fallthrough; case IPC_RMID: return semctl_down(ns, semid, cmd, &semid64); default: return -EINVAL; } } COMPAT_SYSCALL_DEFINE4(semctl, int, semid, int, semnum, int, cmd, int, arg) { return compat_ksys_semctl(semid, semnum, cmd, arg, IPC_64); } #ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION long compat_ksys_old_semctl(int semid, int semnum, int cmd, int arg) { int version = compat_ipc_parse_version(&cmd); return compat_ksys_semctl(semid, semnum, cmd, arg, version); } COMPAT_SYSCALL_DEFINE4(old_semctl, int, semid, int, semnum, int, cmd, int, arg) { return compat_ksys_old_semctl(semid, semnum, cmd, arg); } #endif #endif /* If the task doesn't already have a undo_list, then allocate one * here. We guarantee there is only one thread using this undo list, * and current is THE ONE * * If this allocation and assignment succeeds, but later * portions of this code fail, there is no need to free the sem_undo_list. * Just let it stay associated with the task, and it'll be freed later * at exit time. * * This can block, so callers must hold no locks. */ static inline int get_undo_list(struct sem_undo_list **undo_listp) { struct sem_undo_list *undo_list; undo_list = current->sysvsem.undo_list; if (!undo_list) { undo_list = kzalloc(sizeof(*undo_list), GFP_KERNEL_ACCOUNT); if (undo_list == NULL) return -ENOMEM; spin_lock_init(&undo_list->lock); refcount_set(&undo_list->refcnt, 1); INIT_LIST_HEAD(&undo_list->list_proc); current->sysvsem.undo_list = undo_list; } *undo_listp = undo_list; return 0; } static struct sem_undo *__lookup_undo(struct sem_undo_list *ulp, int semid) { struct sem_undo *un; list_for_each_entry_rcu(un, &ulp->list_proc, list_proc, spin_is_locked(&ulp->lock)) { if (un->semid == semid) return un; } return NULL; } static struct sem_undo *lookup_undo(struct sem_undo_list *ulp, int semid) { struct sem_undo *un; assert_spin_locked(&ulp->lock); un = __lookup_undo(ulp, semid); if (un) { list_del_rcu(&un->list_proc); list_add_rcu(&un->list_proc, &ulp->list_proc); } return un; } /** * find_alloc_undo - lookup (and if not present create) undo array * @ns: namespace * @semid: semaphore array id * * The function looks up (and if not present creates) the undo structure. * The size of the undo structure depends on the size of the semaphore * array, thus the alloc path is not that straightforward. * Lifetime-rules: sem_undo is rcu-protected, on success, the function * performs a rcu_read_lock(). */ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) { struct sem_array *sma; struct sem_undo_list *ulp; struct sem_undo *un, *new; int nsems, error; error = get_undo_list(&ulp); if (error) return ERR_PTR(error); rcu_read_lock(); spin_lock(&ulp->lock); un = lookup_undo(ulp, semid); spin_unlock(&ulp->lock); if (likely(un != NULL)) goto out; /* no undo structure around - allocate one. */ /* step 1: figure out the size of the semaphore array */ sma = sem_obtain_object_check(ns, semid); if (IS_ERR(sma)) { rcu_read_unlock(); return ERR_CAST(sma); } nsems = sma->sem_nsems; if (!ipc_rcu_getref(&sma->sem_perm)) { rcu_read_unlock(); un = ERR_PTR(-EIDRM); goto out; } rcu_read_unlock(); /* step 2: allocate new undo structure */ new = kvzalloc(struct_size(new, semadj, nsems), GFP_KERNEL_ACCOUNT); if (!new) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return ERR_PTR(-ENOMEM); } /* step 3: Acquire the lock on semaphore array */ rcu_read_lock(); sem_lock_and_putref(sma); if (!ipc_valid_object(&sma->sem_perm)) { sem_unlock(sma, -1); rcu_read_unlock(); kvfree(new); un = ERR_PTR(-EIDRM); goto out; } spin_lock(&ulp->lock); /* * step 4: check for races: did someone else allocate the undo struct? */ un = lookup_undo(ulp, semid); if (un) { spin_unlock(&ulp->lock); kvfree(new); goto success; } /* step 5: initialize & link new undo structure */ new->ulp = ulp; new->semid = semid; assert_spin_locked(&ulp->lock); list_add_rcu(&new->list_proc, &ulp->list_proc); ipc_assert_locked_object(&sma->sem_perm); list_add(&new->list_id, &sma->list_id); un = new; spin_unlock(&ulp->lock); success: sem_unlock(sma, -1); out: return un; } long __do_semtimedop(int semid, struct sembuf *sops, unsigned nsops, const struct timespec64 *timeout, struct ipc_namespace *ns) { int error = -EINVAL; struct sem_array *sma; struct sembuf *sop; struct sem_undo *un; int max, locknum; bool undos = false, alter = false, dupsop = false; struct sem_queue queue; unsigned long dup = 0; ktime_t expires, *exp = NULL; bool timed_out = false; if (nsops < 1 || semid < 0) return -EINVAL; if (nsops > ns->sc_semopm) return -E2BIG; if (timeout) { if (!timespec64_valid(timeout)) return -EINVAL; expires = ktime_add_safe(ktime_get(), timespec64_to_ktime(*timeout)); exp = &expires; } max = 0; for (sop = sops; sop < sops + nsops; sop++) { unsigned long mask = 1ULL << ((sop->sem_num) % BITS_PER_LONG); if (sop->sem_num >= max) max = sop->sem_num; if (sop->sem_flg & SEM_UNDO) undos = true; if (dup & mask) { /* * There was a previous alter access that appears * to have accessed the same semaphore, thus use * the dupsop logic. "appears", because the detection * can only check % BITS_PER_LONG. */ dupsop = true; } if (sop->sem_op != 0) { alter = true; dup |= mask; } } if (undos) { /* On success, find_alloc_undo takes the rcu_read_lock */ un = find_alloc_undo(ns, semid); if (IS_ERR(un)) { error = PTR_ERR(un); goto out; } } else { un = NULL; rcu_read_lock(); } sma = sem_obtain_object_check(ns, semid); if (IS_ERR(sma)) { rcu_read_unlock(); error = PTR_ERR(sma); goto out; } error = -EFBIG; if (max >= sma->sem_nsems) { rcu_read_unlock(); goto out; } error = -EACCES; if (ipcperms(ns, &sma->sem_perm, alter ? S_IWUGO : S_IRUGO)) { rcu_read_unlock(); goto out; } error = security_sem_semop(&sma->sem_perm, sops, nsops, alter); if (error) { rcu_read_unlock(); goto out; } error = -EIDRM; locknum = sem_lock(sma, sops, nsops); /* * We eventually might perform the following check in a lockless * fashion, considering ipc_valid_object() locking constraints. * If nsops == 1 and there is no contention for sem_perm.lock, then * only a per-semaphore lock is held and it's OK to proceed with the * check below. More details on the fine grained locking scheme * entangled here and why it's RMID race safe on comments at sem_lock() */ if (!ipc_valid_object(&sma->sem_perm)) goto out_unlock; /* * semid identifiers are not unique - find_alloc_undo may have * allocated an undo structure, it was invalidated by an RMID * and now a new array with received the same id. Check and fail. * This case can be detected checking un->semid. The existence of * "un" itself is guaranteed by rcu. */ if (un && un->semid == -1) goto out_unlock; queue.sops = sops; queue.nsops = nsops; queue.undo = un; queue.pid = task_tgid(current); queue.alter = alter; queue.dupsop = dupsop; error = perform_atomic_semop(sma, &queue); if (error == 0) { /* non-blocking successful path */ DEFINE_WAKE_Q(wake_q); /* * If the operation was successful, then do * the required updates. */ if (alter) do_smart_update(sma, sops, nsops, 1, &wake_q); else set_semotime(sma, sops); sem_unlock(sma, locknum); rcu_read_unlock(); wake_up_q(&wake_q); goto out; } if (error < 0) /* non-blocking error path */ goto out_unlock; /* * We need to sleep on this operation, so we put the current * task into the pending queue and go to sleep. */ if (nsops == 1) { struct sem *curr; int idx = array_index_nospec(sops->sem_num, sma->sem_nsems); curr = &sma->sems[idx]; if (alter) { if (sma->complex_count) { list_add_tail(&queue.list, &sma->pending_alter); } else { list_add_tail(&queue.list, &curr->pending_alter); } } else { list_add_tail(&queue.list, &curr->pending_const); } } else { if (!sma->complex_count) merge_queues(sma); if (alter) list_add_tail(&queue.list, &sma->pending_alter); else list_add_tail(&queue.list, &sma->pending_const); sma->complex_count++; } do { /* memory ordering ensured by the lock in sem_lock() */ WRITE_ONCE(queue.status, -EINTR); queue.sleeper = current; /* memory ordering is ensured by the lock in sem_lock() */ __set_current_state(TASK_INTERRUPTIBLE); sem_unlock(sma, locknum); rcu_read_unlock(); timed_out = !schedule_hrtimeout_range(exp, current->timer_slack_ns, HRTIMER_MODE_ABS); /* * fastpath: the semop has completed, either successfully or * not, from the syscall pov, is quite irrelevant to us at this * point; we're done. * * We _do_ care, nonetheless, about being awoken by a signal or * spuriously. The queue.status is checked again in the * slowpath (aka after taking sem_lock), such that we can detect * scenarios where we were awakened externally, during the * window between wake_q_add() and wake_up_q(). */ rcu_read_lock(); error = READ_ONCE(queue.status); if (error != -EINTR) { /* see SEM_BARRIER_2 for purpose/pairing */ smp_acquire__after_ctrl_dep(); rcu_read_unlock(); goto out; } locknum = sem_lock(sma, sops, nsops); if (!ipc_valid_object(&sma->sem_perm)) goto out_unlock; /* * No necessity for any barrier: We are protect by sem_lock() */ error = READ_ONCE(queue.status); /* * If queue.status != -EINTR we are woken up by another process. * Leave without unlink_queue(), but with sem_unlock(). */ if (error != -EINTR) goto out_unlock; /* * If an interrupt occurred we have to clean up the queue. */ if (timed_out) error = -EAGAIN; } while (error == -EINTR && !signal_pending(current)); /* spurious */ unlink_queue(sma, &queue); out_unlock: sem_unlock(sma, locknum); rcu_read_unlock(); out: return error; } static long do_semtimedop(int semid, struct sembuf __user *tsops, unsigned nsops, const struct timespec64 *timeout) { struct sembuf fast_sops[SEMOPM_FAST]; struct sembuf *sops = fast_sops; struct ipc_namespace *ns; int ret; ns = current->nsproxy->ipc_ns; if (nsops > ns->sc_semopm) return -E2BIG; if (nsops < 1) return -EINVAL; if (nsops > SEMOPM_FAST) { sops = kvmalloc_array(nsops, sizeof(*sops), GFP_KERNEL); if (sops == NULL) return -ENOMEM; } if (copy_from_user(sops, tsops, nsops * sizeof(*tsops))) { ret = -EFAULT; goto out_free; } ret = __do_semtimedop(semid, sops, nsops, timeout, ns); out_free: if (sops != fast_sops) kvfree(sops); return ret; } long ksys_semtimedop(int semid, struct sembuf __user *tsops, unsigned int nsops, const struct __kernel_timespec __user *timeout) { if (timeout) { struct timespec64 ts; if (get_timespec64(&ts, timeout)) return -EFAULT; return do_semtimedop(semid, tsops, nsops, &ts); } return do_semtimedop(semid, tsops, nsops, NULL); } SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, unsigned int, nsops, const struct __kernel_timespec __user *, timeout) { return ksys_semtimedop(semid, tsops, nsops, timeout); } #ifdef CONFIG_COMPAT_32BIT_TIME long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems, unsigned int nsops, const struct old_timespec32 __user *timeout) { if (timeout) { struct timespec64 ts; if (get_old_timespec32(&ts, timeout)) return -EFAULT; return do_semtimedop(semid, tsems, nsops, &ts); } return do_semtimedop(semid, tsems, nsops, NULL); } SYSCALL_DEFINE4(semtimedop_time32, int, semid, struct sembuf __user *, tsems, unsigned int, nsops, const struct old_timespec32 __user *, timeout) { return compat_ksys_semtimedop(semid, tsems, nsops, timeout); } #endif SYSCALL_DEFINE3(semop, int, semid, struct sembuf __user *, tsops, unsigned, nsops) { return do_semtimedop(semid, tsops, nsops, NULL); } /* If CLONE_SYSVSEM is set, establish sharing of SEM_UNDO state between * parent and child tasks. */ int copy_semundo(unsigned long clone_flags, struct task_struct *tsk) { struct sem_undo_list *undo_list; int error; if (clone_flags & CLONE_SYSVSEM) { error = get_undo_list(&undo_list); if (error) return error; refcount_inc(&undo_list->refcnt); tsk->sysvsem.undo_list = undo_list; } else tsk->sysvsem.undo_list = NULL; return 0; } /* * add semadj values to semaphores, free undo structures. * undo structures are not freed when semaphore arrays are destroyed * so some of them may be out of date. * IMPLEMENTATION NOTE: There is some confusion over whether the * set of adjustments that needs to be done should be done in an atomic * manner or not. That is, if we are attempting to decrement the semval * should we queue up and wait until we can do so legally? * The original implementation attempted to do this (queue and wait). * The current implementation does not do so. The POSIX standard * and SVID should be consulted to determine what behavior is mandated. */ void exit_sem(struct task_struct *tsk) { struct sem_undo_list *ulp; ulp = tsk->sysvsem.undo_list; if (!ulp) return; tsk->sysvsem.undo_list = NULL; if (!refcount_dec_and_test(&ulp->refcnt)) return; for (;;) { struct sem_array *sma; struct sem_undo *un; int semid, i; DEFINE_WAKE_Q(wake_q); cond_resched(); rcu_read_lock(); un = list_entry_rcu(ulp->list_proc.next, struct sem_undo, list_proc); if (&un->list_proc == &ulp->list_proc) { /* * We must wait for freeary() before freeing this ulp, * in case we raced with last sem_undo. There is a small * possibility where we exit while freeary() didn't * finish unlocking sem_undo_list. */ spin_lock(&ulp->lock); spin_unlock(&ulp->lock); rcu_read_unlock(); break; } spin_lock(&ulp->lock); semid = un->semid; spin_unlock(&ulp->lock); /* exit_sem raced with IPC_RMID, nothing to do */ if (semid == -1) { rcu_read_unlock(); continue; } sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, semid); /* exit_sem raced with IPC_RMID, nothing to do */ if (IS_ERR(sma)) { rcu_read_unlock(); continue; } sem_lock(sma, NULL, -1); /* exit_sem raced with IPC_RMID, nothing to do */ if (!ipc_valid_object(&sma->sem_perm)) { sem_unlock(sma, -1); rcu_read_unlock(); continue; } un = __lookup_undo(ulp, semid); if (un == NULL) { /* exit_sem raced with IPC_RMID+semget() that created * exactly the same semid. Nothing to do. */ sem_unlock(sma, -1); rcu_read_unlock(); continue; } /* remove un from the linked lists */ ipc_assert_locked_object(&sma->sem_perm); list_del(&un->list_id); spin_lock(&ulp->lock); list_del_rcu(&un->list_proc); spin_unlock(&ulp->lock); /* perform adjustments registered in un */ for (i = 0; i < sma->sem_nsems; i++) { struct sem *semaphore = &sma->sems[i]; if (un->semadj[i]) { semaphore->semval += un->semadj[i]; /* * Range checks of the new semaphore value, * not defined by sus: * - Some unices ignore the undo entirely * (e.g. HP UX 11i 11.22, Tru64 V5.1) * - some cap the value (e.g. FreeBSD caps * at 0, but doesn't enforce SEMVMX) * * Linux caps the semaphore value, both at 0 * and at SEMVMX. * * Manfred <manfred@colorfullife.com> */ if (semaphore->semval < 0) semaphore->semval = 0; if (semaphore->semval > SEMVMX) semaphore->semval = SEMVMX; ipc_update_pid(&semaphore->sempid, task_tgid(current)); } } /* maybe some queued-up processes were waiting for this */ do_smart_update(sma, NULL, 0, 1, &wake_q); sem_unlock(sma, -1); rcu_read_unlock(); wake_up_q(&wake_q); kvfree_rcu(un, rcu); } kfree(ulp); } #ifdef CONFIG_PROC_FS static int sysvipc_sem_proc_show(struct seq_file *s, void *it) { struct user_namespace *user_ns = seq_user_ns(s); struct kern_ipc_perm *ipcp = it; struct sem_array *sma = container_of(ipcp, struct sem_array, sem_perm); time64_t sem_otime; /* * The proc interface isn't aware of sem_lock(), it calls * ipc_lock_object(), i.e. spin_lock(&sma->sem_perm.lock). * (in sysvipc_find_ipc) * In order to stay compatible with sem_lock(), we must * enter / leave complex_mode. */ complexmode_enter(sma); sem_otime = get_semotime(sma); seq_printf(s, "%10d %10d %4o %10u %5u %5u %5u %5u %10llu %10llu\n", sma->sem_perm.key, sma->sem_perm.id, sma->sem_perm.mode, sma->sem_nsems, from_kuid_munged(user_ns, sma->sem_perm.uid), from_kgid_munged(user_ns, sma->sem_perm.gid), from_kuid_munged(user_ns, sma->sem_perm.cuid), from_kgid_munged(user_ns, sma->sem_perm.cgid), sem_otime, sma->sem_ctime); complexmode_tryleave(sma); return 0; } #endif |
| 1 1 1 1 1 1 1 1 1 7 7 7 8 8 7 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 | /* * llc_sap.c - driver routines for SAP component. * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 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 <net/llc.h> #include <net/llc_if.h> #include <net/llc_conn.h> #include <net/llc_pdu.h> #include <net/llc_sap.h> #include <net/llc_s_ac.h> #include <net/llc_s_ev.h> #include <net/llc_s_st.h> #include <net/sock.h> #include <net/tcp_states.h> #include <linux/llc.h> #include <linux/slab.h> static int llc_mac_header_len(unsigned short devtype) { switch (devtype) { case ARPHRD_ETHER: case ARPHRD_LOOPBACK: return sizeof(struct ethhdr); } return 0; } /** * llc_alloc_frame - allocates sk_buff for frame * @sk: socket to allocate frame to * @dev: network device this skb will be sent over * @type: pdu type to allocate * @data_size: data size to allocate * * Allocates an sk_buff for frame and initializes sk_buff fields. * Returns allocated skb or %NULL when out of memory. */ struct sk_buff *llc_alloc_frame(struct sock *sk, struct net_device *dev, u8 type, u32 data_size) { int hlen = type == LLC_PDU_TYPE_U ? 3 : 4; struct sk_buff *skb; hlen += llc_mac_header_len(dev->type); skb = alloc_skb(hlen + data_size, GFP_ATOMIC); if (skb) { skb_reset_mac_header(skb); skb_reserve(skb, hlen); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->protocol = htons(ETH_P_802_2); skb->dev = dev; if (sk != NULL) skb_set_owner_w(skb, sk); } return skb; } void llc_save_primitive(struct sock *sk, struct sk_buff *skb, u8 prim) { struct sockaddr_llc *addr; /* save primitive for use by the user. */ addr = llc_ui_skb_cb(skb); memset(addr, 0, sizeof(*addr)); addr->sllc_family = sk->sk_family; addr->sllc_arphrd = skb->dev->type; addr->sllc_test = prim == LLC_TEST_PRIM; addr->sllc_xid = prim == LLC_XID_PRIM; addr->sllc_ua = prim == LLC_DATAUNIT_PRIM; llc_pdu_decode_sa(skb, addr->sllc_mac); llc_pdu_decode_ssap(skb, &addr->sllc_sap); } /** * llc_sap_rtn_pdu - Informs upper layer on rx of an UI, XID or TEST pdu. * @sap: pointer to SAP * @skb: received pdu */ void llc_sap_rtn_pdu(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); switch (LLC_U_PDU_RSP(pdu)) { case LLC_1_PDU_CMD_TEST: ev->prim = LLC_TEST_PRIM; break; case LLC_1_PDU_CMD_XID: ev->prim = LLC_XID_PRIM; break; case LLC_1_PDU_CMD_UI: ev->prim = LLC_DATAUNIT_PRIM; break; } ev->ind_cfm_flag = LLC_IND; } /** * llc_find_sap_trans - finds transition for event * @sap: pointer to SAP * @skb: happened event * * This function finds transition that matches with happened event. * Returns the pointer to found transition on success or %NULL for * failure. */ static const struct llc_sap_state_trans *llc_find_sap_trans(struct llc_sap *sap, struct sk_buff *skb) { int i = 0; const struct llc_sap_state_trans *rc = NULL; const struct llc_sap_state_trans **next_trans; struct llc_sap_state *curr_state = &llc_sap_state_table[sap->state - 1]; /* * Search thru events for this state until list exhausted or until * its obvious the event is not valid for the current state */ for (next_trans = curr_state->transitions; next_trans[i]->ev; i++) if (!next_trans[i]->ev(sap, skb)) { rc = next_trans[i]; /* got event match; return it */ break; } return rc; } /** * llc_exec_sap_trans_actions - execute actions related to event * @sap: pointer to SAP * @trans: pointer to transition that it's actions must be performed * @skb: happened event. * * This function executes actions that is related to happened event. * Returns 0 for success and 1 for failure of at least one action. */ static int llc_exec_sap_trans_actions(struct llc_sap *sap, const struct llc_sap_state_trans *trans, struct sk_buff *skb) { int rc = 0; const llc_sap_action_t *next_action = trans->ev_actions; for (; next_action && *next_action; next_action++) if ((*next_action)(sap, skb)) rc = 1; return rc; } /** * llc_sap_next_state - finds transition, execs actions & change SAP state * @sap: pointer to SAP * @skb: happened event * * This function finds transition that matches with happened event, then * executes related actions and finally changes state of SAP. It returns * 0 on success and 1 for failure. */ static int llc_sap_next_state(struct llc_sap *sap, struct sk_buff *skb) { const struct llc_sap_state_trans *trans; int rc = 1; if (sap->state > LLC_NR_SAP_STATES) goto out; trans = llc_find_sap_trans(sap, skb); if (!trans) goto out; /* * Got the state to which we next transition; perform the actions * associated with this transition before actually transitioning to the * next state */ rc = llc_exec_sap_trans_actions(sap, trans, skb); if (rc) goto out; /* * Transition SAP to next state if all actions execute successfully */ sap->state = trans->next_state; out: return rc; } /** * llc_sap_state_process - sends event to SAP state machine * @sap: sap to use * @skb: pointer to occurred event * * After executing actions of the event, upper layer will be indicated * if needed(on receiving an UI frame). sk can be null for the * datalink_proto case. * * This function always consumes a reference to the skb. */ static void llc_sap_state_process(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); ev->ind_cfm_flag = 0; llc_sap_next_state(sap, skb); if (ev->ind_cfm_flag == LLC_IND && skb->sk->sk_state != TCP_LISTEN) { llc_save_primitive(skb->sk, skb, ev->prim); /* queue skb to the user. */ if (sock_queue_rcv_skb(skb->sk, skb) == 0) return; } kfree_skb(skb); } /** * llc_build_and_send_test_pkt - TEST interface for upper layers. * @sap: sap to use * @skb: packet to send * @dmac: destination mac address * @dsap: destination sap * * This function is called when upper layer wants to send a TEST pdu. * Returns 0 for success, 1 otherwise. */ void llc_build_and_send_test_pkt(struct llc_sap *sap, struct sk_buff *skb, u8 *dmac, u8 dsap) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); ev->saddr.lsap = sap->laddr.lsap; ev->daddr.lsap = dsap; memcpy(ev->saddr.mac, skb->dev->dev_addr, IFHWADDRLEN); memcpy(ev->daddr.mac, dmac, IFHWADDRLEN); ev->type = LLC_SAP_EV_TYPE_PRIM; ev->prim = LLC_TEST_PRIM; ev->prim_type = LLC_PRIM_TYPE_REQ; llc_sap_state_process(sap, skb); } /** * llc_build_and_send_xid_pkt - XID interface for upper layers * @sap: sap to use * @skb: packet to send * @dmac: destination mac address * @dsap: destination sap * * This function is called when upper layer wants to send a XID pdu. * Returns 0 for success, 1 otherwise. */ void llc_build_and_send_xid_pkt(struct llc_sap *sap, struct sk_buff *skb, u8 *dmac, u8 dsap) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); ev->saddr.lsap = sap->laddr.lsap; ev->daddr.lsap = dsap; memcpy(ev->saddr.mac, skb->dev->dev_addr, IFHWADDRLEN); memcpy(ev->daddr.mac, dmac, IFHWADDRLEN); ev->type = LLC_SAP_EV_TYPE_PRIM; ev->prim = LLC_XID_PRIM; ev->prim_type = LLC_PRIM_TYPE_REQ; llc_sap_state_process(sap, skb); } /** * llc_sap_rcv - sends received pdus to the sap state machine * @sap: current sap component structure. * @skb: received frame. * @sk: socket to associate to frame * * Sends received pdus to the sap state machine. */ static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb, struct sock *sk) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); ev->type = LLC_SAP_EV_TYPE_PDU; ev->reason = 0; skb_orphan(skb); sock_hold(sk); skb->sk = sk; skb->destructor = sock_efree; llc_sap_state_process(sap, skb); } static inline bool llc_dgram_match(const struct llc_sap *sap, const struct llc_addr *laddr, const struct sock *sk, const struct net *net) { struct llc_sock *llc = llc_sk(sk); return sk->sk_type == SOCK_DGRAM && net_eq(sock_net(sk), net) && llc->laddr.lsap == laddr->lsap && ether_addr_equal(llc->laddr.mac, laddr->mac); } /** * llc_lookup_dgram - Finds dgram socket for the local sap/mac * @sap: SAP * @laddr: address of local LLC (MAC + SAP) * @net: netns to look up a socket in * * Search socket list of the SAP and finds connection using the local * mac, and local sap. Returns pointer for socket found, %NULL otherwise. */ static struct sock *llc_lookup_dgram(struct llc_sap *sap, const struct llc_addr *laddr, const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; int slot = llc_sk_laddr_hashfn(sap, laddr); struct hlist_nulls_head *laddr_hb = &sap->sk_laddr_hash[slot]; rcu_read_lock_bh(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { if (llc_dgram_match(sap, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || !llc_dgram_match(sap, laddr, rc, net))) { sock_put(rc); continue; } goto found; } } rc = NULL; /* * 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 (unlikely(get_nulls_value(node) != slot)) goto again; found: rcu_read_unlock_bh(); return rc; } static inline bool llc_mcast_match(const struct llc_sap *sap, const struct llc_addr *laddr, const struct sk_buff *skb, const struct sock *sk) { struct llc_sock *llc = llc_sk(sk); return sk->sk_type == SOCK_DGRAM && llc->laddr.lsap == laddr->lsap && llc->dev == skb->dev; } static void llc_do_mcast(struct llc_sap *sap, struct sk_buff *skb, struct sock **stack, int count) { struct sk_buff *skb1; int i; for (i = 0; i < count; i++) { skb1 = skb_clone(skb, GFP_ATOMIC); if (!skb1) { sock_put(stack[i]); continue; } llc_sap_rcv(sap, skb1, stack[i]); sock_put(stack[i]); } } /** * llc_sap_mcast - Deliver multicast PDU's to all matching datagram sockets. * @sap: SAP * @laddr: address of local LLC (MAC + SAP) * @skb: PDU to deliver * * Search socket list of the SAP and finds connections with same sap. * Deliver clone to each. */ static void llc_sap_mcast(struct llc_sap *sap, const struct llc_addr *laddr, struct sk_buff *skb) { int i = 0; struct sock *sk; struct sock *stack[256 / sizeof(struct sock *)]; struct llc_sock *llc; struct hlist_head *dev_hb = llc_sk_dev_hash(sap, skb->dev->ifindex); spin_lock_bh(&sap->sk_lock); hlist_for_each_entry(llc, dev_hb, dev_hash_node) { sk = &llc->sk; if (!llc_mcast_match(sap, laddr, skb, sk)) continue; sock_hold(sk); if (i < ARRAY_SIZE(stack)) stack[i++] = sk; else { llc_do_mcast(sap, skb, stack, i); i = 0; } } spin_unlock_bh(&sap->sk_lock); llc_do_mcast(sap, skb, stack, i); } void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb) { struct llc_addr laddr; llc_pdu_decode_da(skb, laddr.mac); llc_pdu_decode_dsap(skb, &laddr.lsap); if (is_multicast_ether_addr(laddr.mac)) { llc_sap_mcast(sap, &laddr, skb); kfree_skb(skb); } else { struct sock *sk = llc_lookup_dgram(sap, &laddr, dev_net(skb->dev)); if (sk) { llc_sap_rcv(sap, skb, sk); sock_put(sk); } else kfree_skb(skb); } } |
| 26 45 21 13 18 18 63 24 56 62 63 63 64 22 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */ #ifndef _LINUX_SKMSG_H #define _LINUX_SKMSG_H #include <linux/bpf.h> #include <linux/filter.h> #include <linux/scatterlist.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/tcp.h> #include <net/strparser.h> #define MAX_MSG_FRAGS MAX_SKB_FRAGS #define NR_MSG_FRAG_IDS (MAX_MSG_FRAGS + 1) enum __sk_action { __SK_DROP = 0, __SK_PASS, __SK_REDIRECT, __SK_NONE, }; struct sk_msg_sg { u32 start; u32 curr; u32 end; u32 size; u32 copybreak; DECLARE_BITMAP(copy, MAX_MSG_FRAGS + 2); /* The extra two elements: * 1) used for chaining the front and sections when the list becomes * partitioned (e.g. end < start). The crypto APIs require the * chaining; * 2) to chain tailer SG entries after the message. */ struct scatterlist data[MAX_MSG_FRAGS + 2]; }; /* UAPI in filter.c depends on struct sk_msg_sg being first element. */ struct sk_msg { struct sk_msg_sg sg; void *data; void *data_end; u32 apply_bytes; u32 cork_bytes; u32 flags; struct sk_buff *skb; struct sock *sk_redir; struct sock *sk; struct list_head list; }; struct sk_psock_progs { struct bpf_prog *msg_parser; struct bpf_prog *stream_parser; struct bpf_prog *stream_verdict; struct bpf_prog *skb_verdict; struct bpf_link *msg_parser_link; struct bpf_link *stream_parser_link; struct bpf_link *stream_verdict_link; struct bpf_link *skb_verdict_link; }; enum sk_psock_state_bits { SK_PSOCK_TX_ENABLED, SK_PSOCK_RX_STRP_ENABLED, }; struct sk_psock_link { struct list_head list; struct bpf_map *map; void *link_raw; }; struct sk_psock_work_state { u32 len; u32 off; }; struct sk_psock { struct sock *sk; struct sock *sk_redir; u32 apply_bytes; u32 cork_bytes; u32 eval; bool redir_ingress; /* undefined if sk_redir is null */ struct sk_msg *cork; struct sk_psock_progs progs; #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) struct strparser strp; u32 copied_seq; u32 ingress_bytes; #endif struct sk_buff_head ingress_skb; struct list_head ingress_msg; spinlock_t ingress_lock; unsigned long state; struct list_head link; spinlock_t link_lock; refcount_t refcnt; void (*saved_unhash)(struct sock *sk); void (*saved_destroy)(struct sock *sk); void (*saved_close)(struct sock *sk, long timeout); void (*saved_write_space)(struct sock *sk); void (*saved_data_ready)(struct sock *sk); /* psock_update_sk_prot may be called with restore=false many times * so the handler must be safe for this case. It will be called * exactly once with restore=true when the psock is being destroyed * and psock refcnt is zero, but before an RCU grace period. */ int (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock, bool restore); struct proto *sk_proto; struct mutex work_mutex; struct sk_psock_work_state work_state; struct delayed_work work; struct sock *sk_pair; struct rcu_work rwork; }; int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len, int elem_first_coalesce); int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src, u32 off, u32 len); void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len); int sk_msg_free(struct sock *sk, struct sk_msg *msg); int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg); void sk_msg_free_partial(struct sock *sk, struct sk_msg *msg, u32 bytes); void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg, u32 bytes); void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes); void sk_msg_return_zero(struct sock *sk, struct sk_msg *msg, int bytes); int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); bool sk_msg_is_readable(struct sock *sk); static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes) { WARN_ON(i == msg->sg.end && bytes); } static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes) { if (psock->apply_bytes) { if (psock->apply_bytes < bytes) psock->apply_bytes = 0; else psock->apply_bytes -= bytes; } } static inline u32 sk_msg_iter_dist(u32 start, u32 end) { return end >= start ? end - start : end + (NR_MSG_FRAG_IDS - start); } #define sk_msg_iter_var_prev(var) \ do { \ if (var == 0) \ var = NR_MSG_FRAG_IDS - 1; \ else \ var--; \ } while (0) #define sk_msg_iter_var_next(var) \ do { \ var++; \ if (var == NR_MSG_FRAG_IDS) \ var = 0; \ } while (0) #define sk_msg_iter_prev(msg, which) \ sk_msg_iter_var_prev(msg->sg.which) #define sk_msg_iter_next(msg, which) \ sk_msg_iter_var_next(msg->sg.which) static inline void sk_msg_init(struct sk_msg *msg) { BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != NR_MSG_FRAG_IDS); memset(msg, 0, sizeof(*msg)); sg_init_marker(msg->sg.data, NR_MSG_FRAG_IDS); } static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, int which, u32 size) { dst->sg.data[which] = src->sg.data[which]; dst->sg.data[which].length = size; dst->sg.size += size; src->sg.size -= size; src->sg.data[which].length -= size; src->sg.data[which].offset += size; } static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src) { memcpy(dst, src, sizeof(*src)); sk_msg_init(src); } static inline bool sk_msg_full(const struct sk_msg *msg) { return sk_msg_iter_dist(msg->sg.start, msg->sg.end) == MAX_MSG_FRAGS; } static inline u32 sk_msg_elem_used(const struct sk_msg *msg) { return sk_msg_iter_dist(msg->sg.start, msg->sg.end); } static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which) { return &msg->sg.data[which]; } static inline struct scatterlist sk_msg_elem_cpy(struct sk_msg *msg, int which) { return msg->sg.data[which]; } static inline struct page *sk_msg_page(struct sk_msg *msg, int which) { return sg_page(sk_msg_elem(msg, which)); } static inline bool sk_msg_to_ingress(const struct sk_msg *msg) { return msg->flags & BPF_F_INGRESS; } static inline void sk_msg_compute_data_pointers(struct sk_msg *msg) { struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start); if (test_bit(msg->sg.start, msg->sg.copy)) { msg->data = NULL; msg->data_end = NULL; } else { msg->data = sg_virt(sge); msg->data_end = msg->data + sge->length; } } static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, u32 len, u32 offset) { struct scatterlist *sge; get_page(page); sge = sk_msg_elem(msg, msg->sg.end); sg_set_page(sge, page, len, offset); sg_unmark_end(sge); __set_bit(msg->sg.end, msg->sg.copy); msg->sg.size += len; sk_msg_iter_next(msg, end); } static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state) { do { if (copy_state) __set_bit(i, msg->sg.copy); else __clear_bit(i, msg->sg.copy); sk_msg_iter_var_next(i); if (i == msg->sg.end) break; } while (1); } static inline void sk_msg_sg_copy_set(struct sk_msg *msg, u32 start) { sk_msg_sg_copy(msg, start, true); } static inline void sk_msg_sg_copy_clear(struct sk_msg *msg, u32 start) { sk_msg_sg_copy(msg, start, false); } static inline struct sk_psock *sk_psock(const struct sock *sk) { return __rcu_dereference_sk_user_data_with_flags(sk, SK_USER_DATA_PSOCK); } static inline void sk_psock_set_state(struct sk_psock *psock, enum sk_psock_state_bits bit) { set_bit(bit, &psock->state); } static inline void sk_psock_clear_state(struct sk_psock *psock, enum sk_psock_state_bits bit) { clear_bit(bit, &psock->state); } static inline bool sk_psock_test_state(const struct sk_psock *psock, enum sk_psock_state_bits bit) { return test_bit(bit, &psock->state); } static inline void sock_drop(struct sock *sk, struct sk_buff *skb) { sk_drops_add(sk, skb); kfree_skb(skb); } static inline bool sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { bool ret; spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { list_add_tail(&msg->list, &psock->ingress_msg); ret = true; } else { sk_msg_free(psock->sk, msg); kfree(msg); ret = false; } spin_unlock_bh(&psock->ingress_lock); return ret; } static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock) { struct sk_msg *msg; spin_lock_bh(&psock->ingress_lock); msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list); if (msg) list_del(&msg->list); spin_unlock_bh(&psock->ingress_lock); return msg; } static inline struct sk_msg *sk_psock_peek_msg(struct sk_psock *psock) { struct sk_msg *msg; spin_lock_bh(&psock->ingress_lock); msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list); spin_unlock_bh(&psock->ingress_lock); return msg; } static inline struct sk_msg *sk_psock_next_msg(struct sk_psock *psock, struct sk_msg *msg) { struct sk_msg *ret; spin_lock_bh(&psock->ingress_lock); if (list_is_last(&msg->list, &psock->ingress_msg)) ret = NULL; else ret = list_next_entry(msg, list); spin_unlock_bh(&psock->ingress_lock); return ret; } static inline bool sk_psock_queue_empty(const struct sk_psock *psock) { return psock ? list_empty(&psock->ingress_msg) : true; } static inline void kfree_sk_msg(struct sk_msg *msg) { if (msg->skb) consume_skb(msg->skb); kfree(msg); } static inline void sk_psock_report_error(struct sk_psock *psock, int err) { struct sock *sk = psock->sk; sk->sk_err = err; sk_error_report(sk); } struct sk_psock *sk_psock_init(struct sock *sk, int node); void sk_psock_stop(struct sk_psock *psock); #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock); void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock); void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock); #else static inline int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) { return -EOPNOTSUPP; } static inline void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) { } static inline void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) { } #endif void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock); void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock); int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg); /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). The typecast is * intentional to enforce typesafety. */ #define sk_psock_init_link() \ ((struct sk_psock_link *)kzalloc(sizeof(struct sk_psock_link), \ GFP_ATOMIC | __GFP_NOWARN)) static inline void sk_psock_free_link(struct sk_psock_link *link) { kfree(link); } struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock); static inline void sk_psock_cork_free(struct sk_psock *psock) { if (psock->cork) { sk_msg_free(psock->sk, psock->cork); kfree(psock->cork); psock->cork = NULL; } } static inline void sk_psock_restore_proto(struct sock *sk, struct sk_psock *psock) { if (psock->psock_update_sk_prot) psock->psock_update_sk_prot(sk, psock, true); } static inline struct sk_psock *sk_psock_get(struct sock *sk) { struct sk_psock *psock; rcu_read_lock(); psock = sk_psock(sk); if (psock && !refcount_inc_not_zero(&psock->refcnt)) psock = NULL; rcu_read_unlock(); return psock; } void sk_psock_drop(struct sock *sk, struct sk_psock *psock); static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) { if (refcount_dec_and_test(&psock->refcnt)) sk_psock_drop(sk, psock); } static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock) { read_lock_bh(&sk->sk_callback_lock); if (psock->saved_data_ready) psock->saved_data_ready(sk); else sk->sk_data_ready(sk); read_unlock_bh(&sk->sk_callback_lock); } static inline void psock_set_prog(struct bpf_prog **pprog, struct bpf_prog *prog) { prog = xchg(pprog, prog); if (prog) bpf_prog_put(prog); } static inline int psock_replace_prog(struct bpf_prog **pprog, struct bpf_prog *prog, struct bpf_prog *old) { if (cmpxchg(pprog, old, prog) != old) return -ENOENT; if (old) bpf_prog_put(old); return 0; } static inline void psock_progs_drop(struct sk_psock_progs *progs) { psock_set_prog(&progs->msg_parser, NULL); psock_set_prog(&progs->stream_parser, NULL); psock_set_prog(&progs->stream_verdict, NULL); psock_set_prog(&progs->skb_verdict, NULL); } int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb); static inline bool sk_psock_strp_enabled(struct sk_psock *psock) { if (!psock) return false; return !!psock->saved_data_ready; } #if IS_ENABLED(CONFIG_NET_SOCK_MSG) #define BPF_F_STRPARSER (1UL << 1) /* We only have two bits so far. */ #define BPF_F_PTR_MASK ~(BPF_F_INGRESS | BPF_F_STRPARSER) static inline bool skb_bpf_strparser(const struct sk_buff *skb) { unsigned long sk_redir = skb->_sk_redir; return sk_redir & BPF_F_STRPARSER; } static inline void skb_bpf_set_strparser(struct sk_buff *skb) { skb->_sk_redir |= BPF_F_STRPARSER; } static inline bool skb_bpf_ingress(const struct sk_buff *skb) { unsigned long sk_redir = skb->_sk_redir; return sk_redir & BPF_F_INGRESS; } static inline void skb_bpf_set_ingress(struct sk_buff *skb) { skb->_sk_redir |= BPF_F_INGRESS; } static inline void skb_bpf_set_redir(struct sk_buff *skb, struct sock *sk_redir, bool ingress) { skb->_sk_redir = (unsigned long)sk_redir; if (ingress) skb->_sk_redir |= BPF_F_INGRESS; } static inline struct sock *skb_bpf_redirect_fetch(const struct sk_buff *skb) { unsigned long sk_redir = skb->_sk_redir; return (struct sock *)(sk_redir & BPF_F_PTR_MASK); } static inline void skb_bpf_redirect_clear(struct sk_buff *skb) { skb->_sk_redir = 0; } #endif /* CONFIG_NET_SOCK_MSG */ #endif /* _LINUX_SKMSG_H */ |
| 108 11 3 1 38 10 38 13 5 3 3 5 42 42 42 32 32 1 32 5 5 5 5 5 3 3 3 3 3 18 18 18 5 12 2 9 49 49 7 44 44 16 4 28 32 14 32 32 32 28 5 5 32 11 4 4 5 14 7 24 40 40 32 40 42 16 16 42 42 16 16 16 42 4 4 4 41 1 121 121 121 120 117 3 4 118 4 3 1 118 4 4 118 118 120 112 120 1893 1886 1893 539 1777 1889 1779 10 1 1 1 5 7 6 3 2 245 112 112 42 42 63 63 38 244 244 244 1 244 245 245 244 244 244 245 244 245 1 242 243 242 241 243 243 242 243 240 243 9 111 128 5 169 2 1 1 42 42 113 93 20 27 62 42 52 53 53 6 26 53 2 282 1529 1532 226 5 1287 1286 1287 1286 1 |